Open Images Pre-trained Image Classification

Image Classification is a popular computer vision technique in which an image is classified into one of the designated classes based on the image features. This model card contains pretrained weights of most of the popular classification models. These weights that may be used as a starting point with the classification app in TAO Toolkit to facilitate transfer learning.

It is trained on a subset of the Google OpenImages dataset. Following backbones are supported with these detection networks.

Supported Backbones

resnet10/resnet18/resnet34/resnet50/resnet101
vgg16/vgg19
googlenet
mobilenet_v1/mobilenet_v2
squeezenet
darknet19/darknet53
cspdarknet19/cspdarknet53
efficientnet_b0
efficientnet_b1
cspdarknet_tiny

To see the full list of all the backbones, scroll over to the version history tab.

Note

These are unpruned models with just the feature extractor weights, and may not be used without retraining to deploy in a classification application.
Please make sure to set the all_projections field to False in the spec file when training a ResNet101 model.

You may find more information about these models on NGC.

Previous Overview

Next Open Images Pre-trained Object Detection