resnet50noTopAdditionalTraining

This examples demonstrates the transfer learning concept on ResNet'50 model:

• Model configuration, model weights and labels are obtained from TFModelHub.

• Weights are loaded from .h5 file, configuration is loaded from .json file.

• All layers, are added to the new Neural Network, its weights are frozen.

• New GlobalAvgPool2D and Dense layers are added and initialized via defined initializers.

• Model is re-trained on dogsCatsSmallDatasetPath dataset.

We use the Preprocessing DSL to describe the dataset generation pipeline. We demonstrate the workflow on the subset of Kaggle Cats vs Dogs binary classification dataset.