{ "cells": [ { "cell_type": "markdown", "id": "d1d92b2e", "metadata": {}, "source": [ "[![image](https://raw.githubusercontent.com/visual-layer/visuallayer/main/imgs/vl_horizontal_logo.png)](https://www.visual-layer.com)" ] }, { "cell_type": "markdown", "id": "731484b5", "metadata": {}, "source": [ "# Analyzing Kaggle Datasets\n", "\n", "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/visual-layer/fastdup/blob/main/examples/analyzing-kaggle-datasets.ipynb)\n", "[![Open in Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://kaggle.com/kernels/welcome?src=https://github.com/visual-layer/fastdup/blob/main/examples/analyzing-kaggle-datasets.ipynb)\n", "\n", "This notebook shows how you can use [fastdup](https://github.com/visual-layer/fastdup) to analyze any computer vision dataset from [Kaggle](https://kaggle.com)." ] }, { "cell_type": "markdown", "id": "34d4d2db", "metadata": {}, "source": [ "## Install Kaggle API\n", "\n", "To load data programmatically from Kaggle, we will need to install the [Kaggle API](https://github.com/Kaggle/kaggle-api). The API lets us pull data from Kaggle using Python.\n", "\n", "To install the API, run:" ] }, { "cell_type": "code", "execution_count": 1, "id": "94204bbc-f0dd-464c-aff5-0d9367d88860", "metadata": {}, "outputs": [], "source": [ "!pip install -Uq kaggle" ] }, { "cell_type": "markdown", "id": "eb3fd4c9-bdfb-4ba9-aef6-528d9811b588", "metadata": {}, "source": [ "Note: to use the Kaggle API, you'll need to sign up for a Kaggle account at https://www.kaggle.com/ . \n", "\n", "Go to the 'Account' tab and select 'Create API Token'. This will trigger the download of `kaggle.json`, a file containing your API credentials. \n", "\n", "Place this file in the location `~/.kaggle/kaggle.json` (on Windows in the location `C:\\Users\\\\.kaggle\\kaggle.json`)\n", "\n", "Fore more information on the Kaggle API, click [here](https://github.com/Kaggle/kaggle-api#api-credentials)." ] }, { "cell_type": "markdown", "id": "4b6ae131-572a-4008-a9c1-6f49b21c029e", "metadata": {}, "source": [ "If the set up is done correctly, you should be able to run the kaggle commands on your terminal. For instance, to list kaggle datasets that have the term \"computer vision\" , run:" ] }, { "cell_type": "code", "execution_count": 2, "id": "2363f8b1-bf3f-4650-99ea-5e77275806eb", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ref title size lastUpdated downloadCount voteCount usabilityRating \n", "------------------------------------------------------------ -------------------------------------------------- ----- ------------------- ------------- --------- --------------- \n", "jeffheaton/iris-computer-vision Iris Computer Vision 5MB 2020-11-24 21:23:29 1415 20 0.875 \n", "bhavikardeshna/visual-question-answering-computer-vision-nlp Visual Question Answering- Computer Vision & NLP 411MB 2022-06-14 04:32:28 421 37 0.8235294 \n", "sanikamal/horses-or-humans-dataset Horses Or Humans Dataset 307MB 2019-04-24 20:09:38 8405 120 0.875 \n", "phylake1337/fire-dataset FIRE Dataset 387MB 2020-02-25 16:45:29 12098 180 0.875 \n", "fedesoriano/cifar100 CIFAR-100 Python 161MB 2020-12-26 08:37:10 4881 116 1.0 \n", "fedesoriano/chinese-mnist-digit-recognizer Chinese MNIST in CSV - Digit Recognizer 8MB 2021-06-08 12:15:47 966 45 1.0 \n", "bulentsiyah/opencv-samples-images OpenCV samples (Images) 13MB 2020-05-19 14:36:01 2374 72 0.75 \n", "jeffheaton/traveling-salesman-computer-vision Traveling Salesman Computer Vision 3GB 2022-04-20 01:13:17 183 22 0.875 \n", "sanikamal/rock-paper-scissors-dataset Rock Paper Scissors Dataset 452MB 2019-04-24 19:53:04 4556 78 0.875 \n", "muratkokludataset/dry-bean-dataset Dry Bean Dataset 5MB 2022-04-02 23:19:30 2303 1464 0.9375 \n", "juniorbueno/opencv-facial-recognition-lbph OpenCV - Facial Recognition - LBPH 6MB 2021-12-01 10:47:12 487 45 0.875 \n", "rickyjli/chinese-fine-art Chinese Fine Art 323MB 2020-05-02 03:00:40 821 38 0.8235294 \n", "mpwolke/cusersmarildownloadsmondrianpng Computer Vision. C'est Audacieux, Luxueux, Chic! 417KB 2022-04-10 21:41:35 10 20 1.0 \n", "paultimothymooney/cvpr-2019-papers CVPR 2019 Papers 5GB 2019-06-16 18:28:50 934 50 0.875 \n", "emirhanai/human-action-detection-artificial-intelligence Human Action Detection - Artificial Intelligence 147MB 2022-04-22 21:07:24 1468 40 1.0 \n", "vencerlanz09/plastic-paper-garbage-bag-synthetic-images Plastic - Paper - Garbage Bag Synthetic Images 451MB 2022-08-26 09:57:18 1127 76 0.875 \n", "shaunthesheep/microsoft-catsvsdogs-dataset