Adeel Hassan

I use the following workaround for this to get both images and CSS in the email: - Add `self-contained: no` to the output options of the RMarkdown file - Include...

Thanks for looking into this. I think defining a new compute environment and adding it to the existing job queue makes sense. CC @lewfish

>Are you thinking that there will be different notebooks for the different checkbox points you listed? I was thinking we would have notebooks that covered whole workflows for specific datasets/tasks...

Please feel free to edit the issue body.

An example of RV-as-library code can be seen here: https://github.com/raster-foundry/raster-foundry/tree/develop/app-hitl/hitl/src/hitl/rv

>I was thinking that we might want to add an example of a lower-resolution land cover dataset since that's a common use case @lewfish, do you know of a convenient...

Yes, but it's tied up in the `Learner` as well. You need to create a `Learner` with `Learner(model=your_model, training=False)` and then do basically this: https://github.com/raster-foundry/raster-foundry/blob/develop/app-hitl/hitl/src/hitl/rv/predict.py

Do we have experience publishing packages to conda? Can we also add the automation of conda publishing to this issue?

> It seems like the predictor and evaluation functionality should also be usable a la carte and within a notebook environment. Yeah, prediction is next on my agenda. I'll share...

I think a `Learner.predict_dataset(dataset)` method that returns a generator of predictions gets us most of the way there. The user will then have to just instantiate a dataset (either from...