Jake Snell
Jake Snell
Hi, one simple way may be to check out the Torchmeta package: https://github.com/tristandeleu/pytorch-meta. They support several datasets and have a prototypical networks implementation.
This is expected due to the way data loading is done. As images are read from disk, they are continually cached into memory. Eventually all of the images are loaded...
Hi, thank you for your interest. This is not a problem handled by our paper. However, one thing you could try is to look at the distribution of base classes...