Jacobjia comments

Repositories
Issues
Comments

Results 3 comments of


                                            Jacobjia

The Model seems not training for a long while

When there is only one GPU, the code works perfect, but when the number of GPU>1, it will definitely get stuck. I have no clue why that happens, because other...

The Model seems not training for a long while

The problem may appear in line 284 `loss.backward()`. As soon as I process this line, all gpus will directly go to 100% and get stuck.

TypeError: init() got an unexpected keyword argument 'log_dir'

you can just try tensorboardX==1.6

Jacobjia

The Model seems not training for a long while

The Model seems not training for a long while

TypeError: __init__() got an unexpected keyword argument 'log_dir'

TypeError: init() got an unexpected keyword argument 'log_dir'