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

<a id="model-zoo-segformer-b5-ade20k-torch"></a>

# segformer-b5-ade20k-torch

Largest SegFormer model delivering the best semantic segmentation performance in its family.

**Details**

- Model name: `segformer-b5-ade20k-torch`
- Model source: [https://huggingface.co/nvidia/segformer-b5-finetuned-ade-640-640](https://huggingface.co/nvidia/segformer-b5-finetuned-ade-640-640)
- Model author: Enze Xie, et al.
- Model license: MIT
- Model size: 323.14 MB
- Exposes embeddings? yes
- Tags: `segmentation, torch, segformer, 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("segformer-b5-ade20k-torch")

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

session = fo.launch_app(dataset)
```