Cannot make caffe version due to reverse_axis_layer error

[AndresPMD]

Hello @tonghe90 ,
At the moment it is impossible to compile your caffe version due to the following error:

CXX src/caffe/layers/base_conv_layer.cpp
In file included from ./include/caffe/common.hpp:19:0,
from ./include/caffe/blob.hpp:8,
from ./include/caffe/layers/reverse_axis_layer.hpp:6,
from src/caffe/layers/reverse_axis_layer.cpp:1:
./include/caffe/util/device_alternate.hpp:14:15: error: expected initializer before ‘<’ token
void classname::Forward_gpu(const vector<Blob>& bottom,
^
src/caffe/layers/reverse_axis_layer.cpp:61:1: note: in expansion of macro ‘STUB_GPU’
STUB_GPU(ReverseLayer);
^
./include/caffe/util/device_alternate.hpp:17:15: error: expected initializer before ‘<’ token
void classname::Backward_gpu(const vector<Blob>& top,
^
src/caffe/layers/reverse_axis_layer.cpp:61:1: note: in expansion of macro ‘STUB_GPU’
STUB_GPU(ReverseLayer);
^
Makefile:581: recipe for target '.build_release/src/caffe/layers/reverse_axis_layer.o' failed
make: *** [.build_release/src/caffe/layers/reverse_axis_layer.o] Error 1
make: *** Waiting for unfinished jobs....

Do you have any idea why is this happening?
I am configuring the Makefile.config to run in a CPU rather than GPU.
Let me know any comments.
Thank you!

[tonghe90]

@DreadPiratePsyopus, Thanks for your interest. I have rebuild it but can't replicate this error. I think you can have a try to use CPU version of this layer.

[AndresPMD]

I have tried on different computers (different versions of cuda and cudnn) but I am not able to rebuild the project. I already tried with CPU and GPU and the same error on reverse_axis_layer persists. Any idea what could be happening? Do you have a specific guide to build your custom caffe? I am following this tutorial https://github.com/BVLC/caffe/wiki/Ubuntu-16.04-Installation-Guide along with the official caffe tutorial.

[etworker]

same problem, also waiting for your solution, thanks!

[AndresPMD]

I managed to make this code work, but most of the problems I encountered were solved when I used Cuda 8.0 and CUDNN 6.0.

[Bshowg]

Changing
STUB_CPU(ReverseLayer)
to
STUB_CPU(ReverseAxisLayer)
seems to solve the problem for me