Skip to content
This repository has been archived by the owner on Jan 12, 2024. It is now read-only.

[FeatureRequest] Per Sample option transforms #85

Open
mibaumgartner opened this issue May 17, 2020 · 0 comments
Open

[FeatureRequest] Per Sample option transforms #85

mibaumgartner opened this issue May 17, 2020 · 0 comments
Labels
FeatureRequest Request for additional feature

Comments

@mibaumgartner
Copy link
Member

Description
Introduce a Per Sample option to transforms.

Proposal
How could the feature be implemented?
Spatial Transforms:

  1. Transforms which use pytorch function -> use loop inside the functional.
  2. If possible, introduce an affine equivalent which can be stacked with other affine transforms and will support per sample augmentation without any loop.

Cropping: Probably only possible with an internal loop

Affine Transforms: already support this option

Intensity/ Channel Transforms: tbd

@mibaumgartner mibaumgartner added the FeatureRequest Request for additional feature label May 17, 2020
@mibaumgartner mibaumgartner pinned this issue May 17, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
FeatureRequest Request for additional feature
Projects
None yet
Development

No branches or pull requests

1 participant