Open Balabala-Hong opened 3 years ago
I am also wondering and would be nice to know how to do this for a general dataset
I'm sorry for the late reply. There is unfortunately no proper documentation to add your own dataset, but I have given a couple of guidelines here https://github.com/tristandeleu/pytorch-meta/issues/113#issuecomment-773972272 in order to get your own dataset to work with Torchmeta. My best advice is to look at how Omniglot
works, with the 3 levels of abstractions required, to get inspiration and adapt it to your own dataset. I hope this helps.
I want to conduct some experiments on other datasets using torchmeta, for example, NWPU-RESISC45. How to process the original file to make it well-matched with torchmeta (as I found the miniimagenet dataset is transformed and saved into JSON and HD5 files). I suggest you add some detailed descriptions about the content and the format of the standard dataset in the documentation. And the corresponding code for parsing and sampling the dataset is suggested (maybe just a simple template is enough). Because without these descriptions, the torchmeta can be kind of diffcult for beginners to learn.
Besides, the function
check_integrity()
inpytorch-meta/torchmeta/datasets/utils.py
seems to lose effect inminiimagenet.py
for unfound definition. Addfrom torchvision.datasets.utils import check_integrity
inpytorch-meta/torchmeta/datasets/utils.py
helps solve this bug.