Update app.py

app.py

@@ -75,47 +75,28 @@ def save_dataframe_to_csv(df):
 
 # Main function to perform image captioning and image-text matching for multiple images
 def process_images_and_statements(files):
-    # Initialize an empty list to store the results for all images
     all_results_list = []
-
-    # Loop through each uploaded file (image)
+    
+    # If 'files' is a list, convert it to a dictionary
+    if isinstance(files, list):
+        files = {f.name: f for f in files}
+    
     for file_name, image in files.items():
-        # Generate image caption for the uploaded image using git-large-r-textcaps
         caption = generate_caption(git_processor_large_textcaps, git_model_large_textcaps, image)
-
-        # Loop through each predefined statement
         for statement in statements:
-            # Compute textual similarity between caption and statement
-            textual_similarity_score = (compute_textual_similarity(caption, statement) * 100) # Multiply by 100
-
-            # Compute ITM score for the image-statement pair
-            itm_score_statement = (compute_itm_score(image, statement) * 100) # Multiply by 100
-
-            # Define weights for combining textual similarity score and image-statement ITM score (adjust as needed)
-            weight_textual_similarity = 0.5
-            weight_statement = 0.5
-
-            # Combine the two scores using a weighted average
-            final_score = ((weight_textual_similarity * textual_similarity_score) +
-                           (weight_statement * itm_score_statement))
-
-            # Append the result to the all_results_list
+            textual_similarity_score = compute_textual_similarity(caption, statement) * 100
+            itm_score_statement = compute_itm_score(image, statement) * 100
+            final_score = 0.5 * textual_similarity_score + 0.5 * itm_score_statement
             all_results_list.append({
                 'Image File Name': file_name,  # Include the image file name
                 'Statement': statement,
                 'Generated Caption': caption,
-                'Textual Similarity Score': f"{textual_similarity_score:.2f}%", # Format as percentage with two decimal places
-                'ITM Score': f"{itm_score_statement:.2f}%", # Format as percentage with two decimal places
-                'Final Combined Score': f"{final_score:.2f}%" # Format as percentage with two decimal places
+                'Textual Similarity Score': f"{textual_similarity_score:.2f}%",
+                'ITM Score': f"{itm_score_statement:.2f}%",
+                'Final Combined Score': f"{final_score:.2f}%"
             })
-
-    # Convert the all_results_list to a DataFrame using pandas.concat
     results_df = pd.concat([pd.DataFrame([result]) for result in all_results_list], ignore_index=True)
-
-    # Save results_df to a CSV file
     csv_results = save_dataframe_to_csv(results_df)
-
-    # Return both the DataFrame and the CSV data for the Gradio interface
     return results_df, csv_results
 
 # Gradio interface with File input to receive multiple images and file names
@@ -132,6 +113,4 @@ iface = gr.Interface(
     css=".output { flex-direction: column; } .output .outputs { width: 100%; }" # Custom CSS
 )
 
-#iface.launch()
 iface.launch(debug=True)
-