35 Open Source Autograd Software Projects

Tensors and Dynamic neural networks in Python with strong GPU acceleration

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

A C++ standalone library for machine learning

An Engine-Agnostic Deep Learning Framework in Java

Owl - OCaml Scientific and Engineering Computing @ http://ocaml.xyz

C++ Implementation of PyTorch Tutorials for Everyone

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

Notes, examples, and Python demos for the textbook "Machine Learning Refined" (published by Cambridge University Press).

PennyLane is a cross-platform Python library for differentiable programming of quantum computers. Train a quantum computer the same way as a neural network.

『ゼロから作る Deep Learning ❸』(O'Reilly Japan, 2020)

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

Image registration laboratory for 2D and 3D image data

Julia port of the Python autograd package.

Tensors and differentiable operations (like TensorFlow) in Rust

Deep learning with spiking neural networks (SNNs) in PyTorch.

Tiny and elegant deep learning library

scorch is a deep learning framework in Scala inspired by PyTorch

Introductions to key concepts in quantum machine learning, as well as tutorials and implementations from cutting-edge QML research.

Torch Containers simplified in PyTorch

A pure-python/numpy autograd tensor library

Deep-Learning framework from scratch

用例子学习PyTorch1.0（Learning PyTorch with Examples 中文翻译与学习）

Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.

🌱 Guided-mode expansion of photonic crystal slabs

Deep Learning for Swift - Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation

European Distributed Deep Learning (EDDL) Library

Google AI Princeton control framework

Autograd Engine for Python Written in Python C-API for Speed

NotImplementedError: VJP of gammainc wrt argnum 0 not defined

Autograd (backpropagation, reverse-mode auto differentiation) in Nim

Yaae: Yet another autodiff engine (written in Numpy).

a simple implementation of autograd engine

Source code for Deep Multigrid method https://arxiv.org/pdf/1711.03825.pdf

R Interface to Torch

Scientific computing in pure Crystal