{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Computer vision data" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [], "source": [ "%matplotlib inline\n", "from fastai.gen_doc.nbdoc import *\n", "from fastai import * \n", "from fastai.vision import * " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This module contains the classes that define datasets handling [`Image`](/vision.image.html#Image) objects and their tranformations. As usual, we'll start with a quick overview, before we get in to the detailed API docs." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Quickly get your data ready for training" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To get you started as easily as possible, the fastai provides two helper functions to create a [`DataBunch`](/basic_data.html#DataBunch) object that you can directly use for training a classifier. To demonstrate them you'll first need to download and untar the file by executing the following cell. This will create a data folder containing an MNIST subset in `data/mnist_sample`." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "PosixPath('/home/ubuntu/.fastai/data/mnist_sample')" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "path = untar_data(URLs.MNIST_SAMPLE); path" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "There are a number of ways to create an [`ImageDataBunch`](/vision.data.html#ImageDataBunch). One common approach is to use *Imagenet-style folders* (see a ways down the page below for details) with [`ImageDataBunch.from_folder`](/vision.data.html#ImageDataBunch.from_folder):" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "tfms = get_transforms(do_flip=False)\n", "data = ImageDataBunch.from_folder(path, ds_tfms=tfms, size=24)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Here the datasets will be automatically created in the structure of *Imagenet-style folders*. The parameters specified:\n", "- the transforms to apply to the images in `ds_tfms` (here with `do_flip`=False because we don't want to flip numbers),\n", "- the target `size` of our pictures (here 24).\n", "\n", "As with all [`DataBunch`](/basic_data.html#DataBunch) usage, a `train_dl` and a `valid_dl` are created that are of the type PyTorch [`DataLoader`](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader). \n", "\n", "If you want to have a look at a few images inside a batch, you can use [`ImageDataBunch.show_batch`](/vision.data.html#ImageDataBunch.show_batch). The `rows` argument is the number of rows and columns to display." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "data.show_batch(rows=3, figsize=(5,5))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The second way to define the data for a classifier requires a structure like this:\n", "```\n", "path\\\n", " train\\\n", " test\\\n", " labels.csv\n", "```\n", "where the labels.csv file defines the label(s) of each image in the training set. This is the format you will need to use when each image can have multiple labels. It also works with single labels:" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
namelabel
0train/3/7463.png0
1train/3/21102.png0
2train/3/31559.png0
3train/3/46882.png0
4train/3/26209.png0
\n", "
" ], "text/plain": [ " name label\n", "0 train/3/7463.png 0\n", "1 train/3/21102.png 0\n", "2 train/3/31559.png 0\n", "3 train/3/46882.png 0\n", "4 train/3/26209.png 0" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pd.read_csv(path/'labels.csv').head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can then use [`ImageDataBunch.from_csv`](/vision.data.html#ImageDataBunch.from_csv):" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "data = ImageDataBunch.from_csv(path, ds_tfms=tfms, size=28)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "data.show_batch(rows=3, figsize=(5,5))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "An example of multiclassification can be downloaded with the following cell. It's a sample of the [planet dataset](https://www.google.com/search?q=kaggle+planet&rlz=1C1CHBF_enFR786FR786&oq=kaggle+planet&aqs=chrome..69i57j0.1563j0j7&sourceid=chrome&ie=UTF-8)." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "planet = untar_data(URLs.PLANET_SAMPLE)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "If we open the labels files, we seach that each image has one or more tags, separated by a space." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
image_nametags
0train_21983partly_cloudy primary
1train_9516clear cultivation primary water
2train_12664haze primary
3train_36960clear primary
4train_5302haze primary road
\n", "
" ], "text/plain": [ " image_name tags\n", "0 train_21983 partly_cloudy primary\n", "1 train_9516 clear cultivation primary water\n", "2 train_12664 haze primary\n", "3 train_36960 clear primary\n", "4 train_5302 haze primary road" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df =pd.read_csv(planet/'labels.csv')\n", "df.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "data = ImageDataBunch.from_csv(planet, folder='train', size=128, suffix='.jpg', sep=' ',\n", " ds_tfms=get_transforms(flip_vert=True, max_lighting=0.1, max_zoom=1.05, max_warp=0.))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The `show_batch`method will then print all the labels that correspond to each image." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "data.show_batch(rows=3, figsize=(10,8), ds_type=DatasetType.Valid)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can find more ways to build an [`ImageDataBunch`](/vision.data.html#ImageDataBunch) without the factory methods in [`data_block`](/data_block.html#data_block)." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class ImageDataBunch[source]

\n", "\n", "> ImageDataBunch(`train_dl`:[`DataLoader`](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader), `valid_dl`:[`DataLoader`](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader), `test_dl`:`Optional`\\[[`DataLoader`](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader)\\]=`None`, `device`:[`device`](https://pytorch.org/docs/stable/tensor_attributes.html#torch-device)=`None`, `tfms`:`Optional`\\[`Collection`\\[`Callable`\\]\\]=`None`, `path`:`PathOrStr`=`'.'`, `collate_fn`:`Callable`=`'data_collate'`) :: [`DataBunch`](/basic_data.html#DataBunch)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch, doc_string=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Factory methods" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Normally we'll use one of the convenience wrappers below. However, these wrappers all accept a `kwargs` that is passed to the general [`DataBunch.create`](/basic_data.html#DataBunch.create) method (like `bs`, `num_workers`...)\n", "\n", "If you quickly want to get a [`ImageDataBunch`](/vision.data.html#ImageDataBunch) and train a model, you should process your data to have it in one of the formats the following functions handle. " ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

from_folder[source]

\n", "\n", "> from_folder(`path`:`PathOrStr`, `train`:`PathOrStr`=`'train'`, `valid`:`PathOrStr`=`'valid'`, `valid_pct`=`None`, `classes`:`Collection`=`None`, `kwargs`:`Any`) → `ImageDataBunch`\n", "\n", "Create from imagenet style dataset in `path` with `train`,`valid`,`test` subfolders (or provide `valid_pct`). " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.from_folder)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\"*Imagenet-style*\" datasets look something like this (note that the test folder is optional):\n", "\n", "```\n", "path\\\n", " train\\\n", " clas1\\\n", " clas2\\\n", " ...\n", " valid\\\n", " clas1\\\n", " clas2\\\n", " ...\n", " test\\\n", "```\n", "\n", "For example:" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "data = ImageDataBunch.from_folder(path, ds_tfms=tfms, size=24)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Note that this (and all factory methods in this section) pass any `kwargs` to [`ImageDataBunch.create`](/vision.data.html#ImageDataBunch.create)." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

from_csv[source]

\n", "\n", "> from_csv(`path`:`PathOrStr`, `folder`:`PathOrStr`=`'.'`, `sep`=`None`, `csv_labels`:`PathOrStr`=`'labels.csv'`, `valid_pct`:`float`=`0.2`, `fn_col`:`int`=`0`, `label_col`:`int`=`1`, `suffix`:`str`=`''`, `header`:`Union`\\[`int`, `str`, `NoneType`\\]=`'infer'`, `kwargs`:`Any`) → `ImageDataBunch`\n", "\n", "Create from a csv file. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.from_csv)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Create [`ImageDataBunch`](/vision.data.html#ImageDataBunch) from `path` by splitting the data in `folder` and labelled in a file `csv_labels` between a training and validation set. Use `valid_pct` to indicate the percentage of the total images for the validation set. An optional `test` folder contains unlabelled data and `suffix` contains an optional suffix to add to the filenames in `csv_labels` (such as '.jpg'). \n", "For example:" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "data = ImageDataBunch.from_csv(path, ds_tfms=tfms, size=24);" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

from_df[source]

