A very simple classifier for the fashion mnist dataset

fashion-mnist-clf

# Importing the packages
import tensorflow as tf

# Downloading data
# The default split is 60k images in the training set and 10k in the test set
mnist = tf.keras.datasets.fashion_mnist
(training_images, training_labels), (test_images, test_labels) = mnist.load_data()

# Normalizing the pixel values
training_images  = training_images / 255.0
test_images = test_images / 255.0

# Defining a basic NN 
model = tf.keras.models.Sequential(
    [
        tf.keras.layers.Flatten(), 
        tf.keras.layers.Dense(256, activation=tf.nn.relu), 
        tf.keras.layers.Dense(10, activation=tf.nn.softmax)
    ]
)

# Compiliing and fitting
model.compile(
    optimizer = tf.optimizers.Adam(),
    loss = 'sparse_categorical_crossentropy',
    metrics=['accuracy']
)

model.fit(training_images, training_labels, epochs=5)

# Printing the accuracy
print(model.evaluate(test_images, test_labels, verbose=False)[1])