33 Open Source Acceleration Software Projects

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

A developer friendly approach for sensors in React Native

Reduce CPU usage by non-blocking async loop and psychologically speed up in JavaScript

Display-agnostic acceleration of macOS applications using external GPUs.

Caffe for Sparse and Low-rank Deep Neural Networks

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

:zap: Optimization & CDN for images, CSS, JavaScript, and open source

A BVH implementation to speed up raycasting against three.js meshes.

An open source indexing subsystem that brings index-based query acceleration to Apache Spark™ and big data workloads.

Pytorch implementation of our CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map

volksdep is an open-source toolbox for deploying and accelerating PyTorch, Onnx and Tensorflow models with TensorRT.

A free, header-only C++ swarming (flocking) library for real-time applications

A .NET library provides the hardware-accelerated high performance immediate mode rendering functionality via Direct2D API.

An FPGA I/O Device which services physical memory reads/writes via UMDF2 driver

Experimental VP9 codec support for vdpau-va-driver (NVIDIA VDPAU-VAAPI wrapper) and chromium-vaapi

Repository to track the progress in model compression and acceleration

yolov3 model compress and acceleration (quantization, sparse)， c++ version

A particle effect with dead simple physics.

pytorch realtime multi person keypoint estimation

Caffe Computation Graph Optimization.

Code to speed up k-means clustering. Originally at BaylorCS/baylorml.

A new build tool optimized for local + remote development

This repo contains Go implementation and corresponding APIs for acceleration of Binarized Neural Network (BNN) on FPGAs.

All about acceleration and compression of Deep Neural Networks

Implementation of "Fully Learnable Group Convolution for Acceleration of Deep Neural Networks", CVPR'19

Go library that makes it easy to work with physical types, e.g. distances, velocities and angles.

Code Examples explained in QCon-London 2020 about TornadoVM

Deep Learning Compression and Acceleration SDK -- deep model compression for Edge and IoT embedded systems, and deep model acceleration for clouds and private servers

pymotiontracker is a Python 3 library to read from an MPU6050 (accelerometer + gyroscope) Bluetooth module

Sentieon DNAseq