New Upstream Release - dataset-fashion-mnist

QA Page
Maintainer email: lumin@debian.org
Automatic publish policy: main: push-derived , pristine-tar: push-derived , upstream: push-derived
Last processed: 2022-10-24T00:34 (took 9m13s)
Branch URL: https://salsa.debian.org/deeplearning-team/dataset-fashion-mnist.git -b master (taken from version 0.0~git20200523.55506a9-1)
Queue position: 187535 (a 156w5d wait)

Ready changes

Summary

Merged new upstream version: 0.0~git20220321.b2617bb (was: 0.0~git20200523.55506a9).

Resulting package

Built on 2022-10-24T00:34 (took 9m13s)

The resulting binary packages can be installed (if you have the apt repository enabled) by running one of:

apt install -t fresh-releases dataset-fashion-mnist

Lintian Result

dataset-fashion-mnist_0.0~git20220321.b2617bb-1~jan+nur1.dsc

dataset-fashion-mnist_0.0~git20220321.b2617bb-1~jan+nur1_all.deb

dataset-fashion-mnist_0.0~git20220321.b2617bb-1~jan+nur1_amd64.buildinfo

dataset-fashion-mnist_0.0~git20220321.b2617bb-1~jan+nur1_amd64.changes

Diff

diff --git a/README.ja.md b/README.ja.md
index be3c92e..362c568 100644
--- a/README.ja.md
+++ b/README.ja.md
@@ -101,23 +101,25 @@ data = input_data.read_data_sets('data/fashion')
 data.train.next_batch(BATCH_SIZE)
 ```
 
-Fashion-MNISTを訓練するための高レベルのAPIである`tf.keras`の使用に関する公式のTensorflow[チュートリアルがここにあります](https://www.tensorflow.org/tutorials/keras/basic_classification)。
+Fashion-MNISTを訓練するための高レベルのAPIである`tf.keras`の使用に関する公式のTensorflow[チュートリアルがここにあります](https://www.tensorflow.org/tutorials/keras/classification)。
 
 ### 他の機械学習ライブラリを使用する
 
 今日まで、以下のライブラリは、組み込みデータセットとして `Fashion-MNIST`を含んでいます。 したがって、自分で`Fashion-MNIST`をダウンロードする必要はありません。 そのAPIに従うだけで、あなたは準備が整いました。
 
-- [Apache MXNet Gluon](https://mxnet.incubator.apache.org/api/python/gluon/data.html)
-- [deeplearn.js](https://deeplearnjs.org/demos/model-builder/)
+- [Apache MXNet Gluon](https://mxnet.apache.org/api/python/docs/api/gluon/data/vision/datasets/index.html#mxnet.gluon.data.vision.datasets.FashionMNIST)
+- [TensorFlow.js](https://github.com/tensorflow/tfjs-examples/blob/master/fashion-mnist-vae/data.js)
 - [Kaggle](https://www.kaggle.com/zalando-research/fashionmnist)
-- [Pytorch](http://pytorch.org/docs/master/torchvision/datasets.html#fashion-mnist)
-- [Keras](https://keras.io/datasets/#fashion-mnist-database-of-fashion-articles)
+- [Pytorch](https://pytorch.org/vision/stable/datasets.html#fashion-mnist)
+- [Keras](https://keras.io/api/datasets/fashion_mnist/)
 - [Edward](http://edwardlib.org/api/observations/fashion_mnist)
-- [Tensorflow](https://www.tensorflow.org/versions/r1.5/api_docs/python/tf/keras/datasets/fashion_mnist)
+- [Tensorflow](https://www.tensorflow.org/api_docs/python/tf/keras/datasets/fashion_mnist)
+- [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/fashion_mnist)
 - [Torch](https://github.com/mingloo/fashion-mnist)
-- [JuliaML](https://github.com/JuliaML/MLDatasets.jl)
-- [Chainer (latest)](https://docs.chainer.org/en/latest/reference/generated/chainer.datasets.get_fashion_mnist.html?highlight=fashion-mnist)
-
+- [JuliaML](https://juliaml.github.io/MLDatasets.jl/latest/datasets/FashionMNIST/)
+- [Chainer](https://docs.chainer.org/en/stable/reference/generated/chainer.datasets.get_fashion_mnist.html)
+- [HuggingFace Datasets](https://huggingface.co/datasets/fashion_mnist)
+- 
 ようこそ私たちに参加して、各機械学習ライブラリ用の`Fashion-MNIST`のサポートを追加してください。
 
 
@@ -128,7 +130,7 @@ Fashion-MNISTを訓練するための高レベルのAPIである`tf.keras`の使
 - [C](https://stackoverflow.com/a/10409376)
 - [C++](https://github.com/wichtounet/mnist)
 - [Java](https://stackoverflow.com/a/8301949)
-- [Python](https://pypi.python.org/pypi/python-mnist) and [this](https://pypi.python.org/pypi/mnist) and [this]((https://www.brine.io/fashion-mnist/train))
+- [Python](https://pypi.python.org/pypi/python-mnist) and [this](https://pypi.python.org/pypi/mnist) 
 - [Scala](http://mxnet.io/tutorials/scala/mnist.html)
 - [Go](https://github.com/schuyler/neural-go/blob/master/mnist/mnist.go)
 - [C#](https://jamesmccaffrey.wordpress.com/2013/11/23/reading-the-mnist-data-set-with-c/)
@@ -137,6 +139,7 @@ Fashion-MNISTを訓練するための高レベルのAPIである`tf.keras`の使
 - [R](https://gist.github.com/brendano/39760) and [this](https://github.com/maddin79/darch)
 - [Matlab](http://ufldl.stanford.edu/wiki/index.php/Using_the_MNIST_Dataset)
 - [Ruby](https://github.com/gbuesing/mnist-ruby-test/blob/master/train/mnist_loader.rb)
+- [Rust](https://github.com/AtheMathmo/vision-rs/blob/master/src/fashion_mnist.rs)
 
 
 ## ベンチマーク
@@ -163,7 +166,7 @@ scikit-learn ベースの自動ベンチマーキング・システムを構築
 |3 Conv+2 FC | None | 0.907 | - | [@Cenk Bircanoğlu](https://github.com/cenkbircanoglu) | [:link:](https://github.com/cenkbircanoglu/openface/tree/master/fashion_mnist)|
 |3 Conv+pooling+BN | None | 0.903 | 0.994 | [@meghanabhange](https://github.com/meghanabhange) | [:link:](https://github.com/meghanabhange/FashionMNIST-3-Layer-CNN) |
 |3 Conv+pooling+2 FC+dropout | None | 0.926 | - | [@Umberto Griffo](https://github.com/umbertogriffo) | [:link:](https://github.com/umbertogriffo/Fashion-mnist-cnn-keras)|
-|3 Conv+BN+pooling|None|0.921|0.992|[@GunjanChhablani](https://github.com/GunjanChhablani)|[:link:](https://github.com/GunjanChhablani/CNN-with-FashionMNIST)| 
+|3 Conv+BN+pooling|None|0.921|0.992|[@gchhablani](https://github.com/gchhablani)|[:link:](https://github.com/gchhablani/CNN-with-FashionMNIST)| 
 |5 Conv+BN+pooling|None|0.931|-|[@Noumanmufc1](https://github.com/Noumanmufc1)|[:link:](https://gist.github.com/Noumanmufc1/60f00e434f0ce42b6f4826029737490a)| 
 |CNN with optional shortcuts, dense-like connectivity| standardization+augmentation+random erasing | 0.947 |-| [@kennivich](https://github.com/Dezhic) | [:link:](https://github.com/Dezhic/fashion-classifier)|
 |GRU+SVM | None| 0.888 | 0.965 | [@AFAgarap](https://github.com/AFAgarap) | [:link:](https://gist.githubusercontent.com/AFAgarap/92c1c4a5dd771999b0201ec0e7edfee0/raw/828fbda0e466dacb1fad66549e0e3022e1c7263a/gru_svm_zalando.py)|
@@ -187,7 +190,7 @@ scikit-learn ベースの自動ベンチマーキング・システムを構築
