d-li14 / mobilenetv3.pytorch

74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

https://arxiv.org/abs/1905.02244

Training procedure

irwinherrmann opened this issue 5 years ago · comments

Charles Herrmann commented 5 years ago

Specifically, what optimization algorithm, learning rate schedule, and batch size did you use?

Duo Li commented 5 years ago

the same as https://github.com/d-li14/mobilenetv2.pytorch

Charles Herrmann commented 5 years ago

Thanks! Btw, it might be useful to put this in the README.

Also, how many epochs did it take to converge?