Skip to content

Conversation

@amrirasyidi
Copy link
Contributor

This is how the plot looks like

Default plot

from torchgeo.datasets import WesternUSALiveFuelMoisture
data = WesternUSALiveFuelMoisture('path/to/data')
sample = data[0]
f = data.plot(
    sample,
    show_titles=True, suptitle='test suptitle'
)

image

Single variable defined

f = data.plot(
    sample,
    variables_to_plot=['slope'],
    show_titles=True, suptitle='test suptitle'
)

image

Multiple variables defined

f = data.plot(
    sample,
    variables_to_plot=[
        'slope',
        'green',
        'swir'
    ],
    show_titles=True, suptitle='test suptitle'
)

image

@github-actions github-actions bot added datasets Geospatial or benchmark datasets testing Continuous integration testing labels May 2, 2025
@adamjstewart
Copy link
Member

My vote would be to always plot all variables instead of asking which variables to plot.

@adamjstewart adamjstewart added this to the 0.8.0 milestone May 2, 2025
@adamjstewart
Copy link
Member

Hmm, maybe there are too many variables to always plot all of them. Unless we can somehow group plots together. What's the difference between red, vv_red, and vh_red? Maybe we can only plot RGB instead of all possible color combinations? This one might require some creativity to actually be a useful plot.

Copy link
Member

@adamjstewart adamjstewart left a comment

Choose a reason for hiding this comment

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

I don't think this plot is perfect, but I do think it's better than no plot. Let's merge and refine in future PRs if anyone cares.

@adamjstewart adamjstewart enabled auto-merge (squash) November 15, 2025 11:50
@adamjstewart adamjstewart merged commit 0bb67eb into torchgeo:main Nov 15, 2025
17 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

datasets Geospatial or benchmark datasets testing Continuous integration testing

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants