Instructions to use PaddlePaddle/PP-DocLayoutV3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use PaddlePaddle/PP-DocLayoutV3 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-DocLayoutV3") 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
Customizing the model for new labels
#9 opened about 2 months ago
by
DHackbarthHSB
PP-DocLayoutV3 Inference Benchmark: SafeTensor vs ONNX vs PaddlePaddle
#8 opened about 2 months ago
by
andynoodles
serving (like vllm, etc)
#7 opened 2 months ago
by
prudant
英文版面分析不太行
#6 opened 2 months ago
by
Macropodus
OCR-Format
#5 opened 2 months ago
by
BigTiger78
I want to know the language coverage
#4 opened 3 months ago
by
aoiandroid
What is the input resolution?
#3 opened 3 months ago
by
wamreyaz
Output dimension
1
#2 opened 4 months ago
by
SuHu753
PP-DocLayoutV3 ONNX Version
👍 3
5
#1 opened 4 months ago
by
alex-dinh