Update app.py

app.py

@@ -1,9 +1,13 @@
 import os
 import gradio as gr
 
+from transformers import ViTFeatureExtractor
+feature_extractor = ViTFeatureExtractor()
+# or, to load one that corresponds to a checkpoint on the hub:
+feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
 
-from transformers import VisionEncoderDecoderModel
 
+from transformers import VisionEncoderDecoderModel
 # initialize a vit-bert from a pretrained ViT and a pretrained BERT model. Note that the cross-attention layers will be randomly initialized
 model = VisionEncoderDecoderModel.from_encoder_decoder_pretrained(
     "google/vit-base-patch16-224-in21k", "bert-base-uncased"