zhunge Goto Github PK

awesome-document-image-rectification

A comprehensive list of awesome document image rectification papers.

conformer_ocr

Transformer OCR is a Optical Character Recognition tookit built for researchers working on both OCR for both Vietnamese and English. This project only focused on variants of vanilla Transformer (Conformer) and Feature Extraction (CNN-based approach).

conformervit

ViT + Conformer = ( ͡❛ ͜ʖ ͡❛)👌

deepin-wine-ubuntu

Deepin Wine for Ubuntu/Debian

lite.ai.toolkit

🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, YOLOv6, YOLOR, MODNet, YOLOX, YOLOv7, YOLOv5. MNN, NCNN, TNN, ONNXRuntime, CPU/GPU.

livespeechportraits

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)

lsp

recreating the LSP(LiveSpeechPortraits) alg.

master-pytorch

Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

pfld-pytorch

PFLD pytorch Implementation

pick-pytorch

Code for the paper "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020)

pytorch-distributed

A quickstart and benchmark for pytorch distributed training.

pytorch-gan

PyTorch implementations of Generative Adversarial Networks.

pytorchocr

基于pytorch的ocr算法库，包括 psenet, pan, dbnet, sast , crnn

sdmg_r

tablemaster-mmocr

表格识别 2nd solution of ICDAR 2021 Competition on Scientific Literature Parsing, Task B.

temporal-shift-module-1

PyTorch Implementation of Temporal Shift Module for Jester

trocr-chinese

visual_speech_recognition_for_multiple_languages

Visual Speech Recognition for Multiple Languages

wav2lip384

yolov5ncnn

ncnn of yolov5 v5.0 branch