AI开发平台MODELARTS-TensorFlow 2.1:训练并保存模型

时间：2024-09-05 08:29:59

AI开发平台MODELARTS

训练并保存模型

from __future__ import absolute_import, division, print_function, unicode_literals

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(input_shape=(28, 28)),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(256, activation='relu'),
    tf.keras.layers.Dropout(0.2),
    # 对输出层命名output，在模型推理时通过该命名取结果
    tf.keras.layers.Dense(10, activation='softmax', name="output")
])

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

model.fit(x_train, y_train, epochs=10)

tf.keras.models.save_model(model, "./mnist")

上一篇：AI开发平台MODELARTS-TensorFlow 2.1:推理代码

下一篇：AI开发平台MODELARTS-TensorFlow 2.1:推理代码