Update app.py

app.py

@@ -25,13 +25,13 @@ def find_similarity(image, text_input):
 
 
     with torch.no_grad():
-        image_features = model.encode_image(image).float()
-        text_features = model.encode_text(text_tokens).float()
+        image_features = model.encode_image(image)
+        text_features = model.encode_text(text_tokens)
 
     # Normalize features and calculate similarity
     image_features /= image_features.norm(dim=-1, keepdim=True)
     text_features /= text_features.norm(dim=-1, keepdim=True)
-    similarity = (text_features @ image_features.T).cpu().numpy()
+    similarity = (text_features @ image_features.T).squeeze(0).cpu().numpy()
 
     return similarity[0, 0]