wakahiu/cuda-convnet

Visualising feature output from layers

Opened this issue · 0 comments

When using startFeatureWriter to get out a feature map, I cannot seem to 
visualise the data properly. It seems there is some sort of channel 
interleaving, which is different depending on the layers. Is there anything I 
am missing to be able to visualise the output featuremap of a layer (even a 
simple layer such as resize or gaussian blur)?

Original issue reported on code.google.com by maxjader...@gmail.com on 12 Nov 2013 at 5:21