35

GitHub趋势榜第一：TensorFlow+PyTorch深度学习资源大汇总

 4 years ago
source link: https://www.tuicool.com/articles/aq2eiav
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.

加入极市 专业CV交流群，与 6000+来自腾讯，华为，百度，北大，清华，中科院 等名企名校视觉开发者互动交流！更有机会与 李开复老师 等大牛群内互动！

同时提供每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流 。 点击文末“ 阅读原文 ”立刻申请入群~

本文转自公众号新智元

【导读】 该项目是Jupyter Notebook中TensorFlow和PyTorch的各种深度学习架构，模型和技巧的集合。内容非常丰富，适用于Python 3.7，适合当做工具书。

本文搜集整理了Jupyter Notebook中TensorFlow和PyTorch的各种深度学习架构，模型和技巧，内容非常丰富，适用于Python 3.7，适合当做工具书。

大家可以将内容按照需要进行分割，打印出来，或者做成电子书等，随时查阅。

传统机器学习

感知器

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/basic-ml/perceptron.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/basic-ml/perceptron.ipynb

逻辑回归

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/basic-ml/logistic-regression.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/basic-ml/logistic-regression.ipynb

Softmax Regression (Multinomial Logistic Regression)

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/basic-ml/softmax-regression.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/basic-ml/softmax-regression.ipynb

多层感知器

多层感知器

多层感知器

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mlp/mlp-basic.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-basic.ipynb

具有Dropout多层感知器

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mlp/mlp-dropout.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-dropout.ipynb

具有批量归一化的多层感知器

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mlp/mlp-batchnorm.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-batchnorm.ipynb

具有反向传播的多层感知器

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mlp/mlp-lowlevel.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-fromscratch__sigmoid-mse.ipynb

CNN

基础

CNN

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/cnn/convnet.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-basic.ipynb

具有He初始化的CNN

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-he-init.ipynb

概念

用等效卷积层代替完全连接

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/fc-to-conv.ipynb

全卷积

全卷积神经网络

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-allconv.ipynb

AlexNet

AlexNet on CIFAR-10

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-alexnet-cifar10.ipynb

VGG

CNN VGG-16

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/cnn/cnn-vgg16.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-vgg16.ipynb

VGG-16 Gender Classifier Trained on CelebA

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-vgg16-celeba.ipynb

CNN VGG-19

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-vgg19.ipynb

ResNet

ResNet and Residual Blocks

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/resnet-ex-1.ipynb

ResNet-18 Digit Classifier Trained on MNIST

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet18-mnist.ipynb

ResNet-18 Gender Classifier Trained on CelebA

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet18-celeba-dataparallel.ipynb

ResNet-34 Digit Classifier Trained on MNIST

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet34-mnist.ipynb

ResNet-34 Gender Classifier Trained on CelebA

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet34-celeba-dataparallel.ipynb

ResNet-50 Digit Classifier Trained on MNIST

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet50-mnist.ipynb

ResNet-50 Gender Classifier Trained on CelebA

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet50-celeba-dataparallel.ipynb

ResNet-101 Gender Classifier Trained on CelebA

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet101-celeba.ipynb

ResNet-152 Gender Classifier Trained on CelebA

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet152-celeba.ipynb

Network in Network

Network in Network CIFAR-10 Classifier

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/nin-cifar10.ipynb 

度量学习

具有多层感知器的孪生网络

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/metric/siamese-1.ipynb

自动编码机

全连接自动编码机

自动编码机

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/autoencoder/autoencoder.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-basic.ipynb

具有解卷积/转置卷积的卷积自动编码机

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/autoencoder/ae-deconv.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-deconv.ipynb

具有解卷积的卷积自动编码机（无池化操作）

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/aer-deconv-nopool.ipynb

具有最近邻插值的卷积自动编码机

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/autoencoder/autoencoder-conv-nneighbor.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-conv-nneighbor.ipynb

具有最近邻插值的卷积自动编码机 - 在CelebA上进行训练

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-conv-nneighbor-celeba.ipynb

具有最近邻插值的卷积自动编码机 - 在Quickdraw上训练

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-conv-nneighbor-quickdraw-1.ipynb

变分自动编码机

变分自动编码机

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-var.ipynb

卷积变分自动编码机

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-conv-var.ipynb

条件变分自动编码机

条件变分自动编码机（重建丢失中带标签）

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-cvae.ipynb

条件变分自动编码机（重建损失中没有标签）

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-cvae_no-out-concat.ipynb

卷积条件变分自动编码机（重建丢失中带标签）

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-cnn-cvae.ipynb

卷积条件变分自动编码机（重建损失中没有标签）

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/autoencoder/ae-cnn-cvae_no-out-concat.ipynb

