Composable Data Augmentations #189
Conversation
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
|
this seems like a breaking change. if the default boolean option is dropped, it should be scheduled for deprecation in a few cycles and this code should warn people that the boolean option will be removed in a future version. i suspect that this is not being caught by current tests, so we should add a test as well. |
|
Yes @satra, I will add the test and tutorial ipynb in this PR. |
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
|
Fixes #167 |
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
@Aakanksha-Rana - please check these changes, and do make sure that the transforms are capable of understanding what to do with the y-value (if it's a scalar, if it's image with integer labels, etc.,.)
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
|
We need to change Transforms.py functions in same format as intensity/spatial transforms to be able to take scalar or non-scalar labels. |
can this be done for this PR ? |
I will change the apply_random_transform in this PR @satra . |
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
Types of changes
Summary
The goal of this PR is to enable sequence of on-the-fly augmentation by giving multiple transforms as list for argument 'augment' . This is open to suggestions and modifications to make it better and robust for different transform functionalities available in spatial_transform, intensity_transform and volume.
Checklist
Acknowledgment