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
Add LoveDA dataset #270
Add LoveDA dataset #270
Conversation
Hi @nilsleh and thanks for the contribution! I know that the GID-15 didn't have this, but could you add a plot method and show some examples in the PR description? We are working on adding these to all datasets for visually verifying the image and labels were loaded correctly. |
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.
For the test data, you can actually make the images 1x1 or 2x2 to reduce the total file sizes
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.
Everything looks good to me, just a few comments on style
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.
Actually, there's one thing missing. Can you add this to docs/api/datasets.rst
?
I am not sure why the documentation is not picking up the correct return type for get_item and plot method, those two are causing the sphinx test to fail. |
Sometimes the sphinx test will fail. We can re run by closing and opening the PR. If not then maybe an update to packages broke it. |
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.
Return values do not have names in Sphinx, this is causing the tests to fail
* initial commit, adding LoveDA dataset * recommended changes by ashnair1 * corrections from pydocstyle linter * List[str] * plotting method added * linting test changes * passing test for plotting * linting adjustments * smaller fake data of 2x2 and mypy linter changes * plot only single image and mypy changes * plot method without expecting batch dimension * style changes and adding doc * added lightning data module * sphinx changes * doc string changes * data module in init and fake data for module test
This is my proposal for adding the LoveDA dataset that Caleb Robinson recommended me to look at as a contribution. This is my first time trying to contribute, so I would welcome any suggestions and criticism. I have based everything off of the code for the gid15 dataset. Running pytest it passed all the tests and had 100% cover on loveda.py.
The dataset differentiates between "rural" and "urban" images so here are some samples respectively from the training split.