optimize option for both train and forward

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

optimize option for both train and forward #11

Closed xiuliren closed 9 years ago

xiuliren commented 9 years ago

most of the time, we use optimeze in training, but do not need optimize for forward pass. forward pass is fast and optimize takes a big part of processing time.