Re-sampling tasks after each epoch increases the performance about maml-pytorch HOT 3 OPEN

Lol. Thanks for your result. I think the author is busy making money... He does not care about this little bug. For those who want to implement maml. I recommend https://towardsdatascience.com/advances-in-few-shot-learning-reproducing-results-in-pytorch-aba70dee541d

from maml-pytorch.

Lol. Thanks for your result. I think the author is busy making money... He does not care about this little bug. For those who want to implement maml. I recommend https://towardsdatascience.com/advances-in-few-shot-learning-reproducing-results-in-pytorch-aba70dee541d

Thanks, I'll check that.

from maml-pytorch.

The create_batch function is only called once when the MiniImagenet dataset object is created, which means the tasks sampled are the same in every epoch.

I changed the code to second-order (according to #32) and call create_batch in every epoch, the performance can achieve 47.17%.

@ShawnLixx
Hi!
I have run this code on miniImageNet, I can get almost 47% accuracy on testing dataset. However, when I save the corresponding best model, and load it on my testing code, I can only get 44% accuracy, is there any insight you can provide to help me fix this problem? Or can you tell me the way of how you implement the test code?

from maml-pytorch.