ssd-resnet50-fpn-coco-tf#

Accurate object detector combining strong backbone with multi-scale detection for better results.

Details

  • Model name: ssd-resnet50-fpn-coco-tf

  • Model source: tensorflow/models

  • Model author: Wei Liu, et al.

  • Model license: Apache 2.0

  • Model size: 128.07 MB

  • Exposes embeddings? no

  • Tags: detection, coco, tf, ssd, resnet, legacy

Requirements

  • CPU support

    • yes

    • Packages: tensorflow|tensorflow-macos

  • GPU support

    • yes

    • Packages: tensorflow-gpu|tensorflow>=2|tensorflow-macos

Example usage

 1import fiftyone as fo
 2import fiftyone.zoo as foz
 3
 4dataset = foz.load_zoo_dataset(
 5    "coco-2017",
 6    split="validation",
 7    dataset_name=fo.get_default_dataset_name(),
 8    max_samples=50,
 9    shuffle=True,
10)
11
12model = foz.load_zoo_model("ssd-resnet50-fpn-coco-tf")
13
14dataset.apply_model(model, label_field="predictions")
15
16session = fo.launch_app(dataset)