detr-resnet-50-sku110k

Aquí se muestra cómo utilizar este modelo:

from transformers import DetrImageProcessor, DetrForObjectDetection
import torch
from PIL import Image, ImageOps
import requests

url = "https://github.com/Isalia20/DETR-finetune/blob/main/IMG_3507.jpg?raw=true"
image = Image.open(requests.get(url, stream=True).raw)
image = ImageOps.exif_transpose(image)

# puedes especificar la etiqueta de revisión si no deseas la dependencia timm
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
model = DetrForObjectDetection.from_pretrained("isalia99/detr-resnet-50-sku110k")
model = model.eval()
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)

# convierte las salidas (cajas delimitadoras y logits de clase) a la API COCO
# mantengamos solo detecciones con puntaje > 0.8
target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.8)[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}")

Esto debería generar:

Detected LABEL_1 with confidence 0.983 at location [665.49, 480.05, 708.15, 650.11]
Detected LABEL_1 with confidence 0.938 at location [204.99, 1405.9, 239.9, 1546.5]
...
Detected LABEL_1 with confidence 0.998 at location [772.85, 169.49, 829.67, 372.18]
Detected LABEL_1 with confidence 0.999 at location [828.28, 1475.16, 874.37, 1593.43]