efficientdet-d5-coco-tf1

Legacy object detector with the highest accuracy in its family using TensorFlow 1.

Details

• Model name: efficientdet-d5-coco-tf1

• Model source: https://github.com/voxel51/automl/tree/master/efficientdet

• Model author: Mingxing Tan, et al.

• Model license: Apache 2.0

• Model size: 275.81 MB

• Exposes embeddings? no

• Tags: detection, coco, tf1, efficientdet, legacy

Requirements

• CPU support

  • yes

  • Packages: tensorflow>=1.14,<2

• GPU support

  • yes

  • Packages: tensorflow-gpu>=1.14,<2

Example usage

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("efficientdet-d5-coco-tf1")

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

session = fo.launch_app(dataset)