Regarding the demonstration for faster acceleration results in pytorch

[seulkiyeom]

Hi Ke Ding,

I'm currently implementing your meProp code to understand the flow of the architecture in detail.

However, I couln't see the improved acceleration speed of meprop compared to that of conventional CNN.

In the table 7 and 8 of paper Sun et al., 2017, pytorch based GPU computation can achieve more faster back-propagation procedure.

Could you please let me know how to implement meprop to show faster backprop computation?

Best, Seul-Ki

[akaniklaus]

Hello,

I also didn't experience the speed improvement. There is authors' implementation in the below link but it seems much more complex to plug & play'; and they only provided it for nn.Linear but not Conv(s).

https://github.com/lancopku/meProp/tree/master/src/pytorch