Depth Estimation
Transformers
Safetensors
tipsv2_dpt
feature-extraction
vision
surface-normals
semantic-segmentation
dense-prediction
custom_code
Instructions to use google/tipsv2-b14-dpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tipsv2-b14-dpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="google/tipsv2-b14-dpt", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("google/tipsv2-b14-dpt", trust_remote_code=True) model = AutoModel.from_pretrained("google/tipsv2-b14-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)
da81b55
-
Update files for transformers integration (#1)
- Update files for transformers integration (a77a1cab99ad561931a108d40cf6ecefd9211734) - Remove image_encoder.py (80d568a157731bc00799c6e2492f47535c2aeb9b) - Remove image_encoder.py and update configuration_dpt.py (4b9eb4bb88f1a303ec6b2d6ee46e9e8f99fdc114) - Remove image_encoder.py and update configuration_dpt.py (f5c840c13b3334f02f0b1fb6d39bd3ef0ebef023) - Remove image_encoder.py and update configuration_dpt.py (d2254357d375c346b8ea7d6df6b33943d467b5f2) - Update files (88dc55074c2939a341a1b630620ed88550d0f31f) Co-authored-by: guarin <guarin@users.noreply.huggingface.co>7ab11ac
-
Add arXiv tag to link the paper
Verified signature5b9d7c2 -
Add arXiv paper link to citation
Verified signature0663787
-
Update example image URL to use HF-hosted ADE20K image
Gabriele272325b
-
Add navigation table linking all variants and DPT heads
Gabriele47b7200
-
Revert "Use device-agnostic code instead of hardcoded .cuda()"
GabrieleThis reverts commit 30470873043a863ff7e3798b5735256796a41594.2a2698d -
Use device-agnostic code instead of hardcoded .cuda()
Gabriele3047087 -
Add print statements with descriptive comments to code examples
Gabriele1bfe88b -
Use cat photo, add print statements to code examples
Gabriele05c6fd6 -
Fix zero-shot segmentation section, use public example image
Gabrieleb237704 -
Fix backbone link in Model details
Gabrieleb6e72cb
-
Update README
Gabriele4679e95 -
Upload README.md with huggingface_hub
Verified signature2b0455f
-
Upload model.safetensors with huggingface_hub
Verified signature8e43309 -
Upload README.md with huggingface_hub
Verified signature8301d59 -
Upload config.json with huggingface_hub
Verified signaturec8f35b6 -
Upload dpt_head.py with huggingface_hub
Verified signaturee08e2c1 -
Upload modeling_dpt.py with huggingface_hub
Verified signatured4f10cf -
Upload configuration_dpt.py with huggingface_hub
Verified signature2bc3590 -
initial commit
Verified signaturefb1071a