《深度學習引擎-PyTorch資源集錦》包含大量與 PyTorch (https://pytorch.org/)相關的資源連接,帶你快速玩轉基於神經網絡的深度學習,進入人工智能的神祕領地。連接包括:入門教程,應用實例,圖像、視覺、CNN相關實現,對抗生成網絡、生成模型、GAN實現,機器翻譯、問答系統、NLP實現,先進視覺推理系統,深度強化學習實現,通用神經網絡高級應用等等。html
入門系列教程
- PyTorch Tutorials
https://github.com/MorvanZhou/PyTorch-Tutorial.git
著名的「莫煩」PyTorch系列教程的源碼。
- Deep Learning with PyTorch: a 60-minute blitz
http://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html
PyTorch官網推薦的由網友提供的60分鐘教程,本系列教程的重點在於介紹PyTorch的基本原理,包括自動求導,神經網絡,以及偏差優化API。
- Simple examples to introduce PyTorch
https://github.com/jcjohnson/pytorch-examples.git
由網友提供的PyTorch教程,經過一些實例的方式,講解PyTorch的基本原理。內容涉及Numpy、自動求導、參數優化、權重共享等。
-
PyTorch支持Kubernetes集羣, https://my.oschina.net/u/2306127/blog/1817835python
入門實例
- Ten minutes pyTorch Tutorial
https://github.com/SherlockLiao/pytorch-beginner.git
知乎上「十分鐘學習PyTorch「系列教程的源碼。
- Official PyTorch Examples
https://github.com/pytorch/examples
官方提供的實例源碼,包括如下內容:
MNIST Convnets
Word level Language Modeling using LSTM RNNs
Training Imagenet Classifiers with Residual Networks
Generative Adversarial Networks (DCGAN)
Variational Auto-Encoders
Superresolution using an efficient sub-pixel convolutional neural network
Hogwild training of shared ConvNets across multiple processes on MNIST
Training a CartPole to balance in OpenAI Gym with actor-critic
Natural Language Inference (SNLI) with GloVe vectors, LSTMs, and torchtext
Time sequence prediction - create an LSTM to learn Sine waves
- PyTorch Tutorial for Deep Learning Researchers
https://github.com/yunjey/pytorch-tutorial.git
聽說是提供給深度學習科研者們的PyTorch教程←_←。教程中的每一個實例的代碼都控制在30行左右,簡單易懂,內容以下:
PyTorch Basics
Linear Regression
Logistic Regression
Feedforward Neural Network
Convolutional Neural Network
Deep Residual Network
Recurrent Neural Network
Bidirectional Recurrent Neural Network
Language Model (RNN-LM)
Generative Adversarial Network
Image Captioning (CNN-RNN)
Deep Convolutional GAN (DCGAN)
Variational Auto-Encoder
Neural Style Transfer
TensorBoard in PyTorch
- PyTorch-playground
https://github.com/aaron-xichen/pytorch-playground.git
PyTorch初學者的Playground,在這裏針對一下經常使用的數據集,已經寫好了一些模型,因此你們能夠直接拿過來玩玩看,目前支持如下數據集的模型。
mnist, svhn
cifar10, cifar100
stl10
alexnet
vgg16, vgg16_bn, vgg19, vgg19_bn
resnet18, resnet34, resnet50, resnet101, resnet152
squeezenet_v0, squeezenet_v1
inception_v3
圖像、視覺、CNN相關實現
- PyTorch-FCN
https://github.com/wkentaro/pytorch-fcn.git
FCN(Fully Convolutional Networks implemented) 的PyTorch實現。
- Attention Transfer
https://github.com/szagoruyko/attention-transfer.git
論文 「Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer」 的PyTorch實現。
- Wide ResNet model in PyTorch
https://github.com/szagoruyko/functional-zoo.git
一個PyTorch實現的 ImageNet Classification 。
- CRNN for image-based sequence recognition
https://github.com/bgshih/crnn.git
這個是 Convolutional Recurrent Neural Network (CRNN) 的 PyTorch 實現。CRNN 由一些CNN,RNN和CTC組成,經常使用於基於圖像的序列識別任務,例如場景文本識別和OCR。
- Scaling the Scattering Transform: Deep Hybrid Networks
https://github.com/edouardoyallon/pyscatwave.git
使用了「scattering network」的CNN實現,特別的構架提高了網絡的效果。
- Conditional Similarity Networks (CSNs)
https://github.com/andreasveit/conditional-similarity-networks.git
《Conditional Similarity Networks》的PyTorch實現。
- Multi-style Generative Network for Real-time Transfer
https://github.com/zhanghang1989/PyTorch-Style-Transfer.git
MSG-Net 以及 Neural Style 的 PyTorch 實現。
- Big batch training
https://github.com/eladhoffer/bigBatch.git
《Train longer, generalize better: closing the generalization gap in large batch training of neural networks》的 PyTorch 實現。
- CortexNet
https://github.com/e-lab/pytorch-CortexNet.git
一個使用視頻訓練的魯棒預測深度神經網絡。
- Neural Message Passing for Quantum Chemistry
https://github.com/priba/nmp_qc.git
論文《Neural Message Passing for Quantum Chemistry》的PyTorch實現,好像是講計算機視覺下的神經信息傳遞。
對抗生成網絡、生成模型、GAN相關實現
- Generative Adversarial Networks (GANs) in PyTorch
https://github.com/devnag/pytorch-generative-adversarial-networks.git
一個很是簡單的由PyTorch實現的對抗生成網絡
- DCGAN & WGAN with Pytorch
https://github.com/chenyuntc/pytorch-GAN.git
