Open Images Pre-trained Semantic Segmentation
Semantic segmentation assigns every pixel in an image to a class label. Semantic segmentation does image classification at pixel level. Unlike instance segmentation which can label individual instances belonging to a class, semantic segmentation clubs all instances of a class to same label. This model object contains pretrained weights that may be used as a starting point with the following semantic segmentation networks in TAO Toolkit to facilitate transfer learning.
The following semantic segmentation architecture are supported:
The pre-trained weights are trained on a subset of the Google OpenImages dataset. Following backbones are supported with these UNet networks.
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
Falsein the spec file when training a ResNet101 model.
For more instructions on downloading and using the models defined here, refer to the NGC catalog page.