Upgrade dependency to torchmetrics == 1.0.1 #205
Merged
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
mzweilin
added a commit
that referenced
this pull request
Jul 20, 2023
mzweilin
added a commit
that referenced
this pull request
Aug 1, 2023
mzweilin
added a commit
that referenced
this pull request
Aug 25, 2023
* Initial implementation of adversarial training callback * Make callback work in CPU * style * Add and use on_after_batch_transfer hook * Override on_after_batch_transfer in callback setup * Restore on_after_batch_transfer hook in teardown * cleanup * Call original on_after_batch_transfer hook * Move Adversary.attack into callback * Upgrade dependency to torchmetrics == 1.0.1 (#205) * Move adversary out of the model sequence. * Make an adversarial training/evaluation callback. * Remove stuff that is related to callback entry points. * Replace model wrapper with a configurable model_transform. * Comment. * Rename as train/val/test. * Rename the callback to AdversaryConnector because we may not perform adversarial training by allowing train_adversary=None. * Rename config: adversarial_training -> adversary_connector. * Add configure_model() and simplify batch in Adversary. * Delete Adversary.get_input_adv(). * Move model_transform() to configure_model(). * Add model back to attack batch, because we don't want to wrap LightningModule inside a LightningModule in case of Trainer interference. * Move LightningModuleAsTarget logic into Adversary. * Leave model_transform() for future PRs. * Expand get_input_adv(). * Fix visualizer test. --------- Co-authored-by: Cory Cornelius <[email protected]>
mzweilin
added a commit
that referenced
this pull request
Aug 31, 2023
* Initial implementation of adversarial training callback * Make callback work in CPU * style * Add and use on_after_batch_transfer hook * Override on_after_batch_transfer in callback setup * Restore on_after_batch_transfer hook in teardown * cleanup * Call original on_after_batch_transfer hook * Move Adversary.attack into callback * Upgrade dependency to torchmetrics == 1.0.1 (#205) * Move adversary out of the model sequence. * Make an adversarial training/evaluation callback. * Remove stuff that is related to callback entry points. * Replace model wrapper with a configurable model_transform. * Add Adversary.batch_converter(). * Comment. * Rename as train/val/test. * Rename the callback to AdversaryConnector because we may not perform adversarial training by allowing train_adversary=None. * Rename config: adversarial_training -> adversary_connector. * Update comments. * Remove model_transform, again. * Comment. * Comments. * Rename batch_converter as batch_c15n. * Replace the _transformed suffix with the _orig suffix, because _orig is rare. * Seperate fit() from forward() in Adversary. * Always require batch canonicalizatoin in Adversary.forward(). * Always enforce the threat model in Adversary.forward(). * adversary.forward() -> adversary(). * Allow None enforcer. --------- Co-authored-by: Cory Cornelius <[email protected]>
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?
Upgrade to
torchmetrics v1.0.1because it fixes a bug in AveragePrecision: Lightning-AI/torchmetrics#1913Type 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 🙃