Reland "[pytorch][PR] Support dataclasses in TorchScript" #74353
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
8000
CI Flow Status⚛️ CI FlowRuleset - Version:
|
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit c1dd25a (more details on the Dr. CI page): 💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
|
This pull request was exported from Phabricator. Differential Revision: D34808842 |
|
This pull request was exported from Phabricator. Differential Revision: D34808842 |
zhxchen17
approved these changes
Mar 24, 2022
|
This pull request was exported from Phabricator. Differential Revision: D34808842 |
) Summary: Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D34808842 fbshipit-source-id: aafbb475733a87fb12b6d6cd0d39fb93caf14d13
|
This pull request was exported from Phabricator. Differential Revision: D34808842 |
facebook-github-bot
pushed a commit
that referenced
this pull request
Mar 25, 2022
Summary: Pull Request resolved: #74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes #72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D34808842 fbshipit-source-id: 02f807cff1ea99e606333960225c71a239743a4b
|
Hey @qihqi. |
|
this PR has been reverted since it broke the following test: linux-bionic-py3.7-clang9-slow / test (slow, 1, 1, linux.2xlarge) (https://github.com/pytorch/pytorch/runs/5688066518?check_suite_focus=true) please fix it and re-land |
shahofblah
pushed a commit
that referenced
this pull request
Mar 25, 2022
Summary: Pull Request resolved: #74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes #72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D34808842 fbshipit-source-id: 02f807cff1ea99e606333960225c71a239743a4b (cherry picked from commit ec885a2)
|
This pull request has been reverted by 3b3bdfd. To re-land this change, please open another pull request, assignthe same reviewers, fix the CI failures that caused the revert and make sure that the failing CI runs on the PR by applying the proper ciflow label (e.g., ciflow/trunk). |
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
Mar 30, 2022
…orch#74889) Summary: Pull Request resolved: pytorch#74889 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Differential Revision: D35206262 fbshipit-source-id: f149bba6bb5203aaed7a022f4a3fd702abc95b52
|
This pull request has been reverted by 3b3bdfd. To re-land this change, please open another pull request, assignthe same reviewers, fix the CI failures that caused the revert and make sure that the failing CI runs on the PR by applying the proper ciflow label (e.g., ciflow/trunk). |
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
Mar 30, 2022
…orch#74889) Summary: Pull Request resolved: pytorch#74889 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Differential Revision: D35206262 fbshipit-source-id: 55f14913d76620ddcd8bfa9f8b1c52488c7263c6
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
Mar 30, 2022
…orch#74889) Summary: Pull Request resolved: pytorch#74889 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Differential Revision: D35206262 fbshipit-source-id: 55f14913d76620ddcd8bfa9f8b1c52488c7263c6
pytorchmergebot
pushed a commit
that referenced
this pull request
Mar 31, 2022
) Summary: Pull Request resolved: #74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes #72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Differential Revision: D35206262 Pull Request resolved: #74889 Approved by: https://github.com/zhxchen17
|
Hey @qihqi. |
|
This broke slow tests, see https://github.com/pytorch/pytorch/runs/5763579312?check_suite_focus=true, reverting |
malfet
added a commit
that referenced
this pull request
Mar 31, 2022
…e 2 (#74353)" This reverts commit 5547741. Reverted #74889 on behalf of https://github.com/malfet
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
May 3, 2022
…orch#74353) (pytorch#76771) Summary: Pull Request resolved: pytorch#76771 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: pytorch#74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: ed96735d11b1c9a996dc68c2cfc5bdff7797822b
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
May 4, 2022
…orch#74353) (pytorch#76771) Summary: Pull Request resolved: pytorch#76771 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: pytorch#74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: f25380d72306205cfaf41cd99b2d6c98830e9bed
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
May 4, 2022
…orch#74353) (pytorch#76771) Summary: Pull Request resolved: pytorch#76771 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: pytorch#74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: 3b72e24907f792592a74f3ac922684d4c6db73a2
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
May 21, 2022
…orch#74353) (pytorch#76771) Summary: Pull Request resolved: pytorch#76771 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: pytorch#74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/ F438 contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: 3b72e24907f792592a74f3ac922684d4c6db73a2
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
Jun 6, 2022
…orch#74353) (pytorch#76771) Summary: Pull Request resolved: pytorch#76771 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: pytorch#74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: 3b72e24907f792592a74f3ac922684d4c6db73a2
