depth-anything-v2-small-torch

Lightweight Depth Anything V2 model for fast monocular depth estimation.

Details

• Model name: depth-anything-v2-small-torch

• Model source: https://huggingface.co/depth-anything/Depth-Anything-V2-Small-hf

• Model author: Lihe Yang, et al.

• Model license: Apache 2.0

• Model size: 94.60 MB

• Exposes embeddings? no

• Tags: depth, 3d, torch, transformers

Requirements

• Packages: torch, torchvision, transformers

• CPU support

  • yes

• GPU support

  • yes

Example usage

import fiftyone as fo
import fiftyone.zoo as foz

dataset = foz.load_zoo_dataset(
    "coco-2017",
    split="validation",
    dataset_name=fo.get_default_dataset_name(),
    max_samples=50,
    shuffle=True,
)

model = foz.load_zoo_model("depth-anything-v2-small-torch")

dataset.apply_model(model, label_field="predictions")

session = fo.launch_app(dataset)