Output layer size in the meta-training and meta-testing phases

[AhmedFrikha]

My understanding is that you use a single fully connected layer on top of the neuro-modulated representations.

1. Does this output layer has 963 nodes during meta-training, since you are performing 963-class classification during meta-training ?
2. If yes, how do you use the meta-learned output layer to learn/perform 600-class classification at meta-testing time ? Or do you randomly initialize a new output layer with 600 nodes?

[ZhichenML]

Hi I was wondering if you have addressed this concern. From the code the network has an output layer mapping from 2304 units to 1000 unit, where 1000 covers the training classes 963 and testing classes 600. It is really really really wired to me!