\n", "\n", "> from_df(`path`:`PathOrStr`, `df`:`DataFrame`, `folder`:`PathOrStr`=`'.'`, `sep`=`None`, `valid_pct`:`float`=`0.2`, `fn_col`:`Union`\\[`int`, `Collection`\\[`int`\\], `str`, `StrList`\\]=`0`, `label_col`:`Union`\\[`int`, `Collection`\\[`int`\\], `str`, `StrList`\\]=`1`, `suffix`:`str`=`''`, `kwargs`:`Any`) → `ImageDataBunch`\n", "\n", "Create from a DataFrame. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.from_df)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Same as [`ImageDataBunch.from_csv`](/vision.data.html#ImageDataBunch.from_csv), but passing in a `DataFrame` instead of a csv file. E.gL" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
namelabel
0train/3/7463.png0
1train/3/21102.png0
2train/3/31559.png0
3train/3/46882.png0
4train/3/26209.png0
\n", "
" ], "text/plain": [ " name label\n", "0 train/3/7463.png 0\n", "1 train/3/21102.png 0\n", "2 train/3/31559.png 0\n", "3 train/3/46882.png 0\n", "4 train/3/26209.png 0" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = pd.read_csv(path/'labels.csv', header='infer')\n", "df.head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "data = ImageDataBunch.from_df(path, df, ds_tfms=tfms, size=24)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Different datasets are labeled in many different ways. The following methods can help extract the labels from the dataset in a wide variety of situations. The way they are built in fastai is constructive: there are methods which do a lot for you but apply in specific circumstances and there are methods which do less for you but give you more flexibility.\n", "\n", "In this case the hierachy is:\n", "\n", "1. [`ImageDataBunch.from_name_re`](/vision.data.html#ImageDataBunch.from_name_re): Gets the labels from the filenames using a regular expression\n", "2. [`ImageDataBunch.from_name_func`](/vision.data.html#ImageDataBunch.from_name_func): Gets the labels from the filenames using any function\n", "3. [`ImageDataBunch.from_lists`](/vision.data.html#ImageDataBunch.from_lists): Labels need to be provided as an input in a list" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

from_name_re[source]

\n", "\n", "> from_name_re(`path`:`PathOrStr`, `fnames`:`FilePathList`, `pat`:`str`, `valid_pct`:`float`=`0.2`, `kwargs`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.from_name_re)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Creates an [`ImageDataBunch`](/vision.data.html#ImageDataBunch) from `fnames`, calling a regular expression (containing one *re group*) on the file names to get the labels, putting aside `valid_pct` for the validation. In the same way as [`ImageDataBunch.from_csv`](/vision.data.html#ImageDataBunch.from_csv), an optional `test` folder contains unlabelled data.\n", "\n", "Our previously created dataframe contains the labels in the filenames so we can leverage it to test this new method. [`ImageDataBunch.from_name_re`](/vision.data.html#ImageDataBunch.from_name_re) needs the exact path of each file so we will append the data path to each filename before creating our [`ImageDataBunch`](/vision.data.html#ImageDataBunch) object." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[PosixPath('/home/ubuntu/.fastai/data/mnist_sample/train/3/7463.png'),\n", " PosixPath('/home/ubuntu/.fastai/data/mnist_sample/train/3/21102.png')]" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "fn_paths = [path/name for name in df['name']]; fn_paths[:2]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "pat = r\"/(\\d)/\\d+\\.png$\"\n", "data = ImageDataBunch.from_name_re(path, fn_paths, pat=pat, ds_tfms=tfms, size=24)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['3', '7']" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.classes" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

from_name_func[source]

\n", "\n", "> from_name_func(`path`:`PathOrStr`, `fnames`:`FilePathList`, `label_func`:`Callable`, `valid_pct`:`float`=`0.2`, `kwargs`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.from_name_func)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Works in the same way as [`ImageDataBunch.from_name_re`](/vision.data.html#ImageDataBunch.from_name_re), but instead of a regular expression it expects a function that will determine how to extract the labels from the filenames. (Note that `from_name_re` uses this function in its implementation).\n", "\n", "To test it we could build a function with our previous regex. Let's try another, similar approach to show that the labels can be obtained in a different way." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['3', '7']" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def get_labels(file_path): return '3' if '/3/' in str(file_path) else '7'\n", "data = ImageDataBunch.from_name_func(path, fn_paths, label_func=get_labels, ds_tfms=tfms, size=24)\n", "data.classes" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

from_lists[source]

\n", "\n", "> from_lists(`path`:`PathOrStr`, `fnames`:`FilePathList`, `labels`:`StrList`, `valid_pct`:`float`=`0.2`, `kwargs`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.from_lists)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The most flexible factory function; pass in a list of `labels` that correspond to each of the filenames in `fnames`.\n", "\n", "To show an example we have to build the labels list outside our [`ImageDataBunch`](/vision.data.html#ImageDataBunch) object and give it as an argument when we call `from_lists`. Let's use our previously created function to create our labels list." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['3', '7']" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "labels_ls = list(map(get_labels, fn_paths))\n", "data = ImageDataBunch.from_lists(path, fn_paths, labels=labels_ls, ds_tfms=tfms, size=24)\n", "data.classes" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

create_from_ll[source]

\n", "\n", "> create_from_ll(`dss`:[`LabelLists`](/data_block.html#LabelLists), `bs`:`int`=`64`, `ds_tfms`:`Union`\\[`Callable`, `Collection`\\[`Callable`\\], `NoneType`\\]=`None`, `num_workers`:`int`=`4`, `tfms`:`Optional`\\[`Collection`\\[`Callable`\\]\\]=`None`, `device`:[`device`](https://pytorch.org/docs/stable/tensor_attributes.html#torch-device)=`None`, `test`:`Union`\\[`Path`, `str`, `NoneType`\\]=`None`, `collate_fn`:`Callable`=`'data_collate'`, `size`:`int`=`None`, `kwargs`) → `ImageDataBunch`" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.create_from_ll)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Create an [`ImageDataBunch`](/vision.data.html#ImageDataBunch) from `dss` with `bs`, `num_workers`, `collate_fn` and a potential `test` folder. `ds_tfms` is a tuple of two lists of transforms to be applied to the training and the validation (plus test optionally) set. `tfms` are the transforms to apply to the [`DataLoader`](https://pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader). The `size` and the `kwargs` are passed to the transforms for data augmentation." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Methods" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

show_batch[source]

\n", "\n", "> show_batch(`rows`:`int`=`5`, `ds_type`:[`DatasetType`](/basic_data.html#DatasetType)=``, `kwargs`)\n", "\n", "Show a batch of data in `ds_type` on a few `rows`. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.show_batch)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Create a `rows` by `rows` grid of images from dataset `ds_type` for a `figsize` figure. This function works for all type of computer vision data (see [`data_block`](/data_block.html#data_block) for more examples).\n", "\n", "Once you have your [`ImageDataBunch`](/vision.data.html#ImageDataBunch), you can have a quick look at your data by using this:" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "data.show_batch(rows=3, figsize=(6,6))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In the next two methods we will use a new dataset, CIFAR. This is because the second method will get the statistics for our dataset and we want to be able to show different statistics per channel. If we were to use MNIST, these statistics would be the same for every channel. White pixels are [255,255,255] and black pixels are [0,0,0] (or in normalized form [1,1,1] and [0,0,0]) so there is no variance between channels." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "PosixPath('/home/ubuntu/.fastai/data/cifar10')" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "path = untar_data(URLs.CIFAR); path" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

channel_view[source]

\n", "\n", "> channel_view(`x`:`Tensor`) → `Tensor`\n", "\n", "Make channel the first axis of `x` and flatten remaining axes " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(channel_view)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "data = ImageDataBunch.from_folder(path, ds_tfms=tfms, valid='test', size=24)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "def channel_view(x:Tensor)->Tensor:\n", " \"Make channel the first axis of `x` and flatten remaining axes\"\n", " return x.transpose(0,1).contiguous().view(x.shape[1],-1) " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This function takes a tensor and flattens all dimensions except the channels, which it keeps as the first axis. This function is used to feed [`ImageDataBunch.batch_stats`](/vision.data.html#ImageDataBunch.batch_stats) so that it can get the pixel statistics of a whole batch.\n", "\n", "Let's take as an example the dimensions our MNIST batches: 128, 3, 24, 24." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "t = torch.Tensor(128, 3, 24, 24)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "torch.Size([128, 3, 24, 24])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "t.size()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "tensor = channel_view(t)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "torch.Size([3, 73728])" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tensor.size()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

batch_stats[source]

