Update app.py

app.py

@@ -9,9 +9,9 @@ from PIL import Image
 device = 'cpu'
 
 # Load the pretrained model, feature extractor, and tokenizer
-model = VisionEncoderDecoderModel.from_pretrained("NourFakih/Vit-GPT2-COCO2017Flickr-01").to(device)
-feature_extractor = ViTImageProcessor.from_pretrained("NourFakih/Vit-GPT2-COCO2017Flickr-01")
-tokenizer = AutoTokenizer.from_pretrained("NourFakih/Vit-GPT2-COCO2017Flickr-01")
+model = VisionEncoderDecoderModel.from_pretrained("NourFakih/Vit-GPT2-COCO2017Flickr-02").to(device)
+feature_extractor = ViTImageProcessor.from_pretrained("NourFakih/Vit-GPT2-COCO2017Flickr-02")
+tokenizer = AutoTokenizer.from_pretrained("NourFakih/Vit-GPT2-COCO2017Flickr-02")
 
 def predict(image, max_length=64, num_beams=4):
     # Process the input image
@@ -36,7 +36,7 @@ def process_images(image_files):
         except Exception as e:
             print(f"Skipping file {image_file}: {e}")
     
-    return captions
+    return csv_file_path = save_captions_to_csv(captions, csv_file_path='image_captions.csv')
 
 def process_zip_files(zip_file_paths):
     # Create a directory to extract images
@@ -60,7 +60,7 @@ def process_zip_files(zip_file_paths):
                 except Exception as e:
                     print(f"Skipping file {file}: {e}")
     
-    return captions
+    return csv_file_path = save_captions_to_csv(captions, csv_file_path='zip_captions.csv')
 
 def save_captions_to_csv(captions, csv_file_path='image_captions.csv'):
     with open(csv_file_path, mode='w', newline='') as file: