test image.py import on app.py

app.py

@@ -1,4 +1,7 @@
 import streamlit as st
 
+import os
 x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+st.write(x, 'squared is', x * x)
+
+os.system("python image.py")

image.py

@@ -0,0 +1,20 @@
+from transformers import ViltProcessor, ViltForQuestionAnswering
+import requests
+from PIL import Image
+
+# prepare image + question
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+text = "How many cats are there?"
+
+processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+
+# prepare inputs
+encoding = processor(image, text, return_tensors="pt")
+
+# forward pass
+outputs = model(**encoding)
+logits = outputs.logits
+idx = logits.argmax(-1).item()
+print("Predicted answer:", model.config.id2label[idx])