Releases: okunator/cellseg_models.pytorch
Releases · okunator/cellseg_models.pytorch
v0.1.14
0.1.14 — 2022-12-01
Performance
- Throw away some unnecessary parts of the cellpose post-proc pipeline that just brought overhead and did nothing.
Refactor
-
Refactor the whole cellpose post-processing pipeline for readability.
-
Refactored multiprocessing code to be reusable and moved it under
utils
.
Features
-
Add exact euler integration (on CPU) for cellpose post-processing.
-
added more pathos.Pool options for parallel processing. Added
ThreadPool
,ProcessPool
&SerialPool
-
add all the mapping methods for each Pool obj. I.e.
amap
,imap
,uimap
andmap
v0.1.13
v0.1.2
v0.1.11
v0.1.10
v0.1.9
v0.1.8
v0.1.7
v0.1.6
0.1.6 — 2022-10-14
Features
- Add a Wandb artifact table callback for loading a table of test data metrics and insights to wandb.
Fixes
-
Symmetric CE loss fixed.
-
Add option to return binary and instance labelled mask from the dataloader. Previously binary was returned with
return_inst
flag which was confusing. -
Fix the
SegmentationExperiment
to return preds and masks at test time.