Open redorangeyellowy opened 2 years ago
Hi. Thanks to your great study, I was doing some experiment.
But, I got something error when I ran the file 'train.py'.
As you said in README, I implemented like this: python train.py --gpu 0-3,
python train.py --gpu 0-3
but I got error:
corrupted size vs. prev_size Aborted (core dumped)
I thought that problem caused by multi-gpu training, so I re-implemented like this: python train.py --gpu 0,
python train.py --gpu 0
but I got same error message.
Do you know how can I solve this problem?
Maybe reducing the amount of data would work. Could you add
if len(self.datalist) > 1000: break
after https://github.com/facebookresearch/InterHand2.6M/blob/2b8061d2c8e762aa6fcb8e6f5d18f8a9e83bfd0c/data/InterHand2.6M/dataset.py#L108
I think there is no more aborted error.
Thank you!
Hi. Thanks to your great study, I was doing some experiment.
But, I got something error when I ran the file 'train.py'.
As you said in README, I implemented like this:
python train.py --gpu 0-3
,but I got error:
I thought that problem caused by multi-gpu training, so I re-implemented like this:
python train.py --gpu 0
,but I got same error message.
Do you know how can I solve this problem?