Update app.py

app.py

@@ -93,6 +93,31 @@ def doubleimage_text_zeroshot(image, image2,  text_list):
     with torch.no_grad():
         embeddings = model(inputs)
  
+    scores = (
+        torch.softmax(
+            embeddings[ModalityType.VISION] @ embeddings[ModalityType.TEXT].T, dim=-1
+        )
+        .squeeze(0)
+        .tolist()
+    )
+
+    score_dict = {label: score for label, score in zip(labels, scores)}
+
+    return score_dict
+
+
+
+def doubleimage_text_zeroshotOLD(image, image2,  text_list):
+    image_paths = [image, image2]
+    labels = [label.strip(" ") for label in text_list.strip(" ").split("|")]
+    inputs = {
+        ModalityType.TEXT: data.load_and_transform_text(labels, device),
+        ModalityType.VISION: data.load_and_transform_vision_data(image_paths, device),
+    }
+
+    with torch.no_grad():
+        embeddings = model(inputs)
+