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This repository has been archived by the owner on Nov 17, 2023.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

Fix quantized concat when inputs are mixed int8 and uint8 #15693

Merged
merged 1 commit into from
Aug 1, 2019

Conversation

ZhennanQin
Copy link
Contributor

@ZhennanQin ZhennanQin commented Jul 30, 2019

Description

mkldnn doesn't support mixed int8 and uint8 as concat input. So we need to convert uint8 to int8 for this case.

@pengzhao-intel @TaoLv

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

@piyushghai
Copy link
Contributor

@mxnet-label-bot Add [MKLDNN, Quantization]

@marcoabreu marcoabreu added MKLDNN Quantization Issues/Feature Requests related to Quantization labels Jul 31, 2019
@pengzhao-intel
Copy link
Contributor

@ZhennanQin which topologies are used this concat?

@xinyu-intel
Copy link
Contributor

@pengzhao-intel NCF and GluonCV SSD

Copy link
Contributor

@cchung100m cchung100m left a comment

Choose a reason for hiding this comment

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

LGTM

@pengzhao-intel
Copy link
Contributor

Merging now. Thanks for your contribution.

@pengzhao-intel pengzhao-intel merged commit 773f4dc into apache:master Aug 1, 2019
anirudhacharya pushed a commit to anirudhacharya/mxnet that referenced this pull request Aug 20, 2019
@ZhennanQin ZhennanQin deleted the fix_concat branch September 16, 2019 07:00
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
MKLDNN Quantization Issues/Feature Requests related to Quantization
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants