Can anyone really reproduce the result with the code?

[triangleCZH]

To be honest I think the previous 75+ acc was a misreport because his previous version has the attention part with much more params.

[cxxgtxy]

@triangleCZH I find 3 models which is better than v3large based on NAS, please refer to https://github.com/xiaomi-automl/MoGA

[nullptr-leo]

@triangleCZH I find 3 models which is better than v3large based on NAS, please refer to https://github.com/xiaomi-automl/MoGA

@cxxgtxy MoGA is created for GPU. How about the performance on CPU?

[cxxgtxy]

@leo-nullptr Based on the paper, MoGA's peformance on mobile CPU is highly on par with MobileNetV3 too.

[nullptr-leo]

@cxxgtxy Thanks. I will read it later. Are you the author of MoGA?

[cxxgtxy]

@leo-nullptr Welcome. I recommend because I have tested it.

[triangleCZH]

@cxxgtxy Thank you. I will check the repo. Do they offer training scripts by the way?

[cxxgtxy]

@triangleCZH I think it's not difficult, because they train their models use google's tricks.