DING Guodong
DING Guodong
I've run into this too and solved it by simply reducing the batch size, this seems to be a gpu memory issue.
Your GPU is out of memory, you can try reduce batch size. Sent from my iPhone > On 23 Sep 2017, at 11:18 AM, sde123 wrote: > > @layumi >...
> Hi @gddingcs > Thank you for your attention on our paper. > How about the result in the stage I ? @layumi Seems like stage I also yielded a...
The only problem that I may have encountered is the preprocessing part where as instructed in the readme `resize_image` is done separately leading the `imdb.rgbMean` to be null, which I...
Sorry about the confusion that I first closed and the reopened this issue. I have found your relative reply under a closed issue saying GAN generated images are not used...
Thanks for the clearification. So you are first calculating every pair normally and then assign 0 instanceweight for those pairs contain either single fake image or both are fake, thus...
Same promblem here!!!! Can anyone shed some light on this??? Thanks in advance.
@vanhuyz Thanks for the reply, I have actually trained this twice, both have collapsed. Any lights on how to possibly fix this?
Hi I have managed to resolve this problem by revising some codes in `torchstat/compute_memory.py` Specifically, following revisions are made: replacing all `.size()[1:].numel()` to`[0].numel()` replacing all `size().numel()` to`.numel()` There you can...
> I could get the max MoF of 31.2% on BreakFast and on average 30.3% with 3 trials. I was an older version of the PyTorch and also my I3D...