
print("Execution time to fit 200 epochs: %s seconds" % (end_time[6] - start_time[6]))

Execution time to fit 200 epochs: 22.997885704040527 seconds


fig, (ax1, ax2) = plt.subplots(1, 2, sharey=True, sharex=True, figsize=(16, 5))
nn_plot(hist[4], 200, subplot=ax1, loss=True, title="Reference: minibatch 10 samples / eta = 0.025")
nn_plot(hist[10], 200, subplot=ax2, loss=True, title="minibatch 32 samples / eta = 0.050")


fig, (ax1, ax2) = plt.subplots(1, 2, sharey=True, sharex=True, figsize=(16, 5))
nn_plot(hist[4], 200, subplot=ax1, acc=True, title="Reference: minibatch 10 samples / eta = 0.025")
nn_plot(hist[10], 200, subplot=ax2, acc=True, title="minibatch 32 samples / eta = 0.050")


model.append(tf.keras.models.Sequential([
    tf.keras.layers.Dense(30, kernel_regularizer=tf.keras.regularizers.l2(0.01),
                          activation=tf.nn.sigmoid, input_shape=(784,), name='hidden_1_layer'),
    tf.keras.layers.Dense(10, activation='softmax', name='output_layer')
]))

params.append([tf.keras.losses.SparseCategoricalCrossentropy(),
               tf.optimizers.SGD(learning_rate=0.100),
               tf.keras.metrics.SparseCategoricalAccuracy()])

nn_compile(model[-1], params[-1])

Minibatch: 64 samples / higher learning rate¶