TensorFlow2学习九之存取模型

断点续训可以存取模型

读取模型

读取模型可以直接使用TensorFlow的load_weights(路径文件名)函数

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

保存模型

保存模型参数可以使用TensorFlow给出的回调函数tf.keras.callbacks.ModelCheckpoint()直接保存训练出来的模型参数。

tf.keras.callbacks.ModelCheckpoint(
	filepath=路径文件名,              # 文件存储路径
	save_weights_only=True/False,    # 是否只保留模型参数
	save_best_only=True/False)       # 是否只保留最优结果

# 执行训练过程时加入callbacks选项记录到history中
history = model.fit（ callbacks=[cp_callback] ）

mnist数据集搭建可反复训练模型

原始代码：

import tensorflow as tf

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'])

model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()

可存取模型代码：

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()