RON icon indicating copy to clipboard operation
RON copied to clipboard
verified publisher icon taokong

What is the normal train loss

Open zjuDebug opened this issue 8 years ago • 1 comments

hi, @taokong ,great work! I want to re-implement your experiment, and I have three small issues?

  1. What is the normal train loss when the model converge well? mark: When I train ,the loss always 4.0+ before 8w iters, and I test at 8w Iters only got mAp=0.54(train data is 2007trainval + 2013trainval)
  2. I also notice that I can do test in a pascal Titanx , but got CUDNN_STATUS_SUCCESS (8 vs. 0) CUDNN_STATUS_EXECUTION_FAILED error in a TitanX.
  3. Training needs much time, can you give me some advices? Thanks in advance!

zjuDebug avatar Sep 19 '17 03:09 zjuDebug

hello, i also want to re-implement this work recently, but the loss always went towards nan after several steps. after carefully check i found the objectness proir(after softmax) will all be 0. did you ever got into problems like this? BTW, what's your learning rate setting?

HiKapok avatar Dec 16 '17 11:12 HiKapok