--- title: RT-DETR-H_layout_17cls canonical_url: "https://www.modelscope.cn/models/PaddlePaddle/RT-DETR-H_layout_17cls" md_url: "https://www.modelscope.cn/models/PaddlePaddle/RT-DETR-H_layout_17cls.md" repository: PaddlePaddle/RT-DETR-H_layout_17cls last_updated: 2026-06-12 license: apache-2.0 language: - en - zh downloads: 841 stars: 0 tags: - OCR - PaddlePaddle - PaddleOCR - layout_detection --- # RT-DETR-H_layout_17cls > RT-DETR-H_layout_17cls - PaddlePaddle 在 ModelScope 开源的模型。RT-DETR-Hlayout17cls PaddlePaddle/RT-DETR-H_layout_17cls 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。 - **Repository**: PaddlePaddle/RT-DETR-H_layout_17cls - **License**: apache-2.0 - **Tags**: OCR, PaddlePaddle, PaddleOCR, layout_detection - **Downloads**: 841 - **Stars**: 0 - **Last updated**: 2026-06-12 Source: https://www.modelscope.cn/models/PaddlePaddle/RT-DETR-H_layout_17cls --- # RT-DETR-H_layout_17cls ## Introduction A high-precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using RT-DETR-H. It is a 17-Class Area Detection Model, including 17 common layout categories: Paragraph Title, Image, Text, Number, Abstract, Content, Figure Caption, Formula, Table, Table Caption, References, Document Title, Footnote, Header, Algorithm, Footer, and Seal. The key metrics are as follow: | Model| mAP(0.5) (%) | | --- | --- | |RT-DETR-H_layout_17cls | 98.3 | **Note**: Paddleocr's self built layout area detection data set contains 892 common document type images such as Chinese and English papers, magazines and research papers. ## Quick Start ### Installation 1. PaddlePaddle Please refer to the following commands to install PaddlePaddle using pip: ```bash # for CUDA11.8 python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/ # for CUDA12.6 python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/ # for CPU python -m pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/ ``` For details about PaddlePaddle installation, please refer to the [PaddlePaddle official website](https://www.paddlepaddle.org.cn/en/install/quick). 2. PaddleOCR Install the latest version of the PaddleOCR inference package from PyPI: ```bash python -m pip install paddleocr ``` ### Model Usage You can quickly experience the functionality with a single command: ```bash paddleocr layout_detection \ --model_name RT-DETR-H_layout_17cls \ -i https://cdn-uploads.huggingface.co/production/uploads/63d7b8ee07cd1aa3c49a2026/N5C68HPVAI-xQAWTxpbA6.jpeg ``` You can also integrate the model inference of the layout detection module into your project. Before running the following code, please download the sample image to your local machine. ```python from paddleocr import LayoutDetection model = LayoutDetection(model_name="RT-DETR-H_layout_17cls") output = model.predict("N5C68HPVAI-xQAWTxpbA6.jpeg", batch_size=1, layout_nms=True) for res in output: res.print() res.save_to_img(save_path="./output/") res.save_to_json(save_path="./output/res.json") ``` After running, the obtained result is as follows: ```json {'res': {'input_path': '/root/.paddlex/predict_input/N5C68HPVAI-xQAWTxpbA6.jpeg', 'page_index': None, 'boxes': [{'cls_id': 8, 'label': 'table', 'score': 0.9912393093109131, 'coordinate': [435.64767, 105.309265, 662.8984, 313.5123]}, {'cls_id': 8, 'label': 'table', 'score': 0.990542471408844, 'coordinate': [71.72168, 104.943596, 322.20175, 298.0071]}, {'cls_id': 2, 'label': 'text', 'score': 0.9888639450073242, 'coordinate': [35.285786, 350.7265, 360.89682, 612.0047]}, {'cls_id': 2, 'label': 'text', 'score': 0.9886889457702637, 'coordinate': [35.6621, 648.2065, 360.35577, 849.99054]}, {'cls_id': 2, 'label': 'text', 'score': 0.9880586862564087, 'coordinate': [386.79614, 347.20154, 712.9174, 460.22733]}, {'cls_id': 2, 'label': 'text', 'score': 0.9834797978401184, 'coordinate': [386.9635, 736.2906, 712.5422, 851.08307]}, {'cls_id': 