 |DENSER| - | 0.953| 0.997| [@fillassuncao](https://github.com/fillassuncao)| [:link:](https://github.com/fillassuncao/denser-models) [:link:](https://arxiv.org/pdf/1801.01563.pdf)|
 |Dyra-Net| Rescale to unit interval | 0.906| -| [@Dirk Schäfer](https://github.com/disc5)| [:link:](https://github.com/disc5/dyra-net) [:link:](https://dl.acm.org/citation.cfm?id=3204176.3204200)|
 |Google AutoML|24 compute hours (higher quality)| 0.939|-| [@Sebastian Heinz](https://github.com/sebastianheinz) |[:link:](https://www.statworx.com/de/blog/a-performance-benchmark-of-google-automl-vision-using-fashion-mnist/)|
-
+|Fastai| Resnet50+Fine-tuning+Softmax on last layer's activations| 0.9312| - | [@Sayak](https://github.com/sayakpaul) | [:link:](https://github.com/sayakpaul/Experiments-on-Fashion-MNIST/)|
 
 ### 他の探求
 
@@ -199,7 +202,6 @@ scikit-learn ベースの自動ベンチマーキング・システムを構築
 - [Make a ghost wardrobe using DCGAN](https://twitter.com/spaceLenny/status/901488938023403520)
 - [fashion-mnist的gan玩具](http://kexue.fm/archives/4540/)
 - [CGAN output after 5000 steps](https://github.com/a7b23/Conditional-GAN-using-tensorflow-slim)
-- [live demo of Generative Adversarial Network model with deeplearn.js](http://cognitivechaos.com/playground/fashion-gan/)
 - [GAN Playground - Explore Generative Adversarial Nets in your Browser](https://reiinakano.github.io/gan-playground/)
 
 #### クラスタリング
@@ -237,6 +239,9 @@ Apache MXNet으로 배워보는 딥러닝(Deep Learning) - 김무현 (AWS 솔루
 ### [UMAP](https://github.com/lmcinnes/umap) Fashion-MNIST (左) とオリジナルの MNIST (右) 
 <img src="doc/img/umap_example_fashion_mnist1.png" width="50%"><img src="doc/img/umap_example_mnist1.png" width="50%">
 
+### [PyMDE](https://github.com/cvxgrp/pymde) Fashion-MNIST (左) とオリジナルの MNIST (右) 
+<img src="doc/img/pymde_example_fashion_mnist.png" width="50%"><img src="doc/img/pymde_example_mnist.png" width="50%">
+
 ## 貢献する
 
 Thanks for your interest in contributing! There are many ways to get involved; start with our [contributor guidelines](/CONTRIBUTING.md) and then check these [open issues](https://github.com/zalandoresearch/fashion-mnist/issues) for specific tasks.
diff --git a/README.md b/README.md
index 0318119..9e98787 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@
 
 `Fashion-MNIST` is a dataset of [Zalando](https://jobs.zalando.com/tech/)'s article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. We intend `Fashion-MNIST` to serve as a direct **drop-in replacement** for the original [MNIST dataset](http://yann.lecun.com/exdb/mnist/) for benchmarking machine learning algorithms. It shares the same image size and structure of training and testing splits.
 
-Here's an example how the data looks (*each class takes three-rows*):
+Here's an example of how the data looks (*each class takes three-rows*):
 
 ![](doc/img/fashion-mnist-sprite.png)
 
@@ -102,22 +102,25 @@ Note, Tensorflow supports passing in a source url to the `read_data_sets`. You m
 data = input_data.read_data_sets('data/fashion', source_url='http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/')
 ```
 
