Bachelorwangwei

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

CSBook

cudf

cuDF - GPU DataFrame Library

cugraph

cuGraph - RAPIDS Graph Analytics Library

cupy

NumPy & SciPy for GPU

cython

The most widely used Python to C compiler

dask

Parallel computing with task scheduling

detr

End-to-End Object Detection with Transformers

DRRG

Deep relational reasoning graph network for arbitrary shape text detection; CVPR 2020.

EDPN

fucking-algorithm

手把手撕LeetCode题目，扒各种算法套路的裤子。English version supported! Crack LeetCode, not only how, but also why.

gluten

Image-Process

冈萨雷斯《数字图像处理》Python实现(第三版)

IQA-optimization

Comparison of Image Quality Models for Optimization of Image Processing Systems

mars

Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.

mobile-lpr

Mobile-LPR 是一个面向移动端的准商业级车牌识别库，以NCNN作为推理后端，使用DNN作为算法核心，支持多种车牌检测算法，支持车牌识别和车牌颜色识别。

PaddleOCR

Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices）

pandas

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

ResNeSt

ResNeSt: Split-Attention Network

RSN

Scene-Text-Recognition

spark-rapids

Spark RAPIDS plugin - accelerate Apache Spark with GPUs

substrait-java

TecoGAN

This repo contains source code and materials for the TEmporally COherent GAN SIGGRAPH project.

Text-Image-Augmentation

Geometric Augmentation for Text Image

TextFuseNet

A PyTorch implementation of "TextFuseNet: Scene Text Detection with Richer Fused Features".

velox

A C++ vectorized database acceleration library aimed to optimizing query engines and data processing systems.

Yet-Another-EfficientDet-Pytorch

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

YOLOP

You Only Look Once for Panopitic Driving Perception.（https://arxiv.org/abs/2108.11250）