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
Jun 7, 2022
…orch#74353) (pytorch#76771) Summary: Pull Request resolved: pytorch#76771 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: pytorch#74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: 3b72e24907f792592a74f3ac922684d4c6db73a2
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
Jun 7, 2022
…orch#74353) (pytorch#76771) Summary: Pull Request resolved: pytorch#76771 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: pytorch#74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: 3b72e24907f792592a74f3ac922684d4c6db73a2
qihqi
added a commit
to qihqi/pytorch
that referenced
this pull request
Jun 7, 2022
…orch#74353) (pytorch#76771) Summary: Pull Request resolved: pytorch#76771 Pull Request resolved: pytorch#74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. Fixes pytorch#72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: pytorch#74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: 3b72e24907f792592a74f3ac922684d4c6db73a2
pytorchmergebot
pushed a commit
that referenced
this pull request
Jun 7, 2022
) (#74353) (#76771) Summary: Pull Request resolved: #74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes #72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. Pull Request resolved: #74889 Test Plan: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: zhxchen17 Differential Revision: D35206262 Pulled By: qihqi Pull Request resolved: #76771 Approved by: https://github.com/seemethere
|
Hey @qihqi. |
facebook-github-bot
pushed a commit
that referenced
this pull request
Jun 8, 2022
…#76771) (#74353) Summary: Pull Request resolved: #74353 Repatched `d00de0d43598522b8f6ab2de553b6aaf6768faa5` by Nora Belrose (norabelrose). With following changes: * Register fake source of generated methods in linecache so that inspect.get_source will succeed. * this patching is only triggered if the given dataclass passed to torch.jit.script previously. Effectively we make this feature opt-in. ## Original Summary: Fixes #72901. Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this. What's supported Synthesized __init__, __eq__, and the comparison magic methods when order=True is set on the dataclass decorator Default values for fields __post_init__, including using InitVar fields inside of __post_init__, on Python 3.8+ Overriding __eq__ or any of the comparison magic methods to provide your own implementation What's not supported Default factory initializers for fields Frozen dataclasses InitVar on Python 3.7 __repr__ and __hash__ (these are actually implemented, but the TorchScript interpreter won't call them) Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement __ne__ to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by __eq__ if there's no __ne__. Dataclasses don't actually synthesize an __ne__ method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment. #74889 #76771 Approved by: https://github.com/seemethere Test Plan: contbuild & OSS CI, see https://hud.pytorch.org/commit/pytorch/pytorch/13dff3b2c2f2420f6458804dcc80ded5598636ab Test plan from GitHub: unittest Also run previously failed test: ``` buck test mode/dev-nosan //fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests -- --exact 'fblearner/flow/projects/fluent2/definition/transformers/contrib/faim/test:tests - test_mixmatch_multiclass (fblearner.flow.projects.fluent2.definition.transformers.contrib.faim.test.faim_mixmatch_test.TestFaimTransformerMixMatch)' ``` passes Reviewed By: seemethere, osalpekar, zhxchen17 Differential Revision: D35206262 Pulled By: qihqi fbshipit-source-id: 4b43477930f99ca2dd26073c0ec60f19bb4c8372
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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:
Repatched
d00de0d43598522b8f6ab2de553b6aaf6768faa5by Nora Belrose (norabelrose). With following changes:Original Summary:
Fixes #72901.
Since we can't get access to the source code for synthesized magic methods on dataclasses, we have to synthesize our own versions. torch/jit/_dataclass_impls.py has the code that does this.
What's supported
Synthesized init, eq, and the comparison magic methods when order=True is set on the dataclass decorator
Default values for fields
post_init, including using InitVar fields inside of post_init, on Python 3.8+
Overriding eq or any of the comparison magic methods to provide your own implementation
What's not supported
Default factory initializers for fields
Frozen dataclasses
InitVar on Python 3.7
repr and hash (these are actually implemented, but the TorchScript interpreter won't call them)
Using the != operator on dataclasses inside TorchScript; this is because TorchScript requires that you implement ne to use this operator, whereas in regular Python the != operator will resolve to the negation of whatever is returned by eq if there's no ne. Dataclasses don't actually synthesize an ne method for this reason. I've been toying with different ways to fix this but != is not working in this PR at the moment.
Test Plan:
unittest
Also run previously failed test:
passes
Differential Revision: D34808842