-Also, an official Tensorflow tutorial of using `tf.keras`, a high-level API to train Fashion-MNIST [can be found here](https://www.tensorflow.org/tutorials/keras/basic_classification).
+Also, an official Tensorflow tutorial of using `tf.keras`, a high-level API to train Fashion-MNIST [can be found here](https://www.tensorflow.org/tutorials/keras/classification).
 
 ### Loading data with other machine learning libraries 
 To date, the following libraries have included `Fashion-MNIST` as a built-in dataset. Therefore, you don't need to download `Fashion-MNIST` by yourself. Just follow their API and you are ready to go.
 
+- [Activeloop Hub](https://docs.activeloop.ai/datasets/fashion-mnist-dataset)
 - [Apache MXNet Gluon](https://mxnet.apache.org/api/python/docs/api/gluon/data/vision/datasets/index.html#mxnet.gluon.data.vision.datasets.FashionMNIST)
-- [deeplearn.js](https://deeplearnjs.org/demos/model-builder/)
+- [TensorFlow.js](https://github.com/tensorflow/tfjs-examples/blob/master/fashion-mnist-vae/data.js)
 - [Kaggle](https://www.kaggle.com/zalando-research/fashionmnist)
-- [Pytorch](https://pytorch.org/docs/master/torchvision/datasets.html#fashion-mnist)
-- [Keras](https://keras.io/datasets/#fashion-mnist-database-of-fashion-articles)
+- [Pytorch](https://pytorch.org/vision/stable/datasets.html#fashion-mnist)
+- [Keras](https://keras.io/api/datasets/fashion_mnist/)
 - [Edward](http://edwardlib.org/api/observations/fashion_mnist)
 - [Tensorflow](https://www.tensorflow.org/api_docs/python/tf/keras/datasets/fashion_mnist)
+- [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/fashion_mnist)
 - [Torch](https://github.com/mingloo/fashion-mnist)
-- [JuliaML](https://github.com/JuliaML/MLDatasets.jl)
+- [JuliaML](https://juliaml.github.io/MLDatasets.jl/latest/datasets/FashionMNIST/)
 - [Chainer](https://docs.chainer.org/en/stable/reference/generated/chainer.datasets.get_fashion_mnist.html)
-
+- [HuggingFace Datasets](https://huggingface.co/datasets/fashion_mnist)
+ 
 You are welcome to make pull requests to other open-source machine learning packages, improving their support to `Fashion-MNIST` dataset.
 
 ### Loading data with other languages
@@ -127,7 +130,7 @@ As one of the Machine Learning community's most popular datasets, MNIST has insp
 - [C](https://stackoverflow.com/a/10409376)
 - [C++](https://github.com/wichtounet/mnist)
 - [Java](https://stackoverflow.com/a/8301949)
-- [Python](https://pypi.python.org/pypi/python-mnist) and [this](https://pypi.python.org/pypi/mnist) and [this]((https://www.brine.io/fashion-mnist/train))
+- [Python](https://pypi.python.org/pypi/python-mnist) and [this](https://pypi.python.org/pypi/mnist)
 - [Scala](http://mxnet.io/tutorials/scala/mnist.html)
 - [Go](https://github.com/schuyler/neural-go/blob/master/mnist/mnist.go)
 - [C#](https://jamesmccaffrey.wordpress.com/2013/11/23/reading-the-mnist-data-set-with-c/)
@@ -136,6 +139,7 @@ As one of the Machine Learning community's most popular datasets, MNIST has insp
 - [R](https://gist.github.com/brendano/39760) and [this](https://github.com/maddin79/darch)
 - [Matlab](http://ufldl.stanford.edu/wiki/index.php/Using_the_MNIST_Dataset)
 - [Ruby](https://github.com/gbuesing/mnist-ruby-test/blob/master/train/mnist_loader.rb)
+- [Rust](https://github.com/AtheMathmo/vision-rs/blob/master/src/fashion_mnist.rs)
 
 
 ## Benchmark
@@ -164,7 +168,7 @@ The table below collects the submitted benchmarks. Note that **we haven't yet te
 |3 Conv+2 FC | None | 0.907 | - | [@Cenk Bircanoğlu](https://github.com/cenkbircanoglu) | [:link:](https://github.com/cenkbircanoglu/openface/tree/master/fashion_mnist)|
 |3 Conv+pooling+BN | None | 0.903 | 0.994 | [@meghanabhange](https://github.com/meghanabhange) | [:link:](https://github.com/meghanabhange/FashionMNIST-3-Layer-CNN) |
 |3 Conv+pooling+2 FC+dropout | None | 0.926 | - | [@Umberto Griffo](https://github.com/umbertogriffo) | [:link:](https://github.com/umbertogriffo/Fashion-mnist-cnn-keras)|
-|3 Conv+BN+pooling|None|0.921|0.992|[@GunjanChhablani](https://github.com/GunjanChhablani)|[:link:](https://github.com/GunjanChhablani/CNN-with-FashionMNIST)| 
+|3 Conv+BN+pooling|None|0.921|0.992|[@gchhablani](https://github.com/gchhablani)|[:link:](https://github.com/gchhablani/CNN-with-FashionMNIST)| 
 |5 Conv+BN+pooling|None|0.931|-|[@Noumanmufc1](https://github.com/Noumanmufc1)|[:link:](https://gist.github.com/Noumanmufc1/60f00e434f0ce42b6f4826029737490a)| 
 |CNN with optional shortcuts, dense-like connectivity| standardization+augmentation+random erasing | 0.947 |-| [@kennivich](https://github.com/Dezhic) | [:link:](https://github.com/Dezhic/fashion-classifier)|
 |GRU+SVM | None| 0.888 | 0.965 | [@AFAgarap](https://github.com/AFAgarap) | [:link:](https://gist.githubusercontent.com/AFAgarap/92c1c4a5dd771999b0201ec0e7edfee0/raw/828fbda0e466dacb1fad66549e0e3022e1c7263a/gru_svm_zalando.py)|
@@ -188,6 +192,7 @@ The table below collects the submitted benchmarks. Note that **we haven't yet te
 |DENSER| - | 0.953| 0.997| [@fillassuncao](https://github.com/fillassuncao)| [:link:](https://github.com/fillassuncao/denser-models) [:link:](https://arxiv.org/pdf/1801.01563.pdf)|
 |Dyra-Net| Rescale to unit interval | 0.906| -| [@Dirk Schäfer](https://github.com/disc5)| [:link:](https://github.com/disc5/dyra-net) [:link:](https://dl.acm.org/citation.cfm?id=3204176.3204200)|
 |Google AutoML|24 compute hours (higher quality)| 0.939|-| [@Sebastian Heinz](https://github.com/sebastianheinz) |[:link:](https://www.statworx.com/de/blog/a-performance-benchmark-of-google-automl-vision-using-fashion-mnist/)|
+|Fastai| Resnet50+Fine-tuning+Softmax on last layer's activations| 0.9312| - | [@Sayak](https://github.com/sayakpaul) | [:link:](https://github.com/sayakpaul/Experiments-on-Fashion-MNIST/)|
 
 
 ### Other Explorations of Fashion-MNIST
@@ -236,6 +241,9 @@ Apache MXNet으로 배워보는 딥러닝(Deep Learning) - 김무현 (AWS 솔루
 ### [UMAP](https://github.com/lmcinnes/umap) on Fashion-MNIST (left) and original MNIST (right) 
 <img src="doc/img/umap_example_fashion_mnist1.png" width="50%"><img src="doc/img/umap_example_mnist1.png" width="50%">
 
