bbrattoli / JigsawPuzzlePytorch

Pytorch implementation of the method from the paper "Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles"
165 stars 47 forks source link

batchnorm in training? #7

Open shlokk opened 4 years ago

shlokk commented 4 years ago

I tried training the current model in the current setting i.e without batch norm and I saw jigsaw task was not getting the accuracy of 71(as reported in the original paper). After adding batch norm I was able to get an accuracy of 71 on jigsaw task, but the numbers on VOC classification was 4map points below what paper reported. Any ideas?