Releases: okunator/cellseg_models.pytorch
Releases · okunator/cellseg_models.pytorch
v0.1.16
0.1.16 — 2022-12-14
Dependencies
- Bump old versions of numpy & scipy
v0.1.15
0.1.15 — 2022-12-13
Features
- Use the inferer class as input to segmentation benchmarker class
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
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
and map
v0.1.13
0.1.13 — 2022-11-25
Features
- Add option to return encoder features, and decoder features along the outputs in the forward pass of any model.
Fixes
- Turn the
cellpose
and stardist
postproc dirs into modules.
v0.1.2
0.1.12 — 2022-11-03
Performance
- Reverse engineered the
stardist
post-processing pipeline to python. Accelerated it with Numba and optimized it even further. Now it runs almost 2x faster than the original C++ verion.
Fixes
- Fix bug with padding in
SlidingWindowInferer
v0.1.11
0.1.11 — 2022-10-21
Removed
- unnecessary torchvision dependency
v0.1.10
0.1.10 — 2022-10-21
Removed
- torch-optimizer removed from the optional dependency list. Started to cause headache.
v0.1.9
0.1.9 — 2022-10-21
Refactor
- Moved saving utilities to
FileHandler
and updated tests.
Features
- Added geojson saving support for inference
v0.1.8
0.1.8 — 2022-10-18
Features