PyTorch資源列表:450個NLP/CV/SP、論文實現、教程、示例
新智元推薦
來源:專知(Quan_Zhuanzhi)
【新智元導讀】bharathgs在Github上維護整理了一個PyTorch的資源站,包括論文、代碼、教程等,涉及自然語言處理與語音處理、計算機視覺、機器學習、深度學習等庫,是學習Pytorch必選資源。
項目地址:
https://github.com/bharathgs/Awesome-pytorch-list
PyTorch 是什麼?
PyTorch是一個用於科學計算和深度學習的Python擴展庫。它便於學習、編寫和調試,支持靈活的動態計算圖和GPU高速運算,具有完善的研發生態和技術社區。PyTorch於2017年由Facebook正式推出後,迅速引起了人工智慧研發人員的關注,目前已成為最受重視的機器學習軟體庫之一。近日,Facebook 在首屆 PyTorch 開發者大會發布了PyTorch1.0 預覽版,標誌著這一框架更為穩定可用。
目錄
一. 自然語言與語音處理NLP & Speech Processing
二. 計算機視覺CV
三. 概率生成庫
四. 其他庫
五. 教程和例子
六. 論文實現
七.其他Pytorch資源
目錄內容
Pytorch 官網
項目鏈接:https://github.com/pytorch/pytorch/releases
一. 自然語言與語音處理
pytorch text : Torch text related contents.
pytorch-seq2seq: A framework for sequence-to-sequence (seq2seq) models implemented in PyTorch.
anuvada: Interpretable Models for NLP using PyTorch.
audio: simple audio I/O for pytorch.
loop: A method to generate speech across multiple speakers
fairseq-py: Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
speech: PyTorch ASR Implementation.
OpenNMT-py: Open-Source Neural Machine Translation in PyTorch http://opennmt.net
neuralcoref: State-of-the-art coreference resolution based on neural nets and spaCy huggingface.co/coref
sentiment-discovery: Unsupervised Language Modeling at scale for robust sentiment classification.
MUSE: A library for Multilingual Unsupervised or Supervised word Embeddings
nmtpytorch: Neural Machine Translation Framework in PyTorch.
pytorch-wavenet: An implementation of WaveNet with fast generation
Tacotron-pytorch: Tacotron: Towards End-to-End Speech Synthesis.
AllenNLP: An open-source NLP research library, built on PyTorch.
PyTorch-NLP: Text utilities and datasets for PyTorch pytorchnlp.readthedocs.io
quick-nlp: Pytorch NLP library based on FastAI.
TTS: Deep learning for Text2Speech
LASER: Language-Agnostic SEntence Representations
pyannote-audio: Neural building blocks for speaker diarization: speech activity detection, speaker change detection, speaker embedding
gensen: Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning.
translate: Translate - a PyTorch Language Library.
espnet: End-to-End Speech Processing Toolkit espnet.github.io/espnet
pythia: A software suite for Visual Question Answering
UnsupervisedMT: Phrase-Based & Neural Unsupervised Machine Translation.
jiant: The jiant sentence representation learning toolkit.
二. 計算機視覺
三. 概率生成庫
ptstat: Probabilistic Programming and Statistical Inference in PyTorch
pyro: Deep universal probabilistic programming with Python and PyTorch http://pyro.ai
probtorch: Probabilistic Torch is library for deep generative models that extends PyTorch.
paysage: Unsupervised learning and generative models in python/pytorch.
pyvarinf: Python package facilitating the use of Bayesian Deep Learning methods with Variational Inference for PyTorch.
pyprob: A PyTorch-based library for probabilistic programming and inference compilation.
mia: A library for running membership inference attacks against ML models.
四. 其他庫
pytorch extras : Some extra features for pytorch.
functional zoo : PyTorch, unlike lua torch, has autograd in it"s core, so using modular structure of torch.nn modules is not necessary, one can easily allocate needed Variables and write a function that utilizes them, which is sometimes more convenient. This repo contains model definitions in this functional way, with pretrained weights for some models.
torch-sampling : This package provides a set of transforms and data structures for sampling from in-memory or out-of-memory data.
torchcraft-py : Python wrapper for TorchCraft, a bridge between Torch and StarCraft for AI research.
aorun : Aorun intend to be a Keras with PyTorch as backend.
logger : A simple logger for experiments.
PyTorch-docset : PyTorch docset! use with Dash, Zeal, Velocity, or LovelyDocs.
convert_torch_to_pytorch : Convert torch t7 model to pytorch model and source.
pretrained-models.pytorch: The goal of this repo is to help to reproduce research papers results.
pytorch_fft : PyTorch wrapper for FFTs
五. 教程例子
Practical Pytorch: Tutorials explaining different RNN models
DeepLearningForNLPInPytorch : An IPython Notebook tutorial on deep learning, with an emphasis on Natural Language Processing.
pytorch-tutorial : tutorial for researchers to learn deep learning with pytorch.
pytorch-exercises : pytorch-exercises collection.
pytorch tutorials : Various pytorch tutorials.
pytorch examples : A repository showcasing examples of using pytorch
pytorch practice : Some example scripts on pytorch.
pytorch mini tutorials : Minimal tutorials for PyTorch adapted from Alec Radford"s Theano tutorials.
pytorch text classification : A simple implementation of CNN based text classification in Pytorch
cats vs dogs : Example of network fine-tuning in pytorch for the kaggle competition Dogs vs. Cats Redux: Kernels Edition. Currently #27 (0.05074) on the leaderboard.
六. 論文實現
google_evolution : This implements one of result networks from Large-scale evolution of image classifiers by Esteban Real, et. al.
pyscatwave : Fast Scattering Transform with CuPy/PyTorch,read the paper here
scalingscattering : Scaling The Scattering Transform : Deep Hybrid Networks.
deep-auto-punctuation : a pytorch implementation of auto-punctuation learned character by character.
Realtime_Multi-Person_Pose_Estimation : This is a pytorch version of Realtime_Multi-Person_Pose_Estimation, origin code is here .
PyTorch-value-iteration-networks : PyTorch implementation of the Value Iteration Networks (NIPS "16) paper
pytorch_Highway : Highway network implemented in pytorch.
pytorch_NEG_loss : NEG loss implemented in pytorch.
pytorch_RVAE : Recurrent Variational Autoencoder that generates sequential data implemented in pytorch.
pytorch_TDNN : Time Delayed NN implemented in pytorch.
七. 其他Pytorch資源
詳細資源請看項目地址。
新智元AI WORLD 2018
世界人工智慧峰會全程回顧
新智元於9月20日在北京國家會議中心舉辦AI WORLD 2018世界人工智慧峰會,邀請機器學習教父、CMU教授 Tom Mitchell,邁克思·泰格馬克,周志華,陶大程,陳怡然等AI領袖一起關注機器智能與人類命運。
全程回顧新智元 AI World 2018 世界人工智慧峰會盛況:
愛奇藝
上午:https://www.iqiyi.com/v_19rr54cusk.html
下午:https://www.iqiyi.com/v_19rr54hels.html
新浪:http://video.sina.com.cn/l/p/1724373.html
※神經網路突變自動選擇AI優化演算法,速度提升50000倍!
※最新GAN教程,153PPT附代碼
TAG:新智元 |