Keras 中的仅偏置层

Question

如何在 Keras 中构建一个层，将输入 x 映射到 x+b 形式的输出，其中 b 是相同维度的可训练权重？（这里的激活函数也是恒等式）。

Answer 1

您始终可以通过扩展类来构建自定义层tf.keras.layers.Layer，这就是我的做法

import tensorflow as tf
print('TensorFlow:', tf.__version__)

class BiasLayer(tf.keras.layers.Layer):
    def __init__(self, *args, **kwargs):
        super(BiasLayer, self).__init__(*args, **kwargs)

    def build(self, input_shape):
        self.bias = self.add_weight('bias',
                                    shape=input_shape[1:],
                                    initializer='zeros',
                                    trainable=True)
    def call(self, x):
        return x + self.bias

input_layer = tf.keras.Input(shape=[5])
x  = BiasLayer()(input_layer)
model = tf.keras.Model(inputs=[input_layer], outputs=[x])

model.summary()

TensorFlow: 2.1.0
Model: "model_2"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_7 (InputLayer)         [(None, 5)]               0         
_________________________________________________________________
bias_layer_3 (BiasLayer)     (None, 5)                 5         
=================================================================
Total params: 5
Trainable params: 5
Non-trainable params: 0
_________________________________________________________________