in train_NR.py why cross entropy is divided by batch_size and multiply by 2

zhongyy / Unequal-Training-for-Deep-Face-Recognition-with-Long-Tailed-Noisy-Data

Code for CVPR2019 paper《Unequal Training for Deep Face Recognition with Long Tailed Noisy Data》

67 stars 17 forks source link

Open xysong1201 opened 4 years ago

xysong1201 commented 4 years ago

in train_NR.py line 301 cross_entropy = cross_entropy / args.batch_size/2

could you explain why the loss should be divided by the batch size and then multiply by 2? thank you