app.py

import streamlit as st
import tensorflow as tf
from keras.preprocessing.image import ImageDataGenerator
from keras.preprocessing import image
import numpy as np

# Check TensorFlow version
st.write("TensorFlow version: ", tf.__version__)

# Sidebar for file upload
st.sidebar.title("Upload Image")
uploaded_file = st.sidebar.file_uploader("Choose an image...", type=["jpg", "jpeg"])

if uploaded_file is not None:
    # Display the uploaded image
    st.image(uploaded_file, caption='Uploaded Image.', use_column_width=True)
    st.write("")

    # Data preprocessing
    train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True
    )

    # Load the pre-trained model
    cnn = tf.keras.models.Sequential([
        tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu', input_shape=[64, 64, 3]),
        tf.keras.layers.MaxPool2D(pool_size=2, strides=2),
        tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu'),
        tf.keras.layers.MaxPool2D(pool_size=2, strides=2),
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(units=128, activation='relu'),
        tf.keras.layers.Dense(units=1, activation='sigmoid')
    ])

    # Compile the model
    cnn.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

    # Load the trained weights
    cnn.load_weights('cat_dog_classifier_weights.h5')

    # Make prediction
    test_image = image.load_img(uploaded_file, target_size=(64, 64))
    test_image = image.img_to_array(test_image)
    test_image = np.expand_dims(test_image, axis=0)
    result = cnn.predict(test_image)

    # Class indices
    class_indices = {0: 'cat', 1: 'dog'}

    # Predict
    prediction = 'dog' if result[0][0] == 1 else 'cat'
    st.write("Prediction:", prediction)