{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "d1KVLcqHWdgI" }, "source": [ "# Downloading and Evaluating Open Images\n", "\n", "Downloading Google's [Open Images dataset](https://storage.googleapis.com/openimages/web/download.html) is now easier than ever with the [FiftyOne Dataset Zoo](https://voxel51.com/docs/fiftyone/user_guide/dataset_zoo/index.html#dataset-zoo-open-images-v7)! You can load all three splits of Open Images V7, including image-level labels, detections, segmentations, visual relationships, and point labels.\n", "\n", "FiftyOne also natively supports [Open Images-style evaluation](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html#open-images-style-evaluation), so you can easily evaluate your object detection models and explore the results directly in the library.\n", "\n", "This walkthrough covers:\n", "\n", "- Downloading [Open Images](https://storage.googleapis.com/openimages/web/index.html) from the [FiftyOne Dataset Zoo](https://voxel51.com/docs/fiftyone/user_guide/dataset_zoo/index.html)\n", "- Computing predictions using a model from the [FiftyOne Model Zoo](https://voxel51.com/docs/fiftyone/user_guide/model_zoo/index.html)\n", "- Performing [Open Images-style evaluation](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html#open-images-style-evaluation) in FiftyOne to evaluate a model and compute its mAP\n", "- Exploring the dataset and [evaluation results](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html)\n", "- [Visualizing embeddings](https://voxel51.com/docs/fiftyone/user_guide/brain.html#visualizing-embeddings) through [interactive plots](https://voxel51.com/docs/fiftyone/user_guide/plots.html)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**So, what's the takeaway?**\n", "\n", "Starting a new ML project takes data and time, and the datasets in the [FiftyOne Dataset Zoo](https://voxel51.com/docs/fiftyone/user_guide/dataset_zoo/index.html) can help jump start the development process.\n", "\n", "Open Images in particular is one of the largest publicly available datasets for object detections, classification, segmentation, and more. Additionally, with [Open Images evaluation](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html#open-images-style-evaluation) available natively in FiftyOne, you can quickly evaluate your models and compute mAP and PR curves.\n", "\n", "While metrics like mAP are often used to compare models, the best way to improve your model's performance isn't to look at aggregate metrics but instead to get hands-on with your evaluation and visualize how your model performs on individual samples. All of this is made easy with FiftyOne!" ] }, { "cell_type": "markdown", "metadata": { "id": "R5SJCYnQXnOL" }, "source": [ "## Setup" ] }, { "cell_type": "markdown", "metadata": { "id": "Swt8yYgIbOkv" }, "source": [ "If you haven't already, install FiftyOne:" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "627MxtHOUjU6", "outputId": "0c87eadb-60e4-452d-fa13-a5b8d06b218f" }, "outputs": [], "source": [ "!pip install fiftyone" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In this tutorial, we’ll use some [TensorFlow models](https://github.com/tensorflow/models) and [PyTorch](https://pytorch.org/vision/stable/index.html) to generate predictions and embeddings, and we’ll use the [UMAP method](https://github.com/lmcinnes/umap) to reduce the dimensionality of embeddings, so we need to install the corresponding packages:" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "!pip install tensorflow torch torchvision umap-learn" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This tutorial also includes some of FiftyOne's [interactive plotting capabilities](https://voxel51.com/docs/fiftyone/user_guide/plots.html).\n", "\n", "The recommended way to work with FiftyOne’s interactive plots is in [Jupyter notebooks](https://jupyter.org/) or [JupyterLab](https://jupyterlab.readthedocs.io/en/stable/). In these environments, you can leverage the full power of plots by [attaching them to the FiftyOne App](https://voxel51.com/docs/fiftyone/user_guide/plots.html#attaching-plots) and bidirectionally interacting with the plots and the App to identify interesting subsets of your data.\n", "\n", "To use interactive plots in Jupyter notebooks, ensure that you have the `ipywidgets` package installed:" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "!pip install 'ipywidgets>=8,<9'" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "If you’re working in JupyterLab, refer to [these instructions](https://voxel51.com/docs/fiftyone/user_guide/plots.html#working-in-notebooks) to get setup.\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
\n", "

Support for interactive plots in non-notebook contexts and Google Colab is coming soon! In the meantime, you can still use FiftyOne's plotting features in those environments, but you must manually call plot.show() to update the state of a plot to match the state of a connected session, and any callbacks that would normally be triggered in response to interacting with a plot will not be triggered.

\n", "
" ] }, { "cell_type": "markdown", "metadata": { "id": "wx-yhHuKrsOK" }, "source": [ "## Loading Open Images\n", "\n", "In this section, we'll load various subsets of Open Images from the [FiftyOne Dataset Zoo](https://voxel51.com/docs/fiftyone/user_guide/dataset_zoo/index.html) and visualize them using FiftyOne.\n", "\n", "Let's start by downloading a small sample of 100 randomly chosen images + annotations:" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "id": "q23aIrZSr6FR" }, "outputs": [], "source": [ "import fiftyone as fo\n", "import fiftyone.zoo as foz" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "id": "Nr1Fq8PPh95d" }, "outputs": [], "source": [ "dataset = foz.load_zoo_dataset(\n", " \"open-images-v7\",\n", " split=\"validation\",\n", " max_samples=100,\n", " seed=51,\n", " shuffle=True,\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "9nVJIHp7Ay6e" }, "source": [ "Now let's launch the [FiftyOne App](https://voxel51.com/docs/fiftyone/user_guide/app.html) so we can explore the [dataset](https://voxel51.com/docs/fiftyone/user_guide/using_datasets.html#datasets) we just downloaded." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 821, "resources": { "https://localhost:5151/polling?sessionId=d41be399-4e98-4781-865a-a7821a9e37b4": { "data": "eyJtZXNzYWdlcyI6IFtdfQ==", "headers": [ [ "access-control-allow-headers", "x-requested-with" ], [ "content-type", "text/html; charset=UTF-8" ] ], "ok": true, "status": 200, "status_text": "" } } }, "id": "D5Xw1YZZtPsW", "outputId": "967d1fe3-0be0-4633-c5f3-7f6892511e34" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Connected to FiftyOne on port 5151 at localhost.\n", "If you are not connecting to a remote session, you may need to start a new session and specify a port\n" ] }, { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session = fo.launch_app(dataset.view())" ] }, { "cell_type": "markdown", "metadata": { "id": "TS7hzPZx2iQf" }, "source": [ "Loading Open Images with FiftyOne also automatically stores relevant [labels](https://voxel51.com/docs/fiftyone/user_guide/using_datasets.html#labels) and [metadata](https://voxel51.com/docs/fiftyone/user_guide/using_datasets.html#metadata) like classes, attributes, and a class hierarchy that is used for evaluation in the dataset's `info` dictionary:" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "L_yrMhwu2xGQ", "outputId": "b8a45faf-d9c1-498a-ea70-7a24b8ed4f66" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "dict_keys(['hierarchy', 'attributes_map', 'attributes', 'segmentation_classes', 'point_classes', 'classes_map'])\n" ] } ], "source": [ "print(dataset.info.keys())" ] }, { "cell_type": "markdown", "metadata": { "id": "ZE9ObTIXA4Ab" }, "source": [ "When loading Open Images from the dataset zoo, there are a [variety of available parameters](https://voxel51.com/docs/fiftyone/api/fiftyone.zoo.datasets.base.html#fiftyone.zoo.datasets.base.OpenImagesV7Dataset) that you can pass to `load_zoo_dataset()` to specify a subset of the images and/or label types to download:\n", "\n", "- `label_types` - a list of label types to load. The supported values are (`\"detections\", \"classifications\", \"points\", \"segmentations\", \"relationships\"`) for Open Images V7. Open Images v6 is the same except that it does not contain point labels. By default, all available labels types will be loaded. Specifying `[]` will load only the images\n", "- `classes` - a list of classes of interest. If specified, only samples with at least one object, segmentation, or image-level label in the specified classes will be downloaded\n", "- `attrs` - a list of attributes of interest. If specified, only download samples if they contain at least one attribute in `attrs` or one class in `classes` (only applicable when `label_types` contains `\"relationships\"`)\n", "- `load_hierarchy` - whether to load the class hierarchy into `dataset.info[\"hierarchy\"]`\n", "- `image_ids` - an array of specific image IDs to download\n", "- `image_ids_file` - a path to a `.txt`, `.csv`, or `.json` file containing image IDs to download\n", "\n", "In addition, [like all other zoo datasets](https://voxel51.com/docs/fiftyone/user_guide/dataset_zoo/datasets.html), you can specify:\n", "\n", "- `max_samples` - the maximum number of samples to load\n", "- `shuffle` - whether to randomly chose which samples to load if `max_samples` is given\n", "- `seed` - a random seed to use when shuffling" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's use some of these parameters to download a 100 sample subset of Open Images containing segmentations and image-level labels for the classes \"Burrito\", \"Cheese\", and \"Popcorn\"." ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "1CkIkqtzt9z4", "outputId": "66b29d52-4e19-43bc-99a8-edfdb18fa839" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Downloading split 'validation' to 'datasets/open-images-v7/validation' if necessary\n", "Only found 83 (<100) samples matching your requirements\n", "Necessary images already downloaded\n", "Existing download of split 'validation' is sufficient\n", "Loading existing dataset 'open-images-food'. To reload from disk, either delete the existing dataset or provide a custom `dataset_name` to use\n" ] } ], "source": [ "dataset = foz.load_zoo_dataset(\n", " \"open-images-v7\", \n", " split=\"validation\", \n", " label_types=[\"segmentations\", \"classifications\"], \n", " classes = [\"Burrito\", \"Cheese\", \"Popcorn\"],\n", " max_samples=100,\n", " seed=51,\n", " shuffle=True,\n", " dataset_name=\"open-images-food\",\n", ")" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 821, "resources": { "https://localhost:5151/polling?sessionId=a3fc3576-1f7f-4b13-9a4b-147674a3012b": { "data": "eyJtZXNzYWdlcyI6IFtdfQ==", "headers": [ [ "access-control-allow-headers", "x-requested-with" ], [ "content-type", "text/html; charset=UTF-8" ] ], "ok": true, "status": 200, "status_text": "" } } }, "id": "aeQd9A6-uDMy", "outputId": "e89bded4-1aa5-4b9c-dee2-325d19105021" }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view = dataset.view()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "id": "T1FA-QpAFa0r" }, "outputs": [], "source": [ "session.freeze() # screenshots App for sharing" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can do the same for visual relationships. For example, we can download only samples that contain a relationship with the \"Wooden\" attribute." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "5PqZEKcCffUe", "outputId": "a6dd7529-dd6a-468b-9d80-649d49c6bf7c" }, "outputs": [], "source": [ "dataset = foz.load_zoo_dataset(\n", " \"open-images-v7\",\n", " split=\"validation\", \n", " label_types=[\"relationships\"], \n", " attrs=[\"Wooden\"],\n", " max_samples=100,\n", " seed=51,\n", " shuffle=True,\n", " dataset_name=\"open-images-relationships\", \n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can visualize relationships in the App by clicking on a sample to open the [App's expanded view](https://voxel51.com/docs/fiftyone/user_guide/app.html#viewing-a-sample). From there, you can hover over objects to see their attributes in a tooltip.\n", "\n", "Alternatively, you can use the settings menu in the lower-right corner of the media player to set `show_attributes` to True to make attributes appear as persistent boxes (as shown below). This can also be achieved programmatically by [configuring the App](https://voxel51.com/docs/fiftyone/user_guide/config.html#configuring-the-app):" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 821, "resources": { "https://localhost:5151/polling?sessionId=416bb834-a5e4-4292-bb73-5ba727a5617f": { "data": "eyJtZXNzYWdlcyI6IFtdfQ==", "headers": [ [ "access-control-allow-headers", "x-requested-with" ], [ "content-type", "text/html; charset=UTF-8" ] ], "ok": true, "status": 200, "status_text": "" } } }, "id": "EcqIvwTYftNO", "outputId": "59520b38-69da-4390-8365-ee35f5c878d7" }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# Launch a new App instance with a customized config\n", "app_config = fo.AppConfig()\n", "app_config.show_attributes = True\n", "\n", "session = fo.launch_app(dataset, config=app_config)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "With Open Images V7, Google added point labels to the dataset, which are represented as `Keypoint` labels in FiftyOne. This means that we can select a dataset with points with ground truth point labels (potentially positive, negative, or mixed) for the classes `Tortoise` and `Sea turtle`:" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "dataset = foz.load_zoo_dataset(\n", " \"open-images-v7\",\n", " split=\"validation\", \n", " label_types=[\"points\"], \n", " classes = [\"Tortoise\", \"Sea turtle\"],\n", " seed=51,\n", " shuffle=True,\n", " dataset_name=\"open-images-point\", \n", ")" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view = dataset.view()" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "session.freeze()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "As we can see by inspecting the samples in the grid, some of the point labels have more votes than others, and there are different `source` values, denoting the various methods used to generated these point labels. For details, see the [Open Images V7 paper](https://arxiv.org/pdf/2210.14142v2.pdf). If we just want point labels that we are relatively sure are positive, we can filter the `Keypoints` for these using `filter_labels()`:" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "from fiftyone import ViewField as F\n", "positive_dataset = dataset.filter_labels(\"points\", F(\"estimated_yes_no\") == \"yes\")" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view = positive_dataset.view()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "As a basis for the rest of this walkthrough, let's download a subset of Open Images containing dog and cat objects on which we can evaluate a model.\n", "\n", "To ensure that we have exactly the same number of labels for each class, let's download two subsets, one for dogs and one for cats, and merge them together." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "dataset = foz.load_zoo_dataset(\n", " \"open-images-v7\", \n", " split=\"validation\", \n", " label_types=[\"detections\", \"classifications\"], \n", " classes=[\"Cat\"],\n", " max_samples=250,\n", " seed=51,\n", " shuffle=True,\n", " dataset_name=\"open-images-cat-dog\",\n", ")\n", "\n", "dog_subset = foz.load_zoo_dataset(\n", " \"open-images-v7\", \n", " split=\"validation\", \n", " label_types=[\"detections\", \"classifications\"], \n", " classes=[\"Dog\"],\n", " max_samples=250,\n", " seed=51,\n", " shuffle=True,\n", " dataset_name=\"dog-subset\",\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now let's merge the samples together into one dataset:" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "# Merge the samples together into the same dataset\n", "dataset.merge_samples(dog_subset)" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.dataset = dataset" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The FiftyOne App provides a [patches view](https://voxel51.com/docs/fiftyone/user_guide/app.html#viewing-object-patches) that can be used to view every object in the dataset as an individual image. Just click the [patches icon](https://voxel51.com/docs/fiftyone/user_guide/app.html#viewing-object-patches) and select the appropriate [detections field](https://voxel51.com/docs/fiftyone/user_guide/using_datasets.html#object-detection):" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.show()" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "session.freeze() # screenshot for sharing" ] }, { "cell_type": "markdown", "metadata": { "id": "fpmRecDZuGNn" }, "source": [ "## Open Images-style evaluation\n", "\n", "FiftyOne natively supports [Open Images detection evaluation](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html#open-images-style-evaluation), so you can easily evaluate your object detection models and explore the results directly in FiftyOne.\n", "\n", "This section produces object detection predictions from a model in the [FiftyOne Model Zoo](https://voxel51.com/docs/fiftyone/user_guide/model_zoo/index.html) and evaluates them with FiftyOne.\n", "\n", "Evaluating in FiftyOne is much more flexible than [other evaluation APIs](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/evaluation_protocols.md), which produce only aggregate performance metrics. For example, FiftyOne evaluation also marks individual ground truth and predicted detections as either true positive, false positive, and false negative, allowing you to explore your model results and easily find failure modes of your model or even [annotation mistakes](https://voxel51.com/docs/fiftyone/user_guide/brain.html#label-mistakes)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Generate predictions" ] }, { "cell_type": "markdown", "metadata": { "id": "tQpG4W1j1Q8J" }, "source": [ "The [FiftyOne Model Zoo](https://voxel51.com/docs/fiftyone/user_guide/model_zoo/index.html) does not (yet!) contain models trained on Open Images, so instead we'll use a model trained on [COCO](https://cocodataset.org/#home) and evaluate only classes that overlap between COCO and Open Images.\n", "\n", "Note that, if you want to instead evaluate your own model predictions, [adding custom model predictions](https://voxel51.com/docs/fiftyone/recipes/adding_detections.html) to a FiftyOne dataset is very easy." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The model we are using requires [TensorFlow Models](https://github.com/tensorflow/models), which we can easily install using [ETA](https://github.com/voxel51/eta), a package bundled with FiftyOne:" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "scrolled": true }, "outputs": [], "source": [ "!eta install models" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now let's load the model and run inference on our dataset using FiftyOne:" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yYrR9cPYuzhN", "outputId": "8b9c8adf-5663-420b-98d7-7ae50cc01315" }, "outputs": [], "source": [ "model = foz.load_zoo_model(\"ssd-mobilenet-v1-coco-tf\")" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "MD4_ZIwn0gT1", "outputId": "a8cbcc78-4a76-4db0-90ad-519c0576de80", "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 100% |█████████████████| 500/500 [48.9m elapsed, 0s remaining, 0.2 samples/s] \n" ] } ], "source": [ "dataset.apply_model(model, label_field=\"predictions\", confidence_thresh=0.5)" ] }, { "cell_type": "markdown", "metadata": { "id": "w5zFFqt31jTB" }, "source": [ "The dataset contains ground truth objects and now model predictions in its `predictions` field. However, we are only interested in the classes \"Cat\" and \"Dog\" for this example, so we will [create a view](https://voxel51.com/docs/fiftyone/user_guide/using_views.html) containing only the labels of interest.\n", "\n", "Since we specified these classes when downloading the dataset, all images are guaranteed to be related to the classes \"Cat\" and \"Dog\", we just need to filter the individual labels.\n", "\n", "In addition, there is a capitalization difference between the class names of Open Images (\"Cat\" and \"Dog\") and COCO (\"cat\" and \"dog\"), so we'll use FiftyOne to [normalize the labels](https://voxel51.com/docs/fiftyone/user_guide/using_views.html#modifying-fields):" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "id": "EJ_emCDA0tk5" }, "outputs": [], "source": [ "from fiftyone import ViewField as F\n", "\n", "oi_classes = [\"Dog\", \"Cat\"]\n", "coco_classes = [\"dog\", \"cat\"]\n", "\n", "eval_view = (\n", " dataset\n", " .filter_labels(\"detections\", F(\"label\").is_in(oi_classes), only_matches=False)\n", " .filter_labels(\"predictions\", F(\"label\").is_in(coco_classes), only_matches=False)\n", " .map_labels(\"predictions\", {\"dog\": \"Dog\", \"cat\": \"Cat\"})\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To see a human-readable description of the view, just call print:" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Dataset: open-images-cat-dog\n", "Media type: image\n", "Num samples: 500\n", "Sample fields:\n", " id: fiftyone.core.fields.ObjectIdField\n", " filepath: fiftyone.core.fields.StringField\n", " tags: fiftyone.core.fields.ListField(fiftyone.core.fields.StringField)\n", " metadata: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.metadata.ImageMetadata)\n", " positive_labels: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.labels.Classifications)\n", " negative_labels: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.labels.Classifications)\n", " detections: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.labels.Detections)\n", " predictions: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.labels.Detections)\n", " eval_tp: fiftyone.core.fields.IntField\n", " eval_fp: fiftyone.core.fields.IntField\n", " eval_fn: fiftyone.core.fields.IntField\n", "View stages:\n", " 1. FilterLabels(field='detections', filter={'$in': ['$$this.label', [...]]}, only_matches=False, trajectories=False)\n", " 2. FilterLabels(field='predictions', filter={'$in': ['$$this.label', [...]]}, only_matches=False, trajectories=False)\n", " 3. MapLabels(field='predictions', map={'cat': 'Cat', 'dog': 'Dog'})\n" ] } ], "source": [ "print(eval_view)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Running evaluation" ] }, { "cell_type": "markdown", "metadata": { "id": "6vo_3SgN2UM8" }, "source": [ "We're now ready to evaluate the contents of `eval_view` in FiftyOne with one line of code. \n", "\n", "Before we do this, note that [Open Images evaluation](https://storage.googleapis.com/openimages/web/evaluation.html) provides a few additions on top of the evaluation protocol for [Pascal VOC 2010](http://host.robots.ox.ac.uk/pascal/VOC/voc2010/devkit_doc_08-May-2010.pdf):\n", "\n", "- You can specify sample-level positive and negative labels; any object whose class is not in either list is ignored for that sample\n", "- A [class hierarchy](https://storage.googleapis.com/openimages/2018_04/bbox_labels_600_hierarchy_visualizer/circle.html) can be used to expand ground truth or predicted classes\n", "- Ground truth objects can use the `IsGroupOf` attribute to indicate multiple instances of a class existing within the bounding box\n", "\n", "All of these are required when evaluating a model on Open Images to compute the official mAP used to compare models in challenges and in research papers. If you are developing a custom dataset, you can choose to incorporate any number of these features into your dataset schema and selectively activate them when evaluating in FiftyOne." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Open Images Challenge evaluation\n", "\n", "FiftyOne's implementation of [Open Images-style evaluation](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html#open-images-style-evaluation) matches the reference implementation from the [TF Object Detection API](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/challenge_evaluation.md#object-detection-track), so you can use FiftyOne to compute the official mAP used for the [Open Images Challenge](https://storage.googleapis.com/openimages/web/evaluation.html).\n", "\n", "In addition, by using FiftyOne, you'll also gain access to helpful sample- and label-level results like true positives, false positives, and false negatives that can be used to [evaluate and analyze your model performance](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html) across various slices of your dataset." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The method call below computes the official Open Images mAP for our model predictions, leveraging the required image-level labels and expanded hierarchies that were automatically populated when we loaded the dataset from the FiftyOne Dataset Zoo:" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "a-IG4KU82Nt_", "outputId": "1ffd6166-7dbe-457e-96e5-bd1ef2fd0957" }, "outputs": [], "source": [ "results = eval_view.evaluate_detections(\n", " \"predictions\",\n", " gt_field=\"detections\",\n", " method=\"open-images\",\n", " pos_label_field=\"positive_labels\",\n", " neg_label_field=\"negative_labels\",\n", " hierarchy=dataset.info[\"hierarchy\"],\n", " expand_pred_hierarchy=True,\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "Mgf-0Yiy5D3i" }, "source": [ "The returned `results` object is an [OpenImagesDetectionResults](https://voxel51.com/docs/fiftyone/api/fiftyone.utils.eval.openimages.html#fiftyone.utils.eval.openimages.OpenImagesDetectionResults) instance that provides methods like [mAP()](https://voxel51.com/docs/fiftyone/api/fiftyone.utils.eval.openimages.html#fiftyone.utils.eval.openimages.OpenImagesDetectionResults.mAP), [plot_confusion_matrix()](https://voxel51.com/docs/fiftyone/api/fiftyone.utils.eval.openimages.html#fiftyone.utils.eval.openimages.OpenImagesDetectionResults.plot_confusion_matrix) and [plot_pr_curves()](https://voxel51.com/docs/fiftyone/api/fiftyone.utils.eval.openimages.html#fiftyone.utils.eval.openimages.OpenImagesDetectionResults.plot_pr_curves) that you can use to view common evaluation metrics." ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7817133327903734" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "results.mAP()" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "8436141edf9d4e5288bafece8130d096", "version_major": 2, "version_minor": 0 }, "text/plain": [ "FigureWidget({\n", " 'data': [{'mode': 'markers',\n", " 'opacity': 0.1,\n", " 'type': 'scatter',…" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "results.plot_confusion_matrix()" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "b270f34ee06148c7b729661bdd227aa4", "version_major": 2, "version_minor": 0 }, "text/plain": [ "FigureWidget({\n", " 'data': [{'customdata': array([1. , 0.98868752, 0.98573655, 0.98535502, 0.98457229, …" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "results.plot_pr_curves()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Custom dataset evaluation" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Using image-level labels in evaluation is useful to determine how well the model is able to detect specifically the objects that exist in the image.\n", "\n", "However, in this walkthrough, we are interested in evaluating false positives where the model was confused about the class of an object. This is something that we would not get by only evaluating classes specified by image-level labels, since the model may predict a cat in an image where \"Cat\" was not an image-level label.\n", "\n", "To perform this inter-class evaluation, we will set the parameter `classwise=False` and remove the image-level labels from the evaluation routine. Additionally, since our predictions are from a model trained without a class hierarchy, we will not expand the ground truth detections:" ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "a-IG4KU82Nt_", "outputId": "1ffd6166-7dbe-457e-96e5-bd1ef2fd0957" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Evaluating detections...\n", " 100% |█████████████████| 500/500 [5.3s elapsed, 0s remaining, 103.9 samples/s] \n" ] } ], "source": [ "results = eval_view.evaluate_detections(\n", " \"predictions\",\n", " gt_field=\"detections\",\n", " method=\"open-images\",\n", " eval_key=\"eval\",\n", " classwise=False,\n", " expand_gt_hierarchy=False,\n", ")" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.7714961284473072" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "results.mAP()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The slight drop in mAP is expected when matching predicted objects with ground truth of different classes, but this is desirable when trying to closely evaluate and understand your model. By default, when `classwise=True`, all false positives indicate that a predicted object was left unmatched. On the other hand, with `classwise=False`, some false positives now indicate that a prediction matched a ground truth object with a different class. This implies that the model was confident about the object being the incorrect class and that is information that we want to know." ] }, { "cell_type": "markdown", "metadata": { "id": "VjHqLZL24Sdf" }, "source": [ "### Analyzing the results\n", "\n", "FiftyOne evaluation results also allow you to plot PR curves and [interactivley explore confusion matrices](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html#confusion-matrices):" ] }, { "cell_type": "code", "execution_count": 34, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 542 }, "id": "_JwknB_c5iUQ", "outputId": "a02af960-2233-4903-997f-ee22f4c0defb" }, "outputs": [ { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "df6c101e6077476eb357001f359f9e79", "version_major": 2, "version_minor": 0 }, "text/plain": [ "FigureWidget({\n", " 'data': [{'customdata': array([1. , 0.98868752, 0.98573655, 0.98535502, 0.98457229, …" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plot = results.plot_pr_curves()\n", "plot.show()" ] }, { "cell_type": "code", "execution_count": 35, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 617 }, "id": "8adcIjInw901", "outputId": "405c29bd-c1fb-43e0-9090-16cb45a0eda3" }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "FigureWidget({\n", " 'data': [{'mode': 'markers',\n", " 'opacity': 0.1,\n", " 'type': 'scatter',…" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plot = results.plot_confusion_matrix(classes=[\"Dog\", \"Cat\"])\n", "plot.show(height=512)" ] }, { "cell_type": "markdown", "metadata": { "id": "JL8Zk8ql2JoZ" }, "source": [ "Note that, since we decided to evaluate with `classwise=False`, the off-diagonal elements of the confusion matrix are populated with instances where the model prediction was matched with a ground truth of a different class." ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view=eval_view" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [], "source": [ "session.freeze()" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.show()" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [], "source": [ "# If you are in a Jupyter notebook, attach plot to session\n", "session.plots.attach(plot)" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "9612db9099db44bab8f6ac7701fa21d8", "version_major": 2, "version_minor": 0 }, "text/plain": [ "FigureWidget({\n", " 'data': [{'mode': 'markers',\n", " 'opacity': 0.1,\n", " 'type': 'scatter',…" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plot.connect()\n", "plot.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Thanks to the [interactive plotting in FiftyOne](https://voxel51.com/docs/fiftyone/user_guide/plots.html#attaching-plots), we can attach this plot to our `session` object so that when you [click a cell of the confusion matrix](https://voxel51.com/docs/fiftyone/user_guide/plots.html#confusion-matrices), the session will automatically update to show the relevant samples.\n", "\n", "For example, if we click the top middle cell, the session will be updated to only show the examples where a dog was predicted as a cat." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Note:** Interactive plotting is currently only available in Jupyter notebooks, but it will soon be available in all environments!" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [], "source": [ "session.freeze() # screenshot App and attached plots" ] }, { "cell_type": "markdown", "metadata": { "id": "jKzAsgnA39iJ" }, "source": [ "When running [evaluate_detections()](https://voxel51.com/docs/fiftyone/api/fiftyone.core.collections.html#fiftyone.core.collections.SampleCollection.evaluate_detections), specifying an `eval_key` stores true positive, false positive, and false negative labels on the relevant ground truth and predicted objects. It also stores the ID of the matched ground truth object and the IoU of the match under `_id` and `_iou`.\n", "\n", "The `eval_key` in this example was set to `\"eval\"`:" ] }, { "cell_type": "code", "execution_count": 42, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "mDAiRaNK4Lkx", "outputId": "7bcee34b-747e-426c-e5d8-85124ceee13d" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n" ] } ], "source": [ "print(eval_view.first().predictions.detections[0])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can rerun [evaluate_detections()](https://voxel51.com/docs/fiftyone/api/fiftyone.core.collections.html#fiftyone.core.collections.SampleCollection.evaluate_detections) multiple times with different `eval_key` values to store multiple sets of evaluation runs on a dataset.