This repository has been archived by the owner on Jan 22, 2025. It is now read-only.
do not fuse model again for a QAT model #643
Closed
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
|
This pull request was exported from Phabricator. Differential Revision: D52152688 |
stephenyan1231
force-pushed
the
export-D52152688
branch
from
02013f8 to
2281fbb
Compare
|
This pull request was exported from Phabricator. Differential Revision: D52152688 |
stephenyan1231
force-pushed
the
export-D52152688
branch
from
2281fbb to
bade2a9
Compare
|
This pull request was exported from Phabricator. Differential Revision: D52152688 |
stephenyan1231
force-pushed
the
export-D52152688
branch
from
bade2a9 to
5f99792
Compare
|
This pull request was exported from Phabricator. Differential Revision: D52152688 |
stephenyan1231
force-pushed
the
export-D52152688
branch
from
5f99792 to
dee9233
Compare
|
This pull request was exported from Phabricator. Differential Revision: D52152688 |
Summary: For a QAT model, it contains observers. After QAT training, those observers already contain updated statistics, such as min_val, max_val. When we want to export FP32 QAT model for a sanity check, if we call **fuse_utils.fuse_model()** again (which is often already called when we build the QAT model before QAT training), it will remove statistics in the observers. Differential Revision: D52152688
stephenyan1231
force-pushed
the
export-D52152688
branch
from
dee9233 to
bef6ae8
Compare
|
This pull request was exported from Phabricator. Differential Revision: D52152688 |
|
This pull request has been merged in 8f13023. |
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Outdated suggestions cannot be applied.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.
Summary:
For a QAT model, it contains observers. After QAT training, those observers already contain updated statistics, such as min_val, max_val.
When we want to export FP32 QAT model for a sanity check, if we call fuse_utils.fuse_model() again (which is often already called when we build the QAT model before QAT training), it will remove statistics in the observers.
Differential Revision: D52152688