This repository has been archived by the owner on Mar 12, 2024. It is now read-only.
Reduce the space complexity of the HungarianMatcher module. #606
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
aioaneid
force-pushed
the
optimize-hungarian-matcher
branch
from
eff320f
to
4833f70
Compare
aioaneid
changed the title
The memory reduction factor of the cost matrix is sum(#target objects) / max(#target objects). That is achieved by no longer computing and storing matching costs between predictions and targets at different positions inside the batch. More exactly the original matrix of shape [batch_size * queries, sum(#target objects)] is shrinked to a tensor of shape [batch_size, queries, max(#target objects)]. Besides allowing much larger batch sizes, tested on the table structure recognition task using the Table Transformer (TATR) (125 queries, 7 classes) with pubmed data, this change also results a) on CUDA at all batch sizes and on CPU with small batchs in a small but meaningful speedup, b) on CPU with larger batch sizes in much higher speedups. The processing time decrease computed as (1 - new_time / old_time) is shown below in various configuration: Batch | Device size | cuda cpu ------------------ 1 8.2% 1.6% 2 1.6% 9.3% 3 1.6% 7.7% 4 0.9% 11.2% 5 0.8% 13.9% 6 0.9% 15.5% 7 0.9% 23.1% 8 47.1% 16 70.6% 32 88.3% 64 95.0%
aioaneid
force-pushed
the
optimize-hungarian-matcher
branch
from
4833f70
to
3c2927d
Compare
aioaneid
changed the title
aioaneid
changed the title
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
The memory reduction factor of the cost matrix is sum(#target objects) / max(#target objects).
That is achieved by no longer computing and storing matching costs between predictions and targets at different positions inside the batch. More exactly the original matrix of shape [batch_size * queries, sum(#target objects)] is shrinked to a tensor of shape [batch_size, queries, max(#target objects)].
Besides allowing much larger batch sizes, tested on the table structure recognition task using the Table Transformer (TATR) (125 queries, 7 classes) with Pubmed data, this change also results a) on CUDA at all batch sizes and on CPU with small batches in a small but meaningful speedup, b) on CPU with larger batch sizes in much higher speedups.
The processing time reduction computed as (1 - new_time / old_time) is shown below in various configurations: