Update app.py

app.py

@@ -7,6 +7,9 @@ from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTok
 print("="*150)
 print("MODEL LOADED")
 st.title("img_captioning_app")
+model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 #st.text("Build with Streamlit and OpenCV")
 if "photo" not in st.session_state:
 	st.session_state["photo"]="not done"
@@ -28,9 +31,6 @@ camera_photo = c2.camera_input("Take a photo", on_change=change_photo_state)
 if choice == 'Caption':
     #st.subheader("Detection") 
     if st.session_state["photo"]=="done":
-        model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
-        feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
-        tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
         if uploaded_photo:
             our_image= load_image(uploaded_photo)
         elif camera_photo: