mito_aff_setup53_16nm-ft5

A mito_affinities model for electron microscopy: it predicts mito_aff_z, mito_aff_y, mito_aff_x (raw logits (apply sigmoid / threshold at 0)), from 16 nm voxels to 16 nm voxels, in blocks of 124×124×124 voxels in and 36×36×36 out (fp16).

Finetuned in the browser with cellmap-flow 0.3.0 from cellmap/onnx-web-models/setup_53 (Unet3dIso): its whole network was trained on annotations painted in the browser for 2 epoch(s), to a final loss of 0.333 (2026-11-11).

Open it

• Try it in the browser: cellmap-flow opens with the model chosen; connect any volume to run it.
• Anywhere cellmap-flow takes a model (Add a model in the dashboard's Models tab, in the browser or on a server): ackermand/mito_aff_setup53_16nm-ft5/mito_aff_setup53_16nm-ft5.

mito_aff_setup53_16nm-ft5/manifest.json says the model's voxel sizes, blocks, channels and input normalization in cellmap-flow's format, and mito_aff_setup53_16nm-ft5/mito_aff_setup53_16nm-ft5.onnx is the ONNX graph.