如何在自定义keras图层中使用keras图层 [英] How to use keras layers in custom keras layer

问题描述

我正在尝试编写自己的keras层.在这一层中，我想使用其他一些keras层.有什么办法可以做这样的事情:

I am trying to write my own keras layer. In this layer, I want to use some other keras layers. Is there any way to do something like this:

class MyDenseLayer(tf.keras.layers.Layer):
  def __init__(self, num_outputs):
    super(MyDenseLayer, self).__init__()
    self.num_outputs = num_outputs

  def build(self, input_shape):
    self.fc = tf.keras.layers.Dense(self.num_outputs)

  def call(self, input):
    return self.fc(input)

layer = MyDenseLayer(10)

当我做类似的事情

input = tf.keras.layers.Input(shape = (16,))
output = MyDenseLayer(10)(input)
model = tf.keras.Model(inputs = [input], outputs = [output])
model.summary()

它输出

我如何使密集人群中的训练变得容易?

How do I make weiths in the dense there trainable?

推荐答案

将现有图层放入tf.keras.models.Model类更加舒适和简洁.如果定义非自定义图层(例如，图层，conv2d)，则默认情况下这些图层的参数是不可训练的.

It's much more comfortable and concise to put existing layers in the tf.keras.models.Model class. If you define non-custom layers such as layers, conv2d, the parameters of those layers are not trainable by default.

class MyDenseLayer(tf.keras.Model):
  def __init__(self, num_outputs):
    super(MyDenseLayer, self).__init__()
    self.num_outputs = num_outputs
    self.fc = tf.keras.layers.Dense(num_outputs)

  def call(self, input):
    return self.fc(input)

  def compute_output_shape(self, input_shape):
    shape = tf.TensorShape(input_shape).as_list()
    shape[-1] = self.num_outputs
    return tf.TensorShape(shape)

layer = MyDenseLayer(10)

检查本教程: https://www.tensorflow.org/guide/keras#model_subclassing

这篇关于如何在自定义keras图层中使用keras图层的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！