Open TeddyPorfiris opened 5 months ago
Without knowing the dataset you are using, there could be a number of reasons why the performances would drop. If you cannot trust your version of the Omniglot dataset, I strongly suggest you use the verified implementation from torchvision
which we use in the notebook.
When I import the Omniglot dataset and define the train and test set as follows, I get an accuracy of 98%.
But when I downloaded the Omniglot dataset images from an external website and used EasySet (jsons attached) to have it work with easyfsl, I get an accuracy of 79%.
Why is this? The rest of the code is the same for both situations (I am following the my_first_few_shot_classifier tutorial). Thanks a lot! test.json train.json