Depth Estimation
Transformers
Safetensors
tipsv2_dpt
feature-extraction
vision
surface-normals
semantic-segmentation
dense-prediction
custom_code
Instructions to use google/tipsv2-g14-dpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tipsv2-g14-dpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="google/tipsv2-g14-dpt", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("google/tipsv2-g14-dpt", trust_remote_code=True) model = AutoModel.from_pretrained("google/tipsv2-g14-dpt", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Use relative imports for sibling modules (fixes local loading, save_pretrained, pickling)
997dbf2
-
Update files for transformers integration (#1)
- Update files for transformers integration (4ef05dfb71515b744398cd13138247bdda40ca1e) - Remove image_encoder.py (9cb581a6eaea839f73f0f2703199242b223e65c0) - Remove image_encoder.py and update configuration_dpt.py (b7ed313673498a836f62f992ccb333f114d12ad0) - Remove image_encoder.py and update configuration_dpt.py (0caf79c5908a9c79e12042a763a791cfaf46ccb8) - Remove image_encoder.py and update configuration_dpt.py (6f7faf218966b3558a6747c878cfdfcad2a27951) - Update files (b9247c2418ba148117adfac0ee261867bbfe6096) Co-authored-by: guarin <guarin@users.noreply.huggingface.co>e0aed6e
-
Add arXiv tag to link the paper
Verified signaturedd658b5 -
Add arXiv paper link to citation
Verified signaturee6d2efa
-
Update example image URL to use HF-hosted ADE20K image
Gabriele7eec622
-
Add navigation table linking all variants and DPT heads
Gabriele109ccc8
-
Revert "Use device-agnostic code instead of hardcoded .cuda()"
GabrieleThis reverts commit cd27033a2dc3ddcfbc30db5b77fb565e4c4fe388.071bca8 -
Use device-agnostic code instead of hardcoded .cuda()
Gabrielecd27033 -
Add print statements with descriptive comments to code examples
Gabriele1cc1840 -
Use cat photo, add print statements to code examples
Gabriele28ae6d4 -
Fix zero-shot segmentation section, use public example image
Gabrielee3015bd -
Fix backbone link in Model details
Gabriele51a33d5
-
Update README
Gabriele76a1ecb -
Upload README.md with huggingface_hub
Verified signature4e6a83b
-
Upload model.safetensors with huggingface_hub
Verified signaturecf4ae00 -
Upload README.md with huggingface_hub
Verified signature4a196e1 -
Upload config.json with huggingface_hub
Verified signature247406c -
Upload dpt_head.py with huggingface_hub
Verified signature4a592df -
Upload modeling_dpt.py with huggingface_hub
Verified signature4e09276 -
Upload configuration_dpt.py with huggingface_hub
Verified signature10532f4 -
initial commit
Verified signature4c5ed74