rebalance based on output patch

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

rebalance based on output patch #18

Closed xiuliren closed 9 years ago

xiuliren commented 9 years ago

right now, the rebalance weight is computed in the whole label image stack. We may need to test the performance using rebalance weight based on each output patch.

xiuliren commented 9 years ago

added a flag of is_patch_rebalance