Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,9 @@ tags:
|
|
| 21 |
|
| 22 |
> DOZE-GUARD-RLDD [Real-Time Distracted Driver Detection] is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for binary image classification. It is trained to detect whether a person in the image is drowsy or non-drowsy using the SiglipForImageClassification architecture.
|
| 23 |
|
|
|
|
|
|
|
|
|
|
| 24 |
> [!note]
|
| 25 |
*SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features* https://arxiv.org/pdf/2502.14786
|
| 26 |
|
|
@@ -114,12 +117,10 @@ if __name__ == "__main__":
|
|
| 114 |
|
| 115 |
## Demo Inference
|
| 116 |
|
| 117 |
-
|
| 118 |
|
| 119 |
|
| 120 |
|
| 121 |
|
| 122 |
-
|
| 123 |
## Intended Use
|
| 124 |
|
| 125 |
**DOZE-GUARD-RLDD** is useful in scenarios such as:
|
|
|
|
| 21 |
|
| 22 |
> DOZE-GUARD-RLDD [Real-Time Distracted Driver Detection] is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for binary image classification. It is trained to detect whether a person in the image is drowsy or non-drowsy using the SiglipForImageClassification architecture.
|
| 23 |
|
| 24 |
+
> [!note]
|
| 25 |
+
> DOZE GUARD RLDD detection works best with crisp and high-quality images. Noisy images are not recommended for validation.
|
| 26 |
+
|
| 27 |
> [!note]
|
| 28 |
*SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features* https://arxiv.org/pdf/2502.14786
|
| 29 |
|
|
|
|
| 117 |
|
| 118 |
## Demo Inference
|
| 119 |
|
|
|
|
| 120 |
|
| 121 |
|
| 122 |
|
| 123 |
|
|
|
|
| 124 |
## Intended Use
|
| 125 |
|
| 126 |
**DOZE-GUARD-RLDD** is useful in scenarios such as:
|