learn2learn
learn2learn copied to clipboard
A PyTorch Library for Meta-learning Research
Akin to `l2l.clone_module(module)` and `l2l.detach_module(module)`, but for distributions.
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...
# Patching CVE-2007-4559 Hi, we are security researchers from the Advanced Research Center at [Trellix](https://www.trellix.com). We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a...
related to https://github.com/learnables/learn2learn/issues/355 I tried iterating through a union data set and couldn't. odd the union data set's iterator doesn't work: ``` assert isinstance(dataset, Dataset), f'Expect dataset to be of...
``` import learn2learn as l2l train = torchvision.datasets.CIFARFS(root="/tmp/mnist", mode="train") train = l2l.data.MetaDataset(train) valid = torchvision.datasets.CIFARFS(root="/tmp/mnist", mode="validation") valid = l2l.data.MetaDataset(valid) test = torchvision.datasets.CIFARFS(root="/tmp/mnist", mode="test") test = l2l.data.MetaDataset(test) from learn2learn.data import UnionMetaDataset...
bug
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
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 float32 logger.warn( Traceback (most recent call last): File...
Hi there, will you implement lstm optimizer like in the paper "learn to learn by gradient descent by gradient descent"? thanks.
Are there any implementations of 1. MAML++ 2. BiT with Learn2Learn. I wish to compare pre-training vs meta-learning. Thanks! @saum-g
When passing an `learn2learn.utils.lightning.EpisodicBatcher` to a `lightning.Trainer` the training crashes. **MRE** ```python import sys import logging logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') import torch import lightning import learn2learn from torch.utils.data...