-
Could you please help me out?
When I use --batch_num=32, I cannot run the code on a single GPU. My GPU is Tesla P100-SXM2 16G. I only can run the code with --batch_num=1. Since we have create_graph…
-
I propose updating the C# language specification to include a mention of a `` element in documentation. This "inline" element identifies content that is not yet finalized and/or needs further review.
…
-
With PyTorch's [latest update](https://pytorch.org/blog/pytorch-1.11-released/), the introduction of the functorch library allows, via composable function transforms, to ["efficiently batching togethe…
-
I am using a step size of 1 for my inner loop. Nevertheless I want to use adaptive optimizers in the inner loop and carry the buffers across outer loop iterations. In the context of e.g. MAML that wou…
-
Hi,
I am wondering what are the effects of having `first-order=False`, and when should we use it?
From what I understand of the current implementation, `first_order` only affects the sample meth…
-
hi，thanks to your great works！I have been curious how the meta learning mentioned in the article is implemented in the code.
I have read it several times, and it feels like this is a regular gan tra…
-
I 'm doing my research on federated meta-learning, and I decide to follow the type of MAML by using the two step gradient decent trick on the client side. However, when I tried to modify the client co…
-
Hi,
I tested MAML and Reptile algorithms using mini-imagenet dataset, and the data are sampled using a TasksetDataset,
Question: Is it normal that after the set of tasks are created, the inputs …
-
```
====> about to start train loop
args.number_of_trainable_parameters=26257285
Starting training!
log_zeroth_step
Traceback (most recent call last):
File "/lfs/ampere4/0/brando9/diversity-fo…
-
Hi, thanks for sharing the code!
I have a question on updating the meta learner: in the original paper, the update for meta learner is interpolation between the previous parameter and the parameter…