在 keras 自定义层中使用广播进行元素乘法

Question

我正在创建一个自定义层，其权重需要在激活之前按元素相乘。当输出和输入的形状相同时，我可以让它工作。当我将一阶数组作为输入，将二阶数组作为输出时，就会出现问题。 tensorflow.multiply 支持广播，但是当我尝试在 Layer.call(x, self.kernel) 中使用它时 将 x 乘以 self.kernel 变量，它抱怨说它们是不同的形状：

ValueError: Dimensions must be equal, but are 4 and 3 for 'my_layer_1/Mul' (op: 'Mul') with input shapes: [?,4], [4,3].

这是我的代码：

from keras import backend as K
from keras.engine.topology import Layer
import tensorflow as tf
from keras.models import Sequential
import numpy as np

class MyLayer(Layer):

    def __init__(self, output_dims, **kwargs):
        self.output_dims = output_dims

        super(MyLayer, self).__init__(**kwargs)

    def build(self, input_shape):
        # Create a trainable weight variable for this layer.
        self.kernel = self.add_weight(name='kernel',
                                      shape=self.output_dims,
                                      initializer='ones',
                                      trainable=True)


        super(MyLayer, self).build(input_shape)  # Be sure to call this somewhere!

    def call(self, x):
        #multiply wont work here?
        return K.tf.multiply(x, self.kernel)

    def compute_output_shape(self, input_shape):
        return (self.output_dims)

mInput = np.array([[1,2,3,4]])
inShape = (4,)
net = Sequential()
outShape = (4,3)
l1 = MyLayer(outShape, input_shape= inShape)
net.add(l1)
net.compile(loss='mean_absolute_error', optimizer='adam', metrics=['accuracy'])
p = net.predict(x=mInput, batch_size=1)
print(p)

编辑： 给定输入形状 (4,) 和输出形状 (4,3)，权重矩阵应该与输出形状相同，并用 1 初始化。所以在上面的代码中输入是[1,2,3,4]，权重矩阵应该是[[1,1,1,1],[1,1,1,1],[1,1,1 ,1]] 和输出应该看起来像 [[1,2,3,4],[1,2,3,4],[1,2,3,4]]

Answer 1

在相乘之前，您需要重复元素以增加形状。 您可以为此使用K.repeat_elements。 (import keras.backend as K)

class MyLayer(Layer):

    #there are some difficulties for different types of shapes   
    #let's use a 'repeat_count' instead, increasing only one dimension
    def __init__(self, repeat_count,**kwargs):
        self.repeat_count = repeat_count
        super(MyLayer, self).__init__(**kwargs)

    def build(self, input_shape):

        #first, let's get the output_shape
        output_shape = self.compute_output_shape(input_shape)
        weight_shape = (1,) + output_shape[1:] #replace the batch size by 1


        self.kernel = self.add_weight(name='kernel',
                                      shape=weight_shape,
                                      initializer='ones',
                                      trainable=True)


        super(MyLayer, self).build(input_shape)  # Be sure to call this somewhere!

    #here, we need to repeat the elements before multiplying
    def call(self, x):

        if self.repeat_count > 1:

             #we add the extra dimension:
             x = K.expand_dims(x, axis=1)

             #we replicate the elements
             x = K.repeat_elements(x, rep=self.repeat_count, axis=1)


        #multiply
        return x * self.kernel


    #make sure we comput the ouptut shape according to what we did in "call"
    def compute_output_shape(self, input_shape):

        if self.repeat_count > 1:
            return (input_shape[0],self.repeat_count) + input_shape[1:]
        else:
            return input_shape

Answer 2

这是基于 Daniel Möller 回答的另一种解决方案，但像原始代码一样使用 tf.multiply。

class MyLayer(Layer):

    def __init__(self, output_dim, **kwargs):
        self.output_dim = output_dim

        super(MyLayer, self).__init__(**kwargs)

    def build(self, input_shape):
        # Create a trainable weight variable for this layer.
        output_shape = self.compute_output_shape(input_shape)
        self.kernel = self.add_weight(name='kernel',
                                      shape=(1,) + output_shape[1:],
                                      initializer='ones',
                                      trainable=True)


        super(MyLayer, self).build(input_shape)  # Be sure to call this somewhere!

    def call(self, x):

        return K.tf.multiply(x, self.kernel)

    def compute_output_shape(self, input_shape):
        return (input_shape[0],self.output_dim)+input_shape[1:]