-
Notifications
You must be signed in to change notification settings - Fork 47
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 image tuple support #23
Merged
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
Evizero
force-pushed
the
imagetuple
branch
2 times, most recently
from
June 26, 2018 09:15
84b0974
to
7a6da4a
Compare
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Outdated suggestions cannot be applied.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.
Motivation
The goal of having image tuple support is to support use cases such as image segmentation, where the input and the target are both images.
The interface should be as follows. Where one can currently write:
it should also be possible to write:
These images should always traverse the same path through the pipeline, even if randomness is involved. As an example if one operation in
mypipeline
is an elastic distortion, then the distortion must be the same for each of the three images.Todo list
So far i made some very basic refactors to get the current suite of tests to pass, while allowing for iterative adaption of the individual operations and their tests. Many of the simpler operations should already work, but still lack tests for the new behaviour; those are marked as "missing tests".
General
augment
augment!
augmentbatch!
update README.mdmaybe some other timeOperations
CacheImage
CacheImageInto
Either
(most complex one)Rotate
Scale
ShearX
ShearY
Zoom
Missing Tests
SplitChannels
CombineChannels
PermuteDims
Reshape
ConvertEltype
Crop
CropNative
CropSize
CropRatio
RCropRatio
ElasticDistortion
FlipX
FlipY
MapFun
AggregateThenMapFun
NoOp
Resize
Rotate90
Rotate180
Rotate270