Fix ModelDebugger.step to use only intermediate_outputs

[Zerui18]

Issue

Calling cto.coreml.experimental.linear_quantize_activations on a model with ct.ImageType output(s) fails at the model output because record_intermediate_output expects output_value to be a np.ndarray but the model's final output is PIL.Image.

Ultimately, record_intermediate_output only expects intermediate outputs, not model outputs which could be of type PIL.Image.

Followup From

#2385

[jakesabathia2]

Thanks for the PR @Zerui18 ,
could you also include an unittest for this fix?

[yixingli-apple]

Some references for activation quantization unit tests (you could also put your unit test there):

• coremltools/coremltools/test/optimize/coreml/test_passes.py

  Line 3774 in 32ebc55

  class TestGetActivationStats(TestCompressionPasses):

• coremltools/coremltools/test/optimize/coreml/test_passes.py

  Line 3565 in 32ebc55

  class TestLinearActivationQuantizer(TestCompressionPasses):

References for getting a mlmodel with ImageType as output:

• coremltools/docs-guides/source/image-inputs.md

  Line 135 in 32ebc55

  outputs=[ct.ImageType(color_layout=ct.colorlayout.RGB)],

• coremltools/coremltools/converters/mil/frontend/torch/test/test_torch_conversion_api.py

  Line 1923 in 32ebc55

  outputs=[ct.ImageType(color_layout=ct.colorlayout.RGB)],

[Zerui18]

@jakesabathia2 I've added a corresponding unit test and rebased both changes to be a single commit on top of the current head. Please help to review it, thank you.

[jakesabathia2]

LGTM!
CI: https://gitlab.com/coremltools1/coremltools/-/pipelines/1593429673

[jakesabathia2]

@Zerui18 the CI is failing.
I am seeing this branch is based on an old commit:

commit 3d7bfc8281fcfca31ad5a06f7203f763af2a5462
Author: M_noAria <[email protected]>
Date:   Fri Nov 1 01:39:36 2024 +0800

    Enhance torch.zeros_like for GPU inference in dynamic shape (#2369)

Can you rebase on the latest origin/main ?

[Zerui18]

Hi @jakesabathia2, I have rebase my commit on the current head as requested! Please have a look again. Thanks!