Allow NaNs in datasets #326
Merged
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Outdated suggestions cannot be applied.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.
In the GCP archive, the bits of the image which are off the earth disk are filled with NaNs. There are even times when some random scattered pixels over the earth are NaNs, (probably just a measurements error from the satellite). In the production data, there are no NaNs and the pieces of the image off the earth disk are all zeros.
This is an issue for the cloudcasting model. When training, all the pixels that are NaN are flagged to the model so it knows where they are. This isn't possible in production since all NaNs are now zero, but not all the zero values were NaN - at night the visual channels go dark, for instance.
This PR updates the type of the dataset to float32, which implements NaN.