-
Notifications
You must be signed in to change notification settings - Fork 378
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
Adding the RwandaFieldBoundary dataset #1574
Conversation
18cb57f
to
ab7856b
Compare
6017797
to
1b02126
Compare
@yichiac you might be interested in this one |
…ake mypy happy even though they are the same thing
self.root, f"nasa_rwanda_field_boundary_competition_source_{split}" | ||
) | ||
if os.path.exists(path): | ||
num_files = len(os.listdir(path)) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This could get buggy, for example, if you load one of the images in QGIS and it results in a hidden file left behind
if "mask" in sample: | ||
mask = sample["mask"].numpy() | ||
else: | ||
mask = np.zeros_like(image) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We're plotting a mask even if one doesn't exist? Why?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Remaining comments are food for thought, they could be addressed in a future patch release without an API change.
This dataset is important for the field boundary delineation task.