Downloads · 30 days
0
microsam-vit-b-lm-onnx
jax-image-tools/microsam-vit-b-lm-onnx
microsam-vit-b-lm-onnx is a image segmentation model from jax-image-tools. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for onnxruntime. The card lists the license as cc-by-4.0.
Promptable micro-sam vitblm exported to ONNX for client-side inference with onnxruntime-web + WebGPU, used by the JAX Image Tools viewer (jit-ui90) SAM segment tool.
Access
Public
Updated Aug 26, 2026
Repo size
196 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx196 MB · 100%
At a glance
- Task
- Image Segmentation
- Library
- onnxruntime
- License
- cc-by-4.0
- Access
- Public
- Created
- Aug 26, 2026
- Updated
- Aug 26, 2026
- SHA
- 38e1fa16
Model card
From the Hugging Face model README
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 points1/0.
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.
- Task
- Image Segmentation
- Library
- onnxruntime
- License
- cc-by-4.0
- Created
- Aug 26, 2026
- Updated
- Aug 26, 2026