Instructions to use LiheYoung/depth_anything_vitl14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LiheYoung/depth_anything_vitl14 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="LiheYoung/depth_anything_vitl14")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("LiheYoung/depth_anything_vitl14", dtype="auto") - Notebooks
- Google Colab
- Kaggle
depth-anything-large-hf vs depth_anything_vitl14
#2
by Farhaddlrn - opened
Hello,
- What is difference between "depth-anything-large-hf" and "depth_anything_vitl14"?
- Which one is identical to Depth-anything ViT-L in the paper?
- Are both of them not trained on KITTI?
Hi,
Both have equivalent weights. "depth-anything-large-hf" is the model compatible with the Transformers library, "depth_anything_vitl14" is compatible with the original Depth Anything Github repository. They both correspond to Depth-anything ViT-L in the paper.