Mask should be used for rebalancing

seung-lab / znn-release

Multi-core CPU implementation of deep learning for 2D and 3D sliding window convolutional networks (ConvNets).

GNU General Public License v3.0

94 stars 33 forks source link

Open torms3 opened 8 years ago

torms3 commented 8 years ago

If there exists a mask, it should be used when computing the rebalancing weight mask. Currently rebalancing doesn't take into account the mask.