xiaoxiaokuaile

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

v2ray-core

A platform for building proxies to bypass network restrictions.

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

MathModel

研究生数学建模，本科生数学建模、数学建模竞赛优秀论文，数学建模算法，LaTeX论文模板，算法思维导图，参考书籍，Matlab软件教程，PPT

SlowFast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

ByteTrack

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

captcha_break

验证码识别

mmaction

An open-source toolbox for action understanding based on PyTorch

Swin-Transformer-Object-Detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

Video-Swin-Transformer

This is an official implementation for "Video Swin Transformers".

flexible-yolov5

More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

OCR-Corrector

利用语言模型，纠正OCR识别错误

DocTr

The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

kaggle-landmark-2021-1st-place

text-detection-ocr

Chinese text detection and recognition based on CTPN + DENSENET using Keras and Tensor Flow，使用keras和tensorflow基于CTPN+Densenet实现的中文文本检测和识别

2021_QQ_AIAC_Tack1_1st

QQ浏览器2021AI算法大赛赛道一 第1名 方案

deep_sort_yolov3_pytorch

Replication of MOT project - DeepSort with attention blocks.

pikachu2

微信大数据2021 1st，qq浏览器2021 3rd，mind新闻推荐2020 1st，NAIC2020 AI+遥感影像 2nd

MemoryNet

Code for paper: Memory Augment is All Your Need for image restoration(cloud,rain,shadow removal, low-light image enhancement, image deblur)即插即用提点的记忆模块

UVO_Challenge

Chinese-OCR3

从NLP出发对于OCR的深度实践集锦，重在实战

yolo_deepsort

Fast MOT base on yolo+deepsort, support yolo3 and yolo4

megcup-feedback

RAW-based blind denoising, 1st place in MegCup 2022 (Team Feedback)

megcup-feedforward

RAW-based blind denoising, 3rd place in MegCup 2022 (Team Feedforward)

captcha_ocr

2022DCIC-基于文本字符的交易验证码识别

Video_sim

qq browser multimodal video similarity contest

2021AIWIN_OCR

2021AIWIN交通银行手写字体OCR识别Top1方案

MegCup-2022

MegCup 2022第7名解决方案（8.983分，非RNN形式）

ML_CodeEveryday

ML模型代码

2021DIGIX_OCR_Small_Menu

2021DIGIX 小样本菜单识别 星光卓越奖 小小快乐队伍 方案及源代码