import tensorflow as tf

from tensorflow.keras.preprocessing.image import ImageDataGenerator

​

train_datagen = ImageDataGenerator(

    rescale=1./255,

    shear_range=0.2,

    zoom_range=0.2,

    horizontal_flip=True

)

​

train_generator = train_datagen.flow_from_directory(

    'your training_dataset path',

    target_size=(128, 128),

    batch_size=32,

    class_mode='binary'

)

​

test_datagen = ImageDataGenerator(rescale=1./255)

​

validation_generator = test_datagen.flow_from_directory(

    'your test_dataset path',

    target_size=(128, 128),

    batch_size=32,

    class_mode='binary'

)

​

cnn_model = tf.keras.models.Sequential()

​

# Convolution layer

cnn_model.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu', input_shape=[128, 128, 3]))

​

# Pooling

cnn_model.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2))

​

# Adding another layer

cnn_model.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, activation='relu'))

cnn_model.add(tf.keras.layers.MaxPool2D(pool_size=2, strides=2))

​

# Flatten

cnn_model.add(tf.keras.layers.Flatten())

​

# Fully connected layer

cnn_model.add(tf.keras.layers.Dense(units=128, activation='relu'))

​

# Output layer

cnn_model.add(tf.keras.layers.Dense(units=1, activation='softmax'))

​

cnn_model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

​

# Training the model

cnn_model.fit(x=train_generator, validation_data=validation_generator, epochs=8)