Tensors and Dynamic neural networks in Python with strong GPU acceleration

《Pytorch模型训练实用教程》中配套代码

A topic-centric list of HQ open datasets.

C++ implementation of the ECCV 2016 paper, Natural Image Stitching with the Global Similarity Prior.

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

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

Repository for OpenCV's extra modules

Extremely simple implement for CRNN by Tensorflow

轻量级的车牌检测项目（支持车牌四角定位、矫正对齐）

基于Yolov5车牌检测,更快更准.

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

HMM based on KMeans and GMM

A simple script to generate a object detection dataset with MNIST digits

收集并整理有关OCR的数据集并统一标注格式，以便实验需要

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

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-recog…

A synthetic data generator for text recognition

Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Siamese and triplet networks with online pair/triplet mining in PyTorch