Andrew Tseng
Andrew Tseng
I wonder if this line is not necessary as there are no updates on the weights after this line, but I might be wrong
It seems that people still dont have an exact solution for doing so, I wonder why people mention that `requiers_grad = False is not possible at the moment without disconnecting...
Are you guys considering adding an example for cifar100 on maml, it would be great as a lot of custom datasets has structures that could be directly applied with `cifarfs.py`.
"speeding up in the later training procedure." Is there a reason why this happened?
Even OrderedDict and random.seed are used, the results are still not reproducible.