MultiPredictor.predict_raw: pass on batch_size, too #361
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
|
What is still lacking in Calamari 1 is batch size bucketing as provided by TF2/tfaip in Calamari 2. It's easy to get OOM if the batch includes images with a large width (esp. if they also have low height and thus have to be scaled up for target height), due to zero padding. In those cases, the batch should be split up... |
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Outdated suggestions cannot be applied.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 has been overlooked. When using
MultiPredictor.predict_rawin C1, you had to do a workaround (likeitertools.batched) to prevent OOM. This just passes on thebatch_sizekwarg toPredictor.predict_raw.