-
Notifications
You must be signed in to change notification settings - Fork 785
Open
Labels
module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommtriagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module
Description
📚 The doc issue
I was following this tutorial
and I noticed that the compiled model deeplab file is ./deeplab/dl3_qnn_q8.pte instead of deeplab_v3/dlv3_qnn.pte
and the current qnn executor executable is build-x86/examples/qualcomm/executor_runner/qnn_executor_runner instead of build-x86/examples/qualcomm/qnn_executor_runner
Suggest a potential alternative/fix
I suggest that:
- Change the compiled model name path to
./deeplab_v3/dlv3_qnn.pte - Change the qnn executable path to
build-x86/examples/qualcomm/executor_runner/qnn_executor_runner
cccclai
Metadata
Metadata
Assignees
Labels
module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommtriagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module
Type
Projects
Status
In progress