\n", "\n", "Previous evaluation runs can easily be [loaded, viewed, and deleted](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html#managing-evaluations) at any time, including in future Python sessions." ] }, { "cell_type": "markdown", "metadata": { "id": "rhb1qMZvsYRx" }, "source": [ "## Advanced dataset exploration\n", "\n", "FiftyOne allows you to easily explore any fields that you have on your dataset both through code by creating a [view](https://voxel51.com/docs/fiftyone/user_guide/using_views.html) and through the [App](https://voxel51.com/docs/fiftyone/user_guide/app.html).\n", "\n", "For example, let's find all instances of `dog` or `cat` predictions with confidence >= 0.7 and sort the matching samples by number of true positives in the sample.\n", "\n", "We can construct this view via the [App](https://voxel51.com/docs/fiftyone/user_guide/app.html), we just need to click \"add stage\", select `SortBy`, and enter the field `eval_tp` with `reverse=True`. Then click the down arrow next to the `predictions` field we want to [filter](https://voxel51.com/docs/fiftyone/user_guide/using_views.html#filtering), type in the labels we want to include (cat and dog), and adjust the confidence slider threshold to 0.7." ] }, { "cell_type": "code", "execution_count": 43, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 821, "resources": { "https://localhost:5151/polling?sessionId=ae85c028-613e-4779-96ba-f712ad269943": { "data": "eyJtZXNzYWdlcyI6IFtdfQ==", "headers": [ [ "access-control-allow-headers", "x-requested-with" ], [ "content-type", "text/html; charset=UTF-8" ] ], "ok": true, "status": 200, "status_text": "" } } }, "id": "-trAVamEGkqB", "outputId": "ae68b83f-2601-4762-ebbd-9b3bbecd0a4d" }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session = fo.launch_app(dataset)" ] }, { "cell_type": "markdown", "metadata": { "id": "qy1o2w4sGLMX" }, "source": [ "We could also construct the same view [programmatically](https://voxel51.com/docs/fiftyone/user_guide/using_views.html#filtering):" ] }, { "cell_type": "code", "execution_count": 44, "metadata": { "id": "qlTN6zDps-Hm" }, "outputs": [], "source": [ "from fiftyone import ViewField as F\n", "\n", "dog_cat_view = (\n", " dataset\n", " .filter_labels(\n", " \"predictions\", \n", " (F(\"label\").is_in([\"dog\", \"cat\"])) & (F(\"confidence\") > 0.7),\n", " )\n", " .sort_by(\"eval_tp\", reverse=True)\n", ")" ] }, { "cell_type": "code", "execution_count": 45, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "nHN3VSHsZdFl", "outputId": "46511e80-a16f-40db-bdda-3bfe2420d374" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Dataset: open-images-cat-dog\n", "Media type: image\n", "Num samples: 412\n", "Sample fields:\n", " id: fiftyone.core.fields.ObjectIdField\n", " filepath: fiftyone.core.fields.StringField\n", " tags: fiftyone.core.fields.ListField(fiftyone.core.fields.StringField)\n", " metadata: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.metadata.ImageMetadata)\n", " positive_labels: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.labels.Classifications)\n", " negative_labels: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.labels.Classifications)\n", " detections: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.labels.Detections)\n", " predictions: fiftyone.core.fields.EmbeddedDocumentField(fiftyone.core.labels.Detections)\n", " eval_tp: fiftyone.core.fields.IntField\n", " eval_fp: fiftyone.core.fields.IntField\n", " eval_fn: fiftyone.core.fields.IntField\n", "View stages:\n", " 1. FilterLabels(field='predictions', filter={'$and': [{...}, {...}]}, only_matches=True, trajectories=False)\n", " 2. SortBy(field_or_expr='eval_tp', reverse=True)\n" ] } ], "source": [ "print(dog_cat_view)" ] }, { "cell_type": "code", "execution_count": 46, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 821, "resources": { "https://localhost:5151/polling?sessionId=5a85956a-df76-4660-aaf9-4c4703c6fe77": { "data": "eyJtZXNzYWdlcyI6IFtdfQ==", "headers": [ [ "access-control-allow-headers", "x-requested-with" ], [ "content-type", "text/html; charset=UTF-8" ] ], "ok": true, "status": 200, "status_text": "" } } }, "id": "jGHcLZw6Y_rd", "outputId": "fdf6fbdf-6ba9-4e3f-eb6b-6c46ba0180a6" }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view = dog_cat_view" ] }, { "cell_type": "markdown", "metadata": { "id": "Ii-oCq7Y4WqH" }, "source": [ "These views are easy to create but can be incredibly useful to explore and query your dataset and model predictions.\n", "\n", "For example, we can find all high confidence predictions of \"Dog\" that ended up being false positives." ] }, { "cell_type": "code", "execution_count": 47, "metadata": { "id": "rmEX-gRhGJSB" }, "outputs": [], "source": [ "fp_dog_view = dataset.filter_labels(\n", " \"predictions\", \n", " (F(\"eval\") == \"fp\") & (F(\"confidence\") > 0.9),\n", ")" ] }, { "cell_type": "code", "execution_count": 48, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 821, "resources": { "https://localhost:5151/polling?sessionId=ad668bfa-f68d-4343-a78b-079b70d157f9": { "data": "eyJtZXNzYWdlcyI6IFtdfQ==", "headers": [ [ "access-control-allow-headers", "x-requested-with" ], [ "content-type", "text/html; charset=UTF-8" ] ], "ok": true, "status": 200, "status_text": "" } } }, "id": "gycTuuryHaaR", "outputId": "ed48d768-1a39-4339-9df3-68aec5b5752c" }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view = fp_dog_view" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [], "source": [ "session.freeze()" ] }, { "cell_type": "markdown", "metadata": { "id": "OsphwIXRkpjn" }, "source": [ "Looking through some of these examples, we can see that when the model confuses dogs for cats roughly the same amount as cats for dogs. Additionally, the model occasionally has issues localizing bounding boxes resulting in unmatched detections due to an IoU lower than 0.5. \n", "\n", "In the example above, there are two ground truth \"cat\" boxes and one detected \"dog\" box containing both cats. This implies that we should look more closely at our training data to verify that there are no cats mistakenly annotated as dogs and that the boxes are localized properly.\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The same workflow can be performed through the App using [evaluation views](https://voxel51.com/docs/fiftyone/user_guide/app.html#viewing-evaluation-patches). After evaluating detections and storing the results in an `eval_key`, you can click the following button in the App to open the evaluation view allowing you to explore individual TP/FP/FN patches." ] }, { "cell_type": "code", "execution_count": 50, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view = eval_view" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now let's perform the same evaluation for \"Cat\". The eval view contains the `type` scalar field which we can use to select only false positives. Then under `predictions`, we can select only \"Cat\" predictions and slide the confidence up to 0.9." ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [], "source": [ "session.freeze()" ] }, { "cell_type": "markdown", "metadata": { "id": "VvXJ6JkUEXqI" }, "source": [ "### Visualize embeddings\n", "\n", "FiftyOne is designed to make it easy to explore the labels and attributes that you [add to your datasets yourself](https://voxel51.com/docs/fiftyone/user_guide/using_datasets.html#adding-fields-to-a-sample). However, it can also provide much deeper insights.\n", "\n", "For example, FiftyOne provides methods for [sample uniqueness](https://voxel51.com/docs/fiftyone/user_guide/brain.html#image-uniqueness), [label mistakes](https://voxel51.com/docs/fiftyone/user_guide/brain.html#label-mistakes), and [sample hardness](https://voxel51.com/docs/fiftyone/user_guide/brain.html#sample-hardness). It also provides support for automatically [generating and visualizing embeddings](https://voxel51.com/docs/fiftyone/user_guide/brain.html#visualizing-embeddings), which we'll use next." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The cell below uses [compute_visualization()](https://voxel51.com/docs/fiftyone/api/fiftyone.brain.html#fiftyone.brain.compute_visualization) to generate a 2D representation of the objects in the `predictions` field of our `eval_view` view.\n", "\n", "Internally, the method generates deep embeddings for each object patch and then uses [UMAP](https://github.com/lmcinnes/umap) to generate the 2D representation." ] }, { "cell_type": "code", "execution_count": 52, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing patch embeddings...\n", " 100% |█████████████████| 500/500 [1.4m elapsed, 0s remaining, 6.4 samples/s] \n", "Generating visualization...\n", "UMAP(random_state=51, verbose=True)\n", "Tue Feb 14 22:52:41 2023 Construct fuzzy simplicial set\n", "Tue Feb 14 22:52:41 2023 Finding Nearest Neighbors\n", "Tue Feb 14 22:52:41 2023 Finished Nearest Neighbor Search\n", "Tue Feb 14 22:52:41 2023 Construct embedding\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "840db15938a04a21847f458f01acc1f6", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Epochs completed: 0%| 0/500 [00:00]" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Tue Feb 14 22:52:42 2023 Finished embedding\n" ] } ], "source": [ "import fiftyone.brain as fob\n", "\n", "results = fob.compute_visualization(\n", " eval_view,\n", " patches_field=\"predictions\",\n", " brain_key=\"eval_patches\", # provide a brain key to save results to the dataset\n", " num_dims=2,\n", " method=\"umap\",\n", " verbose=True,\n", " seed=51,\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "First let's launch a new App instance for this exploration:" ] }, { "cell_type": "code", "execution_count": 53, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view=eval_view" ] }, { "cell_type": "markdown", "metadata": { "id": "ylQeGYF21BLP" }, "source": [ "Now let's visualize the object embeddings with each point colored by label and scaled by the size of the bounding box:" ] }, { "cell_type": "code", "execution_count": 54, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 630 }, "id": "6MZnq3Bz_7dj", "outputId": "971acef0-baae-4180-e9c4-7ebb453a15f2" }, "outputs": [ { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "ec5015fc95794512b7115ca535fd5597", "version_major": 2, "version_minor": 0 }, "text/plain": [ "FigureWidget({\n", " 'data': [{'customdata': array(['63ec56fed3964b0824a4dae9', '63ec570bd3964b0824a4daea',\n", " …" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stderr", "output_type": "stream", "text": [ "Executing took 0.165 seconds\n" ] } ], "source": [ "# Computes the area of each predicted object\n", "bbox_area = F(\"bounding_box\")[2] * F(\"bounding_box\")[3]\n", "areas = eval_view.values(\"predictions.detections[]\", bbox_area)\n", "\n", "plot = results.visualize(labels=\"predictions.detections.label\", sizes=areas)\n", "plot.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "cQi6ict_JyLT" }, "source": [ "**Note:** These plots are currently only interactive in Jupyter notebooks. A future release will provide interactive plots in all environments." ] }, { "cell_type": "code", "execution_count": 55, "metadata": {}, "outputs": [], "source": [ "# If you are in a Jupyter notebook, attach plot to session\n", "session.plots.attach(plot)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "If you're working in a Jupyter notebook, click the lasso tool on the plot to select a region of points that you want to visualize in the App.\n", "\n", "You can clearly see the cat detections delinated from the dog detections.\n", "\n", "Now try hiding the \"Dog\" points by clicking on the corresponding legend entry in the upper right so that you see only the \"Cat\" points. You can then lasso the cluster of \"Cat\" points that reside in the \"Dog\" cluster. These points are the false positives that the model predicted as \"Cat\" but were in fact dogs!\n", "\n", "This kind of visiualization can be invaluable for a multitude of reasons, particularly for a dataset like Open Images that contains machine-generated labels. Visualizing and interactively exploring embeddings lets you quickly spot check which labels may need to be reviewed by human annotators." ] }, { "cell_type": "code", "execution_count": 56, "metadata": {}, "outputs": [], "source": [ "session.freeze()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Sort by similarity\n", "\n", "FiftyOne also supports sorting samples and objects by [visual similarity](https://voxel51.com/docs/fiftyone/user_guide/brain.html#brain-similarity).\n", "\n", "To use this feature, we first use [compute_similarity()](https://voxel51.com/docs/fiftyone/api/fiftyone.brain.html#fiftyone.brain.compute_similarity) to index our dataset (the images, in this case):" ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing embeddings...\n", " 100% |█████████████████| 500/500 [1.8m elapsed, 0s remaining, 4.3 samples/s] \n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 77, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import fiftyone.brain as fob\n", "\n", "# Indexes the images in the dataset by visual similarity\n", "fob.compute_similarity(dataset, brain_key=\"similarity\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Under the hood, deep embeddings are again being used to generate the index. By default, a general purpose model packaged with FiftyOne is used, but you can also provide your own embeddings via the optional `embeddings` argument.\n", "\n", "Once similarity has been computed, we can sort the samples in the dataset based on their similarity to selected sample(s) of interest. This can be done either (a) programmatically via the [sort_by_similarity()](https://voxel51.com/docs/fiftyone/api/fiftyone.core.collections.html#fiftyone.core.collections.SampleCollection.sort_by_similarity) view stage, or (b) in the App by clicking the [sort by similarity button](https://voxel51.com/docs/fiftyone/user_guide/app.html#sorting-by-visual-similarity) as shown below." ] }, { "cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view = dataset.view()" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [], "source": [ "session.freeze()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Tagging\n", "\n", "Interactive plots and embeddings can power valuable workflows like [semi-supervised annotation](https://voxel51.com/docs/fiftyone/tutorials/image_embeddings.html), [removing duplicates](https://nbviewer.jupyter.org/github/voxel51/fiftyone-examples/blob/master/examples/image_deduplication.ipynb), [detecting annotation mistakes](https://voxel51.com/docs/fiftyone/tutorials/detection_mistakes.html), and much more.\n", "\n", "For example, Open Images contains a class for \"Cattle\". However, this class contains animals like cows, sheep, and goats. We can use FiftyOne to visualize clusters of embeddings for \"Cattle\" and use the App's [tagging feature](https://voxel51.com/docs/fiftyone/user_guide/app.html#tags-and-tagging) to assign fine-grained labels to each type of cattle, which will conveniently form clusters when visualized." ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Downloading split 'test' to 'datasets/open-images-v7/test' if necessary\n", "Downloading 'https://storage.googleapis.com/openimages/2018_04/test/test-images-with-rotation.csv' to 'datasets/open-images-v7/test/metadata/image_ids.csv'\n", "Downloading 'https://storage.googleapis.com/openimages/v5/class-descriptions-boxable.csv' to 'datasets/open-images-v7/test/metadata/classes.csv'\n", "Downloading 'https://storage.googleapis.com/openimages/2018_04/bbox_labels_600_hierarchy.json' to '/var/folders/8f/wbp6tz9j19z4nff5zt3d1_k80000gn/T/tmpxgkd59dc/metadata/hierarchy.json'\n", "Downloading 'https://storage.googleapis.com/openimages/v5/test-annotations-bbox.csv' to 'datasets/open-images-v7/test/labels/detections.csv'\n", "Downloading 200 images\n", " 100% |███████████████████| 200/200 [6.9s elapsed, 0s remaining, 28.7 files/s] \n", "Dataset info written to 'datasets/open-images-v7/info.json'\n", "Loading 'open-images-v7' split 'test'\n", " 100% |█████████████████| 200/200 [1.0s elapsed, 0s remaining, 199.2 samples/s] \n", "Dataset 'open-images-cattle' created\n" ] } ], "source": [ "# Download some images that contain cattle from Open Images\n", "dataset = foz.load_zoo_dataset(\n", " \"open-images-v7\", \n", " split=\"test\", \n", " label_types=[\"detections\"], \n", " classes=[\"Cattle\"],\n", " max_samples=200,\n", " seed=51,\n", " shuffle=True,\n", " dataset_name=\"open-images-cattle\",\n", ")" ] }, { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [], "source": [ "from fiftyone import ViewField as F\n", "\n", "# Create a view that only contains cattle detections\n", "cattle_view = dataset.filter_labels(\"ground_truth\", F(\"label\") == \"Cattle\")" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session.view=cattle_view" ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [], "source": [ "session.freeze()" ] }, { "cell_type": "code", "execution_count": 64, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "p28s_AuY_xlx", "outputId": "9fbea4c7-9ccb-472e-a666-23621f6e410e" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing patch embeddings...\n", " 100% |█████████████████| 200/200 [50.2s elapsed, 0s remaining, 4.4 samples/s] \n", "Generating visualization...\n", "UMAP(random_state=51, verbose=True)\n", "Tue Feb 14 23:01:46 2023 Construct fuzzy simplicial set\n", "Tue Feb 14 23:01:46 2023 Finding Nearest Neighbors\n", "Tue Feb 14 23:01:47 2023 Finished Nearest Neighbor Search\n", "Tue Feb 14 23:01:47 2023 Construct embedding\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "a6de5263194f4a66988a7f9984dda88c", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Epochs completed: 0%| 0/500 [00:00]" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Tue Feb 14 23:01:47 2023 Finished embedding\n" ] } ], "source": [ "import fiftyone.brain as fob\n", "\n", "# Generate a 2D representation of the cattle objects\n", "results = fob.compute_visualization(\n", " cattle_view,\n", " patches_field=\"ground_truth\",\n", " num_dims=2,\n", " method=\"umap\",\n", " verbose=True,\n", " seed=51,\n", ")" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing patch embeddings...\n", " 100% |█████████████████| 413/413 [52.7s elapsed, 0s remaining, 9.2 samples/s] \n", "Generating visualization...\n", "UMAP(random_state=51, verbose=True)\n", "Wed Feb 15 00:33:37 2023 Construct fuzzy simplicial set\n", "Wed Feb 15 00:33:37 2023 Finding Nearest Neighbors\n", "Wed Feb 15 00:33:37 2023 Finished Nearest Neighbor Search\n", "Wed Feb 15 00:33:37 2023 Construct embedding\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "2c98bbfc6c724ba1825ca4b1a3d07495", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Epochs completed: 0%| 0/500 [00:00]" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Wed Feb 15 00:33:38 2023 Finished embedding\n" ] } ], "source": [ "import fiftyone.brain as fob\n", "\n", "# Generate a 2D representation of the cattle objects\n", "cattle_patches_view=cattle_view.to_patches(field=\"ground_truth\")\n", "patches_results = fob.compute_visualization(\n", " cattle_patches_view,\n", " patches_field=\"ground_truth\",\n", " brain_key=\"cattle_patches_gt\",\n", " num_dims=2,\n", " method=\"umap\",\n", " verbose=True,\n", " seed=51,\n", ")" ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Computing patch embeddings...\n", " 100% |███████████████| 1696/1696 [3.3m elapsed, 0s remaining, 7.1 samples/s] \n", "Generating visualization...\n", "UMAP(random_state=51, verbose=True)\n", "Wed Feb 15 01:00:42 2023 Construct fuzzy simplicial set\n", "Wed Feb 15 01:00:43 2023 Finding Nearest Neighbors\n", "Wed Feb 15 01:00:43 2023 Finished Nearest Neighbor Search\n", "Wed Feb 15 01:00:43 2023 Construct embedding\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "661ad680e6dd41f2960c1ba1b89531e9", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Epochs completed: 0%| 0/500 [00:00]" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Wed Feb 15 01:00:45 2023 Finished embedding\n" ] } ], "source": [ "patches_view=dataset.to_patches(field=\"ground_truth\")\n", "gt_patches_results = fob.compute_visualization(\n", " patches_view,\n", " patches_field=\"ground_truth\",\n", " brain_key=\"patches_gt\",\n", " num_dims=2,\n", " method=\"umap\",\n", " verbose=True,\n", " seed=51,\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "ylQeGYF21BLP" }, "source": [ "The snippet below visualizes the cattle instances that we downloaded in a 2D space, with each point scaled by the size of the bounding box:" ] }, { "cell_type": "code", "execution_count": 67, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 630 }, "id": "6MZnq3Bz_7dj", "outputId": "971acef0-baae-4180-e9c4-7ebb453a15f2" }, "outputs": [], "source": [ "# Computes the area of each cattle detection in the view\n", "# Bounding box coordinates are in the format: [top-left-x, top-left-y, width, height]\n", "bbox_area = F(\"bounding_box\")[2] * F(\"bounding_box\")[3]\n", "areas = cattle_patches_view.values(\"ground_truth\", bbox_area) #cattle_view.values(\"ground_truth.detections[]\", bbox_area)\n" ] }, { "cell_type": "code", "execution_count": 68, "metadata": { "scrolled": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAA9oAAAHCCAYAAAAQDbGYAAAgAElEQVR4XuxdB5gUVdY91T15GIYhM+Scc0ZEMqKoBEEUFXPYdV1z2F9d4+q6pjWsWcyIKAZcUYyLCVFQEQSUoAiS0wAz09Oh/u/eN9XT09OhqhPdPfd9H59CV71w3quqd96991xN13UdUgQBQUAQEAQEAUFAEBAEBAFBQBAQBAQBQSAmCGhCtGOCo1QiCAgCgoAgIAgIAoKAICAICAKCgCAgCDACQrRlIQgCgoAgIAgIAoKAICAICAKCgCAgCAgCMURAiHYMwZSqBAFBQBAQBAQBQUAQEAQEAUFAEBAEBAEh2rIGBAFBQBAQBAQBQUAQEAQEAUFAEBAEBIEYIiBEO4ZgSlWCgCAgCAgCgoAgIAgIAoKAICAICAKCgBBtWQOCgCAgCAgCgoAgIAgIAoKAICAICAKCQAwREKIdQzClKkFAEBAEBAFBQBAQBAQBQUAQEAQEAUFAiLasAUFAEBAEBAFBQBAQBAQBQUAQEAQEAUEghggI0Y4hmFKVICAICAKCgCAgCAgCgoAgIAgIAoKAICBEW9aAICAICAKCgCAgCAgCgoAgIAgIAoKAIBBDBIRoxxBMqUoQEAQEAUFAEBAEBAFBQBAQBAQBQUAQEKIta0AQEAQEAUFAEBAEBAFBQBAQBAQBQUAQiCECQrRjCKZUJQgIAoKAICAICAKCgCAgCAgCgoAgIAgI0ZY1IAgIAoKAICAICAKCgCAgCAgCgoAgIAjEEAEh2jEEU6oSBAQBQUAQEAQEAUFAEBAEBAFBQBAQBIRoyxoQBAQBQUAQEAQEAUFAEBAEBAFBQBAQBGKIgBDtGIIpVQkCgoAgIAgIAoKAICAICAKCgCAgCAgCQrRlDQgCgoAgIAgIAoKAICAICAKCgCAgCAgCMURAiHYMwZSqBAFBQBAQBAQBQUAQEAQEAUFAEBAEBAEh2rIGBAFBQBAQBAQBQUAQEAQEAUFAEBAEBIEYIiBEO4ZgSlWCgCAgCAgCgoAgIAgIAoKAICAICAKCgBBtWQOCgCAgCAgCgoAgIAgIAoKAICAICAKCQAwREKIdQzClKkFAEBAEBAFBQBAQBAQBQUAQEAQEAUFAiLasAUFAEBAEBAFBQBAQBAQBQUAQEAQEAUEghggI0Y4hmFKVICAICAKCgCAgCAgCgoAgIAgIAoKAICBEW9aAICAICAKCgCAgCAgCgoAgIAgIAoKAIBBDBIRoxxBMqUoQEAQEAUFAEBAEBAFBQBAQBAQBQUAQEKIta0AQEAQEAUFAEBAEBAFBQBAQBAQBQUAQiCECQrRjCKZUJQgIAoKAICAICAKCgCAgCAgCgoAgIAjEnWjv3btXUK6FCNjtdtSpUwcHDhyohaOXIScDApqmoV69eti3b18ydEf6UEsRqF+/PuQ7WEsnP0mGTe/BkpISeDyeJOmRdKO2IVC3bl2UlpbC5XLVtqEfkfHSHrywsPCItC2NVkdAiLasiLggIEQ7LrBKpRYQEKJtASy5NG4ICNGOG7RSsUkEhGibBEouixsCQrTjBm3AioVoJxbvUK0J0U6euUirngjRTqvpTMnBCNFOyWlLu04L0U67KU25AQnRTrkpS7sOC9FO7JQK0U4s3kK0kwfvWtMTIdq1ZqqTdqBCtJN2ampVx4Ro16rpTsrBCtFOymmpVZ0Sop3Y6RainVi8hWgnD961pidCtGvNVCftQIVoJ+3U1KqOCdGuVdOdlIMVop2U01KrOiVEO7HTLUQ7sXgL0U4evGtNT4Ro15qpTtqBCtFO2qmpVR0Tol2rpjspBytEOymnpVZ1Soh2YqdbiHZi8RainTx415qeCNGuNVOdtAMVop20U1OrOiZEu1ZNd1IOVoh2Uk5LreqUEO3ETrcQ7cTiLUQ7efCuNT0Rol1rpjppBypEO2mnplZ1TIh2rZrupBysEO2knJZa1Skh2omd7ngQ7bvuugtNmjTB2WefbWowCxYswLJly0D3RVrefPNNfP7557jnnnsireKI3yeq40d8CtKzA0K003NeU2lUQrRTabbSt69CtNN3blNlZEK0U2Wm0refQrQTO7fxINpnnXUW2rdvjxtvvNHUYB566CF8+OGHeOutt0xdH+iiRx99FAsXLsS7774bcR1H+kYh2kd6BtK0fSHaaTqxKTQsIdopNFlp3FUh2mk8uSkyNCHaKTJRadxNIdqJnVwh2onFO1RrQrSTZy7SqidCtNNqOlNyMEK0U3La0q7TQrTTbkpTbkBCtFNuytKuw0K0EzuliSDa1113HVauXImdO3eiqKgIQ4cOxSWXXILGjRvzYMmi/fbbb2P27NkgN/LNmzfjmGOOwf/93/+BvotU3G435s6dy1bvTZs2oUOHDjjvvPMwduxY/l0s2ibWzd69e01cJZekGwJCtNNtRlNvPEK0U2/O0rHHQrTTcVZTa0xCtFNrvtKxt0K0EzuriSDaV155Jfr06YPmzZuDuN7jjz+OTp064ZFHHvES7eeeew6tWrXCiSeeiI0bN7IL+LBhw/Dggw96r5k/fz6mT5+Orl274uOPP8bixYsxZ84c9OzZU4i2mWUjRNsMSul3jRDt9JvTVBuREO1Um7H07K8Q7fSc11QalRDtVJqt9OyrEO3EzmsiiLYxIofDgX379rFl+qWXXmIBNJvN5rVoL1q0CBkZGXz5Y489hqeeeooJN/3b+PHjcemll+LMM8/k310uF0aPHo3JkyfjiiuuEKJtZtkI0TaDUvpdI0Q7/eY01UYkRDvVZiw9+ytEOz3nNZVGJUQ7lWYrPfsqRDux85oIok1CZ0Sa169fX21wS5cuZRIdSAyNFMQvu+wyPP300+w2fsEFF7BFvKCgwFvH2rVr2cX83nvvFaJtZtkI0TaDUvpdI0Q7/eY01UYkRDvVZiw9+ytEOz3nNZVGJUQ7lWYrPfsqRDux8xpvok1kmuKxySV86tSpaNGiBT755BPccccdMEO0yTX84MGDbM2+5pprmGz7Fnpnde/eXYi2mWUjRNsMSul3jRDt9JvTVBuREO1Um7H07K8Q7fSc11QalRDtVJqt9OyrEO3Ezmu8ifbDDz+MZ5991kuqaXQkfHbrrbeGJNr33XcfXn75ZU77dejQIXYRv/766zFt2rSAAIkYmol1I0TbBEhpeIkQ7TSc1BQbkhDtFJuwNO2uEO00ndgUGpYQ7RSarDTtqhDtxE5svIm24QJObuD9+vXDmjVrOP6aYrV9LdokdPaPf/yDLd6ffvopnnnmGYwcOZIJOZWrrrqK//2GG25gYTXijF988QUyMzNx0UUXiUXbzLIRom0GpfS7Roh2+s1pqo1IiHaqzVh69leIdnrOayqNSoh2Ks1WevZViHZi5zVeRJvSbxEpJtGym2++Ge+99x4PjNJ79ejRA5999lk1ok2q43l5eSgtLeXrhg8fjltuuQWFhYX895KSElYpf/31170AUV3XXnstp/gSi7aJdSNE2wRIaXiJEO00nNQUG5IQ7RSbsDTtrhDtNJ3YFBqWEO0Umqw07aoQ7cRObDyIdqAR7N+/n2Oti4uLQW0GKk6nE1u3bgWtASN/tv91RNz37NmD7Oxs0PsqnYqm67oezwEJ0Y4nuslbtxDt5J2b2tIzIdq1ZaaTe5xCtJN7fmpD74Ro14ZZTu4xCtFO7PwkimgndlSp2ZoQ7dSct6TvtRDtpJ+itO+gEO20n+KUGKAQ7ZSYprTupBDttJ7elBicEO3ETpMQ7cTiHao1IdrJMxdp1RMh2mk1nSk5GCHaVdNGOS1tNhsIE/pDjkz0h9y1PB5PSs5vqnRaiHaqzFT69lOIdvrObaqMTIh2YmdKiHZi8RainTx415qeCNGuNVOdtAMVog0QwaaYJ5vHCWz8EijZDnjcgD0TaNwRaNEXLrcbDodDCHecVrIQ7TgBK9WaRkCItmmo5MI4ISBEO07ABqlWiHZi8RainTx415qeCNGuNVOdtANNJ6JNYyHSTM8V/Zf+bhSyTJNVmqzTvhZqIthZdg345iVg1TuKYPuXnEJg8BnQO41GeXk53y8ltggI0Y4tnlKbdQSEaFvHTO6ILQJCtGOLZ7jahGiHQyhxv4vreOKwrlUtCdGuVdOdlINNB6JNYyDCzOT6wFZg41fAnk3qj+OQskwXNgMadwKadAFaD4Tbo9zCMypKgP/eDOz7Pfz8tBsGjLkKZUK2w2Nl8Qoh2hYBk8tjjoAQ7ZhDKhVaRECItkXAorxciHaUAMbwdiHaMQRTqqpCIJmINpEUKmKtq10rNNFE24iD9kXZiIOOJLlDZmYmk2xty/fA8rnAzl/CT2B2PrThF8LWfjj0BVfAs/vX8PcYV3QZB/3oi3H48GEm6lJig4AQ7djgKLVEjoAQ7cixkztjg4AQ7djgaLYWIdpmkYr/dUK0449xrWwhGYg2Ea28vDzYDu/mOfDkN0RpaamQiFqyIn2JNgmBEXE1BMHcbjcfvNB/oy1ZWVmgP5rLAWz9ASDLMwmM5RUBzXtDz2/AbVVUVJiOg2a3b80N/O9hFVttodhHXAxs+Az4bRmQXQdutwWxs0m3oqJhZ47ZlhIbBIRoxwZHqSVyBIRoR46d3BkbBIRoxwZHs7UI0TaLVPyvE6Idf4xrZQvJQLSJ/GSX/A68cbWagyn/gqNuSyY8UtIfAYNoHzp0SFmGiXzuWAd4XED91kDX8ahweSImlbTGc3JyYNv3G7DiVWDT0sCgFrUC+k6D3v5oXnvh1h/Vmek4ALx7M7B/q7WJqtsU9mHnAM+dDjjLgYbtgPz65sl2q/7QJ/wfCDMzxVAxp2sNJXMz99Wma4Ro16bZTs6xCtFOznmpTb0Sop3Y2U5Kov3HKgVCcY/EghGD1lavXo3WrVujTp06lmsTom0ZMrnBDAJJQ7T/WAF8cLfq8rhr4CjuF5bomBmfXJP8CBhE20UHK4tuAbaurN7pes2BSbfBYc+zvCZofefm5kJbMQ9YPs8cGMU9eQ1WaFlByT1Z3XMyAI0EzMpLAPbg1oHSfdDJdZys5iGK1n44bPn1gHdvrbqqUQcgr55Jsq0B583H4bLykNZ3OsQyPARQUaoOL7LrQIdm2XpvDrzUvUqIdurOXbr0XIh2usxk6o5DiHZi5y6piPa3rwDLX6kOQM8TgGHnxgyUL7/8Es899xzWrFnDnqu9e/fGCSecgMmTJ4ds48cff8T69esxZcoU73WLFi0CfbcHDx7s/bcBAwbgqaeeQp8+fSz3WYi2ZcjkBjMIJAPRJjdhch3X1n3IXdY7j+UHUPIGm5nB1L+GiHZRURGcXz4HfDc/8IAsWnCpEu+6+vxRYM0H1oCq1wI46U44kFmD3BNxzc/PB3b+rCzvu9YDFWVAbl2gSWcgtx703Zugb/oK+q4NAdu1dR4FrWQH8M2LVb9rNqC4Ozy2LHNhEzMeQlm2cnf3L9Ws+D8uBDZ8Abh9PERIlK3rBKDzaB6fuKCDP9h79+61tk7kakEghggI0Y4hmFJVRAgI0Y4ItohvOuJEm3ReKDvKwhsAw5LtPxqybJ9we8RjNG58++23ceutt+Liiy/GMcccwxlUli5diueffx5LliwJWf+8efPw8ccf4/HHH/ded9VVV6FLly4477zzhGhHPTtSQdwQsEq0ybWXiAa5n9LmPFbCZUY6JBporGJy4waaVBxTBLxE+6mZSqE7WDnrJZS6EDBem0i1v0s0Hd7Yf/kYWPKfyPrbog/0iTd5D32oDXYXd5dB++oZ4PPHA/e3oDHQfSLQ/XjouzfC88NbNSzcti5joJHKuP/pcY4i66Zi0qfcjbI6LWo8g14r/rcvAd+9HnrsZEUffx2cWXX5o1ebixDt2jz7yTF2IdrJMQ+1uRdCtBM7+0ecaNNw6TD+y6dDD5ys2mTdjrCQeOvEiRNx1lln4ZxzzqlWy+7du9GwYUOsXbuWrdE7d+5knjFo0CC+ng7Ar776amzevBkjRozgtKnjx49n0k7vzM6dO7O7+Pnnnw9fizbto+bPn49PPvkEBQUFbDk/6qijODtMoCIW7QgnV24LjYAVos2x1OV7gS+eBIpaQB9ytigfywKzhACtIVpzRIqdTicTSiKw9LJ0PjIpdF3TH0RZTsNqxNJrtXYcBLLy4XR7mDDSizTXrgMvnhPWjTtko2OvhrPlQO4ru6Bv+Az2Lx4DfvsGcIXWENAKGgFjroCe3xj6ty9BL90PQOXV1joeA436TM+Sf2nSGXp2HXg8YRTFz5iDUj2rGin34kH1/rTI3NwUNAGm3I1yZPE4a2sRoh3ZzBuHpPRfQ8SQaqJnnJ5vQ9BQPJTC4ytEOzxGckV8ERCiHV98/WtPCqIdypptdDhKq/aqVauYNJO7d6NGjQKC/P3332PFihXo1KkT7+Puu+8+TJ06FTNmzMA999yDH374ga3hVDp06ICbb74ZTZo0wbhx43gPOWTIkGpE+6GHHmKSfe655/L36D//+Q8T9lGjRgnRTuwyr92tWSHabM37fn6Ve+/Mx1CWWTdmVu3aPRPpP3qOa9Ydav0UFkPvNpEPaqiw6/icM4HSEK6757yCww5XtZACXpObPgM+fQggwjjzPzh0uJQtzxmr3gaWvRAdsI07ApPv5pe0tuJV2L6bB41isoOk8KKTVqPw/+seYOxV0Bu0g/7x/ervWXnQKB92y/7A3AuhU2y3L6fObwA0bBs6Vju7DjD7Be+hAj3H1B4Tnc3fQH/vjkqcqvoTEojWA6GPv75WH5wJ0bb2qNBhFnk42W0abOX7gf3bAAr/ObQbcJUD2QVK5K9lP3iaduNDHPKCEsIdHGch2tbWoFwdewSEaMce01A1JgXRfjx0fLS3/xe+GTE4H374Ia677josW7aM9ynBCu0JKX6brNrvvvsuf2PuvfdeWHUd79q1K1uvb7jhBm8M99y5c9k6fvvtgd3gxaId8fTKjeEeclLnO3DgQFigOJXRvo3AotsAUmg+8Q4cLi2TjVNY5OQCQoBJ8Q+vKeVvKqc9gTI7pbVyK6K94g3gqyDuSx2PgT7yrzVUtsnKnPHti8DKt1SdZ8/F4Qq3ivl/8xoVPx1lsZ87F57fvoX+4b2w0wdi32bg4M5qtSqCrUOjOGuKhXY71R8q9BuR9ZId0D9/Qv1bVj5ss54E3rkB2PMrk23dsGDT9S37KaLtQ9yrNdhnKrTBZ0Kn2PAf3wbWLwHK9sM+5krgresU0anTkK3ipnNtT7kHjrotLAvORQlv0twuRNv8VPCzbLfBfngn8Pt3wNJngV+/DlxBbj2gRW9g6DlwdxjJh0O12XMiFMpCtM2vQbkyPggI0Y4PrsFqTQqi/drlwJ5NoQdOIXGnVe5fIoCIrNUUS/3++++jQYMGAWv4/PPPcdlll7G1mmKvN27cyNopDzzwgGWiTfeRNbxVq1bsRWmUZs2a4cEHHwzYvhDtCCZWbgmPgBWLNpEJIjaG66+ZFEjheyBXxAMBsh7TfBku2vFow2qdfFCzfSXw3j+Auo2B6Q/hcHkF95Fdx51OaEseAdZ9VL3qZt2AY29EuRs1NuheKznFGDVsC0+boRxTzakdnpxK/qtWu1nterYSj7sGnk1Lof/yP0W0//ixmju6YcXWPE7AWRa4zcJiYMYj0P/7d+h7flVtDD0bNnIvf+cmIDMXuo1kzMnorQPNusGTkRuYJGcXwDbrcUXc6dDrsPIC0NoMgq24O/DqX1T9ZPVu3BEeqPj1sKX3FLgHzGL8amMRom1u1vlwy1UG+75fgbUfKG8S8tQIWTRl3e40Eu4x18Dh0aod6Bjp52p76jkh2ubWoFwVPwSEaMcP20A1JwXR/vRBYN3HoQfeZjAw4fqIwdm/fz/Gjh3LVu2TTz65Wj10+EqHtzNnzsTRRx+NP//5z/w7qZN/9913TLRfffVVJulPP11ljCExNHIzv+CCC7z1GTHabdu2xZgxY/Dyyy/zNWZKNaJNFiBfhm6mgnDXiNpqOITS83crRDs9EUi/UbG1yXkQ2Pgl0GEEKmw5SaEqTZtpsjTbdDdgy4DT5WLrlpHe6+DBg/yy1cgK/fsKtXlv1AF6qwEh81oT2faN+6bNep28HOCp6VFPrt1uA7oeC0/5Iejrl4D//tu33nqZINDfKg6r1FmhyjF/gW7Pgm7EZWfXgXbSndDWLgYoTZg9C8gicg3o9VvDk1e/5jmBZoN2wm3QilrCM+8SlVqsslDct43E5L70ifsmst20i7mUYc26QZ90u+nc3FGDm2QVCNEOPyF8WOY8BPue9cDPn1gXGmzYHmg9AO5Jd6DCrbMLIQvTuF3q+cnMYQ8pOnQLl8c+fG9T7woh2qk3Z+nWYyHaiZ3RpCDatG+YewHgCHLInp0HTLtfhedFUR577DEWO7vlllu8quPLly/n2Om33nqLY6k7duyISy65BFu2bMFdd93FRhgi2hS7TdbuN998k78bhYWFTLrJUk6x3GQgoGt9xdAuvPBC7i2JppEV/ZdffgGlCaOY70CFifbChQsxZ84cVl4jczixdeoYbU6pPPPMM3jnnXeq3d+9e3fcdtttYaERoh0WorS8QIh2+k0rqSvitcuAvb8BxT2gH39rUpEnf4Vwg2jv27ePSbdhjaeZIdJMKvRW4jqpjjr5ecCT06KeXCLWWtuh8GgZ8LBFWwM2L+d6FcnWlfJ4WIse1FxM/Dv0F6tyUmpk5Rt/HbSfPwa+fEq5imfVgV7UAm4SUfO1RJML7rirYSvuAc//Hq6RsoxThh3YBnz7cvVxN2gLPa8+POGs2oXNgFP+AzrwqI1FiHboWafnltLa2dZ/Co1CJ964OoJlonEKO04tN/pyuFe9q5TxD+1Sddkz+XAQ/WbAndcAZWVl5rwxIuhJJLfE2/IuRDuSWZF7YomAEO1Yohm+rqQg2tTN3RuBxXfVCIsDuYyPv055JEVZaC9HcdJPPvmk13OOjC/Tp0/HX/7yF071deONN4L2gvTv7dq18xJtuveKK64A5eGmQm7m27dvZws55demfNxEvH2J9o4dO3DnnXfytUYh9/WLLroo4EiYaFPnSK2tZ8+e+P3333HTTTfhyiuvxEknncQ3UcD4zz//jLPPPttbCblQ9ujRIyw8QrTDQpSWFwjRTr9ppWdee+taJdjVsi/0Y29MKqLtj7gv0Y7VbPBhw7OnqfzWERSyUtvsNthcDoBiofdu5rzY7I7/6zeVJBsAKYebIdncBw04/3Xob1wD3SfGm6zTGPkXFd+98k2V87p+S7jzGynl8bpNgc5jgB6T4LZlKvf1p2fUsKAHtGhTs5wyrFN4q7ZYtCWPdohnhV3GtyyHPSMTWHAVsDtwjvhwj5tGBzokhjh4NvR9W+BZ+2HNWzKygYk3wt24yxEPZaBnni35WVmsw8DWd1sG6xcaAm+mQjPCAQPwprKkpMTSwaKJauUSQcA0AkK0TUMVkwuThmjTaMgzj0L3dlfGazdsC3QarcLQYlyIc5J3NlmafcXRiFDv2rWLuW6gNFz0fqR3sWFgpm5RXbRug6XtIs9Juo8O04Ndwzs0Itr+4yRpc8o/9vDDD3uJNolakZncahGibRWx9LheiHZ6zKPvKHhTqDuBzd8CbQbXiIdMthHHg2jzYcOn/wZ++V9Ew2VLdnmJUhg/6S4VW+1xg0nCtlXQnOWAw4S7uH/rpz0Ffekc6Ft/rP4LuYR3GQN0GQ+tbhOON9fzGsBlz+ZNPX18DAGpXFcJMLfmiWyNGG2jBSLwrSrF1UKhkSIx2oa7Mf3X9wNNXg/0x6oHhAGJWLSDLw72EqFnasU82Ejsj9LBRFJsdmiN2kI7uAt6sx7Qj/kL3IvvDlwTke0ZD6M8o84RE08zrPh252F1cLnxC6CiFKjfBmjeC3phMdxZddjyTpvGaIsQ7WgRlPujRUCIdrQIWrs/qYi2ta6n3dU1iDZtKCigfOjQoZwXjApZtMn0PnLkSGb3FFTepk2bamDs2bOn2t/pA0obDApUl1L7EDA2ErXVXTRdZ5xO7WhujTy2yTxOegfR+8qM8r3ZcdCJZ+Y2El4LnMYhVD2cKuvAH6zcrXUZC731EGDBFeqW+q2g2ezAjnVK+MxqOfnf0H94U8WgByuZucAZc+Cp3xbOvIYcx24U6luOYy8wT4mFVCtZecgYdxXw6iXA/q1VP5E7eqv+cLnCEIEp96CisOURIzXhoKSx07zayH2fDiq2/6SE4OgUPjMPyK8PNO6k0knpOsf4WiE/RHLi/R00XI9prKkk/MWpvJwlsG9eBm3N4iqV/3CT5v97fn1oRKBJaZ/W+bmvwv3lHOj0vAUqXcdDH37REbFqG4cLtp3rgP/+XWle+BYK5RhyFvQBM+Gu05T7GK1lm96Dhw4dEou21XUl18cMATpQi9XBUcw6lcYV0T6NnnspRx6BGkSbEnHPnz+f/d2bN2/OPVywYAHWrVvHbk6rV6/m5N5k7aYk3lRo0zFx4sRqo6HNCyUQtxIDeeThiF0PDMXgaD+QseiRbw7eQPXFo4/Gxq+2zn8s5k3qiB4B+tjEeg3y8/TW9cCOtZY6yBm1Nq/g9FiY+Sjw2aOA4d5KMaRNOqtNt2mXcZ/mT38G+OIpRRKDFdrAnzEH+vJ5wJR/1di8ayQmF0ToTeszFSg/CCy+s6r2rHygWdfQAuytBwIT/hY1UbAEtIWLvTnJV72jYnp9ROBqVEPj7T1Z/SEX33Cx6ZUVxGMNGn3zvtsp5VvZfoDIJrn0VxazfbQAWUwv5f6v+whaToFKHxckj3zYRskjpHQfcHgPp7jD1HsU6d60NPCtGTnAOXNNz2HY9i1cwN9GEmYkrYdSpewfsPSZBky6BXpOYdT9jOcatDB0ubQWI+CvoVKLoUjI0GnfE8qdOSGdkEYYgWpE+8UXX2QVtieeeAL9+vULChEFiTscDtx///1hYaxNruNsFcrJgQ0eJQBApWE7ToND1iMrVpCwwIa5gD7mbH2jdEwl24BNXwF0uk8WKdqU5ZTb8gIAACAASURBVBWpnNUUK0GiTLDxnJJ7ZCyKuI7HAkWpIxoE4uE6Tv1hF/qyPcCCKy1Znw3BM23ijUD3Y6HfM1zFZlamxNZa9gXWf2adaGt24LzXoL9+OfTKlFyBN+5Tgc5j4SZCPu5aVDTvV001nl14SbTkt2U1b8+pC/sxfwK+mgP8tEj9XtQSekGT4AcZpCQ65W6UIysprdkkimI/uB344J/Avt/NLzWKbR93Ldz1WpoS1YqH6zi922kd8kENHRKQQKFRSGW+4wigzzR46jTmPkZz2ETfENqwGRlJDCFBCjmIpl7qLo/jp4WwN2oHPD879EFHiBnSyCOEvm/lB6CT6N/oK+Bxu6DT8xSsnDcfh0rLoyax5hcO2BuIrUyPTgK2fB/+1hPugD74TI4DjObQxN913AiNSCXvh/BgyRXJjIC4jid2dsR1PLF4h2qNiTa9bEkenazYjzzyCIuihSpkzSbpc5JTD1dqC9GmRU2iLtp3rwHfzVdklgpZqvpOh9735KBuM0QIaCNjWCeMeMBw2Ab7neridEaUl/fbueEtb2QF6XE899OlZfChQDQfdR623c6xd7F0240UD7mvdiIQL6JNaDJJ27MRePdmFVtponAKr+KeLD6mUbqtZ04Fyg7wnTZKc9G0C/D7d95/M1GluqT1QOijroA+V6WcCFjIcnjaU/Bs/BI6tdF2KPSxV1cTs2PSU7oDeO3ygGRfa9gWtkGzVMqwH99htXPSVAv4rmjUgRVFnVl1q7momx5TnC9kAa79m4F3bjQ9f9W6RGR20q1wN+wQ1v041kSbD3rcZcD7/wB2/hxizm3AiD9D7zSK+2iVFHsPjg/vVkI2ezYprOq1AJp2ZTLvdKpUepEWXnNr3oGdDnxfOMv62q9sWKvfEtrBHUDpfuhZ+dDHXAWP2wn9lyXBu3b+6zh0OHq3bCtjp7nL3b0GeOxEc7eRl8uf38fB0uhitQ2iTYcmfPjucQJOB5BTh8UM6ZA9kYYAc4OXq9IJASHaiZ1NIdqJxTtUa0y0b7/9ds4h9u9//5tlz41iqLMRCZ8wYQJatmzJ+cIuvfRSTgBOKcDCldpCtNka9NUzyroQqPSYBH3