patho-sam ViT-B (histopathology) — ONNX (browser/WebGPU)
Promptable patho-sam
(vit_b_histopathology, distributed via micro-sam's model registry) exported to
ONNX for client-side inference with onnxruntime-web + WebGPU, used by the JAX
Image Tools viewer (jit-ui#90) SAM segment tool. Finetuned for H&E / stained
tissue — the histopathology sibling of microsam-vit-b-lm-onnx.
Two graphs (SAM v1 I/O):
| file | in → out | run |
|---|---|---|
encoder.fp16.onnx (fp16, ~172 MB) |
image (1,3,1024,1024) fp32 → embedding (1,256,64,64) fp32 |
once per image |
decoder.onnx (fp32, ~16 MB) |
embedding + box/point prompts → mask (resized to orig size) | per prompt |
- Image preprocessing (resize long side → 1024, SAM normalize, pad) is done on the client; the encoder is pure tensor I/O. fp16 keeps fp32 I/O.
- fp16 produced with
onnxruntime.transformers.float16. - Box prompt = two points labelled
2/3; positive/negative points1/0.
Export tooling: the sam-js project (export/export_sam_onnx.py --microsam vit_b_histopathology).
Base model: patho-sam vit_b_histopathology (ViT-Base; Segment Anything, Apache-2.0).
See patho-sam / micro-sam for model license.