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
I was wondering if there is a chance to realize an unpool operation? E.g. when I want to write a custom backward pass for the max pooling operation, how would I go about it? PyTorch has the option to return indices of the pooling operation and also provides an unpooling operation (https://pytorch.org/docs/stable/generated/torch.nn.MaxUnpool2d.html). Technically at some level, we must have access to the indices which are selected during max pool however I am unsure how I would access them.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hey everyone,
I was wondering if there is a chance to realize an unpool operation? E.g. when I want to write a custom backward pass for the max pooling operation, how would I go about it? PyTorch has the option to return indices of the pooling operation and also provides an unpooling operation (https://pytorch.org/docs/stable/generated/torch.nn.MaxUnpool2d.html). Technically at some level, we must have access to the indices which are selected during max pool however I am unsure how I would access them.
Any help is appreciated!
Best,
Clemens
Beta Was this translation helpful? Give feedback.
All reactions