Instructions to use Bingsu/adetailer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use Bingsu/adetailer with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("Bingsu/adetailer", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -89,4 +89,15 @@ pred = Image.fromarray(pred)
|
|
| 89 |
pred
|
| 90 |
```
|
| 91 |
|
| 92 |
-

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 89 |
pred
|
| 90 |
```
|
| 91 |
|
| 92 |
+

|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
## Unsafe files
|
| 96 |
+
|
| 97 |
+

|
| 98 |
+
|
| 99 |
+
Since `getattr` is classified as a dangerous pickle function, any segmentation model that uses it is classified as unsafe.
|
| 100 |
+
|
| 101 |
+
All models were created and saved using the official [ultralytics](https://github.com/ultralytics/ultralytics) library, so it's okay to use files downloaded from a trusted source.
|
| 102 |
+
|
| 103 |
+
See also: https://huggingface.co/docs/hub/security-pickle
|