PP-DocLayout_plus-L_safetensors

import requests
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForObjectDetection

model_path = "PaddlePaddle/PP-DocLayout_plus-L_safetensors"
model = AutoModelForObjectDetection.from_pretrained(model_path)
image_processor = AutoImageProcessor.from_pretrained(model_path)

image = Image.open(requests.get("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout.jpg", stream=True).raw)
inputs = image_processor(images=image, return_tensors="pt")

outputs = model(**inputs)
results = image_processor.post_process_object_detection(outputs, target_sizes=[image.size[::-1]])
for result in results:
    for score, label_id, box in zip(result["scores"], result["labels"], result["boxes"]):
        score, label = score.item(), label_id.item()
        box = [round(i, 2) for i in box.tolist()]
        print(f"{model.config.id2label[label]}: {score:.2f} {box}")