FriedFeid/oVDA-c8#

From Plugin

Note

This is a remotely-sourced model from the online_video_depth_anything plugin, maintained by the community. It is not part of FiftyOne core and may have special installation requirements. Please review the plugin documentation and license before use.

Online Video Depth Anything (cache_size=8). Lighter variant with a smaller temporal cache; faster and lower memory than c16 at some cost to temporal consistency..

Details

  • Model name: FriedFeid/oVDA-c8

  • Model source: https://huggingface.co/FriedFeid/oVDA

  • Model author: Heidelberg University

  • Model license: NC-SA-UHDV1.0

  • Exposes embeddings? no

  • Tags: depth-estimation, video, temporal, heatmap

Requirements

  • Packages: torch, torchvision, einops, natsort, easydict, huggingface_hub

  • CPU support

    • yes

  • GPU support

    • yes

Example usage

 1import fiftyone as fo
 2import fiftyone.zoo as foz
 3
 4foz.register_zoo_model_source("https://github.com/harpreetsahota204/online_video_depth_anything")
 5
 6dataset = foz.load_zoo_dataset(
 7    "coco-2017",
 8    split="validation",
 9    dataset_name=fo.get_default_dataset_name(),
10    max_samples=50,
11    shuffle=True,
12)
13
14model = foz.load_zoo_model("FriedFeid/oVDA-c8")
15
16dataset.apply_model(model, label_field="predictions")
17
18session = fo.launch_app(dataset)