Qualcomm AI Engine Direct - GA DIT

[shewu-quic]

Summary:

• Add DIT example script
  • Use HistogramObserver as act_observer to resolve accuracy issue
• Add the test for DIT
• Support UpsampleBicubic
  • Remove unused pass convert_upsample_bicubic2d.py

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11093

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure, 9 Pending

As of commit 4789975 with merge base 95a1db5 ():

NEW FAILURE - The following job has failed:

• Check Labels / Check labels (gh)
  RuntimeError: Error checking labels: PR does not have required labels

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:.

If not, please add the release notes: none label.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[cccclai]

Curious how do you know Histogram observer can resolve the accuracy issue?

[shewu-quic]

Curious how do you know Histogram observer can resolve the accuracy issue?

In the begining, I observe the scale of some nodes is bigger than 0.1 with MinMaxObserver. Therefore, I try to use other observer to resolve accuracy issue. When I try Histogram observer, it seems to get reasonable accuracy.