annihilation7 Goto Github PK

adelaidet

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

algorithms

Play a game

aster

111

aster.pytorch

ASTER in Pytorch

box_discretization_network

Omnidirectional Scene Text Detection with Sequential-free Box Discretization (IJCAI 2019). Including competition model, online demo, etc.

craft-reimplementation

CRAFT-Pyotorch：Character Region Awareness for Text Detection Reimplementation for Pytorch

data-structure-and-algorithms-with-python

a python repo of bobo teacher's imooc coarse.

db

A PyToch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

decoupled-attention-network

Pytorch implementation for "Decoupled attention network for text recognition".

detection-pytorch-notebook

代码 -《深度学习之PyTorch物体检测实战》

ds-and-al

Come on boy!

leetcode-love

刷——就完事了！

lhy_dl_hw

lihang-code

《统计学习方法》的代码实现

linear-algebra-and-statistic-analysis

没事敲一敲吧

masktextspotter

A PyTorch implementation of Mask TextSpotter

mmdetection

OpenMMLab Detection Toolbox and Benchmark

ocr_evaluation

Modified by icdar codes for OCR results evaluation(detection or end-to-end recognition results). For more details, please see my blog:

opencv-3-computer-vision-with-python-cookbook

Published by Packt

paddledetection

Object detection and instance segmentation toolkit based on PaddlePaddle.

paddleocr

基于飞桨的OCR工具库，包含总模型仅8.6M的超轻量级中文OCR，单模型支持中英文数字组合识别、竖排文本识别、长文本识别。同时支持多种文本检测、文本识别的训练算法。

psenet

pytorch-learning

Note Book

pytorch-love

学习Pytorch，人人有责。

pytorch-yolov3

Minimal PyTorch implementation of YOLOv3

recognition-data-maker

A Generator!

scikit-learn-study

学就完了

split_merge_table_recognition

An implementation of the Splitting and Merging table recognition method.

synthtext_chinese_version

Modify from https://github.com/ankush-me/SynthText.git to generate chinese character

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.