GAN

MNIST上完全连接的GAN

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/gan/gan.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gan/gan.ipynb

MNIST上的卷积GAN

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/gan/gan-conv.ipynb

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gan/gan-conv.ipynb

具有标签平滑的MNIST上的卷积GAN

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/gan/gan-conv-smoothing.ipynb

RNN

Many-to-one: Sentiment Analysis / Classification

A simple single-layer RNN (IMDB)

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_simple_imdb.ipynb

A simple single-layer RNN with packed sequences to ignore padding characters (IMDB)

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_simple_packed_imdb.ipynb

RNN with LSTM cells (IMDB)

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_lstm_packed_imdb.ipynb

RNN with LSTM cells and Own Dataset in CSV Format (IMDB)

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_lstm_packed_own_csv_imdb.ipynb

RNN with GRU cells (IMDB)

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_gru_packed_imdb.ipynb

Multilayer bi-directional RNN (IMDB)

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_gru_packed_imdb.ipynb

Many-to-Many / Sequence-to-Sequence

A simple character RNN to generate new text (Charles Dickens)

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/char_rnn-charlesdickens.ipynb

序数回归

Ordinal Regression CNN -CORAL w. ResNet34 on AFAD-Lite

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/ordinal/ordinal-cnn-coral-afadlite.ipynb

Ordinal Regression CNN -Niu et al. 2016 w. ResNet34 on AFAD-Lite

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/ordinal/ordinal-cnn-niu-afadlite.ipynb

Ordinal Regression CNN -Beckham and Pal 2016 w. ResNet34 on AFAD-Lite

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/ordinal/ordinal-cnn-niu-afadlite.ipynb

技巧和窍门

Cyclical Learning Rate

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/tricks/cyclical-learning-rate.ipynb

PyTorch工作流程和机制

自定义数据集

使用PyTorch数据集加载实用程序用于自定义数据集-CSV文件转换为HDF5

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader-csv.ipynb

使用PyTorch数据集加载自定义数据集的实用程序 - 来自CelebA的图像

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader-celeba.ipynb

使用PyTorch数据集加载自定义数据集的实用程序 - 从Quickdraw中提取

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/custom-data-loader-quickdraw.ipynb

使用PyTorch数据集加载实用程序用于自定义数据集 - 从街景房号（SVHN）数据集中绘制

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/custom-data-loader-svhn.ipynb

训练和预处理

带固定内存的数据加载

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-resnet34-cifar10-pinmem.ipynb

标准化图像

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-standardized.ipynb

图像转换示例

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/torchvision-transform-examples.ipynb

Char-RNN with Own Text File

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/char_rnn-charlesdickens.ipynb

Sentiment Classification RNN with Own CSV File

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/rnn/rnn_lstm_packed_own_csv_imdb.ipynb

并行计算

在CelebA上使用具有DataParallel -VGG-16性别分类器的多个GPU

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/cnn/cnn-vgg16-celeba-data-parallel.ipynb

其它 

Sequential API and hooks 

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/mlp-sequential.ipynb

图层内的权重共享

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/cnn-weight-sharing.ipynb

仅使用Matplotlib在Jupyter Notebook中绘制实时训练性能

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mlp/plot-jupyter-matplotlib.ipynb

Autograd

在PyTorch中获取中间变量的渐变

PyTorch：

https://github.com/rasbt/deeplearning-models/blob/master/pytorch_ipynb/mechanics/manual-gradients.ipynb

TensorFlow工作流及机制

自定义数据集

使用NumPy NPZ Archives为Minibatch训练添加图像数据集

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/image-data-chunking-npz.ipynb

使用HDF5存储用于Minibatch培训的图像数据集

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/image-data-chunking-hdf5.ipynb

使用输入Pipeline从TFRecords文件中读取数据

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/tfrecords.ipynb

使用队列运行器直接从磁盘提供图像

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/file-queues.ipynb

使用TensorFlow的Dataset API

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/dataset-api.ipynb

训练和预处理

保存和加载训练模型 - 来自TensorFlow Checkpoint文件和NumPy NPZ Archives

TensorFlow 1：

https://github.com/rasbt/deeplearning-models/blob/master/tensorflow1_ipynb/mechanics/saving-and-reloading-models.ipynb

参考链接：

https://github.com/rasbt/deeplearning-models

*延伸阅读

点击左下角 “ 阅读原文 ”， 即可申请加入极市 目标跟踪、目标检测、工业检测、人脸方向、视觉竞赛等技术交流群， 更有每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流， 一起来让思想之光照的更远吧~

Yjqyyiq.jpg!web

△长按关注极市平台

觉得有用麻烦给个在看啦~    uE7RJjy.gif


report

Recommend

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK