PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

End-to-End Object Detection with Transformers

Tensors and Dynamic neural networks in Python with strong GPU acceleration

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

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

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

SiamRPN, SiamRPN++, unofficial implementation of "SiamRPN++" (CVPR2019), multi-GPUs, LMDB.

Datasets, Transforms and Models specific to Computer Vision

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.