470 Open source projects that are alternatives of or similar to Diffsharp

OCaml bindings for PyTorch

Multi-dimensional arrays (tensors) and numerical definitions for Elixir

Scientific computing with N-dimensional arrays

A High Level Python Deep Reinforcement Learning library. Great for beginners, prototyping and quickly comparing algorithms

NumPy & SciPy for GPU

50% faster, 50% less RAM Machine Learning. Numba rewritten Sklearn. SVD, NNMF, PCA, LinearReg, RidgeReg, Randomized, Truncated SVD/PCA, CSR Matrices all 50+% faster

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

Unoffcial NVIDIA CUDA GPU support version of Google Tensorflow for MAC OSX

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Deep.Net machine learning framework for F#

Tensors and Dynamic neural networks in Python with strong GPU acceleration

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

⟨Leibniz-Grassmann-Clifford⟩ differential geometric algebra / multivector simplicial complex

Android GPU Inspector

A fast Clojure Tensor & Deep Learning library

Tensors and differentiable operations (like TensorFlow) in Rust

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

The C++ parallel algorithms library.

A curated list of awesome Distributed Deep Learning resources.

An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.

A collection of GICP-based fast point cloud registration algorithms

This is a repository for an object detection inference API using the Tensorflow framework.

High-level Deep Learning Framework written in Kotlin and inspired by Keras

Through this configuration, no per voxel data is transferred between the GPU and the CPU at runtime.

Training deep learning models on AWS and GCP instances

Vulkan compute for people

Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C.

ArrayFire: a general purpose GPU library.

The RWTH extensible training framework for universal recurrent neural networks

The New Official Aparapi: a framework for executing native Java and Scala code on the GPU.

Thinking in tensors, writing in PyTorch (a hands-on deep learning intro)

Fast and flexible AutoML with learning guarantees.

LibRec: A Leading Java Library for Recommender Systems, see

Python bindings for ArrayFire: A general purpose GPU library.

Ngx - Neural network based visual generator and mixer

Next-generation HTML renderer for apps and games

This is a list of useful libraries and resources for CUDA development.

A simple realtime graphics playground for experimentations.

Simple utilities to enable code reuse and portability between CUDA C/C++ and standard C/C++.

GPGPU Javascript library 🐸

gprMax is open source software that simulates electromagnetic wave propagation using the Finite-Difference Time-Domain (FDTD) method for numerical modelling of Ground Penetrating Radar (GPR)

Cross-platform GPU-oriented C++ application/game framework

Climate Machine: an Earth System Model that automatically learns from data

phi: gpu accelerated code-editor; definitely not to be confused phonetically with vi.

🧠 A tool that makes AI easier.

High-performance Bayesian Data Analysis on the GPU in Clojure

vendor independent deep learning library, compiler and inference framework microcomputers and micro-controllers

PopSift is an implementation of the SIFT algorithm in CUDA.

An Open Source, Self-Hosted Platform For Applied Deep Learning Development

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Blitz++ Multi-Dimensional Array Library for C++

Script to remotely check GPU servers for free GPUs

RealSR super resolution implemented with ncnn library

NiuTensor is an open-source toolkit developed by a joint team from NLP Lab. at Northeastern University and the NiuTrans Team. It provides tensor utilities to create and train neural networks.

Grokking Deep Reinforcement Learning

High-Performance Multiple-Backend Renderer Based on LuisaCompute

A high-performance distributed deep learning system targeting large-scale and automated distributed training.

NVIDIA GPUs htop like monitoring tool

A minimalist Deep Learning framework for embedded Computer Vision