tf.keras学习之sequential

参考

https://tensorflow.google.cn/api_docs/python/tf/keras/Sequential

做什么的？

在官方文档中这样说：
“list of layers to add to the model.”
其实就是将一系列的层次堆叠起来。
继承于model

使用

import tensorflow as tf
model = tf.keras.Sequential()

方法

add

model.add(layer)

compile

compile(
    optimizer='rmsprop', loss=None, metrics=None, loss_weights=None,
    weighted_metrics=None, run_eagerly=None, steps_per_execution=None, **kwargs
)

model.compile(
    loss="sparse_categorical_crossentropy",
    optimizer=tf.keras.optimizers.SGD(0.001),
    metrics=["accuracy"]
)

optimizer:

loss:

fit

fit(
    x=None, y=None, batch_size=None, epochs=1, verbose='auto',
    callbacks=None, validation_split=0.0, validation_data=None, shuffle=True,
    class_weight=None, sample_weight=None, initial_epoch=0, steps_per_epoch=None,
    validation_steps=None, validation_batch_size=None, validation_freq=1,
    max_queue_size=10, workers=1, use_multiprocessing=False
)

model.fit(train_scaled, train_label, epochs=10,
          validation_data=(valid_scaled, val_label),
          callbacks=callbacks)

callbacks:

evaluate

evaluate(
x=None, y=None, batch_size=None, verbose=1, sample_weight=None, steps=None,
callbacks=None, max_queue_size=10, workers=1, use_multiprocessing=False,
return_dict=False, **kwargs
)

loss, acc = model.evaluate(test_data, test_label)