PS: The FLOPs is approximated by multiplying two. https://github.com/Lyken17/pytorch-OpCounter/issues/46 pytorch-OpCounter/benchmark at master · Lyken17/pytorch-OpCountergithub.com/Lyken17/pytorch-OpCounter/tree/master/benchmark#macs-flops-what-is-the-difference 使用thop计算FLOPs和Params的大致...
As mentioned in the previous section, the major difference between FLOPs and MACs include what types of arithmetic operations they count and the context in which they are used. The general AI community consensus, like the GitHub comment in Figure 2, is one MACs equals roughly two FLOPs. For ...