DNN 网络-带注释

DNN 网络

import tensorflow as tf
import numpy as np
import os
from matplotlib import pyplot as plt

np.set_printoptions(threshold=np.inf) # 显示numpy所有数据

mnist = tf.keras.datasets.mnist 
(x_train, y_train), (x_test, y_test) = mnist.load_data()  # 下载数据集
x_train = x_train/255.0  # 归一化
x_test = x_test/255.0    # 归一化

# 定义模型
model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])
# 编译
model.compile(optimizer='adam', loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False), metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = './checkpoints/mnist.ckpt'
if os.path.exists(checkpoint_save_path + '.index'):
    print('----------------------------load the model----------------------------')
    model.load_weights(checkpoint_save_path)
# 回调函数Callbacks 断点ModelCheckpoint
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path, save_weights_only=True, save_best_only=True)
#训练
history = model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1, callbacks=[cp_callback])

model.summary()

print(model.trainable_variables)
# 保存权重
file = open('./weight.txt', 'w')
for v in model.trainable_variables:
    file.write(str(v.name) + '\n')
    file.write(str(v.shape) + '\n')
    file.write(str(v.numpy()) + '\n')
file.close()

# 显示训练集和验证集的acc和loss曲线
acc = history.history['sparse_categorical_accuracy']
val_acc = history.history['val_sparse_categorical_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

plt.subplot(1, 2, 1)
plt.plot(acc, label = 'Training Accuracy')
plt.plot(val_acc, label = 'Validation Accuracy')
plt.title('Training and Validation Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label = 'Training loss')
plt.plot(val_loss, label = 'Validation loss')
plt.title('Training and Validation loss')
plt.legend()
plt.show()