498 Open source projects that are alternatives of or similar to Imagenet Classifier Tensorflow

A GPU implementation of Convolutional Neural Nets in C++

LightSeq: A High Performance Inference Library for Sequence Processing and Generation

The Hacker's Machine Learning Engine

AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。

Slides and demo code for past presentations

Python code to fuse multiple RGB-D images into a TSDF voxel volume.

Code and data for paper "Deep Painterly Harmonization": https://arxiv.org/abs/1804.03189

High-performance Vision library in Python. Scale your research, not boilerplate.

Performance-optimized wheels for TensorFlow (SSE, AVX, FMA, XLA, MPI)

Automatically exported from code.google.com/p/cuda-convnet2

TensorFlow examples in C, C++, Go and Python without bazel but with cmake and FindTensorFlow.cmake

Bregman ADMM for mass transportation on GPU

Super fast implementation of ICP in CUDA for compute capable devices 3.5 or higher

Reference implementation of real-time autoregressive wavenet inference

source code for paper "Deep Discrete Supervised Hashing"

All-in-one AI container for rapid prototyping

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

Go package for computer vision using OpenCV 4 and beyond.

CUDA on Intel GPUs

Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL

Large scale K-means and K-nn implementation on NVIDIA GPU / CUDA

RFC for common in-memory tensor structure and operator interface for deep learning system

An interval arithmetic and affine arithmetic library for NVIDIA CUDA

Julia support for native CUDA programming

Low-Rank and Sparse Tools for Background Modeling and Subtraction in Videos

A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN

A CUDA project for Molecular Dynamics, Brownian Dynamics, Hydrodynamics... intended to simulate a very generic system constructing a simulation with modules.

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

Library for faster pinned CPU <-> GPU transfer in Pytorch

A UNIVERSAL MUSIC TRANSLATION NETWORK - a method for translating music across musical instruments and styles.

Python interface to GPU-powered libraries

ILGPU JIT Compiler for high-performance .Net GPU programs

ThunderGBM: Fast GBDTs and Random Forests on GPUs

NVIDIA-accelerated zero latency video compression library for interactive remoting applications

Atmospheric fluid dynamics solver optimized for GPUs.

Thin C++-flavored wrappers for the CUDA Runtime API

PyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT

Distribution-Aware Coordinate Representation for Human Pose Estimation

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

DiffSharp: Differentiable Functional Programming

Monero (XMR) NVIDIA miner

Neural Networks in Java 8 with CuDNN and Aparapi

Python bindings for ArrayFire: A general purpose GPU library.

Fast Point Cloud Segmentation Using Permutohedral Lattices

Efficient GPU kernels for block-sparse matrix multiplication and convolution

A CUDA implementation of SIFT for NVidia GPUs (1.2 ms on a GTX 1060)

FSA/FST algorithms, differentiable, with PyTorch compatibility.

Some basic programming tutorials

Python module for performing basic dense linear algebra computations on the GPU using CUDA.

SIMD Library for Evaluating Elementary Functions, vectorized libm and DFT

A C++-based, cross platform ray tracing library

PyTorch - Python + Nim

Source code that accompanies The CUDA Handbook.

Lighthouse 2 framework for real-time ray tracing

High-performance Bayesian Data Analysis on the GPU in Clojure

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.

an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

OpenCL integration for Python, plus shiny features