-
Notifications
You must be signed in to change notification settings - Fork 21.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in qat #46738
Closed
Closed
Changes from all commits
Commits
Show all changes
7 commits
Select commit
Hold shift + click to select a range
39e4750
[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in qat
jerryzh168 5c038f8
Update on "[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in…
jerryzh168 2a2a061
Update on "[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in…
jerryzh168 a301fe6
Update on "[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in…
jerryzh168 374cffc
Update on "[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in…
jerryzh168 85a777e
Update on "[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in…
jerryzh168 4a1d3b6
Update on "[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in…
jerryzh168 File filter
Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
There are no files selected for viewing
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
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
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
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
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
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
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Does the approach here also work for cases where the scale and zero-point are not fixed? i.e for a hardTanh, the scale and zero-point depend on the arguments to init.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
maybe, this allows to provide special fake quantize(activation_post_process) for a specific pattern (module/functional/torch op), could you write down the details, is it like following?
I think this should be too hard to support in current implementation.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actually for hardtanh, our implementation calls qclamp:
pytorch/aten/src/ATen/native/quantized/cpu/qclamp.cpp
Line 24 in 87a4baf
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
yeah this is how it is implemented right now: https://github.com/pytorch/pytorch/blob/master/torch/quantization/fx/quantization_patterns.py#L512