Instructions to use Intel/dpt-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Intel/dpt-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="Intel/dpt-large")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForDepthEstimation processor = AutoImageProcessor.from_pretrained("Intel/dpt-large") model = AutoModelForDepthEstimation.from_pretrained("Intel/dpt-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from Intel/dpt-large: direct link, hf CLI and curl.
- Browser
- Download file 285 Bytes
-
https://huggingface.co/Intel/dpt-large/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Intel/dpt-large/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Intel/dpt-large/resolve/main/preprocessor_config.json
285 Bytes
| { | |
| "do_normalize": true, | |
| "do_resize": true, | |
| "ensure_multiple_of": 1, | |
| "feature_extractor_type": "DPTFeatureExtractor", | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "keep_aspect_ratio": false, | |
| "resample": 2, | |
| "size": 384 | |
| } | |