Depth Estimation
Transformers
Safetensors
tipsv2_dpt
feature-extraction
vision
surface-normals
semantic-segmentation
dense-prediction
custom_code
Instructions to use google/tipsv2-l14-dpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tipsv2-l14-dpt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="google/tipsv2-l14-dpt", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("google/tipsv2-l14-dpt", trust_remote_code=True) model = AutoModel.from_pretrained("google/tipsv2-l14-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)
eaca790
-
Update files for transformers integration (#1)
- Update files for transformers integration (1ade58d8c4ab689faf23ad10e5286d720ed7e31b) - Remove image_encoder.py (831065605cd206a5a8654c40cc38a768c2ac07bd) - Remove image_encoder.py and update configuration_dpt.py (f112fddeb923a1b87ba1ca66fafa3373e5f9f677) - Remove image_encoder.py and update configuration_dpt.py (b00eec933d78a46bee6884e5f60d2e8f94e9a1ca) - Remove image_encoder.py and update configuration_dpt.py (d378506c391745a31a601bf598b24b1fe002314d) - Update files (4f9d466ad4bca8ad141f9c348feed7277bd9a8e9) Co-authored-by: guarin <guarin@users.noreply.huggingface.co>7df8807
-
Add arXiv tag to link the paper
Verified signature3deb9de -
Add arXiv paper link to citation
Verified signature40070ea
-
Update example image URL to use HF-hosted ADE20K image
Gabriele690a850
-
Add navigation table linking all variants and DPT heads
Gabriele22d3549
-
Revert "Use device-agnostic code instead of hardcoded .cuda()"
GabrieleThis reverts commit 4b9afccd53c71186db655e4eb59e0c9c4ee8cc1e.d8d2fe7 -
Use device-agnostic code instead of hardcoded .cuda()
Gabriele4b9afcc -
Add print statements with descriptive comments to code examples
Gabrieledf8dbf3 -
Use cat photo, add print statements to code examples
Gabrieledef9b0d -
Fix zero-shot segmentation section, use public example image
Gabrieleb4afd52 -
Fix backbone link in Model details
Gabrielecf52fa0
-
Update README
Gabriele64789f3 -
Upload README.md with huggingface_hub
Verified signature1241b68
-
Upload model.safetensors with huggingface_hub
Verified signature160890f -
Upload README.md with huggingface_hub
Verified signature9b9b4fd -
Upload config.json with huggingface_hub
Verified signature0d771a0 -
Upload dpt_head.py with huggingface_hub
Verified signature031a449 -
Upload modeling_dpt.py with huggingface_hub
Verified signature6073817 -
Upload configuration_dpt.py with huggingface_hub
Verified signature281491c -
initial commit
Verified signaturedc02cff