image captioning

app.py

@@ -2,19 +2,41 @@ import streamlit as st
 from transformers import pipeline
 from PIL import Image
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+@st.cache_resourse
+def get_model_hotdog_classification_pipeline()
+	pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+	return pipeline
 
-st.title("Hot Dog? Or Not?")
+@st.cache_resourse
+def get_model_image_captioning_pipeline()
+    captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+    return captioner
 
-file_name = st.file_uploader("Upload a hot dog candidate image")
+tabs1,tabs2 = st.tabs(['Hot Dog? Or Not?','Imaage Captioning'])
+with tabs1:
+    st.title("Hot Dog? Or Not?")
 
-if file_name is not None:
-    col1, col2 = st.columns(2)
+    file_name = st.file_uploader("Upload a hot dog candidate image",key="hotdog_image")
 
-    image = Image.open(file_name)
-    col1.image(image, use_column_width=True)
-    predictions = pipeline(image)
+    if file_name is not None:
+        col1, col2 = st.columns(2)
 
-    col2.header("Probabilities")
-    for p in predictions:
-        col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
+        image = Image.open(file_name)
+        col1.image(image, use_column_width=True)
+        pipeline = get_model_hotdog_classification_pipeline()
+        predictions = pipeline(image)
+
+        col2.header("Probabilities")
+        for p in predictions:
+            col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
+
+with tabs2:
+    st.title("Image Captioning")
+
+    file_name = st.file_uploader("Upload an image to caption",key="caption_image")
+
+    if file_name is not None:
+        image = Image.open(file_name)
+        st.image(image, use_column_width=True)
+        captioner = get_model_image_captioning_pipeline()
+        st.write(f"generated_text: \n{captioner(image)}")