Skip to content
Discussion options

You must be logged in to vote

forward should implement what you want to use when calling model(x).

you may need to call that in training step (usually do), which means you have to do self.forward(...) because you are in the model when you make that call.

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by carmocca
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
2 participants
Converted from issue

This discussion was converted from issue #632 on February 04, 2021 23:45.