ImageNet Pretraining config

[nizhenliang]

您在文中并没有提到在imagenet上训练跑了多少epoch以及用了几块GPU，batch size是多大，还有优化器和学习率等参数。是否方便公布一下这些参数或者将预训练的log放出来？这会极大的帮助我们复现您的工作，非常感谢！

[mulinmeng]

您在文中并没有提到在imagenet上训练跑了多少epoch以及用了几块GPU，batch size是多大，还有优化器和学习率等参数。是否方便公布一下这些参数或者将预训练的log放出来？这会极大的帮助我们复现您的工作，非常感谢！

600epoch, batchsize 128*8, rmsprop，lr=0.064

[nizhenliang]

Thank you very much! According to the above settings, we still cannot achieve the experimental results in the paper. We would appreciate it if you could release the pre-trained config file.

[nizhenliang]

In addition, we found that the above config are consistent with the MobilenetV3 config in MMCLS. Does topformer use the same data augmentation approach as mobilenetv3?