Counting Multiple Addition Operations (MAC) in CNN Caffe Architecture

Recently, I have been comparing some CNNs in terms of time, #Multiple Add (MAC) operations, #parameters and model size. I saw some similar SO questions ( here and here ), and in the latter they suggest using the Netscope CNN Analyzer . This tool allows me to calculate most of the things I need by simply entering the definition of my Caffe network.

However, the number of re-adding operations of some architectures that I have seen in documents and on the Internet does not match what Netscope displays, while other architectures do. I always compare FLOP or MAC with the MACC column in netscope, but there is a ~ 10x factor that I forget at some point (see table below for more details).

Architecture ---- MAC (paper/internet) ---- macc column in netscope VGG 16 ~15.5G ~157G GoogLeNet ~1.55G ~16G 

Link to GoogLeNet macro number and VGG16 macc number in Netscope.

Could anyone who used this tool point me to the mistake I am making while reading the Netscope output?

+7
deep-learning caffe flops conv-neural-network
source share
1 answer

I found what caused the discrepancy between Netscope and the information I found in the newspapers. Most of the pre-installed architectures in Nestcope used a lot size of 10 (this applies to VGG and GoogLeNet ), so the coefficient is x10, which multiplies the number of operations with several add- ons .

+5
source share

All Articles