You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@dicarlolab/daseibert it looks like the mnist training procedure was done only on a few fully connected layers
_on features extracted by a model trained on cifar!!
Besides this being very interesting,
I'm pretty sure that means that
a) we should not test the mnist dataset, or its procedures
b) this resulting extra computation time freed up by not doing this should be used by testing different parameters/procedures which have been used for cifar.
We should codify alex's procedure: https://code.google.com/p/cuda-convnet/wiki/Methodology
And any other ones that we can find. If we could figure out any approximation of the methodology used for imagenet, then we should use that.
I'm having some trouble getting the logs into the repo right now because of some git issues. I'll commit them as soon as possible.
mnist logs are in here (inside figure 2 or 3)
http://cs.nyu.edu/~wanli/dropc/dropnn-exp.tar.gz
cifar logs are in here. (something something run##_log.txt)
http://cs.nyu.edu/~wanli/dropc/cifar10-9_32.tar.gz
The text was updated successfully, but these errors were encountered: