Adding support for pyramids #129
Conversation
edyoshikun
force-pushed
the
support_pyramid
branch
from
308392c to
8a137d4
Compare
edyoshikun
force-pushed
the
support_pyramid
branch
from
eb83d8c to
8a137d4
Compare
|
@edyoshikun thanks - this implementation seems backward compatible with previous configs for training and prediction for virtual staining and contrastive learning tasks. Can you check with the configs we are sharing with the preprint if they need any change (e.g., explicitly setting the scale = 0)? |
|
@mattersoflight we don't need to change the previous configs because by default the Dataloader will be set to "0" the highest resolution if the parameter is not provided in the config. For the preprint, I thought we were pointing them to |
|
I've tested the basic @edyoshikun I'm happy to leave this as a branch while we test this out end to end during the course. |
|
The code changes look good, but we should test that training actually works before merging. |
| @@ -219,7 +223,7 @@ def __getitem__(self, index: int) -> Sample: | |||
| sample = { | |||
| "index": sample_index, | |||
| "source": self._stack_channels(sample_images, "source"), | |||
| "norm_meta": norm_meta, | |||
| # "norm_meta": norm_meta, | |||
| @@ -318,6 +324,7 @@ def __init__( | |||
| augmentations: list[MapTransform] = [], | |||
| caching: bool = False, | |||
| ground_truth_masks: Path | None = None, | |||
| pyramid_resolution: str = "0", | |||
There was a problem hiding this comment.
#218 used array_key for this parameter, which is a more general naming:
VisCy/viscy/data/mmap_cache.py
Line 40 in 1d3261d
This PR adds the support for pyramids to address #125. This modifies the
HCSDataloader()