lianwaijinxifeng's repositories
A-Light-and-Fast-Face-Detector-for-Edge-Devices
a light and fast face detector for edge devices
avatarify
Avatars for Zoom, Skype and other video-conferencing apps.
DeepFaceLab
DeepFaceLab is the leading software for creating deepfakes.
deepstream-plugins
Samples for TensorRT/Deepstream for Tesla & Jetson
DensePose
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
Duke-DeepCC
Fork of https://github.com/ergysr/DeepCC
DukeMTMC-reID_evaluation
ICCV2017 The Person re-ID Evaluation Code for DukeMTMC-reID Dataset (Including Dataset Download)
EasyPR
An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations.
FairMOT
A simple baseline for one-shot multi-object tracking
insightface
Face Analysis Project on MXNet
KANN-DBSCAN
I'm not the author, and just try to code it with python
Market-1501_Attribute
27 hand-annotated attributes of Market-1501
MobileNetV2_TF
Change some code from https://github.com/timctho/mobilenet-v2-tensorflow, so the model can load correctly from the pre-train model from https://github.com/tensorflow/models/tree/master/research/slim/nets/mobilenet.
mtl
Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics
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
Real_Time_Image_Animation
The Project is real time application in opencv using first order model
RepVGG
RepVGG: Making VGG-style ConvNets Great Again
retinaface
Reimplement RetinaFace use C++ and TensorRT
rtsp_hw_decode
rtsp硬件解码python库
SlimYOLOv3
This page is for the SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications
st-gcn
Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch
TensorRT-Yolov3
TensorRT for Yolov3
tensorrt-zoo
openpose, yolov3 with tiny-tensorrt
TensorRT_yolo3_module
You can import this module directly
triplet-reid
Code for reproducing the results of our "In Defense of the Triplet Loss for Person Re-Identification" paper.
Yolo-Fastest
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors