Open Images Pre-trained EfficientDet

Object detection is a popular computer vision technique that can detect one or multiple objects in a frame. Object detection will recognize the individual objects in an image and place bounding boxes around the object. This model object contains pretrained weights that may be used to initialize the EfficientDet object detection networks in TAO Toolkit to facilitate transfer learning.

This is trained on a subset of the Google OpenImages dataset.

Supported Backbones

The following backbones are supported with EfficientDet networks:

  • efficientnet_b0

  • efficientnet_b1

  • efficientnet_b2

  • efficientnet_b3

  • efficientnet_b4

  • efficientnet_b5

Note

These are unpruned models with just the feature extractor weights, and may not be used without re-training in an object-detection application

You may find more information about these models on NGC.