\n", "\n", "> batch_stats(`funcs`:`Collection`\\[`Callable`\\]=`None`) → `Tensor`\n", "\n", "Grab a batch of data and call reduction function `func` per channel " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.batch_stats)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Gets the statistics of each channel of a batch of data. If no functions are specified, default statistics are mean and standard deviation. " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[tensor([0.5008, 0.5082, 0.4419]), tensor([0.2257, 0.2271, 0.2537])]" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.batch_stats()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

normalize[source]

\n", "\n", "> normalize(`stats`:`Collection`\\[`Tensor`\\]=`None`, `do_y`:`bool`=`None`)\n", "\n", "Add normalize transform using `stats` (defaults to `DataBunch.batch_stats`) " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageDataBunch.normalize)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Adds the normalize transform to the set of transforms associated with the data. In the fast.ai library we have `imagenet_stats`, `cifar_stats` and `mnist_stats` so we can add normalization easily with any of these datasets. Let's see an example with our dataset of choice: MNIST." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "ImageDataBunch;\n", "Train: LabelList\n", "y: CategoryList (50000 items)\n", "[Category bird, Category bird, Category bird, Category bird, Category bird]...\n", "Path: /home/ubuntu/.fastai/data/cifar10\n", "x: ImageItemList (50000 items)\n", "[Image (3, 32, 32), Image (3, 32, 32), Image (3, 32, 32), Image (3, 32, 32), Image (3, 32, 32)]...\n", "Path: /home/ubuntu/.fastai/data/cifar10;\n", "Valid: LabelList\n", "y: CategoryList (10000 items)\n", "[Category bird, Category bird, Category bird, Category bird, Category bird]...\n", "Path: /home/ubuntu/.fastai/data/cifar10\n", "x: ImageItemList (10000 items)\n", "[Image (3, 32, 32), Image (3, 32, 32), Image (3, 32, 32), Image (3, 32, 32), Image (3, 32, 32)]...\n", "Path: /home/ubuntu/.fastai/data/cifar10;\n", "Test: None" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.normalize(cifar_stats)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[tensor([ 0.0399, 0.1080, -0.0195]), tensor([0.9139, 0.9346, 0.9719])]" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.batch_stats()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Data normalization" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You may also want to normalize your data, which can be done by using the following functions." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

normalize[source]

\n", "\n", "> normalize(`x`:`Tensor`, `mean`:`FloatTensor`, `std`:`FloatTensor`) → `Tensor`\n", "\n", "Normalize `x` with `mean` and `std`. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(normalize)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

denormalize[source]

\n", "\n", "> denormalize(`x`:`Tensor`, `mean`:`FloatTensor`, `std`:`FloatTensor`) → `Tensor`\n", "\n", "Denormalize `x` with `mean` and `std`. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(denormalize)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

normalize_funcs[source]

