Question

我正在尝试在keras中创建一个具有两个可训练变量的自定义层。我将这两个变量传递给另一个函数，在其中需要获取变量的ndims和形状。但是它显示错误。我的自定义图层代码是-

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.
    assert len(input_shape) >= 3
    input_dim = input_shape[1:]
    print(input_shape)


    self.kernel1 = self.add_weight(
                               shape=self.output_dim[0],input_dim[0]),
                               name = 'kernel1',
                               initializer='uniform',
                               trainable=True)
    print(self.kernel1)

    self.kernel2 = self.add_weight(
                              shape=(self.output_dim[1],input_dim[1]),
                              name = 'kernel2',
                              initializer='uniform',
                              trainable=True)
    print(self.kernel2)


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

def call(self, x):
     print(x.shape)

     mat1 =np.array(self.kernel1)

     print(K.shape(mat1))
     #print(mat1.ndim)

     mat2 =np.array(self.kernel2)

     print(K.shape(mat2))
     #print(mat2.ndim)



     output1 = Myoperation(x,mat1,1)
     output = Myoperation(output1,mat2,2)

     return output


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

在函数Myoperation中，它需要计算 m2=list(np.shape(M))[1]; M是mat1或mat2输入代码错误是-

IndexError：列表索引超出范围如果我们使用mat1.shape检查形状，我们得到 TypeError：预期的二进制或Unicode字符串，得到

请帮助

keras自定义图层变量没有ndim和shape属性

0 个答案: