metadata v12

app.py

@@ -50,39 +50,42 @@ def build_database():
         batch = dataset[i:i + batch_size]
         print(f"📦 Procesando lote {i // batch_size + 1}/{(len(dataset) + batch_size - 1) // batch_size}")
 
-        for j, item in enumerate(batch):
-            try:
-                if not isinstance(item, dict) or "image" not in item:
-                    print(f"⚠️ Saltando item {i + j} - estructura inválida: {item}")
-                    continue
-
-                image_url = item["image"]
-                if not isinstance(image_url, str) or not image_url.startswith("http"):
-                    print(f"⚠️ Saltando item {i + j} - URL inválida: {image_url}")
-                    continue
-
-                # Descargar imagen desde la URL
-                response = requests.get(image_url, timeout=10)
-                response.raise_for_status()
-                img = Image.open(BytesIO(response.content)).convert("RGB")
-
-                img_processed = preprocess_image(img)
-                embedding = DeepFace.represent(
-                    img_path=img_processed,
-                    model_name="Facenet",
-                    enforce_detection=False
-                )[0]["embedding"]
-
-                database.append((f"image_{i + j}", img, embedding))
-                print(f"✅ Procesada imagen {i + j + 1}/{len(dataset)}")
-
-                del img_processed
-                gc.collect()
-
-            except Exception as e:
-                print(f"❌ Error al procesar imagen {i + j}: {str(e)}")
+    for j, item in enumerate(batch):
+        try:
+            # Validar estructura
+            if not isinstance(item, dict) or "image" not in item:
+                print(f"⚠️ Saltando item {i + j} - estructura inválida: {item}")
                 continue
 
+            image_url = item["image"]
+
+            # Validar tipo y formato
+            if not isinstance(image_url, str) or not image_url.startswith("http"):
+                print(f"⚠️ Saltando item {i + j} - URL inválida: {image_url}")
+                continue
+
+            # Descargar y procesar imagen
+            response = requests.get(image_url, timeout=10)
+            response.raise_for_status()
+            img = Image.open(BytesIO(response.content)).convert("RGB")
+
+            img_processed = preprocess_image(img)
+            embedding = DeepFace.represent(
+                img_path=img_processed,
+                model_name="Facenet",
+                enforce_detection=False
+            )[0]["embedding"]
+
+            database.append((f"image_{i + j}", img, embedding))
+            print(f"✅ Procesada imagen {i + j + 1}/{len(dataset)}")
+
+            del img_processed
+            gc.collect()
+
+        except Exception as e:
+            print(f"❌ Error al procesar imagen {i + j}: {str(e)}")
+            continue
+
         # Guardar después de cada batch
         if database:
             print("💾 Guardando embeddings...")