Views
No views yet
kapoorlabs_vollseg
(models_stardist_pytorch). Flat layout — the folder ships:last.ckpt (and optionally per-epoch <model_name>-epoch=NNN.ckpt)training_config.json — Hydra parameters block, what
kapoorlabs_vollseg reads first to rebuild the architecture<model_name>.json — legacy CareInception fallback config(conv_dims, n_rays, anisotropy) in the JSON; no rays.npy
sidecar is needed.1# StarDist
2from kapoorlabs_vollseg import StarDistSegmenter, ensure_model
3folder = ensure_model("./local_models", "models_stardist_pytorch",
4 repo_id="KapoorLabs/xenopus-stardist-pytorch")
5star = StarDistSegmenter.from_folder(folder)
6labels = star.predict(volume).labels
7
8# U-Net
9from kapoorlabs_vollseg import UNetSegmenter, ensure_model
10folder = ensure_model("./local_models", "models_stardist_pytorch",
11 repo_id="KapoorLabs/xenopus-stardist-pytorch")
12unet = UNetSegmenter.from_folder(folder)
13labels = unet.predict(volume).labels
14
15# CARE
16from kapoorlabs_vollseg import CAREDenoiser, ensure_model
17folder = ensure_model("./local_models", "models_stardist_pytorch",
18 repo_id="KapoorLabs/xenopus-stardist-pytorch")
19care = CAREDenoiser.from_folder(folder)
20denoised = care.predict(volume).denoised