Fix: Learner.show_results uses passed dataloader via dl_idx or dl arguments #3554
+3
−3
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
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
Many thanks! |
warner-benjamin
added a commit
to warner-benjamin/fastai
that referenced
this pull request
Jan 19, 2022
kwsp
pushed a commit
to kwsp/fastai
that referenced
this pull request
Jan 25, 2022
Co-authored-by: Benjamin Warner <me@benjaminwarner.dev>
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Outdated suggestions cannot be applied.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.
Changes
Learner.show_resultsfrom being hardcoded to use the training dataloader'sshow_resultsto use the dataloader passed toLearner.show_resultsviadl_idxordlarguments.Resolves an issue when the train and valid dataloaders differ, which could result in the incorrect decodes being applied to valid inputs. For example, when training on image sub-patches and during validation combining patches to form a whole image.