oOdU2tnSqTB9edu8gl7c9vypiTjl+M3O9OT+tkF7euGTaVR5SykdqpZCVe8yV8DTpGrUVRIi2FeDl2nggEE+iTXUTWbMTCVnyMPDHqtBDyKsP28hLoDVoBffbN8Le4zhg/RJg+TylNE7E1G5XQmjbVluDY9y10J3l0Je9WHXA518DuzxPgfuTB4kZk/Q5x7EeLq1u7eQ0S78vV+k4ArmwF7WEfeBpHLesr1kMzy+fASRiZRSKZaYUS51HcywzbeCTrfA70l0KvH55xMSOx0SxwNPuhyO7XsjczLEk2vStyM3KAN64Cti72Ry0lO6q7VFhDwR8K/MeHC9/BVjxauB2iloAY6+Bq6AZfy8iKTwXW5fDnpkFLLwxdOhDiAZI6E9zlXEKGT0jF/q0B+DZ9hP0374J0vdW0E9+IOFZE+idkb3iJeCdm8zDdcNqHPZkROUVQkSbPBBs+38HPn+iCufMHKD3VKDfdJ7DWHm0mR+cXFlbEBCindiZFqKdWLxDtcZEm9J4bd3qI3JTeccbb7zB5PrMM8/ETz9Vxf5NmjSJc4z5yqAHa6Q2EG06Ic7RnLAtnQNkFwCkxltRCr1kW3UV4JmPojxLffC8VmfabJPVmU7jfUuzHsCg0+Fp1NE06eV+ZEB9xCONdaM+jL0anjZDohJhEaKdPA95be1JPIm2gSkRBfqjETkm5WByuzbct4mINe8JtBrAqSxcHp09PbRfl0Lb+gNsLXpzXnItty6QkQXs+BmoVwyNDt18RcdCTSAR27Pp/bETcDmgb18L/cN/VSfcFCIy7T54VsyH7vtemHYfHHWKq5FE7wHCQcqbPVeFnBixyOT50mUcMGAmPBm53Ct2QSUrp8fFqTp0aLxZJ5Jt1YKaiHVK46PDBI2swaSeH22pTF12+PDhoF5AsSTafBDy9XPAj2+b7zlZ3097HOVajimy5sUo1MGx0TqlZ5nyLziyi0IeNgTrLB8c2HXY1r4Pjdy8v3/d/Lh8rqQYb61uI2DHL3xIrZ/9CtxLHgPoICxQGfEnuDqMiviAIKJOVnrCZC19Gnj/DvNVXP8dDmt5puYuWKVFRUVw7dqkcpRTakH/0mkUK7WHWsfmOyxXCgI1ERCindhVIUQ7sXiHai1geq9AN5BiJSX7Jiu3GYJt1FEbiDZtfjJLd6mNKVkZPG4gr57KE+dywL18vvrgDzodFd1O4I0ouZ7io/uADSFiyAjE4RfC02V8WNJLDxXXSSSbXMajLSfcDlejzhFvRIRoRzsBcn+0CCSCaFMfqR3DJdM3LRT95hvPSq6ZhhcLPR9Murd+D7x7C3BgG5NrcilHUQto5KYbKt6aKidr1KyngXrNgTmnqfhWiun89Wvo5NpNhRSzT7wT+p7f4PnpveqQjrgYjrbHBCRI3gMEiiEnwSZbJpBbyOSZSLSREozG7hvvmYzk2nfQbEHdtwl4+/pol1fV/cf+DRVNewe13seKaDMpzbQBz85S3xgrpe80uPudasqqza7pe34xn2qruCf042+JmKSRN5ht7WLYKg4Br1eq8FsZW+W1WoPWrNyvN2gLffDZcNP3NVCh8I1Jt3qtt5zDXte9Kdzi6ULNFu0fXlXPPKXyC1fIw+3vv6DksHXXf9+qmWgvvEmFpgQrk/8JR2HriA5Mwg1DfhcEhGgndg0I0U4s3qFaM020I+1yOhNtw/qTWbIF2mt/rfkRs2UwUUb74XB/8TTQdRwqek5la7Zt2fPmU5kcewNcxb1Dkl62dPz4FvD185FOVfX7SKF45n9Q5kJE7mRCtGMzDVJL5AgkimhH2kPqHx2OZWz8DNqb1wIkWkjEPbsOtHrFSuDq0K7A1ZNq8vE3c3otbPwK+G+lK+rA06FnZENfMV8R8GNvgF52AJ7lAdx/B86Co9sJITfWRKJ9tSOshLFEiks87+P35JJHgJ8/jl0zrQdBH39dUDfkWBFtPiT4fSnw8QPW+17YDPqMR0y5SnMY1Ef3Kg8Ns2X6gyjPbRSR1ZWJ/f5fYXeUAO/eCmz9wWyr1a7jXPT1WkA/7u/wrP0IeqBc9x1HwDbqr+x5oa/7BCCdBVIrp7CpBu2ATiPhdLn50CQea53mMHfnKmjk+r/nV2iFTfl51yn8omQH9Ao/F/zOo6Gf8VxUWif8HiysC9ejJ4XGtf8pvD+JNtyD2jOE88QVPaKlnJY3CdFO7LQK0U4s3kK044A3bQ7oj+3wLmikPrzvd+i7NgRuadRlHHftzqkHvf1waOTm+cpF5ntF6YBOewKHfU61yYJGD5KxGcjyOICXzg0eo2m+taore50Ez6Az2VJhtQjRtoqYXB9rBOJJtI3NpL8F22p+cbrfsOhxeqNDytVVy84HaBNOYmnsJeOTDYDiuUddDp3yba94Fdr464Evn1Tpt466APryV6ATER92HvRtq+ExrNv+AA88DY5uJ9YaCxbNGWGNZ2YGdp+NdAFSqBDFu5eVB3SXjxXRZkL64xsAxU1HUi54AwcPHgx7Z0FBAfDMKYDLJ/Y+3F2Dz4Sjy3ERrSXDVZ20AWykAv/aZda/Y+QeX9wdnl5ToA09G57yQ+owhTxFaBzk2dFuKGwN20Hf8TP0D+4OfIhVpxEw9iq4G7Q3Zf0PB4v/7/S802GP/Y0roP2xClrFQfV859aDXrcJ9J2UrURlIkB+A+DUx+Ao7hf0kL1adhHOH6gKvYfI84SILr8H6xbA9djk0N3tezKcfWZEJW7nje3ft5nD6Dy59cJ641nFUK5PTQSEaCd23oRoJxbvUK2JRTuCuVAbtnzYd6xh5VetZDu7VepbVlYXBjLqzsrjOEp3897weHTYVpDAzHxrLR/3dzgadeWPp4oJd6l4tsJi2LpNgOebuZFvwIL1hNzWznoJpQ6nZUXSVCbarEhMAnVA0go6WVs8tfPqWBPtGi7iTIJ/U/mL6VmhdFZFraDb7Py8kHu1GYsOheJkH9wCjUj2msVK4Xn3BmgUt13QCBrFepNlu7AYaH800P4o6Kvfh758LsdPa22HAP1O4VhvstSxS3m9Yo7H9mxdDVQcVrHZ/jmih50HR8exEZGjQCvKcIf3/83q4UO8Viu/Nz2lwIvhRTxr9CG3EFrzntAKmkDLL2IdDp3I3KFd0Clf89F/Qnl+04AW3dgS7QUsoBdRMUG0vYcRT0yx1kSU1lB2i8/Jgn3XLyrF3Xu3m2+fhP2adIFOaSqPvQGlpWVMLmk9Gh4ZRk5ZjSzYb15X/eDKvyXyRJt8F5yFraIincEGwIf0Zbtgf+cGaCQ8uH+L0kFo1R/67l/V4Tl5oww+E+6h5/FBd6CQDBobecRo21YBP7wJbPkB0N0AHRZ0HcfihxUupSjOruPPn+09yAvYt2MuQUXbo6OyaPO3c91i4IsnKaYGmHw3HHVbxuwdY35RyJXJhoAQ7cTOiBDtxOItRDvGeHM8dJYNdvrAPTWdP2wUH6Y7DilBI1/rE7VNH+5ZT6Gi3Qj14V90G7AlRKwU3VO/NWyN2wM5dQE+re8FV5Ou/BGkTUnmD68pNVh7FuznvAzPvD9DL/ETVIvFuEdeioo2R1n++KYq0VYpjnaqWPfcQuCku1Dm0k0RpljALXXEDoFYEm1vzPLu9cC6j5W2AimEBypkcW4/HOg6Hm5bVtjUObzm1n8M/PQebG0HQWvSRcXgknWvohQabbqbdAIy8xThXrNYec943NAoLVhBY96ka816QCeyvvYD6EZe6NwilTaMSHrZfrh//VaJgFH6wUm3wdGgY1SbYHqfeVMGkfvrtp8AsmbR/9N7i4TYSDDMrnJpxyL3cqQrRMVnbwDe/r9qVWjNugL5jQBHCfTf/XIbZ+XD1m08tOIewNaVSl2e5oDwI4sjufh3OIZTnZXbcgMSs1gRbe7/hk+Bzx+zDgGFAp0xJykt2sZgeHxZmbCTMvYvnwIf/AtwhLHA06ESZenoMQmeoy5EuaNKP8AXJMOSjFcvMSc0SM/cjIeDklzrE1D9DiKkWY59sH14N7TvFwB0SFa/NXS3S1m3B54BT9cJbA0OFDPuFaz74Q1g2QuBu0PP3gm3waFlsxXdtXox8L+HAl9LueFnPIzS8ujSfHHaQ8rCQPNHZchsODpPjOodEy3Wcn9yICBEO7HzIEQ7sXgL0Y4D3uReZ9+7CXjqZKCwGTy2LD7A1ehEuWQnQKSbCqmy1m0MfdBslHedpHJYUnzWbnIRC1Dy68PW60RodZsB6/+nTrvLSoDGHaG37A9PhxHQsvJY8Ajv3wmtZV/Yxl0N9zOnxWGUAHqeAPeg2Zbd6FKVaLN75uq3Va5gKsffDEfDLrJRiM/qimutsSDatEEni7P90A5lpdniR8RCjYBUuvvNUJYlpzPoYRVbWh17gXl/VrWRKzKpj5OFnCzlpCZ+4A92DdeadlUq5XlFsLUZBOQUKNK/9UdgwxfQg71XyCrecSTQfSL0Oo2hr/sI+rhrUOpwWfZWMYZMzwq/z0hp/adFyqLmW+iFSNZGsrKTAFXX8dBbD2KyHW0caCQLh4kciXxR7uzKorUfDlu7IcqKSrHWe3+DZ2WlondhM5XKjLwBvngCoDkIVGiOxl7lJXrkdeRbYkW02eqrOYHnZ1sffveJ8FRaR8PdnOgYbd/+GNk47M7D0Mi6/cVTwJr3a7qSE+ZEDjseA73/TLib9uBDjmAeJDz3O38CFt0abvhVv0+8CY7G3eL27qfnh94t2uHd0LZ8B4+jFDrFmDfvBbcHPJ5g4oJ0X+aOVSqmPVRp2Rf6sTfy4TwTdgo78PeIoEO4CX+DM79x1BZ8/n4e+B345AHlrj/uGpS5bREdVHvfL5rG74xo8rWbn3S5Ml4ICNGOF7JBPkt2OwoLCxPbqLQWEAFxHQ+xMIz4JxYvozQ2lSrC9NIn967cLDu0Z05hd3AjVprJNuXFrYyXon/nP8POh6PDGJUK6KN7gI1f1my5XnPYB5+hRGhog1HhYzGr1xx63WbwaHZg4CzY+05VMZr2LGjb18D91t/is8TJSjbpVlMiOr4dSAaibbj6+ru00nwY7qyGerLRdyY9ejmw5FFFYkb8GaVlZRGTkfhMSvLV6iWklboBRDb8CUeiex0t0fa6ZpJ1hgS0rCo9GwNu2B4Yfx1cOfUCxlp63XWJQPm7dwcCjXJZDzhFEUCyblIcqpVC7uckCNVmMEpKSiyLPhkikPZDO4H/PQhsX+ttnfKBa0278B/OM+1bdI8SoSruARcyGIt4CE4Fg4Kf7YoD1fQx7BOuAygdGuVbrtcCmPEQ3O/eBtRpCPtR5wJEuo1Dt1AYN+0CT/M+0I+9CQ5kVFv7sSLa1DyT4I8pW8XnVmacx+XIbWTqmUy06rj/QIzvLmugwANQurtfl3E4BZecQtYv0FsN4hhg410Tai2p+HaLbvdRusObmSAaK+0vjP0C3WMm1ILXwcL/A7avCd/MtPuQ0aQjf8Np/2GjDCi0fsjrpKgl0HYYnC5XzIisEXpF8xHpd4APlTI04N2bVfrAiTeiPKMgIrG98ADJFYlAQIh2IlCuakMs2onFO1RrQrSDoOPNc00KqKReSimzyFpNbp3kFtruKP446vMvVWIm4cqsp1Buz+e4scw17wJLn61+R24h7EdfCHz3mvrjX8j9klxHaatKJL790dBG/Bk6uTCSK+in/1aEnkh/uL5Y+Z1Ou095xJTLoW+14Yi24XLqq2hM1ohYpAeiOmljxRuYXT8Dm1cod9aDuwB7htpQ0x+yhvhs1Iz+Gyfp9HeyvPmTcSvw1ZZr2WVw8zLgy6eBhm2B0VcecZf7aIi2l2STW+c3L0Y/jWTdmXQbnHmNAm5oGb9vXwLIFTREIbdyW//pKrtAmGtDVlTcA/rU++Bq2NGSWJGXZO9cCyy6HXCpFEVaw3awdZ/AAkgsQvXHauCPlUqgjQqFzzRoAzTvzc8dxZC67LkRp4SKZELYfZhSIJIXku7hKgIS7UW3wz7iYmDzcuCzR8011aofPB5Ap7zmJ91V7XAulkRbxZmXAa9dDpQfMNe3ftPh6TfTtKil1y05znm0Ax1I+w+I3uGcBq/y8Jq/uZWpuOhbYfbdzBbg7+ZZy9PdZxqcfU+JGQE1N1nhr+KDufx84Mmp4S+mKwbOQsbAmaxcTpjRGvI1HMTqu2uuM+auYg+Ebd8Di+9SN0QhtmeuRbkq3ggI0Y43wtXrF6KdWLxD7tv0OJsUUjG9F5+m5uYAnz4E/PxJYPxa9IZt4o3QNy+H/v6doWeUCN3Iv/KJMtdt15VCuE8eTVv/U6BRvtoP/lmzLkr306yrsv5Qbl2KxSZr99BzoA08DfqaD4CP71exmqRcClQS1ioV0oiXHMWNTbs/phZt/ohmZ6tTdcoXTKVxJ3YrjZbYelVP6YBk6ZzwhyDtjuI4Mndu/YRb2CKekyS70WuRfXpGlYvnoDNQ0W3SEXERNuCJhmhzGqj1n6p3QKwKPZ9T70W5nlGDIDCBcpcCL51XpTrs32791rAPOROg/MDkLh5pIXfuFr3hgR36hL/BXdzbdGgIW6v2bADImlZp4bf1OA5aiz7qgPCHBebUqlv0Bib/C54mXfjdEosDNn84DHJmeBXR72wJXHynsmDTAUEA13H9wDbYWvcHXrnYnBcDKcQ37Qo3+ftWkgJ3jxO9mMaSaFP1PAcHtig3aEpNFapQqMCw8/ndZiU/tPc9Sq7GpAUSqBS1AMZeA1dBs5CpJ/1vpfe/l+zRN9DlAAhDm3JvNtSyI13ege6rERJkpvKBs1DR/cQj+g4L1E1+39L+5OnpZkYB9D8FGYNP9xJtczcd2atYByc7EyB1eLJoj72KNRDMHqwc2d5L64EQEKKd2HUhRDuxeIdqTSzaAdDhzZiZ0/w2g2CfeAPc37wMfBsk5UqTzsDxt6LcpU7f6SSZNkq2X5cCH96jNtV5RbCPvAR4+fyaqqCaDVpxdyAjC/oOP+XgjCxoFy8E9m2F/uI5aiQUF0riMJk57NIedWk3DPqYq2JGtPmgIdMG/PdmYEeVyyn3kzbrx96AModKS2K1qAOSXBVPuXqR+dtJ3XnMlfC0HMAbxnhs+s13JjWv5JRARBLJzZPKiD/B0XaEKVfVeI04UqLNB0Flu4H5f1VeLLEsrQdAH/+3gJZcJvcrXoG2fyu0Ru2gkVsnWYKp2OzQiNhs+JJTeen+8dBW+li/FR/KMTEk0j35n6YUllW2Ayfw6l8AUlzXbLANPFWpohN5NQTYzPaFxNKmPwB3t+ODij6Zrcq4jt6vNH/szUJWa3KPzcjhw0d6/3I4yZZv1Qa+sviLodlH/UWRS7PvkAZtoOc3rHpvEB6zX/AKS8WaaFO3mWy7y4FvXwbooNVfgLN+a7Zk6q3UO80KyTZwoY0aWYLZ1ZiU8OlQlEgPeQM17Qp0HAGn07zLcVXqp9+AVf9VB60+h818UNxpFNDjBLgzcmJ68MnP9OEdwGt/Nb+kTv43HPlNIn6H+Yac0Tclkm9aoM56DzbnnFodv2AjO/piZPQ8LqWINg3FEKCk/z9Sug7mF4tcGQ4BIdrhEIrt70K0Y4tnNLUJ0fZDjzeTzgPAXJN5ro+/BVqL3mrju+odJZZEmx5S/Ow6Hug2EY6KCrZG06m6Rr+VHYC9oAFbpj1fPcvuzLa6TYCFN1TvjT0DGhF1Ej8jV0za5PgVbewVQK/J0O8f6XWH5M1z067QM7KjJ9v9Z8LVe5oliwV1MZjrOB9ifPYfYO2HgddthLm7vZu4SOIXjZ6QoFGboaZdLKN58NLtXt74l/wBrPuQSZzeXZGnI3loEQnR9rrNUmwgqUzHo5DwUHGfai6phkt2VmYG8MNbSghx58+KvLqdfNimNeqonvFOo6CTZ8vyuTVVssP1NysfaOZjfaXrSXRtxkMoq3CFJAP87FKsOpEu4v59p0EjHQN6b5mJLQ/UtzoNgbFXw9X3lKjXi/cdQOJslPqQYtipkLhcm8Fs2dOLWqnQmwVXBhakzKkL++i/AmZJDB1sFveAm/zGSfTNKOOu4fzHZJ2NB9GmZuhbxTG3dIywcx2w/w8VF9+0C/S8+jyX5CEUrdMatWO4cFO7VB/VbUVB3usl9tUc4MeFoVcppcMc9deYHnx6n+v371AhAeEKpdqa8H8RhTYQXvytp7AKeoapkMdWRk7UHltGt/lQ7qungdXvhh4JHWad+SzsOXVYj+FIvo/DQS6/pzcCQrQTO79CtBOLd6jWhGj7ocOxXKveBMhKbab0mAT34LPYYsAKvD4iaIYbHKe/cZUqS6shgkZ5PtuT2/JZapNKG5Cvn1Mt0uaNUsfUbQLNngGdYsCDpe7qMxXa2Kugk/Wt0h2S66DNSrNuVe6MZsYS6Jqp98BR0MLyqX4gos0xkuzyNqPqUMC/TbIunzOPLehWNoi88fjx7SoMIxkvbcin3YeKOs2Szl0wkuEk+h7a9NO807zRJjwSK1os+xwJ0WbL1/5NwFvXx7Ir1etq2B76lH95N/Fey+Gun2Fb9hw0OqwjkSMKFSH6lpkDrX5LpRPhorRZmUCvkzh3tr7xK+i04a68NmSn6b6mXeGxZdZ8tvrNgKffKUEPmapc21UOanIVt3UZrWKFKd1VNKV5L3hGXwlXu6NNu7D7N+eNqScsyFoaqNC7eczV0NoP49zXTLb9BO604p6wdRphPtc2kdqs/JoHmv1moKLXNH6PxItoG0MMJPZIRNjK+zOa6Qt3r/cAhMKiKFuG2UJku/2ImB188rPtKVfPdkkIAUHK+HHSnXDYcix/99hFHS6VocBIcWWMl1T/jzofFciI+vvCzyOcwOuXV3kRBcL16D/B3Wk0H8gI0Ta78OS6eCAgRDseqAavU4h2YvEO1ZoQbT902DL39ZzwJ8XGfcU94Tnu5qCbAeUqbQdevwI4sNWvNR1avRawz3iQYxt1JvckW66sBvQ/bAEPlVKo20Rooy/jdD2+7pDcUMN20POKIrdqV8ZnHz582PKmLRDR5rgrcj194azQT8C5r+JQmXlLDG86XIeAuRcGJ/BmnzmyPJx0V0SWDLNNyHWJQSASos0HNqTkvfaD+Hay0i2VDiPonaP5xMLa7TYlIkbWMF2HVtgUGrlAEzn0LZVpefTyg9AX/zP02icX9Cadg4eU0AHXmc+jzBnYxZXfiysXAN/O5TAW++jLlRL7+iXR41SvGHpRa3hmPIxye52I4jBZTG79J8D/HgndHyLbJ/8bWv1W0DctrRJbqrxLazsEtgatgTevDT+uBm2BOg0qD5T89DB6nQhn/9PZayHeRDt8RwNf4UvQDZExw1odS5LOz9RKyvdsVVRQUwefBcVRE1MDAT5I9ziAzx8PrNxOQqfDL4TTlm1ZBM37rX/z6uDaIBS2MflfKHO6o3Yl52fy8C6lmm9onRgDped92LnQK3NxE8kRoh3pkyL3xQIBIdqxQNF8HUK0zWMV7yuFaAci2qT+u/JNc9i3Hgj32GuDWmL4Y/gjWcgr8zIHqNU2jOKrdXi+nFPtV5tNg3ZwB7BvS/C+9D0ZetuhrPrLZN73g5tXBDRqH7lVe/z1cDbva3nDQZ1NpEWbN3JLnwluyTI3k1VXHX8LHA07W7ZmWG0mHa7nmNdKTw4jnUuyjMsq0bYc+xjNQAfMhLv3yazZoBGxX7O4Wm1MtilUZPcGJoUa6Rk4fNL9GVdn1wFO/Af0/X9AX/KfwD0id+LGHaDbsuAJZfkefgGcHccGfN7Zbfzt64Ed66C1Owq2RvS+uTwaBKruNcTEOoyEPuISy3oQ7CmTnwc8X+kdFK5X7YdDH30FHx7aSBmd4rUpVSIdbbYeAFtxD4CySQQrRNbpfZtXFJhk030+itXJRrSJEHpTZ9EhLh3gkGWfrI8nTAAAIABJREFUwgDIZbpO45i5nXtzf5OGSCTp8Yp7Qj/+lpgefHpdu8mTjCzspN5OKcPaDIaeUzdi927+Dn3zAvBDmL1D78nwDDwjJpZ6tqBnZSl3eD6Y8wA5dYFOI+HJzPdqjtSrV0+Idrj3gvweVwSEaMcV3hqVC9FOLN6hWhOi7YcOf7g2fGo+rUv/mXD2mhqUjKoN6t9qCn/5tKt1HQ9brxPhnndJzc02bYIO7Q4+h2OvhsfjhpaVB41SCJE7pLGZpljtln0jI9pth0Afe03EG5xExWirTXY+MOc072Y56ser27HwDDs/JhuhqPuSxBUQMSVLom3bjyqXcoej4cpvbDmeP15DtEq0lXv0IeCl8+PVpap6DSHFle+okJIAxaZp4MM2ZylA1tdghUSkTv439K/mKCutt2icbxiFxZWZCMKIIxLRGHdtNaJLGLInSmVaLN3lhH3MZerg0O9wICrQWg+Am8QbZ7+IMrdmydrHLsEHt6p3n5lC1r7z5vPzTRZOu6NEhZxQGseiFrAPOiO4ojMdXpIoXUZ26PfqkLNR0eXYhLiOmxmycQ1bdDWP8kyg+F5KD+lfGrUHBp0JvbhnxEJq1dpbvRBY9oKVbla/9tTHUJ5ZGJGnQ6hGfUO96Doj5CWSjlYd0pn4DtHB19kvWw6PCtYv+gYaubgNzwTylPEVX0sk0TbeGRQPLjHhkaym9LxHiHZi51WIdmLxDtWaEG0/dLxpJUhBOZzADxHZ055AuS0v6CaAiTZZfvb+FnweGneCfdo9cFO8464N3uvYqsVK40HypdKmb9ZTcH/xDHB4N+xHXwBs/RH45IGqtmgDa6SdMbvuSLF28j9R7lKxtpGUYETbquq4EfNu9MHfpZHJkWMfMO9PkXQz8D159YHTn7acOzx2HUiNmhTB2QIsuEp1mCxip8/BodIyy6EG8RixVaLN49m+Enj/H/HoTrU6tY4jYBtyFtxE6kNY+mgTbSs/AI2EvUhlmmK0A5Wux0LvPxP6a5cp8S8SGSOBRXsmh46YcgUmbYhzXmHvHEMAix2iHSWwk2v509OhFTSGNvJS6M/MZMVjU/WaQbNVf0W0j74IFe1HWXIV5nnbskylPTNbzp2PQ2Wq/14LJympb1gCe4tewPzLVB5weseT3gWJyJFuRkYWk4ewIfGznkK5PZ/fn8li0WbvqkM7gEW3AeQpFa70nQZ9wKyoyDZ//6i9Ld+Fay3470POQkWXiZbWROSNRXYnH/hm2ZWInply9lwcrnAnjIhGQ7TJ+OCrvRFKPd0bj0+6DfkNUOFyJ/W8mZkquSY2CAjRjg2OZmsRom0WqfhfJ0Q7AMa8Idm+GiDl4VDlmEvg6TgqpOVTqYM+FTpVTPeJ0IZfCJ1cv964xtsiE+3dG1Xu7EBl/HUqrYwh3JZXH/ahs4HN3wKfPKhEcGkDa4VoN+4ITLwJFVpWVB/IYESbhhEqj7ZB7Ol+dqslN01jV1spNGekSqEPPl2XveUb4KN7Y/u0XPBGzCwOse1Y8tTG87hpCeDrsnzWizjsNPK4H9m+RkS0/ccTpyHYx1zOXi7uVaHT0LFFu2Q7NNZ30NTzQLoNbkp/p6tng55zItenz4G+8Qvo237iXpsm2MYYs+vAdtYLyr187UfAxi+U8npOAewj/qSIdqdR0HoeD7x6KVt1DRt51IS7VT/wa6pSXJLIvtnC63BvZW5vUzdpwPmv45Cf9gQRbnqfsJL3pq+Aj/7lrU3l4ja0M8I00moA5ycnQUcqyUC0GSN3mbL6lwb5ngQa1oBT4elzcsTePZz274WzgbL9pmYm4EV9p8PZZ3pEIUyRN2rtTrZo5+UAT5nMbX3efBwqjeFBVZjuRkq0eS+0fzPw/QKAPOYGn4kyhzOox0k1LQc6sD/5ATmwtraUwl5N+yL1PopB+tawrcXuAiHascPSTE1CtM2glJhrhGgHwNnrEktkmwgr5RH1LRQXefRF0NsOC5uShjc45XtUzF8gyxVZTKY/CEdOA7as2H79CviQSKMOch3VSB31wB81ezl4NtBtAtyfP6ly2holvz7slNuW/m3pHCAzh4l22JcybeD7TAMGnMbpyCgtTTQlFNGmeuljweO12bgZwpz+0Jg5bm7baiUCR2OnuDN1EVCnscq33aQL0H44tIxMFrXROSd5DAtvxEvD4xbDJlOtKq/3x3//rlSye0yCPvQcyzG28Rp3RET7ty+BTx+MV5dUvYXFsB91LvDh3XBXOEK2xUT7QNU7oLqHhxJM9JYBp0Jv0Q9u1oPwE+cKN6J6zfm9QTmn3Z89Vj1cJSMH9vFXA09Mhdb7JGh1m3LfuWTmqDzV0W78DM+b5r2gH3ezpTXE6zAnW1kTA7lC+489TBteBXNa16T0bqWQW/r0f/P73HiHHmmi7U1ttfgugFKfWS1T74WjoHlE3wQm2s/PDu8dFqpPfU+Gs8+MpCba1H3lvXZZcCE0Y4wkxDftAUtr3OqU+V8fKdHm+SOR0YM7VZWDzkBFt0lBD+FZlHDJQyoMg54FEjaNQEw12vGm4/3efanuZmydLvM57JMBDyHaiZ0FIdqJxTtUa0K0g6BDLzWKZ8uw24Hfl1e5dNdrDrQdAreu8YffTAwSf3yItJPoToWPoBG5I467Bu6m3Zmw0waPToRtJGj2xZPQdq2DzeVQpNMo1P6w8zgvp3vZS0DJ9mojYCtwRia0jsdAo/za23+C/vOnTIRoM1yjv7mFQKfRTJI8ufV4TLFIyxSOaBud9uJMfHvl28APbwAOZQkKWigenYh2fgPYekxkd1b912Vwf/tK1YYgqmdMAy5YIBZtExjSQRL9MWIDy8rKYrJ+TDQd9pKIiLYly2jYLgS8QGs/HLZ6xcD3r4X1Ngl52OZfe5POwAl3wP2eRdd3ItlDZgMrXmVBJTfU4Ze3UJz2xBuAeX+G1mYwNBIv+8xHeI021Fn50Mn5hNy/rRbORd1T5aJu0Bb61HstkxD2HCLl9u/mh2/9uJtR0bhrSI8dPiDVKwASgNvvny0iRBMT/gZ3i37VxDGPNNHmsRzeAbz21/DYBLqi7VDoY6+2PCdUFZPPhX9TGg6RloGzUNH9xKg8rCJt2sp9HP++5dua2T/8Kxl3DZwtBiT04CAqov3iuVVeEANORUWPyUHngtea8yCwdrHKL99E7W2kRI8A6wft/AlYdCuQ3xCY8RBKK9xJ870NN0Ih2uEQiu3vQrRji2c0tQnRDoOer9AIXUpklYioFTJKG34i0HbdBWz4DDi0h9PCoP3RcGsZHAPna3GmFyoLtZRsh/2P74HfvwNc5UDz3moj+sdqeH56vzppZ6XvyrRAJKBGuXdnPw/PzvXQiloqJVJy9Dy8R1nRiGA36uBVziWX7UjjsQNBaIZoew8WdqxRceWhRN+okfqtYOswAlrDtirGcPsaaBWHoeXWAyg3bsOO7DrrXv1eeKtCqHkn8agZD0e0sYzmYUzlew2inUxjsEq0lX6ABjxjMs4ywsHauo6DRgdoGz5X5DJEMZV5wLifvGPOe00RbbMKz1n5sB9zkTrkWj5PhZoEIMus/7D6XWiaDVpBo5qhGtR2dkFklu2CJvxs8zu1WXfok26z/OyxVTs3B2Ar9KrgiPabwbHsZlIW8saWyPbH9wO/rwg926SXMeYKeJp0Y2Lh+z4/0kSb3Xm/fxVYYeIQItAoyZPo3FdRWl5h6btHVXHb380DvnstwqcFwNR74ChoEZFFPfJGrd/p9YRYPjc41v2mQ+9/alhPOOuth74jUqLN87dng0rNRqKLwy8ImgLQ6IERgmFkoQjrTRfrwSZxfYYnH32byOhhxXOQ30er3gDIoEBlxkMoy25gSTjySEIjRDux6AvRTizeoVoTop3AuaCNvBF3bFiXgwmL0IuYrqePVqZNB75+AfrBndBpExnA4ssku3RfleX9uL9zqhIPWb3JjbRec2iUH7bvdHiKWvEL3mzOVHpgqS9G3LQBmW+stL+lPBzR9m5KVv8X+PLp0LOg2WDrcRy0Fr1VCq+Vb/GBgZdfkPs5CcY17crpgdCiLzwbvoBn1buR5dXudRLcA8+Qk/gEPhvxaMoq0aY+sAVu/l+sWTEtdt7W43hornLoP38cNsc9h1NUHOK0WqbK+QvgJs+ZYKJpfpXY+k+H5iwH3r1FuXq27BPQyq61Pwo2SjO2djG0jiMBwsi/UMx2pRu5qb4aFzXtCk9mniKnUSj+szBidjawYp5KsUSHGUYhC9CQs6C3G2ZJ3MsrlLZlBbDmQ6V/QTHyRilqBXQeBXQ7Di7Y2ErpTyyONNHmNU0Cf9T3SMuUf8FRt6UlYkBN8ZxU7AdeuTiyluu1YEJB8e6pQNi8YmDbVgE/vac0Dqg078VrW2/Ww9L6iwy0mndFSrTp/UMEj77/BnGO5YF8rMaX7PXQujC897SNXwK7fmYvQkdmXdPPFD9LmksdiBY0gt7jBFMHhsmCjRDtxM6EEO3E4h2qNSHayTMXQXvCp8olW5RabABhNDI42ChuhxTHqYy+AmjeE+7Pn6ph9SbCjRkP8ws6nNs7kWFOf0PhniSMtGu9yrlKRJ8s4g3aAk27Aa37w1WpLmrUGYpoe0n2DwvUSXmoQqrLg85QIlAf/DMgAeL4btpUk9W/TkPeTGPALHgcpfBQWpkwVsMazZ/8ABz5TU1/AFNgCdXKLkZCtJWYD1kNXo4bZnxolFMHnuWvhlevJk8Vm6by5JopRLQX3w24TWgs1G2mYsUpBpNUgkmpvEGbwO7smbmwj70CGoW0DDhVpb/yJZxG38iqrSmxHlOFlOqbdK5qc+g5qOg8IWI3YXrv0DuLIGMhSTp8JLJW2MybGzrce8+/37SOyCXWmw6Kwn9o7Fl1eKxkiSfyEezQ1CDaxmab6k9k6iMm2m9cpfCItEy4Ho6mvSN6J3L7FGqw9kPrrR97A5zNeiXUzdp6J6vfUWO9+KQOMw64o23D6v2REm2r7cj1NRHgb4qrjN3v7fVbwv3ENHVR9+PgHHSWpbVtZIOg22ktWfGsPNJzI0Q7sTMgRDuxeIdqTYh28sxFyJ7wy9rtAL55EVjzAUDEurIoZeJtQEEzgGIts/LgXvZycKXX8dfB0axPyE2T15Kz5n2VMzdU3DSlvRl6NovDkUXHUAOnDdaBAzVTk3HM+m9fAx9WqfoGG7ytzxRo5PZOuch949t9bmCiTX/ndGw6b6z1olbQScm9dD88379hfpbbDIE+LvL84eYbkivjjUAkRJutBqgAXjzHvPu1xYHY+p8CrV4xPL99C42IJgmK8c6pDHp5CYeG+Ko0s7cKpf0j0hiqVKbnci+6w5Qnh63nJGikBm2IvzVqDz23XlAru63LWGjkGUMaEJT7e/2Smr2xZ0HPzDVPtMlVPDOnqs0znkW5lh11GIsR8kMdNOu5Y2Ya2cOgUsAxoOaFXyV0fVFREb9rNWeZEnek+S4sBnno07/H20KoUmzdqsQlIy0n3QlHvbYREW0OyaDUV29eqw5qzZZeJ0EfPDulrHZmh5bo64RoJxpx1R6nfcvOBF46l78n9lMegr7oNnj2/AYccwmc7UZYItpHZhSxaVWIdmxwNFuLEG2zSMX/OiHa8cc4Zi0QCeDUM2RNIYG2fVvINgJ73cZATiGn/NF/XQrPL0tCk4Qw6VJY0MQOlU/YcH0zM4qOxwAj/4qySvfJQESb63YdYmGlaq6dAerXGneCre9U4NW/hM37ymTb4wQqKoVXyI08rz70Y2+E57sFKnVauEKE/uQHUG7LjfvmN1xX5PfoEYiEaFOrLKxFFu3vX4++E/411G0K+5R/QiM366+fZ/ExPsSi9FyUzaC4J9CsG/Qd6+D5aTETbg43oUOkcGu4ZT9gwvVwv3enqX7bJ1ynhJvIpdieCbToDbfLrdT9AxWbHfYRF0HLrgON3j8Lbwh8XW6huVRYlP6noFGVNbvtEOhjr7Ecn21qsH4X+YbxGPoChnI6HRSatsiHaNxwI87avhLOr56vblEmN/1Oo4CBs+DKzGd34ngVPthcTut5QeRNnDMPpRWuiC1oKt7dCXxwV+gYeqOH/U+B3u+UI+JmHTlIyXunEO0jMzesHZGhA8+ezh2wjboU6Dyave0ozIb0HKx62ByZkUTfqhDt6DG0UoMQbStoxfdaIdrxxTcutdMD5OuGSJsYymWsr/s4sDunfy96nQRn/1kBT1LZ+kCpct66PvzGPtDoKhVqHQ4HaIPnb9Fm68pH9wAUpxSm2I++EFj3kVJDDlMUN/BxISdFd4r9bD1Iic599njoGsgaeMLtcBW1ieumN9w4kuV3IzaPSJ4h2pJqG4JIiTY/A9lZwGuXAfvpMCs2RWvRB7aRf1aHV+SZQtkAAomWkTjYkLOA1gPgWTEf+s71Suhw+zrAcTB4Z4adC71+G3MeHCSCNvYKlfeXDu5IZDG/ftiYcXIvtw+/AFpeITSKuw0kEpZNLtX20GSVQlgKm1V3U5/xEBy5jSKympqZIVrLdNBH88sHF3TAQAKMlD6QXiAkqtiqP/T8huyVQ9bmSNe8NzzmmxeRuXph8IM7CsE57ma4ClvE7b3Dh5v7NikF9UhK897Qj/t71Acg3gwF6/+nskvs3ezXGw1oMwjoNx2e+m1jlgEjkiGn0j20FzBSZQZ7VwvRPnIzyge3W38AKJtMzxNQ7lRiupG+W47cSKJrWYh2dPhZvVuItlXE4ne9EO34YZuwmvlFvuRh4OdPzLU5aBb03tO8L3pjU0k3c12Uf3vVO+bqCnTVUedD7zaRDwN8iTZv+Mp2A69eEr7ugsawDz8f2vNnsEutbwlmbTJyDGsUn0pumo07KjfWKfeqfONGLlD/1us2A8ZfC3dhi6QTQDNcVX3zJxsuq7GwugWbCA5V2P0L8OPbbHnztBzALpypVCIl2jRGtsDRWn3zutDk1iQgWsu+sA2axUI27l+XwW7PUCSecmQHK13GASP+BM83L0PbvREahY6QWzmFR/gXexZw5rPwrFzI1vCwpagl7P2mA8+dDvjHSYe7ubAZMkZdyoJuePykmjmS6ZkjF/JAcdpkuSdth/yi6iR70Onw9JoStzXmJXmbvlJiiqG8A4paAD1PArqMQUWFM6J4cbYib1jCbvlEgkK6h1PozYyHUebS46IgTM8Bvdc18kDY/lO42a35+/G3oKJRl4hw8K+s2mEHHRrt/EWFBNVpxFkwdMoP7HR6xTqtd7Z23eE90Fm1UGHZdgg8bYbWUL4Xon3k1oURs089IIIdTMvhyPUwMS0L0U4MzkYrQrQTi3eo1oRoJ89ceHvC7uE2JShkRjyFScFvX6kUWSaK/Yyn4Tm0F/qPC1W8YO+pcOaSNcuD7PK9wLw/maglxCVkHT79GdhzC7B//37vhbz5XPYcQO2GKbYOw2EraATtnZuUxY2sTpRCyEaWMnVzoI28l2wTGcnMgV7YnOP8PAd3Q9/wefVWyVW392Sg12Q43Z6kiZUyVN694kt0aEBiVaQOTfNFm9LKOFhDhCnWoihKQOlqYPcG1ebZc3HwYAhrargJPQK/R0O0qbt82HCARAhvAUqr1rHloZC7+LHXAV+/CM/m5bxuyQHDpulKwDCQqJjRSNcJwLBz4P7fo7A7DykxxECiVoPOADqMgHvJo6a6pzXuAFvnMSoso1lXCkAJRN+D15Vbjy3iNhL5oTy7B7bSA6mup+fOnl39+SSLMa3bwmJWN6+W1qzjMdAp5CROOdh5Hh37gY8fALbRQYXJQq7tY66Eu25xjRSMoWrguMy8XOD52RwWEJZoU2X9T4G7z/S4HfR5D44WXKneI2ZL1/HQh18U8zhpejb9s1hYTZtpdgipep1X2M+mBPdI/8TfCsrzunEJsOSRqmFOuw+OOsXVPEOEaKfqKkiffgvRTuxcCtFOLN6hWhOinTxzwT3hD6djn3KZbt4b7sZdwm6+eGOXnw8sIGXZDSFHpPU4DrbBZ8L93OyqGOlKJXL6iEdtzTZaHzwb9n7TvESbNlZE3njzyaJlwQtvwrqNhbZrI/CVf+ovrXIjn8UVBLdukye5DVrLftB7ngC9aTd4tq3hfyPxJTTpyjl7acNPbu6xJqqRLCt6MbJrK7kJr/9MueX+9o2yzvuXzFyg9UCA4nI7HA2XW+XkjNU42LNh5ZsAqbZ3HQd9+MVRu45Ggkk090RLtKltJmkVJSqXcqj8zME6SnHNk24G9v8Bz5JHq5FZFjHk2OtfQg9zwt+gZ+bB8/0C5UJOhy4kpmOUxp2Ak+6C+6vngP2/m4OsfmvY+88A3r+DYwUjcmO0Z8E++lJoGVnQKNZ77yalkWDLUK7jZL2m2O+sPOWWTblj3Z7qhJ6ezSFne0UUzXXe/FXew5J3bwbKagozhq2JPAWOu8nUe9ioiz13tq9UGheVKa7CCp7RIcRpT8T1MIsPOikn8ru3BhWWrIZH+6OBMZejrEwJXKZyMcKt/MdgpKhMxrHxO5jESOlgeshsuFsOqLEX4P3Cyterh1eNugyOVkOEaCfjpNbiPgnRTuzkC9FOLN6hWhOinTxzwT1hS+KHdwOblgKVKsJmLIn8wSWL13//HjyutEUfaBNvZLdJnWKwfcv5rwGaHXj+LJWTOtrStBsypv4T+/YppWRWc3YfBl46L2TNbOkjAtJqALT9m1XOyEAlIwt6Ri502raHyCSkNe0MHHUB9C7joZPibUFjtqoRIU0mIRKev6xMYPUiNeYwhxHVICERt/6nAN0nRuzq6g+xNx+spgyVhpp8tMsikffHgmhTf71ux5Ti7tu5Sjk6bNGATscA/U+FvbAJ3HNmAY6arvdMnA/uAvb6EGf/usmVefpDcH90H9fB9xBpJMs2WYhPuAOezSugB1IBD9bPNoNgH3cN9KdnREayjXrtmbD1Oxm2hm3Vut34OVDQBLotk13clcAYrSEPayh4C4VrDD8fevM+cbNkM+F1lqgDSCvPkz9mJFw2+Z9wFrY05fXCz/Kqt7wp4kxZtKnN8xfg0OHDMRFiCzTt9DzQwYO9bB/w1TMAudEHKhQ3PvhM6B1HpeRzbwyJYvEJe9YzIa8Rel4oXIMOLukApW5TdlfnLB2VKdrCHoiEfe5jd0FBQQHwzCmAq4LT7mHa/TUOYlSe8n0qxIXWeFFLYOq9KHU4qx26ikU7dvMiNUWGgBDtyHCL9C4h2pEiF/v7hGjHHtOoaqymeNywPTD1HtNWDt7gZdiAlW8rizgRAnLZpM1Et2N540SWiUybDrx8QZWFp3FnYPJdKvfu06dE1X/vzTY7Mi56ky3atNnmTe+Wb4CP7g1ZP70csG8ztE6joTlKFLEJVrLyofu4kvtfxkrk9ZpDHzCTU+l41n6sLmnYDhh3DZw59U1tnGMDSOBavJvfg9sVNiSYEmmh2FdydS1oasnVNVRzhiJzpF06kvfFimjTGIzYUtrYgmKgSUhrx1qVrog27mS9zavPAnxo1B7oOBI6rU9dh23TlyHXPRNnSt21e1PwtFzT7oNn5y/QN33NkPJhVIs+QL9ToP/yKTyr3zMHNZGogacDlKpL06DTBp3GEWXRWvaBrfNYoEK5t7s3LuXnuFohyzaJE5LgVduhHItL3iRWtQaM0ApDOdxow1c1nIgT5dPWKC1gDMaHuk04jrq0PLzXiCLab3rfXclCtA2cvAdHlNptw2dAWYkKXyBPn0Yd2UvG5Xbz3ETk6RDlWor2dloXNAc2ei7XLlbeQaHeq3T4Stb7bhNYCI/GnQyEmw/dKfMBaQoMOw/udsMDerex1waFoZAGSWExKiqfK18cayvRpmeP39mV8dFmQvGiXX9yf2AEhGgndmUI0U4s3iH30brVXY7Fvu/du9fiHbX7ctok8Abx0E6OaaxwuiyJ0FQ7xa9M02PkkTVUdPnDXLobWPchQJannpPgtufAXrZXEfAYlYyL38b+AweqiPbadwFKaRS06LDbNGDzd9B6T4ZGactC5domkp1VJ4T7uAYtty6n+HLv/R06bbiMQu7y0x/C4SOYXsNLsneuBRbdFjbdmalpIS+IiTeyqyvFvMb58TbVpSN1USyJtjEGqtOwkvkq/xu/EzExBG/oUIuftRVzw6ZWYrLtdrKLOSth+7tpDDoDOuVeXvOBslr1nwmt/VFqfil+fN0HwK/fALvXV8VKG53KyGEFc1LUpjhuCjMgMkGEK3Pd+7B99Qw0eu78ikFcA2maBZxTmx3aoDOg9ZnCGHCN5EpOJI5Itj2TiRvhQkTGKomjww56N3I0+S+fANt+Av74UeUcN2LAm/fmkBtb+2HsJeB5+/+A8hhpCwycBXevKWFDefhQ8Y8VKnWaWddxOqQ5/WnTh6qxeKYMpWpD18L3oMLq3MSiP7Gog9YHHyR/Ow/48a3QaS4DNUgpKgfPhju77hF/f/rGaNN80Ps82LwY8e7B1KxrI9Hm59BTDqyYpw6Tuo6Dp1nPuAkuxmL9pnMdQrQTO7tCtBOLd6jWxKKdPHPh7YkhFEMf1Wg2PL4bKP9hGoJr9O/GxzkPDuDFc2KGSA2i/dPbwDcvB62fFbYrDgI7fobWvCe0kZcCc2bWJA6+NeQWBkxJRPtujRhCTgH0i96B+9NHoPvHr4+5Co4WA+KWTiiQxc13I8Qxk7t+BhbeCOjumOHOIQAn3AZ3o05hSUHsGk2+muJBtK2Okuf4fw8CJty6ac0SmYTHA5TuVaJVRL7J7XrAqdC7HwdPdgFQv41XmZneD0SYaK0x8acOUugHkUsSDyQCR+Jkus73EMllElzpRpyleYDHTgD2b1Xq6l5Bs1wgr4jzXBNBdrvJ9dtEOfEfqKjfnok85//2OewziJyJWmpcQmMkK6X203vANy+FjTG212sGtBkCNO6kUqQFEpCz2hFKGTj7hbCHc5w7NycLeO5M9nYwZdHuMxXu/qfV6ufV6nT4Xu89tCSdADqcDZZhwkwjpH8x6lLorQeXxBJtAAAgAElEQVQnVXiRma4Hu6Y2Em32CCAx1W2rKmHRgNMeR3lGQVJ4LEQzn6l4rxDtxM6aEO3E4i1EO3nwTtqeeJVyn5wWmz5m10HGuXO9Mdp8urx2EfD1cyGINmAj61Tlplg75WFolGosVNqy3MLKGNDqgdrsNk6u8H2mQh99OVyvXVWzXXIp7zOdiYdh9Y9WTMzIacq5el0OJU5HStEZWUBRK6CwKR8MUHvsQfDa5WFJQ0QTQqTg5PvhyKwb9iCBsSI3Yo6nDRHwHlFHwCTQIF2+7RDxi0d7RjdTjWhX9ZsMtDYmvRoRb4p17nsy3H1n8lyGwo1w9ie4xvo26qffydJu2/Yj7Ad3AFu+r65aXG2eNYBixOs28a7boMuALOyjr4y5QjW/O8hKufhOlYM8TOEDCzqgIGt3twnA8IvgWf6qubRn/8/edYBJUWXdU90TGAYYGHLOOQeRJEGCAQRRgoIBxbyGNe+6a1zddV3X7L8GzDkHzAFzQEVBgiKCkoNkmNAz01X/d+7rqunu6VAdpwfqfYur9KsX7nv16p0bzo3W+JF/g6dp76jvlChY6GXw+f3RgTY5FmbeixLdXeNJx6KJLxW/8z2nvF0kj+QeET6AJBR6kfRVHgyJKLyTMJKEmzgYgbbEuD94XKCifvQF8LQdHvX9TVjgTgNVJOAA7fRuCgdop1feDtDOHHln9EhEA/zqFcAfvyY+zi6jkTXu0kCgvWkR8P5/IgBtTaULoksoqZO6T4DGi/Jzf1Lx46FKXv2QlyABj7TonfYUvH/8JhftgJKdB/fUm6EX7YSxdpEiSes9KW6GXfZHi1t2lhv46T2AbLGM3w0uBNydRsHdbwpQtAP6t8/A2JJ4jGxI2bToBWPiDWEvilYsI8EcrafubGGKTlYeW6t95lsmkRhdonUvkJ0r7r20NsYbp2tng2YC0LbrOh51PoNPRlmPSTGFkYRq0wIlzPH80Z0SnuI+7CwVQ77my/DDYK7nRu3hrfAqN+3gQlK2qbeiVNeSai3iHsrLzQZI3mjzXBJFAxUIu3wM7HQHHnUBvF/MS8zSyTn3n46K/jPEjTdSsfIbE2j/uiC8TGg9nXQ9Khq0j9pm1D1ykFYQpcaW5YoINNll6GnQe06qkpc62d2kur2DEWjLfeb9fwO/K14LIZc98X6UarlJPaNSvXYHSvsO0E7vSjpAO73yjtSb4zqeOWtR7SOR+LaV7wJfBqfUimNoE/4Cd8dhVnovuTDTNf2J0yI0Zoj7KzYsUS6zBNsTr4dGojB+MIMLgWF27bD5tLUJfxF3Wy+tWau/CHha63o4XIzZeu2qyuf7HQd90OyYY7gsCyFjrQleQrgtMm+xxtja2oVw5dVTcatM6dOwHfTfFsJYt0hp3r3lMGgBp2U/GWXc5ShvfYho8E3LNZuVVGJUCix6Blj2VmUKMZJ5Me94484JXS6FEMqtqfRgy94MbWWihX/E2dCbqnjyZFuNMgFoixzWLwTIGJ5ICZEbN57m5B3fuQZ47S/W41qLXnD1nQK8d7NKJxeuiGW7WVU38oKWwMTrUJ5bkFRyQa4fySG1T+8BVvqIDG1MWojiSAS5Z3Nl7RFnC8mX97P7bbQQoUrnUdBHXWjrjDCZ+3PWLUT5l49UPRc6DBd2b2/tho7LeJyrIt4OZbuBF/8cW37wWPqbeD0qmvao0YqQgxFoCyN7thtY+rriiug0Ct6Cls67FsveT2JdB2gnUZg2mnKAtg0hpamKA7TTJOia0I3EFtJ6JIzkCQC9wnbitkwAumePShXGS7Pk0WYMOBmWwxS5JAsD8xr1XJ2GwJFXQ9uyAvjo9kBym9y6YoGt4n5MS/aYi6G16Q+0OQQVb93oF6fFZOV14DrmBgEVtChbhUB4+l0xERJVsRD6z4t5vNsPUcRMjJ79/Wshu5I4dMbQ0mWU4IUs0PWawti7RS7jhpYlMdvGphXQyW7N+NlYiysLZILWOgyD1m0cvBXlSu5lRUBuXbjzGwDz/w5s/UkAbhWP8aOvRUWzXnFdLuXya5QBb1wdOW2VOaeR50HvMjYhYB9KPJkAtFW8bq7KH0/Zx1N86b3279+fkKu9hIfk5wMvXFhp7fWNR2vZR4HtxS+rGOhw7ret+kJXdGSqdDoMOOxclCMrqSCbTYuSgkqB14NSEUaRoZwhuzYAtGqbhemcZj8IfeVHMGy4n4ftonV/IVfkWtgplDlBjrBYUwHHNG4khmvcCYY7RxRg/OOU2CVgeQ3wnNm8PPYG7D5BnoMT/oeScm+Nde0/GIE2l9firtA0+c4575rdTZ/8eg7QTr5MI7XoAO30yjtSbw7Qzpy1yIiRiKvrpiXAOzfGNx7Glk79DyrqtxFWYxNoszFx8fvuSWDJqxHbFgZmsi/78hVrJGQa82flCs6YbVrdJLVXVlXg0fYQYMgcReC0awNcw8+Ezjykqz5WrssEt13GAHTZ3LgEePO6yrH0mgR9yGm2rFXmQzKnTYuBt4PkVdAc7gHTlJWF+YV//UTF3JKkjf8g8PV6lOWerNDdx4vFDa0GwFj2hnInJ4jpOhbGtl+hL33DNlDT2g2Gq8topSz5+QMB9fr+7ZasXINnQyNBDK3NeYUAQTdJ43QDuom4a9UFTnrYVjoj/8W0wBxdfWNJq3T0daho1lOAvcnmTQVKIjHzmQC0rX3PNENfPBDfO3XEVShv0S9hICsKkG0rgLdvCD2O+i3h7jdVgWymFGKKQFqC/Eu95jAK20BvNxToNRFG484pS4ckrp+MuY1kZQ8xE3EdZ75kKq78S//pQOdR8H75cHzrwKc6DIMx9jLbQJuPFBYWSgiN8Db43O65rxPZ2/FP4MB5UrwzNi4C3gvh7ZTsaQ6cCW+/6TXWGnqwAu1kb4Oa0p7c47KyZLhULpCcsrqLA7TTuwIO0E6vvCP15gDtzFmLjBiJZaFd/gbw1SOxj2n8FdDbHiqggBdlf6Atrlzle4BnzonaroDt0r3A3q0q3zetw/2OBXpPgaZXwFjzpXKxZq5Uguba9YGOIwQw6r9+CWP158DR16KscTexQvinYjIvueKW+ttXKoaLMab9p6HEU2bbaiHzQRnw7LkBgERr1g2u/tOAH19VYNYHXpXrNhT49tC66Uc8VtAcqNNEgZyxl8LYswXGgtuAvPrAyD8BTbvC+83TwF4/d9hgKdYqgHvQdIDWu68fBSgDloLmKjUUk4nTbfzoq4HnLwAIRsxCK1thG7H2KwCgAXGwssvld82nwCf3RF3jgAr1msE1637lPs413b8DyC+EkZ0Xd8x4pgBty/L2zj+A9T/EJpfuR8AYcXZSCMZEKfTtk2pfhivco60HwNX+UIBx2XS/3vYL4NmvYhybdgP6TpEUYdGI2WKbaGBtCTXJ0oBHToy5GQHafE+CPUHyC4HZD8H73i3xp9LrOxXeQbNjAlwE2k6ay5iXMeIDVljBa1cC21Ylt/FQrfEbc+rjMSseUz8wez04QNuenA6EWqJQ3b9ZcRbUaQRMuRnFnvJqV+w5QDu9u8sB2umVd6TeHKCdOWuRMSOxgMGaz4FP7rV3Ka1VAIy7FHqznnIJZRvBQJsTFCvVx3cpC3OUIi6gJvESwarQCWfBaNZTpR3KayCpiwS4Fu+Ese8PGJuWqfjn5j1hTPpHRIDCMZppzvzTHwUPyz9Nl78likDd9dVDwPK3rEe0Rh3hGnwisOB2wC9vtxUfXV4MeGglDMHu3aqfAjYkDJt0PYySvTA+uFW1PehEgJf8rx6taqnj73WbwH3oScDGpcBHdwSuGa3TBOpM0aS54D7qb8C8aaFzzNZrJnmaxZ180Inw9Jgck7udrO9LF9tzGTel5s6Ge9hpQP1WML5/ATrnYJYmXQB6JTTsELNreaYAbU5FlDI5WSoOmvH40UrdptC6jAIGzbLyTofLkRutKfN3WZu3rrPF3C3P1KoHrUln8R6xircMxvgrxaKbSsZ4uSxuXqzkFWORY4LvWSiSwVOfgL78HRhbfoqxVV/1UeejrP1hMVmIHKAdn6gjPSXvE2OzqeRMVxl9EcraDYtp7dM1tGj9OEA7moQOnN8l5GbpK8CiZ9Wkjr0ZnoJ2MX3HUyENB2inQqrh23SAdnrlHak3B2hnzlpk1EgIQmmddDOe+IcXlQsy01UFl9w6QM+jgb7HokLLFku2pK5yu0MCbbkgGR7FJB5vzGo0SfGmPe1OlOU3TfhSJBZa3QP8/L5Ye9F1HEo9HgGiEs/+yCwF7Flq1YN75LnKvZ35fn3FVBZotNSSPd1H9FZlGrSq5xUodmVaso/7L4xVH8NY8pqqeugp0r/30/8FrkVefbiHz1Vp0L6cV1U6dOdvM8BHYqXBffTfgafOENbzkIX5kxt3hD7iXJS2O8z2B1rikQkmH54ZbYUCfnf1mwqNCpOP74JRt0nVvOgc/6QbUNG4a0wx45kEtDlhKxf0yg9UHDQ9NfyLOwdax2FwdRwuMbz06NB3bYRBLwcSjhW2gQEtbkuyAO2XLwV2/BbT+lSpfOZL2F9UnFKgLZfF5a8rOcVRxCNm/eLKd9Ns45gboe/dAmN1BIb1cP1xH855CiUVhm2vFzblAO04FjDKI3IuL5+vPIbSVbqOg37YuTGFFqVraNH6cYB2NAkdOL/LHctbBHx2n/JKOuwc2bPJJhuNVWIO0I5VYonVd4B2YvJL5tMO0E6mNA/Atnhoi9WX4JU5oQkCCRhz85UbaYM24pJEN1K6aJslHNDm7yqueQnw9j9SIzHmze02PuELkSKHywGe/1MlY7AvRpPzzd34HWBanAG4Bs2Exrjod/8VMC+xZuvlle7l4YA2wWbzXip2nKV5T2DSP2C8eiUMutCzTP4njAoP9B/nq//WNLhHnKXce5miKVxpO8hii5b6TD+25JXw9WnZvuRTFJUZtlOhyAe+dAfw/Pn215VKgjEXKMULPRMadwzt4kZCotkPoqjYPjt5pgFtCoUKLILILLLrM++vzy2bigZX58MUSd4vCyT0Qfd7n0Sg5CggU3XvyTAadRCllv87F03oArTfvcmeRT1cYwSbBNoptmhXscpEm1zQ7wK06R0S7D4+4a/Qy0pg/PppjC0C6DYe+gh1aY2lVCfQ5jvA99Is3C/VfeGORXbh6oo30cd3BHgNJaPdiG1QAXnSwzGRZaZ8TDY7MIE2z59EuS9sdulUq0YJSKrR7GxZa8Znx/KdSNWwHaCdKsmGbtcB2umVd6TeHKCdOWsRcSS8MEnqKzodJ0gSFc+U+YE2yTXM5zkOHuChXEgjAW0rDpwEUZ8nmG4neDJ9psA49NSwuaNjmbu4r/7xE/DW9YGPnfkyKrxeZC1+Afjel5+b5GfD5irG9qLtVn0hP2O8M+PNTXfxcECbT7UZBDAnrNentBh7uTxlmHIqbAtMuwPej+4Si6jW6TC4mnUDXrig8plQk/QD2lqLnnD1OBJ46ZJAZmb/54afCYy+AB53vm0rcjzunFqHoXAxNvzVK5X2vWF7eBmnHaoccRU8zfrYtrBnItA2p2W+T/x/ys3F2P0vHoCx7G31PoXKVe0vk+4TgOFnw1NeblseQpDzw3PKQyXe0qQzjCn/jokMLJ6uBGiveCNuiyXX3qUZKpTC/32b/C/ouzbAIDdDLCUrR5inS121bSuezOarC2hbIUC71irlSt2moqjxHABM53Xr1gWeOy8whVss6xlv3TNfxv6iooS9OczvOZUe6VB8EGjzW60V71REodn5MfEMxCsu5zlHAqYEHKCd3r3gAO30yjtSbwFAm5ZJE8wla4gOCUxikrQsYGSQJGs2LaYFLSySqExgkww1w0hAm/WtSyBjtT+52yIMS0hag2bBIKFZSUlSiD+UC1Yx8NTcymExNvzEB6R998JHVI5ozqfX0dAIphl/7lfEmk13cXoBmCUS0G7VH/hjVaVreKOOwuKuk0COFl+Wo66BUVYMfc1XcI+9GHj3n8o6Gqn4AW0Zb98p0Oq3Aj69N/BZkqINPR3oeBi8P7wEHHOT7bQ2ViqredNDx6CHGJ/WaSRc5UXAFw9WIW2rUv2Q2fD0OMY2sMxkoG3Ozcr1+sY1sbG0swF6lEy6AaXlXlvgTxRH+zYCdB+PtwyZg4oeE20rX+LtJipDuo2GhRTNsw/YurKy9mlPQ1/8Kgx65sRSxl4Cb7thcYGT6gLaYvUNJrVkSMLkf6GkrDwjrFyxLIF/XQHaJMozz8R4G4r1udOfQZHHmxA4FqK/vDzFY9GgNTxl9pVlsQ7XrN+gQQNUrPsB4DlDz5gZ96I0p8DWuRFvn85zjgT8JeAA7fTuBwdop1fekXoToD1//nw88sgjWLduHdq0aYOxY8di7ty5EqPrX6h5vemmm8R17uab7ZHUOEA7/sWuJCX7QrFI+8fUtuglJFHeei3juvzFPyp7T0YD2gL2XC65cLh2/gYsuCOQBdteN6oWLaGjLoDeore40yYzbY5cVtcuVMQiJHwbehrK67USkras5fOhbV8DzZ0FV59JwMqPgE0/Alt+grH1FxmaAG3Goptx3PzLiEC7n3LP94+Hnz1P4rSNVZ+o+fY4ShjS9Q1L4CpsDbxyeWRp0RrXso/lOm5W1joOh6vzKIBghH0y9Rkv4ns2w/vj60qxc+ipqOg5yTawEvdkpoaLBvx9g9A6j4SLFz+6vTfrDj07r2pOb3PAw8+Cp9PhBwzQtt7vD/4DxGphNWXSfiiMcZfb8uCwmJrfvh7Y4AtPiOU9I0fBrAdjjlGOpQuzrgrbyAYePiF8Tm8bDYsLObMTbF+jMgvMvBfed2+O/A4Gtzv4JBh9j7Ml41BDqg6gLWDOpQOPnVxV6TVkDsq6HZUwf4UN8aesigBt7o1QvCEp6xXAaU+jqCwxK7SckZ/9n+I9ad4DxqQbU+4hIkB76Zsqbpdl0j/gadjZ9lmaSpE6bR8cEnCAdnrX2QHa6ZV3pN4EaD/44INo3LgxevfujfXr1+Oaa67BpZdeiilTpgQ8e8899+DRRx9Ft27d8OSTT9qahQO0bYkpZCUBeUtfBRaGIXxhGqcp/0R5QZuEc+zGP8rQT9oB2uaTQmxDiz1dyWlF3f+HveGQTbsPU34dgwpDs4jY7D1sr5bpUWB6epSXl4s1QxQETI/FMe9YC1fDNorNma7dLXrDYPquZW9AYy7ikl2BnRF0m/mqg4chruMrAoHA8LNg6F5h5JZSpzEw6wGgeDfw/XMBxGshZ8UUH3TJlrRdQcWdDa1pV4Dxh0yb9seaQHfyuk2AE++3HZMrLr/bVyrLiY2iNe0CV5/Jij24SedKZUCD1tAoS3eWyp9uGDAOPQXlWfkCEOy4W2a6RVv2/YbvgPdvsSGpCFXGX4HyVoNsnQFiKfbsBsgM7+9lYWcEE/6CilYDbStd7DQZqY7KUHAnYCqY4mxQwHbJXkn/ZzTrAf3bp+215M6W1HpGp5Fxg2x2VB1AW9Z556/A/L9XnWvPo1E+eI6t/WJPUOmvJUA7EqFjqoaUBCJA2ddvXA1sXq7O3TTEfdN1XM7/pfMlHabRdWxCezpV4nXaTZ0EeCbwHmNmWEmmQcLOqB2gbUdKyavjAO3kyTLRlkLGaF933XXYvn07CKzN8tprr+H+++/H5MmT8fnnnztAO1HJR3leLkrF24AXLoxc02elyQRWSf+BxgK0+Rzrc84SB755BbDhe2DLSmDHGqDM53adnSvka7QCCFFY64ESzxtMxJaqpbGY2D174Vr8IjSC3G2roOXUhla/eWWOZALDzmOAgTOVxeW9f1WSMhFgk0Waf4ILFSet+lS1Ng6YDqOgJYwvH/Y9oQHnvKbAOlnPo7G3k626TuOqbN52BXXifSjNDnQz5HqFCzMh2JbYez/m9Uhdifv7jt9h/LIAaDcUWuu+Ko83UzCRIZvuofWaigLD27irsG8TaJt5nMO1nclAm2PjhbtKPnO7a+JfjyEAM+62rQwRMsIdq4E3r7MPtoefCaPHUUnJ5213irbPQBsNumrXg3bC/dBXLoDx1cOhU9v5t0NPj0Nmw5tXKIDUjmIn3DBSDbTNrAb+XBkHukU7KcR+NvZNQBXm0j7t6YTJ0ETBVrJDpbhsdygqClqnXHlFoM07Ar9hLKbCOFYRHIj1+R3jO0TgmcqUhdUpOyvbyw8vqNDDNJ/lnLsDtNO7AxygnV55R+qtCtDmhWLatGkYOnQoLr9cuaR+8803uOyyy/DYY49h0aJFePXVVx2gneI1lMvwt08AP/pSO0Xqb9IN8DTsklFuYLECbXN6JkuuCeSsPNq+CvwQco+S2CWdDLqWm+9vXwIf3w3N64GLNGXrf4CWWwda3YaKeMm/uLKAEecA7QYrUEOlAQsBsr8rufkMmb7pBk8mav/SZzKMJt1gmG5/hKEXfQhj9yafa2iUzdi6P3SONpwVPdpeHnEWPB0Pl4sIP9i8xGtUFBAE8w+t9yTvql0faNwZWv2WcqEzfngROlOTBaex8u+P6cyOuhpZzbrC2PG7Aucr3gXWflvp8uojSZPc3nyWF94uY4R9W6/TOCyraiYDbQGRRVuBFy+KJn17v0+7E578prbOAMqFHhnuoj+AT/8P2BS0b/17pEfDyPOgN+8tYCARwGlvIoG1xKtn0dPK0yWRMv4K6G0PlRZc5ExY/Rmwa72KkyXTO7kJqMSr3xLoPApGjvKcICBJtCQbaJtnpJDoETiZ77WmyfpwzPzDb0hNidG2Ut/55hBtrwmx3+LnAdPLJ9FFsvN8u8Ewxv8lKW7efP+5jjyTqTBMdXHSe4WWsOwjvUy4b4x6zQ9YK78od5a8WEneOusBlLjrpJWnwQHaqX7LA9t3gHZ65R2ptypA++6778YLL7yAZ555Bi1btsSaNWswZ84c3HbbbRg0aBBefPHFKkCbHwvW9y+8AJxwwgkZGT+cOeIPPxKxCr55rXJHjlYGnwxv7ylpPTSjDcl0ueaFqaYX82KrMSWWH0u6XHIZ+1leAq1ek9Bxr7wEDzwB6HGEiqU24+x1b1WrdoveirGcsdH+pe9xMBq2r8yRTYv5RQsApiiaf3Vk8YrbeLv4rdlsfdAJwICZygpIq/Pqz31KBYG9VQvd0TsOh0arYMP2MJa/DYMx3/6uyrTedxsvbWsMAdizScUtEmAX71J9cZ7MJ56bL1gipKKg10SJI/fCVWX/m4CyuLg447YglRXupa/FzapdZUJxnAEyBmYyoGLnt68VCR/3Z04dceMXr5EOQ2XvhMsukGrBmqzseIdpyb6Lr7v+04FDZgmg4R5im+Yff0WeqcRLNhM0AW+y9qAlDxK8/fy+iu0v8+1vKq06DAN6Hi0eMCa5qRbEOs6MCXbcRk1LH4WeSmufzInu/eQqoNJn1J+A9sMspY4JSDkOc42EI2P7L8Drf7O3J6ico5ouEfK0oafB22NiRn1n7U0eolijZ0bcyla7HdWgetxDOW4NeOpMoHSPhIl4O4+pkesbTexy1m/8AXjnnwDvKtPvRpnXSOt+INinAtDO2RNtPs7v0SVg3n+i13RqpFoCAUCbcdd33HEHHnjgAQwYMED6JukZrdgTJkyQ/166dCkWL16Mk08+GbNnzxatOS8mt99+e8BY+fG8+OKLa3QcWKqFH6l9avi19/4JrLVxuRwyB96ekzLqADPBaTq09aleJ36kXIybZlxdQDEUo/jWX6CRlIwpdEIVkp8dcRWQVQt4x5c7PNiqzbjrBq1U3F6w5XnQbCCvHgwztpSg+5THgCWvAgtuizB9DWjZGwZBbbylwzBoh8wSRmzj68d9acrsN6ZxrMPniqXboNKIYQAMd2jUHgYTn9ESTgDFOGUfSZwCPwrE2zLCN2gNHPl36PmNqlySqLDKRGZ+8digpXbxy/aFGalmv+PgHTgrrjPABFRC3OdLK+YPOqv7ci6p0KgQIEM+OQ9iKUPmwOg9udoUBRwqL5gEOYkWkQPzwFEOv3wUubl+xwODT1IpnfxSxYlXSJSXSkAsvVaogNnwA0Cvhi6Hp8yDSN6FVQuA378RBR2yckUJadDboGgXUF6svFgYz8x3vd2hcqbJvAiS/NIpVhFKncbQBkwD8hpINAr2bIHBlIye/TEuhwac+hgq3Hlp9+qIcaAhq/McNBVNyWjvQGhD7ii6p9IrbMB0ePvPjOsMzXR5WO80PelcWRJyl27ASy8OAu1o50+my7ImjS+Y0Lomjf1AGqsAbW78++67T6zS9957r5CimeWTTz7BTz/9ZP33smXLsHLlShx//PE45ZRTBGhHKg4ZWnzbRVyafnwF+M4Gcc+Mu1Faq1FS3BzjG23Vp+J1HU9W/8lqh5fbfO7xZ88B9m2r0qybVu2i7XCR2XvTMqAixIWaHzcyes+aB7x/c6WXgmnVJgCn9XD3OkVwFlwm3gBj2y/KKszS7zhoI86GQdARiUiLwL1esyps4/Zko8E14HhoBc2Bb5+CUbwrIau4Rsvz8DNkLKZWm5c/9/rvgPfsZTCIOO78RkIMWJZTYAHrTHYdF1e+RU8C5praW5TwtfpMRvnAk5IC6BIdSiqeJ/CjzDQqZRY+Vsl5EK4zvk9DT4de2K5aXN79h5UM13FhYWdKKHo5RXL19++4yxgYoy6I2R1Wvj1rv1aZAMziY7ffv98eQOW7Z8YDRwP3PAfyUAas+QL4/kXg148VH4NOHgui46CiucS930VvGM8+eBfcqcIAQhT3qPPUeUvlBMntxl8JI7eufUI8s02fLO3OPxXvgN02TW8Nfy8Ex3U8tPQkNIXfICp1ek9GaYWRUfcou2tut56EdJFY1JYG226r9uo5ruP25JSsWo7reLIkmXg7ArRvvPFGcQe/88470aFDB6tVMpELOZVfCeU6HmkYDtCOb5GEvALlwDNnRyYsat0fxpFXp5WkyM6MDhSgLYDot88kLjtcIauxVl4KjWnK9myuWo3xzATVw84E8gv9rNCGaJfRpPZ9+DkAACAASURBVIuysIS6LGbXAuY8DeONa2DsXKfann6XWLjF2kP26FCldgNoTToJsI3no+oaOBNabj7w1nViYTLqNUsIaMsQCX6Ovgal5bq4LGfvZU7nywAjBBu6nU0WXIcs5cf9FyWeMsuSxwvmrl2VrO9mjDkfpYUn3Vp9c8jCzv7jS5Uxc/HM1/+ZATNQ1uf4jLTeJzo183mCN8qNayieH+t/UBwB+7YCBF8kheMe6DAMRv1WcmHOBG+GZABtAQQ/PA8sei42cY6+EBUdDouJbEuIxl64oKoy46SHUYzcqO+MnJlcI8a+893Oqy/vYyjXZTOntJv5vhfcrs7B/EIY2bQchwlNqdwQcDOspXkP6D+8AiM4pWBWLtwTrgAemlGZxYE8GCf8D963fJ5FdqTJEJYT7kNpVp2MB2GiJIEuKRuN2oWWksUB2qEX2grF8IVHcJ86JTUScIB2auQa/l7qRkFBQXo7dXoLKQEB2kzjtXHjxioVXnnlFbRu3Trg7x2gnb6dJIRoW1cAb/8jdN5XutExH6arVloIVWKZ+YECtOXSSYvr2m8iTj8ryw2NsZKMdfW5PQc8QLfopt2AY24EHjlR/cS83HStLt0trNshS58pMLofAePVv6if2x0KjLsU+nfPwTXoRGDeNOsxjS6XdQrFTZIgWVKC0SLkI92JenH1teTqNhYawf+rVwLFOyVeV8+ta8+NO9omIdie9A9oLg3G8xeGtURFaybs7/2Ogz5otiiegi3acqnPdikvEc6n3/ExW/viHlfQg0KGtpbEenclp8nRF8LTdljGnQPJmVxgK6EIE01lEhUn/FPdLooCeHxKaoLORBTOsm/dOvD4qdHZ0oMFzrjtkx5BUXGxuDzzXCa4MN3J+XfB8deSOovp9vZuCWxt9jyUuGpHjGGVbxY9cz66U1kJWRgWM/pC6M16yHtpFplXrVrAh7cCa76Ei27xIEGYqRwMYc0Omp/MpXEnoP/x0Je/Gwi23dlwH/EX4LFTBHhKYd1jb4H37Rvtb81hc6H3ODpg7PYfTl9N8b6qlaOU8+S5GH0hytoNF2WTA7TTtw5OT6El4ADt9O4Mx6KdXnlH6i1keq9kDi+RC0Yyx1ET26pkB94G/PAyQMZrxrgyZq7r4UDfqUJokQlWm2D5HihAWy6dD80EGIsdqRgGsrKzoO38Hdi1AahgfZ9FRty0yDSuA2e+DLx8scplykvw/u3QSnYrQiNfjLLVDeMST3wAxndPw1j9hYpTnH4X9PWLYfy+UF0imSd368/QaOGu1xQaLUIle2GUFVdasum2XtBM3Ndp4Y5YCtvAfegpwCuXKaI3ljYDEO2xWN4vV59j4Oo/Dd4vHlIWL45190ZgH/OnR7FiReuIls3Z81DqyhNA4G/RFivyT28CCx9XrRxzIzyFnaoFnArIoLPQo7NtBqJHmDhjVec8hZIKhAVBEt/rA34mGI0mSuf3+CRgpSVjLvm8AmRP+y/2ligvi3iK7Ntf3q8kQ4ylERITHvtvRabIwnSDezYpazMVcwwNqVXPyuRABQX7y1r9CfBJZXpPtOoH46hrInpOqRRCpcBzf6okaDPHyvfy+NvgyW8m75uVxYHu6XQZT6BInnRaqofOhferRwOUd65DTxJvI3zxIEDvoOFnwSjeDZ35pO2UDkNhjL282hRydoZo1pHwAipkHjtZ/VX/aSjvN0M8CRygHYsknbqpkIADtFMh1fBtOkA7vfKO1JsDtDNnLcKOhBc3K5WLrxYvy7HkjzYZhk0G11Tn0TwQgDZlVad2XoDVOOLLJPnANWDTckWSxthsuoz7g8c5TwFfPghj22oYRTsFXJvWJY1AW5i5fWDz8Etg1G8J483