[quant][graphmode][fx] Skip observering boolean Tensors #57375
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: Skip observing the input for masked_fill. Currently we don't have a way to query the type of Proxy in GraphModule, hopefully we should have the functionality to annotate the type, we'll need to annotate a Proxy to be a boolean Tensor to remove this hack. Test Plan: python test/test_quantization.py TestQuantizeFxOps.test_boolean_tensor Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
💊 CI failures summary and remediationsAs of commit 13c4695 (more details on the Dr. CI page):
This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions to the (internal) Dr. CI Users group. |
jerryzh168
added a commit
that referenced
this pull request
Apr 30, 2021
Summary: Skip observing the input for masked_fill. Currently we don't have a way to query the type of Proxy in GraphModule, hopefully we should have the functionality to annotate the type, we'll need to annotate a Proxy to be a boolean Tensor to remove this hack. Test Plan: python test/test_quantization.py TestQuantizeFxOps.test_boolean_tensor Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: fa69fca Pull Request resolved: #57375
Summary: Skip observing the input for masked_fill. Currently we don't have a way to query the type of Proxy in GraphModule, hopefully we should have the functionality to annotate the type, we'll need to annotate a Proxy to be a boolean Tensor to remove this hack. Test Plan: python test/test_quantization.py TestQuantizeFxOps.test_boolean_tensor Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D28126003](https://our.internmc.facebook.com/intern/diff/D28126003) [ghstack-poisoned]
Summary: Skip observing the input for masked_fill. Currently we don't have a way to query the type of Proxy in GraphModule, hopefully we should have the functionality to annotate the type, we'll need to annotate a Proxy to be a boolean Tensor to remove this hack. Test Plan: python test/test_quantization.py TestQuantizeFxOps.test_boolean_tensor Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D28126003](https://our.internmc.facebook.com/intern/diff/D28126003) [ghstack-poisoned]
vkuzo
reviewed
Apr 30, 2021
torch/quantization/fx/quantize.py
Outdated
| # it is boolean Tensor | ||
| # TODO: we need type info from proxy, what type of Tensor this is | ||
| # similar to TorchScript | ||
| if (node.op, node.target) == ("call_method", "masked_fill"): |
There was a problem hiding this comment.
could we instead structure this as something like https://github.com/pytorch/pytorch/blob/master/torch/quantization/fx/utils.py#L406,
if second_input_arg_is_boolean_tensor(node):
...
Summary: Skip observing the input for masked_fill. Currently we don't have a way to query the type of Proxy in GraphModule, hopefully we should have the functionality to annotate the type, we'll need to annotate a Proxy to be a boolean Tensor to remove this hack. Test Plan: python test/test_quantization.py TestQuantizeFxOps.test_boolean_tensor Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D28126003](https://our.internmc.facebook.com/intern/diff/D28126003) [ghstack-poisoned]
jerryzh168
added a commit
that referenced
this pull request
Apr 30, 2021
Summary: Skip observing the input for masked_fill. Currently we don't have a way to query the type of Proxy in GraphModule, hopefully we should have the functionality to annotate the type, we'll need to annotate a Proxy to be a boolean Tensor to remove this hack. Test Plan: python test/test_quantization.py TestQuantizeFxOps.test_boolean_tensor Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: dbe46f6 Pull Request resolved: #57375
Codecov Report
@@ Coverage Diff @@
## gh/jerryzh168/590/base #57375 +/- ##
==========================================================
- Coverage 77.63% 77.27% -0.36%
==========================================================
Files 1956 1956
Lines 194841 194853 +12
==========================================================
- Hits 151260 150581 -679
- Misses 43581 44272 +691 |
vkuzo
approved these changes
May 3, 2021
|
This pull request has been merged in 945c93b. |
krshrimali
pushed a commit
to krshrimali/pytorch
that referenced
this pull request
May 19, 2021
Summary: Pull Request resolved: pytorch#57375 Skip observing the input for masked_fill. Currently we don't have a way to query the type of Proxy in GraphModule, hopefully we should have the functionality to annotate the type, we'll need to annotate a Proxy to be a boolean Tensor to remove this hack. Test Plan: python test/test_quantization.py TestQuantizeFxOps.test_boolean_tensor Imported from OSS Reviewed By: vkuzo Differential Revision: D28126003 fbshipit-source-id: 2989766370a607579b3ea07ca36cdc2ce35893cc
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.
Stack from ghstack:
Summary:
Skip observing the input for masked_fill. Currently we don't have a way to
query the type of Proxy in GraphModule, hopefully we should have the functionality to annotate the type,
we'll need to annotate a Proxy to be a boolean Tensor to remove this hack.
Test Plan:
python test/test_quantization.py TestQuantizeFxOps.test_boolean_tensor
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D28126003