在keras中制作一个"non-fully connected"（单连接？）神经网络

Question

我不知道我要找的东西的名称，但我想在 keras 中创建一个层，其中每个输入都乘以它自己的、独立的权重和偏差。例如。如果有 10 个输入，将有 10 个权重和 10 个偏差，每个输入将乘以其权重并与偏差相加得到 10 个输出。

例如这里是一个简单的密集网络：

from keras.layers import Input, Dense
from keras.models import Model
N = 10
input = Input((N,))
output = Dense(N)(input)
model = Model(input, output)
model.summary()

如你所见，这个模型有110个参数，因为它是全连接的：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_2 (InputLayer)         (None, 10)                0         
_________________________________________________________________
dense_2 (Dense)              (None, 10)                110       
=================================================================
Total params: 110
Trainable params: 110
Non-trainable params: 0
_________________________________________________________________

我想用 output = SinglyConnected()(input) 之类的东西替换 output = Dense(N)(input)，这样模型现在有 20 个参数：10 个权重和 10 个偏差。

Answer 1

创建自定义图层：

class SingleConnected(Layer):

    #creator
    def __init__(self, **kwargs):
        super(SingleConnected, self).__init__(**kwargs)

   #creates weights
   def build(self, input_shape):

       weight_shape = (1,) * (len(input_shape) - 1)
       weight_shape = weight_shape + (input_shape[-1]) #(....., input)

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

       self.bias = self.add_weight(name='bias', 
                                   shape=weight_shape,
                                   initializer='zeros',
                                   trainable=True)

       self.built=True

   #operation:
   def call(self, inputs):
       return (inputs * self.kernel) + self.bias

   #output shape
   def compute_output_shape(self, input_shape):
       return input_shape

   #for saving the model - only necessary if you have parameters in __init__
   def get_config(self):
       config = super(SingleConnected, self).get_config()
       return config

使用图层：

model.add(SingleConnected())

在keras中制作一个"non-fully connected"（单连接？）神经网络

Make a "non-fully connected" (singly connected?) neural network in keras

neural-network

deep-learning

keras

keras-layer