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")# Load model directly from transformers import AutoImageProcessor, AutoModelForDepthEstimation processor = AutoImageProcessor.from_pretrained("Intel/dpt-large") model = AutoModelForDepthEstimation.from_pretrained("Intel/dpt-large") - Notebooks
- Google Colab
- Kaggle
DPT-NYU or DPT-Kitti?
#7
by FatemehBehrad - opened
Hello,
Thanks for preparing this repo.
Can you please identify the provided model is fine-tuned on which dataset? NYU or Kitti?
I am asking this question as in the original GitHub different models are available based on the fine-tuning data.
Hi,
This model corresponds to the "dpt_large-midas-2f21e586.pt" original model, found here: https://github.com/isl-org/DPT?tab=readme-ov-file#setup.
This is also known as DPT 3.0.