Fix DS-CNN Cortex-M input memory format

[JacobSzwejbka]

Summary

The shared DS-CNN model wrapper returned a contiguous NCHW example input, while the Cortex-M backend requires channels-last inputs. This caused the nightly Cortex-M FVP run to abort in cortex_m::quantized_depthwise_conv2d.out with input must be channels_last.

Convert the example input to channels-last, matching the existing Cortex-M DS-CNN tests and backend contract. The tensor values and eager model output are unchanged.

Test plan

Ran python -m py_compile examples/models/mlperf_tiny/ds_cnn.py and git diff --check. Loaded the patched wrapper and verified input stride (490, 1, 10, 1), eager output shape (1, 12), and the exported user-input stride (490, 1, 10, 1).

Authored with Claude.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21485

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit 343d6d3 with merge base a1d4d35 ():
💚 Looks good so far! There are no failures yet. 💚

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:. This helps us keep track and include your important work in the next release notes.

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.