System for AI Education Resource.

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

Base on YOLOv5 Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程🚀😆2021.3新增可视化界面❗❗

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

CAN bus tools.

Exercism exercises in Python.

🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Generative Adversarial Transformers

📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

You Only Look Once for Panopitic Driving Perception.（MIR2022）

[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

Library for Fast and Flexible Human Pose Estimation

Simulation of spiking neural networks (SNNs) using PyTorch.

Two-stage CenterNet

Official Pytorch implementation of CutMix regularizer

Machine learning metrics for distributed, scalable PyTorch applications.

基于Yolov5车牌检测,更快更准.

Replication of simple CV Projects including attention, classification, detection, keypoint detection, etc.

PaddleSlim is an open-source library for deep model compression and architecture search.

The PyTorch Implementation based on YOLOv4 of the paper: "Complex-YOLO: Real-time 3D Object Detection on Point Clouds"

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

yolov5 + csl_label.(Oriented Object Detection)（Rotation Detection）（Rotated BBox）基于yolov5的旋转目标检测

list of efficient attention modules