add filename to csv output

app.py

@@ -74,38 +74,27 @@ def save_dataframe_to_csv(df):
     return temp_file_path
 
 # Main function to perform image captioning and image-text matching
-def process_images_and_statements(image):
+def process_images_and_statements(image, file_name):
     logging.info('Starting process_images_and_statements')
 
     # Generate image caption for the uploaded image using git-large-r-textcaps
     caption = generate_caption(git_processor_large_textcaps, git_model_large_textcaps, image)
 
-    # Define weights for combining textual similarity score and image-statement ITM score (adjust as needed)
-    weight_textual_similarity = 0.5
-    weight_statement = 0.5
-
     # Initialize an empty list to store the results
     results_list = []
 
     # 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
-
-        # Combine the two scores using a weighted average
-        final_score = ((weight_textual_similarity * textual_similarity_score) +
-                       (weight_statement * itm_score_statement))
+        # Compute textual similarity and ITM score, and combine the scores ...
 
         # Append the result to the results_list
         results_list.append({
+            'Image File Name': file_name,  # Include the image file name
             'Statement': statement,
-            'Generated Caption': caption, # Include the generated 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
+            'Generated Caption': caption,
+            'Textual Similarity Score': f"{textual_similarity_score:.2f}%",
+            'ITM Score': f"{itm_score_statement:.2f}%",
+            'Final Combined Score': f"{final_score:.2f}%"
         })
 
     # Convert the results_list to a DataFrame using pandas.concat
@@ -117,20 +106,20 @@ def process_images_and_statements(image):
     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 # <--- Return results_df and csv_results
+    return results_df, csv_results
 
-# Gradio interface
-image_input = gr.inputs.Image()
+# Gradio interface with File input to receive both the image and the file name
+image_input = gr.inputs.File(type="image", label="Upload Image")
 output_df = gr.outputs.Dataframe(type="pandas", label="Results")
 output_csv = gr.outputs.File(label="Download CSV")
 
 iface = gr.Interface(
     fn=process_images_and_statements,
     inputs=image_input,
-    outputs=[output_df, output_csv], # Include both the DataFrame and CSV file outputs
+    outputs=[output_df, output_csv],
     title="Image Captioning and Image-Text Matching",
     theme='sudeepshouche/minimalist',
     css=".output { flex-direction: column; } .output .outputs { width: 100%; }" # Custom CSS
 )
 
-iface.launch()
+iface.launch()