---
license: mit
base_model:
  - imgly/isnet-general-onnx
pipeline_tag: image-segmentation
library_name: transformers.js
tags:
  - background-removal
  - image-segmentation
  - isnet
  - onnx
  - int8
  - quantized
---

# ISNet General Use — INT8 Quantized

INT8 quantized version of [imgly/isnet-general-onnx](https://huggingface.co/imgly/isnet-general-onnx) for faster inference with minimal quality loss.

## Model Details

| Variant | Size | Dtype |
|---------|------|-------|
| Original (fp32) | 168 MB | fp32 |
| **This version (INT8)** | **43 MB** | **int8** |

## Usage with Transformers.js

```javascript
import { pipeline } from '@huggingface/transformers';

const segmenter = await pipeline('background-removal', '<username>/isnet-general-onnx-int8');
const result = await segmenter('image.jpg');
```

## Quantization

### Prerequisites

```bash
pip install -r requirements.txt
```

### Download the fp32 source model

```bash
huggingface-cli download imgly/isnet-general-onnx onnx/model.onnx --local-dir .
```

### Run quantization

```bash
python quantize.py
```

Output: `onnx/model_int8.onnx` (~43 MB, ~75% smaller than fp32)

### How it works

Uses ONNX Runtime's `quantize_dynamic` with `QuantType.QInt8`:

```python
from onnxruntime.quantization import quantize_dynamic, QuantType

quantize_dynamic(
    model_input='onnx/model.onnx',
    model_output='onnx/model_int8.onnx',
    weight_type=QuantType.QInt8,
)
```

## License

MIT — same as the original [imgly/isnet-general-onnx](https://huggingface.co/imgly/isnet-general-onnx) model.

## Credits

- Original model: [imgly/isnet-general-onnx](https://huggingface.co/imgly/isnet-general-onnx)
- ISNet architecture: [IS-Net](https://github.com/xuebinqin/DIS)