Python深度学习入门之mnist-VGG（Tensorflow2.0实现）

mnist手写数字数据集深度学习最常用的数据集，本文以mnist数据集为例，利用Tensorflow2.0框架搭建VGG网络，实现mnist数据集识别任务，并画出各个曲线。

Demo完整代码如下：

import tensorflow as tf
from tensorflow.keras import layers
import numpy as np

#加载mnist数据集
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
#预处理
x_train, x_test = x_train.astype(np.float32)/255., x_test.astype(np.float32)/255.
x_train, x_test = np.expand_dims(x_train, axis=3), np.expand_dims(x_test, axis=3)
# 创建训练集50000、验证集10000以及测试集10000
x_val = x_train[-10000:]
y_val = y_train[-10000:]
x_train = x_train[:-10000]
y_train = y_train[:-10000]
#标签转为one-hot格式
y_train = tf.one_hot(y_train, depth=10).numpy()
y_val = tf.one_hot(y_val, depth=10).numpy()
y_test = tf.one_hot(y_test, depth=10).numpy()

# tf.data.Dataset 批处理
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(100).repeat()

val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val)).batch(100).repeat()

test_dataset = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(100).repeat()

from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics,regularizers
from tensorflow import keras

input_shape = (28, 28, 1)
weight_decay = 0.001
num_classes = 10

model = tf.keras.Sequential()

model.add(layers.Conv2D(64, (3, 3), padding='same',
                 input_shape=input_shape, kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.3))

model.add(layers.Conv2D(64, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())

model.add(layers.MaxPooling2D(pool_size=(2, 2)))

model.add(layers.Conv2D(128, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))

model.add(layers.Conv2D(128, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())

model.add(layers.MaxPooling2D(pool_size=(2, 2)))

model.add(layers.Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))

model.add(layers.Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))

model.add(layers.Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())

model.add(layers.MaxPooling2D(pool_size=(2, 2)))


# model.add(layers.Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
# model.add(layers.Activation('relu'))
# model.add(layers.BatchNormalization())
# model.add(layers.Dropout(0.4))

# model.add(layers.Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
# model.add(layers.Activation('relu'))
# model.add(layers.BatchNormalization())
# model.add(layers.Dropout(0.4))

# model.add(layers.Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
# model.add(layers.Activation('relu'))
# model.add(layers.BatchNormalization())

# model.add(layers.MaxPooling2D(pool_size=(2, 2)))


# model.add(layers.Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
# model.add(layers.Activation('relu'))
# model.add(layers.BatchNormalization())
# model.add(layers.Dropout(0.4))

# model.add(layers.Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
# model.add(layers.Activation('relu'))
# model.add(layers.BatchNormalization())
# model.add(layers.Dropout(0.4))

# model.add(layers.Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
# model.add(layers.Activation('relu'))
# model.add(layers.BatchNormalization())

# model.add(layers.MaxPooling2D(pool_size=(2, 2)))
# model.add(layers.Dropout(0.5))

model.add(layers.Flatten())
model.add(layers.Dense(512,kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())

model.add(layers.Dropout(0.5))
model.add(layers.Dense(num_classes, activation='softmax'))   

#设置网络优化方法、损失函数、评价指标
model.compile(optimizer=tf.keras.optimizers.Adam(0.001),
             loss=tf.keras.losses.CategoricalCrossentropy(),
             metrics = ['acc']
             )
#开始训练
history_VGG16 = model.fit(train_dataset, epochs=100, steps_per_epoch=20, validation_data=val_dataset, validation_steps=3)

#在测试集上评估并保存权重文件
model.evaluate(test_dataset, steps=100)
model.save_weights('save_model/VGG_minst/VGG_mnist_weights.ckpt')

网络参数

测试集评估结果

绘制曲线代码

import matplotlib.pyplot as plt

#输入两个曲线的信息
plt.figure( figsize=(12,8), dpi=80 )
plt.plot(history_VGG16.epoch, history_VGG16.history.get('loss'), color='r', label = 'loss')
plt.plot(history_VGG16.epoch, history_VGG16.history.get('acc'), color='g', linestyle='-.', label = 'acc')
plt.plot(history_VGG16.epoch, history_VGG16.history.get('val_acc'), color='b', linestyle='--', label = 'val_acc')

#显示图例
plt.legend() #默认loc=Best

#添加网格信息
plt.grid(True, linestyle='--', alpha=0.5) #默认是True，风格设置为虚线，alpha为透明度

#添加标题
plt.xlabel('epochs')
plt.ylabel('loss/acc')
plt.title('VGG16_Curve of loss/acc Change with epochs in Mnist')

plt.savefig('./save_png/VGG16_mnist.png')

plt.show()

曲线图

最后

以上就是善良蜗牛为你收集整理的Python深度学习入门之mnist-VGG（Tensorflow2.0实现）的全部内容，希望文章能够帮你解决Python深度学习入门之mnist-VGG（Tensorflow2.0实现）所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。