Tipsv2 So400m14 Dpt
DPT (Dense Prediction Transformer) heads for depth estimation, surface normal prediction, and semantic segmentation on top of the frozen TIPSv2 SO400m/14 backbone. The backbone is loaded automatically. The depth and...
Source du modèle
- Type
- Other
- Taille du fichier
- 1,99 GB
- Version
- vRevision 545c26e
- Mis à jour
- 10 oct. 2026
- Téléchargements
- 202
- Source
- Hugging Face
Description de la source
TIPSv2 — SO400m/14 DPT Heads
DPT (Dense Prediction Transformer) heads for depth estimation, surface normal prediction, and semantic segmentation on top of the frozen TIPSv2 SO400m/14 backbone. The backbone is loaded automatically. The depth and normals heads are trained on the NYU Depth V2 dataset and segmentation is trained on the ADE20K dataset (150 classes).
| Variant | Vision params | Text params | Embed dim | DPT Heads |
|---|---|---|---|---|
| B/14 | 86M | 110M | 768 | B/14-dpt |
| L/14 | 303M | 184M | 1024 | L/14-dpt |
| SO400m/14 | 412M | 448M | 1152 | SO400m/14-dpt |
| g/14 | 1.1B | 389M | 1536 | g/14-dpt |
Usage
pip install transformers torch torchvision sentencepiece
from transformers import AutoModel
from torchvision import transforms
from PIL import Image
import requests
model = AutoModel.from_pretrained("google/tipsv2-so400m14-dpt", trust_remote_code=True)
model.eval().cuda()
url = "https://huggingface.co/spaces/google/tipsv2/resolve/main/examples/depth/ade20k_00014.png"
image = Image.open(requests.get(url, stream=True).raw)
transform = transforms.Compose([transforms.Resize((448, 448)), transforms.ToTensor()])
pixel_values = transform(image).unsqueeze(0).cuda()
# All tasks at once
outputs = model(pixel_values)
print(outputs.depth.shape) # (1, 1, 448, 448) — depth map
print(outputs.normals.shape) # (1, 3, 448, 448) — surface normals
print(outputs.segmentation.shape) # (1, 150, 448, 448) — segmentation logits
# Or individual tasks (only runs the requested head)
depth = model.predict_depth(pixel_values)
normals = model.predict_normals(pixel_values)
seg = model.predict_segmentation(pixel_values)
print(seg.argmax(dim=1).shape) # (1, 448, 448) — per-pixel class prediction
Model details
- Backbone: TIPSv2 SO400m/14 (loaded automatically)
- Heads: ~120M total params (depth + normals + segmentation)
- Depth & normals: NYU Depth V2
- Segmentation: ADE20K, 150 classes
- Input: images in
[0, 1]range, any resolution (multiples of 14 recommended)
License
Apache 2.0
Citation
@inproceedings{cao2026tipsv2,
title = {{TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment}},
author = {Cao, Bingyi and Chen, Koert and Maninis, Kevis-Kokitsi and Chen, Kaifeng and Karpur, Arjun and Xia, Ye and Dua, Sahil and Dabral, Tanmaya and Han, Guangxing and Han, Bohyung and Ainslie, Joshua and Bewley, Alex and Jacob, Mithun and Wagner, Rene and Ramos, Washington and Choromanski, Krzysztof and Seyedhosseini, Mojtaba and Zhou, Howard and Araujo, Andre},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2026},
url = {https://arxiv.org/abs/2604.12012}
}
Sources
1 source
Sources
1 sourceVérifié 10 oct.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: apache-2.0 tags: - vision - depth-estimation - surface-normals - semantic-segmentation - dense-prediction - arxiv:2604.12012 library_name: transformers pipeline_tag: depth-estimation --- # TIPSv2 — SO400m/14 DPT Heads DPT (Dense Prediction Transformer) heads for depth estimation, surface normal prediction, and semantic segmentation on top of the frozen [TIPSv2 SO400m/14](https://huggingface.co/google/tipsv2-so400m14) backbone. The backbone is loaded automatically. The depth and normals heads are trained on the NYU Depth V2 dataset and segmentation is trained on the ADE20K dataset (150 classes). | Variant | Vision params | Text params | Embed dim | DPT Heads | |---------|--------------|-------------|-----------|-----------| | [B/14](https://huggingface.co/google/tipsv2-b14) | 86M | 110M | 768 | [B/14-dpt](https://huggingface.co/google/tipsv2-b14-dpt) | | [L/14](https://huggingface.co/google/tipsv2-l14) | 303M | 184M | 1024 | [L/14-dpt](https://huggingface.co/google/tipsv2-l14-dpt) | | [SO400m/14](https://huggingface.co/google/tipsv2-so400m14) | 412M | 448M | 1152 | [SO400m/14-dpt](https://huggingface.co/google/tipsv2-so400m14-dpt) | | [g/14](https://huggingface.co/google/tipsv2-g14) | 1.1B | 389M | 1536 | [g/14-dpt](https://huggingface.co/google/tipsv2-g14-dpt) | ## Usage ```bash pip install transformers torch torchvision sentencepiece ``` ```python from transformers import AutoModel from torchvision import transforms from PIL import Image import requests model = AutoModel.from_pretrained("google/tipsv2-so400m14-dpt", trust_remote_code=True) model.eval().cuda() url = "https://huggingface.co/spaces/google/tipsv2/resolve/main/examples/depth/ade20k_00014.png" image = Image.open(requests.get(url, stream=True).raw) transform = transforms.Compose([transforms.Resize((448, 448)), transforms.ToTensor()]) pixel_values = transform(image).unsqueeze(0).cuda() # All tasks at once outputs = model(pixel_values) print(outputs.depth.shape) # (1, 1, 448, 448) — depth map print(outputs.normals.shape) # (1, 3, 448, 448) — surface normals print(outputs.segmentation.shape) # (1, 150, 448, 448) — segmentation logits # Or individual tasks (only runs the requested head) depth = model.predict_depth(pixel_values) normals = model.predict_normals(pixel_values) seg = model.predict_segmentation(pixel_values) print(seg.argmax(dim=1).shape) # (1, 448, 448) — per-pixe...
Source context: 202 downloads · 12 likes · Pipeline depth-estimation · Library transformers · Repo google/tipsv2-so400m14-dpt
Source context: 224 downloads · 9 likes · Pipeline depth-estimation · Library transformers · Repo google/tipsv2-so400m14-dpt
