Instructions to use Octopus1/PaGE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Octopus1/PaGE with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Octopus1/PaGE", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add Demo Link
Browse files
README.md
CHANGED
|
@@ -14,7 +14,8 @@ language:
|
|
| 14 |
|
| 15 |
**Code:** [github.com/OctopusWen/PaGE](https://github.com/OctopusWen/PaGE) •
|
| 16 |
**Project page:** [page-26.github.io](https://page-26.github.io/) •
|
| 17 |
-
**Paper:** [arXiv:XXXX.XXXXX](https://arxiv.org/abs/XXXX.XXXXX)
|
|
|
|
| 18 |
|
| 19 |
PaGE (Practical Gaze Estimator) is a gaze target estimation model that predicts where a person
|
| 20 |
is looking in a scene. Gaze target estimation combines high-level understanding of global scene
|
|
|
|
| 14 |
|
| 15 |
**Code:** [github.com/OctopusWen/PaGE](https://github.com/OctopusWen/PaGE) •
|
| 16 |
**Project page:** [page-26.github.io](https://page-26.github.io/) •
|
| 17 |
+
**Paper:** [arXiv:XXXX.XXXXX](https://arxiv.org/abs/XXXX.XXXXX) •
|
| 18 |
+
**Demo:** [page-crossgaze-page.hf.space](https://page-crossgaze-page.hf.space/)
|
| 19 |
|
| 20 |
PaGE (Practical Gaze Estimator) is a gaze target estimation model that predicts where a person
|
| 21 |
is looking in a scene. Gaze target estimation combines high-level understanding of global scene
|