Update app.py

app.py

@@ -3,32 +3,37 @@ import torch
 from PIL import Image
 import gradio as gr
 
-# Cargar el procesador y el modelo
+# Cargar procesador y modelo
 processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
 model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
 
-# Función para procesar la imagen y detectar objetos
-def detect_objects(image, threshold=0.9):
+def detect_objects(image: Image.Image, threshold: float = 0.9):
+    if image is None:
+        return "Sube una imagen para iniciar."
+
+    # Preprocesar e inferir
     inputs = processor(images=image, return_tensors="pt")
     with torch.no_grad():
         outputs = model(**inputs)
 
-    # Ajustar tamaño de salida al de la imagen
-    target_sizes = torch.tensor([image.size[::-1]])
+    # (H, W) en enteros; shape (batch, 2)
+    h, w = image.size[1], image.size[0]
+    target_sizes = torch.tensor([[h, w]], dtype=torch.int64)
+
+    # Post-proceso
     results = processor.post_process_object_detection(
         outputs, target_sizes=target_sizes, threshold=threshold
     )[0]
 
-    detected_objects = []
+    # Formatear salida
+    lines = []
     for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
         label_name = model.config.id2label[label.item()]
-        detected_objects.append(
-            f"Objeto: {label_name}, Score: {score:.2f}, Box: { [round(v,2) for v in box.tolist()] }"
-        )
+        box_rounded = [round(float(v), 2) for v in box.tolist()]
+        lines.append(f"Objeto: {label_name}, Score: {float(score):.2f}, Box: {box_rounded}")
 
-    return "\n".join(detected_objects)
+    return "\n".join(lines) if lines else "Sin detecciones (prueba bajando el umbral)."
 
-# Interfaz con la API nueva de Gradio
 demo = gr.Interface(
     fn=detect_objects,
     inputs=[gr.Image(type="pil", label="Imagen"), gr.Slider(0, 1, value=0.9, step=0.05, label="Umbral")],