why there is only two softmax layer in prototxt about dualnet HOT 5 CLOSED

In the iterative training, there are two losses involved. And in most cases, it is enough to set max_iter=1 to obtain the perform gain. Besides, the way to train with max_iter=2 is similar.

from dualnet.

So if the max_iter=2. I need three prototxt files which one of these is used in ite_0 and the other two are used in ite_2k and ite2kpulus1 ?

from dualnet.

The other problem is when three losslayer are needed? The visualization of DualNet has three losslayers in supplementary material. thxs

from dualnet.

1. In each training phase, only one prototxt is needed in my implementation.
2. Three loss layers are need in the jointly finetuning. The loss function is presented in the paper.

from dualnet.

thanks for your response! i will read it again.

from dualnet.