Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add operators necessary for mobilenet #29

Merged
merged 15 commits into from
Mar 31, 2020
Merged

Add operators necessary for mobilenet #29

merged 15 commits into from
Mar 31, 2020

Commits on Mar 24, 2020

  1. feat(//core/conversion/converters/impl/reduce): Mean reduce converter 

    Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 24, 2020
    Configuration menu
    Copy the full SHA
    259aa4c View commit details
    Browse the repository at this point in the history

  2. refactor(//core/conversion/converters): Removing a bunch of boilerplate 

    and add some checking

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 24, 2020
    Configuration menu
    Copy the full SHA
    8ad8fa7 View commit details
    Browse the repository at this point in the history

Commits on Mar 27, 2020

  1. feat(//core/conversion/conversionctx): Move inline function to associate 

    values and tensors to a method in the conversion ctx

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 27, 2020
    Configuration menu
    Copy the full SHA
    6ab9814 View commit details
    Browse the repository at this point in the history

  2. refactor(//core/conversion/converters): Move to key converters by 

    c10::OperatorName allowing support for different converters for
overloaded operators

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 27, 2020
    Configuration menu
    Copy the full SHA
    298b5bb View commit details
    Browse the repository at this point in the history

  3. refactor(//core/conversion): Now check to make sure all node outputs 

    have tensor matches, and move to checking with execptions instead of
bool returns for the conversion stage

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 27, 2020
    Configuration menu
    Copy the full SHA
    de8659b View commit details
    Browse the repository at this point in the history

  4. feat(//core/conversion/converters/impl): Non dimensional reduce 

    converter

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 27, 2020
    Configuration menu
    Copy the full SHA
    ccab7b9 View commit details
    Browse the repository at this point in the history

  5. doc(//tests): Add suggested settings for running the full test suite so 

    as to not exhaust GPU memory

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 27, 2020
    Configuration menu
    Copy the full SHA
    36b2eb4 View commit details
    Browse the repository at this point in the history

Commits on Mar 28, 2020

  1. fix(//core/conversion/converters/impl/linear): In inserting flatten for 

    layers other than conv, did not remove batch size from tensor shape

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 28, 2020
    Configuration menu
    Copy the full SHA
    377ad67 View commit details
    Browse the repository at this point in the history

  2. fix(//core/conversion/converters/impl/reduce): Adds support for multiple 

    reduction dimensions

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 28, 2020
    Configuration menu
    Copy the full SHA
    7622a97 View commit details
    Browse the repository at this point in the history

Commits on Mar 30, 2020

  1. refactor(//tests): Relax threshold for module tests 

    Perhaps revisit in the future to see if we can reduce this back

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 30, 2020
    Configuration menu
    Copy the full SHA
    d1270d9 View commit details
    Browse the repository at this point in the history

  2. fix(//tests/modules): Remove an old script 

    Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 30, 2020
    Configuration menu
    Copy the full SHA
    8be79e1 View commit details
    Browse the repository at this point in the history

  3. feat(//core/conversion/converter/Arg): Add typechecking to the unwrap 

    functions

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 30, 2020
    Configuration menu
    Copy the full SHA
    73bfd4c View commit details
    Browse the repository at this point in the history

  4. feat(hardtanh): Adds support for the the hard tanh operator 

    Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 30, 2020
    Configuration menu
    Copy the full SHA
    391af52 View commit details
    Browse the repository at this point in the history

Commits on Mar 31, 2020

  1. feat(//core/conversion/converters/impl/reduce): adds the rest of TRT's 

    basic reduction operators

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 31, 2020
    Configuration menu
    Copy the full SHA
    956b0c5 View commit details
    Browse the repository at this point in the history

  2. refactor(//core/conversion/converters/impl/element_wise): remove some 

    old comments

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
    @narendasan
    narendasan committed Mar 31, 2020
    Configuration menu
    Copy the full SHA
    ca42ef5 View commit details
    Browse the repository at this point in the history