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

# Disable scientific notation for clarity
np.set_printoptions(suppress=True)

# Load the model
model = load_model("keras_model.h5", compile=False)

# Load the labels
class_names = open("labels.txt", "r").readlines()
class_names = [name.strip() for name in class_names]  # Strip newline characters

# Function to preprocess the image
def preprocess_image(image):
    # resizing the image to be at least 224x224 and then cropping from the center
    size = (224, 224)
    image = ImageOps.fit(image, size, Image.Resampling.LANCZOS)

    # turn the image into a numpy array
    image_array = np.asarray(image)

    # Normalize the image
    normalized_image_array = (image_array.astype(np.float32) / 127.5) - 1

    # Create array of the right shape to feed into the model
    data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32)
    data[0] = normalized_image_array

    return data

# Streamlit app
def main():
    st.title("Image Classifier")

    uploaded_file = st.file_uploader("Choose 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)

        data = preprocess_image(image)
        prediction = model.predict(data)
        index = np.argmax(prediction)
        class_name = class_names[index]
        confidence_score = prediction[0][index]

        st.write("Class:", class_name)
        st.write("Confidence Score:", confidence_score)

if __name__ == "__main__":
    main()