PyTorch - spinningideas/resources GitHub Wiki

PyTorch is an open source machine learning framework based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Meta AI. It is free and open-source software released under the Modified BSD license

PyTorch was started in October 2016, as an internship project by Adam Paszke In Facebook’s AI Research lab (FAIR). Along with Sam Gross, Soumith Chintala, Gregory Chanan.

• https://pytorch.org/
• https://pytorch.org/tutorials/intermediate/flask_rest_api_tutorial.html
• https://pytorch.org/get-started/cloud-partners/

tensorflow-vs-pytorch

• https://medium.com/@ashishpaikray32/is-pytorch-better-than-tensorflow-e4f5a4c6569c
• https://medium.com/aimluae/tensorflow-vs-pytorch-which-will-be-the-top-deep-learning-framework-in-2022-a3488635029
• https://github.com/spinningideas/resources/wiki/Tensor-Flow

Code

• https://github.com/arition/torch-js

Tutorials

Basic Intro

• https://blog.natml.ai/running-pytorch-models-in-nodejs-3bce7b709891
• https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html
• https://pytorch.org/tutorials/
• https://github.com/yunjey/pytorch-tutorial

More Advanced

• https://github.com/bentrevett/pytorch-image-classification
• https://www.pluralsight.com/guides/image-classification-with-pytorch
• https://www.analyticsvidhya.com/blog/2020/07/how-to-train-an-image-classification-model-in-pytorch-and-tensorflow/
• https://lionbridge.ai/articles/end-to-end-multiclass-image-classification-using-pytorch-and-transfer-learning/
• https://curiousily.com/posts/transfer-learning-for-image-classification-using-torchvision-pytorch-and-python/
• https://github.com/terryz1/Image_Classification_App

Example Apps

PyTorch

• PyTorch DQN TicTacToe
• PyTorch Evolution Strategies TicTacToe
• https://github.com/search?q=react+pytorch
• React, PyTorch, Netlify
• https://github.com/Yolantele/pytorch-react-classifier

pytorch implementation of 2 models: SSD-Resnet50 and SSDLite-MobilenetV2

• https://github.com/uvipen/SSD-pytorch + https://youtu.be/Br0QiEuBMzU

Multi-Label Image Classifier using PyTorch, Flask, ReactJS

• https://thevatsalsaglani.medium.com/training-and-deploying-a-multi-label-image-classifier-using-pytorch-flask-reactjs-and-firebase-28c6150c04c

Run PyTorch models in the browser using ONNX.js

• https://www.youtube.com/watch?v=Vs730jsRgO8
• https://github.com/elliotwaite/pytorch-to-javascript-with-onnx-js

Development

Building

• https://github.com/ahkarami/Deep-Learning-in-Production

Hosting

• https://pytorch.org/blog/model-serving-in-pyorch/

Related Frameworks/Libraries

• PyTorch Hub Research-oriented platform for sharing repositories with a wide range of pre-trained models, including those for Audio, Vision, and NLP.

• TorchServe Open-source deployment framework resulting from a collaboration between AWS and Facebook and was released in 2020. It has basic features like endpoint specification, model archiving, and observing metrics.

• PyTorch Live Released in early 2020 to build upon Mobile. It uses JavaScript and React Native to create cross-platform iOS and Android AI-powered apps with associated UIs.

• TorchVision is PyTorch’s official Computer Vision library. It includes everything you need for your Computer Vision projects, including model architectures and popular datasets.

• TorchText Contains datasets frequently seen in the Natural Language Processing (NLP) domain, as well as data processing utilities to operate on these and other datasets.

• TorchAudio PyTorch’s official audio library. TorchAudio includes popular audio models like DeepSpeech and Wav2Vec, and provides walkthroughs and pipelines for ASR and other tasks.

• SpeechBrain Open-source speech toolkit for PyTorch. SpeechBrain supports ASR, speaker recognition, verification and diarization.

• TorchElastic Released in 2020 and the result of collaboration between AWS and Facebook. It is a tool for distributed training which manages worker processes and coordinates restart behaviors so that you can train models on a cluster of compute nodes which can change dynamically without affecting training.

• PyTorch Lightning Sometimes known as the Keras of PyTorch. Lightning is a useful tool for simplifying the model engineering and training processes in PyTorch.