Save & Load TensorFlow Models

Saving and loading models in TensorFlow can be achieved using tf.keras.models.save_model() and tf.keras.models.load_model(). Below is an example code for saving and loading models.

Save model:

# 定义模型
model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu', input_shape=(784,)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

# 编译模型
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# 训练模型
model.fit(x_train, y_train, epochs=5)

# 保存模型
model.save('my_model.h5')

Load model:

# 加载模型
model = tf.keras.models.load_model('my_model.h5')