Can not detect object after training your network ?

Question

Can not detect object after training your network ?

ngthanhtin opened this issue 6 years ago · comments

Hello, I have modified your net to train only 2 objects which are dog and person, but after training process, I get the loss is around 6 and then I tested (inference) the pre-trained model, the net can not detect anything. Do you have encounter this problem ? If yes, please tell me where is wrong.
Anyway, thanks for your contribution.

Benzzzxxx · Answer 1 · Wed Jan 23 2019 10:45:02 GMT+0800 (China Standard Time)

Maybe your train data is not enough or train epochs is not enough.

dididii · Answer 2 · Sat Apr 06 2019 16:20:16 GMT+0800 (China Standard Time)

I have meet the same problem,but my loss was very high,it's about 10,how about yours?

Unhapppy · Answer 3 · Tue Apr 16 2019 17:23:36 GMT+0800 (China Standard Time)

i met the same problem, have you solved it?

Jeremy-lf · Answer 4 · Tue Apr 16 2019 23:05:14 GMT+0800 (China Standard Time)

so am i ,what's your solution?

Thanh Tin Nguyen · Answer 5 · Wed Apr 17 2019 08:59:23 GMT+0800 (China Standard Time)

i dont know, either

eefresher · Answer 6 · Tue Apr 23 2019 20:08:22 GMT+0800 (China Standard Time)

i also have same problem ,my loss is acound 7

mxazz123 · Answer 7 · Sun Jul 14 2019 23:56:46 GMT+0800 (China Standard Time)

The loss is too high. Just uncomments the WEIGHTS in yolo/config file, and retrain it

Thanh Tin Nguyen · Answer 8 · Mon Jul 15 2019 12:01:19 GMT+0800 (China Standard Time)

thank you very much :D