search

gpleiss / efficient_densenet_pytorch

A memory-efficient implementation of DenseNets
MIT License
1.51k stars 329 forks source link

Validation dataset is being augmented as well #51

Closed garyfanhku closed 5 years ago

garyfanhku commented 5 years ago

Thanks for the great repo! Just found out that transformation was applied prior to train val split, effectively augmenting validation set. I don't have a neat solution for this but maybe this gist https://gist.github.com/kevinzakka/d33bf8d6c7f06a9d8c76d97a7879f5cb could be a way out, although it has to load twice the same data.

gpleiss commented 5 years ago

Thanks for the catch. This has been updated with b0a156d87b736d90c3e27933e8e4d0114bd5ef36