shiyuan0806's repositories
AICIty-reID-2020
:red_car: The 1st Place Submission to AICity Challenge 2020 re-id track (Baidu-UTS submission)
Awesome-Crowd-Counting
Awesome Crowd Counting
cavaface.pytorch
:beers: :rocket: :city_sunset: face recognition project(pytorch)
deep-person-reid
Torchreid: Deep learning person re-identification in PyTorch.
Deep-SORT-YOLOv4
People detection and optional tracking with Tensorflow backend.
Deep3dPortrait
Deep 3D Portrait from a Single Image
DM-Count
Code for NeurIPS 2020 paper: Distribution Matching for Crowd Counting.
fast-reid
SOTA ReID Methods and Toolbox
IBN-Net
Instance-Batch Normalization Networks (ECCV2018)
light-reid
[ECCV2020] a toolbox of light-reid learning for faster inference, speed both feature extraction and retrieval stages up to >30x
lpcvc
[LPIRC 2019, ICCV 2019] Winner Solution for 4th LPCVC
msba_reid
Official code for paper "MSBA: Multiple Scales, Branches and Attention Network With Bag of Tricks for Person Re-Identification"
NAIC_Person_ReID_DMT
This is Top 3 Code for the Person ReID Compitition of NAIC
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
PAA
A PyTorch implementation of the paper `Probabilistic Anchor Assignment with IoU Prediction for Object Detection` ECCV 2020 (https://arxiv.org/abs/2007.08103)
PaddleClas
A treasure chest for image classification powered by PaddlePaddle
PyRetri
Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥
ReID-Survey
Deep Learning for Person Re-identification: A Survey and Outlook
Silent-Face-Anti-Spoofing
静默活体检测(Silent-Face-Anti-Spoofing)
Smoke-Detect-by-YoloV5
Yolov5 real time smoke detection system
swa-tutorials-pytorch
Stochastic Weight Averaging Tutorials using pytorch.
thor
thor: C++ helper library, for deep learning purpose
TNN
TNN:由腾讯优图实验室打造,移动端高性能、轻量级推理框架,同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化,同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地,欢迎大家参与协同共建,促进TNN推理框架进一步完善。
Ultra-Fast-Lane-Detection
The implementation of paper "Ultra Fast Structure-aware Deep Lane Detection"
VisDA2020_Code_From_Top_Teams
The code from the top teams in the VisDA-2020 Challenge
Yet-Another-reid-baseline
A simple baseline for Person ReID, it achieves 3rd place in VisDA2020 challenge.
yolov5
YOLOv5 in PyTorch > ONNX > CoreML > iOS