基于TrOCR + UniMER-1M数据集，训练一个小而美的公式识别模型
☆30Mar 17, 2026Updated 3 months ago
Alternatives and similar repositories for TrOCR-Formula-Rec
Users that are interested in TrOCR-Formula-Rec are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 基于transformer的ocr识别，在公章(印章识别, seal recognition）拓展应用☆296Oct 24, 2025Updated 8 months ago
- 生成训练文本检测数据集☆12Jul 1, 2020Updated 5 years ago
- in development - training a TrOCR model for hebrew☆11Nov 9, 2023Updated 2 years ago
- Transformer OCR for Indian Languages☆14Nov 2, 2023Updated 2 years ago
- 中文论文、证券类、财报类PDF数据☆41Jun 13, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- transformers ocr for chinese☆416Jan 13, 2023Updated 3 years ago
- A Bytecode level Implementation of Symbolic OpCode Translator For PaddlePaddle☆15Oct 13, 2023Updated 2 years ago
- Code and data for the paper: DTSM: Toward Dense Table Structure Recognition with Text Query Encoder and Adjacent Feature Aggregator☆13Apr 28, 2024Updated 2 years ago
- DocTr++ in PaddlePaddle☆57Jul 24, 2024Updated last year
- 修正文档扭曲/模糊/阴影等情况，使用onnx模型简单轻量部署，未来持续跟进最新最好的文档矫正方案和模型,Correct document distortion using a lightweight ONNX model for easy deployment. We wi…☆104Dec 17, 2025Updated 6 months ago
- Port of Facebook's LLaMA model in C/C++☆32Mar 7, 2024Updated 2 years ago
- ☆42Sep 2, 2023Updated 2 years ago
- Code and data release for the paper "Learning from noisy labels by distillation"☆21Nov 17, 2017Updated 8 years ago
- SDK for TEE AI Stick (includes model training script, inference library, examples)☆27Feb 15, 2019Updated 7 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- An Optical Character Recognition (OCR) and Document Layout Analysis library written in Rust.☆120Jun 22, 2026Updated last week
- ☆11May 25, 2018Updated 8 years ago
- Apply custom CoreML model with Keras.☆14Apr 2, 2018Updated 8 years ago
- 印章目标检测以及印章内信息提取。☆18Dec 6, 2023Updated 2 years ago
- Convert LaTeX-OCR To ONNX☆14Apr 2, 2024Updated 2 years ago
- UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition☆486Sep 28, 2025Updated 9 months ago
- flowchart dataset proposed with FR-DETR☆10Jun 28, 2022Updated 4 years ago
- Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models☆68Nov 1, 2024Updated last year
- PFCC 社区博客☆14Jun 21, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- 整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX | Organize the currently open-source optimal table recognition models, improve pre-processing and post-…☆955Aug 3, 2025Updated 10 months ago
- Composition of Multimodal Language Models From Scratch☆15Aug 16, 2024Updated last year
- ☆28Oct 14, 2024Updated last year
- ☆14Jul 13, 2022Updated 3 years ago
- 检测和提取各种场景图片中的表格区域，并纠正透视和旋转问题 Detect and extract table regions from images in various scenarios, and correct perspective and rotation i…☆119Dec 10, 2024Updated last year
- An unofficial implementation of the Infini-gram model proposed by Liu et al. (2024)☆33Jun 19, 2024Updated 2 years ago
- Analysis of Chinese and English layouts 中英文版面分析☆273Mar 24, 2026Updated 3 months ago
- A PyTorch implementation of DTrOCR: Decoder-only Transformer for Optical Character Recognition☆205Jun 11, 2026Updated 2 weeks ago
- [CVPR 2025] PyTorch implementation of paper "FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training"☆33Jul 8, 2025Updated 11 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆14Aug 16, 2018Updated 7 years ago
- 该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题： 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作☆63Sep 6, 2024Updated last year
- 使用onnxruntime部署MOWA：多合一图像扭曲模型，能处理6种图像扭曲任务，依然是包含C++和Python两个版本的程序☆34Jul 7, 2024Updated last year
- NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancement☆53Aug 5, 2024Updated last year
- ☆18Aug 23, 2022Updated 3 years ago
- A high content analysis method to study skeletal muscle☆12Apr 26, 2024Updated 2 years ago
- ☆14Mar 26, 2024Updated 2 years ago