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

[onert] Fix DepthwiseConvOp kernel condition #13689

Merged
merged 2 commits into from
Aug 19, 2024
Merged

[onert] Fix DepthwiseConvOp kernel condition #13689

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
14261bc
[onert] Fix DepthwiseConvOp kernel condition
hseok-oh Aug 19, 2024
64bdc17
Update DepthwiseConvolutionLayer.cc
jyoungyun Aug 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions runtime/onert/backend/cpu/ops/DepthwiseConvolutionLayer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,9 +81,9 @@ void DepthwiseConvolutionLayer::convFloat32()
op_params.float_activation_min = output_activation_min;
op_params.float_activation_max = output_activation_max;

// Since DepthwiseConvOp does not support dilation yet, it uses the existing
// kernel in this case.
if (_dilationWidth == 1 && _dilationHeight == 1)
// Since DepthwiseConvOp does not support dilation and different W/H stride yet,
// it uses the existing kernel in this case.
if (_dilationWidth == 1 && _dilationHeight == 1 && _strideWidth == _strideHeight)
Copy link
Contributor

Choose a reason for hiding this comment

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

The prepareF32 function must also be updated to add new constraints.
Thank you!

{
nnfw::cker::DepthwiseConvOp(op_params, getShape(_input), getBuffer<float>(_input),
getShape(_kernel), getBuffer<float>(_kernel), getShape(_bias),
Expand Down