Code Editor for app.py

import streamlit as st
import numpy as np
from PIL import Image
from tensorflow.keras.models import load_model

# Load your pre-trained model
model = load_model('your_model.h5')  # Make sure to put your model file in the same directory

st.title('Image Classifier')

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

if uploaded_file is not None:
    image = Image.open(uploaded_file)
    st.image(image, caption='Uploaded Image.', use_column_width=True)
    st.write('
')

    # Preprocess the image for classification
    image = image.resize((224, 224))  # Adjust size according to your model's input requirements
    image_array = np.array(image)/255.0  # Normalize the image
generated_image = np.expand_dims(image_array, axis=0)  # Add batch dimension
    
    # Predict the class
    predictions = model.predict(generated_image)
    predicted_class = np.argmax(predictions, axis=1)
    st.write(f'Predicted class: {predicted_class[0]}')