+### [PyMDE](https://github.com/cvxgrp/pymde) on Fashion-MNIST (left) and original MNIST (right) 
+<img src="doc/img/pymde_example_fashion_mnist.png" width="50%"><img src="doc/img/pymde_example_mnist.png" width="50%">
+
 
 ## Contributing
 
diff --git a/README.zh-CN.md b/README.zh-CN.md
index dc399a8..e51d707 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -106,21 +106,23 @@ data.train.next_batch(BATCH_SIZE)
 data = input_data.read_data_sets('data/fashion', source_url='http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/')
 ```
 
-Tensorflow的官网也提供了一份使用高级API`tf.keras`训练Fashion-MNIST的详细教程，[你可以在这里查看它](https://www.tensorflow.org/tutorials/keras/basic_classification)。
+Tensorflow的官网也提供了一份使用高级API`tf.keras`训练Fashion-MNIST的详细教程，[你可以在这里查看它](https://www.tensorflow.org/tutorials/keras/classification)。
 
 ### 使用其它机器学习库
 截止今日，以下软件库中已内置了对`Fashion-MNIST`的支持。你只需要按照他们的文档载入`Fashion-MNIST`即可使用此数据集。
-- [Apache MXNet Gluon](https://mxnet.incubator.apache.org/api/python/gluon/data.html)
-- [deeplearn.js](https://deeplearnjs.org/demos/model-builder/)
+- [Apache MXNet Gluon](https://mxnet.apache.org/api/python/docs/api/gluon/data/vision/datasets/index.html#mxnet.gluon.data.vision.datasets.FashionMNIST)
+- [TensorFlow.js](https://github.com/tensorflow/tfjs-examples/blob/master/fashion-mnist-vae/data.js)
 - [Kaggle](https://www.kaggle.com/zalando-research/fashionmnist)
-- [Pytorch](http://pytorch.org/docs/master/torchvision/datasets.html#fashion-mnist)
-- [Keras](https://keras.io/datasets/#fashion-mnist-database-of-fashion-articles)
+- [Pytorch](https://pytorch.org/vision/stable/datasets.html#fashion-mnist)
+- [Keras](https://keras.io/api/datasets/fashion_mnist/)
 - [Edward](http://edwardlib.org/api/observations/fashion_mnist)
-- [Tensorflow](https://www.tensorflow.org/versions/r1.5/api_docs/python/tf/keras/datasets/fashion_mnist)
+- [Tensorflow](https://www.tensorflow.org/api_docs/python/tf/keras/datasets/fashion_mnist)
+- [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/fashion_mnist)
 - [Torch](https://github.com/mingloo/fashion-mnist)
-- [JuliaML](https://github.com/JuliaML/MLDatasets.jl)
-- [Chainer (latest)](https://docs.chainer.org/en/latest/reference/generated/chainer.datasets.get_fashion_mnist.html?highlight=fashion-mnist)
-
+- [JuliaML](https://juliaml.github.io/MLDatasets.jl/latest/datasets/FashionMNIST/)
+- [Chainer](https://docs.chainer.org/en/stable/reference/generated/chainer.datasets.get_fashion_mnist.html)
+- [HuggingFace Datasets](https://huggingface.co/datasets/fashion_mnist)
+- 
 欢迎你同我们一起，为各个机器学习库增加对`Fashion-MNIST`的支持。
 
 
@@ -131,7 +133,7 @@ Tensorflow的官网也提供了一份使用高级API`tf.keras`训练Fashion-MNIS
 - [C](https://stackoverflow.com/a/10409376)
 - [C++](https://github.com/wichtounet/mnist)
 - [Java](https://stackoverflow.com/a/8301949)
-- [Python](https://pypi.python.org/pypi/python-mnist) and [this](https://pypi.python.org/pypi/mnist) and [this](https://www.brine.io/fashion-mnist/train)
