Adding an extra dimension in weight matrix in Tensorflow

I was reading styleGAN2 code, in the networks_stylegan2.py file at line 95, they have added an extra dimension in the weight matrix for incorporating mini-batch. What I know is that TensorFlow can handle the mini-batch automatically if we define the first dimension in input as "None" and there is no need to add an extra dimension weight matrix for the mini-batch. So why they have added an extra dimension in the weight matrix?