metadata v11

app.py

@@ -22,7 +22,12 @@ EMBEDDINGS_FILE = EMBEDDINGS_DIR / "embeddings.pkl"
 
 # ✅ Cargar dataset desde metadata.csv (con URLs absolutas)
 dataset = load_dataset("csv", data_files="metadata.csv")
-dataset = dataset["train"].cast_column("image", HfImage())
+dataset = dataset["train"].cast_column("image", HfImage(decode=True))
+
+# Debug dataset loading
+print("Dataset columns:", dataset.column_names)
+print("Dataset features:", dataset.features)
+print("First item:", dataset[0])
 
 # 🔄 Preprocesar imagen para Facenet
 def preprocess_image(img: Image.Image) -> np.ndarray:
@@ -55,10 +60,15 @@ def build_database():
             try:
                 print(f"Debug - Processing item {i+j}")
                 print(f"Debug - Item type: {type(item)}")
+                print(f"Debug - Item keys: {item.keys() if isinstance(item, dict) else 'Not a dict'}")
                 
                 # Skip if item is not in the expected format
-                if not isinstance(item, dict) or "image" not in item:
-                    print(f"⚠️ Skipping item {i+j} - Invalid format")
+                if not isinstance(item, dict):
+                    print(f"⚠️ Skipping item {i+j} - Not a dictionary")
+                    continue
+                
+                if "image" not in item:
+                    print(f"⚠️ Skipping item {i+j} - No image key")
                     continue
                 
                 img = item["image"]