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

<a id="model-zoo-centernet-resnet50-v2-512-coco-tf2"></a>

# centernet-resnet50-v2-512-coco-tf2

Updated version with improved training stability for more consistent object detection across different images.

**Details**

- Model name: `centernet-resnet50-v2-512-coco-tf2`
- Model source: [https://github.com/tensorflow/models/blob/archive/research/object_detection/g3doc/tf2_detection_zoo.md](https://github.com/tensorflow/models/blob/archive/research/object_detection/g3doc/tf2_detection_zoo.md)
- Model author: Xingyi Zhou, et al.
- Model license: Apache 2.0
- Model size: 226.95 MB
- Exposes embeddings? no
- Tags: `detection, coco, tf2, centernet, resnet`

**Requirements**

- CPU support
  - yes
  - Packages: `tensorflow>=2|tensorflow-macos`
- GPU support
  - yes
  - Packages: `tensorflow-gpu>=2|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("centernet-resnet50-v2-512-coco-tf2")

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

session = fo.launch_app(dataset)
```