Possible bug in WideResnet implementation
micronet-challenge-submissions opened this issue · 2 comments
micronet-challenge-submissions commented
sparse_learning/sparselearning/models.py
Line 353 in 6b97851
Hi Tim,
Looks like the depth is not used by the model. Is this intended?
TimDettmers commented
It is a bit difficult to spot, but the depth variable is used for the n variable which is then used in the NetworkBlock.
Please let me know if you find other possible bugs!
evcu commented
Hi Tim,
Sorry that I opened up the bug using the wrong account. Thanks for your response. It make sense, I missed that the NetworkBlock uses n to decide n_layers. Makes sense!