-
Dear @Kostis-S-Z,
unfortunately, the meta-world example doesn't work anymore.
In the latest version of meta-world, the file MultiClassMultiTaksEnv is missing.
Also, the imports of ML1, ML10, and M…
-
Hi Seba,
Apologies if it seems like a complaint -- it's not. But just wanted to clarify. I was going through the examples and they seemed to lack the standard data transforms that ppl use when runn…
-
I get an issue for mini-imagenet:
```
Traceback (most recent call last):
File "/lfs/hyperturing1/0/brando9/diversity-for-predictive-success-of-meta-learning/div_src/diversity_src/experiment_mains…
-
Not much of a bug as much of a clarification/beginner question - but why do we restrict num_tasks = 20000 in the maml_omniglot.py demo:
https://github.com/learnables/learn2learn/blob/691f573ce6dead…
-
Say I have 3 splits of disjoint classes to create anew meta-learning data set (say in 3 folders with each folder having the class and the image files). I can lead each in a normal pytorch data set. Ho…
-
I'd like to get the same splits of omniglot so that my experiments (or future papers, experiments) don't depend on the seed i personally I use and have the same image class.
Does l2l give an option…
-
running the (maml_omniglot.py)and then:
ImportError: cannot import name 'transforms' from partially initialized module 'learn2learn.data' (most likely due to a circular import)### #344
-
```
import learn2learn as l2l
train = torchvision.datasets.CIFARFS(root="/tmp/mnist", mode="train")
train = l2l.data.MetaDataset(train)
valid = torchvision.datasets.CIFARFS(root="/…
-
Dear Anuj,
I am very impressed from your work and I would like to try and replicate your training to understand how your method works. I was wondering how did you manage to train the models because…
-
When I run this example on Windows 10, the following error occurs:
E:\Anaconda3\envs\meta\lib\site-packages\gym\spaces\box.py:73: UserWarning: WARN: Box bound precision lowered by casting to float3…