I have a 60G Flops model, a 4G Flops model, and a one-layer model with 3*3 kernels. I ran them offline on 64bit Qualcomm Snapdragon 845, Octa-core, 2.8GHz
60G
4G
one-layer
online
0.8~0.9
0.3~0.4
0.01
offline
1.3
0.13
0.001
Why is only the runtime of 60G 2 times greater than that of 4G...