[quant][fx][fix] QAT with object_type in qconfig #60555
Closed
Conversation
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
Summary: When we do QAT, we swap the FP32 modules with the corresponding quantized modules counterpart by calling `qat_swap_modules` in prepare. However when we try to look up using the swapped module type in qconfig_dict, we cannot find a match anymore since the qconfig dict contains the original module type. In this PR we get the list of original `modules` dict from the input model before we do swap for QAT Test Plan: python test/test_quantization.py TestQuantizeFx.test_qconfig_qat_module_type Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
💊 CI failures summary and remediationsAs of commit 001f200 (more details on the Dr. CI page and at hud.pytorch.org/pr/60555):
🕵️ 1 new failure recognized by patternsThe following CI failures do not appear to be due to upstream breakages:
|
Summary: When we do QAT, we swap the FP32 modules with the corresponding quantized modules counterpart by calling `qat_swap_modules` in prepare. However when we try to look up using the swapped module type in qconfig_dict, we cannot find a match anymore since the qconfig dict contains the original module type. In this PR we get the list of original `modules` dict from the input model before we do swap for QAT Test Plan: python test/test_quantization.py TestQuantizeFx.test_qconfig_qat_module_type Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
Summary: When we do QAT, we swap the FP32 modules with the corresponding quantized modules counterpart by calling `qat_swap_modules` in prepare. However when we try to look up using the swapped module type in qconfig_dict, we cannot find a match anymore since the qconfig dict contains the original module type. In this PR we get the list of original `modules` dict from the input model before we do swap for QAT Test Plan: python test/test_quantization.py TestQuantizeFx.test_qconfig_qat_module_type Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
Summary: When we do QAT, we swap the FP32 modules with the corresponding quantized modules counterpart by calling `qat_swap_modules` in prepare. However when we try to look up using the swapped module type in qconfig_dict, we cannot find a match anymore since the qconfig dict contains the original module type. In this PR we get the list of original `modules` dict from the input model before we do swap for QAT Test Plan: python test/test_quantization.py TestQuantizeFx.test_qconfig_qat_module_type Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
supriyar
added a commit
that referenced
this pull request
Jun 23, 2021
Summary: When we do QAT, we swap the FP32 modules with the corresponding quantized modules counterpart by calling `qat_swap_modules` in prepare. However when we try to look up using the swapped module type in qconfig_dict, we cannot find a match anymore since the qconfig dict contains the original module type. In this PR we update the qconfig_dict to include the modules swapped for QATT Test Plan: python test/test_quantization.py TestQuantizeFx.test_qconfig_qat_module_type Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: c74cb9a Pull Request resolved: #60555
|
@supriyar has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Codecov Report
@@ Coverage Diff @@
## gh/supriyar/235/base #60555 +/- ##
========================================================
- Coverage 76.24% 76.23% -0.01%
========================================================
Files 2054 2054
Lines 205027 205035 +8
========================================================
- Hits 156322 156310 -12
- Misses 48705 48725 +20 |
|
This pull request has been merged in 1120a1b. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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:
Summary:
When we do QAT, we swap the FP32 modules with the corresponding quantized modules counterpart by calling
qat_swap_modulesin prepare.However when we try to look up using the swapped module type in qconfig_dict, we cannot find a match anymore since the qconfig dict contains the original
module type.
In this PR we update the qconfig_dict to include the modules swapped for QATT
Test Plan:
python test/test_quantization.py TestQuantizeFx.test_qconfig_qat_module_type
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D29337036