no code implementations • 21 Feb 2018 • Mohamed Hajaj, Duncan Gillies
If training batches are structured as balanced batches (one image per class), and inference is also carried out on balanced test batches, using the batch's own means and variances, then the conditional results will improve considerably.
no code implementations • 21 Feb 2018 • Mohamed Hajaj, Duncan Gillies
Deep convolution networks have proved very successful with big datasets such as the 1000-classes ImageNet.