This article collects a large number of code links based on Pytorch implementations, including "Getting Started" series for beginners in depth learning, and paper code implementations for older drivers, including Attention Based CNN, A3C, Wgan, and more. All code is categorized according to the technical domain, including machine vision/image correlation, natural language processing related, reinforcement learning related, and so on. So if you're going to start the Pytorch technology of the first world, then quickly collect this article.
What Pytorch is.
Pytorch is the Python version of Torch. Torch is a deep learning framework published by Facebook, which supports dynamic definition of graphs, and is more flexible and convenient to use than TensorFlow, especially for small and medium machine learning programs and deep learning beginners. But because Torch's development language is LUA, it has been a minority in the country. Therefore, under the long-awaited, Pytorch emerged. Pytorch inherits the flexibility of Troch and uses popular Python as a development language, so it's popular once it's launched.
Directory:
Getting Started series tutorials
Getting Started example
Image, vision, CNN related implementation
Countermeasure generation network, generation model, Gan correlation implementation
Machine translation, question answering system, NLP related implementation
Advanced Vision Inference System
Deep Reinforcement Learning related realization
Advanced application of General neural network
1
Getting Started series tutorials
1.PyTorch Tutorials
Https://github.com/MorvanZhou/PyTorch-Tutorial.git
The famous "Mo Annoying" pytorch series of tutorials in the source code.
2.Deep Learning with pytorch:a 60-minute Blitz
Http://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html
Pytorch's website recommends a 60-minute tutorial, which focuses on introducing the fundamentals of Pytorch, including automatic derivation, neural networks, and error-tuning APIs.
3.Simple examples to introduce pytorch
Https://github.com/jcjohnson/pytorch-examples.git
Pytorch tutorials provided by users, through a number of examples of ways to explain the basic principles of pytorch. The content involves NumPy, automatic derivation, parameter optimization, weight sharing and so on.
2
Getting Started example
1.Ten minutes Pytorch Tutorial
Https://github.com/SherlockLiao/pytorch-beginner.git
Know the source of the "10-minute Learning Pytorch" series tutorial.
2.Official Pytorch Examples
Https://github.com/pytorch/examples
Official examples of source code, including the following:
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 a lstm to learn Sine waves
3.PyTorch Tutorial for Deep Learning researchers
Https://github.com/yunjey/pytorch-tutorial.git
It is said to be a pytorch tutorial ←_← for deep learning scientists. The code for each instance in the tutorial is controlled in about 30 lines, which is easy to understand and reads as follows:
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
4pytorch-playground
Https://github.com/aaron-xichen/pytorch-playground.git
Pytorch Beginners of the playground, here for the common data set, has written some models, so you can directly to play to see, currently supports the following data set model.
Mnist, Svhn
Cifar10, cifar100
Stl10
Alexnet
Vgg16, Vgg16_bn, Vgg19, vgg19_bn
resnet18, Resnet34, Resnet50, resnet101, resnet152
Squeezenet_v0, SQUEEZENET_V1
Inception_v3
3
Image, vision, CNN related implementation
1.pytorch-fcn
Https://github.com/wkentaro/pytorch-fcn.git
Implemented implementation of FCN (fully convolutional Networks pytorch).
2.Attention Transfer
Https://github.com/szagoruyko/attention-transfer.git
Paper "Paying more Attention to attention:improving the performance of convolutional neural via Networks Attention" Implementation of the Pytorch.
3.Wide ResNet model in Pytorch
Https://github.com/szagoruyko/functional-zoo.git
A pytorch implementation of the Imagenet classification.
4.CRNN for image-based sequence recognition
Https://github.com/bgshih/crnn.git
This is the CRNN implementation of convolutional recurrent neural Network (pytorch). CRNN consists of a number of cnn,rnn and CTC, often used for image-based sequence recognition tasks, such as scene text recognition and OCR.
5.Scaling the scattering transform:deep Hybrid Networks
Https://github.com/edouardoyallon/pyscatwave.git
Using the "Scattering network" CNN implementation, the special architecture improves the network's effectiveness.
6.Conditional similarity Networks (CSNs)
Https://github.com/andreasveit/conditional-similarity-networks.git
The Pytorch realization of "Conditional similarity Networks".
7.multi-style generative network for real-time Transfer
Https://github.com/zhanghang1989/PyTorch-Style-Transfer.git
Msg-net and the Pytorch implementation of neural Style.
8.Big Batch Training
Https://github.com/eladhoffer/bigBatch.git
Generalization implementation of the Train longer, generalize better:closing large gap in batch training neural of networks.
9.CortexNet
Https://github.com/e-lab/pytorch-CortexNet.git
A robust predictive depth neural network using video training.
10.Neural message passing for Quantum chemistry
Https://github.com/priba/nmp_qc.git
The Pytorch realization of the neural message passing for Quantum chemistry is like the transmission of neural information under computer vision.
4
Countermeasure generation network, generation model, Gan correlation implementation
1.Generative adversarial Networks (Gans) in Pytorch
Https://github.com/devnag/pytorch-generative-adversarial-networks.git
A very simple confrontation generation network implemented by Pytorch
2.DCGAN & Wgan with Pytorch
Https://github.com/chenyuntc/pytorch-GAN.git
Dcgan and Wgan implemented by Chinese netizens, the code is very concise.
3.Official Code for Wgan
Https://github.com/martinarjovsky/WassersteinGAN.git
The official pytorch of Wgan is realized.
4.DiscoGAN in Pytorch
Https://github.com/carpedm20/DiscoGAN-pytorch.git
Generative implementation of the Learning to Discover Cross-domain Relations with adversarial Networks pytorch.
5.Adversarial Generator-encoder Network
Https://github.com/DmitryUlyanov/AGE.git
The Pytorch realization of "adversarial generator-encoder Networks".
6.CycleGAN and Pix2pix in Pytorch
Https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix.git
The translation of diagrams to graphs, the famous Cyclegan and the Pytorch implementations of Pix2pix.
7.Weight normalized GAN
Https://github.com/stormraiser/GAN-weight-norm.git
The generative implementation of the effects of Batch and Weight normalization in adversarial Networks.
5
Machine translation, question answering system, NLP related implementation
1.DeepLearningForNLPInPytorch
Https://github.com/rguthrie3/DeepLearningForNLPInPytorch.git
A set of Pytorch basic tutorials with NLP as its theme. This tutorial is written using Ipython notebook, which looks intuitive and easy to learn.
2.Practial Pytorch with Topic RNN & NLP
Https://github.com/spro/practical-pytorch
The Pytorch basic tutorials, starting with RNN for NLP, are divided into "Rnns for NLP" and "Rnns for timeseries data" two sections.
3.pyopennmt:open-source Neural Machine Translation
Https://github.com/OpenNMT/OpenNMT-py.git
A set of machine translation system implemented by Pytorch.
4.Deal or No Deal? End-to-end Learning for negotiation dialogues
Https://github.com/facebookresearch/end-to-end-negotiator.git
Facebook AI Research paper "Deal or No Deal"? End-to-end Learning for negotiation dialogues "Pytorch implementation.
5.Attention is all need:a pytorch implementation
Https://github.com/jadore801120/attention-is-all-you-need-pytorch.git
Google Research, the famous paper "Attention is the all you need" pytorch implementation.
6.Improved Visual Semantic embeddings
Https://github.com/fartashf/vsepp.git
A method of retrieving text from an image is derived from the thesis: "vse++: Improved Visual-semantic embeddings".
7.Reading Wikipedia to Answer open-domain Questions
Https://github.com/facebookresearch/DrQA.git
An open domain question and answer system Drqa pytorch implementation.