linlin's repositories
CFTrackers
(2019)Visual object tracking based on correlation filtering
Dynamic_detection_and_tracking
(2018) Dynamic detection and tracking in UAV scenarios (C++Version); Moving obect detection in dynamic background; Feature point detection
UAV_Control_System
(2016-2017)UAV control system developed in 2016; Quadcopter; STM32; Embedded Systems
Awesome-Profile-README-templates
A collection of awesome readme templates to display on your profile
awesome_video_person_reid
papers collection and understanding for video person re-identification
BackgroundMattingV2
Real-Time High-Resolution Background Matting
deep-person-search
deep-person-search: deep learning person search in PyTorch.
DRConv-PyTorch
A Pytorch Toy Implementation of 'Dynamic Region-Aware Convolution' [ECCV2020]
github-readme-stats
:zap: Dynamically generated stats for your github readmes
micronet
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
MNN_Demo
🥭 移动端MNN部署学习笔记。支持Android与iOS。
Person-Search-Paper-List
The paper list for person search
person_search_demo
利用YOLOv3结合行人重识别模型,实现行人的检测识别,查找特定行人
RUAS
[CVPR 2021] This is the official code for the paper "Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement"
tensorRTIntegrate
TensorRT ONNX Plugin、Inference、Compile
TransT
Transformer Tracking (CVPR2021)
Ultra-Light-Fast-Generic-Face-Detector-1MB
💎1MB lightweight face detection model (1MB轻量级人脸检测模型)
yolact
A simple, fully convolutional model for real-time instance segmentation.
yolact_edge
The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.