Change datamodule input to [0,1] scale #203
Open
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
This reverts commit de77a9d.
15 tasks
mzweilin
changed the base branch from
generalized_adversary
to
add_adv_batch_converter
dxoigmn
reviewed
Aug 31, 2023
There was a problem hiding this comment.
Probably should add 8bit to filename somewhere.
There was a problem hiding this comment.
Rename as times_255_and_round.yaml in 2b0ef2b
There was a problem hiding this comment.
Rename to normalize or something like that?
There was a problem hiding this comment.
Renamed to divided_by_255.yaml in 2b0ef2b
mart/configs/attack/data_coco.yaml
Outdated
mzweilin
changed the base branch from
main
to
mzweilin/upgrade_pre-commit_flake8
|
@dxoigmn This PR is ready to review again. It should simplify input transforms in our existing datamodules. |
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Outdated suggestions cannot be applied.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.
What does this PR do?
This PR makes datamodule give input in the [0,1] scale, so that it is compatible with many other existing tools.
transformanduntransforminAdversaryso we still use epsilon in integer.preprocessorin models that were used for transforming input from [0,255].Type of change
Please check all relevant options.
Testing
Please describe the tests that you ran to verify your changes. Consider listing any relevant details of your test configuration.
pytestCUDA_VISIBLE_DEVICES=0 python -m mart experiment=CIFAR10_CNN_Adv trainer=gpu trainer.precision=16reports 70% (21 sec/epoch).CUDA_VISIBLE_DEVICES=0,1 python -m mart experiment=CIFAR10_CNN_Adv trainer=ddp trainer.precision=16 trainer.devices=2 model.optimizer.lr=0.2 trainer.max_steps=2925 datamodule.ims_per_batch=256 datamodule.world_size=2reports 70% (14 sec/epoch).Before submitting
pre-commit run -acommand without errorsDid you have fun?
Make sure you had fun coding 🙃