BaofengZan / GOT-OCRv2-onnxLinks
用于学习GOT/Qwen/OnnxLLm
☆52Updated 7 months ago
Alternatives and similar repositories for GOT-OCRv2-onnx
Users that are interested in GOT-OCRv2-onnx are comparing it to the libraries listed below
Sorting:
- [MM'2024] PEneo, an effective algorithm for key-value pair extraction from form-like documents, designed for real-world applications.☆33Updated last month
- 研究GOT-OCR-项目落地加速,不限语言☆60Updated 7 months ago
- 基于TrOCR + UniMER-1M数据集,训练一个小而美的公式识别模型☆23Updated 6 months ago
- convert paddleOCR to torchOCR, ppocr-v3,ppocr-v4, onnx, openvino☆32Updated last year
- 使用mnn-llm对GOT-OCR2.0进行推理☆15Updated 8 months ago
- GOT的vLLM加速实现 并结合 MinerU 实现RAG中的pdf 解析☆57Updated 6 months ago
- The official PyTorch implementation of SEMv3.☆41Updated last year
- ☆90Updated 5 months ago
- ☆179Updated last year
- NVIDIA TensorRT Hackathon 2023复赛选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆42Updated last year
- 阅读顺序、Layoutreader☆15Updated 3 weeks ago
- useful text recognition algorithms, CRNN and SVTR text recognition☆29Updated 2 years ago
- Large Language Model Onnx Inference Framework☆35Updated 4 months ago
- llm deploy project based onnx.☆37Updated 7 months ago
- DocTr++ in PaddlePaddle☆51Updated 10 months ago
- ☆95Updated 3 years ago
- ICDAR 2024 Table OCR Model☆34Updated 6 months ago
- [TAI 2023] Appearance Enhancement for Camera-captured Document Images in the Wild☆39Updated last year
- Read Ten Lines at One Glance: Line-Aware Semi-Autoregressive Transformer for Multi-Line Handwritten Mathematical Expression Recognition☆28Updated last year
- ☆56Updated last year
- ☆59Updated 11 months ago
- ☆53Updated last year
- [arXiv: 2505.17163] OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning☆36Updated last week
- Style-Text data synthesis tool☆49Updated 5 months ago
- WikiTableSet: A largest publicly available image-based table recognition dataset in three languages built from Wikipedia☆30Updated 2 years ago
- 卡证和文档检测和矫正☆59Updated 8 months ago
- Vary-tiny codebase upon LAVIS (for training from scratch)and a PDF image-text pairs data (about 600k including English/Chinese)☆83Updated 8 months ago
- CycleCenternet based on MMDetection☆20Updated last year
- The official implementation of SPTS v2: Single-Point Text Spotting☆135Updated last year
- ☆42Updated last year