Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Is it possible to build caffe-fast-rcnn without GPU? #4

Open
Prithviraj7 opened this issue Mar 29, 2016 · 4 comments
Open

Is it possible to build caffe-fast-rcnn without GPU? #4

Prithviraj7 opened this issue Mar 29, 2016 · 4 comments

Comments

@Prithviraj7
Copy link

I'm getting make errors when I run 'make all'.

@gkioxari
Copy link
Owner

You should be able to build it with the right changes in your makefile. Please refer to caffe for that...

@Prithviraj7
Copy link
Author

Hi!
In makefile.config, I have already set the CPU_ONLY mode to 1 and WITH_PYTHON_LAYER to 1 as well. But still I am getting the following error when I run make all.

CXX src/caffe/layers/sigmoid_layer.cpp`

In file included from ./include/caffe/common.hpp:19:0,
                 from ./include/caffe/blob.hpp:8,
                 from ./include/caffe/layer.hpp:8,
                 from src/caffe/layers/sigmoid_cross_entropy_weighted_loss_layer.cpp:5:
./include/caffe/util/device_alternate.hpp:30:39: error: novoid caffe::SigmoidCrossEntropyWeightedLossLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<bool>&, const std::vector<caffe::Blob<Dtype>*>&)’ member function declared in classcaffe::SigmoidCrossEntropyWeightedLossLayer<Dtype>const vector<Blob<Dtype>*>& bottom) { NO_GPU; } \
                                       ^
src/caffe/layers/sigmoid_cross_entropy_weighted_loss_layer.cpp:87:1: note: in expansion of macroSTUB_GPU_BACKWARDSTUB_GPU_BACKWARD(SigmoidCrossEntropyWeightedLossLayer, Backward);
 ^
make: *** [.build_release/src/caffe/layers/sigmoid_cross_entropy_weighted_loss_layer.o] Error 1
make: *** Waiting for unfinished jobs....
src/caffe/layers/mil_layer.cpp: In instantiation ofvoid caffe::MILLayer<Dtype>::Forward_cpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<caffe::Blob<Dtype>*>&) [with Dtype = float]’:
src/caffe/layers/mil_layer.cpp:85:1:   required from here
src/caffe/layers/mil_layer.cpp:48:19: warning: unused variablemax_prob’ [-Wunused-variable]
       Dtype prob, max_prob; 
                   ^
src/caffe/layers/mil_layer.cpp: In instantiation ofvoid caffe::MILLayer<Dtype>::Forward_cpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<caffe::Blob<Dtype>*>&) [with Dtype = double]’:
src/caffe/layers/mil_layer.cpp:85:1:   required from here
src/caffe/layers/mil_layer.cpp:48:19: warning: unused variablemax_prob’ [-Wunused-variable]

I am already following all the instructions in Caffe's website. So, it would be great if you could help me with this issue.

TIA

@samouha
Copy link

samouha commented Apr 3, 2016

I'm getting the same problem when trying make in CPU mode !

@gkioxari
Copy link
Owner

In src/caffe/layers/sigmoid_cross_entropy_weighted_loss_layer.cpp try removing lines:

#ifdef CPU_ONLY STUB_GPU_BACKWARD(SigmoidCrossEntropyWeightedLossLayer, Backward); #endif

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants