Several questions about paper

[Liuyang829]

Thanks for your great work. But I have some questions about paper. In Eq1 v_i=\frac{\sum_{j=1}^n(t_j-\mu)^2}{n-1}, which means that the variance of all x_i in one batch are all the same according to this equ. How can this represent the diversity of feature of each data point x_i , or you just assume that all the data point in same one batch have same variance. And another question for family of SkipNet models. The different parameters and FLOPs for different SkipNet model is just controlled by width_mult or another thing? Thank you very much. I am really looking forward to your reply on my first question

[lusinlu]

AS mentioned in the paper (before Eq. 1) v_i is the variance of the feature maps of the i-th data point in the batch, where t_i stands for i-th data point in the batch, hence the variance of each data point in the batch is considered to be different. The SkipNet models are controlled only by width_mult.