search

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

Load FFT optimization #55

Closed torms3 closed 8 years ago

torms3 commented 8 years ago

Layer-wise FFT optimization takes quite long if the network being optimized is large. The optimized results are saved as fft=1 or fft=0 options in filter edges, but omitted from loading. They should be loaded from the saved instance, so that time-consuming FFT optimization need not be repeated.

xiuliren commented 8 years ago

@torms3 the code only load fft flag, but did not prevent the optimize process, right?

xiuliren commented 8 years ago

@torms3 let's merge to development branch first? we could use that to test.

torms3 commented 8 years ago

@jingpengwu Sounds good. I've already tested it, but it's always good to double check it.

xiuliren commented 8 years ago

I am closing this pull request and merge it to development branch.