Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

FullEmbeddingDropout works during evaluation #61

Closed
jmpark-swk opened this issue Nov 22, 2021 · 1 comment
Closed

FullEmbeddingDropout works during evaluation #61

jmpark-swk opened this issue Nov 22, 2021 · 1 comment
Assignees
@jrzaurin
Labels
bug

Comments

@jmpark-swk
Copy link

jmpark-swk commented Nov 22, 2021 •
edited

pytorch-widedeep/pytorch_widedeep/models/transformers/_embeddings_layers.py

Line 15 in c287c87

class FullEmbeddingDropout(nn.Module):

#60
There is a bug in which FullEmbeddingDropout operates in both train and evaluation.
@jrzaurin jrzaurin self-assigned this Nov 22, 2021
@jrzaurin jrzaurin added the bug label Nov 22, 2021
jrzaurin added a commit that referenced this issue Nov 23, 2021
@jrzaurin
Fixed #60 and #61. Placing dropout in the right position and applying…
3532a98 
… FullEmbeddingDropout only in training
@jrzaurin
Copy link
Owner

@jmpark-swk just in case, this has not been fixed in the branch https://github.com/jrzaurin/pytorch-widedeep/tree/pmulinka/uncertainty

Soon to be merged to master :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@jrzaurin jrzaurin

Labels
bug
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@jrzaurin @jmpark-swk