</div>

from transformers import pipeline


detector = pipeline(
    task="object-detection",
    model="hustvl/yolos-base",
    device=0
)
detector("https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png")

import requests
import torch
from PIL import Image

from transformers import AutoImageProcessor, AutoModelForObjectDetection


processor = AutoImageProcessor.from_pretrained("hustvl/yolos-base")
model = AutoModelForObjectDetection.from_pretrained("hustvl/yolos-base", attn_implementation="sdpa", device_map="auto")

url = "https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
inputs = processor(images=image, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)
logits = outputs.logits.softmax(-1)
scores, labels = logits[..., :-1].max(-1)
boxes = outputs.pred_boxes

threshold = 0.3
keep = scores[0] > threshold

filtered_scores = scores[0][keep]
filtered_labels = labels[0][keep]
filtered_boxes  = boxes[0][keep]

width, height = image.size
pixel_boxes = filtered_boxes * torch.tensor([width, height, width, height], device=boxes.device)

for score, label, box in zip(filtered_scores, filtered_labels, pixel_boxes):
    x0, y0, x1, y1 = box.tolist()
    print(f"Label {model.config.id2label[label.item()]}: {score:.2f} at [{x0:.0f}, {y0:.0f}, {x1:.0f}, {y1:.0f}]")