FCOS: Fully Convolutional One-Stage Object Detection

Total Text Dataset - ICDAR 2017. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

Distributed training framework for TensorFlow, Keras, and PyTorch.

Photographing Chinese-Address OCR implemented using CTPN+CTC+Address Correction. 拍照文档中文地址文字识别。

Computer Vision Annotation Tool (CVAT) is a web-based tool which helps to annotate video and images for Computer Vision algorithms

Generate text images for training deep learning ocr model

Web labelling tool for camera and LIDAR data

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

A library for efficient similarity search and clustering of dense vectors.

Image Polygonal Annotation with Python.

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations.

A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

The Places365-CNNs for Scene Classification

PyTorch implementation of Deformable Convolution

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

Source code of RRPN ---- Arbitrary-Oriented Scene Text Detection via Rotation Proposals

Channel Pruning for Accelerating Very Deep Neural Networks

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

A curated list of promising OCR resources

3.41% and 17.11% error on CIFAR-10 and CIFAR-100

Image-to-image translation in PyTorch (e.g. horse2zebra, edges2cats, and more)

Improving Convolutional Networks via Attention Transfer (ICLR 2017)

An MXNet implementation of Mask R-CNN

主流ocr算法研究实验性的项目，目前实现了CNN+BLSTM+CTC架构