image_label.py

# coding=UTF-8
# 使用MNIST数据集进行图像分类的神经网络模型

'''
File Name: image_label.py
Program IDE: PyCharm
Created Time: 2022/6/5 0005 21:27
Author: Wei Wei
'''

import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt

print(tf.__version__)

fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
# 图片像素值处于 0 到 255 之间，需将这些像素值归一化至 0 到 1 之间，然后将其馈送到神经网络模型
train_images = train_images / 255.0
test_images = test_images / 255.0
plt.figure(figsize=(10, 10))
for i in range(25):
    plt.subplot(5, 5, i + 1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(train_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i]])
plt.show()

# Step1: 构建模型层
model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),  # 在数据输入进全连接层时，要对数据进行铺平处理
    keras.layers.Dense(784, activation='relu'),  # 激活函数为整流线性单元 g(z) = max{0, z}, z = Wx + b
    keras.layers.Dropout(0.2),
    keras.layers.Dense(10)])

# Step2: 编译模型参数
# 损失函数loss - 用于测量模型在训练期间的准确率。
# 优化器 - 决定模型如何根据其看到的数据和自身的损失函数进行更新。
# 指标 - 用于监控训练和测试步骤。
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

# Step3: 训练模型
# epochs 迭代次数
# fit是“拟合”的意思，将模型与训练数据进行拟合
model.fit(train_images, train_labels, batch_size=32, epochs=30, verbose=1)

# Step4: 模型评估准确率
test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)
print('\nTest accuracy:', test_acc)

# Step5：模型预测
probability_model = tf.keras.Sequential([model, tf.keras.layers.Softmax()])
predictions = probability_model.predict(test_images)
np.argmax(predictions[0])


def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_label, img = predictions_array, true_label[i], img[i]
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])

    plt.imshow(img, cmap=plt.cm.binary)

    predicted_label = np.argmax(predictions_array)
    if predicted_label == true_label:
        color = 'blue'
    else:
        color = 'red'

    plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],
                                         100 * np.max(predictions_array),
                                         class_names[true_label]),
               color=color)


def plot_value_array(i, predictions_array, true_label):
    predictions_array, true_label = predictions_array, true_label[i]
    plt.grid(False)
    plt.xticks(range(10))
    plt.yticks([])
    thisplot = plt.bar(range(10), predictions_array, color="#777777")
    plt.ylim([0, 1])
    predicted_label = np.argmax(predictions_array)

    thisplot[predicted_label].set_color('red')
    thisplot[true_label].set_color('blue')


i = 0
plt.figure(figsize=(6, 3))
plt.subplot(1, 2, 1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(1, 2, 2)
plot_value_array(i, predictions[i], test_labels)
plt.show()

i = 12
plt.figure(figsize=(6, 3))
plt.subplot(1, 2, 1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(1, 2, 2)
plot_value_array(i, predictions[i], test_labels)
plt.show()

num_rows = 5
num_cols = 3
num_images = num_rows * num_cols
plt.figure(figsize=(2 * 2 * num_cols, 2 * num_rows))
for i in range(num_images):
    plt.subplot(num_rows, 2 * num_cols, 2 * i + 1)
    plot_image(i, predictions[i], test_labels, test_images)
    plt.subplot(num_rows, 2 * num_cols, 2 * i + 2)
    plot_value_array(i, predictions[i], test_labels)
plt.tight_layout()
plt.show()