-
Hi, I see that your `requirements.txt` file only contains tensorflow based libraries.
How can I use other libs like `pytorch`?
Can you provide an example to use `torch` instead of `tf`. I just c…
-
Hi, when i read your code. i noticed that your meta-training strategy have some differences with MAML. Could you tell me which meta-learning paper design this strategy ? Or it is your design? Besides…
-
Is this implementation a 1st order Approximation version of Maml ?
In meta.py, when you do autograd.grad, you do not specify create_graph = True, which means that the gradient operation would not be…
-
Hi, thanks for your work on this library!
Using a weight normalized network in higher's inner loop raises the following error:
```
load from omniglot.npy.
DB: train (1200, 20, 1, 28, 28) test …
-
Hi,
First thank you for providing us such a nice work!
But I meet a question and really need you help:
In your MeLU.py lines 71-79:
```
grad = torch.autograd.grad(loss, self.model.paramete…
-
Hi,
Would it be possible to make available the pre-trained models, with the different data-sets?
e.g.
- checkpoint of model trained with union data-sets on mini-imagent
- checkpoint of model…
-
I am using the MAML example as a template but I am additionally computing on a GPU. Normally I would use torch.no_grad to do model evaluation without overflowing GPU memory -- I obviously cannot do th…
-
我对各位的项目很感兴趣，但是无法找到maml.py中用到的包，请问通过何种途径可以获得？谢谢！
-
I'd like to use the Adafactor scheduler as the hugging face code has (but their code does not work for CNNS).
questions as follow:
a) How do I use schedulers with pytorch-optimizer?
b) Can we ad…
-
I want to adapt my model and pass the adapted model around in my code. How do I do this?
my guess the best way is to not use the context manager for inner loops but somehow still use the adapted mo…