Instructions to use Intel/dpt-hybrid-midas with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Intel/dpt-hybrid-midas with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="Intel/dpt-hybrid-midas")# Load model directly from transformers import AutoImageProcessor, AutoModelForDepthEstimation processor = AutoImageProcessor.from_pretrained("Intel/dpt-hybrid-midas") model = AutoModelForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas") - Notebooks
- Google Colab
- Kaggle
what is the metric used for output
#4
by FaisalHejary - opened
is the output of the model in cm, meters, or foot?
I would really like to know if it is possible to obtain the absolute depth in meters. But what the model outputs is the inverse depths that needs to be scaled and shifted by unknown values.