Cats-vs-Dogs 788MB 2020-03-12 05:34:30 27897 345 0.875 \n", "birdy654/cifake-real-and-ai-generated-synthetic-images CIFAKE: Real and AI-Generated Synthetic Images 105MB 2023-03-28 16:00:29 1702 44 0.875 \n", "ryanholbrook/computer-vision-resources Computer Vision Resources 13MB 2020-07-23 10:40:17 2491 11 0.1764706 \n", "fedesoriano/qmnist-the-extended-mnist-dataset-120k-images QMNIST - The Extended MNIST Dataset (120k images) 19MB 2021-07-24 15:31:01 844 29 1.0 \n" ] } ], "source": [ "!kaggle datasets list -s \"computer vision\"" ] }, { "cell_type": "markdown", "id": "07c72155-1396-453e-a070-b395a02b0833", "metadata": {}, "source": [ "See more commands [here](https://github.com/Kaggle/kaggle-api#commands). \n", "\n", "Optionally, you can also browse the Kaggle webpage to see the dataset you're interested to download." ] }, { "cell_type": "markdown", "id": "8d6e309c-1317-4183-b909-68e2464244fc", "metadata": {}, "source": [ "## Download Dataset" ] }, { "attachments": { "4ea6f203-55bd-4ca7-817d-ad2a16721ed0.png": { "image/png": "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" } }, "cell_type": "markdown", "id": "622ed625-8e11-4e39-85ed-ae2faf3320a8", "metadata": {}, "source": [ "Let's say we're interested to analyze the [RVL-CDIP Test Dataset](https://www.kaggle.com/datasets/pdavpoojan/the-rvlcdip-dataset-test). You can head to the dataset page and click on \"Copy API command\" and paste it in your terminal.\n", "\n", "![image.png](attachment:4ea6f203-55bd-4ca7-817d-ad2a16721ed0.png)" ] }, { "cell_type": "markdown", "id": "dfa2560e-a945-4683-a841-48b9f29f5fa8", "metadata": {}, "source": [ "Let's run the command here, which will trigger a download of the RVL-CDIP test dataset into our current working directory." ] }, { "cell_type": "code", "execution_count": null, "id": "d4d25bf5-a5d6-4c3d-9617-343a7fd9831f", "metadata": {}, "outputs": [], "source": [ "!kaggle datasets download -d pdavpoojan/the-rvlcdip-dataset-test" ] }, { "cell_type": "markdown", "id": "97ed311c-02c8-4cb6-b5d2-21140ce36a93", "metadata": {}, "source": [ "Once done, we should have a `the-rvlcdip-dataset-test.zip` in the current directory.\n", "\n", "Let's unzip the file to prepare it for further analysis with fastdup in the next section." ] }, { "cell_type": "code", "execution_count": 3, "id": "b73b136f-f077-4016-9316-d0147c4631d2", "metadata": {}, "outputs": [], "source": [ "!unzip -q the-rvlcdip-dataset-test.zip" ] }, { "cell_type": "markdown", "id": "1f8d6b66-3f53-4afb-b040-c5d91a628608", "metadata": {}, "source": [ "Once completed, we should have a folder with the name `test/`, which contains all the images from the dataset." ] }, { "cell_type": "markdown", "id": "41f2abee-1251-4500-8ebf-90c593b6157a", "metadata": {}, "source": [ "## Install fastdup\n", "\n", "Next, install fastdup and verify the installation." ] }, { "cell_type": "code", "execution_count": 4, "id": "7176a4bc", "metadata": {}, "outputs": [], "source": [ "!pip install -Uq fastdup " ] }, { "cell_type": "markdown", "id": "4dea523f", "metadata": {}, "source": [ "Now, test the installation. If there's no error message, we are ready to go." ] }, { "cell_type": "code", "execution_count": 5, "id": "655330c1", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "/usr/bin/dpkg\n" ] }, { "data": { "text/plain": [ "'1.31'" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import fastdup\n", "fastdup.__version__" ] }, { "cell_type": "markdown", "id": "6aac94ea", "metadata": {}, "source": [ "## Run fastdup" ] }, { "cell_type": "markdown", "id": "a10910f4-b772-400b-96b6-f44b62b97fe0", "metadata": {}, "source": [ "To run fastdup, we simply point `input_dir` to the folder containing the images from the dataset." ] }, { "cell_type": "code", "execution_count": 6, "id": "8e90af72", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Warning: fastdup create() without work_dir argument, output is stored in a folder named work_dir in your current working path.\n", "FastDup Software, (C) copyright 2022 Dr. Amir Alush and Dr. Danny Bickson.