Skip to content

Caffe Loss Layer for Ordinal Regression with Multiple Output CNN for Age Estimation.

Notifications You must be signed in to change notification settings

luoyetx/OrdinalRegression

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 

Repository files navigation

Ordinal Regression

Caffe Loss Layer for Ordinal Regression with Multiple Output CNN for Age Estimation.

How to

You need to install Caffe first. Copy relative files to Caffe's source code tree.

export CAFFE_HOME=/path/to/caffe
cp layers/ordinal_regression_loss_layer.hpp $CAFFE_HOME/include/caffe/layers/ordinal_regression_loss_layer.hpp
cp layers/ordinal_regression_loss_layer.cpp $CAFFE_HOME/src/caffe/layers/ordinal_regression_loss_layer.cpp
cp layers/ordinal_regression_loss_layer.cu $CAFFE_HOME/src/caffe/layers/ordinal_regression_loss_layer.cu
cp layers/test_ordinal_regression_loss_layer.cpp $CAFFE_HOME/src/caffe/test/test_ordinal_regression_loss_layer.cpp

Modify $CAFFE_HOME/src/caffe/proto/caffe.proto according to layers/caffe.proto

After all, follow Caffe's documents and compile it.

Test the layer

make runtest GTEST_FILTER='OrdinalRegressionLossLayerTest/*'

References

About

Caffe Loss Layer for Ordinal Regression with Multiple Output CNN for Age Estimation.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published