图像分类，输入图像通道改为6，配置文件 '--image_shape 6 500 512', 中通道也改成了6， 但是 运行过程中报错。 使用最简单的 alexnet测试。

https://github.com/PaddlePaddle/models/blob/develop/PaddleCV/image_classification/models/alexnet.py

----------------------
Error Message Summary:
----------------------
Error: ShapeError: The number of input channels should be equal to filter channels * groups. But received: the input channels is [6], the 
shapeof input is [1, 6, 500, 512], the filter 
channel is [3], the shape of filter is [64, 3, 11, 11],the groups is [1]
  [Hint: Expected input_channels == filter_dims[1] * groups, but received input_channels:6 != filter_dims[1] * groups:3.] at (D:\1.6.2\paddle\paddle\fluid\operators\conv_op.cc:94)     
  [operator < conv2d > error]

问题 ，滤波器的通道数怎么改，里面是默认是3 么？不应该是和输入数据的通道数一致么