\n", "\n", "> normalize_funcs(`mean`:`FloatTensor`, `std`:`FloatTensor`, `do_y`:`bool`=`False`) → `Tuple`\\[`Callable`, `Callable`\\]" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(normalize_funcs, doc_string=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Create [`normalize`](/vision.data.html#normalize) and [`denormalize`](/vision.data.html#denormalize) functions using `mean` and `std`. `device` will store them on the device specified. `do_y` determines if the target should also be normaized or not." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On MNIST the mean and std are 0.1307 and 0.3081 respectively (looked on Google). If you're using a pretrained model, you'll need to use the normalization that was used to train the model. The imagenet norm and denorm functions are stored as constants inside the library named imagenet_norm and imagenet_denorm. If you're training a model on CIFAR-10, you can also use cifar_norm and cifar_denorm.\n", "\n", "You may sometimes see warnings about *clipping input data* when plotting normalized data. That's because even although it's denormalized when plotting automatically, sometimes floating point errors may make some values slightly out or the correct range. You can safely ignore these warnings in this case." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZ4AAAGoCAYAAAB2X4O/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzt3WmQlNXZ//FzZIdh33fZGfZNkEFZBFHZEY0ocUGjJlpxqVSq8sZopZJKmVRp+VgxTxKzPCpWJKkkRqOCIjJssu8wDPu+D/u+3P8XJv94/brthZk53TPz/VT54gfT3Qf6pi/vc/U5x0dR5AAACOWGTA8AAFCxUHgAAEFReAAAQVF4AABBUXgAAEFReAAAQVF4AABBUXiS8N6fkf+ueu9fz/S4kL24ZpAu7/073vsD3vtT3vtC7/13Mj2m0uRZQJo6732Oc+6gc25MFEX5mR4Psh/XDFLhve/unNsaRdFF731X59wXzrmxURStyOzISgd3POmZ4pw77Jybn+mBoMzgmkFSURRtiKLo4n/iv//rkMEhlSoKT3oeds69FXGbiNRxzSAl3vs3vPfnnHMFzrkDzrmPMjykUsNUW4q8922dc9udcx2jKNqR6fEg+3HNIF3e+0rOucHOueHOuZejKLqc2RGVDu54Uvegc24BHyBIA9cM0hJF0dUoihY451o5576X6fGUFgpP6h5yzv1fpgeBMoVrBtersqPHU7F57/Occy2dc3/J9FhQNnDNIFXe+ybe+6ne+xzvfSXv/R3Oufudc3MyPbbSUjnTAygjHnbO/S2KotOZHgjKDK4ZpCpyX02r/a/76mZgl3PuuSiK/pnRUZUivlwAAAiKqTYAQFAUHgBAUBQeAEBQFB4AQFBBv9Xmvc/qbzJ4702uXNn+9dxwQ2ydbtiwockDBw40uVmzZiZfvmwXIutr9unTx+Rdu3aZnJ9v95lcvny5yVevXo0Z49dFUeQT/kAWyfbrpSIoS9eLc1wz2SCVa4Y7HgBAUBQeAEBQFB4AQFDsXPA1derUMblVq1Ym165dO+YxeXl5Jj/22GMmt2zZ0uSjR4+afO7cOZO7dOli8u7du01u3759wjF99tlnMWNEamrUqGFy//79Ta5WrZrJe/fuNVnfq/Pnz5fg6OKrW7euyTVr1jRZ+5JFRUUmX7hwwWQWlCME7ngAAEFReAAAQVF4AABBVageT7du3UweP368ybfffrvJbdq0MblWrVoxz9moUSOTq1SpknAM2kdKpkMHeySH9hl0Dp8eT+q0H9K3b1+Tf/Ob35i8b98+k2fPnm3y4sWLTd66dWvSMXTs2NFkfb91HVj16tVN1r7UlStXTD548KDJs2bNMvnAgQMmnz17NsmIkWmVKlUyuWnTpiZfvHjR5OPHj5t87dq10hlYGrjjAQAEReEBAARF4QEABBW0x6NrVLTfUbVqVZO1X5Ls93Xdha7Dadeuncm6JqZJkyYJX0/3VYv3a7oOIt5jikP3hmvbtm2JPn9Foj27G2+80WTt8Wn/Ra9f/X3tr6Tyms2bNzdZ1+noNak9P/03sXPnTpN1HdmyZctM3r59e8yYkV0aN25s8rvvvmuy9nSeffZZk3W9WSZwxwMACIrCAwAIisIDAAgqaI/n6aefNlnnKovb49E5dp0f158/ffq0yWvWrDG5sLDQ5CNHjji1Z88ek/v162fysGHDTNY+U7o2bdpk8vvvv2+yfsc/2fk8FZn233QNzPr1601u3bq1ybouTM9SSqW/p+uwtEdY3L3TDh8+nPD1SroHiZKn/6ZffPFFk3X92Y4dO0zW9WrZgDseAEBQFB4AQFAUHgBAUEF7PE8++aTJly9fNln3GNI9hfTntUejCgoKTN6/f7/JW7ZsMXnp0qUm6xqIeK938uRJk3XfJF1nka5FixaZPGPGDJNnzpxpcjbsw1RW6JqWf/3rXyZrP017lD179jRZ59L1enUu9vybZFl7MHr+Um5ubsIx6JlA+vzxxojM0XVczjk3evRok3VPSf03r73IRx991OQFCxaYvHLlSpP1c7I0PlO44wEABEXhAQAEReEBAAQVtMejPRU930TPBrl06ZLJ586dM3nXrl0mN2jQwOS1a9cmfH3dSyve3lrJ6P5zOr9av379tJ5P193o35H2rXRfpuKu+6hIdO5az6LZuHGjyU899ZTJAwYMMFnXjcVbI6Pvr2YdU8uWLU0ePHiwybrXm/YhdU2Hzt+fOnUqZowoPS1atDBZ95OcOnVqzGNGjBiR8DHat9P3vHfv3ibrekZdW7h582aTdT+/oqIik6/nM4c7HgBAUBQeAEBQFB4AQFBBezz6fXTtT+iag2xTuXLsX9eoUaNM1rUd1atXN1nnQ3Xtkn6n/osvvjBZ15awbqfk6Huje7epVatWJXx8vH3ykr1fOv8+ZswYk3Wdh64T0/n55cuXm6xr006cOJFwPCgefT/vvfdek2+55RaTR44cGfMcyXqHep3qZ4b2hPSaeeKJJ0zWPTR/9rOfmfzmm2+arL3RVHDHAwAIisIDAAiKwgMACCpoj0fXyZS1/kS8NTlDhgwxuWPHjibrfKzujaVz8u+9957Jn3zyicnXs9YIpUPXmZUEPeNH1woNGjTIZN27bfv27SZrH0rXwqF06RoZ7afoOkA9LykVeh3qa+par7Zt25pcr169hGN49dVXTV6yZInJX375Zcpj/f+vkfYjAAAoBgoPACAoCg8AIKigPZ6y1tNRevaJc7Hfkdc5d6U9ng8//NBk7enovkso3/r06WNy9+7dTdY1HWfOnDFZ18bpOp1ka5NQsr797W+brP2X6+npKO3RTJgwwWTtMyfLyZTEGU7c8QAAgqLwAACCovAAAIIK2uPJdjrXqfus6b5ZzsX2eNJ9jdWrV5t89OjRtJ4PZUulSpVMrlWrlskDBw40WXs8evbKmjVrTC4sLDR57969JpfG2iN8M33/9P1X8d6fDRs2mKzraLZt22by9OnTTS7uWiE9s0n3+7se3PEAAIKi8AAAgqLwAACCosfzNTVr1jT5ueeeM1m/H+9c7BnqStcu6Xfg9ffL+lonJKY9wVtvvdXkfv36mdywYUOTdV3XRx99ZLL2DI8dO3Zd40TJ+MMf/mCyntel/95ff/31mOfQM7r0c2rq1KkmN23a1ORkPR09R2r37t0m//znPze5JM5w4o4HABAUhQcAEBSFBwAQFD2er9Hv2N95550mt2nTJuYxVatWTficev7J0qVLTdbvxF/P+eXITvH2wNLzdr773e+arOc5nT9/3mRds/HBBx+YzN5+2SU/P9/kl156yWTdO2/58uUxz6HngE2ePNnksWPHmtygQQOTk+3Fpq/529/+1uS3337b5KtXryZ8vlRwxwMACIrCAwAIisIDAAiKwgMACKpCf7lAF2LpIVxt27Y1WTcNjUcXY2lzeN68eSYfOXLEZA7qKj9ycnJifk0XkObl5Zmsjdtkm3wmW5CMsPQzQg/uO3DggMnVqlUzedy4cTHPqYuM77rrLpP1cyyZkydPmvzyyy+b/Pe//91k/UwrCdzxAACCovAAAIKi8AAAgqpQPZ7Kle0fV3s4jzzyiMl16tQxOd5me9qT0YPcdMGo9nh0vhXlx8iRI2N+TefrtaejWRf3ffbZZybrIV0oXfoZoJu49ujRw2Rd3Pn444+brAcBpntI2/UoKCgwedasWSaXRk9HcccDAAiKwgMACIrCAwAIqkL1eOrVq2fyoEGDTL777rtNjrcOQ50+fdrkFStWmPzqq6+arD0fXZeBskPn53Nzc03W9RbOOTd48GCTz5w5Y/LatWtNnj9/vsmLFy82WTehRcnSDTYbNWpk8uzZs03u0qWLybqJcLINO0No1qyZydr7DoE7HgBAUBQeAEBQFB4AQFAVqsfTunVrk8ePH2+y7nmUynfqda+1ZcuWmazrdlB+NG7c2GTt6fTv3z/mMbpX2+HDh03WHqH2fLZs2ZL2OHH9tP8xYMAAk7t27WpysoMhs4F+Dup+cSFwxwMACIrCAwAIisIDAAiqXPd4dO6yXbt2JuucfKVKldJ+De0DZeI78cgM7fGMGDHC5JYtW8Y8Rs/P0R7hunXrTD548GBxhogSpuft6Loc3efs0KFDJm/bts3ks2fPmhxv78YFCxYk/BndL/LJJ580Wc980s+5TJzhxB0PACAoCg8AICgKDwAgqHLdkNA59t69e5us87XXo6ioyOQNGzYU+zmRnRo0aGCyXl/t27c3Wfdycy72vKbCwkKTdd3X3r170x4nSo6ej6Q9uF/84hcmd+rUyeS5c+earOuwzp8/b7L2fJxzbteuXSZrn1DX5VSpUsXkZPvDaY8oBO54AABBUXgAAEFReAAAQZXrHk/z5s1N1h5PuuJ9x17nbPW8HZQfffv2NVnX7dSvX99knWt3zrlPP/3U5D//+c8m67oPzmsqXcnW4enfv/57f+GFF0zWtYI7d+40Wdf5XA/tHd53330md+7c2WT9M+q6HXo8AIByj8IDAAiKwgMACKpc9XhatGhh8qBBg0zu169fWs+n87HxzkJZtGiRyXv27EnrNVB29OnTx2TdA0vPYol3npP2DLRvqGs0ULpq165tsq7DWb58eVrPt2PHjmKNJ15fUNeP6R6TTz/9dMKf18+xNWvWmHzx4sW0x1lc3PEAAIKi8AAAgqLwAACCKlc9njp16pis63h07jOZ/fv3m5yfnx/zM7oXUya+E48w6tWrZ3LDhg1NjtfTSfYcut8be/2Vrrp165o8bdo0kx977DGTR44cafKJEyeK9fp6jWhfsFevXjGPmTRpksnPPPOMyTVr1jQ52dqjn/zkJyZnoq/IHQ8AICgKDwAgKAoPACCoctXjOX78uMmrV682eeHChSbn5uaafObMGZO1f/P+++/HvGZBQUHa40TZVK1aNZOTnXMST05OjsnNmjUr1piQHu3xDBkyxOQOHTqY/NBDD5k8Y8YMk/UaqFGjRsLXa9Wqlcn33nuvyVOmTIkZs/aulZ4ZpGuPfvCDH5i8ZMmShM8XAnc8AICgKDwAgKAoPACAoMpVj0fPMvnrX/9q8rJly0zW78drD2jjxo0mF/c7/CjbtMeTyrodpXv5bd++3WT2aitdFy5cMHn37t0m67qa73//+ybfcccdJmtPR8/K0Z6e7g2nZzjpmpxU6OfW1KlTTT548GDaz1nauOMBAARF4QEABEXhAQAE5UviDHAAAFLFHQ8AICgKDwAgKAoPACAoCg8AICgKDwAgKAoPACAoCg8AICgKDwAgKAoPACAoCg8AICgKDwAgKAoPACAoCg8AICgKDwAgKAoPACAoCg8AICgKDwAgKAoPACAoCg8AICgKDwAgKAoPACAoCg8AICgKDwAgKAoPACAoCg8AICgKDwAgKAoPACAoCg8AICgKDwAgKApPEt77M/LfVe/965keF7Kb9/4d7/0B7/0p732h9/47mR4TslNF/IzxURRlegxlhvc+xzl30Dk3Joqi/EyPB9nLe9/dObc1iqKL3vuuzrkvnHNjoyhakdmRIZtVlM8Y7njSM8U5d9g5Nz/TA0F2i6JoQxRFF/8T//1fhwwOCWVDhfiMofCk52Hn3FsRt4lIgff+De/9OedcgXPugHPuowwPCdmvQnzGMNWWIu99W+fcdudcxyiKdmR6PCgbvPeVnHODnXPDnXMvR1F0ObMjQraqSJ8x3PGk7kHn3ILyfkGgZEVRdDWKogXOuVbOue9lejzIahXmM4bCk7qHnHP/l+lBoMyq7OjxILEK8xlD4UmB9z7POdfSOfeXTI8F2c9738R7P9V7n+O9r+S9v8M5d79zbk6mx4bsVNE+YypnegBlxMPOub9FUXQ60wNBmRC5r6bV/td99T93u5xzz0VR9M+MjgrZrEJ9xvDlAgBAUEy1AQCCovAAAIKi8AAAgqLwAACCCvqtNu8932TIsCiKfKbHkKqyfr1UqVIl5tc6depk8tixY02+//77Te7Vq5fJp06dMvkvf7Hfvn3ttddM3rhxY2qD/QZl6XpxruSvmcqV7Udk9erVTb5y5YrJly5dMvnatWsJn997+9dbqVKlmJ+54QZ7f1C1atWEj9Gsj9cvlOmYz5w5k/Dnk0nlmuGOBwAQFIUHABAUC0iBUnL5cux+oFu3bjV53rx5Jo8ePTqt1+jcubPJFy9e/IafRCp0Km3AgAEmP/vssyavWbPG5Lfeesvk3bt3m6xTa/Xr1ze5R48eMWNq3769yWPGjDG5Xbt2JnfoYHdmqlWrlsk6Pfj555+b/MADD5h8+nTJr2nljgcAEBSFBwAQFIUHABAUPR4gIP0qrPYUWrZsmfDxZ8+eNXnnzp0mHzp06PoHB9e8eXOTf/zjH5ucl5dn8qhRo0yeNGmSyTt22KN19P3X/kyTJk1ixqRf6a5Ro0bC39esfSX9mn/Dhg1NzsnJMZkeDwCgzKPwAACCovAAAIKixwMEpD0d7Sm0bdvWZN1yZdu2bSYvXLjQZN3uBOnRfsbixYtNHjZsmMk1a9Y0uWfPnibrOivtt+j1oNvbOOfchQsXTD5y5IjJulZI1wa1adPG5Nq1a5us63xatWpl8oEDB2LGVFzc8QAAgqLwAACCovAAAIKixwOUknhrMvRYBN2bS7e0LyoqMlmPQZgzZ05xhghx8uRJk2fMmGGyrnHp06ePyXXr1jVZ+y26f5/27AoKCmLGpD2cvXv3mqw9nwkTJph87733mqw9Ht27TY/eKA3c8QAAgqLwAACCovAAAIKixwP8W506dUzWfbl0jyydj9+3b5/Jd999d8xr6F5e2iPYtGmTya+++qrJenYKe7OVLO3BbNmyxeRXXnnF5C5duphcr149kxs0aGCyHjOt5zNpz8c5544fP57wOZRet7p2SI+yPn/+vMnHjh1L+PwlgTseAEBQFB4AQFAUHgBAUPR4UGHoOSTNmjUzefr06SbrWSs6/5+fn2/y9u3bTX7++edjxtCiRQuTV6xYYfLMmTNN/uSTT0w+evSoybqXG0qW9kO0j6c5E/SMnw4dOpisa4t0Pz+9brXnUxq44wEABEXhAQAEReEBAARFjwcVhu6DpmsudF8tPaekdevWJusaDl0voc/nXOy+W2+88YbJixYtMpmeDpLR83b0DCC9jnWt2KxZs0w+e/ZsCY4uPu54AABBUXgAAEFReAAAQdHjQYWh63D2799v8t/+9jeTdc+qcePGmaxz6XrOSTyNGjUy+fbbbzf53LlzJus6ksOHD5usfyZUPIMGDTK5efPmJmvvUc/bOXjwYOkMLAHueAAAQVF4AABBUXgAAEHR40GFcfXqVZO1h7Ny5cqEv79x40aTJ0+ebLKeg6Jz7c45l5OTY/KYMWNM1vNbdD+5L774wmTdZ4t1PuXfDTfY+4W77rrL5CZNmph84sQJkxcsWGDykiVLSnB0qeGOBwAQFIUHABAUhQcAEFRW9Xj0zHs9u6Rx48Ymr1+/3mT9frrOhdasWdNkPZ9F9yi6ePGiycyfl2/6/mtPR/Onn35qsvZ4Jk2aFPMaw4YNM/nGG280eeLEiSZ37NjRZL2G//jHP5p8+vTpmNdE2aZ7DN52220m33zzzSZrH1H3/5s7d67JIfZmU9zxAACCovAAAIKi8AAAgsqqHo/ufTV27FiTc3NzTda5yqVLl5qs+1zpfLlmPafiyJEjJut5LM7F9pF0vlT7SE2bNk3480VFRSZv27bN5F27diV8PMLRs+sXL15ssr6XzsW+n7oGY8CAASZ369bN5GnTppmse7u9++67Jp8/f95k/TeB7KefMfo5qL1xfY/XrVtnsvbGM3FNcMcDAAiKwgMACIrCAwAIKqt6PPXq1TNZv58+atQok6dMmWLy7NmzTdazxjt16mRy3bp1TT5+/LjJOkev51o459yFCxdM1p6LntGiY9AxKj0j5oUXXjB5y5YtJrPWKBydG9d1ZMuWLYt5zM6dO03WM4Fq1Khhcv/+/U3u2rWryRMmTDBZr+FZs2aZrNcnPZ/sov0c52LPcLrzzjtN1s8Q3b9Pe496plMmcMcDAAiKwgMACIrCAwAIisIDAAgqq75coI1W3ZRRN1jUxZl33HGHydo41axfFtBDtzTH+3JBcZuz+nj9csCgQYNM1kOetFmtG5siu+ii5Hnz5plcvXp1k/X91C8b3HTTTSbroV979uwxee3atSbrl2OQWfr+Oxf7JSv9TNDHrFq1ymRdQHrp0qXiDLFEcMcDAAiKwgMACIrCAwAIKqt6PNqv+PDDD03u2bOnyV26dDFZ+x+VK9s/XrweTSK6IHDFihUxP6OLXnUDv3hztl+nc/iFhYUmv/feeyavXr064ePxX7oYU/tp2dDfOHjwoMn5+fkm169f3+SBAwearIcj3nLLLSbrglJdcJwNfwf4L11w7pxzkydPTvgz+hmgfTy9xrIBdzwAgKAoPACAoCg8AICgsqrHo4da6Xy3zl1qP+XBBx80+a233jL55MmTJusmoZq1RxTv0LVbb7014ZiS0cPsfvWrX5n8+eefm5wN38EvKwYPHmyyHqqm14P2z7QfonPpJbHB5tWrV03WvuLp06dNrlatWsLn0/n/SpUqmaw9H2SWbgqqfWrnnBs+fLjJ+p5qX3jJkiUmHz16tBgjLB3c8QAAgqLwAACCovAAAILKqh6P0vnvY8eOmbxgwQKTFy5caLLOnybbq01/Xn+/Xbt2MWNs2bKlycnW7agf/ehHJm/atMlkDnZLXevWrU1+++23Tdb3Xw/E0h7PnDlzTF6+fLnJhw4dMln3Sbse+n5r31HX3ej1duXKFZN1/0NkF31/8/LyYn6mVatWCZ9jzZo1Juv+fPo5mg244wEABEXhAQAEReEBAASV1T2edOkcfrpzm/rzumaiT58+MY+ZMGFCwufUOfeCggKT9cyhklgbUlHpGpZFixaZPHHiRJP1vKVevXqZPHToUJPnz59vsu4tqOsl4q2f0L6Q7qOla4V0LdmuXbtM7ty5s8l6zeo13aBBA5OLiopixohwdK/H3r17J32MfkboWkDtXWYj7ngAAEFReAAAQVF4AABBlaseT0nTvb3uvPPOmJ/ROXOlPZxf/vKXJtPTKTm6t9rrr79usu6Dpusj2rdvb7Ku0Zo2bZrJuq4sWXbOuXXr1pm8bds2k8+cOWNy//79Ta5Tp47J2sPRnqI+X05Ojsn0eMLSfda6du1q8vjx42Meo2u7tLeoe7PpdZ6NuOMBAARF4QEABEXhAQAERY8nAZ3THzduXNLH7N271+R33nnH5I8//rj4A0Ncly9fNlnPb/r1r39tcvPmzU3WdVrTp083uU2bNibruiE9KyneeooqVaqYrOs2dAwtWrQwWfcT1P3lFi9ebLL+Hej5PghL1+3o2jFdW+ZcbB9Y33NdL1YW9nfkjgcAEBSFBwAQFIUHABAUPZ6v0XU6mnV+Nh5dt5Ofn2/yyZMnr3N0SJeej6Pn6agPPvjA5Lfeestk3RdNez41atQwWa+FeGPS/eNyc3NN1p6grrvR+f7Zs2ebfOTIEZOz8WyWiqRx48Ymd+rUyWRd5+NcbO/wyy+/NPncuXMlNLpwuOMBAARF4QEABEXhAQAERY/na3RvttatW5vsvU/6HPPmzTN5x44dxR8YMkLPvtF8PfR8He356PWje61pz0bXcLBOJ7vVr1/fZN0PMB7ty23atMlk7QGVBdzxAACCovAAAIKi8AAAgqrQPZ4mTZqY/Nxzz5lcq1Ytk+PtgaRz7DNnzjSZ807wdXpezvbt2xNmlC/VqlUzWdd+xfuM0b7dnj17TNZrqizgjgcAEBSFBwAQFIUHABBUherx1KxZ0+S8vDyTk+3FFq9f88orr5is56EDwH/oZ0hhYaHJrVq1innMkiVLTN6yZYvJeg5VWcAdDwAgKAoPACAoCg8AICiv53kDAFCauOMBAARF4QEABEXhAQAEReEBAARF4QEABEXhAQAEReEBAARF4QEABEXhAQAEReEBAARF4QEABEXhAQAEReEBAARF4QEABEXhAQAEReEBAARF4QEABEXhAQAEReEBAARF4QEABEXhAQAEReEBAARF4QEABEXhAQAEReEBAARF4QEABEXhAQAEReEBAARF4QEABEXhSYH3/h3v/QHv/SnvfaH3/juZHhOyG9cM0lHRrhcfRVGmx5D1vPfdnXNboyi66L3v6pz7wjk3NoqiFZkdGbIV1wzSUdGuF+54UhBF0YYoii7+J/77vw4ZHBKyHNcM0lHRrhcKT4q8929478855wqccweccx9leEjIclwzSEdFul6YakuD976Sc26wc264c+7lKIouZ3ZEyHZcM0hHRbleuONJQxRFV6MoWuCca+Wc+16mx4PsxzWDdFSU64XCc30qu3I8/4pSwTWDdJTr64XCk4T3von3fqr3Psd7X8l7f4dz7n7n3JxMjw3ZiWsG6aiI1ws9niS8942dc391zvV2XxXqXc65/4mi6HcZHRiyFtcM0lERrxcKDwAgKKbaAABBUXgAAEFReAAAQVF4AABBVQ75Yt57vsmQYVEU+UyPIVWhr5cbbrD/H3bt2rUSf42cnByTf/jDH5r8+OOPm9ywYUOTn3/+eZP/8Y9/mLx///7iDtEoS9eLcxXjMybEdVocqVwz3PEAAIKi8AAAgqLwAACCCtrjAbJZSc+VN2rUKObXhg8fbvLo0aNNrlevnskbNmwwee/evSafO3euGCNEaatbt67JXbt2Nblbt24mN2nSJOY59D1ftmyZyYWFhcUZYkZwxwMACIrCAwAIisIDAAiKHg9wnWrUqGFymzZtTB48eHDMYyZOnGhyr169TNb5/JkzZ5q8efNmk+nxZLfGjRubPH78eJMfeughk5s3bx7zHLpWS/uAN998s8l6TZw9e9ZkvcbWrVsX85qljTseAEBQFB4AQFAUHgBAUPR4gBS1bNnS5J49e5o8YMAAk2+99daY5+jdu7fJuk4nPz/f5N///vcmHz9+3OQrV64kGDFC02tE+y+DBg0yuWbNmibHO5gzLy/P5P79+5vcoEEDk2fPnm3yzp07TV6zZo3Jur9fUVFR0jEVF3c8AICgKDwAgKAoPACAoMr/xSmCAAAM9UlEQVR1j0e/796hQweTL126lDDr3GalSpViXqNKlSomX7hwwWT9Tv2pU6dMPn36dMLXROb07dvXZJ2fHzZsWMLfj7cmQ/fV+vjjj03+05/+ZPKRI0dSGiuyQ7NmzUweOnSoydoXrF27tsnx/v3rmUzJ9hTUXmOnTp1M1r6S9nz0M0k/F0sCdzwAgKAoPACAoCg8AICgylSPR/spenaFfp9d59zvu+8+k3UNhGbdi0u/o+9c7Pypnoeuc7arVq0yecqUKSbv2bPH5Gw7Tz2beG+Pdq9Vq5bJbdu2NfnGG29M+Hzaw7vttttM/ta3vmWy9hD1vY9H1+Hs3r3b5H379iV9DmSPLl26mDxy5EiThwwZYnJOTk7ar6HXebxe89fp51T9+vVN1mtM9xjUvdzo8QAAyjwKDwAgKAoPACCorOrxaA9Hzytv3769yffcc4/Jui+Snm/eqFGj4g4xbTo/q9/bb926tck6/0qP55vp3HT37t1N1jUUw4cPN1l7QLpeQufSS2JftM6dO5s8depUk3v06GGy9vwKCgpMXr9+vcm6Tuz8+fMmX7x4MfXBIqnq1aub3K5dO5P1M0c/40qDXqe6bifZnoMbN240+cSJEyU4uq9wxwMACIrCAwAIisIDAAgqaI9H1znoOpmOHTuaPHnyZJN1Plz3Xkv2/fZsoH9mnfNfunRpyOGUabpX2lNPPWWynn2TbB88/X2d2z548KDJui+fXn/xrsfKle0/udzcXJO1x6M9v+XLl5usfSkdoz5ez145c+aMyZzvkx7di1Hfc91rT/++Dx06ZLKenRPvOfS61Ne86aabTNbepu4hePvtt5s8b968pGMqLu54AABBUXgAAEFReAAAQQXt8eialenTp5s8ceJEk/U78boXV0n3dHQNhH6fffHixTGP0Tl73Q9O95O7fPlywtfkPJ5vpmsmdC5brxel7+eWLVtM1v7HsWPHTE72Xul6Cc3OxV7DrVq1MlnXFumai/vvv9/kadOmmXzgwAGTFy1aZPKCBQtM1p7Rpk2bYsaMb6Y9tBkzZpis74ee17Njxw6T586dG/Ma2ge6evWqybpesUWLFglGHHvd6tow7V2WBu54AABBUXgAAEFReAAAQQXt8Tz88MMmP/300ybrPma6r5Hue5aM7kt1+PBhk+fPn2+y9nBWr15tsu6b5ZxzderUMVnXlmiPp2rVqiY3bdrU5HT/jBWJroGaM2eOybpO7OzZsyYXFhaarOsj9PrQrD+vPZ/roftk6ZlBOn+vZ0zpeVDaE9L9C/V61Z6D/htEYrqOR9fhaT9F9588evSoyfHWzOjaH+3x6FqwdGmfiR4PAKDcofAAAIKi8AAAggra43n00UdN1n2mktF9pHQOXufw16xZY/KyZctMXrlypcnaw9G5Tu0xOBe7NinZeRu69qhevXoJfx7/pWfLrFu3zuTTp0+bXFRUZHKy9QqZWEO1e/duk48fP26yrgPRa1T3K+zbt6/J3bp1M3nw4MEm6xlX1apVSzJiJKLXaH5+fom/hq796tWrV8KsPaFkexLS4wEAlDsUHgBAUBQeAEBQQXs8bdq0Sfj7Oveoc/a6t9b7779vss6n6t5c+p15petAGjRoYPLAgQNjHvPII4+YrGdd6J9J+1KffvqpyZyH8s107nnbtm0Jc1lw8uTJhHnv3r0ma1+rUaNGJuu/kTFjxpg8ZMgQk7VHOXr06CQjRmmK1yNu3LixydrD6d69u8m6tks/g/TfkWZd/1gauOMBAARF4QEABEXhAQAEFbTHo99x17lHnd/WvdPeffddkz/55JOEz6/07Bw9L0XnUm+77TaTn3jiiZjn1HUT2ifS+VNdh6GZ83hKj+6Lp2ff6BorPatGz1LKhEuXLpmsZwZ9+eWXCX9e13RMnTrVZF3Xg5Kl66T0M0fXZTnnXF5ensm9e/c2WXs+em5VsnU8en6P9uJ1rzjtvV8P7ngAAEFReAAAQVF4AABBUXgAAEEF/XLBggULTL527ZrJH3zwgcmzZs0yOd0Fgvrlgc6dO5v8wAMPmDxixAiTdSGWHqKVCv3ywNy5c03WL1Tw5YKSo18m0MWT2tjdvHmzydnwZQKl14cuONYvs+jBg/p4/TJMrVq1ijtEfI1+mUAb+QMGDDBZv6zknHP9+vUzWQ8L1EXESr80o4dTTpo0yWS9JnThPV8uAACUORQeAEBQFB4AQFBBezw6l6h0vjrdDTO99ybrAtA333zTZO3Z6AZ9Otd5PXRBni7Y0wV/mrUPhtTpAtHJkyebvHbtWpMXLVpU6mNKl/Ypc3JyTK5du7bJzZo1M/mee+4xedSoUQlfTzeIjHf4IVKnnzE9evQwWfvMelCfc87Vr1+/RMekfT/9jOrTp4/JO3bsMLkkNuPljgcAEBSFBwAQFIUHABBURjcJLWl33XWXyc8884zJ+n33kujhJKPfoe/Zs6fJr732msnaBztw4IDJ9Hy+mfZDdM2EzmXrIWs6v37kyBGTdY3MwYMHE75+PMn6mPpvpGHDhibrhpD9+/c3Wefn9ZAwHWNRUZHJetAcB8Mlpj2wjh07mjxs2DCTb775ZpNzc3NNTuUaSkY3jtV1N9rjqVu3rsl6zeg6Hu3xbN26Ne0xcscDAAiKwgMACIrCAwAIKmiPp6TpXOXw4cNN1vnudHs6egDS/v37Y35GD9rSg5x0Dlj3btK+gz5e51d1nQX+S/cZ0+tD927TvfjOnTtnsvbXDh8+bLL2fFq3bm2yvtfOxV6Dug4n2T5czZs3N1n/DNpD0B6S/pl27dplsh6+SI8nsQYNGpisPbiJEyearHux6TUb7zNK+3CbNm0yedmyZSbr55Q+p47hpptuMln7VLq+ccuWLSbrfpOp4I4HABAUhQcAEBSFBwAQVJnu8ajdu3ebrPPXlSvbP66u41ixYoXJq1atMnnnzp0xr6k9lwcffNDkkSNHmqx9Bp0/HThwoMlr1qxJ+Hr4Znqejq6RGTt2rMmDBg0yWdfx6PUydOhQk3VfLu3/xfs17UPpmVHa86lXr57J2kfS+Xz9M2s/QM/IWr16tckvvviiw39pj03Xfk2ZMsVk/fdcvXp1k/X90T6ic84VFBSYrO+h7jGofWG9JvSMMB3DI488YrJ+Zulnmu55mArueAAAQVF4AABBUXgAAEGV6R6Pzpf/85//NFnn6PX76zpXmp+fn/Dxqbh69arJeiaMzpfq3mu6rxJ7s6XuxIkTJuvc80svvWSyvhfa49F1OW3atDG5S5cuJutZONq/cS72+oiiyGS9prUvqdek7pO1efNmk/V60rNV1q9fb7Ku0YDVsmVLk/V8I92LMd418HUbNmwwed68eTE/o59L2otO93NK1wXpWkKl+8e1a9fO5Os5L4g7HgBAUBQeAEBQFB4AQFBlusejdB2P5vfee6/Ux6Bz9Nqj0Tl9nYNfuHChybofGL6ZrtvRPatOnTplss5N63unc9lDhgwxWffV07OX4u27pWsydO+0s2fPmqxnq+h+cnomkPYM9u3bZ7L+nRw/ftxkvT5hJVt3pT25Q4cOmVxYWGjy/PnzTda98pxL3rdLl/YZk60N9N6brGvJdL/BVHDHAwAIisIDAAiKwgMACKpc9XhKm851Ohe799KIESNM1nU8Ooev38nXOXk9TwWp0z2odC5b+yVz5841WfctW7lypcmtWrUyWc9madiwYcyYdH5ezzLRNRY6Bv35ZPvRad9Kf18fj8S0R/O73/3OZD1/Rz8fdF81XbejPTrnYs8FKy5db6Zrk5LR3qX+GVN6jrQfAQBAMVB4AABBUXgAAEHR40mD7lnknHN33323yU888YTJen6H7g/305/+1GRdV4GSo2uqtN+2bdu2hI9fvnx5Wq8Xbw+runXrmpxsflyvB+3R6DqveGcAoeTo+6HrbnQvPO2h6Xk7us9aaazb03OitKeja5GS2bhxo8nad0wFdzwAgKAoPACAoCg8AICgylSPJ9leWLrmJdm+U/p4Pd8+Ly/P5PHjx8c8x7hx40zWOXvdF0n3btL95FB+xOvX0cMr2/Tf886dOxPmbKDrdjp27Ghy9+7dTdbPTe2F6n6Duv9fKrjjAQAEReEBAARF4QEABJXRHo/2bHr06GFybm6uyfr988aNG5us/RPdF0vX4bRp08bkgQMHmqznregaDOecq1GjRsyvJRqDnnGv3+sHgHToGUEtWrQweejQoSZPmjQp4c/rnpTaw9Eej65dSgV3PACAoCg8AICgKDwAgKA8Z6wDAELijgcAEBSFBwAQFIUHABAUhQcAEBSFBwAQFIUHABAUhQcAEBSFBwAQFIUHABAUhQcAEBSFBwAQFIUHABAUhQcAEBSFBwAQFIUHABAUhQcAEBSFBwAQFIUHABAUhQcAEBSFBwAQFIUHABAUhQcAEBSFBwAQ1P8DRpRNtUJxaq4AAAAASUVORK5CYII=\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "data = ImageDataBunch.from_folder(untar_data(URLs.MNIST_SAMPLE),\n", " ds_tfms=tfms, size=24)\n", "data.normalize()\n", "data.show_batch(rows=3, figsize=(6,6))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

