learn2learn

learn2learn copied to clipboard

Update fc100_benchmark.py

4

data augmentation for f100 ala rfs 2020 ### Description Fixes #[ISSUE NUMBER] Replace this line by a one sentence summary of your PR. If necessary, use the following space to...

brando90

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

5

Hi, thanks for your great work! I am trying to use the l2l.optim.LearnableOptimizer to learn the learning rates, but I encountered an error in the second batch training: RuntimeError: one...

xuliwalker

### Description This PR adds support for computing support on new data for running inference. This is only supported by LightningPrototypicalNetworks right now, as the classifier needs re-fitting. This is...

tchaton

Return pytorch tensor for mini-imagenet labels?

2

https://github.com/learnables/learn2learn/blob/06893e847693a0227d5f35a6e065e6161bb08201/learn2learn/vision/datasets/mini_imagenet.py#L111 Currently, when loading mini-imagenet the inputs are returned as pytorch tensors while the labels as numpy arrays. Since the user will likely use both in a training loop, does...

pietrolesci

### Description Adds a sampler over tasks compatible with PyTorch's DataLoader (incl. num_workers > 1) which doesn't assume classification tasks. If used for classification tasks (or others), it does not...

seba-1511

Warning with clone

1

`E:\Anaconda\envs\RL\lib\site-packages\torch\nn\modules\module.py:385: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the...

wenzhoulyu

Meta-World example not working anymore

5

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 ML45 have changed....

janbolle

Asynchronous vectorized environment does not work for cavia_trpo and maml_trpo.

9

Hi, first of all thank you so much for providing us such an excellent project! But I meet a problem and really need your help: When I am running the...

yurunsheng1

[LEO](https://openreview.net/pdf?id=BJgklhAcK7) introduced a feature map trained on mini-imagenet. It's fairly common to benchmark on this "dataset" where the instances are replaced by the feature mapped instances (which is hardcoded into...

IsakFalk

seba-1511