Update app.py

app.py

@@ -49,12 +49,6 @@ def load_and_preprocess_image(image, target_size=(224, 224)):
 
 # Function to make predictions
 def make_prediction(image, taxonomic_decision, taxonomic_level):
-    # Determine the taxonomic level based on the user's decision
-    if taxonomic_decision == "Yes, I want to specify the taxonomic level":
-        taxonomic_level = taxonomic_level  # Use the level specified in the dropdown
-    else:
-        taxonomic_level = "species"  # Default to species if not specified
-    
     # Preprocess the image
     img_array = load_and_preprocess_image(image)
     
@@ -64,19 +58,31 @@ def make_prediction(image, taxonomic_decision, taxonomic_level):
     # Make a prediction
     prediction = model.predict(img_array)
     
-    # Aggregate predictions based on the selected taxonomic level
-    aggregated_predictions, aggregated_class_labels = aggregate_predictions(prediction, taxonomic_level, class_names)
-    
-    # Get the top 5 predictions
-    top_indices = np.argsort(aggregated_predictions[0])[-5:][::-1]
-    
-    # Get predicted class for the top prediction
+    # Initialize variables for aggregated predictions and level index
+    aggregated_predictions = None
+    current_level_index = taxonomic_levels.index(taxonomic_level)
+
+    # Loop through taxonomic levels to check confidence
+    while current_level_index < len(taxonomic_levels):
+        # Aggregate predictions based on the current taxonomic level
+        aggregated_predictions, aggregated_class_labels = aggregate_predictions(prediction, taxonomic_levels[current_level_index], class_names)
+        
+        # Check if the confidence of the top prediction meets the threshold
+        top_prediction_index = np.argmax(aggregated_predictions)
+        top_prediction_confidence = aggregated_predictions[0][top_prediction_index]
+        
+        if top_prediction_confidence >= 0.80:
+            break  # Confidence threshold met, exit loop
+        
+        current_level_index += 1  # Move to the next taxonomic level
+
+    # Get the predicted class name for the top prediction
     predicted_class_index = np.argmax(aggregated_predictions)
     predicted_class_name = aggregated_class_labels[predicted_class_index]
     
     # Check if common name should be displayed (only at species level)
-    if taxonomic_level == "species":
-        predicted_common_name = taxo_df[taxo_df[taxonomic_level] == predicted_class_name]['common_name'].values[0]
+    if taxonomic_levels[current_level_index] == "species":
+        predicted_common_name = taxo_df[taxo_df[taxonomic_levels[current_level_index]] == predicted_class_name]['common_name'].values[0]
         output_text = f"<h1 style='font-weight: bold;'><span style='font-style: italic;'>{predicted_class_name}</span> ({predicted_common_name})</h1>"
     else:
         output_text = f"<h1 style='font-weight: bold;'>{predicted_class_name}</h1>"
@@ -84,12 +90,14 @@ def make_prediction(image, taxonomic_decision, taxonomic_level):
     # Add the top 5 predictions
     output_text += "<h4 style='font-weight: bold; font-size: 1.2em;'>Top 5 Predictions:</h4>"
     
+    top_indices = np.argsort(aggregated_predictions[0])[-5:][::-1]  # Get top 5 predictions
+
     for i in top_indices:
         class_name = aggregated_class_labels[i]
         
-        if taxonomic_level == "species":
+        if taxonomic_levels[current_level_index] == "species":
             # Display common names only at species level and make it italic
-            common_name = taxo_df[taxo_df[taxonomic_level] == class_name]['common_name'].values[0]
+            common_name = taxo_df[taxo_df[taxonomic_levels[current_level_index]] == class_name]['common_name'].values[0]
             confidence_percentage = aggregated_predictions[0][i] * 100
             output_text += f"<div style='display: flex; justify-content: space-between;'>" \
                            f"<span style='font-style: italic;'>{class_name}</span>&nbsp;(<span>{common_name}</span>)" \
@@ -111,7 +119,7 @@ interface = gr.Interface(
         gr.Radio(choices=["Yes, I want to specify the taxonomic level", "No, I will let the model decide"],
                  label="Do you want to specify the taxonomic resolution for predictions? If you select 'No', the next drop-down menu will be bypassed.",
                  value="No, I will let the model decide"),  # Radio button for taxonomic resolution choice
-        gr.Dropdown(choices=taxonomic_levels, label="Taxonomic level", value="species")  # Dropdown for taxonomic level
+        gr.Dropdown(choices=taxonomic_levels, label="Taxonomic level:", value="species")  # Dropdown for taxonomic level
     ],
     outputs="html",  # Output type: HTML for formatting
     title="Amazon arboreal species classification",