Autograd
Showing 22 of 22 projects
A Python package for tensor computation with GPU acceleration and dynamic neural networks built on a tape-based autograd system.
Automatically differentiate native Python and NumPy code for gradient-based optimization and machine learning.
A fast, flexible C++ standalone library for machine learning with high-performance defaults and total internal modifiability.
A fast, flexible C++ standalone library for machine learning with high-performance defaults and total internal modifiability.
An engine-agnostic deep learning framework for Java developers, providing a high-level API for model training and inference.
A curated list of awesome libraries, projects, tutorials, and resources for the JAX machine learning ecosystem.
A deep learning library for Rust featuring shape-checked tensors and neural networks with compile-time safety.
A deep learning library in Rust featuring shape-checked tensors and neural networks with compile-time safety.
A deep learning JavaScript library built from scratch with PyTorch-like syntax and GPU acceleration via GPU.js.
A Ruby deep learning library powered by LibTorch, providing a PyTorch-like API for Ruby developers.
A deep learning library for Ruby that provides a native interface to LibTorch, enabling GPU-accelerated neural network development.
A JAX-powered reimplementation of MiniGrid offering over 1000x speedup for reinforcement learning experiments.
A high-performance tensor library for the V programming language, providing n-dimensional data structures and linear algebra operations.
A core scientific computing library for Crystal providing n-dimensional tensors, linear algebra, GPU acceleration, and automatic differentiation.
A Swift library for accelerated tensor operations and dynamic neural networks with automatic differentiation, supporting all Apple platforms and Linux.
A minimal pure Python implementation of reverse-mode automatic differentiation (autograd) for educational purposes.
A lightweight, platform-independent tensor library with autograd for the JVM, accelerated by OpenCL.
A neural network framework with automatic differentiation for building and training models in pure Object Pascal.
A learning-focused, high-performance tensor computation library built from scratch in Rust with automatic differentiation and CPU/CUDA backends.
A JavaScript/TypeScript library for accelerated tensor computation and ONNX model execution in the browser.
A Torch-like deep learning framework for JavaScript with direct tensor and autograd operations.
An autograd and GPGPU library for building dynamic neural networks in the D programming language.
Related Tags
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.