setup_54_2d — 2D-slice mito student (experimental)
One z-slice in, one slice out: input float32 [1,1,1,N,N] → output float32 raw logits [1,3,1,N-88,N-88]
(mito affinities z, y, x; threshold at 0). 16 nm, input norm uint8/255*2-1.
Distilled from the 3D model setup_54 (PyTorch: cellmap/mito-aff-resunet-setup-54): every 3D kernel collapsed to 2D (sum of depth taps) and
fine-tuned to reproduce the 3D predictions slice by slice. Training step, per-file fidelity and sizes are in
manifest.json (same schema as the 3D folders, per-axis input_size / output_size).
cellmap-flow serverless: Input size 1,N,N, Output size 1,N-88,N-88, voxel 16,16,16, Channels 3, Has channel axis true.