the loss of detection is so high about drbox

[liulei01]

This is not normal. In my experiments, the loss decreased to less than 1.0 after about 10000 iterations when batchsize = 32. Are you using the given training data or your own dataset?

[gitUserGoodLeaner]

I using the given data and coverted the airplane dataset into LMDB, then starting the training. However the training loss change from 7.0+ up to 300.0+! after about 70000 iterations. I still not clear why this happened. The training setting keep same as the repository provided, just modified the dataset path.

[liulei01]

What do you see in src/caffe/util/? rbox_util.cpp and rbox_util.cpp.ship are used in different tasks. I renamed them 19 days ago after I uploaded all the code 21 days ago. So I want to know your code is downloaded before or after this date. If your code is the newest version, I will re-training my network and reply you soon.

[makefile]

@liulei01 My training loss of ship task doesn't decrease and keeps 8.0 ~ 9.0 between iterations of 5000 ~ 20000. I do as the README instruction and used the rbox_util.cpp.ship and set batchsize = 32, use only 1 GPU. Is this loss normal?
@gitUserGoodLeaner Have you figured out the problem?

[chensonglu]

@gitUserGoodLeaner I encounter the same problem and changing the "base_lr" from 0.001 to 0.0001 works for me.

[gitUserGoodLeaner]

Thanks, I will try your suggestions. 2018-06-21 21:49 GMT+08:00 chensonglu <[email protected]>:

…

@gitUserGoodLeaner <https://github.com/gitUserGoodLeaner> I encounter the same problem and changing the "base_lr" from 0.001 to 0.0001 works for me. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#3 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AgnB8CNx965v9jtc3PY4SGm4_gYpQko5ks5t-6RMgaJpZM4RMGZQ> .

[keck91]

@makefile

@liulei01 My training loss of ship task doesn't decrease and keeps 8.0 ~ 9.0 between iterations of 5000 ~ 20000. I do as the README instruction and used the rbox_util.cpp.ship and set batchsize = 32, use only 1 GPU. Is this loss normal?
@gitUserGoodLeaner Have you figured out the problem?

I am facing the same problem. The loss remains at around 7.1.
Have you found a solution meanwhile?