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.

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

Fix rocAL Tensor build issues PR 1 - Augmentation nodes and OpenVX fix #24

Merged

Conversation

fiona-gladwin
Copy link
Collaborator

  • Modify the augmentation nodes in rocAL to fix build issues
  1. Change reference from Image to Tensor
  2. Comment out the vx_Extrpp calls wrt batchPD (The correct vxExtrpp call for tensor augmentations will be introduced in future PR)
  3. Change the API to get the width and height from TensorInfo
  • Change the name of the API in OpenVX extensions tensor augmentation files wrt latest changes in the Opensource TOT develop

@@ -45,7 +45,7 @@ void ColorTwistBatchNode::create_node()
_hue.create_array(_graph , VX_TYPE_FLOAT32, _batch_size);
_sat.create_array(_graph , VX_TYPE_FLOAT32, _batch_size);

_node = vxExtrppNode_ColorTwistbatchPD(_graph->get(), _inputs[0]->handle(), _src_roi_width, _src_roi_height, _outputs[0]->handle(), _alpha.default_array(), _beta.default_array(), _hue.default_array(), _sat.default_array(), _batch_size);/*A temporary fix for time being*/
// _node = vxExtrppNode_ColorTwistbatchPD(_graph->get(), _inputs[0]->handle(), _src_roi_width, _src_roi_height, _outputs[0]->handle(), _alpha.default_array(), _beta.default_array(), _hue.default_array(), _sat.default_array(), _batch_size);/*A temporary fix for time being*/
Copy link
Collaborator

Choose a reason for hiding this comment

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

why is this commented out?

Copy link
Owner

Choose a reason for hiding this comment

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

What is the temporary fix?

Copy link
Owner

Choose a reason for hiding this comment

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

@rrawther all of it is commented. I think it is so that the branch will build? Only the tensor implemented augmentations seems to call the rpp kernels. @fiona-gladwin is that what you are trying to do here?

Copy link
Collaborator

Choose a reason for hiding this comment

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

We have commented RPP calls for batchPD augmentations so that we can build the existing tensor branch. If we add all augmentations in this PR the changes will be more and hard to review.
Like discussed we will issue subsequent PR's to convert batchPD to Tensor for rest of the augmentations.

Copy link
Collaborator

@rrawther rrawther left a comment

Choose a reason for hiding this comment

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

Is the tot MIVisionX changes are merged into this?

@LakshmiKumar23
Copy link
Owner

@rrawther Seems ok to me. let me know when I can merge this PR

@LakshmiKumar23 LakshmiKumar23 merged commit 68ad794 into LakshmiKumar23:lk/rocalTensor Jul 17, 2023
@fiona-gladwin fiona-gladwin deleted the PR_tensor_w1 branch August 7, 2023 18:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants