Update app.py

app.py

@@ -49,55 +49,73 @@ def load_and_preprocess_image(image, target_size=(224, 224)):
 
 # Function to make predictions
 def make_prediction(image, taxonomic_decision, taxonomic_level):
-    try:
-        # Preprocess the image
-        img_array = load_and_preprocess_image(image)
+    # Preprocess the image
+    img_array = load_and_preprocess_image(image)
+    
+    # Get the class names from the 'species' column
+    class_names = sorted(taxo_df['species'].unique())
+    
+    # Make a prediction
+    prediction = model.predict(img_array)
+    
+    # Initialize variables for aggregated predictions and level index
+    aggregated_predictions = None
+    current_level_index = 0  # Start from the species level
+    
+    # Determine the initial taxonomic level based on the user's decision
+    if taxonomic_decision == "No, I will let the model decide":
+        current_level_index = 0  # Start at species level if letting the model decide
+    else:
+        current_level_index = taxonomic_levels.index(taxonomic_level)  # Use specified 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)
         
-        # Get the class names from the 'species' column
-        class_names = sorted(taxo_df['species'].unique())
+        # 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]
         
-        # Make a prediction
-        prediction = model.predict(img_array)
-
-        # Check the shape of predictions
-        print(f"Prediction shape: {prediction.shape}")
-
-        # Initialize variables for aggregated predictions and level index
-        aggregated_predictions = None
-        current_level_index = 0  # Start from the species level
-
-        # Determine the initial taxonomic level based on the user's decision
-        if taxonomic_decision == "No, I will let the model decide":
-            current_level_index = 0
-        else:
-            current_level_index = taxonomic_levels.index(taxonomic_level)
-
-        # Loop through taxonomic levels
-        while current_level_index < len(taxonomic_levels):
-            aggregated_predictions, aggregated_class_labels = aggregate_predictions(
-                prediction, taxonomic_levels[current_level_index], class_names
-            )
-            
-            # Check if predictions are valid
-            if aggregated_predictions is None or aggregated_predictions.size == 0:
-                return "<h2>No valid predictions available.</h2>"
-
-            top_prediction_index = np.argmax(aggregated_predictions)
-            top_prediction_confidence = aggregated_predictions[0][top_prediction_index]
-
-            if top_prediction_confidence >= 0.80:
-                break
+        if top_prediction_confidence >= 0.80:
+            break  # Confidence threshold met, exit loop
+        
+        current_level_index += 1  # Move to the next taxonomic level
 
-            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_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>"
+
+    # 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
 
-        # 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]
+    for i in top_indices:
+        class_name = aggregated_class_labels[i]
         
-        # Continue with generating output text...
+        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_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>)" \
+                           f"<span style='margin-left: auto;'>{confidence_percentage:.2f}%</span></div>"
+        else:
+            # No common names at higher taxonomic levels
+            confidence_percentage = aggregated_predictions[0][i] * 100
+            output_text += f"<div style='display: flex; justify-content: space-between;'>" \
+                           f"<span>{class_name}</span>" \
+                           f"<span style='margin-left: auto;'>{confidence_percentage:.2f}%</span></div>"
     
-    except Exception as e:
-        return f"<h2>Error during prediction: {str(e)}</h2>"
+    return output_text
 
 # Define the Gradio interface
 interface = gr.Interface(