Instructions to use PaddlePaddle/PP-DocLayoutV2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use PaddlePaddle/PP-DocLayoutV2 with PaddleOCR:
# 1. See https://www.paddlepaddle.org.cn/en/install to install paddlepaddle # 2. pip install paddleocr from paddleocr import LayoutDetection model = LayoutDetection(model_name="PP-DocLayoutV2") output = model.predict(input="path/to/image.png", batch_size=1) for res in output: res.print() res.save_to_img(save_path="./output/") res.save_to_json(save_path="./output/res.json") - Notebooks
- Google Colab
- Kaggle
Download inference.pdmodel from PaddlePaddle/PP-DocLayoutV2: direct link, hf CLI and curl.
- Browser
- Download file 1.52 MB
-
https://huggingface.co/PaddlePaddle/PP-DocLayoutV2/resolve/refs%2Fpr%2F1/inference.pdmodel
- Command line
-
hf download hf://PaddlePaddle/PP-DocLayoutV2@refs/pr/1/inference.pdmodel
-
curl -L -o inference.pdmodel https://huggingface.co/PaddlePaddle/PP-DocLayoutV2/resolve/refs%2Fpr%2F1/inference.pdmodel
1.52 MB
- Xet hash:
- 322c8b6b9ac52369e837b7aca6572319e437e4883abb6028a0ada274000178ac
- Size of remote file:
- 1.52 MB
- SHA256:
- fddd4b4359b95e6f1dd86c86f05e9516517bead9089287681838cdcbf003563b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.