<!-- # hard line break macro for HTML -->

<a id="model-zoo-mask2former-swin-base-coco-instance-torch"></a>

# mask2former-swin-base-coco-instance-torch

Mask2Former with Swin-B backbone for instance segmentation on COCO, returning per-instance binary masks.

**Details**

- Model name: `mask2former-swin-base-coco-instance-torch`
- Model source: [https://huggingface.co/facebook/mask2former-swin-base-coco-instance](https://huggingface.co/facebook/mask2former-swin-base-coco-instance)
- Model author: Bowen Cheng, et al.
- Model license: MIT
- Model size: 412.00 MB
- Exposes embeddings? no
- Tags: `instances, torch, transformers, official`

**Requirements**

- Packages: `torch, torchvision, transformers`
- CPU support
  - yes
- GPU support
  - yes

**Example usage**

```python
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("mask2former-swin-base-coco-instance-torch")

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

session = fo.launch_app(dataset)
```