方法1：只保存模型的權重和偏置

這種方法不會保存整個網絡的結構，只是保存模型的權重和偏置，所以在后期恢復模型之前，必須手動創建和之前模型一模一樣的模型，以保證權重和偏置的維度和保存之前的相同。

tf.keras.model類中的save_weights方法和load_weights方法，參數解釋我就直接搬運官網的內容了。

save_weights( filepath, overwrite=True, save_format=None)

Arguments:

filepath: String, path to the file to save the weights to. When saving in TensorFlow format, this is the prefix used for checkpoint files (multiple files are generated). Note that the '.h5' suffix causes weights to be saved in HDF5 format.

overwrite: Whether to silently overwrite any existing file at the target location, or provide the user with a manual prompt.

save_format: Either 'tf' or 'h5'. A filepath ending in '.h5' or '.keras' will default to HDF5 if save_format is None. Otherwise None defaults to 'tf'.

load_weights( filepath, by_name=False)

實例1：

import tensorflow as tffrom tensorflow import kerasfrom tensorflow.keras import datasets, layers, optimizers # step1 加載訓練集和測試集合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  # step2 創建模型def create_model(): return tf.keras.models.Sequential([ tf.keras.layers.Flatten(input_shape=(28, 28)), tf.keras.layers.Dense(512, activation='relu'), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation='softmax') ])model = create_model() # step3 編譯模型 主要是確定優化方法，損失函數等model.compile(optimizer='adam',  loss='sparse_categorical_crossentropy',  metrics=['accuracy']) # step4 模型訓練 訓練一個epochsmodel.fit(x=x_train,  y=y_train,  epochs=1,  ) # step5 模型測試loss, acc = model.evaluate(x_test, y_test)print("train model, accuracy:{:5.2f}%".format(100 * acc)) # step6 保存模型的權重和偏置model.save_weights('./save_weights/my_save_weights') # step7 刪除模型del model # step8 重新創建模型model = create_model()model.compile(optimizer='adam',  loss='sparse_categorical_crossentropy',  metrics=['accuracy']) # step9 恢復權重model.load_weights('./save_weights/my_save_weights') # step10 測試模型loss, acc = model.evaluate(x_test, y_test)print("Restored model, accuracy:{:5.2f}%".format(100 * acc))

train model, accuracy:96.55%

Restored model, accuracy:96.55%

可以看到在模型的權重和偏置恢復之后，在測試集合上同樣達到了訓練之前相同的準確率。

方法2：直接保存整個模型

這種方法會將網絡的結構，權重和優化器的狀態等參數全部保存下來，后期恢復的時候就沒必要創建新的網絡了。

tf.keras.model類中的save方法和load_model方法