Update app.py

app.py

@@ -99,7 +99,7 @@ model.to(device)
 
 # Tokenizer and Feature Extractor
 tokenizer = T5Tokenizer.from_pretrained('t5-base')
-feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
+feature_extractor = ViTImageProcessor.from_pretrained('google/vit-base-patch16-224-in21k')
 
 # Define the image preprocessing
 transform = transforms.Compose([
@@ -140,7 +140,7 @@ sample_images = [
 # Define Gradio interface
 interface = gr.Interface(
     fn=generate_caption,
-    inputs=gr.inputs.Image(source="upload", tool='editor', type="numpy", label="Upload an image or take a photo"),
+    inputs=gr.Image(source="upload", tool='editor', type="numpy", label="Upload an image or take a photo"),
     outputs='text',
     examples=sample_images,
     title="Image Captioning Model",