PP-OCRv5_server_det_safetensors

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

model_path = "PaddlePaddle/PP-OCRV5_server_det_safetensors"
model = AutoModelForObjectDetection.from_pretrained(
    model_path,
    device_map="auto"
)
image_processor = AutoImageProcessor.from_pretrained(model_path)

image = Image.open(requests.get("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_001.png", stream=True).raw).convert("RGB")
inputs = image_processor(images=image, return_tensors="pt").to(model.device)
outputs = model(**inputs)

results = image_processor.post_process_object_detection(outputs, target_sizes=inputs["target_sizes"])

for result in results:
    print(result)