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

<a id="model-zoo-swin-v2-large-torch"></a>

# swin-v2-large-torch

Large hierarchical transformer with enhanced capacity for demanding applications.

**Details**

- Model name: `swin-v2-large-torch`
- Model source: [https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft)
- Model author: Ze Liu, et al.
- Model license: MIT
- Model size: 2.93 GB
- Exposes embeddings? yes
- Tags: `classification, imagenet, torch, transformers, swin-transformer, official, embeddings`

**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("swin-v2-large-torch")

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

session = fo.launch_app(dataset)
```