Add batchnorm parameters: running_mean, running_var, and others

[mostafaelhoushi]

Batchnorm has other parameters - in addition to weight and bias - that are not counted in torchsummary, such as running_mean and running_var:

https://pytorch.org/docs/stable/_modules/torch/nn/modules/batchnorm.html

[mostafaelhoushi]

I have created a pull request to address this issue:
#88