mnist学习实例(1)

环境: Ubuntu 18.04, tensorflow 2.4.1

mnist是Yann Lecun大神的手写数据,数据中的数字都是28X28的图像,每个像素点是[0-255]的值

其中训练数据为60000,测试数据为10000

打印出数字看一下

def show_mnist(images, labels):
    n = 5
    m = 5
    for i in range(n):
        for j in range(m):
            plt.subplot(n, m, i*n+j+1)
            index = i*n+j
            array = images[index]
            plt.title(labels[index])
            plt.imshow(array, cmap='Greys')
    plt.show()

准备数据

因为数据是三维的, (60000,28,28),但是我们构建的网络是

# 200 个 epoch
EPOCH = 200
BATCH_SIZE = 128
VERBOSE = 1
# 需要把图像二位数据压缩为一维数据
RESHAPED = 784 # 28*28
# 数字分类类别  0~9 一共10个
NUM_CLASSES = 10

# 载入数据,第一次使用时,会稍微花点时间下载
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

# 将图像二维数据压缩为一维,同时将数据转为浮点型
x_train = x_train.reshape(60000, RESHAPED).astype('float32')
x_test = x_test.reshape(10000, RESHAPED).astype('float32')

# normalization
# 如果数据不做归一化,其实训练也可以进行,但是会影响最终的loss
x_train /= 255
x_test /= 255

# 将label的数字 0~9 转为hothot
y_train = tf.keras.utils.to_categorical(y_train, NUM_CLASSES)
y_test = tf.keras.utils.to_categorical(y_test, NUM_CLASSES)

构建网络

使用最简单的一层网络

model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(NUM_CLASSES, input_shape=(RESHAPED,), activation='softmax'))
model.summary()

训练

## compile network
model.compile(loss=tf.keras.losses.categorical_crossentropy, optimizer='adam', metrics=['accuracy'])
history = model.fit(x_train, y_train, batch_size=BATCH_SIZE, epochs=EPOCH, verbose=VERBOSE)

## validation  92.36
val_loss,val_acc = model.evaluate(x_test, y_test, verbose=VERBOSE)
print("Test loss: ", val_loss)
print("Test accuracy: ", val_acc)

完成代码

import tensorflow as tf
import matplotlib.pyplot as plt
# from PIL import Image

EPOCH = 200
BATCH_SIZE = 128
VERBOSE = 1
RESHAPED = 784 # 28*28
NUM_CLASSES = 10

def show_mnist(images, labels):
    n = 5
    m = 5
    for i in range(n):
        for j in range(m):
            plt.subplot(n, m, i*n+j+1)
            index = i*n+j
            array = images[index]
            plt.title(labels[index])
            plt.imshow(array, cmap='Greys')
    plt.show()

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

print('training images data shape:', x_train.shape)
print('training labels data shape:', y_train.shape)
print('testing images data shape:', x_test.shape)
print('testing labels data shape:', y_test.shape)

#show_mnist(x_train, y_train)


x_train = x_train.reshape(60000, RESHAPED).astype('float32')
x_test = x_test.reshape(10000, RESHAPED).astype('float32')

# normalization
x_train /= 255
x_test /= 255

#
y_train = tf.keras.utils.to_categorical(y_train, NUM_CLASSES)
y_test = tf.keras.utils.to_categorical(y_test, NUM_CLASSES)

# train_labels = train_labels.reshape(60000, RESHAPED)

## build network
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(NUM_CLASSES, input_shape=(RESHAPED,), activation='softmax'))
model.summary()

## compile network
model.compile(loss=tf.keras.losses.categorical_crossentropy, optimizer='adam', metrics=['accuracy'])
history = model.fit(x_train, y_train, batch_size=BATCH_SIZE, epochs=EPOCH, verbose=VERBOSE)

## validation  92.36
val_loss,val_acc = model.evaluate(x_test, y_test, verbose=VERBOSE)
print("Test loss: ", val_loss)
print("Test accuracy: ", val_acc)

训练结果