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

<a id="model-zoo-rfdetr-seg-2xlarge-coco-torch"></a>

# rfdetr-seg-2xlarge-coco-torch

RF-DETR Seg 2XLarge instance segmentation model trained on COCO. Maximum segmentation accuracy..

**Details**

- Model name: `rfdetr-seg-2xlarge-coco-torch`
- Model source: [https://github.com/roboflow/rf-detr](https://github.com/roboflow/rf-detr)
- Model author: Roboflow
- Model license: Apache 2.0
- Model size: 146.87 MB
- Exposes embeddings? no
- Tags: `instances, coco, torch, transformer, rfdetr, official`

**Requirements**

- Packages: `torch, torchvision, rfdetr`
- 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("rfdetr-seg-2xlarge-coco-torch")

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

session = fo.launch_app(dataset)
```
