卷积2D“输入深度不是滤波器的输入深度的倍数".

我想在张量流中使用fft2d变换，然后用卷积层分析幅度和相位结果...我制作了一个具有Lambda层的系统，以使用张量流函数并获取幅度和相位.但是，当我添加Conv2d图层时，出现错误

I want to use fft2d transform in tensorflow and then analyse the magnitude and phase result with convolutional layers... I have made a system with Lambda layers to use tensorflow functions and get the magnitude and the phase. But when I add the Conv2d layer, I get the error

输入深度(3)不是输入形状为[?，199,199,3]，[[_，199,199,3]的'1_Magn_Conv_f500_k2_2/convolution'(op:'Conv2D')的过滤器(199)输入深度的倍数.2,2,199,500]

我不知道什么是形状[2,2,199,500] ，是什么导致此错误.

I don't understand what is the shape [2,2,199,500] and what is causing this error.

我试图减少网络中的层数，以检测是哪个层造成了问题.我已经检查过magn_angle输出两个具有形状[None，199,199,3] 的张量.我正在与Google colab合作.

I have tried to reduce the number of layers in my networks to detect which one creates the problem. I have checked that magn_angle outputs two tensors with shapes [None,199,199,3]. I am working with google colab.

这是重现该错误的最少代码

Here is the minimal code to reproduce the error

inpt = Input(shape = (199, 199, 3),name=str(0)+'_'+'Image')
def magn_angle(x):
    x = Lambda(lambda x:K.cast(x,dtype=tf.complex64))(x)
    x_list_magn = []
    x_list_angle = []
    for i in range(3):
        fft = Lambda(lambda x: tf.fft2d(x[:,:,:,i]), output_shape=(None,199,199))(x)# 2-dimensional discrete Fourier transform over the inner-most 2 dimensions
        x_list_magn.append(Lambda(lambda fft:K.expand_dims(tf.math.abs(fft),axis=-1), output_shape=(None,199,199))(fft))
        x_list_angle.append(Lambda(lambda fft: K.expand_dims(tf.math.angle(fft),axis=-1), output_shape=(None,199,199))(fft))
    magn = Concatenate()(x_list_magn)
    angle = Concatenate()(x_list_angle)
    magn = Lambda(lambda magn: K.cast(magn,dtype=tf.float32), output_shape=(None,199,199))(magn)
    angle = Lambda(lambda angle: K.cast(angle,dtype=tf.float32), output_shape=(None,199,199))(angle)
    return magn,angle
magn, angle = magn_angle(inpt)
magn = Conv2D(filters=500,kernel_size=(2,2),activation=None,strides=(1,1),padding='SAME',name=str(1)+'_'+'Magn_Conv_f500_k2',data_format="channels_last")(magn)
...

哪些产出

InvalidArgumentError:输入深度(3)不是输入形状为[[,, 199,199,3]的'1_Magn_Conv_f500_k2_3/convolution'(op:'Conv2D')的过滤器(199)输入深度的倍数.，[2,2,199,500] .