---
library_name: onnx
tags:
  - sam2
  - image-segmentation
  - promptable-segmentation
  - vision
  - onnx
  - inference4j
license: apache-2.0
pipeline_tag: mask-generation
---

# SAM 2.1 Hiera Tiny — ONNX

FP32 ONNX export of [facebook/sam2.1-hiera-tiny](https://huggingface.co/facebook/sam2.1-hiera-tiny), split into an image encoder and a prompt encoder/mask decoder for point- and box-prompted image segmentation. The ONNX graphs are mirrored unchanged from the [onnx-community export](https://huggingface.co/onnx-community/sam2.1-hiera-tiny-ONNX).

Mirrored for use with [inference4j](https://github.com/inference4j/inference4j), an inference-only AI library for Java.

## Original Source

- **Repository:** [Meta (ONNX export by onnx-community)](https://huggingface.co/facebook/sam2.1-hiera-tiny)
- **License:** apache-2.0

## Usage with inference4j

```java
try (Sam2Segmenter segmenter = Sam2Segmenter.builder().build()) {
    SegmentationMask mask = segmenter.segment(
        Path.of("photo.jpg"),
        List.of(new PromptPoint(320, 240, true)));
    ImageIO.write(mask.toImage(), "png", Path.of("mask.png").toFile());
}
```

## Model Details

| Property | Value |
|----------|-------|
| Architecture | SAM 2.1 Hiera Tiny |
| Task | Promptable image segmentation |
| Graphs | `vision_encoder.onnx` and `prompt_encoder_mask_decoder.onnx` (opset 18, FP32) |
| External data | Each graph loads its matching `.onnx_data` sidecar from the same directory |
| Image input | `pixel_values`: `[batch, 3, 1024, 1024]` float32, RGB |
| Image preprocessing | Resize to 1024 x 1024 without preserving aspect ratio; rescale by 1/255; ImageNet mean/std normalization |
| Prompts | Point coordinates and boxes use the 1024 x 1024 input coordinate space |
| Mask output | `pred_masks`: `[batch, prompts, 3, 256, 256]` float32 low-resolution logits |
| Mask selection | Choose one of three candidate masks using `iou_scores` |
| Refinement | No previous-mask (`mask_input`) input; iterative mask refinement is not supported by this export |

## License

The original SAM 2.1 model and weights are licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). Original model by [Meta](https://huggingface.co/facebook/sam2.1-hiera-tiny); ONNX conversion by [onnx-community](https://huggingface.co/onnx-community/sam2.1-hiera-tiny-ONNX).

## Files

The FP32 model remains split into two ONNX graphs and their external-data sidecars:

- `vision_encoder.onnx` + `vision_encoder.onnx_data`
- `prompt_encoder_mask_decoder.onnx` + `prompt_encoder_mask_decoder.onnx_data`

All four files must remain in the same directory. The sidecars are deliberately not
folded into the graph files.

## Prompt Encoding

- Foreground point label: `1`
- Background point label: `0`
- Padding point label: `-10`
- Box layout: `(x1, y1, x2, y2)`

Coordinates are expressed in the resized 1024 x 1024 image space. See the source
`processor_config.json` for processor defaults and the inference4j wrapper for conversion
from original-image coordinates.

## Outputs

The decoder returns three candidate low-resolution mask logits per prompt, their
`iou_scores`, and `object_score_logits`. Resize the selected logits to the original image
size and threshold at zero to obtain a binary mask.