Instructions to use Intel/zoedepth-nyu-kitti with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Intel/zoedepth-nyu-kitti with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="Intel/zoedepth-nyu-kitti")# Load model directly from transformers import AutoImageProcessor, AutoModelForDepthEstimation processor = AutoImageProcessor.from_pretrained("Intel/zoedepth-nyu-kitti") model = AutoModelForDepthEstimation.from_pretrained("Intel/zoedepth-nyu-kitti", device_map="auto") - Notebooks
- Google Colab
- Kaggle
generalisation for different focal length
#3
by alexc2660 - opened
I'm trying this model on images taken with a focal length of 2.8mm and I suspect the results are way off because of this. As far as I understand the data used to train this model have a focal length of 3.6-3.7mm.
Does anyone have experience with this? Is my best bet to zoom/crop/correct distortion or to fine-tune the model?