Adding @tf.function Decorator

As the entry point file official/vision/image_classification/resnet/resnet_ctl_imagenet_main.py is already added with the @tf.function decorator function, this step can be safely skipped.

1
2
3

flags.DEFINE_boolean(name='use_tf_function', default=True,
                     help='Wrap the train and test step inside a '
                     'tf.function.')