Update app.py

app.py

@@ -72,7 +72,6 @@ def process_file(input_file):
         img.save(os.path.join(input_folder, f'image_{i}.jpg'))
 
     return images
-
 def run_detection_and_ocr():
     # Load models
     ocr_model = Model.load('hezarai/crnn-fa-printed-96-long')
@@ -81,29 +80,33 @@ def run_detection_and_ocr():
     input_folder = 'output_images'
     yolo_model.predict(input_folder, save=True, imgsz=320, conf=0.5, save_crop=True)
     
-    output_folder = '/runs/detect/predict'
+    output_folder = 'runs/detect/predict'  # Remove leading slash if needed
+    crop_folder = os.path.join(output_folder, 'crops')
+    
     results = []
     
     for filename in os.listdir(input_folder):
         if filename.endswith('.JPEG') or filename.endswith('.jpg'):
             image_path = os.path.join(input_folder, filename)
-            crop_folder = os.path.join(output_folder, 'crops')
-            crops = []
-            for crop_label in os.listdir(crop_folder):
-                crop_label_folder = os.path.join(crop_folder, crop_label)
-                if os.path.isdir(crop_label_folder):
-                    for crop_filename in os.listdir(crop_label_folder):
-                        crop_image_path = os.path.join(crop_label_folder, crop_filename)
-                        text_prediction = predict_text(ocr_model, crop_image_path)
-                        crops.append({
-                            'crop_image_path': crop_image_path,
-                            'text_prediction': text_prediction,
-                            'class_label': crop_label
-                        })
-            results.append({
-                'image': filename,
-                'crops': crops
-            })
+            
+            # Check if crop_folder exists
+            if os.path.exists(crop_folder):
+                crops = []
+                for crop_label in os.listdir(crop_folder):
+                    crop_label_folder = os.path.join(crop_folder, crop_label)
+                    if os.path.isdir(crop_label_folder):
+                        for crop_filename in os.listdir(crop_label_folder):
+                            crop_image_path = os.path.join(crop_label_folder, crop_filename)
+                            text_prediction = predict_text(ocr_model, crop_image_path)
+                            crops.append({
+                                'crop_image_path': crop_image_path,
+                                'text_prediction': text_prediction,
+                                'class_label': crop_label
+                            })
+                results.append({
+                    'image': filename,
+                    'crops': crops
+                })
 
     output_json_path = 'output.json'
     with open(output_json_path, 'w', encoding='utf-8') as f: