Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Make a quick version of this notebook #3

Open
Bart92 opened this issue Jul 6, 2022 · 3 comments
Open

Make a quick version of this notebook #3

Bart92 opened this issue Jul 6, 2022 · 3 comments
Assignees

Comments

@Bart92
Copy link
Contributor

Bart92 commented Jul 6, 2022

Right now the training time is quite long, so we need to focus on a demo that is simple and speedy for a "GEE classification for dummies " type of feeling.

@Patrick1G
Copy link

could this be linked to the PG-viewer SAP that SIN is working on? classification for dummies in GEE works on any pyramid level, so while zoomed out inference occurs at coarsest pyramid level and is super fast...

@jdries
Copy link

jdries commented Jul 15, 2022

The bottleneck in our current notebook is not only the size or resolution of the area, but also the fact that we work on a long season.
In the quick version, we can perhaps play around with taking only a few months. Working on a more coarse resolution and benefiting from overviews within the files is also supported, we can do that with a simple 'resample_spatial'.

I believe the random forest inference process is not foreseen in the PG-viewer SAP, so don't think that will be possible.

@Patrick1G Patrick1G self-assigned this Nov 16, 2022
@Patrick1G
Copy link

Limitation of rf_predict() as part of the on-demand viewer (SAP02):
SH does not support rf_predict()
Terrascope with Spark does not read RF models...
Thus on hold for now..

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants