bcc0910
Follow
Stars
QMagFace: Simple and Accurate Quality-Aware Face Recognition (WACV 2023)
MagFace: A Universal Representation for Face Recognition and Quality Assessment, CVPR2021, Oral
An efficient implementation of the popular sequence models for text generation, summarization, and translation tasks. https://arxiv.org/pdf/2106.04718.pdf
BANG is a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generation can be uniformly regarded as to what extent previous tok…
ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction
🔥 (yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.
Pytorch implementation of TPAMI 2022 -- 1xN Pattern for Pruning Convolutional Neural Networks
The state-of-the-art image restoration model without nonlinear activation functions.
text recognize use ctc and attention
Pytorch implementation for "Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter".
HWDB1.1单字数据集合成文本行，带有相应的框坐标，同时含有数据增强。
基于pytorch卷积神经网络的中文手写汉字识别，使用HWDB数据库
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
Ongoing research training transformer models at scale
Transformer related optimization, including BERT, GPT
Reformer, the efficient Transformer, in Pytorch
Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.
Easy and Efficient Transformer : Scalable Inference Solution For Large NLP model
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.
Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf
A tool for learning vector representations of words and entities from Wikipedia
Adversarial Training for Natural Language Understanding
Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)
MASS: Masked Sequence to Sequence Pre-training for Language Generation