Shualite

PCAN

UBNet

2020-instanceSeg

Deep Variational Instance Segmentation

BorderDet

Stay tuned for updates!

TextTracer

a text tracer

cnchar

功能全面的汉字工具库 (拼音 笔画 笔顺 偏旁 成语等) (Chinese character util)

CONTA

Implementation for NeurIPS oral paper: Causal Intervention for Weakly-Supervised Semantic Segmentation

CV-Backbones

CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.

defgrid-release

Official PyTorch implementation of Deformable Grid (ECCV 2020)

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

differnet

This is the official repository to the WACV 2021 paper "Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows" by Marco Rudolph, Bastian Wandt and Bodo Rosenhahn.

DRRG

Deep relational reasoning graph network for arbitrary shape text detection; Accepted by CVPR 2020 (Oral). http://arxiv.org/abs/2003.07493

EAST

PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector

EFIFSTR

[ACM MM 2020] Exploring Font-independent Features for Scene Text Recognition

fuzzychinese

A small package to fuzzy match chinese words

github-readme-stats

:zap: Dynamically generated stats for your github readmes

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

GPT2-Chinese

Chinese version of GPT2 training code, using BERT tokenizer.

itsabouttime

Code repository for "It's About Time: Analog clock Reading in the Wild"

NLP_pytorch_project

Embedding, NMT, Text_Classification, Text_Generation, NER etc.

OCR-Corrector

利用语言模型，纠正OCR识别错误

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）

pan_pp.pytorch

Official implementations of PSENet, PAN and PAN++.

plugnet

RRPN_plusplus

Code has been released.

T2T-ViT

Trans2Seg

TransDETR

transformer-debugger

TransVTSpotter

A new video text spotting framework with Transformer