metadata v8

app.py

@@ -41,6 +41,10 @@ def build_database():
     database = []
     batch_size = 10
 
+    # Debug: Print dataset structure
+    print("Dataset structure:", dataset.features)
+    print("First item structure:", dataset[0])
+
     for i in range(0, len(dataset), batch_size):
         batch = dataset[i:i + batch_size]
         print(f"📦 Procesando lote {i // batch_size + 1}/{(len(dataset) + batch_size - 1) // batch_size}")
@@ -48,14 +52,29 @@ def build_database():
         for j, item in enumerate(batch):
             try:
                 img_data = item["image"]
-                
-                # Convertir a PIL Image si es necesario
-                if isinstance(img_data, dict) and "bytes" in img_data:
-                    img = Image.open(BytesIO(img_data["bytes"]))
-                elif isinstance(img_data, str) and img_data.startswith("http"):
-                    response = requests.get(img_data, timeout=10)
-                    response.raise_for_status()
-                    img = Image.open(BytesIO(response.content))
+                print(f"Debug - Image data type: {type(img_data)}")
+                print(f"Debug - Image data content: {img_data}")
+
+                # Handle different image data formats
+                if hasattr(img_data, 'numpy'):
+                    # If it's a tensor/array, convert to PIL
+                    img = Image.fromarray(img_data.numpy())
+                elif isinstance(img_data, dict):
+                    # If it's a dictionary, try to get the image data
+                    if "bytes" in img_data:
+                        img = Image.open(BytesIO(img_data["bytes"]))
+                    elif "path" in img_data:
+                        img = Image.open(img_data["path"])
+                    else:
+                        print(f"❌ Formato de diccionario no soportado: {img_data.keys()}")
+                        continue
+                elif isinstance(img_data, str):
+                    if img_data.startswith("http"):
+                        response = requests.get(img_data, timeout=10)
+                        response.raise_for_status()
+                        img = Image.open(BytesIO(response.content))
+                    else:
+                        img = Image.open(img_data)
                 elif isinstance(img_data, Image.Image):
                     img = img_data
                 else:
@@ -81,6 +100,9 @@ def build_database():
                 continue
             except Exception as e:
                 print(f"❌ No se pudo procesar imagen {i+j}: {str(e)}")
+                print(f"Error details: {type(e).__name__}")
+                import traceback
+                print(traceback.format_exc())
                 continue
 
         # 💾 Guardar después de cada batch