accury problem ade20k
zxmyyds opened this issue · comments
What modifications did you made? And which dataset did you use? Would you please tell me how did you reach this result?
@CoinCheung I did not make any modification and trained ade20k 2016 according to the instructions. I also wonder why some training shows 0. Have you encountered such a situation
Then tell me what is your environment is like, and the steps following which I can achieve your result?
Maybe you should adjust your batch size to match the configuration of what I used. I used 8 gpus, but you only used one.
If your gpu memory cannot afford such batch size, you should try to reduce learning rate.
The training parameters I provided is not carefully tuned(because authors did not have such experiments in the paper), maybe you can have a round of grid search to find the best configuration.
Thanks I used the city training set and its accuracy is normal and I need to try it again
Maybe you have achieved the results that you see correct, so I am closing this.
Thanks I used the city training set and its accuracy is normal and I need to try it again
I met the same problem on one single GPU without any modification, did you solve the problem? thank you