why forward processing time is larger than alexnet?

[mollyStark]

Hi, I used your model to finetune my training data, and it worked well! But I noticed that the the forward processing time is 3 times larger than caffe alexnet(0.09s vs 0.03s). The paper says this model has less computation than alexnet, but why the processing time is larger?

[shicai]

due to poor implementations of caffe group convolutions.