yoyoshuang's starred repositories
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Text_Detector
Text detection model that combines Retinanet with textboxes++ for OCR
SynthText3D
Project page of SynthText3D
hed-tutorial-for-document-scanning
Document Scanning With TensorFlow And OpenCV
Image-Correction
使用python语言,利用opencv库,实现校正图片中的A4纸
Awesome-Deblurring
A curated list of resources for Image and Video Deblurring
generative_inpainting
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
Stereo-Image-SR
A Collection of Algorithms and Datasets for Stereo Image Super-Resolution
Text-Image-Augmentation
Geometric Augmentation for Text Image
deep-learning-utils
A clean and general implementation of some common utils and tools required by various deep learning projects.
AttentionOCR
Scene text recognition
PSENet.pytorch
A pytorch re-implementation of PSENet: Shape Robust Text Detection with Progressive Scale Expansion Network
chineseocr_lite
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
Decoupled-attention-network
Pytorch implementation for "Decoupled attention network for text recognition".
pytracking
Visual tracking library based on PyTorch.
roLabelImg
Label Rotated Rect On Images for training
DIoU-darknet
Distance-IoU Loss into YOLO v3
wukong-robot
🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目,支持ChatGPT多轮对话能力,还可能是首个支持脑机交互的开源智能音箱项目。