Allowing user specified masks about microdl HOT 5 CLOSED

1. could this change wait until Jenny comes back on March 17th, it seems like a big refactor.
2. I am sure mask_dir doesn't include the float weight maps, mask_dir is always binary target, in preprocessing mask_dir is binary masks which is used to compute and combine the float weight maps created into the input_dir by setting them in a channel of the input data which is given as data_dir in the config
3. given that mask_dir is always binary masks, I don't see why we would need any change

Please correct me if I am wrong

from microdl.

Yes mask_dir is always binary masks, but its role is different in segmentation and regression tasks. Here is my understanding of the role of mask_dir for segmentation and regression:
For segmentation,
mask_dir: binary input supplied by the user; used as the target for training
weight_dir: weight maps generated by mask generator using mask_dir as input; used for computing weighted loss

For regression,
mask_dir: generated by mask generator (more common)m or supplied by the user; used for computing weighted loss (masked loss); not the target for training
weight_dir: N/A

To me the change of the role of mask_dir in different use cases is confusing. We can discuss this with Jenny after she is back. I'll leave it as it is for now for this PR

from microdl.

mask_dir is always the same for segmentation or regression i.e it is optional if the user provides it, weight_dir for segmentation is not a mandatory parameter

from microdl.

I've renamed this issue from "mixed usage of mask_dir" since masks from now on will be stored along with other channels in a zarr store.

However the issue still remains that user specified masks (generated outside of microDL) as input to preprocessing would be a good feature to have.
Prior to implementing this, specifications need to be discussed regarding what format of masks to support.

from microdl.

This is still relevant, but straightforward to do by updating the masks in the ome-zarr store. Closing. cc: @Soorya19Pradeep.

from microdl.