\n", "2023-08-01 14:04:04 [INFO] Going to loop over dir test\n", "2023-08-01 14:04:04 [INFO] Found total 39997 images to run on, 39997 train, 0 test, name list 39997, counter 39997 \n", "2023-08-01 14:05:22 [ERROR] Failed to read image test/scientific_publication/2500126531_2500126536.tif\n", "2023-08-01 14:05:37 [INFO] Found total 39997 images to run onimated: 0 Minutes\n", "Finished histogram 12.923\n", "Finished bucket sort 12.997\n", "2023-08-01 14:05:41 [INFO] 4180) Finished write_index() NN model\n", "2023-08-01 14:05:41 [INFO] Stored nn model index file work_dir/nnf.index\n", "2023-08-01 14:05:44 [INFO] Total time took 100130 ms\n", "2023-08-01 14:05:44 [INFO] Found a total of 1392 fully identical images (d>0.990), which are 1.74 %\n", "2023-08-01 14:05:44 [INFO] Found a total of 10177 nearly identical images(d>0.980), which are 12.72 %\n", "2023-08-01 14:05:44 [INFO] Found a total of 73590 above threshold images (d>0.900), which are 91.99 %\n", "2023-08-01 14:05:44 [INFO] Found a total of 4003 outlier images (d<0.050), which are 5.00 %\n", "2023-08-01 14:05:44 [INFO] Min distance found 0.647 max distance 1.000\n", "2023-08-01 14:05:44 [INFO] Running connected components for ccthreshold 0.960000 \n", ".0\n", " ########################################################################################\n", "\n", "Dataset Analysis Summary: \n", "\n", " Dataset contains 39997 images\n", " Valid images are 88.00% (39,996) of the data, invalid are 0.00% (1) of the data\n", " For a detailed analysis, use `.invalid_instances()`.\n", "\n", " Similarity: 52.47% (23,850) belong to 33 similarity clusters (components).\n", " 35.53% (16,147) images do not belong to any similarity cluster.\n", " Largest cluster has 85,160 (187.37%) images.\n", " For a detailed analysis, use `.connected_components()`\n", "(similarity threshold used is 0.9, connected component threshold used is 0.96).\n", "\n", " Outliers: 5.09% (2,312) of images are possible outliers, and fall in the bottom 5.00% of similarity values.\n", " For a detailed list of outliers, use `.outliers()`.\n", "\n", "########################################################################################\n", "Would you like to see awesome visualizations for some of the most popular academic datasets?\n", "Click here to see and learn more: https://app.visual-layer.com/vl-datasets?utm_source=fastdup\n", "########################################################################################\n" ] }, { "data": { "text/plain": [ "0" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "fd = fastdup.create(input_dir='test')\n", "fd.run()" ] }, { "cell_type": "markdown", "id": "676d9175", "metadata": {}, "source": [ "## Inspect Issues" ] }, { "cell_type": "markdown", "id": "01b2cace-9e25-48bf-826b-907bad037df9", "metadata": {}, "source": [ "From the summary above, we have 1 corrupted image. Let's get some more details:" ] }, { "cell_type": "code", "execution_count": 7, "id": "ba8ba8f1-9d29-4953-84f1-7bade200931e", "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", "
filenameindexerror_codeis_validfd_index
0test/scientific_publication/2500126531_2500126536.tif33760ERROR_CORRUPT_IMAGEFalse33760
\n", "
" ], "text/plain": [ " filename index error_code is_valid fd_index\n", "0 test/scientific_publication/2500126531_2500126536.tif 33760 ERROR_CORRUPT_IMAGE False 33760" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "fd.invalid_instances()" ] }, { "cell_type": "markdown", "id": "1017106b", "metadata": {}, "source": [ "There are several other methods we can use to inspect and visualize the issues found:\n", "\n", "```python\n", "fd.vis.duplicates_gallery() # create a visual gallery of duplicates\n", "fd.vis.outliers_gallery() # create a visual gallery of anomalies\n", "fd.vis.component_gallery() # create a visualization of connected components\n", "fd.vis.stats_gallery() # create a visualization of images statistics (e.g. blur)\n", "fd.vis.similarity_gallery() # create a gallery of similar images\n", "```" ] }, { "cell_type": "code", "execution_count": 8, "id": "cd57d5b6-e953-4b2b-a55c-884e467ea2be", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 20/20 [00:00<00:00, 246.94it/s]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Stored similarity visual view in work_dir/galleries/duplicates.html\n", "########################################################################################\n", "Would you like to see awesome visualizations for some of the most popular academic datasets?\n", "Click here to see and learn more: https://app.visual-layer.com/vl-datasets?utm_source=fastdup\n", "########################################################################################\n" ] }, { "data": { "text/html": [ " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " Duplicates Report\n", " \n", " \n", "\n", "\n", "\n", "
\n", "
\n", "
\n", " \n", " \"logo\"\n", " \n", "
\n", " \n", "
\n", "
\n", "
\n", "

