使用MXNet的Keras中的Conv3D：张量形状错误

Question

我在Keras中用TensorFlow实现了一个3D CNN，在这之前它运行得非常好。现在为了加快多个GPU的训练，我想尝试使用MXNet和Keras。我原以为除了“channels_last”到“channels\u first”的问题之外，我不需要修改很多代码，但是程序在Conv3D操作中崩溃了。你知道吗

那个keras.json文件文件是，因此应将其设置为正常运行：

{
    "backend": "mxnet",
    "image_data_format": "channels_first",
    "epsilon": 1e-07,
    "floatx": "float32"
}

这是显示错误的一小部分：

from keras.models import *
from keras.layers import *
from keras.optimizers import *

def SimpleInceptionBlock(input, num_kernels, kernel_init='he_normal', padding='same', bn_axis=1):
    tower1 = Conv3D(num_kernels, 1, padding=padding, kernel_initializer=kernel_init)(input)
    tower1 = BatchNormalization()(tower1)
    tower1 = ELU()(tower1)

    tower2 = MaxPooling3D(pool_size=(2, 2, 2), strides=(1, 1, 1), padding=padding)(input)
    tower2 = Conv3D(num_kernels, 1, padding=padding, kernel_initializer=kernel_init)(tower2)
    tower2 = BatchNormalization()(tower2)
    tower2 = ELU()(tower2)

    output = concatenate([tower1, tower2], axis=bn_axis)
    return output


def TestNet(input_size=(1,64,64,64), num_class=7):
    bn_axis = 1

    img_input = Input(shape=input_size)

    filter1 = SimpleInceptionBlock(img_input, 16)
    # this runs fine, filter1.shape = (None, 32, 64, 64, 64)

    filter2 = SimpleInceptionBlock(filter1, 16)

    output = Conv3D(num_class, (1, 1, 1), activation='softmax', kernel_initializer = kernel_init, padding='same', kernel_regularizer=l2(1e-4))(filter2)
    model = Model(input=img_input, output=output)

    return model


model = TestNet()

第一次调用“SimpleInceptionBlock”运行正常，filter1.shape = (None, 32, 64, 64)与预期一致，但第二次调用产生错误消息：

Error in operator concat0: [15:40:58] C:\Jenkins\workspace\mxnet-tag\mxnet\src\operator\nn\concat.cc:66: Check failed: shape_assign(&(*in_shape)[i], dshape) Incompatible input shape: expected [0,0,64,64,64], got [0,16,64,65,65]