Instructions to use facebook/dpt-dinov2-small-nyu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/dpt-dinov2-small-nyu with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="facebook/dpt-dinov2-small-nyu")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForDepthEstimation processor = AutoImageProcessor.from_pretrained("facebook/dpt-dinov2-small-nyu") model = AutoModelForDepthEstimation.from_pretrained("facebook/dpt-dinov2-small-nyu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from facebook/dpt-dinov2-small-nyu: direct link, hf CLI and curl.
- Browser
- Download file 149 MB
-
https://huggingface.co/facebook/dpt-dinov2-small-nyu/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://facebook/dpt-dinov2-small-nyu/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/facebook/dpt-dinov2-small-nyu/resolve/main/pytorch_model.bin
149 MB
- Xet hash:
- 6825d0b24dcf4aa727f3daeb79b6f25fe6cbe20ba4f8f722e1edffbeb51bdaec
- Size of remote file:
- 149 MB
- SHA256:
- 16f263f1793476fe83a10c02da0897573935b4ddb640123c213b39f672649e2a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.