rVfqsidfDyGsA/atHZBiu/sdD2/E7tO+fgVa/BbB7MwwfyU9Id3FequuTjTg82JaYxpULKrkBahcCjTtEB+g23iNlSQNc/MfYS2Fk14axcQnA+Goqj2DA2PIzjPU/wNj+m40Ww1Tpfzy8A04Ud1l/oC0AaM9axVRMt/jpd6HEyI4bAMU/QPWkeEsQzJDJPZHS5XAYo84Pm3aI+4uux9q6bxWjfc+jBThUl9t8IlOtCc8KMF7+unAbsGQfexP2F3SMW6EjVuKvHwaWvxXT9LU2A0HvFFHqbfoR+qrPqmY0YIsE3O2HAiQiazNI9oW8q3TF3vqzYv7veRRKPWURXafFZZzhEOHc27uPhz78HAHrMqef3olPeVBFCoZiz+8wHGjVH96P76nM6JBdC65ek6A17wboBoyNi6Eve7tqxodQkm3VHzjq7ygp9VTbGRHTggPynrt+/xpgmFGfySjVXbJmDtCOVZL26lsZSXx5uONVptnrrWbXcoB2etfPAdrplbcDtDNH3tUyErn4aTqw4m2xdpLd2uhyuGi6U/VhSDbQllQcvtyjdHdMB5u5Atq1gHnTba8b3R+1ilJoTL9Da62fgVbIf096BMYbV8PYGUjeY4Ft9kSrU+9jYPSdKuRHBq1PE/6qiM1osfGlydIad4TrkFnQ3vsXtJ1rYfjI2iLGZDdsByO/Ycj4R61lH7i6jgGenFuZ57tZN8kpbNftPJSgRCb8oWg7tOLd0OgqX6cJMPVW6C9erNzTWaN5D3VZ7jYOxp7N0Je9GRoYRFsNxsHPfkgu9IxRMmO0LQ8RLorLhQqvHlPsarRuY/1dLIDeImUB5JrHUwiSZt6LUnd+WBAk/ZTuAJ4/X/UwbC7KukzISE+YeESQac9Ylt1P/wfUqovssX/Gnr1741ZsiELG515ta645eeIxojGv/VcPA9tWScy6rRzoDdspq2/TbpZLOc8TfieiKWYEPH/+v/DM8I06wpj6H9l3tfQS4OmzKs8ZWxOLVIlgOws4+jroTCe45svEWuxxpMihNEm51BMbjP2nzZhjnnVmCAWfzjSgLVlVfGOMtq/szz79NUWxQWUxuSJ6H4OSsoqU3anSP7vk9ugA7eTKM1prDtCOJqH0/e5YtNMn62rpyYpLfekS5TJolo4jYBx+ScpI1JINtOUSt30V8Pu3QOeRKK/bIuUMywK069QBHjzengXEJ1sTbGPbrwEASsD0mS/B+OBWxVBeurfKnpA6Q04Fek0Sa4+RW0/S9BjlpdB/nK/cjGmZrtsUaNkH7hY9oC19XcCaLdIzEvu06gdvCKIhN9NwrfoY+P4FNS5e1Bt3jnrBDrexFfOwBtByTwuLrlINaQSVZGenhX7nOhhmf2ZDuXWAIXMkpZC+9A0YGxbH/u6c8hg8Wq5YeHbv3h0gG/8UVrE3nNwnZF9vWAS8+6/4Gj7ir/C2GhgxT7MAPwE2ZyoPi8MvRlmbIZayyta+iW90B+1TFmkbIArCREKo5DL/xX3AT+9Hl2etunAfejKwdzPw3r8VuVhBcxgFLWJTlg2cCWPAzJiUsRKX/v2zwOKXQo+z8yjooy6U31y00FORluTi7j4OGHyKisFmerJYCz1rmNGhVf+Y5h5rN+mun0lAWzwfKooBAtT2Q1FarjgValoRV/0sA3j0JDX0ATNQ3ndayu8lNU1O5ngdoJ3elXOAdnrlHak3B2hnzlqkZCRizf75beDrR6u2P/1OeGo3TYl1ONlAW2KlHz9FxRY27Qpj8r/CusomU5Ds1z3/r75Lm7IS2CnKimuoeG0zLZiP8dZ495/qN8bbF+1QRD38d8ZRjjwXaN4L+v4/gKbdodVrKpYofzDEf+c4+PdUpOTQWvnEaQq82ymNO0KvVT8QmOfWgXvsxaodxoyTDb1FT+halj0AH9Sv5SJOF3CxWKuigHapUkB0HQvjkJNgvHBR6FG3GQSMuxz6mi9h/PqZnZlJ+wLuj7gKRptBcMNAudcQ13vKixe66ibK8p8Ix0uw7SL/AlmXyVBvpzDm9fCLobcfJiA7GlgWQF+yC5pnL1xNfMoTKm18cqGHSE287NoRVXXXSZR1XIDJ8vnAN09EnoorC+7DzgT4zonixudO06g99LzCqHukSuP0LDnsPPH6sHPuiUKnbLfynJCQmaByzI2oaNwVWYypfmRW/F4ckaTgcsM191kYrmwYVMr+9C7AlHDRSpPOQPcjRLlXXlEhVvdo71S0JoPfc3FvB6k6dHveBbF0EKVuJgFt+ZY/d57K0NFpJIwxf07LtzyJ4pSmhHwuNxt4aq5SaB12Dso6jnE8hcII2gHayd6BkdtzgHZ65R2pNwdoZ85apGQkcklb/Dzww4tV2x93GTwtB9UIoC3uk+/cCDBusNdE6ENOTwsLLF2PtY/vBGiFJst73aa+/K5VxUlwKUBSfMT57y512fVWKLfubuNhtBkI/UsVYy318wuhtRuiYiRb9ZXLnUlWRXfNaOCHACpr/bdwMSb8tb8CuzdE30f1W8Co1zzAwqW1PQSulr2A5y9QA2tquozbBH5+vQrYpQhoUaJixP83KiBM4jfmDz/9Wegv/llZvUOVxp2ByTcpd9ANS8LOTYA9c5rTrX7fdmDAdLlsu3//UsmQxHOUcedRMJp0lT2fjvCD6Iuhxk1roGv3euDz+4EtP0V+rFl3sbrp9VvHlCOa75CrbD+Mb59WngskiWL+944jgUEnoCK3oFpd6e3IqibWSRRoWyEGT50RcfquflOhkTDx1SsqFTZ8MVr3j5/McNAs6D52fjvAUxQ6W5arHNymxw7DG0aeB73DCHGrzdm2Anjr+tQt5eEXo7ztUDlLxUWZZyNTwe1ap0jaqORjTu3s2kIgibaDYOTUkbHxrLCjVLA7eCpCqewW5d/+Harvuk1guLLSmn4u44A2vWvIF8FUfGMvSynQ5veI6+DvycS1trOfo62zeHFUUGG+HUZhO9tKqWjtHoi/O0A7vavqAO30ytsB2pkj77SPRCzaG75VQDEQ8QAnP4oSIyslMUXJtmjLZZOpYIp3wcirnza3Pn4cXIz3e+JUgG7XzXuGvIiJBZvWSFqiCS4JYniZy60DraApkJUHnPQQvDl1YZR7VPw2L6CaK4Dx11Ycpd86ysX2ywfgcmepNDdv31DJFh5ut4UA2q5u46AVbVeM3LTu5ObHTYAmLMC0qtFaH1REEVHux7A+60EYS16NbLFuNxgYfyW8n94Xsk1L9nRPN/scfgaMnLqVQNt/HG0GAoedh4rcehkFLE13Y+2PVSpNHAG3Ge5R0AIgwG4/BEbjzjFf0uUcKN0FzL8qtFKjVl1hYS+v09xxfUzyKZ0o0OZwFHHe3cAvH4UcndaoA1zMKU1rsn9aLu6b+i3ifpels2NvQVn9trYsdXy/eU6L1ZpEat4K2bdeuGRf8RzPWfZaJdlikmUtzfmxbfM/+S0KTmvGvyfQMq3LqeAqkXfOZQCLngWWv6PCZczSeoCEBOkN2trySElUTJkEtAWcluwE1n4LdBkDj+FOidKTCkxh0Ge2BX4XeK7S06KwnY8U1Ct7OlHFCttnX5nkKZXofknF8w7QToVUw7fpAO30ytsB2pkj77SPxEqj8jlj/N5T/dPSyrymHQ+LaBVOJJY12UBbhi1uwQqYJkMbbWcxGB+ZXb4PWPgEsPR1GLl1qsQ6CrAkydz21eHz3I6/QmS+b98+a+ycQ6LzEI+FZWQ4flIYhjXm2WaYwLI3wk+vSSfouQUBfSsG8zVy+THcOXG7NgroLdkD/PFraEAgQLukMl3a+L9Iai/jx9ciL8eYi2A0aAv9mycD6kl/tFht/SXQFXX8FTC85XD/5rNoB7dOC/fR16KiQFmFM6WYLLbm5c3/HeS+N61usewbi3V8/t8iW8sL2wDT7pQzIVaFT6bILxPHkQygLYpGtwG8fDmwZ2OVaQq/ApUz/u7lOflAs25yXiWUNK9JZxhT/h0Tn0e4dHICsr57Eoj2vieykF3Hwjvi3Ii8BYk0b+dZyXBAXoT5V4f3MqK3ARWIrQelfKyZBLQpP5MMzTzT7Mg0ljpsnyBb+/VT4PvnlJu6f6FikWSjfaagrFyFCoQqZrYW/sYzN1O8oGKRRabUdYB2elfCAdrplXek3hzX8cxZi5SNhB8LAjKN1tZd68UtWM/OC+t2alnWeBHwxXHygs+PjF3tbyqAdsoEFKFhXhgpO16cjA/+C50ut4pDWwpTVWll+wGyjIcrrQfAOPLv0Jm/tfOYpLq8B7uVak07w9X7GLH8Y/HLwKpPAuN+GXvdqq/P/d03jxa94RpxFrSf35P8spL2O84iSoeNP/ryiFdtJIAMjT+T4bjcA2PJK5F7JDCe/RC8Xz8GMOe2qXiBDmxeUTXec/Y86Ku/QNbWFeHd75lf/Lj/wpNd94C+QCnW8e0qLCBaOeYmeArjT0UVrfmD8fdkAG3KTZRq5fuBd/8ZqMiq2xTuEWcAj5+qYkWlcj2gcSe+HQm9z9Z6TfoHPA07J/yeCND++iFgxTup2wodhsE75pKI4DWcQssclL9SK1alk6XYeuNqYPPyyPOk0nvG3fDUapiwbCN1lGlAO3WLD7Fg59XKBd6/Bfh9YeSuGrUHjroWZe68KmBb3jejDFjxrlIMdxoJb52mKVeKpFI21dm2A7TTK30HaKdX3pF6c4B25qxFSkfiH6cUTotspT/avQ5gHOf6ReqWVqeRaH7JhE3rnx03uwMFaJuLIh/vvDzg0/8Dfq5k/3Uz9m7j0koLbfAqdjwMOPzP0Je+qdizZ9wDT16jpF6qhJX4u6cUsGZxZUFrfyhc7YcoUjPmT6ZbNcF3vWYw6jUTMjRZV8bI5dZV8WufP6BSwMVZJPduyS7gj9VWC8oiS+ReqZzQ6DZvAoJhZ8KoKIsOtNniqD/BqN1QmMi5L91Z7tAu6mQtP/UJeD+8Hdm6JzTQ9imQ0KI3jInXx2Sti1M81faYWNdWfwzQqyVaGXwyPN0nJnV/RuvyQP/dLtD253cIB+7EHTknW3knMQvBno2Skk9jmMp7NwM5jDtuBuQX+jx/kiTdHkdCH3ZmwkpCZdF+Cvjx1SQNLEQzXcfBO+KcsICI74OkimRKptWfqfhtclvQrZjnVZ3GAMNLSMbYeoAVpmHXi0Tetz8Yh36DvTl2Hg1j9IUpjVM+WIC2peRYcBuw+nN78icJ6XG3orik1DIkCKN4bhZAok4zFIPf0qm3wFOnhXM+2pNsQC0HaMchtAQecYB2AsJL8qMO0E6yQGtyc3IJ2vYT8OZ1odmP2x0KY/yVcoGJpuU/0IA219XyDCCL7cJH4dq7BRoZtbevqbrsTBNz6ClAuyHQGYNMqytL72PgHXxqUrXilDXXTvv03qo5bBu2g1bYVkjXSMaG+i2tWDKuIT0UqDiJmprHxsZWsdm/CzEMi5C9EWDTGqBXKKUNc926c3wkaQYw9lIY+/6QOO2ope0hwLjL4H333yqMwOsJzbTO1Gh9j4X3k/8TF0V/QjmLldyvM/2Iq+Fp0sNWDGrUMWZgBbn4r/0S+Piu6KMbeho8XY5wLpLRJWW7RjSgbQE/KqSogMrOE7Isvpeh2K/5vvMZ/j/DMNxGBfDdM8pK7HLB0A3owl5fqdyyPdhwFWkhP+UxCX1JpIiiYPlrSpGbqjJgOsr7Tq/CNWB6J7n3bQG+eFCll4pWSIA5/CzozXoEnCME3eGIKuUsXfQUYOdMY/9Uksx9XoC2XTAfbdjBvx8sQFus0JuWAO/eFJuIDpkNb5+p1ndZzszfPlWKdf/SayIqBs/JqHCj2CZafbUdoJ1e2TtAO73yjtSbA7QzZy2qdSRKg5ujUlWEyO9sDW7U+SjvMDIqYdKBCLQpAwI107XetW0ltOVvArRUU2a5dRWLbfNekuPa2LoS+or3VLoss9RvBWP6XUm3XlhKAHohMD8t3bd52eYljpbtPsdC97GihlKSyAV4xRvRUwhF2KUCtGkd0r2KfZ39lxVVVdpk11Kgmwy8M+6BsXIBjJ8/iL7/aVE44wV4P7gNbm+pCoPwJ34yW5j5f9A3LoXx+8IAoK3Y0A1g51rFAExNABUig06Ed/TFCYOI6BOonhriOm54gCfmRB/AzHtRmlsYle0+ekNODVMCkYC2gLLS3eq9owXOTO9GYsPBJ0Nv3itsiA/3s5zbtWsDrzP+fkXKgJrMZe5zKCotj6pkjbTyAmB2rALoVp2qEiKbhsXs/9tXwEe3h+fSCDUmpj6c/A8grwG8KxeoZzsMh163aci1EYJK9rHmC/szPOMF7C8uTdn6HSxAW0gD37wW2LTUvuxZk3wGc55AUZEyIjhAOzbx2antAG07UkpeHQdoJ0+WibbkAO1EJXiAPC8flvVfAwvuiDwjmzmsD1SgbQrHdFFzb/oRGoF0di7gLYexezOM3Rtg0J3cH2CbD/rcmhO1DIVaJFMJYKUy4aVdc1kkLpFYUWX9d/8OvPaXuHe0uNGvW1SZ4ozKh1B5ocne7qa8ygQ4G69dJYRotgpdwn94CW66evIyRbDuX7qOA4adDu+Hd4gV3d+iLYoAuosSZPuXhu2ASz7Hnj17UnbRtTW3FFaSC+in9wAECuGKz2OFZGipsqylcIpxN833JpXzDQe0RblVvE2B5HDKzVEXQO88OqLLtuQlfvI0oNhPoRe3NCI8eML/UJJdYCt0KFwrknuYioFHZ6tUfMkuPFtOewbFnsA0XRJeQzfxj6J830KMxzV0juI3+fKhQAZ3pizrMrbK2qhMEA+qHN52y5kvY38K37uDAWjL3sqrBcybZlfqgfWOv81yC0+167hJBhfJMyK+SWTuUw7QTu/aOEA7vfKO1JsDtDNnLap1JHLpW/qKSkUSqTAl1enPRrX+HehAmyKKmKM8nAwbtodx3H+TbtEO7s5kq+bf2wER1gX4kVmBaWhs70oDbrq+blisgLZernLWhivMoU1L+4izoD99ju1eMP1u6Gu+hGv7KmDtd4HPMbZy2p3QV7wLw2fRqAK0g59hC8wlfdWP2FemcpgfSMW80HF9s5nWnbno6e0QXJp2FRb2Uq920FizJQ0V8+tSFpomAJIpqOy8L7HskVBAm+8IlR94+dLI6fjodXHCfSjNrhd2XQRoP3ZyJe9BLIOLpe70O1FSq3FCQJvdCej99gn7rtWxjLH7BOjDzw4Av/Jt27sBeOWy2Jnh6reEe8gpimiO5xnJs/Ib+tKlacBJD6PUVStgbaS/Ve8DX8yzN/LGnWAce0tKvwkHA9AWcGyUAFHyzYddlNEXwNN2uBU2kyoyNFHEePaoLAHMcZ/fJKmhZPY2XfprOUA7vTJ3gHZ65R2pNwdoZ85aVOtI5HKw8l3gq4cjj6NuU+DE+xygTW8zWoG3LgXeiSEerN/x8A48MSM/rHIB/moesDw+QjQ3OY5NoE1Ls3/e2Cq7SgOO/JsQpekf3W1/78+4F/qvnymgvW5R5XPZecCUf8LwFEP/4SXr7yuBtiFutvJMMK06Qf9lX2C/lp8wiLA/kdTWtFxlPXsVQ3XTbpLTXQpT3lAO9CIgcRZz+nY9XOKBD5b0NXKJJvhacLsKQchvJKSF3ibdkv5uhgLacnbsWQu8emX0jdDvOHgHzgo7LgHaz54H7A1KYRS95dhqnPQwipGbsDJKQhlQBjx9VlWPlNhGFFibDN4n3ofSrLoW8BUFYn4+8NLFwI7fY25d6zAUrvotgdevUs9qbqBVH+igFwSAw86Bp8PogPdGiDOp1SLgM0kfI/V8+CUobzskajhWzIP3e+CgAdrwAE+eHp+oxlwET5uhVdZSvhtJSu8le18vBp47X3l0cM9O/Q88dVse8GevA7Tj25bxPuUA7Xgll/znHKCdfJnWyBbVB6BUuSBGKlEufeajB4NF27rEvXChuqxHK3RrPPF+lLrzM9JqKJf/0p3Ac+dFm0nI3wNcx6MB7fyGQq5EEid9wxLFim6nnPY09O+ehWvvpkqLdl59YNINQN3G0Je8BsNTBOzfLpf4KhZtieveGthTYVsYf3oH+8uRMIiwM4V01BGryepPKwnQGN9+1N+hN+8tygTKxSxm6r5oBIfpGHc6+rCsyU+fqfaJWeitc/KjKKkwkqpwCQu0f34LWPh49Cm36gfjqGvCWjwlLODD/8YWExy916AaGnDmSyiyQYRpp2nZn79+DHxyj53q9uoMOQ16r0lVrdkbvwfe/7e9NoJn3e4QuJr3BHjGm6WgBYyCFipWfeyl8LQ6pApIktj7zT8Cb/8jcr/M+jD2MlsEo3FNwPfQwQC0La8suo6HClmKJsAZ96C0VsOUfpvlG/vrh4qMzywDZ6Ks93EhyThpAOFdil42VITW5DPaAdrRNmByf3eAdnLlmUhrDtBORHoH2LNi0fz+OeD750PPTFxz70CJV7lZRioHA9Dm/JVlbKOKbQ6OFw4W0OgL4e04MukWs2RuQ7m0f8YUZjbIyQI69lmMN/wobuMaWcZJhBaukG28fmsYS19XNUr3KYtTJBnSan3a0/C+dwvcRrnU1/pPA4bNFSs1yefEvZMMySRcK94J1/rvUb5moVy86IXLyxj2bPIBLJcir6vfAt45z6aU9TeZaxStLXXhzAMePkF4A6zC93fWA1G9UaK1X9N/FxdTWpUItIPLkX+Hp2mvpFqXwgPtt4GFj0UXZ+sBMI78e1igLWfQ8teBb56M3la8NZp0hjHl30lzb+YeJdiO76wJMQkfYGX6Sf/wD6WEuBVY82V8MycR2tiLgZcuUfwOLCSYbNUX3twC4MQHUOwpq6KgozKH83NtXgp8dKdKrRhcmDJzyKkoKSmN+j2Nb/CVTx0MQJuzlfWmUiVa/uxggdYuBE56KOXfADFolO1SFm1TGTDxengada1y5oiX4b5NwA8vKnLVbuOT9v4lup/ied4B2vFILf5nHKAdv+yS/aQDtJMt0RrcnpUmasnLwHfPqpRMZmnWAxhzEcprNbDl4nawAG2KR6wzzD3+wa0KxAUXAsSRf4LRYVjKLReJbj+5CLh0ZcEpCiINi9K4kI3tXCfEQRIj7tkXmt239UAYR1wlTMve4t3igulySSIwYIVp1AAAIABJREFUgKRD+7YB5aVVe+syBhg6F94Pb4O7xwRo/Y8HdqwRgGHQ3d3rt1/pJt15FFx9j4WuZQmBGtdGgW26Ahq+/xnQ2x4KY9wVNfoS4y8sAZI5bgW0/QvdFM986aAH2qKIyM0GHjmhahjBCf+H0pwGSbVqhQXa+zaqGO1oZcB0VPSbETalkLq87waePTdaS/H/PvhkVPSanNS0RlamhLgUe35T6TBcLMslpYGA1fJceGhGoMIpRim4eNY06gDQa4DKPJZeE6GPvxLldVuGlQn7Fx4AnosE+vSmIbjynU16bj35lqaDF+JgAdoCTneuAV7/a2yrfNg5qOg8Nqn7O9wA5L6way2w9hugWQ/JLMCUqcHcEFLvs3uBXz5STZ35EvYXVa0X20Srr7YDtNMrewdop1fekXpzgHbmrEVGjIQvJy8HLpJZMW0VY8yadYdRr7loXO3GcB5MQJsLJ1al7Cxg9RfAtlUqlzTTfTEPa9ex8Lqy5VJVE1y/xO2RFwFa6f2VLVF2KIGyq7wY2PqzIkQz8wL7u/EVtACm3gpj3XcwNiz2kQpVNqwAN3Nve4CSPeqCTBdNIuSj/g6jZT+gblO4GDe34DYYn/4vYqoe1tMHzpK82vqi52Bs+7XqLCb8BWUt+mdcHu1E2LDFssO40q0/V8638ygYoy/KSIWCSd6XbCKycFtWvHeWzQe+frSySo8jYQw/S1yPkzmOcGRoHEOVNQoeMF3+GXccIdzEzICgvXlN6LzyiX5ZqKChS72hcntXGaLLJaRyLLGyKFtg+5cFyp02mleQf+eUzZA5MHoeLWdr8NhE4eTyAo+fkqgE4Oo2FozXRul+dd60GYjynLoR2eDNTjkOyXnOM9HHcM/vQLg83AkPNkQDqQba1r2Bedx9Ocbp6pzuYr0L9BT58TV73dNafPR1aVWC04Xc3AvhsoHInWLd18CHtwMte8sYmWu9phYHaKd35RygnV55O0A7c+RdY0ZiXg7MyxMvMbFcPg8UoM2PoX88K2UQThbC7JydLZcq/rtZ1wQR4rbsu4zSihEp3VZ1bxTRpm9dAbx1Q0xgW6zaW34CPEWCjTVe0nl5NrxA3WbAMTfB2L8NxrI34a3wKgAdoqhLKX/w/U6FxfS7RPZuvRzG639VVoE/Vod2y/S16apVBwZjb7uNB4afiYr3/xuYe7tJFxhTbk7rJSva2lrgQ1MG12B32GjP83eJBTTKgO+eBv5YBbToDQyajdLyirRe8MOtLefIPyYA8a/H94ZAhGvNP6lQTlmuyzt/B8gRQNfoZj3iknW09YiY3suzW6X3omIuVBl/BbxtBkcNN1GWvNWVpF3RBhXL732mQB98SkhQKf3m5KhUe4x3bz0Aem7dsLm/Q3XLtSCocJcXAUteAVa8Gzn1l7zP4wASS/qswqH2iJCSlW4PjK+OZd7BdekyXq85NJ7tPY+Gp/1I24rnRLpNxrOpBNrWu/Ttk2rtaP0fdT48OQXVIh/LM49KNDM0KZwQ2wwExl+J0nL1Pc6kYhFaUjkDiCI408YYi7wcoB2LtBKv6wDtxGWYrBYci3ayJFlN7VReyjVxQeOlPBZAnKph13SgbeakFpDN2Dy6DNLluHlPse7zgxdNY195gSwGVn4IMPczQSeZ29sNhtG4c8Z+PDl/Wrbdu34H3rs5kDQqwqbhnDXGZhNsS9Ykom2IixwvNMaO3xVhWTDzd7SNOOkGVDTproAZx7P2G2nbRQC/eYXKyR1UtIJm0GrVUXmzaYWa8BcYHYajYv61Km8xXfqP+y/K8hpGXctow0vm72KN/uohYNmbwMCZ0PvPsGU5Cx4D965pOSEQoTdKNG6FZM6jynpomoxHUo4xxGL158CW5QC9DMycynzH6reSmES07CuWQ445FURAwUq0VCm+CLR3794t87Zy3EMR78l+5vvy7VPKRVQsuhrQuh8w6EToDTvaAq2WJe+z/wE/v5+8ZSSHwbS7UFLurbJ3xGVd8wK0pG9fo/rk+z7qfOidIuf+DjVAc7+62Mbm5cBWKuyKVfYCguucfFGIcG/oBmQ/RwIeArTL96TGpT4E23jyhJ78llIJtEWpt+Fb5VpvlraHwJjw12qzwFpge8sKpbxZ970KFzJL405AnynyPch0AJuIZ1Pyd1L8LTpAO37ZxfOkA7TjkVpqnnGAdmrkmrZW5VL+yV3AbwuBcZehvFlvWzHUqR5gTQbaliaZVprP7wu0gFJwjToCI8+Ft0G7sIoNS8u/6iPgs/tCxwgyj/SYP8PjVZfGTCziRk7isa8fA35619YQxaq9Z4tSLJCU7JCTVEzjygUw6Fofa+k7FQZjRMmWTSZf5oL2FXE1JzihIsSP+EvLbwAtr0C5Tlf4ZOvOAS7+FPrujfB+Pg+YeD28DTtEtRbGOtxE60u6JubtpTKAqYVm3JMRcdWJXPgsheC2lYq0i0AqShGPhvyG0AadAKPreLkQR1NuRWuzOn4n0BZAyLRqG8mwv9YHGrsC3ScAdRqJ4kmUUgzV0CQjvTzDc8GuUkqAZW6OCvlgSrdEC8Htsf9Ged0WIb8p4n7/xQMhzgXml56HUlftuCxwPDtNhYTpDcSpUA6ml5AdLweJxa+VAzBGO9nlmBvhKeyUsed28HRTCbTFq4FkfFQWmaWgOTDz/6r13OLesRR7DF8i/wcVs3WawHCpMAi+X5H2kqmMMz3UuP+q61ttegFRxKa3T7K3dSrbc4B2KqVbtW0HaKdX3pF6c4B25qxFzCMRspf82sCDx6tnO4+Gd+T51QoczA+TaZ3gxZiWG34Y0kH6ErMQQzwgF8jVnwEf3RG+ObpET7xOrKz0IjAL523OHQSWH98p7r9hL8vNugOT/ylrlqny4QeelykX3VuXzgcYT0l277DFgLtBS6BJV7FIMtba++Mb8eX59cUVU8YE/drbNyjuAL8iYJsAhazljOumYa1Re2U15eXKLDm1gaOuhTFoFvSKMhj5ypLNtaHsM0X+4ra/cTGw8gOg50RUNOmWFpKecMvJy6pYxgHohmHLwurflli8yF8goOy9qK+oxQ5PQryS3cp/ntbtidejIr9x0mOoow4ogQp0iSbDefmb/wC2r67aEic77AwYPY4KkKtdcB3coMharMzXqZCBeAutx0dfG1ERJQqhJ05TaxRcRpwNT8cx1QZKzOHIGJ85WxEsJrPMfR7FnvKMOTOiTS2VQFs8Gyr2Ay/+uTLTxIiz4e06vlrvIoHfCJfKOMEzTNdthaNYVvHNy4CNS5W3RscR0AsUAZ4dZU+0dbH7u/AN5OVVZoQZMAPFQQz7dtuqrnoO0E6v5B2gnV55R+rNAdqZsxZxjUQs2kzHte47ubCVNWhfbVYf68PEC+Xqz5G1fysqsvOBpt2EEKzMhrt1XEJI4kNyUfUw/cafoufiJHvsifdb6c7E+uvZC23TErj429NnANm1gXrNYGgadPo7hiojzkZFl3HVCqbsiNBy7eSFhe70G39UFytajHkJoQWMaVJaD4BWt7Eie/n9Gxjv3GSn+ap1BsyAMfAEsaYReNSmdWre9JBtWeCM5H37t8NVp6FyKef46jUHBs4AOoxQLspZOfAW74Hu9QIkVGrUHmjVDzpcUd1R45tIbE+ZYQu8GPIyZyoDYmslObUt5ub5f1PhAOMuR1nLgbbPGAX8KnzAL7qVVUIPjApg+2+W0sSaSe0GwCmPQ2/ZVyxl8YLR5EgmeitiYc52Ifv1K1G+fW3kB0b+Cd7OY5ICTCzFxpfzgBXvRB9ocA26Zx9+Cbz5jSOOR749ZE030175tzPhr/A071vtQFuUVoueBha/HLscwj0RJd1a8jpKXkupBNocpXz7yvYDVFA36gijWfeM4r2IVZJWKAY5Lphey7+Muxzetocm5V21Oy55p9d9pVLFsYy5CJ42Q6v9/bI7ftZzgHYs0kq8rgO0E5dhslpwgHayJFlN7Zhsn/ww0CJngpJ0D8dylf7mcWDJq9I9L5pWTGhhW7GQlGXl276kp3IOAaDRjy2XY3YxPnb5W/a696W9ISDK2b8FmP83uDqPgrZrXWWOXLpPN+smQC5kaHL9VjCm35WWeDbuE/84UX8mXH/XzEggJpprpz8JHC9gLqY++/JhRZhkpzTtKmm89EYdrfQ3YjUp2gK8dHHEFiRumxZuzQWNLrqt+kqsK9Z8BSx+EeC6dDkc5eVB7MkE3CRYGjBDCJYIbv3Zgrm+JoGdnSkcKHWU+2028NBMNaUeR6JiyFxbSiEBmjlZypXZjOGNIBhZO5rNqSAxY7aD61OZc87rKG/UJa649XSsi6kooTWbKexcS14WTwCT5M0i+PMfDMMaTn4YJV5XUuLoLVf97b8Ci54D1i2KPvV6zYAB0+X9oHtsNDd9AVdrvwI+vC2wbcbYT78LRcXFabX6hZqgZW0NlTM9ukRC1zjiKpQ17xtVPvE2n4rnUg20OWbhXvCRh/KsNJnVM10hFnbflO4Anj+/6s/8np/6BIpKPGnb3wK0S7arfO4sx98GT14jB2in4mU5QNp0gHbmLKQDtDNnLWr0SMRy8MsHKh7ZVwKANv+OBCRT/yMX5HS6XQULVtJmeEuBH15Q+U2Zkqp5b6DvFLhb9ob3hYtDu3mGWqFW/WAcdY38or16hcRGuoedrghYSIBmljqNgYZtq6Szsn5PYY5Mf3d+cZ8r3gVtx29wlfrccgleyOqdWwdGrbow3LnWRTsZlyS6ncsljAzPv34GrF/kyylrWvg1oH4LoM0goMMwIYkLjk+Vi8b2lcCb19p6Tzhnd68joXFe799S6W6ekw+j/RBUkPE8VKEsRl8Ad+eR8G5aoSw0dEdnrHSPo8RDwz9UwNZganglsVyueFtZtAfMgKd2k6gXPMsixPALxibbKGLN3uuL7Y9Un0q7Cz9AUVl6UyTZmIK4p4pyafMyuN1ZwLxpcFWUQM+po96x7Dx4ma4uVBk6F2VdJyQNwAXEqNK9m3t590YVI874f+51gmL+aT1AiMZiIZ6zlKts9/sXgOKdQNtDgENPTbpC1Z+4zmSkt7MerCOhQAvJQD3f7iPh67XoDWPi9TUqfIGTSQfQZj+KIK8CWP62pKTyNuqcVstv4gusWpDvzcp3AtP/+Td+3K0oyW9hKcX8s7SwWiqIFeWOBfXd8sJd4+TqWLSTtTvtteMAbXtySkctB2inQ8oHeB9i9WKs+GOnqLzbvlIFaPPvq9mlUD6gjCejlY3paIKKe9wlQHkpvJ/8n71VK2gB7YT/g0EwRgIrAO7DzlKET2RVNgt9m9sMDA+0z3gB+4uVi3QyixVfu2MN8PMHAnp48ddIHLZrfWBqLLKhdx4paXOYDsqbUydpsePmRVk8BgioTOInTtaVZVn7eNEPdUmRC1zxNuDFi2yJR+s0Eu62A6DR5ZnWVMo1KweG5oLRmusQBmhz/Ujm1muSuEB6P3ugMu6Q4QCTbkB5vVYZQThoSxBJqMQPtsTou1y22PbZpSizgojrog1F5L5pmbx/Ucu4y+AdeUG1ki2FGqNYedctBL57Bu5BJwCPzha5iWKRvA7Ne0B354T2bOk9GeWDTkrJ3uL7E+yJYp41Jj9BPOCAbXJvmGnaTLKoZBJGWcqLHavVu9xxJMq1LNtyUiRx2cArlyseh3hLrbrAcbfBk103qqIp3i5S9Vy6gLaAwa98IQtUNJ3+HPYXFSf9u5YqOZntyj1h/UJgwe2hu5r9EIq1WvIdETK4LLdSIhfvAFoPhFHYNiWpAv3jzFMtg2S37wDtZEs0cnsO0E6vvCP15gDtzFmLGjsSAUES13xewBxCAu3+01Deb4btS1KyhSLWOVo4f/86ZNPu7Bxg9EXQl78Dw46rc6t+0CZeB4Og9fkLpE3XwBnQ1n4LLH4psI+2g0IDbbqinfZMUkGDlZ6reDvwxTwVw8+x0a2acctbfwkfg04Q3HOipMPSG7QRl/ZwHggmK3CsCgJ/NmGOK9rzQgZTKxd4aLoCzZFKQQu4h88VZYrrj1UBbRskeWraLaxVUdyXK4qBzT8BR18DI68BDGFw1mCQMZox6D43/2hjTvberSntWXHdL1wA7Npge9gCtNeqfRq1NO0K/ZTHUZrTIGNAjygca9dWCrfa9eEeMA147ORKoM1JMc68cafQip5eE1F+yKnVdjZGlXk1VRAgs3GR8kxhoYv7jHtQVFJqKQ9MZUY4NmZpo6IIeONqZdWPtfDcYIrB+m1qpEdLuoC2KJqWvAQsehagF9es+7F/f1HU8z3W5Uh1fet78+y5gYSa7LhVXxhHXSvfRbn7GKXA638DSL5ploEzYQyYWeM8H1Ip12QCbdODgN/gmpxbPJXydoB2KqUbW9sO0I5NXk7tEBIQ7e++jQCJcfxKSKDd91iUD5gV9jLpn07DtHyasY2JxnzJRTgvNyyhFocul/2u42BUlENnXttoZfDJ0PscCxd04OETVL7mDsPhLmwFvHpl5dME0817hQZ4PY6EPuzMpMWcWhagtdTI32HlmBYQqZcrqyHTnUQrtHDPfhDeFop8KnhtTSunpCRyZVkcAakKCxAlyXv/AqjEiFBcQ0+DRlD85bxAkMNnGA9fr2lYYjrm8NX2bgL2bAbyG0G74F1gwxIYRTvEfVws3FP/g5KsukmJpY22BDXxdzkP/vgJeOv6mIYv7x4Z5b1B8fOhWmnRC3rf4+A99LSkvTcxDTZEZbl0l/wBvHAhUKsu3IdfJLHtzPVe+U5oQNswni2DT0JZj2OS5jqe6Hwy5Xmxkn7+v8BQnKm3Qm/YHi7m2KZLOLML0DW/10R4yr0hlS8CtlEB7dsngD9Ww9ix1jobI861UQdg7GXCeF9Tw0bSBbQDCFHrt0Q57HseZMp+M8chXjlUVH96j+KNYOk4HDjsPHgMt+wxleLu/tDZFKbfZSvMJtPmnarxJAtoyznLNIY0HjRoA71OE/G8cxTfgSvnAO1U7eTY23WAduwyc54IkoBof0l69LCPMMn3e0igPfR0lHU9IuRl0orlZf7l375W+atLdgGMb6QVg8RWzXta7quxHqwyTleF5eIdaiGFvbrfcTBK9kKnq3Wk4sc6LqCTFzgSwWXnwT32z8CH/1XzYGnUAUbtBlUBXnaeWGdK3fHlnA0eHsE0L6aun98DPr/f72dD3Dt5wWSMtu1CSw7Jpwo7WIBGXDF9RE9Y9qa6rNKt8pCTYHRTKV1SAbblosw47TdUTHzIUtAM7mFzgcfnAJ59gUCbrrut+vpI6UJbxUW5s3s9sHcrtPxCaKPPl71gUGFx9LXQi3fD6HMsSvKbO0A7zBLI5VMYr9+2vc1Y0U3+AMYP+6dkC9UCieta94PXXQuY85RYlmI9C2IamM3KKrxhq0pzxPmMvQRY+ChcvyywB7RnP4hSdx3HQhMkbwE8qz8GPvWF89SqC232Q5JrHC9eDOzxs1A36wZM/ldIHhAqgNiWa+9mFQ6il0Nf+BQMKh5DFeaC7nuckCTaIYezuU2qpVq6gDYnZ4YoxBpLXy2CidKpdSehYppZNKDJ3cW0okr6uKfPCn1mDZkDT9cjM8bjprrlmyygLQp3/zSfk/8FT4P2jpyDFtgB2tW94yv7d4B25qxFjR6JHH4f3wGsqiQ+qgK0adWdPa8Ks65lgd2zQbk5R3LZJikV88627BtzDJRy7cwDHpqhLM8hiwH3mIug59SG8e7N4dckKI+2gHi2/en/gJ/fh9a6H1zdJwBv3SCAD/WaVnUbJ8hmrtpGnZJGbCLWH5KN0fLrV8SaTav7+h9i32fNusMQN936csmQtf7kbiCUxX/4mfB2OyJp8wmeA0GcFoFgy9X1cGgEbD43Uys+lg01bCdW6rBkVKZrPWP3d66FVqchNKY6GnEu9KfOkJQqzNBmjDgHRaVlKVEmxL44mfeEXD6fPD02hQ6d86nkondENI+Lhu1g1G4oTN6ipKrVMCPAqXW+PHqyECxqbQ+Bq90hcL30Z+ilPu6KvPpAE7qOB3mU9D0W+iEnZ4x1Ptqu4tnOP2ZstlmfrtvJZue3SNfWfA7s3gR0Hi3nqWSG+OLBqkM9+lp4GncPuHhbDPh0Hd/6s+KJaD8MGHsJvD9/CBRtByTdn1tIIcmngQJFdsUzLxWKw2gyDve7CWRN2UsaRcMQuZteX8HPphNoxzuvTH4uXIiUfAvfuk6lugwuE66Ep3l/BwD65JIMoG2FJT0wtVLaA2eirPdxjieQA7Qz9ghxgHbGLk3NGphYc1CuSMZ8sUpVgPYRV8HbakAACLMssL99odyc7bg0UzT9p8EYNCtmsK2sbQ+Gzy9bq564SxuubGj8eH5+n7Ks+5dGHYGR58LboJ30b1rTrJQ6dDNevwha065wNWwrJGTeJa8DtNSzUOHAy2L/6fDWKghoI5FVlzXwFgHPnQ/QpdKvMGuSsIzbSLNUZQx1GsPoejj0KbfIpSGnfB9A4BmqUHlAK2NRauLy1IU5W8Vabv25yghcQ06Ftupjxfrus67IJZkX8watw5PR+bXkZo6pzctFGaM1bANt1jwYv38tbOheTzH0DofVGECUyH6K51kVnlFL2LbjKeJ1UboP+GNVaGVYQQthqLeA6sjz4Gk/MmMus6Lo+vUTgIoo7r8hp8JtlEN/8wY1r+bdYWTX9gNuhqTTwugLk0Y8GI/c7T5jppMUl21mVSB/AQnGeG43aAU07gzwrPClyLPSO9rtIEw97iuebyx8n/nfOUtfUbHAwWXE2fB0HBOwJ8Qb5qc3gYWPB56Lh18Mb4cRAqhNwGr2wb/LBE8Jc8AcHy3yPAOx/nvlzkzrPMkD8xsCtMB3GiWeU/5WVz7vAO0EN2CYx8XbYtsK4M3rAmtQqXvcbRmR4i41M4+91WQAbfaqFP33AL8sALJqAVP/DU/tphnzDYhdMql5wrFop0au8bTqAO14pHYAPeNPSpXopUI+OkY58O2TwM8fIkvTlXtt817AoSdB96X68O9HLqYbFgHvBlpgbYl44AnQ+0+PKT5HATW3cj/eujKwGwLgo69DRUOVv9l0G8OO31RdWjua94RRr3lE9mUzn6jZuJWPmc6OvJC6suSySNCaTCIP+QDRXX3NF1XEJ9bCfdsqwb4tAfsq5RVI6h/vsLOA7kcoNnX2E66c8hiKvO6UWYEkBjg7C/jigSqxce4JV6i8vmu/kdG53G7oBa2Auo19BFRUOUQuQhhHy+qOtdCY+o2KF+bRzsqD0W5IzMqdaP0dSL+LZwc8yqIdZxH5G15g3x+Apwjgv+fUVmAip3agsmTQiSjrdWzGWDMs6ysZiL9+GCgrRvbgWdCZQovx5xu+h3f3FrhzctW52OMoGG0GieImWaA0TrFHfUwUeQwZIckjc3Mzc0HIogG9J0maL095he0LsGmpZZP8RkQCunIG7FoDvH5V0Ag0eV9L3fkBZ6t8m75/WoX2+JcM2z/hFsGKfSY/BcMyIoVXdBwBDD0dFTl1rZhyB2hH3d5xVbAMBZuXKa6AfVuBVv2AgSegDFkZcy7FNbkkP5QsoG0ZNPZvA2oVwOvKDutBJ++9KOjo8aGnxNMuyWJKWnMO0E6aKBNuyAHaMYiQFwFeABIFpDF0mZKqpnXAAoR0wfRzPyP4i/fSxzZ5CZJLk1GBCkOTlErBeZE5Mbm46aXAc+faS+kTShqT/4mywo4xfdDkkpabC6z8ANi0XC7DzHHNS683t16Ahdk/f6udC2CkBYuXodvOJhBZlu0CnvVjfndnQWszEK5WfaHVawaNsdTlpTBoWft9oczfoCtmtJJfKDHm3twCaCc/An3bKmhMlROupChVmX931sd211pgxbsK/Hv2w33U34D5V6s86PmFcBU0g665bVmy/dsXxQRd0KkYOfo66C37WW6kkVKDRRPlgf67KLIq9gHPnJ3QVKkO4fsi74xPN6J7dRWX6194oe09Nab3P6GB2XjYTHkllkfPfmTn5qFCUynsWMRtmXmtt/wEY8sK6P1noriCnsvhU87Z6DalVRQvQy7wzo32w09IIjbpBniMrIhg27LUkgyPJIb7dwAMVyloIc+FShVm5Wmn5wpTKXJnMHZ/9AXQO4yo4nEiFu3NS4B3/xkop2l3wJPfzLYyIKVCDtO4BbK/egjCiWGnkDPjqGvgLWwv4MIB2naEFl8d7kXuL3nffUqiZCvR4xtZZj2VLKDNWVHmfC/MkIlQM1VelmXAS0zZWgJMufmgIqdzgHbm7H8HaEdZCzOHrLg0VnjEqmlobuvSXdNAt5VX+bevgFUfBbL80urSaaQwt1a4csSqG+/8+NGhm/bevXvDtiFu3My5uTw20qSAJWvaFYaP/CaWsZrKBllXPwtKMi3M8b7m/i6MdtsQz4DvnrJcplHYDu7+UwHm9/75PWgbFkOjtp1WqBa9gXaHCoOqsfxtGN+FcL/077h+Sxj1mikityP/Ble7wdCfv1ARVwWXzqNgjL5ICKpSXUwliJkjmOznbuZu/YDp2xZKSi4z93NCY5l2Ozz5zTP6Mp7Q/JL4sFi03bqktUpLGXwyPN0nZuTaCC+Cy4WCggLs3LnTEodYWZa9Bnz7lPq7mfeiJKdB3MrNVMvZArURuBHCjqFZD2DyTSHJycxn5Oza9jPwwa0AFRBmoWVw3GVhgXqAGzuzBDRoBd2VLYrS4Jhqaw785tGqnZULDJwJvdWAjA4Dscb9DYk2VTiM7UIPran/QVntJmDaLX6LMynW3PY8nIoHhASSCbTtCEQMKlt+rFSuHWTkdA7QtrNL0lPHAdoR5GxZzUi68sMLCrSwMA5t6BzoTbrF5LacniUN34to9b0lwAf/UTGo4QrJYMZeCr1Fn7jnx5ecrsx79vhkFtSXRRzElFhhXRDtSUw78X+oqN1YKosV0gec/clhYgHh9npNfi3L0q7rpC0LeWEM16sQUNGKuG8btGZd4RowQ8Uj+l3ORDaleyvj4Bt3AsZdAWNOjV2IAAAgAElEQVTnOhgf3xV+Qi37yAVWZNhrErThZ8DgxfadmwJd0Vv2ASb8FaVeJNUl3q6krdzhi56xcpgThCesPJn7PIo95RltcbQro1TXU2Q1+cCDx0fPd+43GBqu1Xvr+4f5F9EGXAMIhwoLCwOAtliHs11qj9ZpAqPr2IzOtyuKgc0/Kmt2PGXEOajoMjZkaiw580p3qpRoDNcILi16w5h4fUT5UJ4823jeR/IKMD0NTOWqSXSWyd8GlWnhF8VJEU+hV8Fx/xXrnwO04xGg80yyJJBuoC1K37w84OtHlEV76FyUVKiQlIOhOEA7c1bZAdph1sLSJJMM66f3Qtc66hpUNO9dI3JrihuNSwdevQLY7ZcOJdJePOpqyaFM17NYSzSgHT7Gzn5PymKkAYNPhtGoE/S136kYqYoycRvWSIDV9hDo9dvUCA8EAcuMOdzyk5AjlbcfETbfuL+U5IOSm63Y1GsXwj3qXODjuwGSggWAGV/sMVPbmIVxr8feAuOXj2D8+HpV4ddpLG71FvlUg9Ywpt0p8pTYJ8adkvyuSRcYjTqGdfW0v6qJ1ZR9tXWpUgL4whMiAW3lzh/skKxYfKU07gjj2P+kxUKf2Mwz52nhCuA5Q6KssOdrpVJM8mYzrIGFlkZyIfhIr8xlCNvQnCerZDHIHEmokQQDbXNfmq6P3J+ZbGmU9ZzPc6kq+aAtWdduAJz0cMg0bGLNXvhIZJfoqbfAU69NUr0WzHhwE6Sb8yBQ59mWsHLOlmAiV7LuIK/9FdgWxCcSS/tjL0FW1zGi9M7kfRbLlJy6NU8C6Qba8jnJylJhgkAAJ47pDWdmJQkVnlLzJBw4YgdoZ84KOkA7zFooILgaeP1v4VeLJFEnPYyi4qquapmzxCqeRdIiLbhNxbLaLWSQPvE+lCIn5ouHLaC96gNF7BJHUYRVXqU06DwSRos+0Je8Ji0JACd+YixyrTrQG3aAMWg2jFb9BbhmokZTLIG1awPzjlfS6HI4vIedZ0vJofL3bgNevAiugTOh7dsCLLg9pFQl7pUhEP6s5C3/n73rgLKiyNpfvzd5GHJODiAZJCdRMooiKAgSRFBxVdb1d111ZVfX1V3dXdd115zAgFnAiDkHRFSSgSAiCIjkOMzMi93/ubem37yZeaG7X+r3puqcOXp4VdVVt6qr67vhuydBO+Ov0Cj/r+61Qa1zC4FmXURKKx3xEAi6ZClKSkSOaj0ujarT5TTV1iHhKVEgyLjKj7AyINSl2UFyoE1Ce8h9XISF8Jc5V6T3oRARVYM69FJ4O442pPCwsI0zsgm5qWZ9+xKw6rmQ83NSLC4pw47tFWmVqqfao1jbOo0FU7wzOzyJXcNiaOf+1/ZKkFBAO10Wnq3vFArwxKzYhjzpP3DXbV0DLBOIdxBpHL2Dmgrtl2+qnkH01Di7fAYIknasFqkkic+BeDqKmgKN2gEdR0Kr0zjl3wo+173HYuY7QNv+yDrrrxJox7aDM7a1lVA1K8JIBdAON07+Rh3eBhC54InD4C1slnHfeAm0rezSxLSRQDuMXPlFXE0spVHioojspVGnuGrb473UrDQo3w8svtJ8170mwd//fEOAL7hzQ0B705s10q1EHaCmwZnlBMqPiQsSXdJPmgit7QCo68Ra8UV+3xYR70egqXkXYZHtPAoYdgVc7viyfUcdc4gKOhN58E+seaXc1JRHuNc58BQ2M0TyxOt74AcOCXCOvjrgQh5qXDohm6J6AU95pTV34j+g7dkETWflJUt2w7acq7iGVfHSlxlo27Xwu7vlI+DTB2oAbVbQUA50SsFGLOx0wQ9VaN+07AHMXQy3x2trrxVSLughEzQVUnaQ5SpVSo9AmrlqKeACHigUdmDIq0YBGrZhAET8ADXmc/Il8HU53dZrQ+uRzkC7uoeI5Xc+DFim+HVl52pg3Uucfg+tesG/4jHxbupl+JVwFw+N+RsbYIg+uFWkXzu0I/x0Oo8Ghl4Cj+owdAZblkuEhuw2vvldYMWjsXXvyELW5S+z67idCfdim6RsbVYC9M2gbyUpnYkMl1LCJdKyayegzd6DT10olHpEvDjhNtsrbM2urwTaZiWWuPoSaIeRLbu0LX8A+OHDyNIfdgXc7U5N6AEV6/Iz8Fi3BFiz2HxXZLW/4AnTwMoQ0N7xBfDR3abGxCC67EhVt9S+50Fr2gnq929WAm1ycyQQRXkWW/WodH1u1Qs4868oT4Flm3O/5uSwFZjTR5GigNyuKc9zURN2v3bkFgZS2xh12dfd8JVvXoaDwOGSyAqVANgmaZHLLikrep0DrU0/aCufEGmUsnJCgxtqY3OgHUix9ObNyN63MWDRZpBN8z2wLTzADt6NE26DRiCPGMfzG9oG0NUggSPrMKU6IascESDVacr/JbCtu8Em22WU3Y2rkWdxbCzt+dJKYjBDL38gfIFYuSuCuYlV+fxH0yJ2Pu2B9tZPgM8eNLRUYSuFYIen97SosADKo1OFZYnKsCsE8WKF0hTOHGD2Eyj3IWZPJCbf3LkKePdfxvgDCPiTIt2Rn5LvOwNt8gxZ80JssidHnUuXoqTcE7MMYx6IDToIzsmuhwrYYFhJHwJ7dvy6TrwPTTpwCBmRmCZKQWsnoM3fpzdvBnZ9C3Q7HdrQy0ICbVIap0uIT/UNJIF20l+psA+UQDuMaPgQWrcYWLs08mqFcYmzzxKDSckUYmLettLasC5+HqVun6n4rmhAO5zVK9IAOS0OkVrs3lA1rnbU1cK9+cdPuLkAVF7hllrQEJozly2zgdJtHLShlyaVgIgvTTk5wJZPgU3vCat1qNKwLdDlND78fSoMMb/rslS+fBIO1cOWXCOlMj5ZAdr2A06dB/XTB9iCHfZjS/mML3zGtOLFyHjiWYeVD4of2W/fAu+ezSKlEuXE3rs5NOlS9YePvIrzofqXLwBf9sffAl+91ikF27ReNC9Oy0cxm5SreeuKqkzN+jzI7b/dEPHXpm8g73uiLlHVxRd4v1+4gt3yWUF2+Bfg2B5ry0wZEeo1r1SYjbwKvnanpHQ9jE4k7YH2rtWCQDOWEoIdnt3S3YfgfPH/xHtJRI2UA3rgLPg/e0Q8bfS18BcPNu1RVX2ofP4e+wWgtISUss9oadoROOd2lJWVJ90aLID2i9YU5NXml/WbJShxWU/baVRcdq9XhX2eQst6TkRZefLX1g5yYgPM10+K/N9ULnwGpV7hDZWIYiegzfcDuo+V7IVWJNzGq4cU8jdM8QnSynotoXUek9Q7Y6xrIIF2rBKMX3sJtMPIUrChHgToohiukMZ76j0J1QLGY6kFmc2NwB4CqBbKBU+gVM0ydQBHA9qBD97Sq4DDOw0MSoOT4oNpDmS50wvFc174DPyrXwAO/hz4Z45FrsgNHhJcWMi/bWCQNaoEmLCP7hTWe32MBQ2hNOvEMcEK52dXQaRQGllbycpd0BAY/juorXpFZR/X45KVT+6Fw10CfF5xSTUzYLKEj7wa/k/uj9yqTV9o425MCzcruqgW5mbB9/5/4fjpU5EzPRSzcfCMc4uAUVcDTU6En1jbdetrfn3g3P/C7SxIiXUrkMro4E8AudbuNUFMRefUkIugteqd1LhT9gr6+Qs4PvofFG8psHujmR1ZtS69zwPPh9agGFqLblAors4rmODpYmgHfoBwk0tnoM2XTbUMeHqu9bWjluNvgbtx5yrvjp55Qnl+HhxlB4Bj+4D+M6DVawF1/1bOcKA26Rj1/Is2sMC3hkA2eVSYLadcCl+nsUlX6jDQ3viG+fCq6vNTFGRd/iqOlZQkXVkQSdR66lSdMZ5clxMF8vRx8L3u6A5BCkvl5LlwdxybkjPd7DaMd/3AHZfSezY5EVrPCQn9rtsJaJMs9ZAr+oaEuiOyse2bpZWKrpkLUO4sTBuvEAm04/3GWO9PAu0IsmNXs03vAMtDABeyGE24Fd6iVrYnUeB5fHy3sKZaKZcswfEyczm1owFtGgYfZD9/bsh9nK3UFE9Tncm450SA4siJZdtMadUL2pl/TeiHJRATSDGI793OLtpKi+5wdDwVKGwsLn17fxCKg6wcgFKxUN5ZbznUnz6HRu6UA86H1msyW3QiXUKYVGjLx3CQ0sJKKhiy8nc7A+rKRZGlOOB8eHucbfs9T5Mg+devX198RFcvBoh0KZwnAVnqu50B9J4MrWQf1LUvAcHs7NRh237QTr8h6VrtQJpBSlu2ZomZXV61LsWdDvstx5wnMhZPf6juws/EaG/+LbTl3cBsFPK2GHgBlNwCaL9+Dy2nDtTj+6E584B6LYDWfaA172rbzALpDLRFurY6QuFMCkArhcIZyFoWgjSUvwGUcvKHD+BodAKUEwYwGKR3lpQntE9j9cIwRGwaaV5EzDdzQdIV6jzukl+Bl/5gReqVbZp1Qda5d9iKDC2g/NjwlvC06zgCWqeRCf0ek0ACnjbPzxNpRcfdCHezHkk5D2NbxMS0JmUOyYTuFqToSGQMv92AdjSJsqLr17XCtZ7OgGn3o9Rl7wwRwXOSQDvaCifv9ypAm14yPcdkqCGQawX9rsd4GhnmoUMm4/GMdJqkOgGyiD3rhXsN5Z4mVuLiwUCfc+HLrZd0LbeVqfNlZv0y4KunzDeni+y0B0y7ChsB2oFYWgKGkfJ66wRnZOUoC9pPFLs59R6o378OzYq17ILH4VLyTDOqGxUiu2bt2wi8fhOQUwBHn8lQipoJV6QNb1e1zBMwpAspxcQTIOo3XcRJ//w1tPZDmTm9tLQ07KWT13jfBjgpBvnxmZXpkowOdsSV0LILoG58L3KLmY/AlVWUMJkZHa6RejrQ9u1azxZtpU0fIfOda4ULM3kREMBu1oU1+hRqoG75DBpZvsOVibfB3UCkMUtGYffa/Dzhurv1i9gfSXMdfwtcPmEFTnShS1xhQb4A2hYyDCj9Z0DpMgb4chGw9XMG1X6NaA2quTcSW/SweVAbdYjZAhpvmaQz0CZZCHLBj4FPw3u7iLTnQWnxgoXYZyr8faeFdf/mUIiKvOmJ8Ezg8a99IXoYWKSFn/EwXNl1k/LO6MMIKDmev1ww9FstQ3+DrF4TbQW0WYlwfBfw4jWVs0qSxZA9bcjDxueBWtCQ92WsyhyrS1Ob2qUb0A7c/ykcz5EDr9+fFgYGfU9JoG2ft4uB9rJly/D4449jx44daNu2LUaPHo25c+eyxZHKQw89hNdeew379gkm0EmTJuHaa68N5KeLNJ10Btp8dQiOi6y4DNAljy7aybioRpIt5zGGIImJ9KFgLa7mEimPoiamrfbEwXPg63aWaYWCEaBNT+IPruYR+aOP/BJ2uhzjSelY9PHnFAITb4PmLoW69kVrb9Qpl8LdYVRCQJOQuRtY/DtOFeUcPFuw3H7wH5F2LKgoROxEeb/Jqk2/eYgJWwGGXgqN4rX3bIDWcQTUgkZ80IcCeZxLOy8Hzu1fCVenaGz5wQMobAjMWAD/F08ARyPkWD9hALTT/pRwq4P+3tGcdDZtndjLzELTu9ugQQN43/svsPlDXgelWWf2JlCImEtxQCMiOJ8b2p4fqipxwj2o0yiow65gpUeiS0ARRQzJxEYfr9KyJ5M80QVTZ7/XLYjxtmjw+31oC5xE1kbKDZqLIcZxQOkzBUrH4QCR1qh+aEQYmJUHvyMn/Hk36g9Q2w+11eU53YE2u3gXFgKUz7layEKAxZ+sgxSWQYpoRakkUqzbAph6N8o9vpS5XHLo1Ad3CkWN1TL6D3C3HpiQb0WkIbGS4OcVYdM1Rp0OEVvOeAjO7FxmHU+0a3bU8VRUSCXQpiEwIamiRL07GZ2PrBddAukGtPUZ6WRodnl3okta1JBA26ikEl+PgfaCBQvQpEkT9OzZEzt37sRNN92Ea665BmeffTaP4NZbb8XgwYPRqVMn/Prrr/jjH/+IefPmYcaMGVFHmO5AO+oEDVagDwsd7Ho8ocFmIasFXJLJuqv6odZpEvViye7jq54RaVSMFrK+nncfytwe0y5FRoE2DYVddAhsU55vsjaGKE5Fq/yNCMPG/BGa6oP65dPmyG2C++47Fd5eUxOipWR5f/YAsOUTOIf+Btj/I/Dev6vOTHFAqd9CWLKP7mFijhpEPcSo3vNs4P1/Q+s5Ef7e50Gt15LHXB0UkaY+6/DPcJTuF5aCCIqLKgMZfwu0nHyoXz8f9M9EHlfB8Kz/69S74S5oltDLJu0bnZmdyZHIFV5xcqoxLTufL0akaDDy0SOAQK7j3ofPrcyTbXTvh6tHQOLi55PiRsqWF4ot//ieWEdds33f8zgelmVMihkie+l2Rtzd4vlCvekNYNULcPQ4AwqBfFIarH8DOLA17LyUZl2gnPEX4P3bmSFe8/sqiGuaQy1sFFlfeNbf4WvaxbRyMP5CFj2mO9CmOfA6qi6AuD4qzhVWfrpLBe8EkVTqhfJRN2gDNb8BtPF/g7ewaULOWKPrxUD7nduEotZqSVF2kYCy7d1/VjKzm5lDxbtA31g7Ae1UuY6bEZ2sG18JpCvQjq8UktebBNrJk3W0J4WM0b755ptx4MAB3HfffTXa0+V+8uTJmDp1KmbNmhWtf0igXeF6d3wvsG0FuwV7surElJuTLz2le4ClVwv27Qm3wd0wsjsrWzzzyYXzFmDXN1HXjV1qJ95mOQbdDNCmwZAFmC4DCsUlf/868Ot3gTFy/l1y36Hc2d3PBLqMhbZzDdT1b5m30AfPvOdEePvPivslkN19FS/w5Bw4epwJhSzGL11bBUQrzmygQSsoPjewn/KB+8KvyehrodVpCm3NYmh5daH2mw6t95QaxFb6pcz58woo5CL91t8i54olcrnR10Bp2R3q54+KNoSt2WuAcmuKIXFe5j7ToPaZmlBLLu9ryiVObvXfvlLTXbJRMdBrMrQOp/D7E82jhNahbq4D3oXTo+93MzXmPIUyv8O08snMI3gPOfzAs5dWBTFmOolS13H+Amib3odGRIJUZj6CcmeduFoeeU03LAO+fkY8o24zONqfzHuO0/SRBwblNHeXAZofIE+V3EKwy/jO1dCI2K/sCDR696k0aAu1TuPIQJv4D2Y8jLIQyqhwIgnEwVMFReG1JWWWEYVO9T5pznqIFb07ZJXMhO8gK0ThAz65D47tX4oMEEROGcpLqsNQDjlyZ9VJucKDlZ4rFohzxWqhNF+NOllWMuqeI/rjSWFodG+xd1S2U5zn4TgmQs1r9DVQ253MSnjKV24noE3DTQUZmtXll+1il4AE2rHL0EwPEmibkVZi69YA2nT4T5kyBUOGDMF1110XeDpdat966y0sX74c27ZtwyOPPMJumdFKJlwwos0x2u9FRUXiwnx8PxAHEi6+vO5bD7z1d/Hokb+Hu+3gqJcA/mATkPniMQFmw5XGHZh52V/U3HJaFbNAW9xvFQZagTzTZCkpOwwlrw4T5RBxmLZnE9Qty4Fju6OJPfrvvc+Ft8+0uANtjpfe+Ba7bztH/k6A7GDrHaWaatgWClmDjLDgEvg4fyG0b16BdvyAAHgdh0MbcRVfYoMt28IV3w3Hjx9BqdcK+O418Vd2uFIeBLA7nAplwAx2nyYQpO37ESCyORoTKW94QRxAXl2AYmSn/A9ery9h8a98iSeL2du3Afs2R167E/qzR4PL648Itmm/F/mOwPvsvOh7wUyNqfegPK9xXAFp9cezNZvIzyieP0HF0X86M9/73/w7QFbIqfei1GXMW8DokHg/bvu0Zso5ZzaU5l2hEMkM8RLk1mGAC6+LXfwdtMaPTIJGYDy4NOkANa+C4C7SIIb9Ft4OIwy92wGr4fKHgI3vAtn5gvG/eLApxVIgwwB5lGx8Bzh+AKjbAtm9z0a5kptywGl0zSLV0xWiWYe2AssfFvLSzxZi7D9hgEjR1bo3ex64CltE/S7FY1yR+uCzZfN7ljgCxDmoABe/YClnO+0J+h5kkUcWua6X7AcatAaKB8HrMx7zyd/uvFyAlGJrlgqlVLhCqfBGXAm18YmB85o8e+wGtBO97rJ/e0lAAu3krocE2smVd6Sn1QDa9957L5YsWYLnnnsOrVq1CrSlmERyJ//pp5/Qr18/XH/99QGgTRf9Sy65pMpzaJEXLlyY0MuofcQYeSRMMPfyH4X7cIdTgdF/iNkaxn3+8IFgzuw2jrXjRgg92DrscAg35U3vC4sEEa2QBZsYr9v0BYoHCitmjPkUaYxWYz6DCfdEqi4Aj04T841XGXgBtF6TYp5n9eHw2pAbvCNbxF2/fWvVKnWbC2vxHhMpmgZeAFAKrk3vVayzAvSZwqzk1WXMOaPJSkgEUo3aMahnEE1xsgTa6fkEaLZ9IYDc0QhKi+KBwNjroZG77wkDgU4jDe81o8vEexKqyHEblKItYvvWvYEz/xpxLNSvs3Q/tOcuNzCUEK7y4VpNfxAqeRiY5TswMAq9ipPe0UWzahDmmegietX8elBmPgKNFCqKk9Ursb7z1R/Ka0vA09AaVLTuMBRKQQPgjZtrzoEYxklRFK0QYeVp1xs6f3iMWz6p6qJP8ftznoaWlWt4nfm9IyURkTsGnVNKfl1oE/4JtW5zw31Fm16qf2eLPX0/CupXHQq5+ZM30vZVQNfToPWfGfc9ZXbuvL4+F/DkbA61Ml1IcTD6GkN7qXrfvCcoswS5flOYhl4oLOv0P0MjF3uD31k9ZaVCKRxJ9iRnUtT6PAC9L61OYrJAtBtc4/sdy7fYtLxkAymBEBKgPWj0nioFGLsESNak6JYl9RKoArSffvpp3HXXXWyt7tu3b8jRkcvTZZddho4dO2L+/PmBOt99V+nqq/8jxXyTFrW2F9JGZyuqAFatesLjjZ0Yhj7gOkO8nkvWjJzJalzdnY1eTOorGrmakedQ3+Qyefw4EXvFXsjCh1fni3RYBosg6hH+z0JxUGGp1dtPvhOeuq3jrgzisVJu2H7nQSGX2U1BTN7ZeVDIokEugOQ2brTUbwVMvQ/aZw/A7wtyM5/0b3jrF9ew7HKcs+YTTMHbv4ZC7PGkTFF9DMIVUrSQFTs4tjJ4LCS3AbM43ZVKlvRdFe83XTpHXc0poqwqUapPmSw+pvkDqJNhv4W/46iwYRi0BwvzcuB7eHJEKQvlkyJcYIOJnMK1mruYrelGL8hGl1ivx+fF3vUizCPRpSJHcCLYnmnoupWX3gcmQzNQlC6j4aBUUrq7ud6GlEQtusLv8wsrY6RCFnJy8S8ri/pEfle+eRFYHcxRAE7n4s5rZHif83u/+Moa3Ah01vpa9WEiQfJASffCa0pEqQsmC68XUiZSIcBHTP566TUJvn4zU27RpuHwGbOGrMGLzYmf9tnUeznOPFqoSvWOad1zfKXA878FCOhXLxTiMP1BuLzG3cipC/3bzSA+6D2gbxx9u0N9v8mrjowliTqzzAlV1q6NEqAQjlDcMrVRFsmYM50PnJpRlpRLgIE2HdDELE5W7Pvvv59J0SKVO+64A9u3bw8Zw129nXQdFxKhjyNtfAIn8QIoydw9fPnPzg6A+2h5Tq24jkeaD7tj//AOsOJRQ9Nmoh5yaST3TTIfE2Nxfj34/RUXQUoNNvORhJBacajAU3PgHHmVYHoPcttW6reE4i2LHDsdboZzl0Bb9yJ8R4IAS6uToJ15c0iFRiDu/ddvgVXPM2Mw3cscdBneszE80D9xmCDKys6Dfw1ZvKvlzy0eBG3s9TXc1g0tTLVKzB2QmwU8Mcu8twLFvp//aNg1DLCOP3VJBJCniT2tu86T23CzzlDJollNL8NDJ2+A6Q+aTndnRjbMNPzNUuEmmujS9XSoQy815SJtdkgiPdRHNd3Hw3Tk6D4OClnqqs+/cXtoBQ1qKsxC9UNW70uWGlonwYC8G3iROC8qSr2WDLRJUWjEc4GZuXOzgcem1RgNvYdeOncMjsesfFNRnwnGSF6Htod//LDfwtN+eEx8JPGaW4CjZNkN4uwzWoZfAbXjKEvvB3+zvntJnL3hyqnz4OkwIuEykq7jRhdc1kuUBKTreKIkG7pf6TqeXHlHehoDbWIVf+WVV3D33Xejffv2gfrERE4aqEWLFmH8+PFo3bo1Nm7ciCuuuAJz5szhFGDRSm0E2sGW4nQF1sHryhcG1S3cjLd9Kayg5KZ20tlQGxaHZDyPN9BmcigihHlmLrMQRypsyS4/IkjGgkvTTtByi6ASgjp1HnwdRyXEwsRAe/Hv4Dz5Yo4zDRSHA46mJwJkHTZjzdY7mPYgtF3fwLe7mst5hByvVdLTleyBk9zFiRRo5xrhykgWKQKslF+ZyMY6juAYWXXL59C2f0m+xKFFPfhCqD0mWLqABnfIIGfXKuD9/0Q7SkL/PvUeuPKbhLQ2BYD2yqfCgla2Zruq7RVi4K7XIjSg6zcN/t5TDVlKrU0InErJ8el98U3pFW4wjdtBm3Rn3DxPQj0mkB6KQgP2b4kqFkfXMVAoBViwRZtS4DXrXKGkjGLNpidUWLRLSqqm0gv3cJb5vk3Als9YwQQiSsyuYyjGm/rknMeUL3zhlBqPYKCtZAMXPmMI+EcVkA0q8Ddh1xrg3X+FHg150Ey9F2Uut20Uy3zWZCnirCHSzYg3Iwcw/ApoHUfyu27FEsw8C5R5glILhit9z4PnpHMl0LbBnpZDSKwEdKBNd2I9Na2VtJ2JHWXm9C6Btn3WkoE2pfHatatm/tyXX36ZU5MQoN6ypfKCNHHiRI7RZobgKKW2AW2+gDgV4OevGLAQOQy5ihNLcjoWvpx4S4DX/lRhHa42i9P+BH+bfjWAR7yBNj3VaE5RtmbrFsrg4ZKrXuNi+Bu2BybdkTBXOrb2fPhfODuPrAK0KVZTqdMI+MUA63uozXLefdB2r4fv1w1VU28Nmg1P1/ER95ieEi7r2C4olDKLwERwcR1jQjTt4HZo4ZiEg+s7spigzaXkmnapDO6GiYq+ezngthtw968ImdY9ECrdJEN6VIgAACAASURBVDXmaiMrI1XRTp0Hd7thId1Tac5kyfEdPwQ8PTckszsDbU8JsDeIgK1BG2hFTWsCbZrzrEfhQk5Mc452DvD+eeMmcwzD0ToN9zuR3c1elHAAyOvsOSrCP0oPRcY4J54CByl/9BhtSqnWvAtUiiMP5WUQqrfiwdDG/tGwAkFXSNG5pbvgmnUV5nWjFH4/r6wyIgbaXc+AOnBOzIopq8sc73aB9ExEhkaM3sGxzw1PAE6bD29+I8OKiniPL1x/AS+fn4mf4hXBm1L9XCOPnr5TmYeBXP2tgOzA94pSalIGhXBl4Cx4uk1I+P1AWrSTtcPkc8JJQAfanJXh8HZg93rmF4pGaiolak0CEmhbk1siWoVM7xXqQRTfc+TIEQbeBHiMltoEtJkZ1HcceO3PgmGcCjE/n/2PhF/Oja6H2Xp8eYyUwzMrD7jgMZT7UCXWORFAu5IdmNhu3wk7FQG0twBk1Q4ulBaI2HAn/BOe3PoJu9ywQuD7V+Fs3A54bEYgPk8pbASFYoEj5A+OuD5zF0P97nX4D+6oWq3bGfANvjiqdZ7XkhQmepy7Ht9nGL1UG12fKfD3nR6TdVcA7ZcqLM4amARs9wZB1tasI5BbVxDHUXoncsGnf3dmAcRwXNQY2tDLUN5+ZESgTXm3Hd8vA1Y+EUK8Fa7j5B5fcgDIrws0PAEUzl/DZThOVvxo7yCvExFq0UUk0YXkOOfJhAPtAPAoOwi8+4/IoRNFTeE85TfAotmCAb/pidAc2cZcxnV5mWAdj5eIBeO/R6RhCrLcZ7cfBO+oa1Hu9sadDyJeY7fSD53HdNY5KBSGGLVdx3mtKLMGvXN2VS7TuDkuPysLCsVO03lMqQ0pvIjSx2lgRRrNIZbC++HINuDVP4Xuhs7fmQvgchYmVHFHD5dAu+oS6KSwkpwrlh1uri0BbVJc5eVkAY/PFKFiJ50Db7+ZSVXI6ZltdKUqfefJc5e4DTKpSKBtn9U0DLStDrk2Ae2w+TorSGHSjQgnUtxhlf1w6uVwtx9R5WKSCKBNz9RJ1pQVC4H1b4bclmwVJbdosmoHl44joJ39L3gKmkQFpVb3O7XjC1bZPjiP/Qq8dzuwYzV3R9ZsRfUCh38x3z0RQf3mJfg//B9UTzVinbb94R87PyLgZdd7eICnLjT/7HAtChuxVdtoHGuobkTqHbKKPcrut5wvvYJ4jeLZUb8VNAoBCGUFJRKmC5+Bp1VNjwqWd4VFmwgZCRBEUhixcqaiiMtXtdGeMCBAZpVojgU+Rz76H/DT8vitVbie6reGNvUew5bfWAfE652dBXzzCrDuJcBD6eRqFuewywUY3/g2r4Upq6KFPNqxzktvz/MjpldSklD8ctPOyG7ZhRUZZi3k8RpTovvR+Uf055jJEZ3osUXrP3jsdOG2Qiwa6hl09oiUXHnQvn4OICK26mX4lVA7jkiKl4ME2pXCpzWndeHwsgJSuHtiVqpE22fyd6ASaOeIewix5/ebDu9Jk5MGtPl8Lt0Lx7olUOq2BBq3g//nr6AN+13SvoHJ2gsSaCdL0tGfI4F2dBkZrhHWEtV+KPwjr47J8md4EHGsyODMf1zkAI9U+k2Hp+ekKhaMRAFtGkYAbG//Cvj8kZAgjIETWUEJoJHlgMi9RvwfXH4k/FDX3Sqd27+E8sP7wOcLWHoxAe3u46GdfDF8H95bcyVO6A//mMhAm8H/z58Dn4RoH8ueufAZlPsVy9rggBfIs79h6yUTkx35lWPYmZ299AC0wzXDWoRAncClL8HfokdIa6EOtA8fPiwuvbk5wAf/AbZ+YW7G7YcAo6+Fy+1JClhij4i1LwBrl5obp5XaHUdAHX5lUi77+vBojenCw94Lv6wD9m8WngpUiIyueVegZU84iAH+xWuM5ZoPnvtZf4evaZeEKtMiiZoUlHR26oW+C7VJ4WxlG2ZSmwCQIy8Z1Q9nk3ZQd66D9uMnIpUipVvsPBpqo/YxuaabkZkE2pXSYkXm108D37zMKTO18X/LOJBlZm8kq67uOk7f4izPMeDANqBtP34HkmVNZt6ELxbC+cN7ImxkxsPwf/aIIFUtLTVEfJksecX6HAm0Y5Vg/NpLoB0/WYJf4nVLahIvDbkY3i7jEg7w4jgV7oot2vm5wMLzhAtnuDLyKrjbDkmKRVsfAoEo0kpnEaCmCwyRe+1cW2khczjhaNwOClkiu4yBmt+Q5Z8sqxIBiVzNDQfFOz91EY9LKWwIheL2iVHZbJn1GNR9W+D/aUXNlt3PhG/QRRGBRfVYaLOPD1v/nH/DXa9tTBYBVlBRKqtd37CXOOeLpdQ1qh8arWu40mUsMHgO/KWH4e1yRo33KxhoUxeBCzCRE5EbeRRSPSbUGnwhtE6jkupaxkqRX74GPrgzbssUtqNBs+HtdlZKziYdkOr5gWmMHHtfkaaI1itXdQFv/DUyu3Xw5Eb9AWr7oSEJGhMvTPEEPd6b/ktzoYu9BNrJkn7qn8PnGcWtr39LDKbjMDhGX8NgQt8T9B1KVEq9UBKQQLtSKrw+b90iuFJIsXfRs0kJnUn9zkztCIJZxwls07uQbO8X5lD6ZRUcH94JpUEb4NTfwn9gG7QuYzNO2SKBdmr3e/DTJdCO41qwBZitZncCxO5MpdNIYPiVKCsvtw37qpkp80fp43uAHz8O3Sy/HjBzIcrcnirzS6RFO3gg9BySu35wB3x+Ky65el7wZAHs4LHRBTurdD8U0p5/fA+UvCIoFAdIVjwz5aSzoQ25BL4P76pKOqT3MfhCeLqcETEmsmostJmHR6k7/ha4G3eOCWgLd659Ir2SKuKkOA1Z2SHg4M+hB0AkXlPvgbrlM2hEknX6n2t8KKsDbeqIwB19bJ1QBRswrcWub0WMJhXKNU6M+q17A51GwQ8Hg1BTrssxilekPMsGHp8Rer1j7L9Kc4oRzaqTNAWU2aHz3iByyS+fBNa/IXKdhyqN2gHD5kFt1CFpVsJQwwjwSOxYBZCSLTsf2b0noszvTIkyw6y8Zf3YJMDvbrZDvLvB5fyFKHcUJM1yV30WEmhXSoTB1vG9IqtD277wN+2Sdt6Gse3S1LS2Q3qvAK+EQ4HDUUl8SXwSiQ4JS7bUJdBOtsTDP08C7TivRYDVlAGDAs0hLljJco2J83SEy61DBZbdCBzcVrV7IkIbfzN8FZfb4B+TBbSrz5fAlV6M5L+Nt7yC+9PTGnGsNuVv3fyxSO9F8ZuUIs1Iad6NAaVv1QvMCh6ynP8oXM6CiGCJAcv616qmTDLy/Gh1pt4NV37TmIEae4P8+g3w9m2Apop47ZK9wJEQ8ewEhsffAk1xQP3qGaBxB2iT7jAEtPXp0P5kFzYiRAraM/R7MOt08MeX6lF9+qP24dpRm1gVO+zeuPxBYNP70VbA+u8RcrBb7zT+LdmynZsLB8Vz//iRCC0gskmyRlEaqdZ9oDXvymcsXZhS+d7zPia3xOUPBwSR3bAVvGf/B+U+LW2/A/Ff1czskc/8vByRTz1YKTTnSVa2pOoyL4F21f1GXkO0VnRWEOldKs+MzHwTas7KDkBbH5XuWZLJspdA2z6rK4F2gtZCP8Qz4QAPEBhR/mUiqiKW2SYnAt3PhD+vPluQqs8zVUA7QctpuVu2cNDl23UYePXPUHathULxqESUFK0UDwTG/w3+LcuhbglDjNW2H7TTb4jq9sTuyHu/E0A2nuWSJShzVfVmsNI9ffgoNtl5ZAfw6QNQDmyBg8hSqisXyNJ8yuXQfG4Bskmh1WkU1GFX1IgzDmXRDjc2HTSHel91V2D2mqC4SyIpI2slMUt7ygUrOrmZUy5y+iPSvYIGfIGzylzM6+U5Ajw3L3LYRrUJses9MdvzoFhtIO77FenQqlSfcCs8jTpGZYemsTDBF0RmAVIcpqKEUnIQcNEVG3Y4a4uKioBFswB3Jckbp/caMBvujmMt74dUyFs+05oEWEm2+QOhbKGXb9BsaD0nRj2jrT3NWCsJtI3JSdZKnATsBLQTN0v79CyBtn3WQgJt+6yFrUcSbAGkgZIrrR5nFmrgEmhXSkV3V8pWNCZHU1Y/B2x4J5D2q4b8iM17yFxo3cbB//2b0LavCr83ptwFd2HzqBf4gDvyY9PZYhyX0qwztIn/jOsFkpQ6DGgPbIFz1zpgy2fCfZpCFIoHMQs5u4v/+GnlFE6bD0/LPjUAoxmgHU4eJDdyNXQc3Ap89ZRwMzdS2g0BBl4AtaiZZVdmvrATW/GaxVGfGMg/Ti7wxLhPMqNLvuIAiJ29oAFQ4SqnUv6iE4dBG/l7Vk5EAqi8b/LzgHf+ARw/AIz9I9x5jaLut6gDztAKDLQXTqni8s9Au/d58HSfGFWpkaFiqVXTCrinVui66HUj5VSqrNkkfAm0a9UWtOVkJdBO7rJIoJ1ceUd6mgTa9lmLjBqJBNo1l5OsghwfTERfP68EKHabUhiVHwVyCzl/M5p3g1Y8GNrhHfB//xZQsi/8vhg0G2rPsw0zRnO8/Sf3sAt7XEqCchXrqXFIXk7XEeCHDzknulayHxrFVPvclcOvSLtVVlZWI446VqCtp+fh+GBiqDVbCOQOuRha9zMZbJu9aAuQmy/CDvZsDPl0utQrRFRYsh84tlvkJg1X8usD9Vtwyin1nDtQ7hXKskhF5AL+GXh1vqgWIsOAWbFkcn1Wjnz+MLDx3cA0s3Pz4D33HriyiqLKO5NlU9vmFslLJtmykEA72RKXz6suAQm0k7snJNBOrrwl0LaPvGvNSDIJaOsxubR4BExiJcZi0jxyk/Ych/Lrd0BWNuD3QyvZC+3gdqi7NwDH9kTeK93PhHbyJUziYnQ8DJpcB4EXroh9HxY1BaY/iLLyxFlq6KJKbveOHV8Dn9wv8m4Gl66nAUMvg8sTOu1WLECb1ygvV7jaR2I+NyLJLmOhnTrPEtjmNVP8ITkSOIUdxfpTnnE9PVa08dC6zVwArU1f3jvRgLa0aEcTaNXfA/vmq6eBrZ8DRc2QffIcuOoVS8Ilc6KUteMoAQm04yhM2ZUlCUigbUlslhtJoG1ZdHFvKC3acRdpenVIFjGdsTseJE767DMFaPPFOSdLWDSLmkI7cXhUd1sjOyAQk3xoG/D+fwAi/jJSKD3YyXOhdR1nCbixxe2bl2InRZtwG7yNOyY8XjeQxo3ijrd/LcjRcgqBdoOh5dePSDRoFWgHmKPfv6Mye4CRtYlU56RzoA2abWnvMEeCQwNoPDtW81Mox7RCXAl7fzAeCtC0E3DafGhHdkElNvdxN6Lc5Y5K0GWXGO1YlyBZ7enMYG8Mp2C1pf+nXO52iCFPlgzkc+wlAQm07bUetXE0Emgnd9Ul0E6uvCM9TQJt+6xFSkbC7sTE5EsuzL0mwaXkRrVyGRlopgDtGmzd0x9EeXa9qODEiIyoDqcaofRF370OfPcqUHYkdFNHFpN+oe8UqAWNLMf90rqQNV356H8i/tlKGXYF1E6jkpqrmMZNf3oh0BLNGmsEaFem+3CwZwDFUtKaO394F1j+iBXphG8z7gb4WvaOmO88XONANoPNH0L5chEc5YcA8nygWOxoxZkD9J8O9DoH6o8U3/6JaNFpJLThV1oC/9EeKX+vlEDDhg0zPo92dRZ/PR96svNFy30XWgISaMudkWoJSKCd3BWQQDu58pZA2z7yttVI2C3U4QOenCPG1ftcePtMi4uVMqOA9q7VwHv/FszSMx5CmU8xHW8baeFJVmT1IksYp1DjvM6U/ksDnFlAo/ZA615Q4WASqmgAM9omo+cQwFe+otjjV6JVr/ydANvIq6AWD7YM9I0/LPaaRoA2M8JvXQ6sWAicdDbQZ4ogE3vmN4DfE/sggnsgkrsZD6PMZS1np54DPIdcxinW/tvXBPN5uFK/NYNpdBsHeErh//b1munSTv8TvC37xOWdj6+wMqe3TAfarCzMcopUdORxQcSBlPqxZU+g43BoTTuldYrLTNiJEmhnwiqm9xwk0E7u+kmgnVx5S6BtH3nbaiSc85MYhSlml1yXx1wLT+sBcWHGzRSgHbB4uo5y3l6fkmXJImlk4XUSsFD5mfU0Rkb6MVInYNneu0mwaYch2wr01XE4MGAW/PkN+NJsNC7cyFgSVccI0GaW6BevBsiVOisHzt8shX/F49bIz4xM5JTL4O042jKwJWt77qEtUH5ZC6VZZ0F+tnczcGSnIIlzZgP1Woo0YzkF0PZtgbZrHbTdocnUOA/1tAeYOV66NhtZQPN1Mhlok3dM1vG9wDv/BI7uCi2cLmOBYcRR4IqbJ5D5VajdLSTQrt3rb4fZJwpo65lKaI5khHC7g8hS7TDxFI1BAu0UCT7EY6XruH3WIiUjCVgjfB6ozpy4WSrjDbQDaZYcwsWXWJyTCfbICkxAxCxzdEoW1eBDq+SHJsbqbSsFy3npAUBxAnWbAXWbi1RQOYX8AYvVmm5waHGpZgRos0V75ypg5SKg19lw9jgT/kdnsAU4IaVRMbTJ/7WcEo1DPci7gljrFQeURsVgsOzIAs2XwTK5kx/fD41I0ijPeLQy/ha4G3eWKbuiycni75kKtJmVHx5g6dVA2aHI0uk8GlpFrnup0LG4kWJoJoF2DMKTTeMigUQAbebQyYIgLSWl8+l/gkvJS6t7SlyEG6ITCbQTJVnz/UqgbV5mGdeCUwQp8XeHJlBw9OjRuMiLSbw2vgOsXQoMmg1/+1Mki29cJAtee51ZnQ5n3aJOigzdku7zGQBscRpPvLoxArR1d2x93hqRi71yfbyGELqfOU+hXHWatu6xB0pBPrBwqnECNCMz6TUJ/v7ny/fJiKws1MlUoM1n8vIHhcu4kTLxNnganigtTkZkFec6EmjHWaCyO9MSSATQ5qwcO1YCH90lxnPyXLg7jpVKY4A5berVq2d6nWSD+EtAAu34y1T2WPGSxxNos4vvolmAuxSo2wKY/gBKSqqle5KSlxIIkoARoB0sMCa+2/C6cKVPZBlzHdyt+pm+DLAF0XUAWHxlfEfXsge08X+zbGWP72Ayr7dMBNrM75GXAzw6zbjSp8tYqKdczuR7siRXAhJoJ1fe8mk1JZAIoC0t2uF3mgTa9nkLJdC2z1pk1Eji7TouLdoZtT2SMhmzQJvDKNYtFl4TiSwDZ8Hd9SzTQJu193u/E25y8Sx1GnNubam4iqdQK/vKRKDNe7HkF+Cla40LragJMOMRuc+MSyxuNSXQjpsoZUcWJZAIoE1DkTHaoRdEAm2LGzUBzSTQToBQZZfCbSWeFu1Ux2jLNU0/CZgF2kzs9PVTwHevJXay/abD03OSaRdaCbQTuyyJ6j1jgfbBH4HX/2JcbHlFwOwnJdA2LrG41ZRAO26ilB1ZlEA0oE3WafrGUaFQNcqwEq7o4Jr4Hog7Jh1D2yyK0XAzCbQNiyrhFSXQTriIa+cD4g20a6cU5axjkYAloL3meWDdi7E8NnrbAefD3W2CaYt2bXAdpznqnBEkSLpIEVcAXaTSlUQrE4E2u2wSEdpTF0bf73qNlj2hjb9FhigYl1jcakqgHTdRyo4sSiAS0Gb+kcJCYOUTgPs4MPgiuDRnSFIzVji7DgGfLwAatIY2+CIOR0nX74NFcUZtJoF2VBElrYIE2kkTde16kATatWu97Thbs0CbY7TXvwZ8/UxipzPy93C3HWwaaGcyGRoBbJK/Un4E+Gk54CL+BY1TlKHdYGhFzVlekawciV00670bAdp0XhJ4pT1LSgU7W2hojPRHjP0KpcY7tN2YcIZcDG+XcZZT2xl7iKwVSgISaMt9kWoJRALaDJ4PbgZev0kMc8AseLpPCOn1JUK8lgBrl4i60x9CeXZdW5+ZqZC9BNqpkHroZ0qgbZ+1yKiRSKCdUcuZlpMxC7RrfOwBOBwCVBDm04D4pJSb9RhcjnxLKUiqpPeK16qkOL0Xu+x7SoAVjwJbPw89q1a9gFMuhb9OM07tl07Wi2hAm/YXWXOUTe8CpYeAPlNQ7rEn2Oa1cjroRYCSlQ1tx2rgrb9H34l1mgDT7keZ25tRKRKjT9weNSTQtsc61OZRRALa7CHjUIGX/iCUrBNvg7tOS1as0l2Szh09Mw55OGUf+kmcOw3act3SsuSme02HdZRA2z6rJIG2fdYio0YigXZGLWdaTsYs0A5YjB+fAfg8/GF3qB5g72bA4QSadYYKh2mQR2CdCqW41oqasgb++PHjpvuhPtjqvocI0W6Nz5pQDu5pD1geT6yDYOB2bBfwxs0AWbMjlawc4My/wt+kc1qlIosGtFnBc/xX4MU/iNkPvACebmeZjuGPdS2itefLsOIFlvyfyP4w8TYozTpDW7MkshdIbh3grL/DW7eVtGZHE3KCfpdAO0GCld0alkC0GG22VGdn84fSr6qBM56Vy189CWz6ABj+O/ha9+VvM90xSeGarp5OhgVnsaIE2hYFl4BmEmgnQKiyy/iToUmZSgmYlYBZoE39M7v9igXAhreFNfvYXuDIL+LRTTpAza3Hlm1jRePLAI7vZwsg6jaDOmAWtJMEEZqeo9xYX6JWwPpJLna7vzfTNHTd0/8Eb8s+KQFAHHPu8ANLrgJKDxqbS1YuMOUuuHMbpI0beTigTYod3V08R3UDL/xWxCeecRPcTbvZbn6sEDi0BVh2o1irQbOBXpPEHt+xiuMr1YM7qr4fHU4BBs2BL68+eyLIkhoJSKCdOLnTOUbnstfrtaQ8TdzI7NVzNKCtf9/ov7rHEsmVgDYemSQm07o31HF/kSkCDSytBNoGhJSkKhJoJ0nQte0x0qJd21bcfvO1ArQZ/PlKgOcuA9mhHZoPOLBNWLQbt4eqaWyZNlLI49zhOQ7s+xEKpdBq2hG4YBH8h3aIPhoWQ1UcDKjokma0MODxHBUWUE8MOYk7jYQ2/MqUEcmwUuOLR4H1bxqduqh3wgBop/0pbUi1QgFttg7n5wP7fgAatYeSlQPN6wZUL9SsfLbm2M09nhQDHJdNZIHuEjgGXQCt7Ai0b1+Do7ABlLb9AWc2tKO7oTqzgSYdoTlz4m5x0q1Z5EJKf7JEl4AE2tFlZKUGvQ9OdwngOQ6tXit+b+WeDC1JI0A7VEu2aK97Cdj8IYcPeZt2S4li2Mr+SGUbCbRTKf2qz5ZAO0VrEWzNIOIbsm5lUpFAO5NWMz3nYgVo00wZAK55AVizuIIBW8yfLlBGQTbV113PFdcxKJrKLsFq3Rbwr3hcdKg4gE6jgMFz4HXkmro8sMv1oW3AGzcBXpf5BWrTBxh3I8pdqUmNQudDQV4O8NgMQPWZG39OARyzn4DqyK7SjtaHFBZ2syyFAtq8xz5/BNj4DitwMPnOgKuknb8FtG6k6KH/Oryl0F64stLlPzsfSsvuwCmXswVb99owt7iRa7MiLC8POLaHPURcLrcpJVU8x5JOfUmgHf/V4r2ouoDnLgX8XmDMtXC36m87T5T4z9xaj1aBdnBqVzob042jw5q0Ym8lgXbsMoxXDxJox0uSJvoJuH9uWyFcJntMQFl5eUaBbQm0TWwIWTUhErAKtBkEkrVx2Q3Ano0xjS0rywmFyF2KmkIbeRV8nzxU0026qJkgf8mqY+qSxtaUY78C798BHN5pfJwnTQQGX5hSkBKKeM7IBJSWPeA4aQLgc0P9db0g43IdA/LrA237seJCa9yBlRZ2Ye4OBbTZSvPOP4TLdV5dYPaitMovHZGhv/e58PWdnhBXcZbbJ/cCmz8C2vaHdvqf08azwcj+TlQdCbTjL1k+w8r3A4uvFJ0PuQiezuPCciuQcUV3MyfAaMaLKf6jT36PVoF28keaGU+UQNs+6yiBdgrWwuwBnYIhxvxICbRjFqHsIEYJWAXa9Fh+RxU/8PpfgANbLY2ELdpQoZAb7Wnz4V/7ErTdG0L31aI7tLP+btqNmwlksrKADW8B5F4XKda5eBDQdyrUhu0YiKbScsry3fKByIVqsCjFA+HoPBr4+G5eE61eC6hqCD/+LmOAU+fB5Tbnkm9wGKarhQLaDFS9JcCm94HiQfDVa50QYGp6sAYb8L5b/Qzw7as1W3QeDf8p8xJCWMdA++VrxTtJ4RgzF6SVgsKgeONeTQLtuIu0ki/DoMGE9+6PHwGHdjC3gUvJrVVgWwLt+O/BSD1KoJ1ceUd6mgTaKViL2uByJIG28Y1FgIxcgSWLpnGZGakZC9AOgO0sBfjobmDrCiOPrFKHydTIytp1HNTvXof2y7rIfZz9L7jrF5uyalOHujsvxf3i4M8APcdbJgjYnFkAWcyLB0HLFinFKCY81fG/DLS3fgJ89qAxudZvDefJFwHL/iJI4Oq1hFavZfh4yBMGQjttvi1iJsORodF3gKxcOnOuMUHYoxYrCrZ+Cnx6f80BDZkLb5fTTYVCGJ0VA/yS3SLXervB8NVvm1YKCqPzjHc9CbTjLVHRn26lpv+PFALIXlIOH/DkHNGw97nw9pmWkHckMTONvVcJtGOXoZkeJNA2I63E1pVAO7HyDdt7ppNoSKBtfGPxpXX/JpGyqXE7YOK/UCpJVYwLMEzNWIE2dUtgiNZH+flL4MsnAGIhN1Iat4dz6CUcf6yuXARt/0/RW/WbDk9PwUhupdB8dddEzv1dwd5KQI7il+3iSk3jqpHSKsqEWZbbv2Jmay6N20HNbxA5Zn74FfB1GJFyIBYtvZeVtU51G06FV1goctnuXFM5nOZdgQm3oqw8cR4TtHfo+bSnSWmUyhL8nqVyHNGeHU+gHRwzS2tAMbOSACzyCvD7kp8HvHAFULKX47k9rQfUOOvpW8MprgBWilr9FkTbD6n4XQLt5EpdAu3kyjvS0yTQTuFaZHJaCAm0jW8sttKsfV64/lK54HGUaTkpde01Pnr71owH0KbZ0SWJLvd8Adr+NUBxwQT6yg5XnTzlyD5hIFvatObd2NKsLvk9cHCbMSFZsHLQHONlnQ7OTZpot/IAUHtqDlB+LLJ8OxGz3wAAIABJREFU6jSG89TLgUUXVLKst+kTPad5YSPg/IUpyxGuTyoTgTbNLaCEoneC9niD1kD7oQwOUg2Ajb1wsdWqzPurgiIY7MgUr88wnkBbsEC/KMIGTr4E/vanJCRMILbVsV9rEebjBHweqM6cGgoKzkRA6Q7fvk0MftwNKFedtlKQxiJVCbRjkZ75thJom5dZolpIoJ0oySahXzq42V0UiHsKlViHX9uANueSBSyBY7buuQ4CXz4JNCqG1nea6VjdWNcrE9vHC2jrstHdBOmdo/9nc6rPRfTigDOX/0sAlSzHZI0gi1+A8MqIgAecD0/3iYasGPR8CjdwCE0AtyHATRYRGh/9v/4XPKZwoJz2L/WnEGAqagqfMy/hlmD26tn4NrBiYUTpKO1PhoNA3KvzRT1SaDRsC7/fQGqn6Q/ClVM/pbGQmQq0xdarzAVOe4v2fm2wbrKiKDcbWHoVcHw/cOZf4Wnc2dC7a+QoiHedeALtoqIi4LFpDBjpe4Vz/5fQOPnAeVshFLt555hZK9o39F0KpcisEU5z6jy42w/PGKWVBNpmdkrsdSXQjl2G8epBAu14STLJ/XCct/cY8O6/gPx6wOk3oMztsQT0EjH02gK06aNJgIHzJTuc8DvzLGn3dZcxuqymmqgqEfshFX3GG2hXnwP1X91FO7gOWzB+eAdY8aix6U+9B+6CpoYuVtz3tuXAx/cAzbvCOel2wO+DsuFNoFE7BswMtBu3h3/3RqBNP2gNT2AgEIrttspY6TwhS3CZK27W8lAC4LjFggLgtT9HZHdXThwGh68MWP4IkJUHtOgGgtiGUq2NuQ7uVv0MydTYIpmvlclA27w0MqMFWx9dB4Al/ycmFGPYR6KlEk+gzanpKC3dd8s4NaG/TX9L37xoc9a/iYr7OLDrG6D8KFDQAGjdC1p2ge2MC9HmE+13adGOJiH5uxkJSKBtRlqJrSuBdmLlm7DeRXqVV4GvnxXPOPNmuJt0SemFMniytQVosxb60E8iFRSxS593H1zZdVNqQUvYpkuzjhMNtKOJg4EkWb0oLo+sXpEKuZuP+aNhTwa2Bn/2ALPYspXk/AXMaK6sXQqlsCGw6lloeXWhjboG6sHt0IjMrXgwMGwevM78GiQ8DLTXPA98Q+ELCnDxcyh1J946ye+PQxX8BGEY2Rlo+13AykVA047QnDnGraZjr4e7ZZ+UnosSaEd7U9Lv90CKTnKhPn4AGDATLuTY9tyPJ9CunteYFMPx9GIIeOsc2Sk4GUKRSJ4wgFMU+us0y6i8yjJGO/3OAruOWAJt+6yMBNr2WQtTI5EWbVPiSlhlBgo/fSisbVTG3wJ3486WLvaBmEdFYRdMIpmRxboEUg20aeQMYI/tAt64CaB82qFK4w7AhL/D5VcMX9TpQpZbtg+O714FssnK24MZxpWfPofiLQe+eRGapkIb+2eo+7dA2/qFeDKlRDrrb/DmN64Ctvk8IYb1715nMKu26MGgPxmF36HcXICsZGuXCuASVJSOp8LRfijw3u3QoJi71J+/EC5noWG5JmK+EmgnQqqp71Nn+6dzhs5rO8elxxNoJ1LyAQ+xn78APrgzstuKIws4/U/wt+yVEIt6IudZG/uWruPJXXUJtJMr70hPk0DbPmtheiQyRtu0yOLegK2W+fnAt68A2fnQup5uKaUQXTCIZAYf3QXs2wyMugbuuq1tfXmLuzDj3KEdgDZNiWKfszwlwKrngB8/BvxeMdO8ukDPCZxT1e01d1GnuVGspGPXOmi7voe65VM4WvaAo/NIoEFbgP79+EF2tfR/9jDgdVVKt14L4Ny7UO4V8eR6IddFnWsg2SnAyIqlx5ejZD9wYAugqUDDYqB+K0Es99RFYk5GS4PW0KbcY9hLwGi3ZutJoG1WYrJ+vCWQLkCbFZMHt4hwEiNFcQCT74SnqKVt4+ONTKM21JFAO7mrLIF2cuUtgbZ95F1rRlJbXMdpQYMBSqRcmpEWnwE73MDTF4tqvSfD22d6rcqzGe+Xwy5Am+ZFFmORlkgB3KUcz0+KGSLFobhpsyzfHDpCIQvVL6QUvlDYEErTjpxHW9u5FiALd/Vy0jlQB16QNKu10bWlNaP3KTj2nd4pVipu/UzEpBstp10Pb6t+KX+HJNA2umCyXqIkkA5AO5CJYPGVwJFfjIuiaSdoZ/8r5Qo14wOunTUl0E7uukugnVx5S6BtH3nXmpHUJqAdj0WVFu14SLFqH3YC2vrIggnUYolr5BQ7790OUH5vK8WZBVz4DMrcPtMg38rjYm1Dl3CKS1fI42PLp9G7634GtJN/Y4vLt92Ats4UrguRyPHCsdGTgogZ9itystcWVvHoGyy9aqQD0OYQkoM/Aq//xbxwp9wNd2Ez6QFmXnJJayGBdtJEzQ+SQDu58pZA2z7yrjUjkUDb/FLLGG3zMot4uCkK6IJ5+HC1fNfxfUzSe2Pvh7xc4NGpBqm3wwxx1B/gbjMwZZdTUjrQ5bp6+h4CfcEpyfTRUz2ybCurnhWx3KEKuZIOOB9ar0nMcWDWUyARi2knoB04Y3Z9CxzaBjTvBq1JR7b6B4cR0NpQyIPTdQTYTOEOHqDJidDa9g/LXJ8I2ck+4yOBdADa7KXz3cvA6ufNT3rgBfB0O0u6j5uXXNJaSKCdNFFLoJ1cUUd9mozRjioiWcGKBCTQtiI12SaeErCjRTse82PisrJ9IodvLKXfNHh6Tk7J5ZQANv0plLZn20pg5xqg7JBwqW94AtCmL9DlNKj59aukuwswHlPdH94H9m8BSg8Jkjdyl+88BmpePVulyLML0BZ8EnnAm7cABLT10mkktOFXVuGWYFb73d8Cb/8DUCvj+HHCQCagKisrs4USI5btX5vapgPQ5vjs1c8A375qfmn6ngfPSeem5CwzP9ja2UIC7eSuu7RoJ1fekZ4mgbZ91iKjRmIVaJObYiwutRklRDkZlkCwq6sZ19VMBdrsYnlgE/DGzbHtkN7nwttnWtJjmJkcruwg8Mk9YVN68cQUBeh9rkid5Kqa/5uUDcHcCKK6YCSnPaK7Qkdyi45NeMZbxwNo0zugn41Wz0cGMpveBr54rObgx14HTythrQ6kpXvqQsBTVrPuKZfB23F00veNcYnHpyZZWGlP0V4yQg5IdWlf6vswVL76+IzMfC9pA7TXLQ7vrRJp2jbPY25mxej9ozNS33t28cwxM4dQdSXQjlWC5tpLoG1OXomsLYF2IqVbi/s2CrSpHl1O6I8ZjzUVqgZ2+7TTRaUWLyVPnUAN/VGhdUmWS24gX+0vawCfF1rxIMOs7pkKtNmiXboHePHq2LZlCqxADLKP7gRevwlwHzc2/ta9gDNuQrnLXcW9WW+s555VSvYCO1YJsrmsXKBlT6BJB96vBCDDxSEbG4T1WrECbXapzXIAh3cyC7vb47Hk7l9YWAjHxxTj/lnNyfSZAm/v8xg8syJn7/cit3mocsIAaKf9CcePG1y/CiWIDkCtSzJ5LVkpQfuUsgQUD4S/adeoKaRYvr+sBQ78BPQ4Cy7VYZtvWDoAbd7nWz8BPn3A/EKPvR7uln0svRfmH5bYFsy/8dWTwDevAANmQe01yXaklVYkIIG2FalZbyOBtnXZxbulBNrxlqjsjyVgBGgH8udueg/OXWsBYkjOKQT6TAF6jEdJSUnSAJ1ctvASCKQwW/ci4MyG1nOiYbAbq1x5jxzaAiy7UXRl4kJlZ6CtW2ODGbZpejprfSQlk4jRzgEWTo1NvCOugvuEIUm7nLKCQPECS64CykzGzXcZA+3U31YhNwvk3D28Hfh8AbBnY015UCqzIXOhtembspjtWIA2kyQWFgJLiIl5FysPtPG3mAK5ulDYHfyrRcB3y2rKaeAseLpNYIVEvIE295eTA7iOQsurl7J10Cete8iQ4iXce8Zg59X5ItVibh1gzlP8PQpXmDE7Nwt4bLqo0msSvH1n2Mbqnw5Am87C/CwFeHJ2ZQpEIycc3RlmL0KZy3z2BiPdJ7sOpW3EotmAuwSo1xKYdn/EvZfs8Vl9ngTaViVnrZ0E2tbklohWVYA2Wan0PKqhHhbt91BtDh06lIhxyz5tLoFoQJs/qjlZwBs3AXs2wel0AL9+L/L9EiPyOXfAd5LQ5KbKEmVzESdteHxR3vZppaXhtPlwt+idFIDGzz66HXjlejHfM26Eu2kPQ8+2I9AOxBgTudSPHwEHfwYObQf8PqBucxGffOIwaEVNeY70F6owECCLI8U2WylEGnbhMyj3aSGtxFa6jNaGLX7LHwQ2vR+taujfJ/4DnoYdAnGY3B9ZsIl9nXJuRyr9Z0LrMyVpCqLgocQCtFmp4tSARbMqulSAS1+ydPHmd6l8P7D06qpx15TP/bx74UIOA894u47zXn1tPrB3M9BvGtQ+56XMQhdwy927EajXCr7sQgb+1QvvLbIqUrxw8UBoY+dHVG6wQqQgH3j2UsE1cMql8HYcI4G2yTed5f7Ny8DXTxtveerl8HcaE9XjwHiHqa3JCrGdq4ENbwG9zoG/eY+MmJsE2sndVxJoJ1fekZ7GQHvZsmV4/PHHsWPHDrRt2xajR4/G3LlzmeGVyh133IF3332X2Xt79eqF8ePHY/LkyYZmIYG2ITFlXKVoQJs/qF88Cqx/k+dO+YUVTylw/CDnAUZuEfxn3ARPk66S4CTFu4Mv6CW7gJevAxxZwNS74cqpnxS3yIDV8sAWtnJozbsZBkt2A9oBy97aJSIO0e8Nv7LthgAnXwJfbl2+rFdXNrGb5f6N1uO0u58BdcglSQM8rFhzqsATF1CiKGs7ut0QaGOuY8DD86c9+dK10UG2/rTR18B3wuCQwMragIy1igVoB0InVj4G/PChAKrdz7K8bnyJP/wzsGYxcGAr0Lw79+krbFJFLvEkQ2ML3aPnif1ePAja2OstWeSNSTtyLXYJ3/gmsPIJYame9TiOl9d8vwIM994y9rKidzBaKBOHRWg+oPQgtHotU265D5ZEOli0abys5CkoAN65Ddi+KvqSk1Jy5O8NfxOid5j6GuQdQecbyYKMW6HOf32UdD5QSQdjhATayd1bEmgnV95RgfaCBQvQpEkT9OzZEzt37sRNN92Ea665BmeffTa3vfHGGzF27Fi0adMGK1euxH//+18sXboUxcXFUWcigXZUEWVcBTr86UNBl5ojR47UmB+72ZH2ny5fqj/wO4PtCvIZlQK1OwyFNuqalF3KMm5hLE4oAHb9boq2hN+RnVQNu04yRMM3Q25lJ6DNIFvxAW/+TbijGikEBM74C/yNOtSQdwCAGc0rHfw8YuiecjfK/UrSrNkMjH/6CPjsISMzD12HrPCXLEFpWbnIqb3shtDu4uGekFcEzHoMZS5PUkNSogHtYFI32t/Vyc6CyZHoN7p4x8KREIhpDyL6qu45Ec/0Xgza96wHiGG+82h48hunTHnKQHvtCwCFwdB+uuhZlLp9YQk46VtFIMYokNFDQYIJ+axv+Pi1TBegTTPmEBNKX/jlUwBZt0MVWrt+09lLpXpquvhJzb490b4kxQ5nuHc4+H0K5/1kl1lIoJ3clZBAO7nyjgq0q1e4+eabceDAAdx3330h2xLonjVrFubMmRN1JhJoRxVRRlUIAIBDO5CVXwhPXkMGCcEXFdZaq2XAs7+JPHcCBDMXWHKTzCih2mQyelhJLJf8ZE7FLkA7kFbplfnA/h/NiYBIvSbdAU9hsxrghK3EuTnAG38Fdq831i+5CZ/1d3iLWiTVrZUBzjqy5C8xNs5wtaY/AF9BE2SVHQCen2e+rxFXwVN8clKBXiSgHQihIRfl+q2gnjDIsrXavDCityDQQ5d6KnSGm2H913vX86XrZGipBAQBeX//BtCsM9SmnW0l7+grYq1GOgFtmmEgxKac8rh/KEJsyg8DhY2ARu2ATqOg5hbFrHSyJs3Ut+LzdMeXwAd3irSG5/ybDRJGFUKpmIEE2smVugTayZW3KaBNGvMpU6ZgyJAhuO6662q03bt3L7uO33777exirpfdu3dXqUsf1ebNm4e0aNpn+nIk8ZYAWe6yd38L5Z3b+GPpm3wXPAVNqrjd8UfUQW6k5wcer7tA6Rc6/qHJiQwyKE5bFikBsxKgPUUf96NHj5ptGtf6bH1d9ay1tDU0EorbnnIXu6JWt3YSEMrJzga+pHjSVyKPm1i4R1wJf37DpIJsGhRdDJ0U8/rda7HJ9pzboTY+EY4NbwIrHjXfV69J8PWbmVSgTSAnlGcPDZ6sy1nfvgSsek7MZdZjcDnyY7JYmxdK7WpBYFtXHpjxkElnKdE5SEDMamq4VM1dz3ZB66V7u5Gil/5I6VNbC1uzVywANrwtRDB3Mco94T0z7CAnCiGhb1htXrdkrgPdszlsR5aUS6AG6/i9996LJUuW4LnnnkOrVq2qDJBcdH73u9/xJe2JJ54IpPuhQ093M9cb0AH5yiuvpN3BnvIVSfMBMGD+4QPgk/vEh3HCP4DmXWpoWrney9dCoVQoVFQV8LmZ1Zr/oEEbMIvz6NpZS5vmy5Xxw7dDXnbmHqCcxEFhEqYFP+L/gE4jw74L/D4dPwBselcQpB3aCWh+YQFq0xdof7JId5WieD4e39ekbIjRoj3jIaCoGbD6BWD186bFiM6jgOFXGjpT6NwJVgCaf5hoEWkPcv+UQuqju0XM8MwF0MiLwcYlneJCbSzGpA7NDudgUiec4Q/jd/Dor8C6l4BmXQDKyqBZ5L5Ikqx0RUmSHlfrH0O4jBTxsqReAlWA9tNPP4277roLjzzyCPr27VtldKT5veGGG/DDDz9g4cKFHNNtpEjXcSNSypw69EFnC96m95BVWA/eNgNDMoeThYvYpBXKBUxuYa5jlULIzgc6nAzMXIhSlycqCU3mSE/OJJ4SsIPruCBfegtY+XhsU2vZA9r4v0XkK6CPqh7vGwwQyYpF53cqrXcco03M9Z/cb10ODicwdwm8Ph+yN7wBfLnIfF89J8Db/4KkWvQjuY4HzkvKAZ5XBJ8jN+lkbWaEyIRfriPA3k1A+6Eod7mkhcqMAFNUN91cx1MkprR6rE6YRgCbYrTj6a2gh3uQQPTvR6zCka7jsUrQXHvpOm5OXomszUCbXtSHHnqIrdj3338/k6IFF3I5mj9/fiBuu3HjxobHJIG2YVFlTEV6wQWhSR6OHTsW8gNAH4l8JwTZycf3AEd+qZw/MS6fejm05l3hzW8clXiLwAX1FxxLSB+eaCyxdhO4WeIdu43fbuOxA9Dm1EYUR7f189jEQxaMS15EaVlZXC9UsQ3KeGuRIxfAE7OMs4RX7/7EU6GNvJpJf3KP/cIeMabLyZfA02lsUl3Ho5Gh0T6lM5O+w3bmP6Bxck5v8s4gxehJ58DX/3xbKwZM748MbSCBdoYubIKmxVlhfv0W2PcD0H08XFpWzPcpCbQTtFhhupVAO7nyjvQ0Btq33noru3nffffdaN++faA+Wa0JrFx00UV8uaG4bLo4UqFFbNq0adSZSKAdVUQZWSFSeq8AYdobN8HRtCOUlj04JQrKDjMhEBxOqJs+hLZng2AJdvvCXkAZ0GdnARSvROlvKJ/uicOAUy6Dyy9Yqu1eAqzCdHnNK4LH60sqELC7fKyOzw5Am2Oknv8tcKwqh4WlOc16HGXIsTUYizSv6in9TMtg0n/grtua32n+Dr3wW+CoCblSarrZi5LKtk5zjAa0TcshRQ0E0C4QyhJvOdDjLPgHXRhVEZqi4crHBkkgFqBN31hSZNP6kyKI4mzt7qYsF9+6BDgrTF4O8Ng0ILsA6D4Ovj7TY1aoSaBtfU2stJRA24rUEtOGgTbFV+/atavGE15++WU+YM8888wavzVo0ADvvfde1FFJoB1VRBlZIRLQZnDsOVLJGpydD4WYM3PygdJD0Pb/VGn1Gn4l3MVDw6auYIthqBRHbftBO/2GtEgNxu6Ym94W5E4N2nKearsziKbDprUN0H7mEqFIirXMfBjlzqK0ctWlS5vuacL5YR0asPQqoGSfOWn0OAvakIsDYSjskr/7W+DtW433M2AW1F6Tkk6umClAmwTNqbpK9gC7vgW6jIXL60sLZabxTZKZNa0CbVaukFLr3X8CuzcAp10PT6NOUhGcmduEZ6V7rjg3vw8UNGAyTn9hk5izv0igndxNI4F2cuUd6Wk1yNDiPTQJtOMt0fToLxhoExM5/VHRU7vk/rIK+OA/0SfTbxo8PSeH/LDzB6EgD1g4NXQ/Fz6NMp/Qwtu58OX184eBTe/RVw6YuxTHq6VEs/P47To2o0Cb6pHyh/asbrUhZtR47BtWBJnN9xxOoBe/gFJ3zTzLdpS//s4rqhc4sgtQnED9lnBk5UA7/Au0ZX8Byg4ZGzoRuY25ji2n+poEvGLWLgWI0T1aaTcE2pjr2CoTj3WN9rjg3zMJaNO89LOcYjclg7CZnZC6ulaBNls3iU+JvBiopIDjIHVSq71PpjtJDoXnEIdOYUP4z7kTLiU3JqWaBNrJ3U8SaCdX3hJo20feGTMSnXSJJkSunNWJOHSgTam58rOdwIf/A+jSPfL38Gflw7l3A/D6TdHlMXAWPN0mhATafAnIzRYuTqFKmrja0sU111sCbHgLaN4Vauu+Sbe6RV+I9KthBGgH3PZ3fw9s/xrwuoBGxUDX0+Hx+WO23LASZdXTwDdRUm9FEy9ZFmY9FrNVIdpjYv2dZE4eGmz1pJRj27+q7FJxAB2HwzF4DiuU1I/uBXasCv9Iyj4wYBa0nhOYvKw6qAusHcW/f/4I4Cqp2Re5i/ebDq335JB9xDpfI+0zDWiHmrOeMkuCbyM7Ivl1rAJtGikrC4l4cM9GDsny1G0d87mYfAnIJ5qRAN1J8ja/C6x8DExmPu4GuJv1DOtZaKRvCbSNSCl+dSTQjp8sY+1JWrRjlWAtbM/ERjlZgsisqCm0E4fXYBbXgTZZkHJ3rATIvZvKyXPh6zIOWY4KLTml9IpUzrsPrrxGYTWpfAl4dT6wb3PVXijW+7z70sYFmz5sOhlaKMUF/ca5iJ1OtsgR8Igny2gmbuNoQDtgFV2zuGaqKMpdffY/Ue5DTFY7VqIc3gq89ufYRNzrHPj7z7J9PCwrFohA582bAX8YfoS8ulAm/B1Ko2Ko+34EtiwHSNFxbK9I7dekPdCiB9B5DPxZeXypD2eFZnd0ykVN5wn1c3gH4DoK5BSKNGCdRkLNyuP3JdmWbH3BMx1oM6O85hVKk+JBcKtKTBfy2F4U2TqUBGIB2jrZKJ2XpOyid0mWzJYA3/HIQEIKluw8YOAFfMeL5c4hgXZy94wE2smVd6SnSaBtn7VIm5HwxWr9a8DXz4gxT38Q5dn1qgCSKhZtxQe8/hfA7wHG/w2urDrCVZfSHlFccrhy4jBoI38fMj2Y3oTH4joIvH2bcFGlUtQUOP0GeItaZMylgImkfvoM+PYVttD52/S3PehK9YaOBrQZBB/fLdzjQpWeE6AOujAm74IAmCegTSmRrBRyu575CFzOgphc96w82kwb5l6AR3AveMoiNyUQPO1++FSRq5oAc3B+ZrrQ639GxkDnjW5V1fO10qWQwHWq3ZszHWgLZef1AClN2vSBNu4vhrgxdJItWl9SLpJCRZbESCAWoJ2YEcle7S4Bej/pj4jv6P2M9RyVQDu5Ky6BdnLlHelpEmjbZy3SZiQMbnetBt77N5BbB5jxUI1Y6OAYba5fEaNNBzZpxANunwTW171Yc+7tBgOjr0W52xP1gGdipOxs4OA2SvoING7PuXYzSfPO7NWLLgDcx4G6LYDpD9jejTjVGzoa0OZ9+d3LNa3Z+sDz6wMXPB6znPk5pXuAF/8AqBb4AoZcBLX7WTEB/mSsBVuzVz8LrHvJ2OOGXgpvpzFp+Z7qJG8E5qNZeewCtOmM1D1n9AWiSzRdoAnkWmWS5rNp6e+BQ9sBA/ne6dl0/hcQszGFFBGD+YirYo4BNbbpamctCbRr57rbadYSaCd3NSTQTq68JdC2j7wzYiR0yaQ4TAe5aGbnw6dk1Uj9EIl1XBcC1SGQ7KDUR2StpfRWOQVA6z7Qmnfjy5/R9Fw0JrJoUaGLY7TLb7otBF1mHdu/glJ2CFrjDtCadmIAaPVynG7ztzJeY0D7JWD1C6G7zy0C5jwZM9CmzhmE/rIGeOefACjozWDpPBrasCvYe8Hue9p0KrPiQdDGXm/I+mlQWgmvFjj7oIp0hAUN4dcQMZQj1UA7EDfvPiaUIHTWlh/lNIpo2RPodga0EwZYjmFnRSdxTGxdwakVPQ7h7h+psDfJ7nXAu/8S1QbNhrvLmdLlPEE7WALtBAlWdmtYAhJoGxZVXCpKoB0XMcalE2nRjosYa2cnBGwJ6IWKfTQCtHWp6VaWYJdPAtgSRAoJsUU0ywHnxreBAz9x/KmflBGt+6aERTlddns0oM2X/UNbgGU3hp5SlzFQT5kXF0syjYXAtmPfJuCDOzmNXcRC7PMDL4B20jmWAVCi1onmQuBKf/91ojIG2gunGLfaV/AokMIoHUogDOD7ZcCXTwGqD3DmAEN/A7XTKFaGhDqzUg20Rdz8JhFeQ9bjUKXTCLYqBzO7m1kTspbr57cR5SjHgDo1EVLkLgXG3wJXTj3DilUzY5N1AQm05S5ItQQk0E7uCkignVx5R3qaBNr2WYuMGokZoJ1RE4/zZDju1eEHXpkPHPmlau+9J0MbMCtiDHuch5NW3UUD2gHg9Ol9wA8fVp1bYWNg0u1wOeIXFx0AqIoGrH8T2PgucPTXqs8lj46OI4CTzoZa2DilJF7hFpsVP0d+Bj65D2jdG9rgi9gqzUD7ydmh2b9Ddda8G7QJt6aNRZvnvYdyd99WczYT/wF3g/YhLbKpBNqsTHIfBpZcJTgyIpXek6H2Pz8uiiUjBwXJUwfoekiRkXayjnkJSKBtXmayhXEJ6N6EZHQJZyCRQNu4PON0Vp9UAAAgAElEQVRRUwLteEgxPn1IoB0fOcatl+Cc0+lMECOBdny2BJOgrXwM+P6N0B1O+g/cdVtLl8sQ0okGtKkJXRDIOqv8+JFwfaUUUS26A73OgdeZn5D4YXo36D3nvN0Efo7uFtbROk2A/HrsIk755o1YBuOzy8z1whbSFQuAje+IhhX5vTmc5NP7gc3VlBbhuu8zBb4+02qEnZgbTfJq0/yyvnwMWP9WzYf2PhfePtNC7pdUAm0mKqM4aHIXN1JmPQaXI9+2e8/IFGSdqhIghQa9s+TOH4nBX8pNSsCKBPh74C4BPMeh1WsVNsxJAm0r0rXeRgJt67KLd0sJtOMt0Rj6EwQxucD7/wbKjwGjr2GGbrteuCNNVQLtGDZCUFO2Ej51oYipDFX6TYen56SoMZHxGU3qewlWREWL4TcCtGlGFHdL/epaeQK69M4l472j90Rn3NZZsu0eMsGW3QObhQs8sUwPv5Kt0mw9PboDeOWP0TcKxQfPeBguZ2FS5Bx9QNFrCKD9BLA+hNLLhkCb9lVhQT6wcCqgqdEnSDUGzYan6/iUnCd6ekO7739jgrRHLX4nXQeRtfpZ+Oq1htZ3mvSAssfSZMQo2ONOdQHPXSrSOY65Fu5W/UMq/iXQTu6SS6CdXHlHepoE2vZZC3FR3b9J5KClMmAmPN3PTsmlx6pY9JQtBHIIuBw9etT2JE5W55qMdlHdcftNg6fn5LTaI1blxh91ShX3yf0it+fw36HMFT7HslGgbXU8tbVdgFzL6WQ3QT1GO+CKv/p5gHKTRyoj/g/qicOT5qYcj7ViBQOdz2/8tWZ3k/8Dd1Foz5JUWbRZcauVA89cYnz65MnRd2ZCPDnCDSKQgUL1csw77adkKLmMCyV9azJR3drnkfX9ayJ7xwWPo0zLiUtOeVKM2J2gMX1XLj1GznfW8v3A4ivFgIdcBE/ncSHvIzrQpm8GvfPkZh6K3yc9Zm7/UUqgbZ81kkDbPmshUp7kZgugTRbMcTfAndswrdyC2VXx3X8AO9Yga9x8lDfvndRLW6TlZFddRYmaLsxGWwLsOv75wyKeN1SZ+E+4G7RLqz1iVb78Ud/0FvDlItHFaX+Cu0WvsHPPRKBNl1sCfPRfuqTEkpbJ6jpEe8fI8quQW/nKxwFftbhgYnIfNg9a8eC0YFIPnmtAkbD5I2DFQkEsRukNT50HtWI+diJD4++J4hUeMUZLBMu80S7M1mPX0/XLgJWLgNa9oJ3x17SJ2zc712TX15VDWe//C776bYCJ/0JpjBkMAuE2fi80Z7btyBqTLePa/LzAmbhtBVB6EOgxAWXl5SEBNAFtUqBlEUfJ7g2cCtDt9dWKu0sq9ogE2qmQeuhnSqBtn7XgkeiusXSApRtBDI25TmEBsOBcnktWt7FwD7mML9RGik6Mk4j0XOz2CT8z3GoFDdLmks9WXM0t3HFL9lUVY9fToZ1yWa1xBRRukIcES3huAV8ay1VHWMVJJgJtVrxsXQ78+DHQZyp8jTvaLsaZlABkSXNqXmDLcuD4foBY1Ou1AtqfDJ+qsYIgHa1hgbk5HYDXzZ4VpPAgK2y4+aTKos3ncZ06wOMzw7ONVz+YT50HT4cRSfWQYeXsO6ScXSVSjl2yNC4p9Yx8czK9ju59QoBbz5dO/A+xFF4vUqJ9twzoNDIQOhJLn7Jt+kqAzkS6p1ChPRbOSk1Am4r22p8F0C4eCG3sfKlUS9DSS6CdIMFa6FYCbQtCS3YTAhhU6CLH7l82LvwRJkblX9Yia/BslBU0N3RpYyDsOQYc2Aa07cfgIV5zZctOjhN49jKAcn+P/gM8bQYZGpcdRM3ufwRavn0V+P/2zgNciup+/+/eXkUUECEgAexijYqIFY0VsWsiWGJJYokaoz/9a9QYNZYkNkwsqFiJBQU1GHuwIBiToFFEUUSsdOTWvffuzv/5nmXXey/33p2dnTl7Zs47z3MfTHbmnO/3fc/OzmdOW/JRqhdN9iAeNtq67b1UO1m7X3q2F1FRBO3UFlrHpBZPM3zVbvEpPf9cPWCt3QowCsMFpW2lt7PKNqe4UKAtmqsXM/96EHh3WvZbmax4P/4+NLZ0/7CcvZDcz1D3tzVfAbJ94aCdkBy0U6imFOSesf4r/Fh1XNq7evFbUQHn8V8BKxcDleur4ehh2aJPv/KsMa1ABrQfPQtY/RWw0RZwDruWoB1QEyFoBySsh2IJ2h5E03mJAouGZQpcsfl+aG5LLdRk6iFfbnl7Lv/K3+rVq7OGqnpeqqpSQxxl9cqdjkfrtkf6NuRc7dmalLmKp6ZiybH8IHvas4qz9gTJQeIQTeWQlxDSMxHGXkG3Oed7XhRBW73Iev2vwPyXgNFnILH5/q5HjOSrJ6/3pkAhQVvd+0pjwNRfp1a37+nY7zdIbJIa0q/7SP9mpFfc533NXwcEtGXBwp62X2pfY/o3L/1yPzNE+Kt3UVRWgVhxKRLzXgSGjUZioy0L0mb8VYilBa2AgLY8txQ3LAU+fQPYdB+0lK0Xmg6PoPXxu3yCtt+Kei+PoO1du8CvTA39qwbuPxGI1wNb/hiJUWeE4kctl1XHU6BdkRriKCtXbns4Wnfyd0EeBSgy5Hb112rrpuY2x9ULCzV/UF50rPwczia7WNeDHHgjD7CCKIJ2Zn5kLKZessjIj/ZQIjnLka2XNUDZWXQnBQoJ2hKK6jGW0UIvXAcs+2Rdf4pLgT3PhDN8r1BMqUmPlJA2bvJLZ1O+COn7YFtzgxqa35ZEj9NN1Mv95tXAl3OBTfdCc2tCjd4oX/MF8NSFQEk5ig66FMmNR6iXvfLH+40pbpsbR3oxtPa7bPD7G5xfBO3gtM21ZIJ2roppPD8zx+6hnwGNq4CtD0Zi5M+MBO3OD/i5gLZIqoB21efANx8AWx2oftz9vAmn5xFJnPJW303Zash5aRHwwEmA7Hc88mS0bnmwbz3tGpuSlVVFEbTTRqaHLbc39vth9Q7a2hLGzd22shECKDRoi+5qUSyZgrTwTeDr/wGrvkxNQek7HNhifyTKanqcZ26Kd2qdhlgCkAXpNtkZbZUbdGjnAuHtp5ZEYZpCvtqrfbRXfYK26ZcBlesBx05EYyK1mGJXh5qeIqO/GlYCm++L5B5nqd/L8vpvgKnnpy7Z/yLEB+zIhazyNcei67m9l16zCdp69e6pNoK2OV50GYl6eI6vAb79ABi6O5qa477NXfYrddVjIothyBzMZFK9CMgVtNPzvySmruaiF6KnLgXaMWDy+NQ+tDufgNZtxkUetNt7IQ9YYe2tiDJod/7uqrmTiUbgqd+kRoUcfgPiFeHascCv+5Fp5ZgA2qJJ+mWjgGj6fiqwJcM53bx4NEFXNTLp5T8CC2cBNX2An96dmR+shsmXlQD/fhSoqIUz4rBQ9NB70TW9aKrcm6VHuSf/FGh/9Bza3pqcqurIP6GpeuNunyO6Am35TZeX4UUrFgItTXAGbBNZbb34wWuyK0DQzq6Rn2cQtP1UM7+yCNr56afl6vR8Kb/3HZQvokByej9MWTk31x4A9XBTlASe/DXQXAccdg3iNQNUOfJQJPto53tkQB4OEokUyHs95KGj/ZxrybknkFSLCa1cBCz/VM2Rb2puNu5Fh1cturpOHsDVA5XkLC89Nhii9A4jbOsE7WxDuv30qKuyVE/fl28DL/859fHupyM+fAx7nIIW3kX5poC2i1CNP0WB9qs3A5+8BvTaGDjuLxnQVr32H874fvs/+S3qPSxy3wH1m1vsAG/cCZRWqrUaGpu6/+2W82sry9A25xGgujecrQ/pcaeKroaOC8hH5QWs8Y08ogEStPUaS9DWq3dPtRG0zfFCeyQKIt9/FnjnYeBHJyC5zaE5r/aqHvBXfAw8e3kq/p3Ho2XrsQpG/QBt1VOHltRiPrJv7bjrEK/q5+nhScXashp46Y9A40pg73PRttFWPQ6xbf9w4feLDu2Gu6hQabTqU+DpS1Nnh/hhVSdoKwD45y0pANjzbCTWznd1Ibkvp6jRF5UVwKx7UiuS73YqmlpTvZU8CqsAQds//dXvQWkx8NlbwMDt0FpSlRlhlLp3LUxt/ycrqB87Ec2x8tD01rtVSeU5/7nvXygccAni/bfr8Texd+/emS31BJqzvVDvvBia29h4HhXoTgGCtt62QdDWqzdB2xy9jYqkwxCx6g2AE+7JeZsO6Q0XYMfsyakF20aegmanWA3/9gO01UPFt+8Bss+qHCNPRnzzAz2BtnpT/86DwHtPp8pabyPg+DtyztkoE30ORum95H/AP65JlXzgpYhvlFr0pqtD/Jdr0vMi0wsU5btXqx9pBQXaUq7kLD9k6VWS1Xfg7iPV9AkM2gHOgb/Vvm2JeJDeClAepsMyHNgPr00ug6DtrzvpHS06L4aWGY2TbAVixWhzel70y9+o9JWm7tFNywHZj7isEjj8RjQ5JT2+VPNjey99GbKmKCpA0NbrKkFbr94EbXP0NioStQDZ57OB/z4B7HC0561d2j/gp7edynWOdnfCpHrqKoHZ96V6tKWnrk0We8q9p04NQX9/OvCvh1PVDRgB55DfaQcioxpBp2AEnKVdxGQOpKxePXRUt3PxxBt5eRGTBZZku46G5UC/zYFtDkGiZiM1UqCQQ86DAm31wmbVotQWW0N3Q6L/NmpYZdGCfwKysv2Ox6F1g6GRn8tvcjs2KTaCtl435B4m951C3nuCzvj7hQ+hXqjJFKiejq5AO/3CQq4z4cVo0Jqx/MIqQNDWqz9BW6/eBG1z9DYqEnkgEfiUL6QMJZMfa7/2L/ULtEUwv3rq1Ny2igrgvWlAvEEBYUtJNfdx7AK20z3U8kKjqzaR2Vf1zbuBec91LKGoBBj7e7RuMCzrA2CQX4igQFsNE5/2f8CyBUBZNXDyQ2rKRXq9A9EsHo9H+kE/SN/CVLbcQwV60nAn99DOLwEJ2mFyNDyxdrXzQHfRdwbtzG/hJzOBvpsiUds/r7VPwqMaIy2UAgRtvcoTtPXqTdA2R2+jI0nvT+rHXGQ/QdtP0SSu9Kq7brf58rP+qJSlhi+u/CQ1H7Kro7Yf8JM71WiBQvUsBQXaam2Ddx4B5k4Fhu0OZ98LOCoiKg07xzzUqKBP/gm8/ldgywPgjDptnbZA0M5RVJ7uuwKdQVv1iL87Ffj334DiMuDkB9HQ3Orbi3bfE2CBoVeAoK3XQoK2Xr0J2ubobWwkalh1siW1j/XgndDckt8cT1NB21gDQhaYai9zH0tNO+juOO4vaCpb39Mwfz/kCAq0M0PmE61wiktV7zXnQ/vhWPjKUKMbnrkU+PZDoKgYOO2JddZ8IGiHz9eoRUzQjpqj4cuHoK3XM4K2Xr0J2ubobWwkamG0x88BVn0JbLo3nL1/lVcvXVRAO73wlfybXvjKWBM1BqZA+z9TgHef6r7Wo25CU9VGkQPtdMLpbfE0ym5tVe23T5Oh2dm25dMllOoZXDofkBEOm49BctN91tm5gaCtyw3W050CHDrOtlFoBQjaeh0gaOvVm6Btjt7GRqJA+6FTU9teDRkJZ/+LCNqAWlG96Kt3gW/eB7b4MeLl63PhGABqz9rPZwGv3tJ1my4pB05+GA1N3ub9t18/QF5weNnjPagebWO/xJoDczM/2Y+QMusBvHZ7asTNvuejZf0hRqytILGl17lIt9POaxoQtP1oBSwjHwW4GFo+6vFaPxQgaPuhovsyCNrutQr6TO6jHbTCISlf9cw0LAMWzQG22A9xlOYFlFHo0ZaH6BrZtumeY4BkAhi+JxJ7/YqLxgBq8Se1pdW0i4ClC9Zt5Xv8EonNxnjWSs19/eIdYPb9wIixSG55QM57vBO0g735qHvGV/8BXrkJGL4HnNG/zOvlXHfRqp0HShxg8vjUKSPGovVHEwq60F4uyhK0c1GL5wahALf3CkJVlpmLAgTtXNTK/1yCdv4a+lUCQdsvJSNQTnoP3s77k3pJLQqgLXmrnv4nLwCWLwR2mYC2bQ5T21bxgNqzubwYqT3UP3oZSLQCsgjazifAGbZHt9uCudFO6T71fGDFIqCkDPjZoznvd07QdqO093PU/OSXbgA+m50q5IwnUV/f4Pvidyb3aLtRj6DtRiWeE6QCBO0g1WXZbhQgaLtRyb9zCNr+aZlvSQTtfBXk9V0qEBXQVkOkS0uB5u/gVPRSkC2rlfNIKSBzZ0Uj6eGG4wCxmJqTLQuE5bNVnOrRlj2pZ00Cth0HZ/ujcu4tJWgH20rVPP0VnwCz7gGGjoKz3RE5e+Q2QlPnaLuJn6DtRiWeE6QCBO0g1WXZbhQgaLtRyb9zCNr+aZlvSQTtfBXk9ZEGbUlOIDK9GFqhtqoyvZmJPnL4pU/7+b+co22m++3nJ4vvXubRm5mZv1ERtP3Vk6XlrgBBO3fNeIW/ChC0/dUzW2kE7WwK6fucoK1Pa6tqikqPtlWmRSxZ9mhHzNCQpkPQDqlxEQqboB0hM0OaCkFbr3EEbb1691QbQdscLyIVCUE7UnYak4z0dMswYjfrCBC0jbHN6kAI2lbbb0TyBG0jbLA6CIK2XvsJ2nr1Jmibo7c1kRC0rbFaW6LSpmSl69jnbwMbbIJEdd8eVzUnaGuzhhX1oIDJoC3fEflOyXcrPfxf1ljgES0FCNrR8jOM2RC09bpG0NarN0HbHL2tiSSKoC09qZKXHK2trXkt9mVNQ/AxUbX41oczUqucF5cBJ96PhpZEtz4QtH0Un0V5VsBk0FbfqaXzgJdvAn64K5zRvwhsQTvPAvLCvBUgaOctIQvIUwGCdp4C5ng5QTtHwQI8nUPHAxTX5qKjBtoC2ZUV5cB704GqDeAM31Pt6+zX4l82t5X2uZeWlqpVzNMvM2T18vShoOD96cC/HgZiRcDJD6GhJUnQZuMxWgGTQVut7v/abcCCmSkNT5uK+sZG3teMblG5B0fQzl0zXuGvAgRtf/XMVhpBO5tC+j4naOvT2qqaogbaapuv+c+lelPlOOYWNFX0VVtZ8fBHAZl/XV1VBfzzVqBhBbD3OWguqVWjB+RIveyoAD56CegzDMkNhqiXHd0d7NH2xxeWkp8CJoN2Zou21/4CDNkFzs7j2aOdn91GXk3QNtIWq4IiaOu1m6CtV++eaiNom+NFpCKJJGh//R/gheuBknLgJ3ei0Snlnto+ttqysjKUr14ETL84VepOx6NlxBFqT+70Ie2q/fD9nkYUELR9NIdFeVbAZNBOb9EmL7G8bqPnWRheqE0BgrY2qVlRNwoQtPU2DYK2Xr0J2ubobU0kYQTt9g+dnRcGkt5WGWYZq18GlFUiUVLV40Jc1hjtY6LSZqrKy4BnLwPqlwMHXY549UZoaWnxVAtB25NsvMhnBUwGbZ9TZXGGKkDQNtQYi8IiaOs1m6CtV2+Ctjl6WxNJGEFbDQ9f+Snw6s3AoB3g7P7zDsMoBdzSq/MmEglrvNSZqPRqy59oLcPym5qaPFdP0PYsHS/0UQGCto9isihPChC0PcnGi3xUgKDto5guiiJouxBJ0ykcOq5JaNuqCSNoq4WBZt0NfPh8yq5TH0VDM1cXD2vbJWiH1bloxU3QjpafYcyGoB1G16IVM0Fbr58Ebb1691QbQdscLyIVSRhBO1uPdqQMsiAZgrYFJocgRYJ2CEyKeIgE7YgbHIL0CNp6TSJo69XbNWjLcNj0QkN+hbhy5Uq/imI5IVIgjKDd0xztoKWXuisrKzND05ubm7mieZ6iE7TzFJCX+6IAQdsXGVlIHgoQtPMQj5f6ogBB2xcZXRdC0HYtVeAnqh7tZ555Bvfddx8WL16MwYMHY8yYMTj11FMhW3+0P+699161ANTZZ5/tOjCCtmupInViGEG7kAaobXaWzgNevgn44a5wRv+C2+zkaQhBO08BebkvChC0fZGRheShAEE7D/F4qS8KELR9kdF1IQRt11IFfqIC7bvvvht9+/bFiBEj8MUXX+Dyyy/HBRdcgHHjxqkAZs+ejUmTJmHu3Lk44ogjcOmll7oOjKDtWqpInRh10BaIKy0tVZ7JPs89bTPlxlg1P/y124AFM1OnnzYV9Y2NeZfrpu6onkPQjqqz4cqLoB0uv6IYLUE7iq6GKyeCtl6/CNp69e6pti7naF955ZVYvnw5Jk6cqK5dtmwZvvzySzzwwAPo06cPQdsc/4yNJMqgndnq69t5QHEpkn2Gq5Ee+cC26tFe8Qnw2l+AIbvA2Xk8e7TzbN0E7TwF5OW+KEDQ9kVGFpKHAgTtPMTjpb4oQND2RUbXhRC0XUsV+InrgHYymcTRRx+N3XbbDRdeeGGHAP7whz9APmePduC+hL6CKIO2bD9VvvR94LmrUz4dfj3ivTZRPdtet/9qPz9cvmMyR5tbiOX3NSBo56cfr/ZHAYK2PzqyFO8KELS9a8cr/VGAoO2Pjm5LIWi7VSr489YB7dtuuw2PP/44pkyZgoEDB7oCbenJu//++zucK71+J554Yl774AafPmsISgGBHFnFW4AxaofcwIoX/wt48fpUamOvRnKjLSFtHmu+BSpq4ZRWKfDmUVgFZIG5fPbiLmz0rD0KCrANRsHFcOcgI6bi8Xheo67CrQCjL7QC8jwoz0TSkcBDjwLy28Oj8Ap0AO2HHnoIN998M+666y7suOOO60TXXY+2fHFuv/32DucLjJx55pl8yC28xwWJQKBT5jDLj3vUjsz87M9mAyWlwKCd1I9H0aevAa/eApTXAD+9G60o5oNNAc2P8sueAspqTdXSfvKZDpIWiqBtTZMxNlGCtrHWWBMYQVuv1elRknprZW1dKaBAWx4m7rjjDtWLLcAsi6J1dXDoOBuRWwWiPHRcNJAXCSUlJUqOtrY29VKh7P1pwDtTUhKNvxdNsQpu0eW2wQRwXpBDx8V/ASj5V+6f3I4tAAMjUiSHjkfEyBCnwaHjITYvIqFz6LheIzl0XK/ePdWmQPvqq6/GtGnTcMstt2Do0KGZ82UlcoEJmSsqPXbXX3+9eqi8+OKL1VxUNVQ2y8FVx7MpFM3Pow7anV2T70llWQnw3nRg/YFIbrIrGhoaomluSLLqDrTlzXp6Lr2MuHA7lK09XCvAXvgWnJf+CGy2D5w9fsnF60LSLnSHSdDWrTjr66wAQZttotAKELT1OkDQ1qt3VtCWbby++uqrdc576qmnMGjQIDz55JO49tprO3x+xRVXYOzYsVkzIWhnlSiSJ9gG2mKiwLbkLQfnIhW+WXcF2gLZZXVfA/99Ahi4LZwt9s8KyFKOHGoLtjVfw3n1ZhT/YDtg8E5ITJetDmPAGU+irq6u8EkzAuMUIGgbZ4l1ARG0rbPcuIQJ2notIWjr1TsraAcZDkE7SHXNLdtG0DbXDTsj6wq0FSy/fjvw8aspUU6fivqGrrdmy/RgC0rLAnhFMTjvTgd6bZza73zPM5H4x7XA0N2R3OLHHMFgZzPLmjVBO6tEPCFgBQjaAQvM4rMqQNDOKpGvJxC0fZUzr8K63Ec7rxI7XUzQ9lPN8JRF0A6PV1GNtCvQVvuVL54NvHwTMHAEnIOv7LZHW/V+f/0f4MUbUNJ3GGJ7nQXn8XOByvXgHHkTnNp+mWk1Mkfb7RD0qOrNvLpWgKDNllFoBQjahXaA9RO09bYBgrZevXuqjaBtjheRioSgHSk7Q5lMV6Cd6aWWFaUBtSp+d9uwKSh/5yEUffAMimX0+H4XwXntdqB2IzhH3YQ1a9YQrkPZMvQG7Sdo+7USul4FWFuhFSBoF9oB1k/Q1tsGCNp69SZom6O3NZEQtK2x2thEe1p13A2wlJWVoTy+GsXvPYlYzYbApnvDefVWYO9z0Fy+QST3iDfWzBAH5gdoy/1UVrlPt1vZG14WKeVBBdwoQNB2oxLPCVIBgnaQ6q5bNkFbr94EbXP0tiYSgrY1VhubqB/bewlsS892bPknwLzngf5bwdlsH9WbzYMKuFHAD9CuqalB7O0HgXefArY7As4uE7Iu4ucmNp5jngKyVWR6RxfZ5UW2j8x3WgpB2zyfbYuIoK3XcYK2Xr0J2ubobU0kBG1rrDY2UT9AW5LL9CYmW4HiMtWT3d1wc2PFYGAFU8AP0K6trQUeOR2oXw7U9AF+ejdXuS+Yo8FUnJnW0rgC+OQ1INEG9NsUzg92QEtLi/rzehC0vSrH6/xSgKDtl5LuyiFou9NJx1mco61DZQvrIGhbaLphKfsF2um01N7ZjqP+eFABtwr4Adpqtfxv3wfm/QPY6kAk+m+DxsZGtyHwPMMVkHuVeFz04fPAm3d1jHbjbYCDfoum1oTq3fZyELS9qMZr/FSAoO2nmtnLImhn10jXGQRtXUpbVg9B2zLDDUzXb9A2MEWGFAIF/ABtacuyCr687JFhxLKIH1/4hMB8lyGqHQ5WLQSmX9L1FVvuj+Tuv/C8hSBB26URPC0wBQjagUnbZcEEbb1691QbQdscLyIVCUE7UnaGMhmCdihti1zQfoB25ERhQh0UqK6uRtGsScC857pWJlYEnPY46hsaPb1gIWizwRVaAYK2XgcI2nr1Jmibo7c1kRC0rbHa2EQJ2sZaY1VgpoO2fE9k0T+5Z8tK5jIXmL3lepuoWuzu+WuAxf/uvuJTHkFDS9LTwmgEbb1+srZ1FSBo620VBG29ehO0zdHbmkgI2tZYbWyiBG1jrbEqMNNBW83/XvIh8OkbwOb7om2DoZDtw3joU0B58K8Hgfemd11paQVwyhS10ryXlyAEbX1esqauFSBo620ZBG29ehO0zdHbmkgI2tZYbWyiBG1jrbEqMNNBW61o/uApQNNqoPcg4JhbuaK55hYqIwrK4yuBx84Bkl3sj77zCUhse4TnBfAI2poNZXXrKEDQ1tsoCNp69SZom6O3NZEQtK2x2thECdrGWmNVYKaDthq2PPM24ONXgRFj4Yw8hXt0F6CFZkYWvPRHoPm77yNY64mMMpCh/V4OgrYX1XiNnwoQtKJ6bVsAACAASURBVP1UM3tZBO3sGuk6g4uh6VLasnoI2pYZbmC6BG0DTbEwJNNBu6SkBBUVFYglWuEUl6p94r1uI2Whvb6lLPcr8aGkuAj4+gMgXgcMGIFkWbXyxCtkS4AEbd9sYkEeFSBoexTO42UEbY/CBXAZQTsAUVkk1MI60lPy3Xft3sxTGCqgUQGCtkaxWVW3CpgO2unA01uH0crCKiA+yMsPOWQrNz9eemQDbfm9rqyshNwzZQ54Pr3nhVWPtZuqAEFbrzMEbb1691QbQdscLyIVCUE7UnaGMhmCdihti1zQYQHtyAnPhDIKZANttb3Yfx4F/vMYsOOxSO54nOc9uyk7FehKAYK23nZB0NarN0HbHL2tiYSgbY3VxiZK0DbWGqsCI2hbZbeRyWYDbbUg3sOnAQ0rgOoNgRMmcUE8I50Mb1AEbb3eEbT16k3QNkdvayIhaFtjtbGJErSNtcaqwAjaVtltZLLZQFstxPb1XOB/zwIjDkViwPaeVzg3UgAGVXAFCNp6LSBo69WboG2O3tZEQtC2xmpjEyVoG2uNVYERtK2y28hks4G2zAsvLy9Xa6vIomvxeFzND+dBBfxSgKDtl5LuyiFou9NJx1mco61DZQvrIGhbaLphKRO0DTPE0nAI2pYab1Da2UDboFAZSkQVIGjrNZagrVdv9mibo7c1kRC0rbHa2EQJ2sZaY1VgBG2r7DYyWYK2kbZYFRRBW6/dBG29ehO0zdHbmkgI2tZYbWyiBG1jrbEqMIK2VXYbmSxB20hbrAqKoK3XboK2Xr0J2ubobU0kBG1rrDY2UYK2sdZYFRhB2yq7jUyWoG2kLVYFRdDWazdBW6/eBG1z9LYmkjCBtiwEU1FRoRaCkQVgmpub1YIwPMKtAEE73P5FJXqCdlScDG8eBO3weheVyAnaep0kaOvVm6Btjt7WRBIm0FZbm3w+G3jrXmDEOCS3ORQNDQ3WeBXVRAnaUXU2XHkRtMPlVxSjJWhH0VWzc5JnwNLSUhVka2srqqur1ZZxbW1tZgcekegI2uYYyVXHzfEiUpGECbRra2uBqecDKxYBJWXAzx5FXV1dpPywMRmCto2um5czQds8T2yLiKBtm+OFzVee/6QDA3OfTAWy/ZGQkYPSgUHQ1uMNQVuPzm5qIWi7UYnndFBAvsBlZWUQkJE3lfLX+QgTaLNHO5oNnKAdTV/DlhVBO2yORS9egnb0PDU5I3k+LP9iDvDKTakw9z0fRZvtTdDWaBpBW6PYWaoiaJvjRSgikbeSAqax/zwGNK0Gdj4BzU7JOrAdJtDmHO1QNL2cgyRo5yyZtRfIPUAeDktKStQLRDlknYbuXiTmIhRBOxe1eG4QChC0c1c13Zkg67Z01ZmQe4n2XKFAu3EpMPXXqaSP+jOKNtyEoK2xCRC0NYpN0DZH7ChEom6ga74Anrowlc6PfoqWbcYhHo93SC8N2k1NTZmHVi4wFoUWEJ4cCNrh8aqQkQpcy2KIsU9mAh++ACxfCFT0AoaNArY/Cm3FFUjfx7zESdD2ohqv8VMBgnZualZWVqKkfgnw2Sxg8zFoKalZ5xkntxLtO1uNFEy2pJ7/ilIvMTlHW187IGjr0zpbTezRzqZQCD9vP7Rb5sO0tKRudn4ccrOsLAHw+LlA0yrg0N8jvv4P16lDYpBVJtu+/hBYtVj9WMlNlrDthwssw40CBG03Ktl9TmaEzit/Bj59Y10xqjcADr0aLZUben7QJmib1cbkt0lerIj3hdplQu5NjuNoE4agnZvUat2WR84A6pcBA7eDc/AVqK+vz60Qnq12clGgnUio50GCtr5GQdDWp3W2mgja2RQK2efyAy6rO8Y++DuwcjGw47GIl9b6CtvyplJ6tpFMwonF1MJh8sDS/pDPq4uTaLv3BAAOMPJktGxxkOeH1ZDZwHANUICgbYAJhoegeq4WvAy8fkf3kfYdDufwG9SwRy9wRNA2qxHI72PR+88C7zwM/OgErbtMZEZPxADhbBkpoePlM0E7tzZYU1OD2LT/A5YtAIbtAWff8wnauUm4ztkE7TwFzPFygnaOggV4OkE7QHELUbRa7THWCjx4cqr67Y9E6w7Hq72hcz3Sb/4FWORhQMqQB031IzTnfmDRHGDUaWjdeNt1ylegXeKg7b7xQDKhzmvZbH+Cdq4m8HzPChC0PUtnzYXqXvbY2cB3X/ec81F/RrxmgKcXlgRts5qT6q18+FSgYSUgIxZOuEfbLhOqvb3xV+DDF4FdJiC57eFatpIkaOfWBsvLy1FW5ADfzgcGjkBzvMXoedoyOkOOzh0euWUd7NkE7WD17Vw6QVuv3j3VRtA2xwtfIpEbbnVVJfDE+cDqL4AD/h9a+m/bI+DKNfKmXW7S7bdeUA8F8uZ/wT+Bkaegte/mqpyammrgriNT8f5wJBL7/kYNCWp/ZIaOr1gMrP4SzuCdtb2990VIFhJ6BQjaobcw0ASkfcg9Dncdkb2e3U9HfPgYgnZ2pYw/I7PLxH+fAHY4GolNRq7z+xVUEgry7/sJ0NoM9BkG54gbtfSUErRzd1SeieTZSDoZdIw6yD3C1BWd50J3fhbzWq7X6+QlhTz/SaeMPC+m4Z+g7VVRb9cRtL3pFsRVBO0gVC1wmept7Nqh3TKgW4andfemU825rqwAvvof0Hc4WmOlqnd6nYfQH2yP5IG/VW/fFYD/59HUnMbRv1AA3rnHvPNiaALwJr9tLbBlrD4ABQjaAYgaoSIz97hJR6dG3fR07HMe4oNHErQj4H/7XSbSI7V0/TapYetfvAN8/Cow4jC09dk0r4X23NpB0HarVLjO62p173hVP0/3KT8yV8+edV8D8hJr4LZwttg/8yKJoO2Hwu7LIGi71yroMwnaQStcoPLTW9R0N6dQbtDp7WycN+5C8n/PAr0GAMfdnhlGp4B61iTgo1eAvc9B2+Bd1ENB+8VkBKDTQ8rbpxqm7b0KZBGrDVgBgnbAAkegeHWPe/mPwMJZ3WYTKypC0SmPIFlSoXq2enpx2VUhHDoegYbiUwrpbeTSC7FJj5+Xef+5hkPQzlWxcJzf1X7V8UG7Fgy0Ve/667enXiTJcfpU1Dc0qjZO0NbbpgjaevXuqTaCtjleaIkk1YNdieK2ZqBhOWLFpXDm3I/kwtlwyqqBkx7MgPb3C7fEVG90Lg+YBG0tdrKSHhQgaLN5ZFPg+x6h87vt1S7e5SdA/62ReO4aYN/z0Dpgh5zWvGgP2tlegGaLl59TAS8KELS9qGb+NWpNnqoqYO6TqWC3P7Kgu7vIav6li2cDL9+k5rY7B1/JHu0CNSOCdoGE76JagrY5XmiJRHpwit6ahKK5TwDVfRE77PdwEgk4X72H5KCd0LbeQF+GshG0tdjJSgjabAN5KqB6YZZ9BLx4I9C0umNp2x2B4lGnIPG3s4BVX3S7JkVPIQhor1q1KvWCsygGIIbWtSOB8gydl1MBVwoQtF3JFMqT5FmrtLRUxd7a2lrQ+eQyUkPuc0WxGBCLqReSEpMc7NHW27wI2nr17qk2grY5XmiJRIH2k+ejaNXnwJqlwPF/RbLXQLRVrK8WQvNrz22CthY7WQlBm20gTwWkl1l6YkoEgj+bBaz+GiirBIaNRrJifbUgkuoxkuHlo05F64bDc+7Rlj14y9d8ATx9KVBRCxx9sxpBlN5PWe67ft1785SDl0dQAYJ2BE01MCU1Qqi8XG392nl9IIK2XsMI2nr1Jmibo3cgkcgQb5kD42ZlTLVv7KpFKFr4BmJDR8HZaAv1gCfDwv08CNp+qsmyvCjAoeNeVLP3GrlnyV8afuWeKr0x3W1z6FYp6dGWRSTL5j0LvP2guqxo3DVqH2XnuauBvsOAQ69Cfb23fbrdxsHz9CsgL2nSvY3y+9x+Vw+/o0nvHiLldl58lKDtt9osr7MCmcUlp10ELF0AjLkArYN3zbyUJGjrbTMEbb16E7TN0dvXSOSHVYY9xhpXAeXVaENxVmCWm6G8dWzfkxLEYiwEbV+tZmEeFCBoexCNl/iugID2mjVrUFmCFGiX16Bol/FIznkwtTqvHOPvRSPKXb0s9T1AFhiIAnL/kVXGY5+8BjSuBLYdh6bmeCCwnXkW+PR1INEKZ7N91Vzd9GrqBO1ALGah7RRQW8tWlAH3HJv6f7c6EIndTstsnUfQ1ttcCNp69SZom6O3r5GorRS+mAO8/Gegohfw0zvR2GLGno8EbV+tZmEeFCBoexCNl/iuQHoxNOnZlL/0i82Sum+BtyYBGw6Fs8sE1esdxEtPtwnJ90Xik3+D7n11G1OYz0sttLcEePzcVBojT0bLFgepvYW9HulRF533dlZ1LfsQmPG7VNFjfo34D3bJTEcgaHtV3O7rpF2lV8iX0T3Z7k9qF4ePXgaWzFcLs8UrNsy0QYK23rZE0NarN0HbHL19jUSt8Pjek8C//5Yq94R70FRUGcgb81wDJ2jnqhjP91sBgrbfirI8Lwp0t72Xmhe+dtqPwFe2YcXywCsPutkedr3EKNeoReFWfgZ89R6w9UFoTsQyCxl5LdPm6+SlRYUTB6b8HGiLAz/+P8Q33sHzXHxVnsx/Xfox0Hc44q3fr6miQLv+a2Dqr1OSH3oV4htuRtCOeAOUNiEdLumXYzIF0K/7g3q+bFgCyIiMTXZGW+8fZh0xKfeo9vG0f6lE0NbbGAnaevUmaJujt6+RqB/ekhjw7jRg/QFwho7ObKXga0UeCiNoexCNl/iqAEHbVzlZmEcF8t1HO7OSr5MAikrQ0tqaV69oV2mo+ZXVVcC9PwESLQq0EyNPzQz79Ji69ZeplxdtjUBLE5yavh2Gc+cqToc93weMgHPI7zK/9+Kf1FUkoySSbUj2+oGqKw1d7NHOVW3zz89MTXjlJuCb94H9LkTLBsN8uzeo9vbMpcC3HwKVvYAJkzNbv3pRh6DtRTXv1xC0vWvn95UdVh2X4UhiTneHzPdRK7DmcKxcuTKHs3lqrgoIbItn6YV70nOyci3H7/MJ2n4ryvJyVYCgnatiPD8IBfIFbTVF6Ov/Ai9cB/QaABxzK+ob/eu5kpxToF0NPHI60LAC2PEYtG1/bNYerCD0ilqZMmpB9JURC/n0NirwmX5xqkd7vf5qx5C6urqMXFJHuq7Ow3wJ2lFrVVDP4tWyq9fk8ankRoxF648m5LQjQk+qqPb25p3AvOeBgdt22BPbi5oEbS+qeb+GoO1dO7+vVKD9zDPP4L777sPixYsxePBgjBkzBqeeeqra8kSO1atX4/e//z1mzpyJ3r17Y/z48TjppJNcxULQdiVT5E4iaEfO0tAlRNAOnWWRDDhf0FZDOP/7KDB3akqfCZPRkCzJLHTll2iqnmQcWLEIzsZbqwf2bMPZ/aqb5WRXQPnTtAJYMBMYtjvaavpnfREiMCb3wdraWrUgnykv4rNnyzPcKKBgeNbdwDfzgL3ORkuvwb71aMtLG2lzsbolQO1GiOe5BSFB242j/p1D0PZPy3xLUqB99913o2/fvhgxYgS++OILXH755bjgggswbtw4Vf7FF1+M5cuX47LLLsNXX32Fc889FzfddBP22GOPrPUTtLNKFMkTCNqRtDVUSRG0Q2VXZIPNF7TVFKFkI/DfqcAGg+Fs8ePApgjJw7XAWeftoSJrjkGJyciF9FZgMrdVeqU7H513DOkpfLWVZ8xR88NLqtdXoO1mC1CDJGEoWRRIw7CclvY2PSrVjxdl8hsq5ckLmnxf0hC09TZngrZevXuqrcPQ8fSJV155pQLriRMnqh/0vffeG3fccQd+9KMfqVOuuuoqtcjG1VdfnTUTgnZWiSJ5AkE7kraGKimCdqjsimyw+YK2CCOAJQ/V8rArAGYSMMn3rP3e45E1sovE0vtkS/7ijTwXeTkyL1NevRWoWA/Y9zw0NjV79ll+f6tkO7m/nQk0f4eSQ36Lpn4jfBtW7CXHqF2jRhis3UVAvpP5rCbvhzZqisl3i4GZE4GNt4Iz6vTAXsh5iZeg7UU179cQtL1r5/eV64C2/FgcffTR2G233XDhhRdi0aJF6n8/99xzqtdbjoceeggvvPACHnjggazxELSzShTJEwjakbQ1VEkRtENlV2SD9QO0TRVHAaJMMWtcBadyfeuGm8s+2UWfvQUs+xjY5lDES9frEbbTK82LnwLlaTBXkPTBdOBfj6SsPvhKxPtu4Rnc5aVMZcsq4NGzVHElu52I5i3HZh1qbmo7My2uzIuRGVcBJWXAQVegKZkaCVKoQ41g+NcDwP+eSYVw8kNoaEXePdF+5UPQ9ktJd+UQtN3ppOOsdUD7tttuw+OPP44pU6Zg4MCBePfdd9V87VdeeQXyRZHjiSeewIMPPojp06er/y1v1ydMmNAhXjFZzinkjUeHgKyjawUEcuRtv0k9L/TKLgXSw954D7LLd7+ylYWrpA3lewj0RLUNqmGqL14PfDYb2GJ/YM8zrbrnFyMJ3HNsqolsfTCcUad1CzbqN7FheWpRO1nF+YBLkYyltmxTn635JrUPduX6wNjfI1n0/Z7rXtqg8mb+S0D9UsR2OFqVl+/wXy9xRPEa5de8GcCse1Lp7XMeksP26HKxu/b3kHwWw8umo5qPL/tXv3QjsPE2ai91k56/0kPQg9Qgm0Y2fS7fdRkJxaPwCnQAbempvvnmm3HXXXdhxx13VNF9+umnOO644/D8889jww03VP/fI488ghkzZqie7fTx0UcfdchGbi6bbbaZmhfEwz4F5KYv243I1AMeVKBQCsgiQO1X5i1UHKw3fAr4Bdrygjqqv4Nyj8fDp6VWKt9wCHDUTdZsCSbPONKLiMd/Baz6Qi1G1TZsr257oaUXtPT9aR16rVs32iozF1t6tdPza2UocldztHP5FslvsLzkkUPKlt9iQk4uCnZ/ruhalmxOQW1xKbDfRYgnY+uArfhZLrCz+B1go82RKK0ObIi5tEcBq/a70Jj0gk9Gf8i8cZPg35/WYGYp6UUQzYzOrqgUaMvNV+ZgSy/27bffrhZFSx+y4vh+++2HyZMnY5tttlH/9w033IAlS5bgT3/6U1a1OHQ8q0SRPIFDxyNpa6iS4tDxUNkV2WCjPHRcDVdduTDVoz18D7Su9wOr5gGrId+lpUBbM5ySih73yVbDjVvXdOjRboy39AgemT3Ui1I9390tkpbty8PtvbIplPvn7Revaz8NoH1Jah/1t+9PDeeu3hA4YZLnFx7tX5x03r4t9+j1X8Gh43o159BxvXr3VJsCbVnUbNq0abjlllswdOjQzPkyJ1ve3P3iF7+APCzIauTffvstTjzxRLUS+cEHH5w1E4J2VokieQJBO5K2hiopgnao7IpssFEG7XQvWr6LgYXZ/FymSXU3R7u7/NWCW7KH+kt/BDbZGc6Y33gaJUbQLkwLU6D95h2pIfxlVWredH19Q84jC+R5Sl5qxT55Dajpi+RGW6iXOmEaoUDQ1tsGCdp69c4K2rKNl2zb1fl46qmnMGjQILUgmmzplT7nsMMOwyWXXJLZiqKnCgja5pitMxKCtk61WVdXChC02S5MUCDKoG2CvlGOQYHaaxOBBf9MpXnaVNR7ACyCdmFaiRrFUAzgw+eBQTsisd4AT1Mr1MiJT14B3rgzlcjxd6C5rFfe0wt0qkLQ1qk21BSCXr166a2UtXWpQJfbe3Wn1bJly9S8W5lr4fYgaLtVKlrnEbSj5WcYsyFoh9G16MVM0I6ep7oySm3Z9Dkw+35g8E5wtj2cPdq6xPepnvTe9FKc1+3fVDv47PXU1l2IAT+9C80lNQRtnzyKYjEEbXNczQm0vYRN0PaiWvivIWiH38OwZ0DQDruD0YifoB0NHwuRhdzDBLIE1mSYsNfFpNijXQj3/Kszvbhs7Mu5KF6vL7DBJmq+vrSHsAwfZ4+2f+3BTUkEbTcq6TmHoK1HZ+tqIWhbZ7lxCRO0jbPEyoAI2lbablTSBG2j7PAUjMB2TU2NWljN+fRNYOTJaOn9w8BWMfcUZA8XEbT9VrTn8gjaevXuqTaCtjleRCoSgnak7AxlMgTtUNoWuaAJ2pGzNHQJEbRDZ9k6AcvvWU11FXD3UanPNt0biT3P9jTnuxBqELT1qk7Q1qs3Qdscva2JhKBtjdXGJkrQNtYaqwIjaFtlt5HJErSNtCXnoKRHOzbzVuCzOcB+v0Fr/xGh2U6PoJ2z3XldQNDOSz5fL2aPtq9ysrC0AgRttoVCK0DQLrQDrF8UIGizHRRaAYJ2oR3ovn5ZmVzm4csh+2PL3OvuDpmrL1u+yW9bIpFAU1OTOlWGlSeTSaPna/cE2pKP5CXPjZKXaCD58PCuAEHbu3Z+X0nQ9ltRlqcUIGizIRRaAYJ2oR1g/QRttgETFCBom+DCujEIIFdXVQH/vBVoWAHsfQ6aS2pdryaeAe+m1UBVb9W7LbBu4tETaMse4SVL5wNzpwJb7I/kkJFoaGgwMY3QxETQNscqgrY5XkQqEoJ2pOwMZTIE7VDaFrmg2aMdOUtDlxBBW79l8vsjvdWyKnh38FtWVoby1YuA6RenAtzpeLSMOML1Amey1W7R7HuB9/+u9ul2DrzM0/ZvPanTvrc5n5XvewJtNST+qd8AyxcCJRXAz6agrq5Ov2kRqpGgbY6ZBG1zvIhUJATtSNkZymQI2qG0LXJBE7QjZ2noEiJo67VMnn+klza29GOgti8S5b26XLRMzqsqLwOevQyoXw4cdDni1Ru53m9bAerTlwBLPgIqaoETH/ANUOX3U+KTlwHFSz4EZt+nFmBztjnUE8z3BNrqhcEHfwfeuhfY+mA4o07zVIdel82ujaBtjj8EbXO8iFQkBO1I2RnKZAjaobQtckGHDbTl3i1DUuX709bWpv7CdKTnvEr80pMow2ltPwjaeluAzLku+3Qm8PpfgJJyYPy9aGyDmn/c+RCQlb/09y0979pNxDKvubTua2DBa8CQnZHos6kvq5Bn9u2uW4Li6t5wPnkDyZkTUyGd8VTOMC/fSYHp7vb+zryYiMUy+8WH7b7jxi+d5xC0dardc10EbXO8iFQkBO1I2RnKZAjaobQtckGHCbTlOyMPxLH5LwANK4EdjkZTS3hgOzPn9cXrgO++Afa7EPGqfq57CCPX+NYmRNDW66wC7Q+eAf71UKriCZPR6JR2Cdr5RiaQLu1ehnW3tLT4siCaiv/zWcCrt6CoshaxI25E4vnrgP5b5dzbLJBdUZREyfx/INF7CBIDt+92/rXkIoe8IJN8eHhXgKDtXTu/ryRo+60oy1MKELTZEAqtAEG70A6wflEgTKCt5ozWfw1M/XXKvF0moGWrQ13PGS204yr+hm+BJ85LhbLTcWgZcWRo4g9KP4J2UMp2Xa6MCKmsKE/Nne49GMkBI0K1uJcC7fenAe9MST3PnXQ/khW91ErgMkIkl95mtdDZvx9ByQfPqBcNzilT0NSaTP13O5hWw8cblgPxBjgbDlE981x53Hu7JWh7187vKwnafivK8gjabANGKEDQNsIG64MIE2grQIi1AY+eCcTrU3NG+22ltUc4PZRWGo480Ocy9Js92l1/3Qja+m9D8l0S2EkvhhamHlp1HygrAd6bDqw/EMlNdlXg6yUHNbx9wUsomX0vEr03QdHRf0aiuR4orVIvwKQXXvV6t64B/vZLwEkC+1+E+IAdtd539LeQYGskaAerby6lE7RzUYvnulaAPdqupeKJASlA0A5IWBabkwJhAm1JTPVAIQkkW5EsqfT8gJ2TSGtPVg/4pUXA89cCLQ3Ajy9Bc3F1TlsWcY72usoTtL20RruvSb8oEBVkKLfX3uX0/OvShqVwavrAeX8GkrPuBfptChx+g5rvrUaiyFzzJ9eOpBn9c8SH7UPQzqMJErTzEM/nSwnaPgvK4lIKELTZEgqtAEG70A6wflEgbKAtMUvPsHx/ulq8KUhX1QP3N3OBF65LVbPriYhvcTAfuPMUnaCdp4C8PC8F5F4iq45Lj7jz0p+AT18HYkXAaU+gvqFBLb4oPd/4bDbQtBrOlgdAFoXTff/JK0nDLiZom2MIQdscLyIVCUE7UnaGMhmCdihti1zQYQTtQpngR492oWI3uV6Ctsnu2BGbgLb0jJc0LAXm/QMYMALO4B+p5GN1S4GKGsTKa9RUEQFsQnZ+7YKgnZ9+fl5N0PZTTZaVUYCgzcZQaAUI2oV2gPWLAgTt3NpBPnO0c6vJnrMJ2vZ4bWqm6X20ZbRMepV0+Y0uXTwHePlPQGkl8NO70JgoImT7YCJB2wcRfSqCoO2TkCymowIEbbaIQitA0C60A6yfoM02YIICBG0TXLA7hjRot1+xXK1uPu9Z4O0HU+IcfweaStfLaVVzu1XtPnuCtjktg6BtjheRioSgHSk7Q5kMQTuUtkUuaPZoR87S0CVE0A6dZa4Dlt85ObysCO66Eh9O7Aq01VSR8lLgvaeB2n5whu6utkEzPRcf5Ai8CIJ24BK7roCg7VoqnpiLAgTtXNTiuUEoQNAOQlWWmasCBO1cFeP5fisQFdCWe7r8qUW12u3B7LdeYSlP7RBQXKzCbUsk1AJiph5dgbbE6tfq5qbmXai4CNqFUn7degna5ngRqUgI2pGyM5TJELRDaVvkgiZoR87S0CUUBdBOr0wda1oNVPVWi2bJ4lq2Hmrv6ZbvgKcuSElwxJ/QXNbLWE26A21b/Qs6b4J20Aq7L5+g7V4rnpmDAgTtHMTiqYEoQNAORFYWmqMCBO0cBePpvisQBdCurq5G0ex7gff/DgzaEc6Bl6G+vt53rcJSoNoKb9EbwMyJqZD3OhvxIaON3QqPoK23ZRG09erdU20EbXO8iFQkBO1I2RnKZAjaobQtckETtCNnaegSigJo19TUIPb0JcCSj4CKWuDEB1BXVxc6L/wKWJ6xqmTv6Tn3p4rc9SQ0rt0ay686/CyHoO2nmtnLImhn10jXGQRtXUpbVg9BGmEvnwAAGvhJREFU2zLDDUyXoG2gKRaGRNC20HTDUo4CaFdUVKC07mtgwWvAkJ2R6LMpGhsbDVNabzgynF6GkMshw+jbr+itN5LstRG0s2vk5xkEbT/VzK8sgnZ++vHqbhQgaLNpFFoBgnahHWD9ogBBm+2g0ApEAbRFQxkund6DuaWlJZAF0dovziXgmkgkCm1fJOpPg3Z6ETvqGqytBO1g9c2ldIJ2LmrxXNcKELRdS8UTA1KAoB2QsCw2JwUI2jnJZc3JAo3yJ4dAo/wFdUQFtIPSJ12u2m6qohyY+xRQsR6cLfYLdLspeWmQfnmQTCYRj8cDeXkQtG5uyhfQlhxjbXHZjAzJ4nI1IkHAW36rZU9t0UPOke+C/MvDuwIEbe/a+X0lQdtvRVmeUoCgzYZQaAUI2oV2gPWLAgRttoPOCiigK3aAF29IfbT/RWhKxAIb+kvQdtcGBfbKPnoeeOve1AXjrkN8/SGBvQRRC7x98Q7w8avAiMPQ1mdTo7focqdi12f16tULznffwHnsV0CyDTjiRsRrBypt1bSAlQuB96YDw0YjOWSkesHBw7sCBG3v2vl9JUHbb0VZHkGbbcAIBQjaRthgfRAEbeubwDoCqBWjF84EXv9r6rM9fon40L0CAzqCtrs2qHxZNh+YcSVQUg4c/xc0F1UFtmVWbW0tcN9PgNZmoM8wOEfcGNmV1BVofzYbzvN/SJmx55mI/3BP1ebVQnfPXgZ8Mw8oKgFOe9zqhe7ctdaezyJo+6GiP2UQtP3RkaV0UoA92mwShVYgTKAtQ+akN0VilrlrMoSQRzQUIGhHw0c/s1B7IKMFmPG7VLEHX4FmlAUGdARtd+7J/beqqgpF8TqguBSJtcOb3V2d+1kKMN/4K/Dhi8AuE5Dc9vCcenLbz1mXxdBMHm6tQNtx4Lw7DUi0AtsfhcamJvV7J5oXz5uRGkmw6V5w9j43si8ccm8l3q4gaHvTLYirCNpBqMoyOXScbaDgCoQJtNUD10cvA0vmA9sfiXjFhoH1bhXcGMsCIGhbZrjLdOXFWvsVo4N8uUbQdmnK2tMEUuRov2CX/J6IX/KvAK2Abb6HTCGQYdOxGOA4UMPG3S4SpnrfW+uAec8B/bdE8gc75gTpXmOX/OVIL2rmthyZoy1tPH29LDSXXiVd9K6srISU7ABobm4ObBqF23jDfh5B2xwHCdrmeBGpSNijHSk7Q5lMWEBberOrK8qAe45N6bzVgUjsdpr1W9eEstF1ETRBOypOhjcPgnb+3qle1+ULgK/+B2x9EJqdEl9gWyKT36pcwVXF8+adwPwXpQDg1CdQv3ZxsfyzXbcEiVFguFhQuKgIbYlkTvPJ3Wzv5UWHIHKNQpkEbXNcJGib40WkIiFoR8rOUCYTFtCWOKVHG9MuApYuAMZcgNbBu6q3+jzCrwBBO/wehj0DgnZ+Dqp7dHUVcO9xQKKtx5eh8uwjvdTyAlV6bOU+nitEu4lWoLdk/j+AWfcAvQcDx9yihlsHUZfEo3rQv/scePpSoLwaOOZWNDmlrnue3YC2m7x5jjsFCNrudNJxFkFbh8oW1kHQttB0w1IOC2hnHmLKy4FkErKpiQwhNHm+nWFWGx0OQdtoe6wIjqCdn82pl6HVwCM/B+qXATsdj7btjuqyR1dNA/rXQ8Cit9WCX60bDg/kpWlmuHXzGqCiFi2tbYGu7aFWZP/w78CcB1Jijr0a8Q2Gu57iRNDOrw3mejVBO1fFgjufoB2ctlaXTNC22n4jkg8TaItgXue+GSE2g+hWAYI2G0ehFSBo5++A2oIKbcDqr+D0GdblfGoF5FVVwKSjUhVuuhcSe54T2DQgqU96zqUX28uL2fScc+l5z3a92pKutAh45xGgvBaOLGbW2Jj1urTyBO3822AuJRC0c1Er2HMJ2sHqa23pBG1rrTcm8bCBtjHCMRBfFSBo+yonC/OgAEHbg2hdXCKwmR4S3h2YplYSvwP4bA4w5ny09tsqkB7tfDNSc7wbVwBrvoUzYISrhdgEzEUDOWRbLrcLt8n5BO18HcvteoJ2bnoFeTZBO0h1LS6boG2x+YakTtA2xAjLwyBoW94ADEifoK3PhO9XEk9t1SjTgIKaN+01K3k+qypxgAdPSW21NfrnaBm+b6BDzwnaXt3ydh1B25tuQVxF0A5CVZbJ7b3YBgquAEG74BYwAAAEbTaDQitA0C60A2bVr0C7qA144KRUYLueiJYtDyFom2VTXtEQtPOSz9eLCdq+ysnC0gqwR5ttodAKELQL7QDrFwUI2mwHhVaAoF1oB8yrv7q6GkVL5gOrPge2PBBNAe9dzR5tvW2AoK1X755qI2ib40WkIiFoR8rOUCZD0A6lbZELmqAdOUtDlxBBO3SWBR6w/D7KnGs5ZIh7LvOtvQRH0PaimvdrCNretfP7SoK234qyPKUAQZsNodAKELQL7QDrFwUI2mwHhVaAoF1oB1g/QVtvGyBo69W7p9oI2uZ4EalICNqRsjOUyRC0Q2lb5IImaEfO0tAlRNAOnWWRC5igrddSgrZevQna5uhtTSQEbWusNjZRgrax1lgVGEHbKruNTJagbaQtVgVF0NZrN0Fbr94EbXP0tiYSgrY1VhubKEHbWGusCoygbZXdRiZL0DbSFquCImjrtZugrVdv30A7mUyiqKgop+hXrlyZ0/k8ORoKELSj4WOYsyBoh9m96MRO0I6Ol2HNhKAdVueiEzdBW6+XBG29ersG7bfffht33XUXJk2a1OGaBQsW4LrrrsO7776L3r1749RTT8Xxxx/vKguCtiuZIncSQTtyloYuIYJ26CyLZMAE7UjaGqqkCNqhsiuSwRK09dpK0Nard1bQ/vbbb3Httddi1qxZ6NevH2bMmNHhmvHjx2P48OE46aSTsHjxYlxwwQW4+eabMXr06KyZELSzShTJEwjakbQ1VEkRtENlV2SDJWhH1trQJEbQDo1VkQ2UoK3XWoK2Xr2zgnZTUxPmz5+POXPm4Omnn+4A2tKLLT3Y//jHP9CnTx9V1jXXXIO6ujrVy53tIGhnUyianxO0o+lrmLIiaIfJrejGStCOrrdhyYygHRanohsnQVuvtwRtvXpnBe30Cc8//zxuueWWDqD9+uuv4/zzz8cbb7yBiooKdeojjzyigPxvf/tbpuxFixZ1qEcecjfZZBN899135mTLSLQpIHP5q6ur1QsZHlSgEArIPai2thZr1qwpRPWskwooBXr16sXfQbaFgiog98GGhgbIOjs8qEAhFKipqYF06iUSiUJUb12d8gwu33sehVegwz7aXYH2qlWrMG7cOIwcORLHHHOMemidMmWKenB4/PHHVQbyxTn22GM7ZCNvUx577DF+qQrvcUEiEMiRP/6wF0R+VrpWAbkP8YedzcGLAo7jqHtYvgfbYL4K8vp8FWAbzFdBXp+vAgJ+ck+VPx7BKyDP3qWlpcFXxBqyKpAVtKWEjz/+WC2QJvOzBw4ciM8++0z1Vt90001ZK+DQ8awSRfIEDh2PpK2hSopDx0NlV2SD5dDxyFobmsQ4dDw0VkU2UA4d12sth47r1bun2lyBdvsCZOjHAQccgDPOOAOySFq2g6CdTaFofk7QjqavYcqKoB0mt6IbK0E7ut6GJTOCdlicim6cBG293hK09eqdFbRlKEdbWxtefPFFTJw4EdOnT1dD5kpKStS1q1evRmVlJebOnauGg7/33nvqnKqqqqyZELSzShTJEwjakbQ1VEkRtM2wS3yQ+4H8ztg4jJ+gbUY7tDkKgrbN7puRO0Fbrw8Ebb16ZwXthQsXrjPH+tBDD8WVV16prhX4njx5svrvUaNG4bLLLlPbgLk5CNpuVIreOQTt6HkatowI2oV3TOblyQvZWN1SoLwaiZJKNDY2Fj4wjREQtDWKzaq6VICgzYZRaAUI2nodIGjr1TsraGcLR4aLr1ixAv3798/0cme7Jv05QdutUtE6j6AdLT/DmA1BuzCuie7pBW/Ky8tR9sXbwMt/AkorgZ/ehcZEkVU92wTtwrRD1vq9AgRttoZCK0DQ1usAQVuv3nmDdj7hErTzUS+81xK0w+tdVCInaPvrpEwlklVMRdfW1lb11/6Q77xMMYrJyrKxGJqbm9WQ8bJ5zwJvP5g69fg70FS6npqqZMtB0LbFaXPzJGib640tkRG09TpN0NarN0HbHL2tiYSgbY3VxiZK0PbPmswQ8H9PAeL1wC4T0NSGDsBcXV2NonceBuY+CWz5Yzijf6Fgu7K8FHjvaaC2H5yhu6v9fG3a4oWg7V87ZEneFCBoe9ONV/mnAEHbPy3dlETQdqOSnnM6rDoeRJXs0Q5CVfPLJGib71HUIyRo++dwWVkZylcsAJ79barQXSagZatDEY/HM5XU1tYCj50DrP4SqOgFnDgZdXV1arqR3A/kkF5w2d/TpoOgbZPbZuZK0DbTF5uiImjrdZugrVfvnmojaJvjRaQiIWhHys5QJkPQ9s82geXKogTwxHlAcx1w2DWIrzcILS0tmUpk2HjJ8gXAh88Dm+2DRP9trFv4rCvFCdr+tUOW5E0BgrY33XiVfwoQtP3T0k1JBG03Kuk5h6CtR2fraiFoW2e5cQkTtP21pKKiAqVqy0cHiaQDWSSz/RBw0VsWP5Nh5tJrLb3dNg0R705tgra/7ZCl5a4AQTt3zXiFvwoQtP3VM1tpBO1sCun7nKCtT2uraiJoW2W3kckStPOzRYBZNGy/97X8bzkI0O61JWi714pnBqMAQTsYXVmqewUI2u618uNMgrYfKvpTBkHbHx1ZSicFCNpsEoVWgKDt3QHVe11cBLQ0wCmvVUPAbZtb7V29jlcStP1SkuV4VYCg7VU5XueXAgRtv5R0Vw5B251OOs4iaOtQ2cI6CNoWmm5YygRtd4ZktuWKxTJDvisryoG/nQnULQH2PgctQ0arwmR7LzlkUbP2C6G5q8nOswjadvpuUtYEbZPcsDMWgrZe3wnaevXuqTaCtjleRCoSgnak7AxlMgTtjrbJ/On0PtgyHFx6qGU/a+m9js15AJj3HLDHmXCG74FYWxy47yepArYdB2fXkxBr/g54/g9AcSlw4KXrbO8VykaiIWiCtgaRWUWPChC02UAKrQBBW68DBG29ehO0zdHbmkgI2tZYbWyiBO3vrZHtuSpkHbOZE1Esc69HnwGntRlOTT8F3M7dRwHJBLDRlnAOu0bNwS5a9Baw/DNgxFgky2tRNG8GMOueVKH7nIf44JEdVh03tiEUODCCdoENYPUgaLMRFFoBgrZeBwjaevUmaJujtzWRELStsdrYRAnaKWukx7q8OIbY1+8hBgex1/8C9NscTt0yOKNOhdN/KyTfnwF8+AKw60lo67+1GhbevvdbleM0s0fbQ2snaHsQjZf4qgBB21c5WZgHBQjaHkTL4xKCdh7i+Xwph477LCiLSylA0GZLKLQCBG2oVcNramoQe/RMFK1ejNiQXREbuA1QUgnnzbvhHPD/0DpgB2VVeoXx5ubmLlcVTw89l3M5R9t96yZou9eKZwajAEE7GF1ZqnsFCNrutfLjTIK2Hyr6UwZB2x8dWUonBQjabBKFVoCgvRa0q6uAe45FEZIo2vogxPY8E86yT+Es+QjY6kDU1dV12MKr0L5FrX6CdtQcDV8+BO3weRa1iAnaeh0laOvVu6faCNrmeBGpSAjakbIzlMkQtFO2VVdXo+jbD4Bv5gFbH4S2kqpMj7X0TLffJzuURhseNEHbcIMsCI+gbYHJhqdI0NZrEEFbr94EbXP0tiYSgrY1VhubKEE7ZY3oIIuhySELnwlc89CnAEFbn9asqWsFCNpsGYVWgKCt1wGCtl69Cdrm6G1NJARta6w2NlGCtrHWWBUYQdsqu41MlqBtpC1WBUXQ1ms3QVuv3gRtc/S2JhKCtjVWG5soQdtYa6wKjKBtld1GJkvQNtIWq4IiaOu1m6CtV2+Ctjl6WxMJQdsaq41NlKBtrDVWBUbQtspuI5MlaBtpi1VBEbT12k3Q1qs3Qdscva2JhKBtjdXGJkrQNtYaqwIjaFtlt5HJErSNtMWqoAjaeu0maOvVm6Btjt7WRELQtsZqYxMlaBtrjVWBEbStstvIZAnaRtpiVVAEbb12E7T16k3QNkdvayIhaFtjtbGJErSNtcaqwAjaVtltZLIEbSNtsSoogrZeuwnaevUmaJujtzWRELStsdrYRAnaxlpjVWAEbavsNjJZgraRtlgVFEFbr90Ebb16E7TN0duaSAja1lhtbKIEbWOtsSowgrZVdhuZLEHbSFusCoqgrddugrZevQna5uhtTSQEbWusNjZRgrax1lgVGEHbKruNTJagbaQtVgVF0NZrN0Fbr94EbXP0tiYSgrY1VhubKEHbWGusCoygbZXdRiZL0DbSFquCImjrtZugrVdvgrY5elsTCUHbGquNTZSgbaw1VgVG0LbKbiOTJWgbaYtVQRG09dpN0NarN0HbHL2tiYSgbY3VxiZK0DbWGqsCI2hbZbeRyRK0jbTFqqAI2nrtJmjr1ZugbY7e1kRC0LbGamMTJWgba41VgRG0rbLbyGQJ2kbaYlVQBG29dhO09epN0DZHb2siIWhbY7WxiRK0jbXGqsAI2lbZbWSyBG0jbbEqKIK2XrsJ2nr1Jmibo7c1kRC0rbHa2EQJ2sZaY1VgBG2r7DYyWYK2kbZYFRRBW6/dBG29ehO0zdHbmkgI2tZYbWyiBG1jrbEqMIK2VXYbmSxB20hbrAqKoK3XboK2Xr0J2ubobU0kBG1rrDY2UYK2sdZYFRhB2yq7jUyWoG2kLVYFRdDWazdBW6/eBG1z9LYmEoK2NVYbmyhB21hrrAqMoG2V3UYmS9A20hargiJo67WboK1Xb4K2OXpbEwlB2xqrjU2UoG2sNVYFRtC2ym4jkyVoG2mLVUERtPXaTdDWqzdB2xy9rYmEoG2N1cYmStA21hqrAiNoW2W3kckStI20xaqgCNp67SZo69W7oKBtTqqMhApQASpABagAFaACVIAKUAEqQAWoQPAKxBzHcYKvhjXYpsDHH3+MK664AlOmTLEtdeZriAKrV6/GUUcdhZdfftmQiBiGjQqMGjUKr776KsrLy21MnzkboMDYsWNx5513YsCAAQZEwxBsVOC0007DWWedhR122MHG9JmzxQoQtC02P8jUCdpBqsuy3ShA0HajEs8JWgGCdtAKs/xsChC0synEz4NWgKAdtMIs31QFCNqmOhPyuAjaITcwAuETtCNgYgRSIGhHwMSQp0DQDrmBEQifoB0BE5mCJwUI2p5k40XZFCBoZ1OInwetAEE7aIVZvhsFCNpuVOI5QSpA0A5SXZbtRgGCthuVeE4UFSBoR9FVA3IiaBtgguUhELQtbwCGpE/QNsQIi8MgaFtsviGpE7QNMYJhaFeAoK1dclZIBagAFaACVIAKUAEqQAWoABWgAlFWgKAdZXeZGxWgAlSAClABKkAFqAAVoAJUgApoV4CgrV1yVkgFqAAVoAJUgApQASpABagAFaACUVaAoB1ld5kbFaACVIAKUAEqQAWoABWgAlSACmhXgKCtXXJ7K3QcB/JXVFRkrwjMnApQAasUSCaTvOdZ5TiTpQJUoLMCiUQCxcXFFIYKWKcAQds6y/Un/P777+OPf/wj5N+qqiocdNBBGD9+PAYNGqQ/GNZotQLfffcdTjzxREyaNAl9+/a1WgsmH6wC8+fPx9VXXw35d/DgwbjoooswcuTIYCtl6VSgkwLyoueCCy7AuHHjsPfee1MfKqBVgRtvvBEvvPACVq1ahe222w6HHHIIjjzySK0xsDIqUEgFCNqFVN+Sul999VUsWLAAe+65J5qbm3HzzTerB8+rrrrKEgWYpgkKXH755XjrrbfUD/6zzz6L/v37mxAWY4igAm1tbeqF4oEHHojjjjsOr7zyCm699Vb1wLnBBhtEMGOmZKICDz30EJ588kksXrxYvfSR9siDCuhU4LLLLsP++++vOlZmz56NP//5z3jiiScwZMgQnWGwLipQMAUI2gWT3t6KBXKuvPJKddMtKSmxVwhmrlWBd999F8uWLcPFF19M0NaqvH2VzZkzB2eddRbeeOMNVFRUKAHkYfPMM8/EEUccYZ8gzLggCixcuBAyikdGU0ivNkG7IDaw0nYKyH1QRjSedNJJ1IUKWKEAQdsKm81K8rrrrsPbb7+t3rTzoAI6FViyZIkausYebZ2q21fXtGnT8MADD3S4x5133nkYPnw4zj77bPsEYcYFVUCGjf/yl78kaBfUBVae/v29/vrrMWbMGApCBaxQgKBthc3BJCm9g2+++Wa3hcvb83RvTvqk119/Heeffz5k3s4+++wTTGAs1RoFZP7hM888oxbZ6+rYeeedMXDgwMxHBG1rmkZBE508eTJeeuklyNDd9CEjKXr16oVLLrmkoLGxcvsUIGjb57lpGcu0QXnJKP/K/ZGjGU1ziPEEpQBBOyhlLSh30aJFqtemu0OGqlVXV2c+/u9//4vTTz8d5557LiZMmGCBQkwxaAVkLuy1117bbTXHHHMMttxyS4J20Eaw/A4KTJ06FQ8//HCHHm15wTh06FCcc845VIsKaFWAoK1VblbWSYHW1lZceuml+Oijj7gQKVuHdQoQtK2zvDAJz5w5U80Rk16do48+ujBBsFbrFWCPtvVNQIsAr732Gn796193WIdCVto99thjcfzxx2uJgZVQgbQCBG22hUIpUF9fr577li9fjokTJ6JPnz6FCoX1UoGCKEDQLojsdlU6Y8YMyIrP0qOz7777ZpJff/31UVlZaZcYzLZgCshbdQHtww8/HE899RQ23nhjDl8rmBvRrrixsVHtsvCb3/xGvViURdHkv6dPn95hKkO0VWB2hVZARvzItBppgzKa7IADDkBpaWmhw2L9lijQ1NSEU045BS0tLZB52TU1NSpz2U+7X79+lqjANG1XgKBtewvQkP8f/vAHyFDKzscVV1yBsWPHaoiAVVABKPARAEofvXv3xosvvkhpqEAgCqRH8aQL52ieQGRmoT0oIG1O1gpof8hLRtlqiQcVCFqBpUuX4uCDD16nGv72Bq08yzdJAYK2SW4wFipABagAFYiMAtKjKA+bffv2ZU9iZFxlIlSAClABKkAF3ClA0HanE8+iAlSAClABKkAFqAAVoAJUgApQASrgSgGCtiuZeBIVoAJUgApQASpABagAFaACVIAKUAF3Cvx/+U3bdCqkT6AAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "", "version_major": 2, "version_minor": 0 }, "text/plain": [ "FigureWidget({\n", " 'data': [{'customdata': array(['63ec8290d3964b0824a4f481', '63ec8290d3964b0824a4f485',\n", " …" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stderr", "output_type": "stream", "text": [ "Executing took 0.136 seconds\n" ] } ], "source": [ "plot = patches_results.visualize(labels=\"ground_truth.label\", sizes=areas)" ] }, { "cell_type": "markdown", "metadata": { "id": "cQi6ict_JyLT" }, "source": [ "**Note:** These plots are currently only interactive in Jupyter notebooks. A future release will provide interactive plots in all environments." ] }, { "cell_type": "code", "execution_count": 69, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "
\n", "
\n", " \n", "
\n", " \n", "
\n", "\n", "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "session = fo.launch_app(view=cattle_view)" ] }, { "cell_type": "code", "execution_count": 70, "metadata": {}, "outputs": [], "source": [ "# If you are in a Jupyter notebook, attach plot to session\n", "session.plots.attach(plot)\n", "plot.connect()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "If you're working in a Jupyter notebook, click the lasso tool on the plot and then select a cluster of points so you can visualize them in the App. Once you have identified a set of samples that you [want to tag](https://voxel51.com/docs/fiftyone/user_guide/app.html#tags-and-tagging), select them and then click the tag icon in the App and assign an appropriate tag.\n", "\n", "From here, you could, for example, [export the tagged subset](https://voxel51.com/docs/fiftyone/user_guide/export_datasets.html) and send to human annotators for verification and relabeling." ] }, { "cell_type": "code", "execution_count": 71, "metadata": {}, "outputs": [], "source": [ "session.freeze()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Summary\n", "\n", "In this tutorial, we saw how to download, explore, and evaluate using Open Images. In particular, we covered:\n", "\n", "* Downloading the [Open Images dataset](https://storage.googleapis.com/openimages/web/index.html) from the [FiftyOne Dataset Zoo](https://voxel51.com/docs/fiftyone/user_guide/dataset_zoo/index.html)\n", "* Computing predictions with a model from the [FiftyOne Model Zoo](https://voxel51.com/docs/fiftyone/user_guide/model_zoo/index.html)\n", "* Using FiftyOne's native support for [Open Images evaluation](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html#open-images-style-evaluation) to evaluate a model and compute its mAP\n", "* Exploring the dataset and [evaluation results](https://voxel51.com/docs/fiftyone/user_guide/evaluation.html)\n", "* [Visualizing embeddings](https://voxel51.com/docs/fiftyone/user_guide/brain.html#visualizing-embeddings) through [interactive plots](https://voxel51.com/docs/fiftyone/user_guide/plots.html)\n", "\n", "**So, what's the takeaway?**\n", "\n", "Open Images is a massive and thoroughly labeled dataset that would make a useful addition to your data lake and model training workflows. And, the easiest way to download and explore Open Images is using FiftyOne!\n", "\n", "With huge and diverse datasets like Open Images, hands-on evaluation of your model results can be difficult. FiftyOne makes it easy to understand your dataset, find failure modes in your model, and reveal hidden patterns in your data using techniques like embedding visualization." ] } ], "metadata": { "accelerator": "CPU", "colab": { "collapsed_sections": [], "name": "fiftyone_open_images.ipynb", "provenance": [] }, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.14" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "state": { "02a70fd9efa1492193a91c04c1c11102": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_5dac46c8932f4be0843a984637d10124", "style": "IPY_MODEL_9608b4bb06fa454b9fe36d99b528c5ef", "value": " 500/500 [00:00]" } }, "0e0a46f4790a4e66bce3a4168228dc16": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "10c375a899fa45389372ab446b602ff6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_6608f0de80bc4e5a9128fa129333dfd1", "style": "IPY_MODEL_61cfefeb1903403083492cb764129056", "value": " 500/500 [00:01]" } }, "168c110060db41b5b2cc154a198dfd8b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "description_width": "" } }, "17209076e45646c68f617cabb6f50114": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "211a55978a2b4f95afc80c0bcb67a1c8": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "22dc1b4b57904486b75f1fb83ff49a20": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "bar_style": "success", "layout": "IPY_MODEL_211a55978a2b4f95afc80c0bcb67a1c8", "max": 500, "style": "IPY_MODEL_7a2c4fc71cea4e198a615995f3f099a9", "value": 500 } }, "248093c330f24d0c9241d8f8aa0fe68d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "description_width": "" } }, "2ae1c531aa8e4adebcd41bbf6fdf5d5d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "2c98bbfc6c724ba1825ca4b1a3d07495": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "children": [ "IPY_MODEL_493ca490168848a18fa837bdafb9dd59", "IPY_MODEL_7cfd2dd6ff394c2ba6883e19686df2be", "IPY_MODEL_f575aee4210e4cb7b93d01ba158477ab" ], "layout": "IPY_MODEL_17209076e45646c68f617cabb6f50114" } }, "375761aa0a5b4fed99d793114e7af76a": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "493ca490168848a18fa837bdafb9dd59": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_9d0badf8b964433eb21521df8231bad0", "style": "IPY_MODEL_d4fac055073146deb265fb0f8812ead0", "value": "Epochs completed: 100%| " } }, "49dd463084ce4018945ba6d51bcfa9af": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "4bd26fbcec8f41c398ed7d58da752f04": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "4c4059c2e3594d3c9b637f6360611af3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "bar_style": "success", "layout": "IPY_MODEL_4fbbf04366514273a0d90d38d7c10ff9", "max": 500, "style": "IPY_MODEL_e0fedca28a8247809b3cf18c2d9e265f", "value": 500 } }, "4cb6553752844e848b33276521dedc6d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "4fbbf04366514273a0d90d38d7c10ff9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "54c524edf2aa495293153eb803574a9a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "564a2bf1006e4e9382b3dddd82d33f1a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "5b35688f8c0c40d5b8088d96bf778e02": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "bar_style": "success", "layout": "IPY_MODEL_8023aeb5ec394216ad2e120338b9bb40", "max": 500, "style": "IPY_MODEL_248093c330f24d0c9241d8f8aa0fe68d", "value": 500 } }, "5b70ba0b3c4e467ea89756ddae8ede9a": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "5d2ff423c7a94b3e855fadf1e8e6fa2e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "5dac46c8932f4be0843a984637d10124": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "61cfefeb1903403083492cb764129056": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "63b885f3a4a843d09c12177e835051be": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_c08180f9d3204262a9149a52df05ff47", "style": "IPY_MODEL_0e0a46f4790a4e66bce3a4168228dc16", "value": " 500/500 [00:00]" } }, "6608f0de80bc4e5a9128fa129333dfd1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "661ad680e6dd41f2960c1ba1b89531e9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "children": [ "IPY_MODEL_6a550c9a35a6428781673fbe07c19622", "IPY_MODEL_b818176e1dd0479b9c365d04df17153e", "IPY_MODEL_bf46909f40b54dcaa090847fac4f99e2" ], "layout": "IPY_MODEL_c40332db490142519e1d4547769c1aa4" } }, "6a550c9a35a6428781673fbe07c19622": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_932e28227ba2448cae43cba10a45a779", "style": "IPY_MODEL_54c524edf2aa495293153eb803574a9a", "value": "Epochs completed: 100%| " } }, "6df2d9e2967f451995b71cccbf46c633": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "children": [ "IPY_MODEL_aec04ca49d44453e84bc87b381ab5fe8", "IPY_MODEL_e4e3ab6c7a904fa8bd85ccf1fbc8f3bb", "IPY_MODEL_b6c69d24d96b4017989a49fabff4361b" ], "layout": "IPY_MODEL_a3b8544640f14eb792472878f8bfb2c5" } }, "774b86f403654d08aa2c3a1ce27bbff4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "79143a7c04a64a7993df2ba72922bc72": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "7a2c4fc71cea4e198a615995f3f099a9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "description_width": "" } }, "7cfd2dd6ff394c2ba6883e19686df2be": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "bar_style": "success", "layout": "IPY_MODEL_fcb7d296d5084718bab6599c4129d052", "max": 500, "style": "IPY_MODEL_81738aa0775b452c9936f7e6dde522d2", "value": 500 } }, "8023aeb5ec394216ad2e120338b9bb40": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "81738aa0775b452c9936f7e6dde522d2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "description_width": "" } }, "840db15938a04a21847f458f01acc1f6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "children": [ "IPY_MODEL_888ed16d2d81430d92208a57d11635c8", "IPY_MODEL_22dc1b4b57904486b75f1fb83ff49a20", "IPY_MODEL_10c375a899fa45389372ab446b602ff6" ], "layout": "IPY_MODEL_5d2ff423c7a94b3e855fadf1e8e6fa2e" } }, "8436141edf9d4e5288bafece8130d096": { "model_module": "jupyterlab-plotly", "model_module_version": "^5.9.0", "model_name": "FigureModel", "state": { "_config": { "plotlyServerURL": "https://plot.ly" }, "_data": [ { "mode": "markers", "opacity": 0.1, "type": "scatter", "uid": "456eb7e1-3d1c-417c-957e-5556334c9119", "x": [ 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5 ], "y": [ 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5 ] }, { "colorscale": [ [ 0, "rgb(255,245,235)" ], [ 0.125, "rgb(254,230,206)" ], [ 0.25, "rgb(253,208,162)" ], [ 0.375, "rgb(253,174,107)" ], [ 0.5, "rgb(253,141,60)" ], [ 0.625, "rgb(241,105,19)" ], [ 0.75, "rgb(217,72,1)" ], [ 0.875, "rgb(166,54,3)" ], [ 1, "rgb(127,39,4)" ] ], "hoverinfo": "skip", "showscale": false, "type": "heatmap", "uid": "40a81f17-8cf2-4b60-8660-c43622914755", "z": [ [ 20, 20, 13, 7, 20, 0 ], [ 0, 0, 0, 0, 460, 123 ], [ 0, 0, 0, 220, 0, 81 ], [ 0, 0, 240, 0, 0, 42 ], [ 0, 460, 0, 0, 0, 123 ], [ 460, 0, 0, 0, 0, 123 ] ], "zmax": 460, "zmin": 0 }, { "colorbar": { "len": 1, "lenmode": "fraction" }, "colorscale": [ [ 0, "rgb(255,245,235)" ], [ 0.125, "rgb(254,230,206)" ], [ 0.25, "rgb(253,208,162)" ], [ 0.375, "rgb(253,174,107)" ], [ 0.5, "rgb(253,141,60)" ], [ 0.625, "rgb(241,105,19)" ], [ 0.75, "rgb(217,72,1)" ], [ 0.875, "rgb(166,54,3)" ], [ 1, "rgb(127,39,4)" ] ], "hovertemplate": "count: %{z}
truth: %{y}
predicted: %{x}", "opacity": 0.25, "type": "heatmap", "uid": "da871c17-f0c9-435e-88cf-70fbb64adcee", "z": [ [ 20, 20, 13, 7, 20, 0 ], [ 0, 0, 0, 0, 460, 123 ], [ 0, 0, 0, 220, 0, 81 ], [ 0, 0, 240, 0, 0, 42 ], [ 0, 460, 0, 0, 0, 123 ], [ 460, 0, 0, 0, 0, 123 ] ], "zmax": 460, "zmin": 0 } ], "_js2py_layoutDelta": { "layout_delta": { "activeshape": { "fillcolor": "rgb(255,0,255)", "opacity": 0.5 }, "annotations": [], "autotypenumbers": "strict", "calendar": "gregorian", "colorscale": { "diverging": [ [ 0, "rgb(5,10,172)" ], [ 0.35, "rgb(106,137,247)" ], [ 0.5, "rgb(190,190,190)" ], [ 0.6, "rgb(220,170,132)" ], [ 0.7, "rgb(230,145,90)" ], [ 1, "rgb(178,10,28)" ] ], "sequential": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "sequentialminus": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ] }, "colorway": [ "#F8766D", "#A3A500", "#00BF7D", "#00B0F6", "#E76BF3" ], "dragmode": "zoom", "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "height": 470.127, "hidesources": false, "hoverdistance": 20, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "grouptitlefont": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hovermode": "closest", "images": [], "margin": { "autoexpand": true, "pad": 0 }, "modebar": { "activecolor": "rgba(68, 68, 68, 0.7)", "add": "", "bgcolor": "rgba(255, 255, 255, 0.5)", "color": "rgba(68, 68, 68, 0.3)", "orientation": "h", "remove": "" }, "newshape": { "drawdirection": "diagonal", "fillcolor": "rgba(0,0,0,0)", "fillrule": "evenodd", "layer": "above", "line": { "color": "#444", "dash": "solid", "width": 4 }, "opacity": 1 }, "paper_bgcolor": "white", "plot_bgcolor": "rgb(237,237,237)", "separators": ".,", "shapes": [], "showlegend": false, "sliders": [], "spikedistance": -1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 17 }, "pad": { "b": 0, "l": 0, "r": 0, "t": 0 }, "text": "Click to enter Plot title", "x": 0.5, "xanchor": "auto", "xref": "container", "y": "auto", "yanchor": "auto", "yref": "container" }, "uniformtext": { "mode": false }, "updatemenus": [], "width": 986.221, "xaxis": { "anchor": "y", "automargin": true, "autorange": false, "autotypenumbers": "strict", "color": "#444", "constraintoward": "center", "domain": [ 0.2646726862302483, 0.7353273137697517 ], "dtick": 0.01, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "mirror": false, "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "bottom", "tick0": 0, "tickangle": "auto", "tickcolor": "rgb(51,51,51)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 5, "tickprefix": "", "ticks": "outside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15, "text": "Click to enter X axis title" }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 1 }, "yaxis": { "anchor": "x", "automargin": true, "autorange": false, "autotypenumbers": "strict", "color": "#444", "constraintoward": "middle", "domain": [ 0, 1 ], "dtick": 0.01, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "mirror": false, "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "left", "tick0": 0, "tickangle": "auto", "tickcolor": "rgb(51,51,51)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 5, "tickprefix": "", "ticks": "outside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15, "text": "Click to enter Y axis title" }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 1 } }, "layout_edit_id": 3 }, "_js2py_restyle": {}, "_js2py_traceDeltas": { "trace_deltas": [ { "cliponaxis": true, "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverinfo": "all", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hoveron": "points", "hovertemplate": "", "hovertext": "", "index": 0, "legendgroup": "", "legendgrouptitle": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "marker": { "color": "#F8766D", "gradient": { "type": "none" }, "line": { "color": "#444", "width": 0 }, "maxdisplayed": 0, "opacity": 1, "size": 6, "symbol": "circle" }, "name": "trace 0", "selected": { "marker": { "opacity": 1 } }, "showlegend": true, "stackgroup": "", "text": "", "uid": "456eb7e1-3d1c-417c-957e-5556334c9119", "unselected": { "marker": { "opacity": 0.2 } }, "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 }, { "autocolorscale": false, "connectgaps": false, "dx": 1, "dy": 1, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hoverongaps": true, "hovertemplate": "", "index": 1, "legendgroup": "", "legendgrouptitle": { "text": "" }, "legendrank": 1000, "name": "trace 1", "opacity": 1, "reversescale": false, "showlegend": false, "textfont": { "color": "auto", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": "auto" }, "texttemplate": "", "transpose": false, "uid": "40a81f17-8cf2-4b60-8660-c43622914755", "visible": true, "x0": 0, "xaxis": "x", "xcalendar": "gregorian", "xgap": 0, "xhoverformat": "", "xperiod": 0, "y0": 0, "yaxis": "y", "ycalendar": "gregorian", "ygap": 0, "yhoverformat": "", "yperiod": 0, "zauto": false, "zhoverformat": "", "zsmooth": false }, { "autocolorscale": false, "colorbar": { "bgcolor": "rgba(0,0,0,0)", "bordercolor": "#444", "borderwidth": 0, "exponentformat": "B", "minexponent": 3, "nticks": 0, "orientation": "v", "outlinecolor": "#444", "outlinewidth": 0, "separatethousands": false, "showexponent": "all", "showticklabels": true, "thickness": 30, "thicknessmode": "pixels", "tickangle": "auto", "tickcolor": "rgb(237,237,237)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 6, "tickmode": "auto", "tickprefix": "", "ticks": "inside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "side": "top", "text": "Click to enter Colorscale title" }, "x": 1.02, "xanchor": "left", "xpad": 10, "y": 0.5, "yanchor": "middle", "ypad": 10 }, "connectgaps": false, "dx": 1, "dy": 1, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hoverongaps": true, "index": 2, "legendgroup": "", "legendgrouptitle": { "text": "" }, "legendrank": 1000, "name": "trace 2", "reversescale": false, "showlegend": false, "showscale": true, "textfont": { "color": "auto", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": "auto" }, "texttemplate": "", "transpose": false, "uid": "da871c17-f0c9-435e-88cf-70fbb64adcee", "visible": true, "x0": 0, "xaxis": "x", "xcalendar": "gregorian", "xgap": 0, "xhoverformat": "", "xperiod": 0, "y0": 0, "yaxis": "y", "ycalendar": "gregorian", "ygap": 0, "yhoverformat": "", "yperiod": 0, "zauto": false, "zhoverformat": "", "zsmooth": false } ], "trace_edit_id": 2 }, "_js2py_update": {}, "_last_layout_edit_id": 3, "_last_trace_edit_id": 2, "_layout": { "autosize": true, "clickmode": "event", "margin": { "b": 0, "l": 0, "r": 0, "t": 30 }, "template": { "data": { "bar": [ { "error_x": { "color": "rgb(51,51,51)" }, "error_y": { "color": "rgb(51,51,51)" }, "marker": { "line": { "color": "rgb(237,237,237)", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "rgb(237,237,237)", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "rgb(51,51,51)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(51,51,51)" }, "baxis": { "endlinecolor": "rgb(51,51,51)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(51,51,51)" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "fillpattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "rgb(237,237,237)" }, "line": { "color": "white" } }, "header": { "fill": { "color": "rgb(217,217,217)" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowhead": 0, "arrowwidth": 1 }, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "colorscale": { "sequential": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "sequentialminus": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ] }, "colorway": [ "#F8766D", "#A3A500", "#00BF7D", "#00B0F6", "#E76BF3" ], "font": { "color": "rgb(51,51,51)" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "rgb(237,237,237)", "showlakes": true, "showland": true, "subunitcolor": "white" }, "hoverlabel": { "align": "left" }, "hovermode": "closest", "paper_bgcolor": "white", "plot_bgcolor": "rgb(237,237,237)", "polar": { "angularaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "bgcolor": "rgb(237,237,237)", "radialaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" } }, "scene": { "xaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" }, "yaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" }, "zaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" } }, "shapedefaults": { "fillcolor": "black", "line": { "width": 0 }, "opacity": 0.3 }, "ternary": { "aaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "baxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "bgcolor": "rgb(237,237,237)", "caxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" } }, "xaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "title": { "standoff": 15 }, "zerolinecolor": "white" }, "yaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "title": { "standoff": 15 }, "zerolinecolor": "white" } } }, "xaxis": { "constrain": "domain", "range": [ -0.5, 5.5 ], "tickmode": "array", "ticktext": [ "Animal", "Carnivore", "Cat", "Dog", "Mammal", "(none)" ], "tickvals": [ 0, 1, 2, 3, 4, 5 ] }, "yaxis": { "constrain": "domain", "range": [ -0.5, 5.5 ], "scaleanchor": "x", "scaleratio": 1, "tickmode": "array", "ticktext": [ "(none)", "Mammal", "Dog", "Cat", "Carnivore", "Animal" ], "tickvals": [ 0, 1, 2, 3, 4, 5 ] } }, "_py2js_addTraces": {}, "_py2js_animate": {}, "_py2js_deleteTraces": {}, "_py2js_moveTraces": {}, "_py2js_removeTraceProps": {}, "_py2js_restyle": {}, "_view_count": 2 } }, "888ed16d2d81430d92208a57d11635c8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_f5ffbea1cd054092aada8eb9f61fe325", "style": "IPY_MODEL_564a2bf1006e4e9382b3dddd82d33f1a", "value": "Epochs completed: 100%| " } }, "932e28227ba2448cae43cba10a45a779": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "9390307ed5374e06b33c2afbfe157950": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "9608b4bb06fa454b9fe36d99b528c5ef": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "9612db9099db44bab8f6ac7701fa21d8": { "model_module": "jupyterlab-plotly", "model_module_version": "^5.9.0", "model_name": "FigureModel", "state": { "_config": { "plotlyServerURL": "https://plot.ly" }, "_data": [ { "mode": "markers", "opacity": 0.1, "selectedpoints": [], "type": "scatter", "uid": "9bd6c7c6-fec8-47c5-92c0-176e0349ae96", "x": [ 0, 1, 2, 0, 1, 2, 0, 1, 2 ], "y": [ 0, 0, 0, 1, 1, 1, 2, 2, 2 ] }, { "colorscale": [ [ 0, "rgb(255,245,235)" ], [ 0.125, "rgb(254,230,206)" ], [ 0.25, "rgb(253,208,162)" ], [ 0.375, "rgb(253,174,107)" ], [ 0.5, "rgb(253,141,60)" ], [ 0.625, "rgb(241,105,19)" ], [ 0.75, "rgb(217,72,1)" ], [ 0.875, "rgb(166,54,3)" ], [ 1, "rgb(127,39,4)" ] ], "hoverinfo": "skip", "showscale": false, "type": "heatmap", "uid": "766b6d60-4a85-4c8d-9ef9-fa696e707542", "z": [ [ null, null, null ], [ null, null, null ], [ 440, null, null ] ], "zmax": 478, "zmin": 0 }, { "colorbar": { "len": 1, "lenmode": "fraction" }, "colorscale": [ [ 0, "rgb(255,245,235)" ], [ 0.125, "rgb(254,230,206)" ], [ 0.25, "rgb(253,208,162)" ], [ 0.375, "rgb(253,174,107)" ], [ 0.5, "rgb(253,141,60)" ], [ 0.625, "rgb(241,105,19)" ], [ 0.75, "rgb(217,72,1)" ], [ 0.875, "rgb(166,54,3)" ], [ 1, "rgb(127,39,4)" ] ], "hovertemplate": "count: %{z}
