Depth Estimation
Transformers
Safetensors
tipsv2_dpt
feature-extraction
vision
surface-normals
semantic-segmentation
dense-prediction
custom_code
Instructions to use google/tipsv2-so400m14-dpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tipsv2-so400m14-dpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="google/tipsv2-so400m14-dpt", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("google/tipsv2-so400m14-dpt", trust_remote_code=True) model = AutoModel.from_pretrained("google/tipsv2-so400m14-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)
545c26e
-
Update files for transformers integration (#1)
- Update files for transformers integration (800359da67742d71a4d4a7f5027590a9db951395) - Remove image_encoder.py (b94e3be502b61614b56c8d52b8c7ced45f3b789d) - Remove image_encoder.py and update configuration_dpt.py (bb165407c42187e3f2403b48d788840e7e70760a) - Remove image_encoder.py and update configuration_dpt.py (ee319e47d98e01bc75c7057d84ef1d33fd13a1aa) - Remove image_encoder.py and update configuration_dpt.py (11c04fac06cec21ed8896b55e522051ec22de242) - Update files (ccad5c042021efa62965f31bda418bffaeaee117) Co-authored-by: guarin <guarin@users.noreply.huggingface.co>f1dfed3
-
Add arXiv tag to link the paper
Verified signature36b73af -
Add arXiv paper link to citation
Verified signature4ee765b
-
Update example image URL to use HF-hosted ADE20K image
Gabriele551339b
-
Add navigation table linking all variants and DPT heads
Gabriele824676e
-
Revert "Use device-agnostic code instead of hardcoded .cuda()"
GabrieleThis reverts commit a8bfb7d29d4ced0fbdc340639389fb9c1df94585.5300c3b -
Use device-agnostic code instead of hardcoded .cuda()
Gabrielea8bfb7d -
Add print statements with descriptive comments to code examples
Gabrieleb800f0a -
Use cat photo, add print statements to code examples
Gabriele982002b -
Fix zero-shot segmentation section, use public example image
Gabriele4482ee7 -
Fix backbone link in Model details
Gabriele964153d
-
Update README
Gabriele06ff717 -
Upload README.md with huggingface_hub
Verified signature50a51ff
-
Upload model.safetensors with huggingface_hub
Verified signatureebb9752 -
Upload README.md with huggingface_hub
Verified signature5178988 -
Upload config.json with huggingface_hub
Verified signature8da89eb -
Upload dpt_head.py with huggingface_hub
Verified signatureab33843 -
Upload modeling_dpt.py with huggingface_hub
Verified signature233ec29 -
Upload configuration_dpt.py with huggingface_hub
Verified signature2dbacf7 -
initial commit
Verified signature9c3f8c8