size mismatch for linear.weight when running "adaptive_FitNet_teacher-level.ipynb"

[Masterchef2000]

Hey, I try to run the code of "adaptive_FitNet_teacher-level.ipynb", however, an error occurs

RuntimeError: Error(s) in loading state_dict for ResNet:
	size mismatch for linear.weight: copying a param with shape torch.Size([3, 64]) from checkpoint, the shape in current model is torch.Size([10, 64]).
	size mismatch for linear.bias: copying a param with shape torch.Size([3]) from checkpoint, the shape in current model is torch.Size([10]).

It seems that the checkpoint is not correctly satisfy the code, could you please tell me how to solve it?

[ShristiDasBiswas]

def train_adapter(n_epochs=70, model=st_model): print('Training adapter:') start_time = time.time() model.train() adapter.eval() for ep in range(n_epochs): lr_scheduler2.step() lr_scheduler3.step() for i, (input, target) in enumerate(train_loader):

why is adaptor set to eval mode for adaptor training?