由中國網友實現的DCGAN和WGAN,代碼很簡潔。
- Official Code for WGAN
https://github.com/martinarjovsky/WassersteinGAN.git
WGAN的官方PyTorch實現。
- DiscoGAN in PyTorch
https://github.com/carpedm20/DiscoGAN-pytorch.git
《Learning to Discover Cross-Domain Relations with Generative Adversarial Networks》的 PyTorch 實現。
- Adversarial Generator-Encoder Network
https://github.com/DmitryUlyanov/AGE.git
《Adversarial Generator-Encoder Networks》的 PyTorch 實現。
- CycleGAN and pix2pix in PyTorch
https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix.git
圖到圖的翻譯,著名的 CycleGAN 以及 pix2pix 的PyTorch 實現。
- Weight Normalized GAN
https://github.com/stormraiser/GAN-weight-norm.git
《On the Effects of Batch and Weight Normalization in Generative Adversarial Networks》的 PyTorch 實現。
機器翻譯、問答系統、NLP相關實現
- DeepLearningForNLPInPytorch
https://github.com/rguthrie3/DeepLearningForNLPInPytorch.git
一套以 NLP 爲主題的 PyTorch 基礎教程。本教程使用Ipython Notebook編寫,看起來很直觀,方便學習。
- Practial Pytorch with Topic RNN & NLP
https://github.com/spro/practical-pytorch
以 RNN for NLP 爲出發點的 PyTorch 基礎教程,分爲「RNNs for NLP」和「RNNs for timeseries data」兩個部分。
- PyOpenNMT: Open-Source Neural Machine Translation
https://github.com/OpenNMT/OpenNMT-py.git
一套由PyTorch實現的機器翻譯系統。(包含,Attention Model)
- Deal or No Deal? End-to-End Learning for Negotiation Dialogues
https://github.com/facebookresearch/end-to-end-negotiator.git
Facebook AI Research 論文《Deal or No Deal? End-to-End Learning for Negotiation Dialogues》的 PyTorch 實現。
- Attention is all you need: A Pytorch Implementation
https://github.com/jadore801120/attention-is-all-you-need-pytorch.git
Google Research 著名論文《Attention is all you need》的PyTorch實現。Attention Model(AM)。
- Improved Visual Semantic Embeddings
https://github.com/fartashf/vsepp.git
一種從圖像中檢索文字的方法,來自論文:《VSE++: Improved Visual-Semantic Embeddings》。
- Reading Wikipedia to Answer Open-Domain Questions
https://github.com/facebookresearch/DrQA.git
一個開放領域問答系統DrQA的PyTorch實現。
- Structured-Self-Attentive-Sentence-Embedding
https://github.com/ExplorerFreda/Structured-Self-Attentive-Sentence-Embedding.git
IBM 與 MILA 發表的《A Structured Self-Attentive Sentence Embedding》的開源實現。
先進視覺推理系統
- Visual Question Answering in Pytorch
https://github.com/Cadene/vqa.pytorch.git
一個PyTorch實現的優秀視覺推理問答系統,是基於論文《MUTAN: Multimodal Tucker Fusion for Visual Question Answering》實現的。項目中有詳細的配置使用方法說明。
- Clevr-IEP
https://github.com/facebookresearch/clevr-iep.git
Facebook Research 論文《Inferring and Executing Programs for Visual Reasoning》的PyTorch實現,講的是一個能夠基於圖片進行關係推理問答的網絡。
深度強化學習相關實現
- Deep Reinforcement Learning withpytorch & visdom
https://github.com/onlytailei/pytorch-rl.git
多種使用PyTorch實現強化學習的方法。
- Value Iteration Networks in PyTorch
https://github.com/onlytailei/Value-Iteration-Networks-PyTorch.git
Value Iteration Networks (VIN) 的PyTorch實現。
- A3C in PyTorch
https://github.com/onlytailei/A3C-PyTorch.git
Adavantage async Actor-Critic (A3C) 的PyTorch實現。
通用神經網絡高級應用
- PyTorch-meta-optimizer
https://github.com/ikostrikov/pytorch-meta-optimizer.git
論文《Learning to learn by gradient descent by gradient descent》的PyTorch實現。
- OptNet: Differentiable Optimization as a Layer in Neural Networks
https://github.com/locuslab/optnet.git
論文《Differentiable Optimization as a Layer in Neural Networks》的PyTorch實現。
- Task-based End-to-end Model Learning
https://github.com/locuslab/e2e-model-learning.git
論文《Task-based End-to-end Model Learning》的PyTorch實現。
- DiracNets
https://github.com/szagoruyko/diracnets.git
不使用「Skip-Connections」而搭建特別深的神經網絡的方法。
- ODIN: Out-of-Distribution Detector for Neural Networks
https://github.com/ShiyuLiang/odin-pytorch.git
這是一個可以檢測「分佈不足」(Out-of-Distribution)樣本的方法的PyTorch實現。當「true positive rate」爲95%時,該方法將DenseNet(適用於CIFAR-10)的「false positive rate」從34.7%降至4.3%。
- Accelerate Neural Net Training by Progressively Freezing Layers
https://github.com/ajbrock/FreezeOut.git
一種使用「progressively freezing layers」來加速神經網絡訓練的方法。
- Efficient_densenet_pytorch
https://github.com/gpleiss/efficient_densenet_pytorch.git DenseNets的PyTorch實現,優化以節省GPU內存。