Downloads · 30 days
0
fastsam-onnx
anakhiu/fastsam-onnx
fastsam-onnx is a machine learning model from anakhiu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for onnx. The card lists the license as apache-2.0.
ONNX export of FastSAM-s (YOLOv8s-seg, ~11.8M params) for click-to-select segmentation on CPU. Used by MicrostockEngine to mask a watermark from a single click before inpainting.
Access
Public
Updated Jul 27, 2026
Repo size
47.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx47.6 MB · 100%
At a glance
- Library
- onnx
- License
- apache-2.0
- Access
- Public
- Created
- Jul 27, 2026
- Updated
- Jul 27, 2026
- SHA
- 8bb24a5b
Base models
Model card
From the Hugging Face model README
FastSAM-s ONNX (fp32)
ONNX export of FastSAM-s (YOLOv8s-seg, ~11.8M params) for click-to-select segmentation on CPU. Used by MicrostockEngine to mask a watermark from a single click before inpainting.
Provenance
- Source weights: ultralytics
FastSAM-s.pt, assets releasev8.4.0. - Export:
ultralytics8.4.107,imgsz=1024,opset=17, simplified withonnxslim. - No quantization — full fp32.
I/O contract
- input
images:[1, 3, 1024, 1024]float32, values0..1, letterboxed top-left with pad value114/255. - output0:
[1, 37, 21504]— per anchor: 4 box (xywh, in 1024-space) + 1 class score (sigmoid already applied; FastSAM is class-agnostic) + 32 mask coefficients. - output1:
[1, 32, 256, 256]— 32 mask prototypes at a quarter of input resolution. An instance mask issigmoid(sum(coeff_i * proto_i)), cropped to its own box.
Licence
Apache-2.0 (CASIA-IVA-Lab/FastSAM). The weights were trained with Ultralytics code (AGPL-3.0); noted here so the provenance is not lost.
- Library
- onnx
- License
- apache-2.0
- Created
- Jul 27, 2026
- Updated
- Jul 27, 2026