Update app.py

app.py

@@ -8,16 +8,14 @@ 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"
-feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 c2, c3 = st.columns([2,1])
 def change_photo_state():
 	st.session_state["photo"]="done"
-print("="*150)
-print("RESNET MODEL LOADED")
-
 @st.cache
 def load_image(img):
 	im = Image.open(img)
@@ -25,7 +23,6 @@ def load_image(img):
 activities = ["About"]
 choice = st.sidebar.selectbox("Select Activty",activities)
 uploaded_photo = c2.file_uploader("Upload Image",type=['jpg','png','jpeg'], on_change=change_photo_state)
-tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 camera_photo = c2.camera_input("Take a photo", on_change=change_photo_state)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
@@ -41,16 +38,17 @@ def predict_step(our_image):
    preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
    preds = [pred.strip() for pred in preds]
    return preds
-#st.subheader("Detection") 
-if st.session_state["photo"]=="done":
-   if uploaded_photo:
-      our_image= load_image(uploaded_photo)
-   elif camera_photo:
-      our_image= load_image(camera_photo)
-   elif uploaded_photo==None and camera_photo==None:
-      our_image= load_image('image.jpg')
-   st.success(predict_step(our_image))
-if choice == 'About':
+#st.subheader("Detection")
+if st.checkbox("Generate_Caption"):
+   if st.session_state["photo"]=="done":
+      if uploaded_photo:
+         our_image= load_image(uploaded_photo)
+      elif camera_photo:
+         our_image= load_image(camera_photo)
+      elif uploaded_photo==None and camera_photo==None:
+         our_image= load_image('image.jpg')
+      st.success(predict_step(our_image))
+elif choice == 'About':
    st.subheader("About Image Captioning App")
    st.markdown("Built with Streamlit by [Soumen Sarker](https://soumen-sarker-personal-website.streamlit.app/)")
    st.markdown("Demo applicaton of the following model [credit](https://huggingface.co/nlpconnect/vit-gpt2-image-captioning/)")