How to use `l2l.vision.models.ResNet12`? about learn2learn HOT 4 CLOSED

All right, thank you for your help! Have a nice day😊

from learn2learn.

Hello @Jeong-Bin,

Method 3 is correct. Try using maml.clone(first_order=True) when testing. Or, you can reduce the number of adaptation steps (at the price of performance).

How much GPU memory do you have? If you have more than 1 GPU, you can use model.features = torch.nn.DataParallel(model.features) to distribute the activations on the GPUs.

from learn2learn.

@seba-1511
Thanks! My GPU is RTX 3090 Ti with 20GB memory.
I'll try your solution.

Additionally, I referred to 'adaptation steps' in MAML paper.
In section A.1. Classification of the paper, authors use 10 gradient steps at test time.
Is the gradient step means adaptation step?

from learn2learn.

Yes, gradient steps are adaptation steps.

from learn2learn.