autodiff 开源项目推荐（320 个）

tracel-ai /burn

Burn 是新一代张量库和深度学习框架，在灵活性、效率和可移植性上毫不妥协。

google /tangent

纯Python中的源到源可互换衍生品

autodiff /autodiff

C++更容易自动区分

chelsea0x3b /dfdx

Deep learning in Rust, with shape checked tensors and neural networks

microsoft /Trace

面向 AI 智能体的端到端生成式优化

lmfit /uncertainties

Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.

DiffSharp /DiffSharp

DiffSharp: Differentiable Functional Programming

just-cameron /julia-bootcamp-2022

该项目在 GitHub 上没有填写描述

dlsys-course /assignment1-2018

Assignment 1: automatic differentiation

auto-differentiation /xad

最快的 C++ 自动微分库，带 Python 绑定。支持前向、伴随和高阶导数、检查点、Eigen 支持和 JIT。提供针对 CppAD、Adept 和 autodiff 的可复现基准测试

google /autobound

AutoBound automatically computes upper and lower bounds on functions.

nabla-ml /nabla

Nabla: High-Performance Scientific Computing

leopard-ai /betty

Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization

JuliaDiff /DifferentiationInterface.jl

An interface to various automatic differentiation backends in Julia.

PennyLaneAI /catalyst

A JIT compiler for hybrid quantum programs in PennyLane

rsokl /MyGrad

Drop-in autodiff for NumPy.

kmolan /multicalc-rust

Scientific computing that fits on a microcontroller. Estimation, control, kinematics, Lie groups, calculus, autodiff and linear algebra in stable no_std Rust with no heap, no panics and no unsafe. Run the same code on your laptop and your Cortex-M0.

maciejkula /wyrm

Autodifferentiation package in Rust.

tsotchke /eshkol

High-Performance LISP-like language for Scientific Computing and AI written in C++

hikettei /cl-waffe2

[Experimental] Graph and Tensor Abstraction for Deep Learning all in Common Lisp