In [1]:

    

import tensorflow as tf


    

In [2]:

    

mnist = tf.keras.datasets.mnist


    

In [8]:

    

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 25.0


    

In [9]:

    

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28)),
    tf.keras.layers.Dense(512, activation=tf.nn.relu),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])


    

In [10]:

    

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


    

In [13]:

    

model.fit(x_train, y_train, epochs = 5)


    

    




Epoch 1/5
60000/60000 [==============================] - 6s 100us/step - loss: 0.2181 - acc: 0.9355
Epoch 2/5
60000/60000 [==============================] - 6s 94us/step - loss: 0.0964 - acc: 0.9705
Epoch 3/5
60000/60000 [==============================] - 6s 95us/step - loss: 0.0697 - acc: 0.9785
Epoch 4/5
60000/60000 [==============================] - 6s 101us/step - loss: 0.0543 - acc: 0.9825
Epoch 5/5
60000/60000 [==============================] - 6s 105us/step - loss: 0.0425 - acc: 0.9861






    
Out[13]:





<tensorflow.python.keras.callbacks.History at 0x12843ec10>

In [14]:

    

model.evaluate(x_test, y_test)


    

    




10000/10000 [==============================] - 0s 33us/step






    
Out[14]:





[0.24156368299915448, 0.9806]

In [ ]: