Microsam Vit T Lm Onnx

--- license: cc-by-4.0 tags: - segment-anything - micro-sam - mobile-sam - onnx - webgpu - microscopy - image-segmentation library_name: onnxruntime --- # micro-sam ViT-T (light microscopy) — ONNX (browser/WebGPU) Promptable [micro-sam](https://github.com/computational-cell-analytics/micro-sam) `vit_t_lm` (TinyViT encoder, via [MobileSAM](https://github.com/ChaoningZhang/MobileSAM)) exported to ONNX for client-side inference with **onnxruntime-web + WebGPU**, used by the JAX Image Tools viewer (jit-ui#90) SAM segment tool. This is the **tiny** sibling of `microsam-vit-b-lm-onnx` — ~12x smaller encoder, ideal for fast in-browser segmentation. Two graphs (SAM v1 I/O): | file | in → out | run | |---|---|---| | `encoder.fp16.onnx` (fp16, ~14 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 points `1`/`0`. Export tooling: the `sam-js` project (`export/export_sam_onnx.py --microsam vit_t_lm`). Base model: micro-sam `vit_t_lm` (TinyViT / MobileSAM, Apache-2.0); underlying architecture Segment Anything (Apache-2.0). See micro-sam for model license.

Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Library onnxruntime · Repo Ballon999/microsam-vit-t-lm-onnx