Michael Moor

Added meta_lr_final parameter to indicate the final value of the meta learning rate. By setting meta_lr_final to a smaller value than meta_lr, the meta learning rate is effectively decayed during...

Reptile Vision example has constant meta learning rate

3

In the following reptile example script https://github.com/learnables/learn2learn/blob/master/examples/vision/reptile_miniimagenet.py:111, the meta-learning rate has a bug: it remains constant and does not decay. ```new_lr = frac_done * meta_lr + (1 - frac_done) *...

Batch support of SampleLoss

1

First of all thanks for the great library! I just tried to run SampleLoss with batches of data and it did not work. So, I have two tensors x,y of...