Update app.py

app.py

@@ -152,7 +152,8 @@ def extract_zip(zip_file):
     return temp_dir
 
 # Function to classify images in a folder
-def classify_images(image_dir, model_pipeline):
+# Function to classify images in a folder
+def classify_images(image_dir, model_pipeline, model_idx):
     images = []
     labels = []
     preds = []
@@ -164,15 +165,19 @@ def classify_images(image_dir, model_pipeline):
             img_path = os.path.join(folder_path, img_name)
             try:
                 img = Image.open(img_path).convert("RGB")
+
+                # Now use the specific model pipeline passed in
                 pred = model_pipeline(img)
                 pred_label = np.argmax([x['score'] for x in pred])
+
                 preds.append(pred_label)
                 labels.append(ground_truth_label)
                 images.append(img_name)
             except Exception as e:
-                print(f"Error processing image {img_name}: {e}")
+                print(f"Error processing image {img_name} in model {model_idx}: {e}")
     return labels, preds, images
 
+
 # Function to generate evaluation metrics
 def evaluate_model(labels, preds):
     cm = confusion_matrix(labels, preds)
@@ -200,20 +205,22 @@ def evaluate_model(labels, preds):
 
     return accuracy, roc_score, report, fig, fig_roc
 
+# Batch processing for all models
 # Batch processing for all models
 # Batch processing for all models
 def process_zip(zip_file):
     extracted_dir = extract_zip(zip_file.name)
-    
-    # Initialize model pipelines (instead of re-using the same pipe in each iteration)
+
+    # Initialize model pipelines (already initialized outside)
     model_pipelines = [pipe0, pipe1, pipe2]
 
     # Run classification for each model
     results = {}
     for idx, pipe in enumerate(model_pipelines):  # Ensure each model pipeline is used separately
-        labels, preds, images = classify_images(extracted_dir, pipe)
+        print(f"Processing with model {idx}")
+        labels, preds, images = classify_images(extracted_dir, pipe, idx)  # Pass in model index for debugging
         accuracy, roc_score, report, cm_fig, roc_fig = evaluate_model(labels, preds)
-        
+
         # Store results for each model
         results[f'Model_{idx}_accuracy'] = accuracy
         results[f'Model_{idx}_roc_score'] = roc_score
@@ -232,6 +239,7 @@ def process_zip(zip_file):
             results['Model_2_cm_fig'], results['Model_2_roc_fig'])
 
 
+
 # Single image section
 def load_url(url):
     try: