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

<a id="model-zoo-deeplabv3-mnv2-cityscapes-tf"></a>

# deeplabv3-mnv2-cityscapes-tf

Efficient street scene labeler designed to run on phones and edge devices with limited resources.

**Details**

- Model name: `deeplabv3-mnv2-cityscapes-tf`
- Model source: [https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md](https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md)
- Model author: Liang-Chieh Chen, et al.
- Model license: Apache 2.0
- Model size: 8.37 MB
- Exposes embeddings? no
- Tags: `segmentation, cityscapes, tf, deeplabv3, legacy`

**Requirements**

- CPU support
  - yes
  - Packages: `tensorflow|tensorflow-macos`
- GPU support
  - yes
  - Packages: `tensorflow-gpu|tensorflow>=2|tensorflow-macos`

**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("deeplabv3-mnv2-cityscapes-tf")

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

session = fo.launch_app(dataset)
```