Duplicates Report

\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", "
Info
Distance1.0
From/memo/0001461863.tif
To/memo/0001460963.tif
\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", "
Info
Distance1.0
From/news_article/87275097_87275098.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/1002325902.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/1002325721.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/1002325688.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/87366386.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/91574477_91574478.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/91582383_91582384.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/85145710_85145711.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/91572245_91572246.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/1002325088.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/1002325029.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/87688462.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/1002325750.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/92173757_92173758.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/scientific_report/2056457981.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/92729007_92729008.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/92729362.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/92173705_92173708.tif
To/advertisement/1002325068.tif
\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", "
Info
Distance1.0
From/advertisement/85145249_85145250.tif
To/advertisement/1002325029.tif
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", " \n", "
\n", " \n", " " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "0" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "fd.vis.duplicates_gallery()" ] }, { "cell_type": "code", "execution_count": 9, "id": "2003f116-a5ed-4ded-950a-2a5971c8005b", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 20/20 [00:02<00:00, 9.53it/s]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Finished OK. Components are stored as image files work_dir/galleries/components_[index].jpg\n", "Stored components visual view in work_dir/galleries/components.html\n", "Execution time in seconds 4.2\n", "########################################################################################\n", "Would you like to see awesome visualizations for some of the most popular academic datasets?\n", "Click here to see and learn more: https://app.visual-layer.com/vl-datasets?utm_source=fastdup\n", "########################################################################################\n" ] }, { "data": { "text/html": [ " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " Components Report\n", " \n", " \n", "\n", "\n", "\n", "
\n", "
\n", "
\n", " \n", " \"logo\"\n", " \n", "
\n", " \n", "
\n", "
\n", "
\n", "

