YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Source Code of our CVPR2021 paper "Rethinking BiSeNet For Real-time Semantic Segmentation"

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image …

Human segmentation models, training/inference code, and trained weights, implemented in PyTorch

This repository has been deprecated. Suggest to use edgeai-mmdetection in https://github.com/TexasInstruments/edgeai-tensorlab

[ACM MM 2021] Privacy-Preserving Portrait Matting

Blueprint Separable Residual Network for Efficient Image Super-Resolution

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Model Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

🔄 A tool for object detection and image segmentation dataset format conversion.

Score probability calculation model based on Poisson distribution

This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.

PArameterized Max Scale

An implementation of EQFace: A Simple Explicit Quality Network for Face Recognition (https://arxiv.org/abs/2105.00634, CVPRW 2021)

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

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

This is a pytorch implementation of DocUNet: Document Image Unwarping via A Stacked U-Net

DataFountain HUAWEI OCR 2019 rank Top1% ,Text Localization using pixellink,Word Recognition using densenet

Pytorch implementation and extension of "DocUnet: Document Image Unwarping via A Stacked U-Net"

An Intent Classifier For Chatbot

State-of-the-art 2D and 3D Face Analysis Project

2019CCF-BDCI大赛 最佳创新探索奖获得者 基于OCR身份证要素提取赛题冠军 天晨破晓团队 赛题源码

A two stage lightweight and high performance license plate recognition in MTCNN and LPRNet

Scene text recognition

🤘 LabelImg is a graphical image annotation tool and label object bounding boxes in images

一个用于提取简体中文字符串中省，市和区并能够进行映射，检验和简单绘图的python模块

On the Variance of the Adaptive Learning Rate and Beyond

An Intent Classifier For Chatbot