parameter numbers of the entire model?

[Sunting78]

Thanks for the great work !
I want to ask a question that confuses me. In the Paper, Table 4 shows that the parameter numbers of the entire model is not increased. However, i see that in the code the prototype is inceased by class_num as follow:
self.prototypes = nn.Parameter(torch.zeros(self.num_classes, self.num_prototype, in_channels), requires_grad=True)
If class_num is increased, the parameter numbers of prototypes are also increased. Did I get it wrong？

[tfzhou]

Hi @Sunting78, Thanks for your interests. Table 4 actually report the number of learnable parameters, while in our model, self.prototypes are non-learnable. P.s., though requires_grad is set to True in the code you refer to, it will be changed to False immediately in the forward function. It is same to directly set requires_grad=False in the definition.

[Sunting78]

@tfzhou Thanks for your reply. I got it.