get_annotations[source]

\n", "\n", "> get_annotations(`fname`, `prefix`=`None`)\n", "\n", "Open a COCO style json in `fname` and returns the lists of filenames (with maybe `prefix`) and labelled bboxes. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(get_annotations)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To use this dataset and collate samples into batches, you'll need to following function:" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

bb_pad_collate[source]

\n", "\n", "> bb_pad_collate(`samples`:`BatchSamples`, `pad_idx`:`int`=`0`) → `Tuple`\\[`FloatTensor`, `Tuple`\\[`LongTensor`, `LongTensor`\\]\\]\n", "\n", "Function that collect `samples` of labelled bboxes and adds padding with `pad_idx`. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(bb_pad_collate)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Finally, to apply transformations to [`Image`](/vision.image.html#Image) in a [`Dataset`](https://pytorch.org/docs/stable/data.html#torch.utils.data.Dataset), we use this last class." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## ItemList specific to vision" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The vision application adds a few subclasses of [`ItemList`](/data_block.html#ItemList) specific to images." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class ImageItemList[source]

\n", "\n", "> ImageItemList(`items`:`Iterator`, `path`:`PathOrStr`=`'.'`, `label_cls`:`Callable`=`None`, `xtra`:`Any`=`None`, `processor`:[`PreProcessor`](/data_block.html#PreProcessor)=`None`, `x`:`ItemList`=`None`, `kwargs`) :: [`ItemList`](/data_block.html#ItemList)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageItemList, title_level=3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Create a [`ItemList`](/data_block.html#ItemList) in `path` from filenames in `items`. `create_func` will default to [`open_image`](/vision.image.html#open_image). `label_cls` can be specified for the labels, `xtra` contains any extra information (usually in the form of a dataframe) and `processor` is applied to the [`ItemList`](/data_block.html#ItemList) after splitting and labelling." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

from_folder[source]

\n", "\n", "> from_folder(`path`:`PathOrStr`=`'.'`, `extensions`:`StrList`=`None`, `kwargs`) → [`ItemList`](/data_block.html#ItemList)\n", "\n", "Get the list of files in `path` that have an image suffix. `recurse` determines if we search subfolders. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageItemList.from_folder)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

from_df[source]

\n", "\n", "> from_df(`df`:`DataFrame`, `path`:`PathOrStr`, `cols`:`Union`\\[`int`, `Collection`\\[`int`\\], `str`, `StrList`\\]=`0`, `folder`:`PathOrStr`=`'.'`, `suffix`:`str`=`''`, `kwargs`) → `ItemList`\n", "\n", "Get the filenames in `col` of `df` and will had `path/folder` in front of them, `suffix` at the end. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageItemList.from_df)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

get_image_files[source]

\n", "\n", "> get_image_files(`c`:`PathOrStr`, `check_ext`:`bool`=`True`, `recurse`=`False`) → `FilePathList`\n", "\n", "Return list of files in `c` that are images. `check_ext` will filter to `image_extensions`. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(get_image_files)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class ObjectCategoryList[source]

\n", "\n", "> ObjectCategoryList(`items`:`Iterator`, `classes`:`Collection`=`None`, `sep`:`str`=`None`, `kwargs`) :: [`MultiCategoryList`](/data_block.html#MultiCategoryList)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ObjectCategoryList, title_level=3)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class ObjectItemList[source]

\n", "\n", "> ObjectItemList(`items`:`Iterator`, `path`:`PathOrStr`=`'.'`, `label_cls`:`Callable`=`None`, `xtra`:`Any`=`None`, `processor`:[`PreProcessor`](/data_block.html#PreProcessor)=`None`, `x`:`ItemList`=`None`, `kwargs`) :: [`ImageItemList`](/vision.data.html#ImageItemList)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ObjectItemList, title_level=3)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class SegmentationItemList[source]

\n", "\n", "> SegmentationItemList(`items`:`Iterator`, `path`:`PathOrStr`=`'.'`, `label_cls`:`Callable`=`None`, `xtra`:`Any`=`None`, `processor`:[`PreProcessor`](/data_block.html#PreProcessor)=`None`, `x`:`ItemList`=`None`, `kwargs`) :: [`ImageItemList`](/vision.data.html#ImageItemList)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(SegmentationItemList, title_level=3)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class SegmentationLabelList[source]

\n", "\n", "> SegmentationLabelList(`items`:`Iterator`, `classes`:`Collection`=`None`, `kwargs`) :: [`ImageItemList`](/vision.data.html#ImageItemList)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(SegmentationLabelList, title_level=3)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class PointsItemList[source]

\n", "\n", "> PointsItemList(`items`:`Iterator`, `path`:`PathOrStr`=`'.'`, `label_cls`:`Callable`=`None`, `xtra`:`Any`=`None`, `processor`:[`PreProcessor`](/data_block.html#PreProcessor)=`None`, `x`:`ItemList`=`None`, `kwargs`) :: [`ItemList`](/data_block.html#ItemList)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(PointsItemList, title_level=3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Building your own dataset" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This module also contains a few helper functions to allow you to build you own dataset for image classification." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

download_images[source]

\n", "\n", "> download_images(`urls`:`StrList`, `dest`:`PathOrStr`, `max_pics`:`int`=`1000`, `max_workers`:`int`=`8`, `timeout`=`4`)\n", "\n", "Download images listed in text file `urls` to path `dest`, at most `max_pics` " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(download_images)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

verify_images[source]

\n", "\n", "> verify_images(`path`:`PathOrStr`, `delete`:`bool`=`True`, `max_workers`:`int`=`4`, `max_size`:`Union`\\[`int`, `Tuple`\\[`int`, `int`\\]\\]=`None`, `dest`:`PathOrStr`=`'.'`, `n_channels`:`int`=`3`, `interp`=`2`, `ext`:`str`=`None`, `img_format`:`str`=`None`, `resume`:`bool`=`None`, `kwargs`)\n", "\n", "Check if the image in `path` exists, can be opened and has `n_channels`. If `n_channels` is 3 – it'll try to convert image to RGB. If `delete`, removes it if it fails.\n", "If `resume` – it will skip already existent images in `dest`. If `max_size` is specifided,\n", "image is resized to the same ratio so that both sizes are less than `max_size`, using `interp`.\n", "Result is stored in `dest`, `ext` forces an extension type, `img_format` and `kwargs` are\n", "passed to PIL.Image.save. Use `max_workers` CPUs. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(verify_images)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Undocumented Methods - Methods moved below this line will intentionally be hidden" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "

get[source]

\n", "\n", "> get(`i`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(PointsItemList.get)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "

new[source]

\n", "\n", "> new(`items`, `classes`=`None`, `kwargs`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(SegmentationLabelList.new)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "

from_csv[source]

\n", "\n", "> from_csv(`path`:`PathOrStr`, `csv_name`:`str`, `header`:`str`=`'infer'`, `kwargs`) → `ItemList`" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageItemList.from_csv)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "

get[source]

\n", "\n", "> get(`i`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ObjectCategoryList.get)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [ { "data": { "text/markdown": [ "

get[source]

\n", "\n", "> get(`i`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageItemList.get)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## New Methods - Please document or move to the undocumented section" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

process_one[source]

\n", "\n", "> process_one(`item`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ObjectCategoryProcessor.process_one)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

generate_classes[source]

\n", "\n", "> generate_classes(`items`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ObjectCategoryProcessor.generate_classes)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class ObjectCategoryProcessor[source]

\n", "\n", "> ObjectCategoryProcessor(`ds`:[`ItemList`](/data_block.html#ItemList), `pad_idx`:`int`=`0`) :: [`MultiCategoryProcessor`](/data_block.html#MultiCategoryProcessor)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ObjectCategoryProcessor)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

reconstruct[source]

\n", "\n", "> reconstruct(`t`, `x`)\n", "\n", "Reconstuct one of the underlying item for its data `t`. " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ObjectCategoryList.reconstruct)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

open[source]

\n", "\n", "> open(`fn`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageItemList.open)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

class ImageToImageList[source]

\n", "\n", "> ImageToImageList(`items`:`Iterator`, `path`:`PathOrStr`=`'.'`, `label_cls`:`Callable`=`None`, `xtra`:`Any`=`None`, `processor`:[`PreProcessor`](/data_block.html#PreProcessor)=`None`, `x`:`ItemList`=`None`, `kwargs`) :: [`ImageItemList`](/vision.data.html#ImageItemList)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(ImageToImageList)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": { "hide_input": true }, "outputs": [ { "data": { "text/markdown": [ "

open[source]

\n", "\n", "> open(`fn`)" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "show_doc(SegmentationLabelList.open)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [] } ], "metadata": { "jekyll": { "keywords": "fastai", "summary": "Basic dataset for computer vision and helper function to get a DataBunch", "title": "vision.data" }, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" } }, "nbformat": 4, "nbformat_minor": 2 }