Skip to content
This repository has been archived by the owner on Feb 16, 2022. It is now read-only.

Add Usage Recommendations section #18

Merged
merged 3 commits into from
May 19, 2021
Merged

Add Usage Recommendations section #18

merged 3 commits into from
May 19, 2021

Conversation

duckontheweb
Copy link
Collaborator

Adds a Usage Recommendation section for describing conditions under which a model should behave as expected.

This section is based on the outline from the original Google Doc, except that it leaves out the "Input Data" element from that overview. Finding a way of consistently representing restrictions on input data (e.g. GSD, bands, etc.) in a way that is both machine-readable and understandable to humans is important, but also a difficult problem. In the interest of pushing towards an initial release of this spec that we can begin testing, I think it might be best to tackle that problem as a separate PR so that we can have a more focused discussion.

The term "behave as expected" is admittedly a bit vague. It didn't seem appropriate to use the term "perform well" since there is nothing in the current spec that guarantees that a model "performs well" even under conditions identical to the training environment. If anyone has suggestions on how to better define this I'm open to input.

@duckontheweb duckontheweb added prio: must-have Required for associated release addition Involves an addition to the spec labels May 13, 2021
@duckontheweb duckontheweb added this to the v0.1.0 milestone May 13, 2021
@duckontheweb duckontheweb requested a review from HamedAlemo May 13, 2021 20:32
@duckontheweb
Copy link
Collaborator Author

Merged in the new Model Training section as well to make it easier to review these changes in the full context of the spec.

Copy link
Collaborator

@HamedAlemo HamedAlemo left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I like "behave as expected". This is basically based on the knowledge and judgment of the developer.
In a future release we may want to expand this and allow for transfer learning applications. For example, if they have used the model in a region/domain that has limited validation data what has been the performance.

@duckontheweb
Copy link
Collaborator Author

@calebrob6 @batic No pressure, but if you want to leave comments on this, please do. I'll plan on merging by 4 PM EDT today if there are no pressing concerns.

@batic
Copy link
Collaborator

batic commented May 17, 2021

The section very aptly addresses where "the model will work well". In my experience, we often know also where/when the model will not perform (well, or at all). As such, perhaps the section should be extended (or re-worded) so that the information therein can also identify areas/... where the model is not to be used.

a new geographic region. This section is meant to capture that information in a systematic way,
while also providing publishers the opportunity to describe their recommendations in a more
free-form style.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A short sentence/paragraph could be added, noting that the section can also provide possible conditions, where the model will not perform.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated in a829170 to have separate recommendations and cautions sections.

@duckontheweb
Copy link
Collaborator Author

The section very aptly addresses where "the model will work well". In my experience, we often know also where/when the model will not perform (well, or at all). As such, perhaps the section should be extended (or re-worded) so that the information therein can also identify areas/... where the model is not to be used.

That's a really good point. It seems like restructuring this to include "recommended" and "discouraged" sections with the same structure might be the best approach. That way a users could apply the same filter logic (just inverted) to find both recommended and discouraged conditions.

@duckontheweb
Copy link
Collaborator Author

It seems like restructuring this to include "recommended" and "discouraged" sections with the same structure might be the best approach.

The section has been updated in a829170 to include a field for "recommendations" and a field for "cautions." Each of these is a list of objects describing the conditions that apply to that recommendation/caution.

@duckontheweb duckontheweb requested a review from batic May 17, 2021 18:34
@duckontheweb
Copy link
Collaborator Author

@batic I'm going to merge this so we can cut an initial release. If you have any concerns about the structure, feel free to open an issue and we can touch things up in a future PR. Thanks for your input on this!

@duckontheweb duckontheweb merged commit 2a71332 into main May 19, 2021
@duckontheweb duckontheweb deleted the gh-16-usage-recs branch May 19, 2021 20:59
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
addition Involves an addition to the spec prio: must-have Required for associated release
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants