Segment Anything 2 (SAM 2) — ONNX Models

ONNX-exported versions of Meta's Segment Anything Model 2 (SAM 2), ready for CPU/GPU inference with ONNX Runtime — no PyTorch required at runtime.

These models are used by AnyLabeling for AI-assisted image annotation, and exported by samexporter.

Looking for SAM 2.1? See vietanhdev/segment-anything-2.1-onnx-models — an improved version with better accuracy.

Available Models

File	Variant	Notes
`sam2_hiera_tiny.zip`	SAM 2 Hiera-Tiny	Smallest, fastest
`sam2_hiera_small.zip`	SAM 2 Hiera-Small	Good balance
`sam2_hiera_base_plus.zip`	SAM 2 Hiera-Base+	Higher accuracy
`sam2_hiera_large.zip`	SAM 2 Hiera-Large	Most accurate

Each zip contains two ONNX files: an encoder (runs once per image) and a decoder (runs interactively for each prompt).

Prompt Types

Point (+point / -point): click to include/exclude regions
Rectangle: draw a bounding box around the target object

Use with AnyLabeling (Recommended)

AnyLabeling is a desktop annotation tool with a built-in model manager that downloads, caches, and runs these models automatically — no coding required.

Install: pip install anylabeling
Launch: anylabeling
Click the Brain button → select a Segment Anything 2 model from the dropdown
Use point or rectangle prompts to segment objects

Use Programmatically with ONNX Runtime

import urllib.request, zipfile
url = "https://huggingface.co/vietanhdev/segment-anything-2-onnx-models/resolve/main/sam2_hiera_tiny.zip"
urllib.request.urlretrieve(url, "sam2_hiera_tiny.zip")
with zipfile.ZipFile("sam2_hiera_tiny.zip") as z:
    z.extractall("sam2_hiera_tiny")

Then use samexporter's inference module:

pip install samexporter
python -m samexporter.inference \
    --encoder_model sam2_hiera_tiny/sam2_hiera_tiny.encoder.onnx \
    --decoder_model sam2_hiera_tiny/sam2_hiera_tiny.decoder.onnx \
    --image photo.jpg \
    --prompt prompt.json \
    --output result.png \
    --sam_variant sam2

Re-export from Source

To re-export or customize the models using samexporter:

pip install samexporter
pip install git+https://github.com/facebookresearch/segment-anything-2.git

# Download SAM 2 checkpoints
cd original_models && bash download_sam2.sh && cd ..

# Export Tiny variant
python -m samexporter.export_sam2 \
    --checkpoint original_models/sam2_hiera_tiny.pt \
    --output_encoder output_models/sam2_hiera_tiny.encoder.onnx \
    --output_decoder output_models/sam2_hiera_tiny.decoder.onnx \
    --model_type sam2_hiera_tiny

# Or convert all SAM 2 variants at once:
bash convert_all_meta_sam2.sh

Related Repositories

Repo	Description
vietanhdev/samexporter	Export scripts, inference code, conversion tools
vietanhdev/anylabeling	Desktop annotation app powered by these models
vietanhdev/segment-anything-2.1-onnx-models	Improved SAM 2.1 ONNX models
facebookresearch/segment-anything-2	Original SAM 2 by Meta

License

The ONNX models are derived from Meta's SAM 2, released under the Apache 2.0 license. The export code is part of samexporter, released under the MIT license.

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