2, 'label': 'text', 'score': 0.9647906422615051, 'coordinate': [386.95007, 497.8405, 713.4789, 699.4109]}, {'cls_id': 9, 'label': 'table_title', 'score': 0.9521941542625427, 'coordinate': [35.65011, 21.414091, 361.0532, 77.568085]}, {'cls_id': 2, 'label': 'text', 'score': 0.9295578598976135, 'coordinate': [388.43976, 717.0956, 526.74976, 730.4071]}, {'cls_id': 2, 'label': 'text', 'score': 0.9274019002914429, 'coordinate': [36.738716, 628.7795, 187.91776, 642.0003]}, {'cls_id': 2, 'label': 'text', 'score': 0.9150785207748413, 'coordinate': [36.569218, 331.93774, 143.65463, 345.63232]}, {'cls_id': 9, 'label': 'table_title', 'score': 0.7173759937286377, 'coordinate': [386.58502, 21.287352, 714.23517, 76.551476]}, {'cls_id': 2, 'label': 'text', 'score': 0.7161796689033508, 'coordinate': [387.91153, 477.7165, 701.8612, 491.80142]}]}} ``` The visualized image is as follows: ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63d7b8ee07cd1aa3c49a2026/q230sr0n0iAOlU1J6FyNE.jpeg) For details about usage command and descriptions of parameters, please refer to the [Document](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/module_usage/layout_detection.html#iii-quick-integration). ### Pipeline Usage The ability of a single model is limited. But the pipeline consists of several models can provide more capacity to resolve difficult problems in real-world scenarios. #### PP-TableMagic (table_recognition_v2) The General Table Recognition v2 pipeline (PP-TableMagic) is designed to tackle table recognition tasks, identifying tables in images and outputting them in HTML format. PP-TableMagic includes the following 8 modules: * Table Structure Recognition Module * Table Classification Module * Table Cell Detection Module * Text Detection Module * Text Recognition Module * Layout Region Detection Module (optional) * Document Image Orientation Classification Module (optional) * Text Image Unwarping Module (optional) You can quickly experience the PP-TableMagic pipeline with a single command. ```bash paddleocr table_recognition_v2 -i https://cdn-uploads.huggingface.co/production/uploads/63d7b8ee07cd1aa3c49a2026/tuY1zoUdZsL6-9yGG0MpU.jpeg \ --layout_detection_model_name RT-DETR-H_layout_17cls \ --use_doc_orientation_classify False \ --use_doc_unwarping False \ --save_path ./output \ --device gpu:0 ``` If save_path is specified, the visualization results will be saved under `save_path`. The command-line method is for quick experience. For project integration, also only a few codes are needed as well: ```python from paddleocr import TableRecognitionPipelineV2 pipeline = TableRecognitionPipelineV2( layout_detection_model_name=RT-DETR-H_layout_17cls, use_doc_orientation_classify=False, # Use use_doc_orientation_classify to enable/disable document orientation classification model use_doc_unwarping=False, # Use use_doc_unwarping to enable/disable document unwarping module device="gpu:0", # Use device to specify GPU for model inference ) output = pipeline.predict("tuY1zoUdZsL6-9yGG0MpU.jpeg") for res in output: res.print() ## Print the predicted structured output res.save_to_img("./output/") res.save_to_xlsx("./output/") res.save_to_html("./output/") res.save_to_json("./output/") ``` The default model used in pipeline is `PP-DocLayout-L`, so it is needed that specifing to `RT-DETR-H_layout_17cls` by argument `layout_detection_model_name`. And you can also use the local model file by argument `layout_detection_model_dir`. For details about usage command and descriptions of parameters, please refer to the [Document](https://paddlepaddle.github.io/PaddleOCR/main/en/version3.x/pipeline_usage/table_recognition_v2.html#2-quick-start). ## Links [PaddleOCR Repo](https://github.com/paddlepaddle/paddleocr) [PaddleOCR Documentation](https://paddlepaddle.github.io/PaddleOCR/latest/en/index.html)