test.py

from transformers import AutoImageProcessor, DeformableDetrForObjectDetection
import torch
from PIL import Image
import requests

# url = "http://images.cocodataset.org/val2017/000000039769.jpg"
url = "https://e0.365dm.com/22/12/768x432/skysports-lionel-messi-world-cup-2022_6000455.jpg?20221218174405"
image = Image.open(requests.get(url, stream=True).raw)

processor = AutoImageProcessor.from_pretrained("zongzhuofan/co-detr-vit-large-coco-instance")
model = DeformableDetrForObjectDetection.from_pretrained("zongzhuofan/co-detr-vit-large-coco-instance")

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)

# convert outputs (bounding boxes and class logits) to COCO API
# let's only keep detections with score > 0.7
target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.7)[0]

for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    box = [round(i, 2) for i in box.tolist()]
    print(
            f"Detected {model.config.id2label[label.item()]} with confidence "
            f"{round(score.item(), 3)} at location {box}"
    )

# open the image and draw bounding boxes on it with labels
from PIL import ImageDraw

draw = ImageDraw.Draw(image)
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    box = [round(i, 2) for i in box.tolist()]
    draw.rectangle(box, outline="red", width=3)
    draw.text((box[0], box[1]), f"{model.config.id2label[label.item()]} {round(score.item(), 3)}", fill="red")

# show the image
image.show()