pytorch-meta
pytorch-meta copied to clipboard
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
Within a conda environment, I installed a conda environment containing these pytorch libraries: ```conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch``` However, when I pip install torchmeta, it seems that...
Hi, I have been trying to retain the original labels of test/train set targets, for example, the targets in lines [45](https://github.com/tristandeleu/pytorch-meta/blob/master/examples/protonet/train.py#L45) and [50](https://github.com/tristandeleu/pytorch-meta/blob/master/examples/protonet/train.py#L50) in the protonet training script. Could you...
There is an import missing in file torchmeta/datasets/utils.py. Method "download_file_from_google_drive(...)" makes use of "check_integrity(...)" from torchvision.datasets.utils.
Is it possible to create my own torchmeta data set using my own classification data set pytorch obj?
I have a data set object (e.g. from l2l or a standard pytorch one) that I want to wrap in the torchmeta data loaders. Will it work properly (without bugs)...
Trying to add meta-data set to here & learn2learn. Feel free to ping me for useful resources. https://github.com/learnables/learn2learn/issues/286
I noticed the rethinking few shot learning paper here https://github.com/WangYueFt/rfs/issues/34 augments their support set. How can I do this in torchmeta? (same q for l2l framework https://github.com/learnables/learn2learn/issues/316)
Thank you very much for your work. Can the code count the number of segmented targets?
Fixes #148 Not tested
I noticed that we have this: https://github.com/tristandeleu/pytorch-meta/blob/d55d89ebd47f340180267106bde3e4b723f23762/torchmeta/datasets/helpers.py#L165 ``` defaults = { 'transform': Compose([Resize(84), ToTensor()]) } ``` i.e. there is no normalization e.g. using: ``` normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229,...
Bug List
Hi again! I came with a little more bugs this time, hopefully I don't bother you :) - CIFARFS imported from torchmeta.datasets returns list index out of range error after...