Skip to content

Cleaner workaround for max pool #103

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.

Sign up for GitHub

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

Merged
drnikolaev merged 1 commit into from
Jan 20, 2016
Merged

Cleaner workaround for max pool #103

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions src/caffe/layer_factory.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,13 +79,14 @@ shared_ptr<Layer<Dtype> > GetPoolingLayer(const LayerParameter& param) {
} else if (engine == PoolingParameter_Engine_CUDNN) {
PoolingParameter p_param = param.pooling_param();

// FIXME We assume that precision issue will be fixed in cuDNN v5.0
#if CUDNN_VERSION >= 5000
return shared_ptr<Layer<Dtype> >(new CuDNNPoolingLayer<Dtype>(param));
#else
return shared_ptr<Layer<Dtype> >(new PoolingLayer<Dtype>(param));
#endif

// CuDNN handles tie breaks differently than Caffe for MaxPooling.
// Until there is a workaround in Caffe (index management) or cuDNN,
// use Caffe layer to max pooling
if (param.pooling_param().pool() == PoolingParameter_PoolMethod_MAX) {
return shared_ptr<Layer<Dtype> >(new PoolingLayer<Dtype>(param));
} else {
return shared_ptr<Layer<Dtype> >(new CuDNNPoolingLayer<Dtype>(param));
}
#endif
} else {
LOG(FATAL) << "Layer " << param.name() << " has unknown engine.";
Expand Down