首页 文章

Keras自定义图层没有不同的output_shape

提问于
浏览
1

我正在尝试在Keras中实现一个层,它为每个输入添加元素 . 因此,输入,重量和输出具有完全相同的形状 . 然而,我正在努力实现这一点,我没有找到任何自动图层的例子,不会改变输入形状 .

来自keras.engine.topology导入层导入keras.backend为K.

class SumationLayer(Layer):

def __init__(self, **kwargs):
    self.output_dim = K.placeholder(None)
    super(SumationLayer, self).__init__(**kwargs)

def build(self, input_shape):
    # Create a trainable weight variable for this layer.
    self.kernel = self.add_weight(name='kernel', 
                                  shape=(input_shape[1], self.output_dim),
                                  initializer='uniform',
                                  trainable=True)
    super(SumationLayer, self).build(input_shape)  # Be sure to call this somewhere!
    self.output_dim = (input_shape[0], self.output_dim)
def call(self, x):
    return x + self.kernel

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

这会输出以下错误:

TypeError: Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64

如果我像Keras示例那样实现该层,那么我必须在初始化时输入输出形状,这会产生不希望的行为(通过完全连接输入来平坦化输出) .

1 回答

  • 0

    玩代码我得到它的工作:但这仅适用于二维张量 . 如果你需要一个三维张量,你还需要包含input_shape [3] .

    from keras.layers import Layer, Input
    from keras import backend as K
    from keras import Model
    import tensorflow as tf
    
    class SumationLayer(Layer):
    
        def __init__(self, **kwargs):
            super(SumationLayer, self).__init__(**kwargs)
    
        def build(self, input_shape):
            # Create a trainable weight variable for this layer.
            self.kernel = self.add_weight(name='kernel', 
                                          shape=(input_shape[1], input_shape[2]),
                                          initializer='uniform',
                                          trainable=True)
            super(SumationLayer, self).build(input_shape)  # Be sure to call this somewhere!
        def call(self, x):
            return x + self.kernel
    
        def compute_output_shape(self, input_shape):
            return (input_shape[0], input_shape[1], input_shape[2])
    
    
    
    input = Input(shape = (10,10))
    output = SumationLayer()(input)
    model = Model(inputs = [input], outputs = [output])
    model.summary()
    

相关问题