-
Notifications
You must be signed in to change notification settings - Fork 3.4k
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.
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
[TFLite] Add support to int16 data type in TFLite frontend #10915
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @leandron, looks good to me!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good, thanks for adding the int16 support @leandron! Do you know if there any int16 models around by any chance we could test?
d1d1311
to
8940807
Compare
Add support for int16 data type and int64 biases/accumulators in the TFLite frontend. Adjusts TFLite tests to cover int16 convolutions and element-wise; Fixes a minor typo negtive->negative in the element-wise tests.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good to me, few nits... Great job for getting int16 mobilenet and conv2d tests running, I think it's a really good improvement to our frontend infra!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for all the work on this @leandron, LGTM! :)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @leandron LGTM! Just a couple of comments about testing but feel free to take in a follow up
Co-authored-by: Elen Kalda <elen.kalda@arm.com>
) * [TFLite] Add support to int16 data type in TFLite frontend Add support for int16 data type and int64 biases/accumulators in the TFLite frontend. Adjusts TFLite tests to cover int16 convolutions and element-wise; Fixes a minor typo negtive->negative in the element-wise tests. * Update src/relay/qnn/op/convolution.cc Co-authored-by: Elen Kalda <elen.kalda@arm.com> Co-authored-by: Elen Kalda <elen.kalda@arm.com>
) * [TFLite] Add support to int16 data type in TFLite frontend Add support for int16 data type and int64 biases/accumulators in the TFLite frontend. Adjusts TFLite tests to cover int16 convolutions and element-wise; Fixes a minor typo negtive->negative in the element-wise tests. * Update src/relay/qnn/op/convolution.cc Co-authored-by: Elen Kalda <elen.kalda@arm.com> Co-authored-by: Elen Kalda <elen.kalda@arm.com>
) * [TFLite] Add support to int16 data type in TFLite frontend Add support for int16 data type and int64 biases/accumulators in the TFLite frontend. Adjusts TFLite tests to cover int16 convolutions and element-wise; Fixes a minor typo negtive->negative in the element-wise tests. * Update src/relay/qnn/op/convolution.cc Co-authored-by: Elen Kalda <elen.kalda@arm.com> Co-authored-by: Elen Kalda <elen.kalda@arm.com>
Add support for int16 data type and int64 biases/accumulators in the TFLite frontend. Adjusts TFLite tests to cover int16 convolutions and element-wise; Fixes a minor typo negtive->negative in the element-wise tests.
cc @lhutton1 @NicolaLancellotti @ekalda @masahi for reviews