Update app.py

app.py

@@ -1,35 +1,28 @@
-import gradio as gr
 from transformers import DetrImageProcessor, DetrForObjectDetection
 import torch
 from PIL import Image
 import requests
 
-# Charger le modèle
+# URL de l'image d'exemple
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+# Téléchargement du modèle sans la dépendance 'timm'
 processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
 model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
 
-def detect_objects(image_url):
-    image = Image.open(requests.get(image_url, stream=True).raw)
-    inputs = processor(images=image, return_tensors="pt")
-    outputs = model(**inputs)
-    target_sizes = torch.tensor([image.size[::-1]])
-    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
-    
-    detections = []
-    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
-        box = [round(i, 2) for i in box.tolist()]
-        detections.append(
-            f"Detected {model.config.id2label[label.item()]} with confidence "
-            f"{round(score.item(), 3)} at location {box}"
-        )
-    return "\n".join(detections)
+# Préparer l'image pour le modèle
+inputs = processor(images=image, return_tensors="pt")
+outputs = model(**inputs)
 
-# Interface Gradio
-iface = gr.Interface(
-    fn=detect_objects,
-    inputs="text",  # Entrée: une URL d'image
-    outputs="text",  # Sortie: liste des détections
-    description="Paste an image URL to detect objects."
-)
+# Post-traitement des résultats pour obtenir les boîtes englobantes et les labels
+target_sizes = torch.tensor([image.size[::-1]])
+results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
 
-iface.launch()
+# Afficher les résultats
+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}"
+    )