Instructions to use moonbox-dev/BiRefNet_lite-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- BiRefNet
How to use moonbox-dev/BiRefNet_lite-ONNX with BiRefNet:
# Option 1: use with transformers from transformers import AutoModelForImageSegmentation birefnet = AutoModelForImageSegmentation.from_pretrained("moonbox-dev/BiRefNet_lite-ONNX", trust_remote_code=True)# Option 2: use with BiRefNet # Install from https://github.com/ZhengPeng7/BiRefNet from models.birefnet import BiRefNet model = BiRefNet.from_pretrained("moonbox-dev/BiRefNet_lite-ONNX") - Notebooks
- Google Colab
- Kaggle
Model card and the original license
Browse files
README.md
CHANGED
|
@@ -26,6 +26,7 @@ its own score on the eval set (details under *How to run*).
|
|
| 26 |
| Precision | File | Size | sha256 | Benchmark |
|
| 27 |
|---|---|---|---|---|
|
| 28 |
| fp16 | [`fp16/model.onnx`](https://huggingface.co/moonbox-dev/BiRefNet_lite-ONNX/blob/main/fp16/model.onnx) | 0.11 GB | `311cfd8088ee` | vs fp32: IoU 0.9981, MAE 0.0002; DIS5K MAE 0.0171, S 0.939 |
|
|
|
|
| 29 |
|
| 30 |
## How to run
|
| 31 |
|
|
|
|
| 26 |
| Precision | File | Size | sha256 | Benchmark |
|
| 27 |
|---|---|---|---|---|
|
| 28 |
| fp16 | [`fp16/model.onnx`](https://huggingface.co/moonbox-dev/BiRefNet_lite-ONNX/blob/main/fp16/model.onnx) | 0.11 GB | `311cfd8088ee` | vs fp32: IoU 0.9981, MAE 0.0002; DIS5K MAE 0.0171, S 0.939 |
|
| 29 |
+
| int8 | [`int8/model.onnx`](https://huggingface.co/moonbox-dev/BiRefNet_lite-ONNX/blob/main/int8/model.onnx) | 0.09 GB | `97dd832a68fe` | vs fp32: IoU 0.9972, MAE 0.0004; DIS5K MAE 0.0171, S 0.939 |
|
| 30 |
|
| 31 |
## How to run
|
| 32 |
|