Official implementation for ICDAR 2021 paper "Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer"

꼼꼼한 딥러닝 논문 리뷰와 코드 실습

🧠 Implementations/tutorials of deep learning papers with side-by-side notes; including transformers (original, xl, switch, feedback), optimizers(adam, radam, adabelief), gans(dcgan, cyclegan, stylegan2), reinforcement learning (ppo, dqn), capsnet, sketch-rnn, etc.

Document Text Recognition (DocTR) made seamless, high-performing & accessible to anyone using Deep Learning for OCR-related tasks.

Image captioning using Bahdanau and Luong attention applied on COCO and Flickr8k datasets. The performances have been measured using BLEU and METEOR scores.

A highly optimized code for the recognition of handwritten English or Arabic text, supporting multiple datasets.

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet) and (cbam)

PyTorch Tutorial for Deep Learning Researchers

An OCR for classical Sanskrit document images

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

Camera-based Document Analysis

Focal CTC for End-To-End OMR task with Class Imbalance, SangCTC (Part I)

Pytorch implementation of various Attention Mechanism

This repository contain various types of attention mechanism like Bahdanau , Soft attention , Additive Attention , Hierarchical Attention etc