Components Report

Showing groups of similar images

\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", "
Info
component55
num_images21,951
mean_distance0.96
\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", "
Info
component3135
num_images74
mean_distance0.9601
\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", "
Info
component3919
num_images52
mean_distance0.9602
\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", "
Info
component0
num_images32
mean_distance1.0
\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", "
Info
component2449
num_images32
mean_distance0.9607
\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", "
Info
component3238
num_images28
mean_distance0.9615
\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", "
Info
component8531
num_images24
mean_distance0.9625
\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", "
Info
component390
num_images21
mean_distance1.0
\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", "
Info
component2861
num_images20
mean_distance0.9604
\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", "
Info
component9795
num_images19
mean_distance0.964
\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", "
Info
component2603
num_images15
mean_distance0.9602
\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", "
Info
component15389
num_images14
mean_distance0.9605
\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", "
Info
component9792
num_images13
mean_distance0.9693
\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", "
Info
component11433
num_images13
mean_distance0.9601
\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", "
Info
component7681
num_images13
mean_distance0.9603
\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", "
Info
component2590
num_images12
mean_distance0.9618
\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", "
Info
component2475
num_images12
mean_distance0.9613
\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", "
Info
component12871
num_images11
mean_distance0.9609
\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", "
Info
component13591
num_images11
mean_distance0.9658
\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", "
Info
component1153
num_images10
mean_distance0.9601
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", " \n", "
\n", " \n", " " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "0" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "fd.vis.component_gallery()" ] }, { "cell_type": "code", "execution_count": 11, "id": "c242a31d-220f-4216-a39a-6882323d4465", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 20/20 [00:00<00:00, 610.40it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Stored mean visual view in work_dir/galleries/mean.html\n", "########################################################################################\n", "Would you like to see awesome visualizations for some of the most popular academic datasets?\n", "Click here to see and learn more: https://app.visual-layer.com/vl-datasets?utm_source=fastdup\n", "########################################################################################\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] }, { "data": { "text/html": [ " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " Dark Image Report\n", " \n", " \n", "\n", "\n", "\n", "
\n", "
\n", "
\n", " \n", " \"logo\"\n", " \n", "
\n", " \n", "
\n", "
\n", "
\n", "

Dark Image Report

Showing example images, sort by ascending order

\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", "
Info
mean12.5146
filenametest/file_folder/94373419.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean13.6359
filenametest/questionnaire/513553162+-3315.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean15.5563
filenametest/file_folder/94398147.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean15.927
filenametest/questionnaire/0000012100.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean19.9641
filenametest/questionnaire/519489404+-9454.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean20.0391
filenametest/file_folder/2048394500.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean22.0036
filenametest/file_folder/2048045266.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean22.5692
filenametest/letter/00420507_00420508.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean22.6016
filenametest/file_folder/2048292000.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean22.8505
filenametest/file_folder/2501249122.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean22.8664
filenametest/file_folder/2062217828.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean23.0896
filenametest/scientific_report/2050087475_2050087535.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean23.7749
filenametest/file_folder/2501195751.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean23.877
filenametest/file_folder/2048337054.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean24.0289
filenametest/questionnaire/0000012854.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean24.2214
filenametest/specification/509019614+-9626.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean25.0368
filenametest/file_folder/82843434.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean25.3956
filenametest/file_folder/2501287422.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean26.3646
filenametest/file_folder/60038569.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean28.0583
filenametest/file_folder/2051170843.tif
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", " \n", "
\n", " \n", " " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "0" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "fd.vis.stats_gallery(metric='dark')" ] }, { "cell_type": "code", "execution_count": 12, "id": "1dd0f9ac-a151-485b-bbbc-c4113361536c", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 20/20 [00:00<00:00, 714.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Stored mean visual view in work_dir/galleries/mean.html\n", "########################################################################################\n", "Would you like to see awesome visualizations for some of the most popular academic datasets?\n", "Click here to see and learn more: https://app.visual-layer.com/vl-datasets?utm_source=fastdup\n", "########################################################################################\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] }, { "data": { "text/html": [ " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " Bright Image Report\n", " \n", " \n", "\n", "\n", "\n", "
\n", "
\n", "
\n", " \n", " \"logo\"\n", " \n", "
\n", " \n", "
\n", "
\n", "
\n", "

