cifar_model_on_images.py

# Normalizing the images
x_train_normalized, x_test_normalized = x_train/255.0, x_test/255.0
EPOCHS = 2

model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(filters=32,kernel_size=(3,3),activation='relu',input_shape=(32,32,3)),
    tf.keras.layers.MaxPooling2D((2,2)),
    tf.keras.layers.Conv2D(filters=64,kernel_size=(3,3),activation='relu'),
    tf.keras.layers.MaxPooling2D((2,2)),
    tf.keras.layers.Conv2D(filters=64,kernel_size=(3,3),activation='relu'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(64,activation='relu'),
    tf.keras.layers.Dense(10)
])

model.compile(
    optimizer='adam',
    loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    metrics=['accuracy']
)

# training directly on images creates batches of 32
history_images = model.fit(
    x_train_normalized,
    y_train,
    validation_data=(x_test_normalized,y_test),
    epochs=EPOCHS
)