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This repository has been archived by the owner on Nov 17, 2023.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

Add quantization support for GluonCV #15754

Merged
merged 21 commits into from
Aug 7, 2019
Merged

Add quantization support for GluonCV #15754

merged 21 commits into from
Aug 7, 2019

Conversation

xinyu-intel
Copy link
Contributor

Description

Add a User-level API for Gluon users to generate a quantized SymbolBlock from a FP32 HybridBlock w/ or w/o calibration.

@zhreshold @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

@xinyu-intel xinyu-intel requested a review from szha as a code owner August 5, 2019 07:06
@pengzhao-intel pengzhao-intel added MKLDNN Quantization Issues/Feature Requests related to Quantization labels Aug 5, 2019
@xinyu-intel xinyu-intel mentioned this pull request Aug 5, 2019
Merged
zhreshold
zhreshold approved these changes Aug 5, 2019
View reviewed changes
python/mxnet/contrib/quantization.py

with TemporaryDirectory() as tmpdirname:
prefix = os.path.join(tmpdirname, 'tmp')
network.export(prefix, epoch=0)
Copy link
Member

Choose a reason for hiding this comment

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

I feel like it's more convenient to allow export return (sym, arg_params, aux_params) so we can avoid using temporary file.

Copy link
Member

Choose a reason for hiding this comment

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

It's no mandatory and urgent now, but gluoncv also has the same implementation

Copy link
Contributor Author

Choose a reason for hiding this comment

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

agree, will enhance them later to make it more easier to switch between symbolic and block:)

pengzhao-intel
pengzhao-intel approved these changes Aug 7, 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.

LGTM

@pengzhao-intel pengzhao-intel merged commit ce62873 into apache:master Aug 7, 2019
anirudhacharya pushed a commit to anirudhacharya/mxnet that referenced this pull request Aug 20, 2019
@xinyu-intel
Add quantization support for GluonCV (apache#15754)
2de9674 
* enhance quantization api

* integrate gluoncv solution

* support gluon ssd

* enhance api

* [TODO]split to another PR

* enhance example script

* add wildcard match for exclude layers

* support int8 dtype parameter

* enable dataiter api

* use try method

* add unit test for quantize gluon

* fix lint

* fix lint 2

* fix temporary directory in python2

* fix lint

* fix try import and add todo

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

@zhreshold zhreshold zhreshold approved these changes

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

@szha szha Awaiting requested review from szha szha is a code owner

Assignees
No one assigned
Labels
MKLDNN Quantization Issues/Feature Requests related to Quantization
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@xinyu-intel @zhreshold @pengzhao-intel