[AutoMM] Improve DINO performance #3970
Merged
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
zhiqiangdon
reviewed
Mar 9, 2024
zhiqiangdon
reviewed
Mar 10, 2024
Comment on lines
71
to
74
| self.frozen_layers = frozen_layers | ||
| # Based on our offline benchmarking results, instead of freezing layers, | ||
| # Setting backbone to a smaller learning rate achieves better results, | ||
| self.frozen_layers = [] | ||
| self.backbone_layers = frozen_layers |
There was a problem hiding this comment.
- Assigning
frozen_layerstobackbone_layerslooks confusing. How about having a new attributebackbone_layers? - This change also deprecates the previous functionality of supporting freezing layers. Is this deprecation a good choice? Maybe we still support freezing layers as a choice.
There was a problem hiding this comment.
Normally frozen_layers and backbone_layers should refer to the same layers. It's just are we freezing the backbone layers or using a small lr. Adding a new hyperparameter seems redundant.
There was a problem hiding this comment.
I think we need to make names clear to improve code readability. Otherwise, others probably can't understand them correctly. If we no longer support freezing layers, then we should remove it to reduce confusion.
There was a problem hiding this comment.
Sent an up date to remain frozen layers, and set up backbone to have low lr for dino
|
Job PR-3970-99a4181 is done. |
zhiqiangdon
approved these changes
Mar 12, 2024
ddelange
added a commit
to ddelange/autogluon
that referenced
this pull request
Mar 21, 2024
…tch-4 * 'master' of https://github.com/awslabs/autogluon: (46 commits) [core] move transformers to setup_utils, bump dependency version (autogluon#3984) [AutoMM] Fix one lightning upgrade issue (autogluon#3991) [CI][Feature] Create a package version table (autogluon#3972) [v.1.1][Upgrade] PyTorch 2.1 and CUDA 12.1 upgrade (autogluon#3982) [WIP] Code implementation of Conv-LoRA (autogluon#3933) [timeseries] Ensure that all metrics handle missing values in the target (autogluon#3966) [timeseries] Fix path and device bugs (autogluon#3979) [AutoMM]Remove grounding-dino (autogluon#3974) [Docs] Update install modules content (autogluon#3976) Add note on pd.to_datetime (autogluon#3975) [AutoMM] Improve DINO performance (autogluon#3970) Minor correction in differ to pick correct environment (autogluon#3968) Fix windows python 3.11 issue by removing ray (autogluon#3956) [CI][Feature] Package Version Comparator (autogluon#3962) [timeseries] Add support for categorical covariates (autogluon#3874) [timeseries] Add method for plotting forecasts (autogluon#3889) Update conf.py copyright to reflect current year (autogluon#3932) [Timeseries][CI]Refactor CI to skip AutoMM and Tabular tests w.r.t timeseries changes (autogluon#3942) Fix HPO crash in memory check (autogluon#3931) [AutoMM][CI] Capping scikit-learn to avoid HPO test failure (autogluon#3947) ...
LennartPurucker
pushed a commit
to LennartPurucker/autogluon
that referenced
this pull request
Jun 1, 2024
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.
Update the settings to which used in automl maper
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.