micro-sam ViT-B (light microscopy) — ONNX (browser/WebGPU)

Promptable micro-sam vit_b_lm exported to ONNX for client-side inference with onnxruntime-web + WebGPU, used by the JAX Image Tools viewer (jit-ui#90) SAM segment tool.

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 (cosine ≈ 1.0000 vs fp32).
Box prompt = two points labelled 2/3; positive/negative points 1/0.

Export tooling: the sam-js project (export/export_sam_onnx.py, export/quantize_fp16.py). Base model: micro-sam vit_b_lm; underlying architecture Segment Anything (Apache-2.0). See micro-sam for model license.

Downloads last month: -; Downloads are not tracked for this model. How to track