yolo26x-depth-torch#

Maximum accuracy monocular metric depth estimation.

Details

  • Model name: yolo26x-depth-torch

  • Model source: https://docs.ultralytics.com/tasks/depth/

  • Model author: Glenn Jocher, et al.

  • Model license: AGPL-3.0

  • Model size: 109.32 MB

  • Exposes embeddings? no

  • Tags: depth, 3d, torch, yolo, official

Requirements

  • Packages: torch>=1.7.0, torchvision>=0.8.1, ultralytics>=8.4.104

  • CPU support

    • yes

  • GPU support

    • yes

Example usage

 1import fiftyone as fo
 2import fiftyone.zoo as foz
 3
 4dataset = foz.load_zoo_dataset(
 5    "coco-2017",
 6    split="validation",
 7    dataset_name=fo.get_default_dataset_name(),
 8    max_samples=50,
 9    shuffle=True,
10)
11
12model = foz.load_zoo_model("yolo26x-depth-torch")
13
14dataset.apply_model(model, label_field="predictions")
15
16session = fo.launch_app(dataset)