universal-segmentation-transformer-torch

Hugging Face Transformers model for universal segmentation (instance, panoptic, or semantic).

Details

• Model name: universal-segmentation-transformer-torch

• Model source: https://huggingface.co/docs/transformers/en/model_doc/mask2former

• Model author: Bowen Cheng, et al.

• Model license: MIT

• Exposes embeddings? no

• Tags: instances, panoptic, segmentation, torch, transformers, official

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("universal-segmentation-transformer-torch")

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

session = fo.launch_app(dataset)