stq's repositories
CASIA_HW_data_processing
CASIA-HWDB1-2、CASIA-OLHWDB1-2、ICDAR2013联机脱机数据处理
cnocr
基于 PyTorch/MXNet 的中文/英文 OCR Python 包
cp-vton-plus
Official implementation for "CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On", CVPRW 2020
CRNN_ACE_Loss
CRNN training with ACE Loss
crnn_ctc-centerloss
ctcloss + centerloss crnn text recognition
DBNet
DeepVAC-compliant DB Net implementation.
deepvac
PyTorch Project Specification.
DewarpNet
Code for the paper "DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks" (ICCV '19)
hand-gesture-recognition-using-mediapipe
MediaPipe(Python版)を用いて手の姿勢推定を行い、検出したキーポイントを用いて、簡易なMLPでハンドサインとフィンガージェスチャーを認識するサンプルプログラムです。（Estimate hand pose using MediaPipe(Python version). This is a sample program that recognizes hand signs and finger gestures with a simple MLP using the detected key points.）
handwritten-chinese-ocr-samples
End-to-end model training and deployment reference for handwritten Chinese text recognition, and can also be extended to other languages.
image-to-latex
Convert images of LaTex math equations into LaTex code.
KeyFrames
视频关键帧项目
Keyframes-CNN-RNN-action-recognition-
使用关键帧技术提取关键帧后，使用CNN-RNN网络模型框架提取并融合特征，最后softmax分类
lifeRestart
やり直すんだ。そして、次はうまくやる。
mediapipe-python-sample
MediaPipeのPythonパッケージのサンプルです。2021/06/04時点でPython実装のある7機能(Hands、Pose、Face Mesh、Holistic、Face Detection、Objectron、Selfie Segmentation)について用意しています。
MNIST
image classification via Triplet/Contrastive loss on MNIST dataset
ocr_torch
ocr_torch是基于Torch1.8实现的DBNet(2.2M) + CRNN(3.8M)实现的轻量级文字检测识别项目(支持onnx推理).
openbilibili-common
bilibili leaked source code
PaddleOCR
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 deployment among server, mobile, embedded and IoT devices）
python-wechaty
Python Wechaty is a Conversational RPA SDK for Chatbot Makers written in Python
pytorch-gken
Official Pytorch implementation of the ACM MM'21 paper: Keyframe Extraction from Motion Capture Sequences with Graph based Deep Reinforcement Learning
pytorchOCR-1
基于pytorch的ocr算法库，包括 psenet, pan, dbnet, sast , crnn
SwinTextSpotter
Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)
Synthesize-Distorted-Image-and-Its-Control-Points
Synthesize distorted document image and control points.
TESTR
(CVPR 2022) Text Spotting Transformers
Text-Recognition-on-Cross-Domain-Datasets
Improved Text recognition algorithms on different text domains like scene text, handwritten, document, Chinese/English, even ancient books
text-to-handwriting
So your teacher asked you to upload written assignments? Hate writing assigments? This tool will help you convert your text to handwriting xD
unilm
UniLM AI - Large-scale Self-supervised Pre-training across Tasks, Languages, and Modalities