mito_aff_setup53_16nm-ft2

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 172×172×172 voxels in and 84×84×84 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 9 epoch(s), to a final loss of 0.313 (2026-10-28). The annotations were painted on precomputed://gs://liconn-public/ExPID82_1/image_230130b.

Open it

• Try it in the browser: cellmap-flow opens with the model chosen; connect any volume to run it.
• Open it on the dataset it was trained on.
• 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-ft2/mito_aff_setup53_16nm-ft2.

mito_aff_setup53_16nm-ft2/manifest.json says the model's voxel sizes, blocks, channels and input normalization in cellmap-flow's format, and mito_aff_setup53_16nm-ft2/mito_aff_setup53_16nm-ft2.onnx is the ONNX graph.