This research proposes a modified network YOLOv5 model to determine the best model for jeans fabric defect detection.

OpenCVのGrabCut()を利用したセマンティックセグメンテーション向けアノテーションツール(Annotation tool using GrabCut() of OpenCV. It can be used to create datasets for semantic segmentation.)

Label And Segment are Based on Results of AttentionGAN Using Region Growing Segmentation Algorithm

Code and dataset of Triplet- Graph Reasoning Network for Few-shot Metal Generic Surface Defect Segmentation

DCASE2020 Task2 Self-supervised learning solution

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

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

unofficial version of centerface, which achieves the best balance between speed and accuracy at face detection

A real-time version of FCOS, inspired by FCOSv2.

face recognition training project(pytorch)

A visual editor for manually annotating facial landmarks in images of human faces.

Code of kaggle semantic segmentation competition: Steel Defect Detection.

Kaggle Segmentation Challenge

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

nniefacelib是一个在海思35xx系列芯片上运行的人脸算法库

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

Face reconstruction and dense alignment

适用于移动端的人脸识别模型，计算量与mobilefacenet相同，但megaface上提升了2%+

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

Using modified BiSeNet for face parsing in PyTorch

Easy-to-use face related tools, including face detection, landmark localization, alignment & recognition, based on PyTorch.

Train code of face anti-spoofing with a single RGB frame

Observe workers as they pass in front of a camera to determine if they have adequate safety protection.

yolov3 with mobilenet v2 and ASFF

1M人脸检测模型(含关键点)

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

A simple face detect and alignment method, which is easy and stable.

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