truth: %{y}
predicted: %{x}", "opacity": 0.25, "type": "heatmap", "uid": "80ff38bd-97d8-448d-afd0-8a6c520f0ff8", "z": [ [ 7, 20, 0 ], [ 10, 478, 38 ], [ 440, 8, 77 ] ], "zmax": 478, "zmin": 0 } ], "_js2py_layoutDelta": { "layout_delta": { "activeshape": { "fillcolor": "rgb(255,0,255)", "opacity": 0.5 }, "annotations": [], "autotypenumbers": "strict", "calendar": "gregorian", "colorscale": { "diverging": [ [ 0, "#8e0152" ], [ 0.1, "#c51b7d" ], [ 0.2, "#de77ae" ], [ 0.3, "#f1b6da" ], [ 0.4, "#fde0ef" ], [ 0.5, "#f7f7f7" ], [ 0.6, "#e6f5d0" ], [ 0.7, "#b8e186" ], [ 0.8, "#7fbc41" ], [ 0.9, "#4d9221" ], [ 1, "#276419" ] ], "sequential": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "sequentialminus": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ] }, "colorway": [ "#636efa", "#EF553B", "#00cc96", "#ab63fa", "#FFA15A", "#19d3f3", "#FF6692", "#B6E880", "#FF97FF", "#FECB52" ], "dragmode": "zoom", "font": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "height": 470.127, "hidesources": false, "hoverdistance": 20, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "grouptitlefont": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hovermode": "closest", "images": [], "margin": { "autoexpand": true, "b": 80, "l": 80, "pad": 0, "r": 80, "t": 100 }, "modebar": { "activecolor": "rgba(68, 68, 68, 0.7)", "add": "", "bgcolor": "rgba(255, 255, 255, 0.5)", "color": "rgba(68, 68, 68, 0.3)", "orientation": "h", "remove": "" }, "newshape": { "drawdirection": "diagonal", "fillcolor": "rgba(0,0,0,0)", "fillrule": "evenodd", "layer": "above", "line": { "color": "#444", "dash": "solid", "width": 4 }, "opacity": 1 }, "paper_bgcolor": "white", "plot_bgcolor": "#E5ECF6", "separators": ".,", "shapes": [], "showlegend": false, "sliders": [], "spikedistance": -1, "title": { "font": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 17 }, "pad": { "b": 0, "l": 0, "r": 0, "t": 0 }, "text": "Click to enter Plot title", "x": 0.05, "xanchor": "auto", "xref": "container", "y": "auto", "yanchor": "auto", "yref": "container" }, "uniformtext": { "mode": false }, "updatemenus": [], "width": 986.221, "xaxis": { "anchor": "y", "automargin": true, "autorange": false, "autotypenumbers": "strict", "color": "#444", "constraintoward": "center", "domain": [ 0.3198757763975155, 0.6801242236024845 ], "dtick": 0.01, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "bottom", "tick0": 0, "tickangle": "auto", "tickfont": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "tickprefix": "", "ticks": "", "ticksuffix": "", "title": { "font": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15, "text": "Click to enter X axis title" }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 2 }, "yaxis": { "anchor": "x", "automargin": true, "autorange": false, "autotypenumbers": "strict", "color": "#444", "constraintoward": "middle", "domain": [ 0, 1 ], "dtick": 0.005, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "left", "tick0": 0, "tickangle": "auto", "tickfont": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "tickprefix": "", "ticks": "", "ticksuffix": "", "title": { "font": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15, "text": "Click to enter Y axis title" }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 2 } }, "layout_edit_id": 3 }, "_js2py_restyle": {}, "_js2py_traceDeltas": { "trace_deltas": [ { "cliponaxis": true, "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverinfo": "all", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hoveron": "points", "hovertemplate": "", "hovertext": "", "index": 0, "legendgroup": "", "legendgrouptitle": { "font": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "marker": { "color": "#636efa", "gradient": { "type": "none" }, "line": { "color": "#444", "width": 0 }, "maxdisplayed": 0, "opacity": 1, "size": 6, "symbol": "circle" }, "name": "trace 0", "selected": { "marker": { "opacity": 1 } }, "showlegend": true, "stackgroup": "", "text": "", "uid": "9bd6c7c6-fec8-47c5-92c0-176e0349ae96", "unselected": { "marker": { "opacity": 0.2 } }, "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 }, { "autocolorscale": false, "connectgaps": false, "dx": 1, "dy": 1, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hoverongaps": true, "hovertemplate": "", "index": 1, "legendgroup": "", "legendgrouptitle": { "text": "" }, "legendrank": 1000, "name": "trace 1", "opacity": 1, "reversescale": false, "showlegend": false, "textfont": { "color": "auto", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": "auto" }, "texttemplate": "", "transpose": false, "uid": "766b6d60-4a85-4c8d-9ef9-fa696e707542", "visible": true, "x0": 0, "xaxis": "x", "xcalendar": "gregorian", "xgap": 0, "xhoverformat": "", "xperiod": 0, "y0": 0, "yaxis": "y", "ycalendar": "gregorian", "ygap": 0, "yhoverformat": "", "yperiod": 0, "zauto": false, "zhoverformat": "", "zsmooth": false }, { "autocolorscale": false, "colorbar": { "bgcolor": "rgba(0,0,0,0)", "bordercolor": "#444", "borderwidth": 0, "exponentformat": "B", "minexponent": 3, "nticks": 0, "orientation": "v", "outlinecolor": "#444", "outlinewidth": 0, "separatethousands": false, "showexponent": "all", "showticklabels": true, "thickness": 30, "thicknessmode": "pixels", "tickangle": "auto", "tickfont": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "tickmode": "auto", "tickprefix": "", "ticks": "", "ticksuffix": "", "title": { "font": { "color": "#2a3f5f", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "side": "top", "text": "Click to enter Colorscale title" }, "x": 1.02, "xanchor": "left", "xpad": 10, "y": 0.5, "yanchor": "middle", "ypad": 10 }, "connectgaps": false, "dx": 1, "dy": 1, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hoverongaps": true, "index": 2, "legendgroup": "", "legendgrouptitle": { "text": "" }, "legendrank": 1000, "name": "trace 2", "reversescale": false, "showlegend": false, "showscale": true, "textfont": { "color": "auto", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": "auto" }, "texttemplate": "", "transpose": false, "uid": "80ff38bd-97d8-448d-afd0-8a6c520f0ff8", "visible": true, "x0": 0, "xaxis": "x", "xcalendar": "gregorian", "xgap": 0, "xhoverformat": "", "xperiod": 0, "y0": 0, "yaxis": "y", "ycalendar": "gregorian", "ygap": 0, "yhoverformat": "", "yperiod": 0, "zauto": false, "zhoverformat": "", "zsmooth": false } ], "trace_edit_id": 2 }, "_js2py_update": {}, "_last_layout_edit_id": 3, "_last_trace_edit_id": 2, "_layout": { "autosize": true, "clickmode": "event", "template": { "data": { "bar": [ { "error_x": { "color": "#2a3f5f" }, "error_y": { "color": "#2a3f5f" }, "marker": { "line": { "color": "#E5ECF6", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "#E5ECF6", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "#2a3f5f", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "#2a3f5f" }, "baxis": { "endlinecolor": "#2a3f5f", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "#2a3f5f" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "fillpattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 0, "ticks": "" }, "colorscale": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "#EBF0F8" }, "line": { "color": "white" } }, "header": { "fill": { "color": "#C8D4E3" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowcolor": "#2a3f5f", "arrowhead": 0, "arrowwidth": 1 }, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 0, "ticks": "" } }, "colorscale": { "diverging": [ [ 0, "#8e0152" ], [ 0.1, "#c51b7d" ], [ 0.2, "#de77ae" ], [ 0.3, "#f1b6da" ], [ 0.4, "#fde0ef" ], [ 0.5, "#f7f7f7" ], [ 0.6, "#e6f5d0" ], [ 0.7, "#b8e186" ], [ 0.8, "#7fbc41" ], [ 0.9, "#4d9221" ], [ 1, "#276419" ] ], "sequential": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ], "sequentialminus": [ [ 0, "#0d0887" ], [ 0.1111111111111111, "#46039f" ], [ 0.2222222222222222, "#7201a8" ], [ 0.3333333333333333, "#9c179e" ], [ 0.4444444444444444, "#bd3786" ], [ 0.5555555555555556, "#d8576b" ], [ 0.6666666666666666, "#ed7953" ], [ 0.7777777777777778, "#fb9f3a" ], [ 0.8888888888888888, "#fdca26" ], [ 1, "#f0f921" ] ] }, "colorway": [ "#636efa", "#EF553B", "#00cc96", "#ab63fa", "#FFA15A", "#19d3f3", "#FF6692", "#B6E880", "#FF97FF", "#FECB52" ], "font": { "color": "#2a3f5f" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "#E5ECF6", "showlakes": true, "showland": true, "subunitcolor": "white" }, "hoverlabel": { "align": "left" }, "hovermode": "closest", "mapbox": { "style": "light" }, "paper_bgcolor": "white", "plot_bgcolor": "#E5ECF6", "polar": { "angularaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "bgcolor": "#E5ECF6", "radialaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" } }, "scene": { "xaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" }, "yaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" }, "zaxis": { "backgroundcolor": "#E5ECF6", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "ticks": "", "zerolinecolor": "white" } }, "shapedefaults": { "line": { "color": "#2a3f5f" } }, "ternary": { "aaxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "baxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" }, "bgcolor": "#E5ECF6", "caxis": { "gridcolor": "white", "linecolor": "white", "ticks": "" } }, "title": { "x": 0.05 }, "xaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "ticks": "", "title": { "standoff": 15 }, "zerolinecolor": "white", "zerolinewidth": 2 }, "yaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "ticks": "", "title": { "standoff": 15 }, "zerolinecolor": "white", "zerolinewidth": 2 } } }, "xaxis": { "constrain": "domain", "range": [ -0.5, 2.5 ], "tickmode": "array", "ticktext": [ "Dog", "Cat", "(none)" ], "tickvals": [ 0, 1, 2 ] }, "yaxis": { "constrain": "domain", "range": [ -0.5, 2.5 ], "scaleanchor": "x", "scaleratio": 1, "tickmode": "array", "ticktext": [ "(none)", "Cat", "Dog" ], "tickvals": [ 0, 1, 2 ] } }, "_py2js_addTraces": {}, "_py2js_animate": {}, "_py2js_deleteTraces": {}, "_py2js_moveTraces": {}, "_py2js_removeLayoutProps": {}, "_py2js_removeTraceProps": {}, "_py2js_restyle": {}, "_view_count": 2 } }, "9d0badf8b964433eb21521df8231bad0": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "a3b8544640f14eb792472878f8bfb2c5": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "a6de5263194f4a66988a7f9984dda88c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "children": [ "IPY_MODEL_d5065c5747434d1bb197137813b4e649", "IPY_MODEL_4c4059c2e3594d3c9b637f6360611af3", "IPY_MODEL_02a70fd9efa1492193a91c04c1c11102" ], "layout": "IPY_MODEL_49dd463084ce4018945ba6d51bcfa9af" } }, "aec04ca49d44453e84bc87b381ab5fe8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_774b86f403654d08aa2c3a1ce27bbff4", "style": "IPY_MODEL_af5e9d84be974f81a29a6df0d9f29a97", "value": "Epochs completed: 100%| " } }, "af5e9d84be974f81a29a6df0d9f29a97": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "b270f34ee06148c7b729661bdd227aa4": { "buffers": [ { "data": "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", "encoding": "base64", "path": [ "_data", 0, "customdata", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 0, "x", "value" ] }, { "data": "AAAAAAAA8D8AAAAAAADwPwAAAAAAAPA/AAAAAAAA8D8AAAAAAADwPwAAAAAAAPA/AAAAAAAA8D8AAAAAAADwPwAAAAAAAPA/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z/2obE+NNbvP/ahsT401u8/9qGxPjTW7z9A3bU/3bXvP0DdtT/dte8/QN21P9217z9A3bU/3bXvP0DdtT/dte8/QN21P9217z9A3bU/3bXvP0DdtT/dte8/jvxcMcuR7z/1pje96U3vP2Fo+RUMLe8/x2g7zQoO7z//EPD+EPDuPyDnpxICcu4/cdCaMxFb7j9x0JozEVvuPwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA==", "encoding": "base64", "path": [ "_data", 0, "y", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 1, "customdata", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 1, "x", "value" ] }, { "data": "AAAAAAAA8D8AAAAAAADwPwAAAAAAAPA/AAAAAAAA8D/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/5h1wpGiI7z/mHXCkaIjvP+YdcKRoiO8/PiInCHdj7z8+IicId2PvPz4iJwh3Y+8/PiInCHdj7z8+IicId2PvPz4iJwh3Y+8/PiInCHdj7z+mfB2WcFTvP6Z8HZZwVO8/pnwdlnBU7z+mfB2WcFTvP6Z8HZZwVO8/pnwdlnBU7z+mfB2WcFTvP6Z8HZZwVO8/pnwdlnBU7z+mfB2WcFTvP6Z8HZZwVO8/0Bf0BX1B7z/QF/QFfUHvP9AX9AV9Qe8/0Bf0BX1B7z/QF/QFfUHvP9AX9AV9Qe8/0Bf0BX1B7z8mv1jyiyXvPya/WPKLJe8/Jr9Y8osl7z90U1IdYgPvPwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA==", "encoding": "base64", "path": [ "_data", 1, "y", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 2, "x", "value" ] }, { "data": "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA==", "encoding": "base64", "path": [ "_data", 2, "y", "value" ] } ], "model_module": "jupyterlab-plotly", "model_module_version": "^5.9.0", "model_name": "FigureModel", "state": { "_config": { "plotlyServerURL": "https://plot.ly" }, "_data": [ { "customdata": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "hovertemplate": "class: %{text}
recall: %{x:.3f}
precision: %{y:.3f}
threshold: %{customdata:.3f}", "line": { "color": "#3366CC" }, "mode": "lines", "name": "Cat (AP = 0.845)", "text": [ "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat" ], "type": "scatter", "uid": "3284803b-16b5-4ec4-a1c3-427481e0d715", "x": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "y": { "dtype": "float64", "shape": [ 101 ], "value": {} } }, { "customdata": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "hovertemplate": "class: %{text}
recall: %{x:.3f}
precision: %{y:.3f}
threshold: %{customdata:.3f}", "line": { "color": "#DC3912" }, "mode": "lines", "name": "Dog (AP = 0.720)", "text": [ "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog" ], "type": "scatter", "uid": "c760ae7a-6827-4ffb-85f5-88dd88c9daf8", "x": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "y": { "dtype": "float64", "shape": [ 101 ], "value": {} } }, { "hovertemplate": "class: %{text}
recall: %{x:.3f}
precision: %{y:.3f}
threshold: %{customdata:.3f}", "line": { "color": "#FF9900" }, "mode": "lines", "name": "Mammal (AP = 0.000)", "text": [ "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal", "Mammal" ], "type": "scatter", "uid": "abb39460-2114-40a8-a7e4-9efdebf8d932", "x": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "y": { "dtype": "float64", "shape": [ 101 ], "value": {} } } ], "_js2py_layoutDelta": { "layout_delta": { "activeshape": { "fillcolor": "rgb(255,0,255)", "opacity": 0.5 }, "annotations": [], "autotypenumbers": "strict", "calendar": "gregorian", "clickmode": "event", "colorscale": { "diverging": [ [ 0, "rgb(5,10,172)" ], [ 0.35, "rgb(106,137,247)" ], [ 0.5, "rgb(190,190,190)" ], [ 0.6, "rgb(220,170,132)" ], [ 0.7, "rgb(230,145,90)" ], [ 1, "rgb(178,10,28)" ] ], "sequential": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "sequentialminus": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ] }, "colorway": [ "#F8766D", "#A3A500", "#00BF7D", "#00B0F6", "#E76BF3" ], "dragmode": "zoom", "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "height": 470.127, "hidesources": false, "hoverdistance": 20, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "grouptitlefont": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hovermode": "closest", "images": [], "legend": { "bgcolor": "white", "bordercolor": "#444", "borderwidth": 0, "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "groupclick": "togglegroup", "grouptitlefont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "itemclick": "toggle", "itemdoubleclick": "toggleothers", "itemsizing": "trace", "itemwidth": 30, "orientation": "v", "title": { "text": "" }, "traceorder": "normal", "valign": "middle", "x": 1.02, "xanchor": "left", "y": 1, "yanchor": "auto" }, "margin": { "autoexpand": true, "pad": 0 }, "modebar": { "activecolor": "rgba(68, 68, 68, 0.7)", "add": "", "bgcolor": "rgba(255, 255, 255, 0.5)", "color": "rgba(68, 68, 68, 0.3)", "orientation": "h", "remove": "" }, "newshape": { "drawdirection": "diagonal", "fillcolor": "rgba(0,0,0,0)", "fillrule": "evenodd", "layer": "above", "line": { "color": "#444", "dash": "solid", "width": 4 }, "opacity": 1 }, "paper_bgcolor": "white", "plot_bgcolor": "rgb(237,237,237)", "separators": ".,", "shapes": [ { "editable": false, "fillcolor": "black", "fillrule": "evenodd", "layer": "above", "line": { "width": 0 }, "opacity": 0.3, "visible": true, "xref": "x", "xsizemode": "scaled", "yref": "y", "ysizemode": "scaled" } ], "showlegend": true, "sliders": [], "spikedistance": -1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 17 }, "pad": { "b": 0, "l": 0, "r": 0, "t": 0 }, "text": "Click to enter Plot title", "x": 0.5, "xanchor": "auto", "xref": "container", "y": "auto", "yanchor": "auto", "yref": "container" }, "uniformtext": { "mode": false }, "updatemenus": [], "width": 986.221, "xaxis": { "anchor": "y", "automargin": true, "autorange": false, "autotypenumbers": "strict", "color": "#444", "constraintoward": "center", "domain": [ 0.2506361323155216, 0.7493638676844784 ], "dtick": 0.2, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "mirror": false, "nticks": 0, "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "bottom", "tick0": 0, "tickangle": "auto", "tickcolor": "rgb(51,51,51)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 5, "tickmode": "auto", "tickprefix": "", "ticks": "outside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15 }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 1 }, "yaxis": { "anchor": "x", "automargin": true, "autorange": false, "autotypenumbers": "strict", "color": "#444", "constraintoward": "middle", "domain": [ 0, 1 ], "dtick": 0.2, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "mirror": false, "nticks": 0, "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "left", "tick0": 0, "tickangle": "auto", "tickcolor": "rgb(51,51,51)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 5, "tickmode": "auto", "tickprefix": "", "ticks": "outside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15 }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 1 } }, "layout_edit_id": 1 }, "_js2py_restyle": {}, "_js2py_traceDeltas": { "trace_deltas": [ { "connectgaps": false, "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hoveron": "points", "hovertext": "", "index": 0, "legendgroup": "", "legendgrouptitle": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "line": { "dash": "solid", "shape": "linear", "simplify": true, "width": 2 }, "opacity": 1, "showlegend": true, "stackgroup": "", "uid": "3284803b-16b5-4ec4-a1c3-427481e0d715", "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 }, { "connectgaps": false, "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hoveron": "points", "hovertext": "", "index": 1, "legendgroup": "", "legendgrouptitle": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "line": { "dash": "solid", "shape": "linear", "simplify": true, "width": 2 }, "opacity": 1, "showlegend": true, "stackgroup": "", "uid": "c760ae7a-6827-4ffb-85f5-88dd88c9daf8", "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 }, { "connectgaps": false, "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hoveron": "points", "hovertext": "", "index": 2, "legendgroup": "", "legendgrouptitle": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "line": { "dash": "solid", "shape": "linear", "simplify": true, "width": 2 }, "opacity": 1, "showlegend": true, "stackgroup": "", "uid": "abb39460-2114-40a8-a7e4-9efdebf8d932", "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 } ], "trace_edit_id": 0 }, "_js2py_update": {}, "_last_layout_edit_id": 1, "_layout": { "autosize": true, "margin": { "b": 0, "l": 0, "r": 0, "t": 30 }, "shapes": [ { "line": { "dash": "dash" }, "type": "line", "x0": 0, "x1": 1, "y0": 1, "y1": 0 } ], "template": { "data": { "bar": [ { "error_x": { "color": "rgb(51,51,51)" }, "error_y": { "color": "rgb(51,51,51)" }, "marker": { "line": { "color": "rgb(237,237,237)", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "rgb(237,237,237)", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "rgb(51,51,51)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(51,51,51)" }, "baxis": { "endlinecolor": "rgb(51,51,51)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(51,51,51)" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "fillpattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "rgb(237,237,237)" }, "line": { "color": "white" } }, "header": { "fill": { "color": "rgb(217,217,217)" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowhead": 0, "arrowwidth": 1 }, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "colorscale": { "sequential": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "sequentialminus": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ] }, "colorway": [ "#F8766D", "#A3A500", "#00BF7D", "#00B0F6", "#E76BF3" ], "font": { "color": "rgb(51,51,51)" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "rgb(237,237,237)", "showlakes": true, "showland": true, "subunitcolor": "white" }, "hoverlabel": { "align": "left" }, "hovermode": "closest", "paper_bgcolor": "white", "plot_bgcolor": "rgb(237,237,237)", "polar": { "angularaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "bgcolor": "rgb(237,237,237)", "radialaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" } }, "scene": { "xaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" }, "yaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" }, "zaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" } }, "shapedefaults": { "fillcolor": "black", "line": { "width": 0 }, "opacity": 0.3 }, "ternary": { "aaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "baxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "bgcolor": "rgb(237,237,237)", "caxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" } }, "xaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "title": { "standoff": 15 }, "zerolinecolor": "white" }, "yaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "title": { "standoff": 15 }, "zerolinecolor": "white" } } }, "xaxis": { "constrain": "domain", "range": [ 0, 1 ], "title": { "text": "Recall" } }, "yaxis": { "constrain": "domain", "range": [ 0, 1 ], "scaleanchor": "x", "scaleratio": 1, "title": { "text": "Precision" } } }, "_py2js_addTraces": {}, "_py2js_animate": {}, "_py2js_deleteTraces": {}, "_py2js_moveTraces": {}, "_py2js_removeLayoutProps": {}, "_py2js_removeTraceProps": {}, "_py2js_restyle": {}, "_py2js_update": {}, "_view_count": 2 } }, "b6c69d24d96b4017989a49fabff4361b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_4cb6553752844e848b33276521dedc6d", "style": "IPY_MODEL_eed958ff52fb49e586e6fc2ea9466262", "value": " 500/500 [00:00]" } }, "b818176e1dd0479b9c365d04df17153e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "bar_style": "success", "layout": "IPY_MODEL_d074113efa454142beb9e64628d6b3e7", "max": 500, "style": "IPY_MODEL_168c110060db41b5b2cc154a198dfd8b", "value": 500 } }, "bf46909f40b54dcaa090847fac4f99e2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_5b70ba0b3c4e467ea89756ddae8ede9a", "style": "IPY_MODEL_c39194036d2c4f9c8f4a9036c4a9a23c", "value": " 500/500 [00:02]" } }, "c08180f9d3204262a9149a52df05ff47": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "c14a2c2e6dde478a8e37d6d72cfdef51": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "children": [ "IPY_MODEL_e8d62464502948f2aaeff3fa7b0ce1de", "IPY_MODEL_5b35688f8c0c40d5b8088d96bf778e02", "IPY_MODEL_63b885f3a4a843d09c12177e835051be" ], "layout": "IPY_MODEL_2ae1c531aa8e4adebcd41bbf6fdf5d5d" } }, "c39194036d2c4f9c8f4a9036c4a9a23c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "c40332db490142519e1d4547769c1aa4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "cb6c8685e12741e0aa151bc0ba06bda3": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "cca649d00d03407e9631afc6ee6ba0b1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "d074113efa454142beb9e64628d6b3e7": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "d3cd521274384969b719bfde0af91de4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "description_width": "" } }, "d473c77ac98749eba6eaeb67ff3ba6b9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "d4fac055073146deb265fb0f8812ead0": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "d5065c5747434d1bb197137813b4e649": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_375761aa0a5b4fed99d793114e7af76a", "style": "IPY_MODEL_4bd26fbcec8f41c398ed7d58da752f04", "value": "Epochs completed: 100%| " } }, "df6c101e6077476eb357001f359f9e79": { "buffers": [ { "data": "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", "encoding": "base64", "path": [ "_data", 0, "customdata", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 0, "x", "value" ] }, { "data": "AAAAAAAA8D8AAAAAAADwPwAAAAAAAPA/AAAAAAAA8D8AAAAAAADwPwAAAAAAAPA/AAAAAAAA8D8AAAAAAADwPwAAAAAAAPA/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvPx1SE4y3su8/HVITjLey7z8dUhOMt7LvP/5EwinNi+8//kTCKc2L7z/+RMIpzYvvP/5EwinNi+8//kTCKc2L7z/+RMIpzYvvP/5EwinNi+8//kTCKc2L7z/+RMIpzYvvP/5EwinNi+8//kTCKc2L7z/+RMIpzYvvP30fq9mTfO8/fR+r2ZN87z99H6vZk3zvP30fq9mTfO8/fR+r2ZN87z99H6vZk3zvP30fq9mTfO8/fR+r2ZN87z99H6vZk3zvP30fq9mTfO8/fR+r2ZN87z99H6vZk3zvP30fq9mTfO8/fR+r2ZN87z99H6vZk3zvP30fq9mTfO8/P+iowBdX7z8/6KjAF1fvPzMzMzMzM+8/MzMzMzMz7z8mv1jyiyXvPya/WPKLJe8/Jr9Y8osl7z8mv1jyiyXvPya/WPKLJe8/Jr9Y8osl7z8mv1jyiyXvPya/WPKLJe8/dFNSHWID7z9P7MRO7MTuP/cn55JYpu4/XxeKXheK7j/o4FGXgg7uP73QC73QC+0/+OCDDz747D8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA==", "encoding": "base64", "path": [ "_data", 0, "y", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 1, "customdata", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 1, "x", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 1, "y", "value" ] } ], "model_module": "jupyterlab-plotly", "model_module_version": "^5.9.0", "model_name": "FigureModel", "state": { "_config": { "plotlyServerURL": "https://plot.ly" }, "_data": [ { "customdata": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "hovertemplate": "class: %{text}
recall: %{x:.3f}
precision: %{y:.3f}
threshold: %{customdata:.3f}", "line": { "color": "#3366CC" }, "mode": "lines", "name": "Cat (AP = 0.828)", "text": [ "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat" ], "type": "scatter", "uid": "4aa43897-e6fc-4ec2-a7fa-780fce577529", "x": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "y": { "dtype": "float64", "shape": [ 101 ], "value": {} } }, { "customdata": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "hovertemplate": "class: %{text}
recall: %{x:.3f}
precision: %{y:.3f}
