[NAACL 2022] Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning.

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Code for the paper "UVDoc: Neural Grid-based Document Unwarping"

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 275+ supported cars.

最完整的AI算法面试题目仓库，1000道，25个类目

Accelerate segment anything model inference using Tensorrt 8.6.1.6

📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO and PaddlePaddle.

This repository is the implementation of "Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context".

The official code for “Geometric Representation Learning for Document Image Rectification”, ECCV, 2022.

Document Image Dewarping

YOLOv8 Target Model plugin for Autodistill

Images to inference with no labeling (use foundation models to train supervised models).

table detect(yolo) , table line(unet)

An app to interact privately with your documents using the power of GPT, 100% privately, no data leaks

PyTorch code and models for the DINOv2 self-supervised learning method.

The repository provides code for automatic segmentation using YOLOv5 and Segment Anything Model (SAM), which is used to create stickers.

This package can generate artificial training data for the yolo framework. All you need is a greescreen / cut image of your object.

Helper project for generating data for a pascal voc dataset

Ultralytics YOLO11 🚀

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

A robust fish detection model for real-time underwater fish detection in any marine environments.

简易的yolo半自动标注库，目前只支持单目标。如果数据集图片背景复杂，可能工作量不比直接标的小，因为sam是通用的分割模型。但是可以适当通过调整参数修改。

YOLOv8 Object Tracking using PyTorch, OpenCV and DeepSORT

简单描述工作内容，帮你生成完整周报

An Action RPG created to learn Game Development.

ManTra-Net: Manipulation Tracing Network For Detection And Localization of Image Forgeries With Anomalous Features

Tianchi Competition "Forgeries and Forensics" Track 2

发音转换器