monosdf icon indicating copy to clipboard operation
monosdf copied to clipboard

The final output result cannot be found

Open wujinhu1999 opened this issue 2 years ago • 5 comments

I'm not using distributed training, I changed the code slightly, the command I run on the terminal is:python training/exp_runner.py --local_rank=2 --conf confs/dtu_mlp_3views.conf --scan_id 65,and then: image After a period of training, the program stops without outputting any additional information: image Looking forward to your reply.

wujinhu1999 avatar Aug 31 '23 02:08 wujinhu1999

At your first training, the cuda kernel needs to be complied and it might take several minutes.

niujinshuchong avatar Aug 31 '23 08:08 niujinshuchong

But I have trained several times and still haven't seen the result.

wujinhu1999 avatar Aug 31 '23 08:08 wujinhu1999

Dose it start training?

niujinshuchong avatar Aug 31 '23 10:08 niujinshuchong

I want to ask if it has started training? But it does not output training process information. image

wujinhu1999 avatar Aug 31 '23 11:08 wujinhu1999

I think no as it will print the loss if it starts training.

niujinshuchong avatar Aug 31 '23 11:08 niujinshuchong