miopen-benchmark icon indicating copy to clipboard operation
miopen-benchmark copied to clipboard

Does this benchmark judge the accuracy of the classification?

Open deltaguo opened this issue 3 years ago • 1 comments

Hi, I'm trying to train the dataset using resnet from your benchmark, I found that the initialization of the input is random in your code. And there is no label as input, I'm a little confused. Does this benchmark judge the accuracy of the classification?

deltaguo avatar Aug 09 '22 10:08 deltaguo

No it does not at all. This benchmark was for benchmarking the AMD GPU performance for training when using MiOpen

patflick avatar Aug 09 '22 15:08 patflick