Roadmap for V2 of the ML Model Extension

[fmigneault]

🚀 Feature Request

originally posted on crim-ca#7

Below are acceptance criteria for #2 the new version of the ML Model Extension. After all these items are done I think #2 is ready to merge and we can publish a new version 2 release to https://github.com/stac-extensions/ml-model/issues . I'm working on most of these, let me know if you think other acceptance criteria should be included cc @fmigneault

• Incorporate feedback from @fmariv and others at @earthpulse
  • I had a meeting with @fmariv, they're keen to review the extension, provide feedback and see if we can align it more with general ML use cases. They're working on supporting the STAC extension ecosystem for ML as a part of the EOTDL initiative
  • https://hackmd.io/DBRF1sQCS1WmSqygJNKQJQ?view
  • feel free to comment first and then submit a PR against https://github.com/rbavery/dlm-extension/tree/validate
• address Fix bands #5
  • this will involve segregating flat fields from objects that are not meant to be searched on and are instead used for inference model loading, model input and output processing, and documenting in detail the accelerator and runtime details needed to run the model
• Roadmap for V2 of the ML Model Extension #4 by creating output objects for common detection tasks. At a minimum, start with single label classification, semantic segmentation, object detection. This will help resolve common ambiguities when interpreting model outputs, like the bbox coordinate ordering for object detection. EDIT this can be left for after the v2 release
• resolve update schema to recommend storage extension #3, deciding how to refer to model extension metadata. within it's own STAC item/collection json or are these fields composed with common metadata in STAC json representing a spatiotemporal asset?
• New Machine Learning Model Extension Version 2.0.alpha schema and (de)serialization, validation package dlm-extension#2 (comment) create an example and schema for the final spec
• reorganize and update the stac_model extension validation and serialization package according to the final spec: New Machine Learning Model Extension Version 2.0.alpha schema and (de)serialization, validation package dlm-extension#2 (comment)
• fix JSON schema with MLM fields + support pydantic/pystac objects rbavery/dlm-extension#2
• consider inputs from user feedback (Revisiting the ML Model extension stac-extensions/ml-model#13)
• consider community examples applying DLM (https://github.com/sentinel-hub/stac-ml-example)
• add missing item_assets check + remove mlm:name unique requirement #8
• fix requirement of mlm:model role, required only by at least one asset #9
• use glob_exclude new feature for bump-my-version #12
• Invalid stac-model version on PyPI #13
• integrate JSON schema representing new properties/fields (mix of https://github.com/crim-ca/dlm-extension/tree/main/json-schema and ML Model schema definition rbavery/dlm-extension#1)
• stac-model release workflow #14
• Proposal: Extend the Classification schema for integration with Machine Learning Model extension stac-extensions/classification#48
• Proposal: Extend the example JSON definition to Assets stac-extensions/example-links#4
• Add more example expression objects stac-extensions/processing#31
• add more processing:expression examples for python, docker and generic URI stac-extensions/processing#33
• consideration of end_datetime: null not supported by STAC Core spec
  (Datasets without time radiantearth/stac-spec#1268)
  • new issue to track for the specific use case: Representing open datetime ranges using Common Metadata radiantearth/stac-spec#1161

[fmigneault]

Remaining issues moved to stac-extensions/mlm#28 and stac-extensions/mlm#29.