Incompatible attr in node at 0-th output: expected [96,1,5,5], got [96,3,5,5]

[mkhoshle]

Hi I am trying to fine tune lightened_cnn model for face recognition purpose on my own dataset. My data shape is (3,128,128) and when I run the code I get the following error:

MXNetError: [15:57:10] /home/travis/build/dmlc/mxnet-distro/mxnet-build/3rdparty/mshadow/../../src/operator/tensor/../elemwise_op_common.h:135: Check failed: assign(&dattr, vec.at(i)): Incompatible attr in node  at 0-th output: expected [96,1,5,5], got [96,3,5,5]

Does this mean that this model can not be used for images with 3 channels?