+- [Python](https://pypi.python.org/pypi/python-mnist) and [this](https://pypi.python.org/pypi/mnist)
 - [Scala](http://mxnet.io/tutorials/scala/mnist.html)
 - [Go](https://github.com/schuyler/neural-go/blob/master/mnist/mnist.go)
 - [C#](https://jamesmccaffrey.wordpress.com/2013/11/23/reading-the-mnist-data-set-with-c/)
@@ -140,6 +142,7 @@ Tensorflow的官网也提供了一份使用高级API`tf.keras`训练Fashion-MNIS
 - [R](https://gist.github.com/brendano/39760)和[这里](https://github.com/maddin79/darch)
 - [Matlab](http://ufldl.stanford.edu/wiki/index.php/Using_the_MNIST_Dataset)
 - [Ruby](https://github.com/gbuesing/mnist-ruby-test/blob/master/train/mnist_loader.rb)
+- [Rust](https://github.com/AtheMathmo/vision-rs/blob/master/src/fashion_mnist.rs)
 
 
 ## 基准测试
@@ -168,7 +171,7 @@ Tensorflow的官网也提供了一份使用高级API`tf.keras`训练Fashion-MNIS
 |3 Conv+2 FC | None | 0.907 | - | [@Cenk Bircanoğlu](https://github.com/cenkbircanoglu) | [:link:](https://github.com/cenkbircanoglu/openface/tree/master/fashion_mnist)|
 |3 Conv+pooling+BN | None | 0.903 | 0.994 | [@meghanabhange](https://github.com/meghanabhange) | [:link:](https://github.com/meghanabhange/FashionMNIST-3-Layer-CNN) |
 |3 Conv+pooling+2 FC+dropout | None | 0.926 | - | [@Umberto Griffo](https://github.com/umbertogriffo) | [:link:](https://github.com/umbertogriffo/Fashion-mnist-cnn-keras)|
-|3 Conv+BN+pooling|None|0.921|0.992|[@GunjanChhablani](https://github.com/GunjanChhablani)|[:link:](https://github.com/GunjanChhablani/CNN-with-FashionMNIST)| 
+|3 Conv+BN+pooling|None|0.921|0.992|[@gchhablani](https://github.com/gchhablani)|[:link:](https://github.com/gchhablani/CNN-with-FashionMNIST)| 
 |5 Conv+BN+pooling|None|0.931|-|[@Noumanmufc1](https://github.com/Noumanmufc1)|[:link:](https://gist.github.com/Noumanmufc1/60f00e434f0ce42b6f4826029737490a)| 
 |CNN with optional shortcuts, dense-like connectivity| standardization+augmentation+random erasing | 0.947 |-| [@kennivich](https://github.com/Dezhic) | [:link:](https://github.com/Dezhic/fashion-classifier)|
 |GRU+SVM | None| 0.888 | 0.965 | [@AFAgarap](https://github.com/AFAgarap) | [:link:](https://gist.githubusercontent.com/AFAgarap/92c1c4a5dd771999b0201ec0e7edfee0/raw/828fbda0e466dacb1fad66549e0e3022e1c7263a/gru_svm_zalando.py)|
@@ -192,7 +195,7 @@ Tensorflow的官网也提供了一份使用高级API`tf.keras`训练Fashion-MNIS
 |DENSER| - | 0.953| 0.997| [@fillassuncao](https://github.com/fillassuncao)| [:link:](https://github.com/fillassuncao/denser-models) [:link:](https://arxiv.org/pdf/1801.01563.pdf)|
 |Dyra-Net| Rescale to unit interval | 0.906| -| [@Dirk Schäfer](https://github.com/disc5)| [:link:](https://github.com/disc5/dyra-net) [:link:](https://dl.acm.org/citation.cfm?id=3204176.3204200)|
 |Google AutoML|24 compute hours (higher quality)| 0.939|-| [@Sebastian Heinz](https://github.com/sebastianheinz) |[:link:](https://www.statworx.com/de/blog/a-performance-benchmark-of-google-automl-vision-using-fashion-mnist/)|
