Flops computation for swin transformer

[russ-spec]

Hi all, as title described, in the view of engineering and chip, one MAC(Multiply Accumulate) equals two Ops. So the flops computation for Convolution, MatMul, Linear should multiply to 2，which as changed here. Thus, for the swin-v1-tiny, the whole Flops should be 9GFlops.

### Tasks
- [ ] https://github.com/microsoft/Swin-Transformer/pull/339