Bug/sg 861 decouple qat from train from config #1001
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
shaydeci
requested review from
ofrimasad,
BloodAxe and
Louis-Dupont
as code owners
…in_from_config' into bug/SG-861_decouple_qat_from_train_from_config
There was a problem hiding this comment.
Looks great!
I wrote a small note about naming (non-blocking)
Other than that I think we should also add this as a "quickstart" section in the ptq/qat tutorial: https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/ptq_qat.md
…in_from_config' into bug/SG-861_decouple_qat_from_train_from_config
geoffrey-g-delhomme
pushed a commit
to geoffrey-g-delhomme/super-gradients
that referenced
this pull request
May 26, 2023
* adde unit tests * changed local * switch to ema model before quantization if exists * midifying method complete * midifying method cal in pre launch callback * removed option to get the defaults from previous training * added unit tests passing * updated docs and test names * moved logger init * comments resolved
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Outdated suggestions cannot be applied.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 PR decouples QAT/PTQ from train_from_config.
The goal is to let users launch PTQ/QAT using Python instead of CLI + configs, while using as much defaults as possible.
Note that automatic adaptation of the parameters using the best practices is the users responsibilty when they choose to launch this way, since the new "quantize" method I added can expect objects rather then parameters.