-
+|Fastai| Resnet50+Fine-tuning+Softmax on last layer's activations| 0.9312| - | [@Sayak](https://github.com/sayakpaul) | [:link:](https://github.com/sayakpaul/Experiments-on-Fashion-MNIST/)|
 ### 更多在Fashion-MNIST上的探索和尝试
 
 #### [Fashion-MNIST: 年度总结](https://hanxiao.github.io/2018/09/28/Fashion-MNIST-Year-In-Review/)
@@ -203,7 +206,6 @@ Tensorflow的官网也提供了一份使用高级API`tf.keras`训练Fashion-MNIS
 - [Make a ghost wardrobe using DCGAN](https://twitter.com/spaceLenny/status/901488938023403520)
 - [fashion-mnist的gan玩具](http://kexue.fm/archives/4540/)
 - [CGAN output after 5000 steps](https://github.com/a7b23/Conditional-GAN-using-tensorflow-slim)
-- [live demo of Generative Adversarial Network model with deeplearn.js](http://cognitivechaos.com/playground/fashion-gan/)
 - [GAN Playground - Explore Generative Adversarial Nets in your Browser](https://reiinakano.github.io/gan-playground/)
 
 #### 聚类
@@ -241,6 +243,8 @@ Apache MXNet으로 배워보는 딥러닝(Deep Learning) - 김무현 (AWS 솔루
 ### [UMAP](https://github.com/lmcinnes/umap)在Fashion-MNIST(左侧)和经典MNIST上的可视化(右侧)  
 <img src="doc/img/umap_example_fashion_mnist1.png" width="50%"><img src="doc/img/umap_example_mnist1.png" width="50%">
 
+### [PyMDE](https://github.com/cvxgrp/pymde)在Fashion-MNIST(左侧)和经典MNIST上的可视化(右侧)  
+<img src="doc/img/pymde_example_fashion_mnist.png" width="50%"><img src="doc/img/pymde_example_mnist.png" width="50%">
 
 ## 参与贡献
 我们热烈欢迎您参与贡献这个项目。[请先阅读这里！](/CONTRIBUTING.md) 并查看有什么[open issues](https://github.com/zalandoresearch/fashion-mnist/issues)可以帮助解决。
diff --git a/debian/changelog b/debian/changelog
index 39acfaf..d91b19a 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -1,8 +1,9 @@
-dataset-fashion-mnist (0.0~git20200523.55506a9-2) UNRELEASED; urgency=low
+dataset-fashion-mnist (0.0~git20220321.b2617bb-1) UNRELEASED; urgency=low
 
   * Set upstream metadata fields: Bug-Database, Bug-Submit.
+  * New upstream snapshot.
 
- -- Debian Janitor <janitor@jelmer.uk>  Sat, 11 Jul 2020 20:03:54 -0000
+ -- Debian Janitor <janitor@jelmer.uk>  Mon, 24 Oct 2022 00:27:55 -0000
 
 dataset-fashion-mnist (0.0~git20200523.55506a9-1) unstable; urgency=medium
 
diff --git a/doc/img/pymde_example_fashion_mnist.png b/doc/img/pymde_example_fashion_mnist.png
new file mode 100644
index 0000000..3c09f4b
Binary files /dev/null and b/doc/img/pymde_example_fashion_mnist.png differ
diff --git a/doc/img/pymde_example_mnist.png b/doc/img/pymde_example_mnist.png
new file mode 100644
index 0000000..e6360b2
Binary files /dev/null and b/doc/img/pymde_example_mnist.png differ
diff --git a/requirements.txt b/requirements.txt
index 1e649a2..fc45692 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,3 +1,2 @@
 scikit-learn>=0.19.0
 psutil>=5.2.2
-

Debdiff

File lists identical (after any substitutions)

No differences were encountered in the control files

More details

Full run details