[Python] model optimization and super parameter selection

Tensorflow Realize model optimization and super parameter selection

import tensorflow as tf
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# Model optimization and super parameter selection 
(train_image, train_label), (test_image, test_label) = tf.keras.datasets.fashion_mnist.load_data()
train_label_onehot = tf.keras.utils.to_categorical(train_label)
test_label_onehot = tf.keras.utils.to_categorical(test_label)
model = tf.keras.Sequential()
model.add(tf.keras.layers.Flatten(input_shape=(28, 28)))
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001), loss='categorical_crossentropy', metrics=['acc'])
model.fit(train_image, train_label_onehot, epochs=20)