TensorFlow-2.x-04-多分類邏輯迴歸的簡潔實現

        本文不做多餘解釋，主要是銜接上一章TensorFlow-2.x-03-從0開始的多分類邏輯迴歸內容，使用TF-2.x來快速實現多分類邏輯迴歸。

1、獲取/讀取數據集，歸一化數據

(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
print(x_train.shape,y_train.shape)

2、定義及初始化模型

def net():
    net=tf.keras.Sequential()
    net.add(tf.keras.layers.Flatten(input_shape=(28,28)))
    net.add(tf.keras.layers.Dense(10,activation=tf.nn.softmax)) #輸出10個神經元，softmax用於分類
    return net

3、定義優化器

optimizer = tf.keras.optimizers.SGD(0.1)

4、模型訓練

model.compile(optimizer=optimizer,
              loss = 'sparse_categorical_crossentropy', #交叉熵損失
              metrics=['accuracy']) # 準確率

model.fit(x_train,y_train,epochs=5,batch_size=256)

訓練結果：

#5、模型驗證

test_loss, test_acc = model.evaluate(x_test, y_test)
print('Test Acc:',test_acc)

驗證結果：

附上所有源碼：

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
from tensorflow import data as tfdata
from tensorflow.keras.datasets import fashion_mnist

# 1、獲取和讀取數據
(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
x_train = x_train / 255.0
x_test = x_test / 255.0
print(x_train.shape,y_train.shape)


#2、定義及初始化模型
def net():
    net=tf.keras.Sequential()
    net.add(tf.keras.layers.Flatten(input_shape=(28,28)))
    net.add(tf.keras.layers.Dense(10,activation=tf.nn.softmax)) #輸出10個神經元，softmax用於分類
    return net

model=net()
model.summary()

#3、定義優化器
optimizer = tf.keras.optimizers.SGD(0.1)

# 4、模型訓練
model.compile(optimizer=optimizer,
              loss = 'sparse_categorical_crossentropy', #交叉熵損失
              metrics=['accuracy']) # 準確率

model.fit(x_train,y_train,epochs=5,batch_size=256)

# 5、模型驗證
test_loss, test_acc = model.evaluate(x_test, y_test)
print('Test Acc:',test_acc)