Pau Rodriguez
Pau Rodriguez
This is weird, I just reproduced them for another issue. Could you share your log and executing command?
Looking at your log, I would say that one of the main differences is the batch size. Since you multiply it for the number of gpus, you should modify the...
Does it happen with all the other setups?
Weird, I'll try to run it again with the new version of pytorch. Meanwhile it would be interesting to see what results you get with the dropout versions. I reproduced...
@Fridaycoder it could be. I'll try to run again with pytorch 1.3.1
Hi, thanks for pointing out the issue, I am looking for the logs to put them again. If I have to rerun the code it may take more time.
I have uploaded logs on CIFAR, now I am uploading the logs on ImageNet
Done
Hi, the results I report are the median of five runs, so maybe if you run more times you will find the correct accuracy. It is also possible that the...
Ah, maybe you should add 0.3 dropout. The baseline in the sh is the no_dropout baseline I think.