如何在 keras 中创建可训练参数？

感谢您查看我的问题。

例如。

最终的输出是两个矩阵A和B的和，如下所示：

output = keras.layers.add([A, B])

现在，我想构建一个新参数 x 来更改输出。

我想让新输出 = Ax+B(1-x)

x 是一个可训练参数在我的网络中。

我应该怎么办？ 请帮助我~非常感谢！

编辑（部分代码）：

conv1 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(input)
drop1 = Dropout(0.5)(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(drop1)

conv2 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
conv2 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
drop2 = Dropout(0.5)(conv2)

up1 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(drop2))

#the line I want to change:
merge = add([drop2,up1])
#this layer is simply add drop2 and up1 layer.now I want to add a trainable parameter x to adjust the weight of thoese two layers.

我尝试使用代码，但仍然出现一些问题：

1.如何使用自己的图层？

merge = Mylayer()(drop2,up1)

或者其他方式？

2.out_dim的含义是什么？ 这些参数都是3维矩阵。out_dim的含义是什么？

谢谢你……T.T

编辑2（已解决）

from keras import backend as K
from keras.engine.topology import Layer
import numpy as np

from keras.layers import add

class MyLayer(Layer):

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

def build(self, input_shape):

    self._x = K.variable(0.5)
    self.trainable_weights = [self._x]

    super(MyLayer, self).build(input_shape)  # Be sure to call this at the end

def call(self, x):
    A, B = x
    result = add([self._x*A ,(1-self._x)*B])
    return result

def compute_output_shape(self, input_shape):
    return input_shape[0]

您必须创建一个继承自的自定义类Layer并使用创建可训练参数self.add_weight(...)。你可以找到一个这样的例子here and there.

对于您的示例，该图层在某种程度上看起来像这样：

from keras import backend as K
from keras.engine.topology import Layer
import numpy as np

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.
        self._A = self.add_weight(name='A', 
                                    shape=(input_shape[1], self.output_dim),
                                    initializer='uniform',
                                    trainable=True)
        self._B = self.add_weight(name='B', 
                                    shape=(input_shape[1], self.output_dim),
                                    initializer='uniform',
                                    trainable=True)
        super(MyLayer, self).build(input_shape)  # Be sure to call this at the end

    def call(self, x):
        return K.dot(x, self._A) + K.dot(1-x, self._B)

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

Edit：仅仅基于我（错误地）假设的名字x是层输入并且您想要优化A and B。但是，正如您所说，您想要优化x。为此，您可以执行以下操作：

from keras import backend as K
from keras.engine.topology import Layer
import numpy as np

class MyLayer(Layer):

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

    def build(self, input_shape):
        # Create a trainable weight variable for this layer.
        self._x = self.add_weight(name='x', 
                                    shape=(1,),
                                    initializer='uniform',
                                    trainable=True)
        super(MyLayer, self).build(input_shape)  # Be sure to call this at the end

    def call(self, x):
        A, B = x
        return K.dot(self._x, A) + K.dot(1-self._x, B)

    def compute_output_shape(self, input_shape):
        return input_shape[0]

Edit2：您可以使用调用该层

merge = Mylayer()([drop2,up1])