create app.py

app.py

@@ -0,0 +1,31 @@
+import streamlit as st
+from transformers import pipeline
+from PIL import Image
+
+st.set_page_config(page_title="ViT Image Classifier")
+
+st.title("ViT Image Classification")
+
+@st.cache_resource
+def load_model():
+    return pipeline("image-classification", model="google/vit-base-patch16-224")
+
+pipe = load_model()
+
+uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    image = Image.open(uploaded_file).convert("RGB")
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    with st.spinner("Classifying..."):
+        preds = pipe(image)
+
+    st.subheader("Predictions")
+    for i, pred in enumerate(preds):
+        st.write(f"{i+1}. {pred['label']} ({pred['score']:.3f})")
+
+# This is optional but sometimes helps initialization on some platforms
+if __name__ == "__main__":
+    import streamlit.web.bootstrap
+    streamlit.web.bootstrap.run()