Join GitHub today
GitHub is home to over 28 million developers working together to host and review code, manage projects, and build software together.Sign up
Cannot perform backprop: Dropout mask array is absent (already cleared?) in beta2 #6326
i'm training the following network:
on 1.0-alpha and it works fine.
I gave a try to 1.0-beta2 and i get the following exception as soon as training starts:
Exception in thread "main" java.lang.IllegalStateException: Cannot perform backprop: Dropout mask array is absent (already cleared?)
@AlexDBlack here is a gist: https://gist.github.com/fmorbini/936a7f1c9b0aa905e3ecf71dc096cb30
it's not the same issue but related to #5571
Thanks for reporting - fixed here: #6370
FYI the issue is specific to dropout on output layers in computation graph.