import streamlit as st
from transformers import ViTFeatureExtractor, ViTForImageClassification
from PIL import Image
import torch

# Load model and feature extractor
MODEL_NAME = "google/vit-base-patch16-224"
feature_extractor = ViTFeatureExtractor.from_pretrained(MODEL_NAME)
model = ViTForImageClassification.from_pretrained(MODEL_NAME)

# Streamlit UI
st.title("Animal Recognition App")
st.write("Upload an image, and the model will identify the animal.")

uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png", "jpeg"])

if uploaded_file is not None:
    image = Image.open(uploaded_file)
    st.image(image, caption="Uploaded Image", use_column_width=True)
    
    # Preprocess image
    inputs = feature_extractor(images=image, return_tensors="pt")
    
    # Predict
    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits
        predicted_class_idx = logits.argmax(-1).item()
    
    # Get label
    label = model.config.id2label[predicted_class_idx]
    st.success(f"Predicted Animal: **{label}**")