lhoyer/DAFormer

Questions about training on custom dataset

qubewx opened this issue · 3 comments

When I was training, I found that the accuracy of verification set was very high at the beginning and then it began to decline. Besides, the segmentation graph generated by demo-image.py was not effective. Besides, I did not see the Lt loss function marked in the graph on the code. Thank you

Could you please provide further details to your issue:

  • Can you please upload the concerning log file?
  • What do you mean with "segmentation graph"? Do you mean the predicted semantic segmentation?
  • What do you mean with "not effective"?

You can find the backward of the target loss here:

mix_loss.backward()

[
20230301_211002.log
Thanks for your reply. The above is my log file,the 4347th row shows the 8000 epoch' result,89% .But after this,the aACC always decline.Besize, Can you send me your train log?Thank you very much!

It seems that you only train with two classes on custom datasets. Without knowing your setup, I cannot provide insights what causes the issues, which you observe. The DAFormer checkpoints from https://github.com/lhoyer/DAFormer#checkpoints are accompanied with logs.