Arithmetic intensity of some vision models


GFLOPS and params are obtained from Models and pre-trained weights — Torchvision main documentation. Parameters are all in float32 (4 bytes).

modelParamsGFLOPSFLOPS/byte
MobileNet_V3_Large54830320.2210.0
ShuffleNet_V2_X2_073939960.5819.6
ResNet1526019280811.5147.8
VGG1914366724019.6334.2
EfficientNet_V2_L11851527256.08118.3
ViT_B_168656765617.5650.7
Swin_V2_B8793084820.3257.8