Keras Conv2D自定义内核初始化

1 回答

• 2

  关于形状的警告：如果你的内核大小为 (11,11) ，并且假设你有64个输入通道和1个输出通道，那么你的最终内核形状必须是 (11,11,64,1) .

  你可能应该去 a[None,None] 和 b[:,:,:,None,None] .

  class CustomConv2D(Conv2D):
  
      def __init__(self, filters, kernel_size, kernelB = None, **kwargs):
          super(CustomConv2D, self).__init__(filters, kernel_size,**kwargs)
          self.kernelB = kernelB
  
      def build(self, input_shape):
  
  
          #use the input_shape to calculate the shapes of A and B
          #if needed, pay attention to the "data_format" used. 
  
          #this is an actual weight, because it uses `self.add_weight`   
          self.kernelA = self.add_weight(
                    shape=shape_of_kernel_A + (1,1), #or (1,1) + shape_of_A
                    initializer='glorot_uniform', #or select another
                    name='kernelA',
                    regularizer=self.kernel_regularizer,
                    constraint=self.kernel_constraint)
  
  
          #this is an ordinary var that will participate in the calculation
              #not a weight, not updated
          if self.kernelB is None:
              self.kernelB = K.constant(....) 
              #use the shape already containing the new axes
  
  
          #in the original conv layer, this property would be the actual kernel,
          #now it's just a var that will be used in the original's "call" method 
          self.kernel = K.sum(self.kernelA * self.kernelB, axis=2)  
          #important: the resulting shape should be:
              #(kernelSizeX, kernelSizeY, input_channels, output_channels)   
  
  
          #the following are remains of the original code for "build" in Conv2D
          #use_bias is True by default
          if self.use_bias:
              self.bias = self.add_weight(shape=(self.filters,),
                                      initializer=self.bias_initializer,
                                      name='bias',
                                      regularizer=self.bias_regularizer,
                                      constraint=self.bias_constraint)
          else:
              self.bias = None
          # Set input spec.
          self.input_spec = InputSpec(ndim=self.rank + 2,
                                  axes={channel_axis: input_dim})
          self.built = True
  

  ---

  自定义图层的提示

  从零创建自定义图层（从 Layer 派生）时，您应该具有以下方法：

  • __init__(self, ... parameters ...) - 这是创建者，在您创建图层的新实例时会调用它 . 在这里，您将用户传递的值存储为参数 . （在Conv2D中，init会有"filters"，"kernel_size"等）

  • build(self, input_shape) - 这是你应该创建权重的地方（根据输入的形状在这里创建所有可学习的变量）

  • compute_output_shape(self,input_shape) - 在此处根据输入形状返回输出形状

  • call(self,inputs) - 在这里执行实际的图层计算

  由于我们不是从零创建这个层，而是从 Conv2D 派生出来，所以一切准备就绪，我们所做的就是构建方法并替换被认为是Conv2D层的内核 .

  有关自定义图层的更多信息：https://keras.io/layers/writing-your-own-keras-layers/

  conv层的 call 方法是here in class _Conv(Layer): .

  回复于 2024-04-20T06:12:44+08:00