threshold: %{customdata:.3f}", "line": { "color": "#DC3912" }, "mode": "lines", "name": "Dog (AP = 0.711)", "text": [ "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog" ], "type": "scatter", "uid": "0f0d0076-786b-4832-8a93-08e208020980", "x": { "dtype": "float64", "shape": [ 101 ], "value": {} }, "y": { "dtype": "float64", "shape": [ 101 ], "value": {} } } ], "_js2py_layoutDelta": { "layout_delta": { "activeshape": { "fillcolor": "rgb(255,0,255)", "opacity": 0.5 }, "annotations": [], "autotypenumbers": "strict", "calendar": "gregorian", "clickmode": "event", "colorscale": { "diverging": [ [ 0, "rgb(5,10,172)" ], [ 0.35, "rgb(106,137,247)" ], [ 0.5, "rgb(190,190,190)" ], [ 0.6, "rgb(220,170,132)" ], [ 0.7, "rgb(230,145,90)" ], [ 1, "rgb(178,10,28)" ] ], "sequential": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "sequentialminus": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ] }, "colorway": [ "#F8766D", "#A3A500", "#00BF7D", "#00B0F6", "#E76BF3" ], "dragmode": "zoom", "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "height": 470.127, "hidesources": false, "hoverdistance": 20, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "grouptitlefont": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hovermode": "closest", "images": [], "legend": { "bgcolor": "white", "bordercolor": "#444", "borderwidth": 0, "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "groupclick": "togglegroup", "grouptitlefont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "itemclick": "toggle", "itemdoubleclick": "toggleothers", "itemsizing": "trace", "itemwidth": 30, "orientation": "v", "title": { "text": "" }, "traceorder": "normal", "valign": "middle", "x": 1.02, "xanchor": "left", "y": 1, "yanchor": "auto" }, "margin": { "autoexpand": true, "pad": 0 }, "modebar": { "activecolor": "rgba(68, 68, 68, 0.7)", "add": "", "bgcolor": "rgba(255, 255, 255, 0.5)", "color": "rgba(68, 68, 68, 0.3)", "orientation": "h", "remove": "" }, "newshape": { "drawdirection": "diagonal", "fillcolor": "rgba(0,0,0,0)", "fillrule": "evenodd", "layer": "above", "line": { "color": "#444", "dash": "solid", "width": 4 }, "opacity": 1 }, "paper_bgcolor": "white", "plot_bgcolor": "rgb(237,237,237)", "separators": ".,", "shapes": [ { "editable": false, "fillcolor": "black", "fillrule": "evenodd", "layer": "above", "line": { "width": 0 }, "opacity": 0.3, "visible": true, "xref": "x", "xsizemode": "scaled", "yref": "y", "ysizemode": "scaled" } ], "showlegend": true, "sliders": [], "spikedistance": -1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 17 }, "pad": { "b": 0, "l": 0, "r": 0, "t": 0 }, "text": "Click to enter Plot title", "x": 0.5, "xanchor": "auto", "xref": "container", "y": "auto", "yanchor": "auto", "yref": "container" }, "uniformtext": { "mode": false }, "updatemenus": [], "width": 986.221, "xaxis": { "anchor": "y", "automargin": true, "autorange": false, "autotypenumbers": "strict", "color": "#444", "constraintoward": "center", "domain": [ 0.2589175891758918, 0.7410824108241082 ], "dtick": 0.2, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "mirror": false, "nticks": 0, "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "bottom", "tick0": 0, "tickangle": "auto", "tickcolor": "rgb(51,51,51)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 5, "tickmode": "auto", "tickprefix": "", "ticks": "outside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15 }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 1 }, "yaxis": { "anchor": "x", "automargin": true, "autorange": false, "autotypenumbers": "strict", "color": "#444", "constraintoward": "middle", "domain": [ 0, 1 ], "dtick": 0.2, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "mirror": false, "nticks": 0, "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "left", "tick0": 0, "tickangle": "auto", "tickcolor": "rgb(51,51,51)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 5, "tickmode": "auto", "tickprefix": "", "ticks": "outside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15 }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 1 } }, "layout_edit_id": 1 }, "_js2py_restyle": {}, "_js2py_traceDeltas": { "trace_deltas": [ { "connectgaps": false, "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hoveron": "points", "hovertext": "", "index": 0, "legendgroup": "", "legendgrouptitle": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "line": { "dash": "solid", "shape": "linear", "simplify": true, "width": 2 }, "opacity": 1, "showlegend": true, "stackgroup": "", "uid": "4aa43897-e6fc-4ec2-a7fa-780fce577529", "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 }, { "connectgaps": false, "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hoveron": "points", "hovertext": "", "index": 1, "legendgroup": "", "legendgrouptitle": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "line": { "dash": "solid", "shape": "linear", "simplify": true, "width": 2 }, "opacity": 1, "showlegend": true, "stackgroup": "", "uid": "0f0d0076-786b-4832-8a93-08e208020980", "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 } ], "trace_edit_id": 0 }, "_js2py_update": {}, "_last_layout_edit_id": 1, "_layout": { "autosize": true, "margin": { "b": 0, "l": 0, "r": 0, "t": 30 }, "shapes": [ { "line": { "dash": "dash" }, "type": "line", "x0": 0, "x1": 1, "y0": 1, "y1": 0 } ], "template": { "data": { "bar": [ { "error_x": { "color": "rgb(51,51,51)" }, "error_y": { "color": "rgb(51,51,51)" }, "marker": { "line": { "color": "rgb(237,237,237)", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "rgb(237,237,237)", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "rgb(51,51,51)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(51,51,51)" }, "baxis": { "endlinecolor": "rgb(51,51,51)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(51,51,51)" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "fillpattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "rgb(237,237,237)" }, "line": { "color": "white" } }, "header": { "fill": { "color": "rgb(217,217,217)" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowhead": 0, "arrowwidth": 1 }, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "colorscale": { "sequential": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "sequentialminus": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ] }, "colorway": [ "#F8766D", "#A3A500", "#00BF7D", "#00B0F6", "#E76BF3" ], "font": { "color": "rgb(51,51,51)" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "rgb(237,237,237)", "showlakes": true, "showland": true, "subunitcolor": "white" }, "hoverlabel": { "align": "left" }, "hovermode": "closest", "paper_bgcolor": "white", "plot_bgcolor": "rgb(237,237,237)", "polar": { "angularaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "bgcolor": "rgb(237,237,237)", "radialaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" } }, "scene": { "xaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" }, "yaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" }, "zaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" } }, "shapedefaults": { "fillcolor": "black", "line": { "width": 0 }, "opacity": 0.3 }, "ternary": { "aaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "baxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "bgcolor": "rgb(237,237,237)", "caxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" } }, "xaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "title": { "standoff": 15 }, "zerolinecolor": "white" }, "yaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "title": { "standoff": 15 }, "zerolinecolor": "white" } } }, "xaxis": { "constrain": "domain", "range": [ 0, 1 ], "title": { "text": "Recall" } }, "yaxis": { "constrain": "domain", "range": [ 0, 1 ], "scaleanchor": "x", "scaleratio": 1, "title": { "text": "Precision" } } }, "_py2js_addTraces": {}, "_py2js_animate": {}, "_py2js_deleteTraces": {}, "_py2js_moveTraces": {}, "_py2js_removeLayoutProps": {}, "_py2js_removeTraceProps": {}, "_py2js_restyle": {}, "_py2js_update": {}, "_view_count": 2 } }, "e0fedca28a8247809b3cf18c2d9e265f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "description_width": "" } }, "e4e3ab6c7a904fa8bd85ccf1fbc8f3bb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "bar_style": "success", "layout": "IPY_MODEL_d473c77ac98749eba6eaeb67ff3ba6b9", "max": 500, "style": "IPY_MODEL_d3cd521274384969b719bfde0af91de4", "value": 500 } }, "e8d62464502948f2aaeff3fa7b0ce1de": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_cb6c8685e12741e0aa151bc0ba06bda3", "style": "IPY_MODEL_cca649d00d03407e9631afc6ee6ba0b1", "value": "Epochs completed: 100%| " } }, "ec5015fc95794512b7115ca535fd5597": { "buffers": [ { "data": "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", "encoding": "base64", "path": [ "_data", 0, "marker", "size", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 0, "x", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 0, "y", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 1, "marker", "size", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 1, "x", "value" ] }, { "data": "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", "encoding": "base64", "path": [ "_data", 1, "y", "value" ] } ], "model_module": "jupyterlab-plotly", "model_module_version": "^5.9.0", "model_name": "FigureModel", "state": { "_config": { "plotlyServerURL": "https://plot.ly" }, "_data": [ { "customdata": [ "63ec56fed3964b0824a4dae9", "63ec570bd3964b0824a4daea", "63ec5712d3964b0824a4daeb", "63ec571dd3964b0824a4daed", "63ec571fd3964b0824a4daee", "63ec571fd3964b0824a4daef", "63ec5723d3964b0824a4daf0", "63ec5727d3964b0824a4daf1", "63ec5729d3964b0824a4daf2", "63ec572ad3964b0824a4daf3", "63ec572cd3964b0824a4daf4", "63ec573ad3964b0824a4daf7", "63ec573cd3964b0824a4daf8", "63ec573cd3964b0824a4daf9", "63ec573dd3964b0824a4dafb", "63ec573dd3964b0824a4dafc", "63ec5740d3964b0824a4dafe", "63ec5749d3964b0824a4daff", "63ec574bd3964b0824a4db01", "63ec574dd3964b0824a4db02", "63ec575cd3964b0824a4db03", "63ec5763d3964b0824a4db04", "63ec5767d3964b0824a4db05", "63ec576ad3964b0824a4db06", "63ec576bd3964b0824a4db07", "63ec5773d3964b0824a4db08", "63ec5773d3964b0824a4db09", "63ec577bd3964b0824a4db0b", "63ec577cd3964b0824a4db0c", "63ec577ed3964b0824a4db10", "63ec577fd3964b0824a4db11", "63ec5780d3964b0824a4db12", "63ec5780d3964b0824a4db13", "63ec5784d3964b0824a4db14", "63ec5785d3964b0824a4db15", "63ec5787d3964b0824a4db18", "63ec5789d3964b0824a4db19", "63ec578ad3964b0824a4db1a", "63ec578cd3964b0824a4db1b", "63ec578dd3964b0824a4db1d", "63ec578ed3964b0824a4db1e", "63ec5790d3964b0824a4db1f", "63ec5791d3964b0824a4db20", "63ec5792d3964b0824a4db21", "63ec5793d3964b0824a4db22", "63ec5793d3964b0824a4db23", "63ec5794d3964b0824a4db24", "63ec5796d3964b0824a4db26", "63ec5796d3964b0824a4db27", "63ec579bd3964b0824a4db28", "63ec579cd3964b0824a4db29", "63ec579dd3964b0824a4db2a", "63ec57a1d3964b0824a4db2b", "63ec57aad3964b0824a4db2c", "63ec57aad3964b0824a4db2d", "63ec57abd3964b0824a4db2e", "63ec57add3964b0824a4db30", "63ec57aed3964b0824a4db31", "63ec57afd3964b0824a4db32", "63ec57b2d3964b0824a4db33", "63ec57b3d3964b0824a4db34", "63ec57b4d3964b0824a4db35", "63ec57bed3964b0824a4db36", "63ec57bed3964b0824a4db37", "63ec57c0d3964b0824a4db38", "63ec57c1d3964b0824a4db39", "63ec57cbd3964b0824a4db3b", "63ec57d1d3964b0824a4db3c", "63ec57d1d3964b0824a4db3d", "63ec57d2d3964b0824a4db3e", "63ec57d5d3964b0824a4db3f", "63ec57d9d3964b0824a4db40", "63ec57dad3964b0824a4db41", "63ec57dfd3964b0824a4db42", "63ec57e0d3964b0824a4db43", "63ec57e5d3964b0824a4db44", "63ec57e5d3964b0824a4db45", "63ec57e6d3964b0824a4db46", "63ec57e7d3964b0824a4db48", "63ec57e8d3964b0824a4db49", "63ec57e9d3964b0824a4db4a", "63ec57e9d3964b0824a4db4b", "63ec57e9d3964b0824a4db4c", "63ec57efd3964b0824a4db4d", "63ec57fdd3964b0824a4db4e", "63ec5804d3964b0824a4db4f", "63ec5804d3964b0824a4db50", "63ec5805d3964b0824a4db51", "63ec5808d3964b0824a4db52", "63ec5808d3964b0824a4db53", "63ec580ad3964b0824a4db54", "63ec580ed3964b0824a4db55", "63ec580fd3964b0824a4db57", "63ec580fd3964b0824a4db58", "63ec581cd3964b0824a4db59", "63ec581dd3964b0824a4db5a", "63ec581dd3964b0824a4db5b", "63ec581ed3964b0824a4db5c", "63ec581fd3964b0824a4db5d", "63ec5820d3964b0824a4db5e", "63ec5821d3964b0824a4db5f", "63ec5823d3964b0824a4db60", "63ec5824d3964b0824a4db61", "63ec5828d3964b0824a4db62", "63ec582cd3964b0824a4db64", "63ec5836d3964b0824a4db65", "63ec5836d3964b0824a4db66", "63ec5837d3964b0824a4db67", "63ec5838d3964b0824a4db68", "63ec5839d3964b0824a4db69", "63ec583cd3964b0824a4db6a", "63ec5844d3964b0824a4db6b", "63ec5845d3964b0824a4db6c", "63ec5845d3964b0824a4db6d", "63ec584ad3964b0824a4db6e", "63ec5852d3964b0824a4db6f", "63ec5859d3964b0824a4db70", "63ec585bd3964b0824a4db72", "63ec585fd3964b0824a4db73", "63ec5867d3964b0824a4db74", "63ec5868d3964b0824a4db75", "63ec5870d3964b0824a4db76", "63ec5872d3964b0824a4db77", "63ec5878d3964b0824a4db78", "63ec587ad3964b0824a4db79", "63ec587bd3964b0824a4db7b", "63ec587cd3964b0824a4db7c", "63ec588fd3964b0824a4db7f", "63ec588fd3964b0824a4db80", "63ec5890d3964b0824a4db81", "63ec5890d3964b0824a4db82", "63ec5897d3964b0824a4db83", "63ec5897d3964b0824a4db84", "63ec5898d3964b0824a4db85", "63ec5899d3964b0824a4db86", "63ec589ed3964b0824a4db87", "63ec58a0d3964b0824a4db88", "63ec58a2d3964b0824a4db89", "63ec58aad3964b0824a4db8a", "63ec58abd3964b0824a4db8b", "63ec58afd3964b0824a4db8c", "63ec58c4d3964b0824a4db8d", "63ec58dad3964b0824a4db8e", "63ec58dbd3964b0824a4db8f", "63ec58ded3964b0824a4db90", "63ec58edd3964b0824a4db91", "63ec58fdd3964b0824a4db92", "63ec5903d3964b0824a4db93", "63ec590bd3964b0824a4db94", "63ec590cd3964b0824a4db95", "63ec590cd3964b0824a4db96", "63ec590fd3964b0824a4db97", "63ec5915d3964b0824a4db98", "63ec591ad3964b0824a4db99", "63ec591bd3964b0824a4db9a", "63ec591cd3964b0824a4db9b", "63ec592ad3964b0824a4db9f", "63ec5930d3964b0824a4dba0", "63ec5930d3964b0824a4dba1", "63ec5932d3964b0824a4dba2", "63ec593ed3964b0824a4dba3", "63ec5941d3964b0824a4dba4", "63ec5943d3964b0824a4dba6", "63ec5949d3964b0824a4dba7", "63ec5950d3964b0824a4dba8", "63ec595ad3964b0824a4dba9", "63ec595ed3964b0824a4dbaa", "63ec5960d3964b0824a4dbab", "63ec5962d3964b0824a4dbac", "63ec596fd3964b0824a4dbad", "63ec5979d3964b0824a4dbb0", "63ec597ad3964b0824a4dbb1", "63ec597dd3964b0824a4dbb2", "63ec5985d3964b0824a4dbb3", "63ec5987d3964b0824a4dbb4", "63ec598ad3964b0824a4dbb5", "63ec598bd3964b0824a4dbb6", "63ec598cd3964b0824a4dbb7", "63ec598dd3964b0824a4dbb9", "63ec598fd3964b0824a4dbbc", "63ec5993d3964b0824a4dbbe", "63ec5996d3964b0824a4dbc0", "63ec5996d3964b0824a4dbc1", "63ec5997d3964b0824a4dbc2", "63ec5998d3964b0824a4dbc3", "63ec5998d3964b0824a4dbc5", "63ec5999d3964b0824a4dbc6", "63ec599ad3964b0824a4dbc7", "63ec599bd3964b0824a4dbc8", "63ec599bd3964b0824a4dbc9", "63ec59a1d3964b0824a4dbca", "63ec59a6d3964b0824a4dbcb", "63ec59abd3964b0824a4dbcc", "63ec59acd3964b0824a4dbcd", "63ec59b3d3964b0824a4dbce", "63ec59b5d3964b0824a4dbcf", "63ec59b5d3964b0824a4dbd0", "63ec59b5d3964b0824a4dbd1", "63ec59b6d3964b0824a4dbd2", "63ec59b7d3964b0824a4dbd3", "63ec59b7d3964b0824a4dbd4", "63ec59b8d3964b0824a4dbd5", "63ec59bad3964b0824a4dbd6", "63ec59bdd3964b0824a4dbd9", "63ec59bed3964b0824a4dbda", "63ec59bed3964b0824a4dbdb", "63ec59bfd3964b0824a4dbdc", "63ec59c2d3964b0824a4dbdf", "63ec59ced3964b0824a4dbe2", "63ec59d8d3964b0824a4dbe3", "63ec59d9d3964b0824a4dbe4", "63ec59d9d3964b0824a4dbe5", "63ec59dad3964b0824a4dbe6", "63ec59dcd3964b0824a4dbe7", "63ec59ddd3964b0824a4dbe8", "63ec59ddd3964b0824a4dbe9", "63ec59e4d3964b0824a4dbea", "63ec59e6d3964b0824a4dbeb", "63ec59e9d3964b0824a4dbec", "63ec59e9d3964b0824a4dbed", "63ec59ead3964b0824a4dbef", "63ec59ebd3964b0824a4dbf0", "63ec59ebd3964b0824a4dbf1", "63ec59ecd3964b0824a4dbf2", "63ec59eed3964b0824a4dbf3", "63ec59f1d3964b0824a4dbf4", "63ec59f7d3964b0824a4dbf6", "63ec59f9d3964b0824a4dbf7", "63ec59fad3964b0824a4dbf8", "63ec59fad3964b0824a4dbf9", "63ec59fbd3964b0824a4dbfa", "63ec5a03d3964b0824a4dbfb", "63ec5a03d3964b0824a4dbfc", "63ec5a05d3964b0824a4dbfd", "63ec5a05d3964b0824a4dbfe", "63ec5a18d3964b0824a4dbff", "63ec5a1ad3964b0824a4dc00", "63ec5a1bd3964b0824a4dc01", "63ec5a1ed3964b0824a4dc02", "63ec5a2cd3964b0824a4dc04", "63ec5a2dd3964b0824a4dc05", "63ec5a2fd3964b0824a4dc06", "63ec5a30d3964b0824a4dc08", "63ec5a30d3964b0824a4dc09", "63ec5a32d3964b0824a4dc0a", "63ec5a34d3964b0824a4dc0b", "63ec5a36d3964b0824a4dc0c", "63ec5a37d3964b0824a4dc0d", "63ec5a38d3964b0824a4dc0e", "63ec5a38d3964b0824a4dc0f", "63ec5a39d3964b0824a4dc10", "63ec5a39d3964b0824a4dc11", "63ec5a44d3964b0824a4dc12", "63ec5be0d3964b0824a4dc67", "63ec5c4cd3964b0824a4dc7f", "63ec5c8fd3964b0824a4dc98", "63ec5e22d3964b0824a4dcce", "63ec5eb5d3964b0824a4dced", "63ec5f22d3964b0824a4dcfe", "63ec5f48d3964b0824a4dd0b", "63ec6238d3964b0824a4dd94", "63ec6238d3964b0824a4dd96", "63ec6251d3964b0824a4dd9f" ], "hovertemplate": "label: %{text}
size: %{marker.size}
x, y = %{x:.3f}, %{y:.3f}
ID: %{customdata}", "line": { "color": "#3366CC" }, "marker": { "size": { "dtype": "float64", "shape": [ 263 ], "value": {} }, "sizemin": 4, "sizemode": "diameter", "sizeref": 0.0332115939187967 }, "mode": "markers", "name": "Cat", "showlegend": true, "text": [ "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat", "Cat" ], "type": "scattergl", "uid": "8480ba68-118d-43f5-a597-66e97ef1d3f6", "x": { "dtype": "float32", "shape": [ 263 ], "value": {} }, "y": { "dtype": "float32", "shape": [ 263 ], "value": {} } }, { "customdata": [ "63ec5740d3964b0824a4dafd", "63ec585ad3964b0824a4db71", "63ec588bd3964b0824a4db7e", "63ec5977d3964b0824a4dbaf", "63ec5998d3964b0824a4dbc4", "63ec5a66d3964b0824a4dc16", "63ec5a66d3964b0824a4dc17", "63ec5a67d3964b0824a4dc18", "63ec5a67d3964b0824a4dc19", "63ec5a7bd3964b0824a4dc1c", "63ec5a8ed3964b0824a4dc20", "63ec5aa3d3964b0824a4dc21", "63ec5ab4d3964b0824a4dc22", "63ec5ab5d3964b0824a4dc23", "63ec5abdd3964b0824a4dc26", "63ec5ad0d3964b0824a4dc2a", "63ec5ad0d3964b0824a4dc2b", "63ec5ad1d3964b0824a4dc2c", "63ec5ae2d3964b0824a4dc2d", "63ec5aead3964b0824a4dc30", "63ec5aebd3964b0824a4dc32", "63ec5aecd3964b0824a4dc33", "63ec5aeed3964b0824a4dc34", "63ec5aeed3964b0824a4dc35", "63ec5afcd3964b0824a4dc36", "63ec5b09d3964b0824a4dc37", "63ec5b0bd3964b0824a4dc38", "63ec5b0bd3964b0824a4dc39", "63ec5b0dd3964b0824a4dc3a", "63ec5b0ed3964b0824a4dc3c", "63ec5b22d3964b0824a4dc3d", "63ec5b23d3964b0824a4dc3e", "63ec5b28d3964b0824a4dc40", "63ec5b3cd3964b0824a4dc42", "63ec5b3fd3964b0824a4dc43", "63ec5b4dd3964b0824a4dc45", "63ec5b4ed3964b0824a4dc46", "63ec5b4ed3964b0824a4dc47", "63ec5b5cd3964b0824a4dc48", "63ec5b5dd3964b0824a4dc4b", "63ec5b5dd3964b0824a4dc4c", "63ec5b63d3964b0824a4dc4d", "63ec5b76d3964b0824a4dc50", "63ec5b78d3964b0824a4dc51", "63ec5b79d3964b0824a4dc52", "63ec5b90d3964b0824a4dc53", "63ec5b90d3964b0824a4dc54", "63ec5bb1d3964b0824a4dc56", "63ec5bb9d3964b0824a4dc58", "63ec5bbdd3964b0824a4dc59", "63ec5bcfd3964b0824a4dc5a", "63ec5bd1d3964b0824a4dc5b", "63ec5bd2d3964b0824a4dc5c", "63ec5bd2d3964b0824a4dc5f", "63ec5bd4d3964b0824a4dc61", "63ec5bd4d3964b0824a4dc62", "63ec5bd7d3964b0824a4dc63", "63ec5bded3964b0824a4dc64", "63ec5be8d3964b0824a4dc69", "63ec5bebd3964b0824a4dc6b", "63ec5becd3964b0824a4dc6d", "63ec5bf5d3964b0824a4dc71", "63ec5bf6d3964b0824a4dc72", "63ec5c04d3964b0824a4dc73", "63ec5c19d3964b0824a4dc74", "63ec5c1cd3964b0824a4dc78", "63ec5c2ed3964b0824a4dc7a", "63ec5c31d3964b0824a4dc7b", "63ec5c4cd3964b0824a4dc7d", "63ec5c55d3964b0824a4dc80", "63ec5c57d3964b0824a4dc85", "63ec5c5bd3964b0824a4dc86", "63ec5c5fd3964b0824a4dc87", "63ec5c60d3964b0824a4dc8b", "63ec5c61d3964b0824a4dc8c", "63ec5c76d3964b0824a4dc8e", "63ec5c77d3964b0824a4dc90", "63ec5c77d3964b0824a4dc91", "63ec5c7ed3964b0824a4dc94", "63ec5c8fd3964b0824a4dc97", "63ec5ca2d3964b0824a4dc99", "63ec5ca2d3964b0824a4dc9a", "63ec5ca3d3964b0824a4dc9b", "63ec5ca4d3964b0824a4dc9c", "63ec5cd3d3964b0824a4dc9e", "63ec5cdfd3964b0824a4dc9f", "63ec5ce0d3964b0824a4dca0", "63ec5cead3964b0824a4dca1", "63ec5cf4d3964b0824a4dca4", "63ec5cf5d3964b0824a4dca5", "63ec5cf6d3964b0824a4dca7", "63ec5d1ed3964b0824a4dca9", "63ec5d20d3964b0824a4dcab", "63ec5d2cd3964b0824a4dcac", "63ec5d30d3964b0824a4dcad", "63ec5d42d3964b0824a4dcb3", "63ec5d42d3964b0824a4dcb4", "63ec5d43d3964b0824a4dcb5", "63ec5d45d3964b0824a4dcb6", "63ec5d4cd3964b0824a4dcb7", "63ec5d4dd3964b0824a4dcb8", "63ec5d55d3964b0824a4dcb9", "63ec5d55d3964b0824a4dcba", "63ec5d6dd3964b0824a4dcbb", "63ec5d78d3964b0824a4dcbc", "63ec5da0d3964b0824a4dcbd", "63ec5da2d3964b0824a4dcbe", "63ec5db2d3964b0824a4dcbf", "63ec5dd3d3964b0824a4dcc0", "63ec5de3d3964b0824a4dcc1", "63ec5de6d3964b0824a4dcc2", "63ec5de7d3964b0824a4dcc3", "63ec5debd3964b0824a4dcc4", "63ec5df7d3964b0824a4dcc5", "63ec5df9d3964b0824a4dcc6", "63ec5df9d3964b0824a4dcc7", "63ec5e20d3964b0824a4dcc9", "63ec5e21d3964b0824a4dcca", "63ec5e22d3964b0824a4dccd", "63ec5e33d3964b0824a4dcd0", "63ec5e41d3964b0824a4dcd3", "63ec5e4bd3964b0824a4dcd6", "63ec5e4dd3964b0824a4dcd8", "63ec5e4dd3964b0824a4dcd9", "63ec5e57d3964b0824a4dcda", "63ec5e58d3964b0824a4dcdb", "63ec5e59d3964b0824a4dcdc", "63ec5e72d3964b0824a4dce6", "63ec5e89d3964b0824a4dce9", "63ec5e92d3964b0824a4dcea", "63ec5eb2d3964b0824a4dceb", "63ec5eb5d3964b0824a4dcec", "63ec5ebdd3964b0824a4dcee", "63ec5ebed3964b0824a4dcf0", "63ec5ec7d3964b0824a4dcf1", "63ec5ed6d3964b0824a4dcf3", "63ec5ed9d3964b0824a4dcf4", "63ec5ee8d3964b0824a4dcf5", "63ec5eefd3964b0824a4dcf6", "63ec5ef4d3964b0824a4dcf7", "63ec5ef4d3964b0824a4dcf8", "63ec5f06d3964b0824a4dcfa", "63ec5f07d3964b0824a4dcfb", "63ec5f13d3964b0824a4dcfc", "63ec5f20d3964b0824a4dcfd", "63ec5f23d3964b0824a4dcff", "63ec5f36d3964b0824a4dd02", "63ec5f3ad3964b0824a4dd03", "63ec5f3dd3964b0824a4dd04", "63ec5f40d3964b0824a4dd05", "63ec5f40d3964b0824a4dd06", "63ec5f42d3964b0824a4dd07", "63ec5f42d3964b0824a4dd09", "63ec5f42d3964b0824a4dd0a", "63ec5f4ad3964b0824a4dd0c", "63ec5f4bd3964b0824a4dd0d", "63ec5f4cd3964b0824a4dd0e", "63ec5f56d3964b0824a4dd0f", "63ec5f5ad3964b0824a4dd12", "63ec5f60d3964b0824a4dd14", "63ec5f8ad3964b0824a4dd15", "63ec5f8cd3964b0824a4dd17", "63ec5f8ed3964b0824a4dd18", "63ec5f8ed3964b0824a4dd19", "63ec5f91d3964b0824a4dd1a", "63ec5f98d3964b0824a4dd1d", "63ec5f98d3964b0824a4dd1e", "63ec5f9bd3964b0824a4dd1f", "63ec5fb5d3964b0824a4dd20", "63ec5fb9d3964b0824a4dd23", "63ec5fc0d3964b0824a4dd24", "63ec5fdfd3964b0824a4dd25", "63ec5fe8d3964b0824a4dd26", "63ec6008d3964b0824a4dd2c", "63ec600dd3964b0824a4dd30", "63ec6020d3964b0824a4dd31", "63ec602fd3964b0824a4dd34", "63ec6032d3964b0824a4dd35", "63ec6046d3964b0824a4dd37", "63ec6049d3964b0824a4dd38", "63ec604bd3964b0824a4dd3a", "63ec6054d3964b0824a4dd3c", "63ec605cd3964b0824a4dd43", "63ec605cd3964b0824a4dd45", "63ec605ed3964b0824a4dd4b", "63ec6061d3964b0824a4dd4e", "63ec6070d3964b0824a4dd52", "63ec607cd3964b0824a4dd53", "63ec607fd3964b0824a4dd54", "63ec6080d3964b0824a4dd57", "63ec6091d3964b0824a4dd5a", "63ec6094d3964b0824a4dd5b", "63ec6096d3964b0824a4dd5c", "63ec6098d3964b0824a4dd5d", "63ec609bd3964b0824a4dd5f", "63ec60a1d3964b0824a4dd63", "63ec60a1d3964b0824a4dd64", "63ec60a1d3964b0824a4dd66", "63ec60b1d3964b0824a4dd67", "63ec60bad3964b0824a4dd69", "63ec60bad3964b0824a4dd6a", "63ec60bed3964b0824a4dd6b", "63ec60c7d3964b0824a4dd6d", "63ec60d5d3964b0824a4dd6e", "63ec60d5d3964b0824a4dd6f", "63ec60dcd3964b0824a4dd76", "63ec60dcd3964b0824a4dd78", "63ec60eed3964b0824a4dd7b", "63ec6102d3964b0824a4dd7d", "63ec611dd3964b0824a4dd7f", "63ec6129d3964b0824a4dd80", "63ec613ed3964b0824a4dd81", "63ec615ad3964b0824a4dd82", "63ec615dd3964b0824a4dd83", "63ec6160d3964b0824a4dd84", "63ec6167d3964b0824a4dd85", "63ec6183d3964b0824a4dd87", "63ec6190d3964b0824a4dd88", "63ec61b0d3964b0824a4dd89", "63ec61b7d3964b0824a4dd8b", "63ec61bfd3964b0824a4dd8c", "63ec61c1d3964b0824a4dd8d", "63ec61d8d3964b0824a4dd8e", "63ec61e2d3964b0824a4dd8f", "63ec61fed3964b0824a4dd90", "63ec6208d3964b0824a4dd91", "63ec6223d3964b0824a4dd92", "63ec6238d3964b0824a4dd95", "63ec623bd3964b0824a4dd97", "63ec623dd3964b0824a4dd98", "63ec6241d3964b0824a4dd9a", "63ec624fd3964b0824a4dd9b", "63ec6251d3964b0824a4dd9e", "63ec625fd3964b0824a4dda0" ], "hovertemplate": "label: %{text}
size: %{marker.size}
x, y = %{x:.3f}, %{y:.3f}
ID: %{customdata}", "line": { "color": "#DC3912" }, "marker": { "size": { "dtype": "float64", "shape": [ 234 ], "value": {} }, "sizemin": 4, "sizemode": "diameter", "sizeref": 0.0332115939187967 }, "mode": "markers", "name": "Dog", "showlegend": true, "text": [ "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog", "Dog" ], "type": "scattergl", "uid": "94690c34-7c3e-45ea-a26d-fe1c529f0878", "x": { "dtype": "float32", "shape": [ 234 ], "value": {} }, "y": { "dtype": "float32", "shape": [ 234 ], "value": {} } } ], "_js2py_layoutDelta": { "layout_delta": { "activeshape": { "fillcolor": "rgb(255,0,255)", "opacity": 0.5 }, "annotations": [], "autosize": true, "autotypenumbers": "strict", "calendar": "gregorian", "clickmode": "event", "colorscale": { "diverging": [ [ 0, "rgb(5,10,172)" ], [ 0.35, "rgb(106,137,247)" ], [ 0.5, "rgb(190,190,190)" ], [ 0.6, "rgb(220,170,132)" ], [ 0.7, "rgb(230,145,90)" ], [ 1, "rgb(178,10,28)" ] ], "sequential": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "sequentialminus": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ] }, "colorway": [ "#F8766D", "#A3A500", "#00BF7D", "#00B0F6", "#E76BF3" ], "dragmode": "zoom", "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "height": 470.127, "hidesources": false, "hoverdistance": 20, "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "grouptitlefont": { "family": "Arial, sans-serif", "size": 13 }, "namelength": 15 }, "hovermode": "closest", "images": [], "legend": { "bgcolor": "white", "bordercolor": "#444", "borderwidth": 0, "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "groupclick": "togglegroup", "grouptitlefont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "itemclick": "toggle", "itemdoubleclick": "toggleothers", "itemwidth": 30, "orientation": "v", "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "side": "top" }, "traceorder": "normal", "valign": "middle", "x": 1.02, "xanchor": "left", "y": 1, "yanchor": "auto" }, "margin": { "autoexpand": true, "pad": 0 }, "modebar": { "activecolor": "rgba(68, 68, 68, 0.7)", "add": "", "bgcolor": "rgba(255, 255, 255, 0.5)", "color": "rgba(68, 68, 68, 0.3)", "orientation": "h", "remove": "" }, "newshape": { "drawdirection": "diagonal", "fillcolor": "rgba(0,0,0,0)", "fillrule": "evenodd", "layer": "above", "line": { "color": "#444", "dash": "solid", "width": 4 }, "opacity": 1 }, "paper_bgcolor": "white", "plot_bgcolor": "rgb(237,237,237)", "separators": ".,", "shapes": [], "showlegend": true, "sliders": [], "spikedistance": -1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 17 }, "pad": { "b": 0, "l": 0, "r": 0, "t": 0 }, "text": "Click to enter Plot title", "x": 0.5, "xanchor": "auto", "xref": "container", "y": "auto", "yanchor": "auto", "yref": "container" }, "uniformtext": { "mode": false }, "updatemenus": [], "width": 986.221, "xaxis": { "anchor": "y", "automargin": true, "autorange": true, "autotypenumbers": "strict", "color": "#444", "constrain": "range", "constraintoward": "center", "domain": [ 0, 1 ], "dtick": 1, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "mirror": false, "nticks": 0, "range": [ 5.0649085199234545, 12.648903667156446 ], "rangemode": "normal", "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "bottom", "tick0": 0, "tickangle": "auto", "tickcolor": "rgb(51,51,51)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 5, "tickmode": "auto", "tickprefix": "", "ticks": "outside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15, "text": "Click to enter X axis title" }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 1 }, "yaxis": { "anchor": "x", "automargin": true, "autorange": true, "autotypenumbers": "strict", "color": "#444", "constrain": "range", "constraintoward": "middle", "domain": [ 0, 1 ], "dtick": 1, "exponentformat": "B", "fixedrange": false, "gridcolor": "white", "griddash": "solid", "gridwidth": 1, "hoverformat": "", "layer": "above traces", "minexponent": 3, "mirror": false, "nticks": 0, "range": [ 0.2778011087069032, 6.346091157205503 ], "rangemode": "normal", "separatethousands": false, "showexponent": "all", "showgrid": true, "showline": false, "showspikes": false, "showticklabels": true, "side": "left", "tick0": 0, "tickangle": "auto", "tickcolor": "rgb(51,51,51)", "tickfont": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 12 }, "tickformat": "", "ticklabeloverflow": "hide past div", "ticklabelposition": "outside", "ticklabelstep": 1, "ticklen": 5, "tickmode": "auto", "tickprefix": "", "ticks": "outside", "ticksuffix": "", "tickwidth": 1, "title": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 14 }, "standoff": 15, "text": "Click to enter Y axis title" }, "type": "linear", "visible": true, "zeroline": true, "zerolinecolor": "white", "zerolinewidth": 1 } }, "layout_edit_id": 0 }, "_js2py_relayout": {}, "_js2py_restyle": {}, "_js2py_traceDeltas": { "trace_deltas": [ { "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hovertext": "", "index": 0, "legendgroup": "", "legendgrouptitle": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "marker": { "color": "#3366CC", "line": { "color": "#fff", "width": 1 }, "opacity": 0.7, "symbol": "circle" }, "opacity": 1, "selected": { "marker": { "opacity": 0.7 } }, "uid": "8480ba68-118d-43f5-a597-66e97ef1d3f6", "unselected": { "marker": { "opacity": 0.13999999999999999 } }, "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 }, { "error_x": { "visible": false }, "error_y": { "visible": false }, "fill": "none", "hoverlabel": { "align": "left", "font": { "family": "Arial, sans-serif", "size": 13 }, "namelength": -1 }, "hovertext": "", "index": 1, "legendgroup": "", "legendgrouptitle": { "font": { "color": "rgb(51,51,51)", "family": "\"Open Sans\", verdana, arial, sans-serif", "size": 13 }, "text": "" }, "legendrank": 1000, "marker": { "color": "#DC3912", "line": { "color": "#fff", "width": 1 }, "opacity": 0.7, "symbol": "circle" }, "opacity": 1, "selected": { "marker": { "opacity": 0.7 } }, "uid": "94690c34-7c3e-45ea-a26d-fe1c529f0878", "unselected": { "marker": { "opacity": 0.13999999999999999 } }, "visible": true, "xaxis": "x", "xcalendar": "gregorian", "xhoverformat": "", "xperiod": 0, "yaxis": "y", "ycalendar": "gregorian", "yhoverformat": "", "yperiod": 0 } ], "trace_edit_id": 0 }, "_js2py_update": {}, "_layout": { "legend": { "itemsizing": "constant", "title": { "text": "label" } }, "margin": { "b": 0, "l": 0, "r": 0, "t": 30 }, "template": { "data": { "bar": [ { "error_x": { "color": "rgb(51,51,51)" }, "error_y": { "color": "rgb(51,51,51)" }, "marker": { "line": { "color": "rgb(237,237,237)", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "bar" } ], "barpolar": [ { "marker": { "line": { "color": "rgb(237,237,237)", "width": 0.5 }, "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "barpolar" } ], "carpet": [ { "aaxis": { "endlinecolor": "rgb(51,51,51)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(51,51,51)" }, "baxis": { "endlinecolor": "rgb(51,51,51)", "gridcolor": "white", "linecolor": "white", "minorgridcolor": "white", "startlinecolor": "rgb(51,51,51)" }, "type": "carpet" } ], "choropleth": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "choropleth" } ], "contour": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "contour" } ], "contourcarpet": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "contourcarpet" } ], "heatmap": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "heatmap" } ], "heatmapgl": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "heatmapgl" } ], "histogram": [ { "marker": { "pattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 } }, "type": "histogram" } ], "histogram2d": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "histogram2d" } ], "histogram2dcontour": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "histogram2dcontour" } ], "mesh3d": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "type": "mesh3d" } ], "parcoords": [ { "line": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "parcoords" } ], "pie": [ { "automargin": true, "type": "pie" } ], "scatter": [ { "fillpattern": { "fillmode": "overlay", "size": 10, "solidity": 0.2 }, "type": "scatter" } ], "scatter3d": [ { "line": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatter3d" } ], "scattercarpet": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattercarpet" } ], "scattergeo": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattergeo" } ], "scattergl": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattergl" } ], "scattermapbox": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scattermapbox" } ], "scatterpolar": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterpolar" } ], "scatterpolargl": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterpolargl" } ], "scatterternary": [ { "marker": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "type": "scatterternary" } ], "surface": [ { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" }, "colorscale": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "type": "surface" } ], "table": [ { "cells": { "fill": { "color": "rgb(237,237,237)" }, "line": { "color": "white" } }, "header": { "fill": { "color": "rgb(217,217,217)" }, "line": { "color": "white" } }, "type": "table" } ] }, "layout": { "annotationdefaults": { "arrowhead": 0, "arrowwidth": 1 }, "autotypenumbers": "strict", "coloraxis": { "colorbar": { "outlinewidth": 0, "tickcolor": "rgb(237,237,237)", "ticklen": 6, "ticks": "inside" } }, "colorscale": { "sequential": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ], "sequentialminus": [ [ 0, "rgb(20,44,66)" ], [ 1, "rgb(90,179,244)" ] ] }, "colorway": [ "#F8766D", "#A3A500", "#00BF7D", "#00B0F6", "#E76BF3" ], "font": { "color": "rgb(51,51,51)" }, "geo": { "bgcolor": "white", "lakecolor": "white", "landcolor": "rgb(237,237,237)", "showlakes": true, "showland": true, "subunitcolor": "white" }, "hoverlabel": { "align": "left" }, "hovermode": "closest", "paper_bgcolor": "white", "plot_bgcolor": "rgb(237,237,237)", "polar": { "angularaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "bgcolor": "rgb(237,237,237)", "radialaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" } }, "scene": { "xaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" }, "yaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" }, "zaxis": { "backgroundcolor": "rgb(237,237,237)", "gridcolor": "white", "gridwidth": 2, "linecolor": "white", "showbackground": true, "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "zerolinecolor": "white" } }, "shapedefaults": { "fillcolor": "black", "line": { "width": 0 }, "opacity": 0.3 }, "ternary": { "aaxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "baxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" }, "bgcolor": "rgb(237,237,237)", "caxis": { "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside" } }, "xaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "title": { "standoff": 15 }, "zerolinecolor": "white" }, "yaxis": { "automargin": true, "gridcolor": "white", "linecolor": "white", "showgrid": true, "tickcolor": "rgb(51,51,51)", "ticks": "outside", "title": { "standoff": 15 }, "zerolinecolor": "white" } } } }, "_py2js_addTraces": {}, "_py2js_animate": {}, "_py2js_deleteTraces": {}, "_py2js_moveTraces": {}, "_py2js_relayout": {}, "_py2js_removeLayoutProps": {}, "_py2js_removeTraceProps": {}, "_py2js_restyle": {}, "_py2js_update": {}, "_view_count": 2 } }, "eed958ff52fb49e586e6fc2ea9466262": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "description_width": "" } }, "f575aee4210e4cb7b93d01ba158477ab": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "layout": "IPY_MODEL_9390307ed5374e06b33c2afbfe157950", "style": "IPY_MODEL_79143a7c04a64a7993df2ba72922bc72", "value": " 500/500 [00:00]" } }, "f5ffbea1cd054092aada8eb9f61fe325": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} }, "fcb7d296d5084718bab6599c4129d052": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": {} } }, "version_major": 2, "version_minor": 0 } } }, "nbformat": 4, "nbformat_minor": 4 }