the ratio of classification loss and verification loss is 1/2 about 2016_person_re-id HOT 4 CLOSED

@JoyLuo
Hi Joy,
Sorry for the late response.

1. The 'shake' of the verification loss may be due to the (x-y)^2 in the Square layer.
   I have tried to add L2-norm Layer but it seems to harm the training process and loss some information. I did not try adding the BatchNorm, and I think it may work.

2. Actually I have tried classification:verification = 1:0.1,1:0.01 and the result is similar or no better than 1:1. So I do not try more variants.

Thank you!
Zhedong

from 2016_person_re-id.

@layumi thanks for you kindly answer.
could you show me the figure of loss_dif your trained? it will tell me the right way about how to down the loss_dif.

thank you!
luoze

from 2016_person_re-id.

I just uploaded the training curve of the Market-1501. You may refer to it.
https://github.com/layumi/2016_person_re-ID/blob/master/market1501-train-curve.pdf

The top1_compare and objective_compare are for the verification loss.

from 2016_person_re-id.

dear @layumi
i see the curve from you link. thanks for you kindly help

from 2016_person_re-id.