Tensorflow2.0笔记25——断点续训，存取模型

Tensorflow2.0笔记

本博客为Tensorflow2.0学习笔记，感谢北京大学微电子学院曹建老师

目录

• Tensorflow2.0笔记
  • • 2.3 断点续训，存取模型
      • 1.读取数据
      • 2.保存模型

2.3 断点续训，存取模型

1.读取数据

checkpoint_save_path = "./checkpoint/mnist.ckpt"
if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)

2.保存模型

借助 tensorflow 给出的回调函数，直接保存参数和网络

tf.keras.callbacks.ModelCheckpoint(

​ filepath= 路 径 文 件 名 , save_weights_only=True, monitor='val_loss', # val_loss or loss save_best_only=True)

history = model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1, callbacks=[cp_callback])

注：monitor 配合 save_best_only 可以保存最优模型，包括：训练损失最小模型、测试损失最小模型、训练准确率最高模型、测试准确率最高模型等。

代码：

import tensorflow as tf
import os

mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = "./checkpoint/mnist.ckpt"
if os.path.exists(checkpoint_save_path + '.index'):
    print('-------------load the model-----------------')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_save_path,
                                                 save_weights_only=True,
                                                 save_best_only=True)

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()