视觉检测大模型RT-DETR部署使用-transformers

from transformers import RTDetrForObjectDetection, RTDetrImageProcessor
from PIL import Image
import requests
import torch

# 1. 加载模型（支持 PekingU/rtdetr_r50vd, rtdetr_r101vd, rtdetr_r50vd_m_coco_o365 等）
model_name = "PekingU/rtdetr_r50vd"
processor = RTDetrImageProcessor.from_pretrained(model_name)
model = RTDetrForObjectDetection.from_pretrained(model_name)

# 2. 推理
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)

# 3. 后处理
target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.5)[0]

for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    print(f"{model.config.id2label[label.item()]}: {score.item():.3f}, box: {box.tolist()}")