Repository navigation
First stable release of the 0.8 series, consolidating the two v0.8.0 alpha pre-releases (v0.8.0a1–a2). 5 commits since v0.7.0.
Highlights
- Cellpose v4 DINO support — the GPU-resident segmentation path now covers all four v4 models: the SAM backbones (
cpsam,cpsam_v2) and the DINOv3 backbones (cpdino,cpdino-vitb). - Wiener-Butterworth back projector for Richardson-Lucy deconvolution — converges in ~1–2 iterations instead of 10–50 (Guo et al. 2020), with the matched path byte-for-byte unchanged by default.
New features
Segmentation
segment_cellposeis now the canonical GPU-resident entry point, supporting all four Cellpose v4 backbones (SAM + DINO).segment_cpsamis kept as a deprecated alias (emitsDeprecationWarning, slated for removal after 0.8). (#51)- Tunable tile size via a new
bsizeparameter (defaults 256 for SAM, 384 for DINO), centralized in_resolve_bsizewith cellpose's SAM→256 guard and non-positive-bsizevalidation. (#51)
Preprocessing — deconvolution
create_backprojector(cubic.preprocessing) — device-agnostic NumPy/CuPy port ofBackProjector.m, supportingtraditional,gaussian,butterworth,wiener, andwiener-butterworthtypes. (#52)backprojectortoggle onrichardson_lucy_xp, threaded throughdecon_xpy,richardson_lucy_iter, anddeconv_iter_num_finder. Faithful unmatched RL update (noH^T1, nocorrection<0clip, estimate floored at 1e-3, both projectors sum-normalized); circulant only, and the default (None) leaves the matched path unchanged. (#52)
Packaging
- Require
cellpose>=4.2.0(the release that first shipscpsam_v2/cpdino). - New
cellpose-dinoextra for thedinov3dependency (pip install cubic[cellpose-dino]).
Docs & examples
- New notebook
deconvolution_wb_backprojector_3d.ipynb— matched-vs-WB convergence by PSNR/SSIM and absolute FSC resolution (+ paired script + README row). - 3D feature-extraction notebook gains a CPU-vs-GPU comparison.
Install
pip install cubic==0.8.0Full changelog: v0.7.0...v0.8.0