Update app.py

app.py

@@ -5,10 +5,10 @@ from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecode
 
     
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
 encoder_checkpoint = 'google/vit-base-patch16-224'
 decoder_checkpoint = 'sachin/vit2distilgpt2'
 model_checkpoint = 'nlpconnect/vit-gpt2-image-captioning'
+model.to(device)
 feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
 tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
 model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)