Breaking Changes - read-pngs parameter name change. - rename several operators to make them more consistent: cutout --> read-precomputed, save --> write-precomputed, save-pngs --> write-pngs
Deprecations
Features - add a plugin to inverse image / affinitymap intensity
Bug Fixes
Improved Documentation
1.0.3
Breaking Changes - replace global_offset to voxel_offset to be consistent with neuroglancer info - change operator name `fetch-task` to `fetch-task-from-sqs` to be more specific.
Features - output tasks as a numpy array and save as npy file. - work with slurm cluster - fetch task from numpy array
Bug Fixes - fetch task from numpy array
Improved Documentation
1.0.2
Features - hdf5 file with cutout range
Bug Fixes - fix neuroglancer visualization for segmentation.
Improved Documentation
1.0.1
Breaking Changes - renamed custom-operator to plugin Deprecations
Features - new operator: normalize-intensity - a plugin system with a median filter example - new operator: normalize-intensity - support cutout from hdf5 file - new operator: cutout-dvid-target
Bug Fixes - cutout whole volume in default
Improved Documentation
1.0.0
Breaking Changes - rename inference backend `general` to `universal`
Deprecations
Features - threshold operator
Bug Fixes
Improved Documentation
0.6.3
Breaking Changes - remove convnet inference backend `pytorch-multitask` since it could be included by the `pytorch` backend. Deprecations
Features - a general convnet inference backend - support combined convnet inference including semantic and affinity map inference. - all-zero option for create-chunk operator and inference test in travis - new operator to delete chunk for releasing memory
Bug Fixes - log-summary operator will work for combined inference
Improved Documentation - added corresponding documentation - added new operator