myhub Goto Github PK

advancedeast

AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.

caffe_ocr

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构

chineseocr

yolo3+ocr

crnn_seq2seq_ocr.pytorch

Extremely simple implement for Chinese OCR by PyTorch

demo

demo

focal-loss-pytorch

全中文注释.(The loss function of retinanet based on pytorch).(You can use it on one-stage detection task or classifical task, to solve data imbalance influence).用于one-stage目标检测算法,提升检测效果.你也可以在分类任务中使用该损失函数,解决数据不平衡问题.

keras-yolo3-text

运用yolo3实现自然场景文字检测

lets_ocr

A repository for OCR, which inlcudes some classical OCR algorithms Pytorch implementation such as CTPN, EAST and CRNN.

megreader

A research project for text detection and recognition using PyTorch 1.2.

models

nanorwkv

RWKV in nanoGPT style

nlp

NLP入门

nlp-mnist

NLP入门训练数据集

notes

ocr-notes

pixellink-with-pytorch

PixelLink-with-pytorch

pytorch-cifar

95.47% on CIFAR10 with PyTorch

pytorch-vgg-cifar10

This is the PyTorch implementation of VGG network trained on CIFAR10 dataset

pytorch_ctpn

This is a pytorch implementation of CTPN(Detecting Text in Natural Image with Connectionist Text Proposal Network)

rwkv-lm

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

shake-drop_pytorch

PyTorch implementation of shake-drop regularization

shake-shake_pytorch

PyTorch implementation of shake-shake regularization

simpledns

a simple dns client

ssot

基于Qt的截图软件

table-ocr

text_renderer

Generate text images for training deep learning ocr model

tr

Free Offline OCR 离线的中文文本检测+识别SDK

transformerdemo

Pytorch nn.Transformer Demo

trwebocr

开源易用的中文离线OCR，识别率媲美大厂，并且提供了易用的web页面及web的接口，方便人类日常工作使用或者其他程序来调用~

tutorials

PyTorch tutorials.