XJhaoren

AI-Toolbox

Algorithm Engineer Toolbox, for the purpose of quickly iterating new ideas

ann-benchmarks-1

Benchmarks of approximate nearest neighbor libraries in Python

awesome-Gesture-Recognition

resources about Gesture Recognition

awesomeCV

记录state-of-art计算机视觉相关论文。

Class-balanced-loss-pytorch

Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

coco-annotator

:pencil2: Web-based image segmentation tool for object detection, localization, and keypoints

cvpr2020

cvpr2020/cvpr2019／cvpr2018/cvpr2017 papers，极市团队整理

CVPR21Chal-SLR

This repo contains the official code of our work SAM-SLR which won the CVPR 2021 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition.

deep-person-reid

Deep learning person re-identification in PyTorch.

DEKR

This is an official implementation of our CVPR 2021 paper "Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression" (https://arxiv.org/abs/2104.02300)

EfficientNet-PyTorch

A PyTorch implementation of EfficientNet

FairMOT

A simple baseline for one-shot multi-object tracking

faiss

A library for efficient similarity search and clustering of dense vectors.

finegan

FineGAN: Unsupervised Hierarchical Disentanglement for Fine-grained Object Generation and Discovery

HigherHRNet-Human-Pose-Estimation

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

Hybrid-Attention-based-Decoupled-Metric-Learning

Caffe implementation of "Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval"

image-matching-benchmark

Public release of the Image Matching Benchmark: https://vision.uvic.ca/image-matching-challenge

insightface

Face Analysis Project on MXNet

InterHand2.6M

Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020

MedicalNet

Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.

Mimic3DWeb

nanodet

⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

Person_reID_baseline_pytorch

A tiny, friendly, strong pytorch implement of person re-identification baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

PyRetri

Open source deep learning based unsupervised image retrieval toolbox based on PyTorch🔥

SOSNet

Pretrained pytorch model for the SOSNet descriptor [CVPR 2019]

tpu

Reference models and tools for Cloud TPUs.

TransT

Transformer Tracking (CVPR2021)

vcpkg

C++ Library Manager for Windows, Linux, and MacOS

XJhaoren.github.io

Yet-Another-EfficientDet-Pytorch

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.