Skip to content

Remove artifical limitation on 5D tensors for GPU #325

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

Merged
Ryan Lai (ryanlai2) merged 1 commit into from
Jul 13, 2020
Merged

Remove artifical limitation on 5D tensors for GPU #325

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 0 additions & 7 deletions Tools/WinMLRunner/src/Run.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -293,13 +293,6 @@ HRESULT CheckIfModelAndConfigurationsAreSupported(LearningModel& model, const st
else if (inputFeature.Kind() == LearningModelFeatureKind::Tensor)
{
auto tensorFeatureDescriptor = inputFeature.try_as<TensorFeatureDescriptor>();
if (tensorFeatureDescriptor.Shape().Size() > 4 && deviceType != DeviceType::CPU)

@smk2007 Sheil Kumar (smk2007) Jul 13, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

should you leave this check and update the check and message to allow up to 5d tensors and not 6?

@fdwr Dwayne Robinson (fdwr) Jul 13, 2020

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

I'm adding 6D, 7D, 8D in just a few weeks. Please don't put artificial limitations in a tool, when the API should check it.

{
std::cout << "Input feature " << to_string(inputFeature.Name())
<< " shape is too large. GPU path only accepts tensor dimensions <= 4 : "
<< tensorFeatureDescriptor.Shape().Size() << std::endl;
return E_INVALIDARG;
}

// If image as input binding, then the model's tensor inputs should have channel 3 or 1
if (hasInputBindingImage &&
Expand Down