Allow loading custom weights files for EfficientNet #259
+20
−11
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
IanButterworth
force-pushed
the
ib/efficientnet_custom_pretrain
branch
from
7a93dfa
to
bac14c0
Compare
2 tasks
|
This generally makes sense to me, can you think of any way taking a string path could limit us further down the line @darsnack @theabhirath ? |
|
There was a plan to open up the But I think the way this is implemented, it should be easy to add that case down the line. Looks good to me! I guess the only suggestion is to add this feature to other models as well for consistency. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Intends to make it possible to load custom pretrained EfficientNet models.
Opening this PR as a draft to see if there are opinions as I am unfamiliar with this package.
PR Checklist