Trying Salesforce image classification

app.py

@@ -1,7 +1,19 @@
 import streamlit as st
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
 
 enable = st.checkbox("Enable camera")
 picture = st.camera_input("Take a picture", disabled=not enable)
 
 if picture:
-    st.image(picture)
+	raw_image = Image.open(picture)
+
+	# conditional image captioning
+	text = "A view of a person in"
+	inputs = processor(raw_image, text, return_tensors="pt")
+
+	out = model.generate(**inputs)
+	st.write(processor.decode(out[0], skip_special_tokens=True))