QiuPaul

I wonder if the code is different from the algorithm in origin paper？？ thanks

4

In paper , while not converged do 1. Update weights w by descending GRADw(w; alpha) 2. Update architecture alpha by descending GRADalpha(updated w; alpha) Which means: when update weights ,the...

accuracy only 52.4%？

1

hello，I use the code to generate the vgg16 caffemodel，to valid on the imagenet，the result is 52.4%, so how is your result ? maybe difference is data process or others? thanks...