Add dataloader for Kuro Siwo Flood Dataset #3
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Dataloader for Kuro Siwo dataset.
It accepts as input the flood events selected for train/val and test. This can be modified to simulate low data regimes and assess generalization in multiple setups. Default split is as reported in the original paper.
Assumes data are downloaded in root path. Samples are stored in root/data and extra information is stored in root/pickles/.
There are two pickles, publicly available in the original repo, containing metadata and paths of samples.
Pickle "grid_dict_full.pkl" has information on all samples, while "grid_dict_water.pkl" includes all samples with at least one pixel containing water.
SAR Mean and stds (i.e data_mean and data_std) are calculated with input clipped at 0.15 max value. If clip value is changed these stats should be updated.