Stars
End-to-End Object Detection with Fully Convolutional Network
Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)
(WIP)The deployment framework aims to provide a simple, lightweight, fast integrated, pipelined deployment framework for algorithm service that ensures reliability, high concurrency and scalability…
A scene text recognition toolbox based on PyTorch
[ACM MM 2020] Exploring Font-independent Features for Scene Text Recognition
Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
Scene Text Recognition (STR) methods trained with fewer real labels (CVPR 2021)
ctcloss + centerloss crnn text recognition
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.
This repository provides train＆test code, dataset, det.&rec. annotation, evaluation script, annotation tool, and ranking.
Data and implementation of ECCV2020 paper 'Adaptive Text Recognition through Visual Matching'
Implementation of Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition published in AAAI 2019 in PyTorch
[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal
Interview Questions for Google, Amazon, Apple, etc. 根据超过 2000 篇真实面经整理的腾讯，阿里，字节跳动，Shopee，美团，滴滴高频面试题
PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)
This is an implementation of Show, Attend and Read with tensorflow
Pytorch implementation for "Decoupled attention network for text recognition".
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Pytorch implementation of CoordConv introduced in 'An intriguing failing of convolutional neural networks and the CoordConv solution' paper. (https://arxiv.org/pdf/1807.03247.pdf)
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
Exploring Self-attention for Image Recognition, CVPR2020.
Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)