Skip to content
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

Patch data loader for single-frame ("Static") 2D data #86

Merged
merged 1 commit into from May 22, 2020

Conversation

ngreenwald
Copy link
Collaborator

The data loader currently takes the first dimension of the image as the number of stacks, but for 2D data that is the rows axis, not the stack axis. Modified it to only do this for images with more than 2 dimensions.

@MekWarrior MekWarrior changed the title Fix dataloader bug for 2D data Patch dataloader for single-frame 2D data May 22, 2020
@MekWarrior MekWarrior changed the title Patch dataloader for single-frame 2D data Patch data loader for single-frame ("Static") 2D data May 22, 2020
@MekWarrior
Copy link
Collaborator

This PR serves as a temp patch for a larger issue. Under the DeepCell Data Ontology, 2D data are just images - dynamic denotes that you would expect multiple images stored in 1 tif file for a given session and position. For the static branch, it is expected that the each tif would only have one frame in it. But it is all "2D data." The data loader should use either the ontological location or the number of frames to make this distinction and initialize an array of the appropriate size.

N.B. The number of frames is not currently available in metadata but it should be. Once it is available, the array initialization should be handled with a database call rather than calculated on the fly.

@MekWarrior MekWarrior merged commit 4a3d153 into master May 22, 2020
@MekWarrior MekWarrior deleted the data_loader_bugfix branch May 22, 2020 18:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants