How to use PaddlePaddle/PP-DocLayoutV3_safetensors with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="PaddlePaddle/PP-DocLayoutV3_safetensors")
# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("PaddlePaddle/PP-DocLayoutV3_safetensors") model = AutoModelForObjectDetection.from_pretrained("PaddlePaddle/PP-DocLayoutV3_safetensors", device_map="auto")
How to use PaddlePaddle/PP-DocLayoutV3_safetensors 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_safetensors") 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")
Thanks.
afaik it is Apache2.0 license. maybe you should check github.
· Sign up or log in to comment
