Page Vitb Screen
Base distilled student fine-tuned for screen / webcam gaze. Part of the PaGE gaze target estimation family.
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 715 MB
- Versão
- vRevision 295437f
- Atualizado
- 10 de out. de 2026
- Downloads
- 10
- Fonte
- Hugging Face
Descrição da fonte
PaGE ViT-B Distill (Screen)
Base distilled student fine-tuned for screen / webcam gaze. Part of the PaGE gaze target estimation family.
- Backbone: DINOv3 ViT-B (derivative of DINOv3, full-parameter trained)
- Params: ~90M
- Scene input: 512×512, Head input: 256×256, Heatmap output: 64×64
- Source checkpoint:
vitb_distill_screen.pt
Self-contained weights
This checkpoint includes the full DINOv3 backbone weights in its safetensors files. No external
DINOv3 weights are downloaded — the DINOv3 model structure is provided by transformers==5.6.2
(built-in dinov3_vit), and the backbone weights here are derivative weights from full-parameter
training of DINOv3. The model code (modeling_page.py) is loaded automatically from
Octopus1/PaGE via auto_map when you pass
trust_remote_code=True.
Installation
pip install torch torchvision timm "transformers==5.6.2" safetensors pillow
Tested with transformers 5.6.2.
Usage
from transformers import AutoModel, AutoImageProcessor
from PIL import Image
import torch
repo = "Octopus1/page-vitb-screen"
model = AutoModel.from_pretrained(repo, trust_remote_code=True).eval()
processor = AutoImageProcessor.from_pretrained(repo, trust_remote_code=True)
scene = Image.open("scene.jpg").convert("RGB")
head = Image.open("head.jpg").convert("RGB")
inputs = processor(scene, head_crops=[head], bboxes=[[(0.10, 0.10, 0.30, 0.40)]])
with torch.no_grad():
out = model(inputs)
heatmap = out["heatmap"][0] # [Np, 64, 64]
inout = out["inout"][0] # [Np]
Inputs / Outputs
See the family README for the full spec.
- Input dict:
images(list of[B,3,512,512]),head_images(list of[sum(Np),3,256,256]),bboxes(per-image list of(xmin,ymin,xmax,ymax)in[0,1]). - Output dict:
heatmap(list of[Np,64,64], sigmoid),inout(list of[Np], sigmoid).
License
- The PaGE decoder and gaze heads are released under the MIT License (see
LICENSE). - The DINOv3 backbone is a derivative work of DINOv3 (facebook/dinov3). The backbone was initialized from the public DINOv3 self-supervised weights and then trained in full (all parameters updated) as part of PaGE training — i.e. the backbone weights here are derivative weights produced by full-parameter training of DINOv3, not the original DINOv3 weights verbatim.
- DINOv3 is released by Meta AI under the Meta DINO License (see
DINOv3_LICENSE.md). Under its Section 1.b.i, derivative works of DINOv3 (including these backbone weights) are distributed under the DINO License terms, andDINOv3_LICENSE.mdmust accompany any redistribution. - By using or redistributing this model you agree to the DINO License for the DINOv3-derived portions.
See the family README for full license details.
Fontes
1 fonte
Fontes
1 fonteVerificado 10 de out.
Artefatos de modelo
1 artefato
Artefatos de modelo
1 artefatoTrechos de fonte
3 trechos
Trechos de fonte
3 trechos--- license: mit library_name: transformers tags: - gaze-estimation - gaze-target-estimation - dinov3 pipeline_tag: image-feature-extraction --- # PaGE ViT-B Distill (Screen) Base distilled student fine-tuned for screen / webcam gaze. Part of the [PaGE](https://huggingface.co/Octopus1/PaGE) gaze target estimation family. - **Backbone:** DINOv3 ViT-B (derivative of DINOv3, full-parameter trained) - **Params:** ~90M - **Scene input:** 512×512, **Head input:** 256×256, **Heatmap output:** 64×64 - **Source checkpoint:** `vitb_distill_screen.pt` ## Self-contained weights This checkpoint includes the full DINOv3 backbone weights in its `safetensors` files. **No external DINOv3 weights are downloaded** — the DINOv3 model *structure* is provided by `transformers==5.6.2` (built-in `dinov3_vit`), and the backbone weights here are derivative weights from full-parameter training of DINOv3. The model code (`modeling_page.py`) is loaded automatically from [`Octopus1/PaGE`](https://huggingface.co/Octopus1/PaGE) via `auto_map` when you pass `trust_remote_code=True`. ## Installation ```bash pip install torch torchvision timm "transformers==5.6.2" safetensors pillow ``` Tested with `transformers` 5.6.2. ## Usage ```python from transformers import AutoModel, AutoImageProcessor from PIL import Image import torch repo = "Octopus1/page-vitb-screen" model = AutoModel.from_pretrained(repo, trust_remote_code=True).eval() processor = AutoImageProcessor.from_pretrained(repo, trust_remote_code=True) scene = Image.open("scene.jpg").convert("RGB") head = Image.open("head.jpg").convert("RGB") inputs = processor(scene, head_crops=[head], bboxes=[[(0.10, 0.10, 0.30, 0.40)]]) with torch.no_grad(): out = model(inputs) heatmap = out["heatmap"][0] # [Np, 64, 64] inout = out["inout"][0] # [Np] ``` ## Inputs / Outputs See the family [README](https://huggingface.co/Octopus1/PaGE) for the full spec. - Input dict: `images` (list of `[B,3,512,512]`), `head_images` (list of `[sum(Np),3,256,256]`), `bboxes` (per-image list of `(xmin,ymin,xmax,ymax)` in `[0,1]`). - Output dict: `heatmap` (list of `[Np,64,64]`, sigmoid), `inout` (list of `[Np]`, sigmoid). ## License - The PaGE decoder and gaze heads are released under the **MIT License** (see `LICENSE`). - The **DINOv3 backbone is a derivative work of DINOv3** ([facebook/dinov3](https://huggingface.co/facebook/dinov3)). The b...
Source context: 10 downloads · 0 likes · Pipeline image-feature-extraction · Library transformers · Repo Octopus1/page-vitb-screen
Source context: 7159 downloads · 0 likes · Pipeline image-feature-extraction · Library transformers · Repo Octopus1/page-vitb-screen
