usage: NBSSCLI.py [-h] [--config CONFIG] [--print_config [={comments,skip_null,skip_default}+]] {fit,validate,test,predict,tune} ... NBSSCLI-debug.py: error: 'Configuration check failed :: No action for destination key "test.model.lr_scheduler_kwargs.mode" to check its value.'

[DRJAIF49]

python NBSSCLI.py test --config=logs/NBSS_ifp/version_66/config-test.yaml --ckpt_path=logs/NBSS_ifp/version_66/checkpoints/epoch707_neg_si_sdr-13.7777.ckpt --trainer.gpus=0, --data.seeds="{'train':null,'val':2,'test':3}" Hello, we encountered this problem in the test according to the example you sent. How can we solve it

[quancs]

Could you post the packages installed using pip list

[quancs]

Sorry, the checkpoints are old ones. You can train it from scratch

[quancs]

The new checkpoints are available now.

[quancs]

I close the issue now. If you still have any question, you can reopen it.

[wen0320]

usage: NBSSCLI.py [-h] [--config CONFIG] [--print_config [={comments,skip_null,skip_default}+]] {fit,validate,test,predict,tune} ... NBSSCLI.py: error: '"subcommand" is required but not given or its value is None.' According to what you said in the README, we will only modify the path of the data in NB-BLSTM-fit. yml. The above question appears, could you please answer it?

[quancs]

@WenbingWei Did you set the subcommand in your command, like fit, validate, test, predict, tune? You can post your command, so that I can test if your command works or not on my computer.

[quancs]

For example, python NBSSCLI.py fit ..., python NBSSCLI.py test ..., .... Introduction about CLI (command line interface) can be found in the CLI docs of pytorch-lightning.

[wen0320]

@quancs Thank you very much for your reply, which helped me a lot and made me realize that Pytorch-Lightning and PyTorch run code differently. This was my first experience with Pytorch-Lightning, and the questions I asked seemed a bit silly. Thank you again for your reply.

[quancs]

Haha~ You are welcome. It's not silly, it's just because we didn't mention that in the readme. Thanks to your question, we know that we need to remind the users to read the CLI docs first.