Update app.py

app.py

@@ -11,7 +11,6 @@ def load_models():
     feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
     tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
     return model, feature_extractor, tokenizer
-model, feature_extractor, tokenizer = load_models()
 #st.text("Build with Streamlit and OpenCV")
 if "photo" not in st.session_state:
 	st.session_state["photo"]="not done"
@@ -27,6 +26,7 @@ camera_photo = c2.camera_input("Take a photo", on_change=change_photo_state)
 
 #st.subheader("Detection")
 if st.checkbox("Generate_Caption"):
+   model, feature_extractor, tokenizer = load_models()
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model.to(device)
    max_length = 16