Create app.py

app.py

@@ -0,0 +1,38 @@
+import streamlit as st
+from transformers import AutoModelForCausalLM, AutoProcessor
+from PIL import Image
+import torch
+
+# Load the model and processor
+@st.cache_resource
+def load_model():
+    st.text("Loading model...")
+    processor = AutoProcessor.from_pretrained("vikhyatk/moondream2", trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(
+        "vikhyatk/moondream2",
+        revision="2025-03-27",
+        trust_remote_code=True,
+        # device_map="auto"  # Enable if running on GPU
+    )
+    st.text("Model loaded successfully!")
+    return model, processor
+
+model, processor = load_model()
+
+# File uploader
+uploaded_file = st.file_uploader("Upload an image of a dish", type=["jpg", "jpeg", "png"])
+
+if uploaded_file:
+    image = Image.open(uploaded_file).convert("RGB")
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    # Auto-ask the food question
+    question = "What food is in this image?"  # or try: "What is the name of the dish?"
+
+    if st.button("Classify Dish"):
+        inputs = processor(image, question, return_tensors="pt").to(model.device)
+        with torch.no_grad():
+            output = model.generate(**inputs, max_new_tokens=64)
+        answer = processor.batch_decode(output, skip_special_tokens=True)[0].strip()
+
+        st.success(f"🍽️ Predicted Dish: **{answer}**")