This is a PyTorch implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification" (Ze Yang, Tiange Luo, Dong Wang, Zhiqiang Hu, Jun Gao, Liwei Wang).
MIT License
450
stars
118
forks
source link
为什么每块GPU里面batchsize数量越少，效果越好，8 img per gpu只有86.2，但是4 img per gpu能到87.1 #26
I met the same problem! When I use 2 GPUS with batch_size 32，I can only get highest acc 83.1 with 500 epochs, but when I change batch_size from 32 to 16, now with 200 epochs, the highest acc is 87+
I met the same problem! When I use 2 GPUS with batch_size 32，I can only get highest acc 83.1 with 500 epochs, but when I change batch_size from 32 to 16, now with 200 epochs, the highest acc is 87+