403 Open source projects that are alternatives of or similar to Convnet

FSA/FST algorithms, differentiable, with PyTorch compatibility.

ArrayFire: a general purpose GPU library.

GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

Distribution-Aware Coordinate Representation for Human Pose Estimation

Unsupervised Learning of Video Representations using LSTMs

a reimplementation of PWC-Net in PyTorch that matches the official Caffe version

PyTorch - Python + Nim

(Mirror of GitLab) GPGPU Framework for Rust

Sample codes for my CUDA programming book

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

Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.

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

Fast parallel CTC.

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

Fuse multiple depth frames into a TSDF voxel volume.

SIMD Library for Evaluating Elementary Functions, vectorized libm and DFT

Integral Human Pose Regression

High-performance Bayesian Data Analysis on the GPU in Clojure

BitCracker is the first open source password cracking tool for memory units encrypted with BitLocker

A CUDA backend for Torch7

C++ library for solving large sparse linear systems with algebraic multigrid method

A collection of GICP-based fast point cloud registration algorithms

H2Oai GPU Edition

CUDA Voxelizer to convert polygon meshes into annotated voxel grids

ILGPU JIT Compiler for high-performance .Net GPU programs

VUDA is a header-only library based on Vulkan that provides a CUDA Runtime API interface for writing GPU-accelerated applications.

The FFmpeg build script provides an easy way to build a static FFmpeg on OSX and Linux with non-free codecs included.

All-in-one AI container for rapid prototyping

Stereo Semi Global Matching by cuda

A code generator for array-based code on CPUs and GPUs

Go package for computer vision using OpenCV 4 and beyond.

Python bindings for ArrayFire: A general purpose GPU library.

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

Some basic programming tutorials

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

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

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

Source code that accompanies The CUDA Handbook.

Julia support for native CUDA programming

CUDA Data Parallel Primitives Library

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

GPU-accelerated micromagnetic simulator

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

A single-header C++ library for simplifying the use of CUDA Runtime Compilation (NVRTC).

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

The C++ parallel algorithms library.

cuDF - GPU DataFrame Library

Fast k nearest neighbor search using GPU

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

ICCV2017 Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

Implementation of SYCL for CPUs, AMD GPUs, NVIDIA GPUs

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

PyTorch implementation of Deformable Convolution

CUDA programming in Julia.

A Docker image for PyTorch

🌀 Oxygen Engine 2.0. [Preview] Discord: https://discord.gg/P3aMf66

Open3D: A Modern Library for 3D Data Processing

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