Effect of mean and scale during the training

[Maharshi-Aupera]

Hello,
Thanks for the great work. One thing I noticed is that if I change the default mean and scale value, the softmax loss overflows. The problem is that I can not use this 127.5 and 0.0078125 as the scale value somehow. Could anyone please suggest, how to use mean value as 127 and scale as 1.0 and still make the model convergent?

  transform_param {
    mean_value: 127.5
    mean_value: 127.5
    mean_value: 127.5
    scale: 0.0078125
    mirror: true
  }

Thanks.