Error fix

app.py

@@ -36,6 +36,17 @@ def compute_semantic_similarity(img_a: Image.Image, img_b: Image.Image) -> float
     with torch.no_grad():
         image_features = clip_model.get_image_features(**inputs)
         
+    # --- FIX: Handle Transformers 5.x object returns ---
+    if not isinstance(image_features, torch.Tensor):
+        if hasattr(image_features, "image_embeds"):
+            image_features = image_features.image_embeds
+        elif hasattr(image_features, "pooler_output"):
+            image_features = image_features.pooler_output
+        else:
+            # Fallback for tuple-like object behavior
+            image_features = image_features[1] if isinstance(image_features, tuple) and len(image_features) > 1 else image_features[0]
+    # ---------------------------------------------------
+            
     # Normalize and compute cosine similarity
     image_features = F.normalize(image_features, p=2, dim=-1)
     score = F.cosine_similarity(image_features[0].unsqueeze(0), image_features[1].unsqueeze(0))