zhangliliang

tensorflow

An Open Source Machine Learning Framework for Everyone

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

onnx

Open standard for machine learning interoperability

detr

End-to-End Object Detection with Transformers

autogluon

Fast and Accurate ML in 3 Lines of Code

pysot

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

AdelaiDet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

Super-SloMo

PyTorch implementation of Super SloMo by Jiang et al.

Auto-PyTorch

Automatic architecture search and hyperparameter optimization for PyTorch

once-for-all

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

SOLO

SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.

training_extensions

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

ObjectDetectionImbalance

Lists the papers related to imbalance problems in object detection [TPAMI]

bolt

Bolt is a deep learning library with high performance and heterogeneous flexibility.

nncf

Neural Network Compression Framework for enhanced OpenVINO™ inference

vega

AutoML tools chain

dabnn

dabnn is an accelerated binary neural networks inference framework for mobile platform

SiamDW

[CVPR'19 Oral] Deeper and Wider Siamese Networks for Real-Time Visual Tracking

onnx-mlir

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

larq

An Open-Source Library for Training Binarized Neural Networks

compute-engine

Highly optimized inference engine for Binarized Neural Networks

IR-Net

[CVPR 2020] This project is the PyTorch implementation of our accepted CVPR 2020 paper : forward and backward information retention for accurate binary neural networks.

RRN

Riptide

Simple Training and Deployment of Fast End-to-End Binary Networks

apq

[CVPR 2020] APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

UnsupervisedDepthFromFocus

Single Image Depth Estimation Trained via Depth from Defocus Cues

Robustness-Aware-Pruning-ADMM

Code release for "Adversarial Robustness vs Model Compression, or Both?"

AutoBNN