allow to load pretrained weights when the include_top variable is False #290
Conversation
This file contains hidden or 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
|
Why hasn't this been merged yet? A simple solution to a problem affecting many users. |
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Outdated suggestions cannot be applied.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.
This merge request is related to the bug #278
The class initialization is failed when called using
from_pretrained(.., include_top=False)function or when the number of classes is not equal to 1000, i.e.from_pretrained(.., num_classes=100).This pull request allow to load the pre-trained weights even when the number of classes is not equal to 1000 or when the top classifier is ignored.
_fc.weightand_fc.biaswill only be loaded wheninclude_top=Trueandnum_classes=1000(default values)