Write test for merging transform

[benjijamorris]

• test with example experiment data with missing_key_mode=create

[benjijamorris]

Traceback (most recent call last):
File "/Users/brian.kim/anaconda3/envs/ml-seg/lib/python3.10/site-packages/monai/transforms/transform.py", line 141, in apply_transform
return _apply_transform(transform, data, unpack_items, lazy, overrides, log_stats)
File "/Users/brian.kim/anaconda3/envs/ml-seg/lib/python3.10/site-packages/monai/transforms/transform.py", line 98, in _apply_transform
return transform(data, lazy=lazy) if isinstance(transform, LazyTrait) else transform(data)
File "/Users/brian.kim/anaconda3/envs/ml-seg/lib/python3.10/site-packages/cyto_dl/image/transforms/multiscale_cropper.py", line 144, in call
slices = self.generate_slices({k: image_dict[k] for k in available_keys})
File "/Users/brian.kim/anaconda3/envs/ml-seg/lib/python3.10/site-packages/cyto_dl/image/transforms/multiscale_cropper.py", line 144, in
slices = self.generate_slices({k: image_dict[k] for k in available_keys})
KeyError: 'target'

[yrkim98]

To replicate my issue with segmenter:

• Using segmentation_plugin.yaml
• Changed all missing_key_mode’s in /data/im2im/segmentation_plugin.yaml to “create" instead of “ignore"
• Running training with example_experiment_data from cyto-dl
• CSV contaings raw, seg1, seg2, exclude_mask, base_image, merge_mask columns

More info at https://alleninstitute.atlassian.net/wiki/spaces/SF/pages/184549397/Current+cyto-dl+issues+with+ml-segmenter under Training is not working using the sementation_plugin config -> Merged transform not working with the fixes on cyto-dl branch