laygin

pytorch_ctpn. This is a pytorch implementation of CTPN(Detecting Text in Natural Image with Connectionist Text Proposal Network). You may want to finetune from: https://drive.google.com/open?id=1JHhI4sEIXfs5gDa1I9AgJBY477HTzAd0

Transformer_STR. PyTorch implementation of my new method for Scene Text Recognition (STR) based on Transformer,Equipped with Transformer, this method outperforms the best model of the aforementioned deep-text-recognition-benchmark by 7.6% on CUTE80.

keras-shufflenetV2. Keras implementation of ShuffleNet V2

face_detection_in_realtime. This repository is the implementation of face detection in real time using YOLOv3 framework with keras(tensorflow backend). For use in embeded devices, so I choose a computation-efficient CNN architecture named ShuffleNet version 2 and train it from scratch(about 50 epoches) on FDDB.

pixellink_keras. pixellink in keras

keras_std_plus_plus. This repository is the official implementation of `A Semantic-based Arbitrarily-Oriented Scene Text Detector`(named STD++ as it is the improved version of STD).

blogs. 本仓库用于记录和共享“laygin”公众号中的博客文章，包括文中用到的素材资源、代码资料等等。

keras_std. This repository is the official implementation of Semantic-based Scene Text Detector(STD for short), a new scene text detection method, inspired by the idea of CSP, which is used on Pedestrian Detection.

learning-resources. 分享学习资源，包括在线课程、国内外名校公开课、高质量的书籍、论文、数据集等。内容有：深度学习，机器学习，计算机视觉，Python，C/C++、算法、安卓开发和数据分析与挖掘等