Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

[Quantization] Support zero-size tensor input for quantization flow #15031

Merged
merged 4 commits into from
May 23, 2019
Merged

[Quantization] Support zero-size tensor input for quantization flow #15031

merged 4 commits into from
May 23, 2019

Conversation

ciyongch
Copy link
Contributor

Description

This PR is to support zero-size tensor input for quantization flow.
Let's take RNN related model as an example, the begin_state is always initialized into shape (0, self._num_hidden), it worked well in FP32 pass, but failed in INT8 pass due to unknown dimension error with latest MXNet code base.
With this patch, models with such inputs are able to be quantized and run in INT8 mode.

@pengzhao-intel @TaoLv @ZhennanQin

Checklist

Essentials

Please feel free to remove inapplicable items for your PR.

  • The PR title starts with [MXNET-$JIRA_ID], where $JIRA_ID refers to the relevant JIRA issue created (except PRs with tiny changes)
  • Changes are complete (i.e. I finished coding on this PR)
  • All changes have test coverage:
  • Unit tests are added for small changes to verify correctness (e.g. adding a new operator)
  • Nightly tests are added for complicated/long-running ones (e.g. changing distributed kvstore)
  • Build tests will be added for build configuration changes (e.g. adding a new build option with NCCL)
  • Code is well-documented:
  • For user-facing API changes, API doc string has been updated.
  • For new C++ functions in header files, their functionalities and arguments are documented.
  • For new examples, README.md is added to explain the what the example does, the source of the dataset, expected performance on test set and reference to the original paper if applicable
  • Check the API doc at http://mxnet-ci-doc.s3-accelerate.dualstack.amazonaws.com/PR-$PR_ID/$BUILD_ID/index.html
  • To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change

Changes

  • Feature1, tests, (and when applicable, API doc)
  • Feature2, tests, (and when applicable, API doc)

Comments

  • If this change is a backward incompatible change, why must this change be made.
  • Interesting edge cases to note here

@pengzhao-intel
Copy link
Contributor

@ZhennanQin @TaoLv @xinyu-intel please help take a review.

@pengzhao-intel
Copy link
Contributor

Please also add a test case

@pengzhao-intel pengzhao-intel mentioned this pull request May 22, 2019
Closed
@pengzhao-intel pengzhao-intel mentioned this pull request May 22, 2019
Closed
@ciyongch ciyongch force-pushed the zero-size-quantization branch from 652af82 to bc9760c Compare May 22, 2019 11:05
@ciyongch
Copy link
Contributor Author

@pengzhao-intel @TaoLv test case is added, redundant file is remove. Please help to review again:)

pengzhao-intel
pengzhao-intel approved these changes May 22, 2019
View reviewed changes
Copy link
Contributor

@pengzhao-intel pengzhao-intel left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the improvements.

LGTM

@ZhennanQin
Copy link
Contributor

LGTM.

@pengzhao-intel
Copy link
Contributor

Thanks for your contribution. Merging now.

@pengzhao-intel pengzhao-intel merged commit d4e458e into apache:master May 23, 2019
haohuanw pushed a commit to haohuanw/incubator-mxnet that referenced this pull request Jun 23, 2019
@ciyongch
[Quantization] Support zero-size tensor input for quantization flow (a…
f39b0cc 
…pache#15031)

* [Quantization] Support zero-size tensor input for quantization flow

* Comment out quantized_act and quantized_sum

* retrigger CI

* Add test cases
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers

@pengzhao-intel pengzhao-intel pengzhao-intel approved these changes

@TaoLv TaoLv TaoLv approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@ciyongch @pengzhao-intel @ZhennanQin @TaoLv