[quant][graphmode] Add tests for script models got from tracing and fix issues #30210
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: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…acing" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…acing" Summary: att Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…acing and fix the issues" Summary: Changes to make tracing work 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 3. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
changed the title
…acing and fix the issues" Summary: Changes to make tracing work 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 3. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…acing and fix the issues" Summary: Changes to make tracing work 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 3. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
changed the title
…acing and fix issues" Summary: Changes to make tracing work 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 4. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…acing and fix issues" Summary: Changes to make quantizing traced model work: 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 4. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…acing and fix issues" Summary: Changes to make quantizing traced model work: 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 4. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…acing and fix issues" Summary: Changes to make quantizing traced model work: 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 4. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
…acing and fix issues" Summary: Changes to make quantizing traced model work: 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 4. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Nov 26, 2019
…ix issues Summary: Changes to make quantizing traced model work: 0. aten::_convolution(landed by Lingyi) 1. Added ConstantPooling for traced graph to merge redundant constant nodes 2. Added FuseLinear to fuse exploded linear function into `aten::linear` 3. Refactored the code to identify weight and bias 4. Added weight/bias identification for aten::linear Test Plan: python test/test_quantization.py Reviewers: pt1quant Subscribers: Tasks: Tags: ghstack-source-id: b40d002 Pull Request resolved: #30210
ZolotukhinM
suggested changes
Nov 26, 2019
There was a problem hiding this comment.
This PR has too many independent changes piled in and is hard to review because of that. Please split out those changes into individual PRs (e.g.: 1) renaming stuff in tests without changing logic and formatting stuff, 2) factoring out isAtenFuncNthArg, 3) invoking more passes in insertObservers, 4)... )
|
deprecated by stack: #30473 |
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:
Changes to make quantizing traced model work:
aten::linearTest Plan:
python test/test_quantization.py
Reviewers:
pt1quant
Subscribers:
Tasks:
Tags: