Re:Grand jury indicts Trevor Milton, Nikola founder, on thre...
by godelski on Friday July 30, 2021 @01:18AM
(#28004734)
> MobileNet
Okay, compare accuracy of MobileNet to ViT. ViT has 90.45% accuracy and 1.843Bn parameters and MobileNet has 79% with 5.47M parameters (2020, v3 is 75% with 5.4). [0]
These two networks are nowhere near equal. If you could put ViT on a phone and run real-time inference you would. But you can't, so you take a major cut in performance to get what you can.
There are multiple metrics you need to look at when evaluating networks. "Being able to perform on a dataset" is not even that useful of one.
Okay, compare accuracy of MobileNet to ViT. ViT has 90.45% accuracy and 1.843Bn parameters and MobileNet has 79% with 5.47M parameters (2020, v3 is 75% with 5.4). [0]
These two networks are nowhere near equal. If you could put ViT on a phone and run real-time inference you would. But you can't, so you take a major cut in performance to get what you can.
There are multiple metrics you need to look at when evaluating networks. "Being able to perform on a dataset" is not even that useful of one.
[0] Have fun https://paperswithcode.com/sota/image-classification-on-imag...