Update app.py

app.py

@@ -2,9 +2,6 @@ import streamlit as st
 import torch
 from PIL import Image
 from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
-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")
 #pickle.load(open('energy_model.pkl', 'rb'))
 #vocab = np.load('w2i.p', allow_pickle=True)
 print("="*150)
@@ -31,6 +28,9 @@ 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: