第一步要先將資料型態從 12828 轉換成 1*784:
轉換是為了配合全連接神經網路（FCN）輸入層的要求，並進行影像正規化，全部除以255。

x_Train=x_train_image.reshape(60000,784).astype('float32')
x_Test=x_test_image.reshape(10000,784).astype('float32')
x_Train_normalize=x_Train/255
x_Test_normalize=x_Test/255

y_TrainOneHot=np_utils.to_categorical(y_train_label)
y_TestOneHot=np_utils.to_categorical(y_test_label)

第二步建立多元感知模型:

from keras.models import Sequential
from keras.layers import Dense
model = Sequential()
model.add(Dense(units=256,input_dim=784,kernel_initializer='normal',activation='relu'))
model.add(Dense(units=10,kernel_initializer='normal',activation='softmax'))
print(model.summary())

以上是輸出結果，可以看出這是一個兩層的模型，隱藏層有256個神經元，輸出層有10個神經元。
另外是 param 參數，關於計算方式第一個是 200960=256784+256，另外一個是2570=25610+10=2570。
下面則是全部訓練 total params=200960+2570=203530。

第三步就開始訓練了:

model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
train_history=model.fit(x=x_Train_normalize,y=y_TrainOneHot,
            validation_split=0.2,epochs=10,batch_size=200,verbose=2)

第四步將訓練過程繪製成圖輸出:

def show_train_history(train_history, metric, val_metric):
    plt.plot(train_history.history[metric])
    plt.plot(train_history.history[val_metric])
    plt.title('Train History')
    plt.ylabel(metric)
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Validation'], loc='upper left')
    plt.show()
show_train_history(train_history, 'accuracy', 'val_accuracy')
show_train_history(train_history, 'loss', 'val_loss')

最後附上完整連接再一起的程式碼:

import numpy as np
import tensorflow as tf
from tensorflow.keras import layers, models
from tensorflow.keras.datasets import mnist
import matplotlib.pyplot as plt

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.astype('float32') / 255.0
x_test = x_test.astype('float32') / 255.0
x_train = x_train.reshape(-1, 28 * 28)
x_test = x_test.reshape(-1, 28 * 28)
y_train_one_hot = tf.keras.utils.to_categorical(y_train, num_classes=10)
y_test_one_hot = tf.keras.utils.to_categorical(y_test, num_classes=10)

model = models.Sequential([
    layers.Dense(128, activation='relu', input_shape=(784,)),
    layers.Dropout(0.2),
    layers.Dense(64, activation='relu'),
    layers.Dense(10, activation='softmax')
])
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

train_history = model.fit(x=x_train, y=y_train_one_hot, validation_split=0.2, epochs=10, batch_size=200, verbose=2)

def show_train_history(train_history, metric, val_metric):
    plt.plot(train_history.history[metric])
    plt.plot(train_history.history[val_metric])
    plt.title('Train History')
    plt.ylabel(metric)
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Validation'], loc='upper left')
    plt.show()
show_train_history(train_history, 'accuracy', 'val_accuracy')
show_train_history(train_history, 'loss', 'val_loss')