training loss error: inf

[jxlijunhao]

I follow the steps in the readme, but it occurs trainning loss error, the trainning locatization loss
the logs:

1 Epoch:1 || epochiter: 0/517|| Totel iter 0 || L: inf C: 23.2587||Batch time: 16.6584 sec. ||LR: 0.00000100
2 Epoch:1 || epochiter: 10/517|| Totel iter 10 || L: inf C: 19.0657||Batch time: 0.8695 sec. ||LR: 0.00001647
3 Epoch:1 || epochiter: 20/517|| Totel iter 20 || L: inf C: 16.3741||Batch time: 0.9224 sec. ||LR: 0.00003194
4 Epoch:1 || epochiter: 30/517|| Totel iter 30 || L: inf C: 14.5374||Batch time: 0.8792 sec. ||LR: 0.00004741

[lzx1413]

which model are you training?

[manlinting]

I encountered the same problem with RFB_mobile 300.

[lzx1413]

I will update the mobilenet models without pyinn in a few days, please stay tuned.

[manlinting]

I tested the other network, the same problem. Is it related to my use of python2.7?

[lzx1413]

It only support python3 now, the prior box generation needs the division in python3, you may solve this problem with using from __future__ import division.

[manlinting]

after from future import division, I have solve this problem.thank you very much! Another question, can you help to support mobilenetv2?

[lzx1413]

@manlinting https://github.com/ShuangXieIrene/ssds.pytorch there is an another pytorch ssd including mobilentv2

[manlinting]

thanks!