the output is strange after training on my own dataset about dbnet HOT 4 CLOSED

Hi, it is pretty strange. There must be some bugs while transplanting to your dataset. I could not ensure the problems with the information provided. Have you modified the loss by the way or adjust the hyper-parameters? Will the training loss decrease in the training?

from dbnet.

Sorry for not responding in time. I don`t understand why should I change the loss? For now I am working on the image only model, and besides IO I did not change any other things. The loss only drops in the first epoch and did not decrease over dozens epochs. The loss is like:

What can I do to make the loss decrease? I had doubled the train set already.

from dbnet.

Also I change the lr decrease steps, so the lr is normal, I think. I also tried to use the pre-trained res-151 model to initialize the network but it turned out to be the same.

from dbnet.

Sorry, I still don't know the causes from your description :(
It is hard to diagnose from the experience without the code and data.

from dbnet.