Fix Detr batchsize 1 - Explicitly reshape target classes #552
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
facebook-github-bot
added
the
CLA Signed
|
@padentomasello has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
|
@padentomasello has updated the pull request. You must reimport the pull request before landing. |
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Outdated suggestions cannot be applied.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.
Some weird arrayfire behavior allows you to assign arrays of different dimensions but only if the dimensions are * not * singlular for the other dimensions.
For example, below, with batch_size 2, and num boxes 3, target_classes_full is { 100, 3 } and targetClassesi is { 1, 3 }. srcIdxs = { 3, 1 } . target_classes_full(srcIdxs, i) = targetClassesi is fine. (Arrayfire can assign to { 3, 1} from { 1, 3}.
For whatever reason, with batch_size 1, and num boxes 3, target_classes_full is now { 100, 1 } and like before targetClassesi is { 1, 3 }. srcIdxs = { 3, 1 } . target_classes_full(srcIdxs, i) = targetClassesi now fails. (Arrayfire cannot assign to { 3, 1} from { 1, 3 }.
Anyway, probably better to be explicit.