Serialization and range reduction support for Fake Quant/Observer#26519
Closed
raghuramank100 wants to merge 12 commits intogh/raghuramank100/28/basefrom
Closed
Serialization and range reduction support for Fake Quant/Observer#26519raghuramank100 wants to merge 12 commits intogh/raghuramank100/28/basefrom
raghuramank100 wants to merge 12 commits intogh/raghuramank100/28/basefrom
Conversation
Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
raghuramank100
pushed a commit
that referenced
this pull request
Sep 20, 2019
Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) ghstack-source-id: 90463022 Pull Request resolved: #26519
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
This was referenced Sep 20, 2019
Closed
jerryzh168
reviewed
Sep 23, 2019
jerryzh168
reviewed
Sep 23, 2019
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
dzhulgakov
requested changes
Sep 23, 2019
| default_fake_quant = FakeQuantize | ||
| def _save_to_state_dict(self, destination, prefix, keep_vars): | ||
| super(FakeQuantize, self)._save_to_state_dict(destination, prefix, keep_vars) | ||
| destination[prefix + 'quant_min'] = self.quant_min |
Collaborator
There was a problem hiding this comment.
interesting, looks like we have a legit use cases for non-Tensor register_buffer (cc @gchanan). No action now, just interesting
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
dzhulgakov
reviewed
Sep 24, 2019
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
raghuramank100
pushed a commit
that referenced
this pull request
Sep 24, 2019
Pull Request resolved: #26519 ghstack-source-id: 90622881 Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/)
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
raghuramank100
pushed a commit
that referenced
this pull request
Sep 24, 2019
Pull Request resolved: #26519 ghstack-source-id: 90701068 Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/)
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
dzhulgakov
reviewed
Sep 24, 2019
supriyar
pushed a commit
to supriyar/pytorch
that referenced
this pull request
Sep 25, 2019
Pull Request resolved: pytorch#26519 ghstack-source-id: 90622881 Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/)
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
dzhulgakov
approved these changes
Sep 26, 2019
Collaborator
dzhulgakov
left a comment
There was a problem hiding this comment.
Looks good, please address nits before landing
| @@ -13,23 +12,20 @@ class FakeQuantize(Module): | |||
| `calcqparam`: A function that calculates quantization parameters | |||
Collaborator
There was a problem hiding this comment.
the docstring is way out of date - please update
Contributor
Author
There was a problem hiding this comment.
Good catch, will update
| self.ch_axis = ch_axis | ||
| self.min_vals = None | ||
| self.max_vals = None | ||
| self.register_buffer('min_vals', None) |
Collaborator
There was a problem hiding this comment.
maybe just register empty tensor? (torch.tensor([])). Then you don't need to override _load_from_state_dict?
Contributor
Author
There was a problem hiding this comment.
Will try that
Contributor
Author
There was a problem hiding this comment.
Doesnt work, so sticking with current approach
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
Contributor
Author
|
@pytorchbot Retest this please |
Contributor
Author
|
@pytorchbot retest this please |
1 similar comment
Contributor
Author
|
@pytorchbot retest this please |
…bserver" Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/) [ghstack-poisoned]
raghuramank100
pushed a commit
that referenced
this pull request
Sep 27, 2019
Pull Request resolved: #26519 ghstack-source-id: 90895631 Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/)
jerryzh168
reviewed
Sep 27, 2019
Contributor
|
This pull request has been merged in b0a2f6f. |
pdlive215
pushed a commit
to pdlive215/pytorch
that referenced
this pull request
Nov 27, 2019
…torch#26519) Summary: Pull Request resolved: pytorch#26519 ghstack-source-id: 90895631 Test Plan: buck test caffe2/test:quantization -- 'test_histogram_observer \(test_quantization\.ObserverTest\)' --print-passing-details and buck test caffe2/test:fake_quant -- 'test_fq_serializable \(test_fake_quant\.TestFakeQuantizePerTensorAffine\)' --print-passing-details Differential Revision: D17217408 fbshipit-source-id: 0da7efdcdae0c065dd035c5dd2b6a78231545ece
xxtEchjovs44
pushed a commit
to xxtEchjovs44/pytorch
that referenced
this pull request
Jan 29, 2020
Pull Request resolved: pytorch/pytorch#26519 ghstack-source-id: 90704280 Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/)
xxtEchjovs44
pushed a commit
to xxtEchjovs44/pytorch
that referenced
this pull request
Jan 29, 2020
Pull Request resolved: pytorch/pytorch#26519 ghstack-source-id: 90905579 Differential Revision: [D17217408](https://our.internmc.facebook.com/intern/diff/D17217408/)
laurentdupin
pushed a commit
to laurentdupin/pytorch
that referenced
this pull request
Apr 24, 2026
…torch#26519) Summary: Pull Request resolved: pytorch#26519 ghstack-source-id: 90895631 Test Plan: buck test caffe2/test:quantization -- 'test_histogram_observer \(test_quantization\.ObserverTest\)' --print-passing-details and buck test caffe2/test:fake_quant -- 'test_fq_serializable \(test_fake_quant\.TestFakeQuantizePerTensorAffine\)' --print-passing-details Differential Revision: D17217408 fbshipit-source-id: 0da7efdcdae0c065dd035c5dd2b6a78231545ece
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
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.
Stack from ghstack:
Differential Revision: D17217408