You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have tried your code and get some result. For omniglot dataset, the accuracy I got is lower than the original implementation. For 5-way 5-shot, the accuracy on test set is around 96%, while the paper report that the accuracy could achieve 99.9% for convolution network. The same thing happens for 5-way 1 shot.
I checked the code and found the model parameters are the same with original code. Do you have any idea about this?
The text was updated successfully, but these errors were encountered:
I-am-Bot
changed the title
Questions about the performance
Performance on Omniglot is slightly lower than paper report
Apr 25, 2020
@I-am-Bot I think it might be because this code implements a first-order approximation of the original MAML algorithm. See #32 and this post for a discussion on it.
In the original implementation, 90 degree rotation is used as a data augmentation on omniglot. I can't find such preprocessing in this implementation. maybe this is the reason? @dragen1860 @I-am-Bot
In the original implementation, 90 degree rotation is used as a data augmentation on omniglot. I can't find such preprocessing in this implementation. maybe this is the reason? @dragen1860@I-am-Bot
I find it as well. Have u try if it could improve the performance? It seems hard to add a rotation over this reproduction.
Hi, thank you for your implement MAML in pytorch.
I have tried your code and get some result. For omniglot dataset, the accuracy I got is lower than the original implementation. For 5-way 5-shot, the accuracy on test set is around 96%, while the paper report that the accuracy could achieve 99.9% for convolution network. The same thing happens for 5-way 1 shot.
I checked the code and found the model parameters are the same with original code. Do you have any idea about this?
The text was updated successfully, but these errors were encountered: