Image Feature Extraction
Transformers
Safetensors
page
feature-extraction
gaze-estimation
gaze-target-estimation
dinov3
custom_code
Instructions to use Octopus1/page-vitb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Octopus1/page-vitb with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="Octopus1/page-vitb", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Octopus1/page-vitb", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "image_processor_type": "PaGEImageProcessor", | |
| "auto_map": { | |
| "AutoImageProcessor": "Octopus1/PaGE--modeling_page.PaGEImageProcessor" | |
| }, | |
| "scene_size": [ | |
| 512, | |
| 512 | |
| ], | |
| "head_size": [ | |
| 256, | |
| 256 | |
| ], | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "resample": 2 | |
| } |