Views
No views yet
kapoorlabs_lightning (inception_nmorpho_fate). Classifies cell-fate
labels from 25-timepoint sliding-window tracklets of 18 morphodynamic
features (6 shape + 12 dynamic channels: SHAPE_DYNAMIC_FEATURES
in kapoorlabs_lightning.tracking.track_features).epoch=N-step=M.ckpt — Lightning checkpoint with optimizer +
scheduler state.training_config.json — Hydra parameters block, what
predict-cellfate.py reads first to rebuild the architecture
(architecture knobs from the JSON win over the prediction yaml so
the same predict script handles checkpoints trained with different
arches).<experiment_name>.json / <experiment_name>.npz — CustomNPZLogger
side-cars (per-epoch metrics).1from kapoorlabs_lightning.hub import ensure_model
2
3# Auto-downloads to ./local_models/inception_nmorpho_fate/ if missing
4folder = ensure_model("./local_models", "inception_nmorpho_fate",
5 repo_id="KapoorLabs/xenopus-cellfate-inception-pytorch")
6
7# Then point predict-cellfate.py at it:
8# python predict-cellfate.py \
9# experiment_data_paths.checkpoint_path=<folder>predict-cellfate.py without a checkpoint_path
override — it falls back to this model automatically:1python scripts/model_prediction/predict-cellfate.py \
2 experiment_data_paths.xml_file=<your_xml> \
3 experiment_data_paths.output_dir=<results_dir>