Bright Image Report

Showing example images, sort by descending order

\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", "
Info
mean254.9557
filenametest/file_folder/2504075165.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.935
filenametest/file_folder/2046721605.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.9031
filenametest/resume/50420594-0596.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8947
filenametest/file_folder/2501096788.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8934
filenametest/file_folder/2500145302.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8922
filenametest/file_folder/91383093.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8896
filenametest/file_folder/2501096831.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8855
filenametest/budget/ti31039016_9020.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8837
filenametest/file_folder/2044687370.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8712
filenametest/file_folder/2044115217.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8708
filenametest/file_folder/2042386755.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8699
filenametest/file_folder/2043901266-a.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8685
filenametest/budget/ti31399014_9023.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8662
filenametest/file_folder/60037624.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8649
filenametest/budget/83565505_5508.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8635
filenametest/file_folder/2064961137.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.854
filenametest/invoice/83565336_5338.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8537
filenametest/presentation/2077725710_5715.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8519
filenametest/invoice/83565146_5147.tif
\n", "
\n", "
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", "
\n", " \n", " \n", " \n", " \n", " \n", "\n", " \n", " \n", "\n", "\n", " \n", " \n", "\n", " \n", "
Info
mean254.8512
filenametest/file_folder/2501153738.tif
\n", "
\n", "
\n", "
\n", " \n", "
\n", "
\n", " \n", "
\n", " \n", " " ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "0" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "fd.vis.stats_gallery(metric='bright')" ] }, { "cell_type": "markdown", "id": "a4eb87fa", "metadata": {}, "source": [ "## Wrap Up\n", "\n", "That's a wrap! In this notebook we showed how you load dataset from Kaggle and analyze it using fastdup. You can use similar methods to run on other similar datasets on [Kaggle](https://kaggle.com).\n", "\n", "Try it out and let us know what issues you find.\n", "\n", "\n", "Next, feel free to check out other tutorials -\n", "\n", "+ โšก [**Quickstart**](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/quick-dataset-analysis.ipynb): Learn how to install fastdup, load a dataset and analyze it for potential issues such as duplicates/near-duplicates, broken images, outliers, dark/bright/blurry images, and view visually similar image clusters. If you're new, start here!\n", "+ ๐Ÿงน [**Clean Image Folder**](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/cleaning-image-dataset.ipynb): Learn how to analyze and clean a folder of images from potential issues and export a list of problematic files for further action. If you have an unorganized folder of images, this is a good place to start.\n", "+ ๐Ÿ–ผ [**Analyze Image Classification Dataset**](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/analyzing-image-classification-dataset.ipynb): Learn how to load a labeled image classification dataset and analyze for potential issues. If you have labeled ImageNet-style folder structure, have a go!\n", "+ ๐ŸŽ [**Analyze Object Detection Dataset**](https://nbviewer.org/github/visual-layer/fastdup/blob/main/examples/analyzing-object-detection-dataset.ipynb): Learn how to load bounding box annotations for object detection and analyze for potential issues. If you have a COCO-style labeled object detection dataset, give this example a try. " ] }, { "cell_type": "markdown", "id": "08fd287b", "metadata": {}, "source": [ "\n", "# VL Profiler\n", "If you prefer a no-code platform to inspect and visualize your dataset, [**try our free cloud product VL Profiler**](https://app.visual-layer.com) - VL Profiler is our first no-code commercial product that lets you visualize and inspect your dataset in your browser. \n", "\n", "[Sign up](https://app.visual-layer.com) now, it's free.\n", "\n", "[![image](https://raw.githubusercontent.com/visual-layer/fastdup/main/gallery/vl_profiler_promo.svg)](https://app.visual-layer.com)\n", "\n", "As usual, feedback is welcome! \n", "\n", "Questions? Drop by our [Slack channel](https://visualdatabase.slack.com/join/shared_invite/zt-19jaydbjn-lNDEDkgvSI1QwbTXSY6dlA#/shared-invite/email) or open an issue on [GitHub](https://github.com/visual-layer/fastdup/issues)." ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.10.12" } }, "nbformat": 4, "nbformat_minor": 5 }