[detext] Adding multilabel classification

[amberkaur1]

Description

Added multi-label classification task to detext. Updated input label format to array (shape [num_classes], assuming one-hot array input), changed loss and activation functions, added precision/recall metrics. Passed unit tests on detect-dev mp while being backwards compatible.

Please delete options that are not relevant.

• [x] New feature (non-breaking change which adds functionality)

List all changes

Please list all changes in the commit.

• Added MULTILABEL_CLASSIFICATION TaskType and fixed
• Updated input label format to array (shape [num_classes], assuming one-hot array input
• Changed loss and activation functions for multi-label classification
• Added precision/recall metrics

Testing

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

Passed unit tests on detect-dev mp while being backwards compatible. Also passed unit tests on li-detext, but full pipeline with real data yet to be confirmed

Test Configuration:

• Firmware version:
• Hardware:
• Toolchain:
• SDK:

Checklist

• [x] My code follows the style guidelines of this project
• [x] I have performed a self-review of my own code
• [x] I have commented my code, particularly in hard-to-understand areas
• [x] I have made corresponding changes to the documentation
• [x] My changes generate no new warnings
• [x] I have added tests that prove my fix is effective or that my feature works
• [x] New and existing unit tests pass locally with my changes
• [x] Any dependent changes have been merged and published in downstream modules

[amberkaur1]

Thank you for your effort on multilabel classification! Please check my comments below.

Updated the code accordingly, thanks for reviewing!