Defining a deep learning model in PyTorch, I have read something similar:
class Network(torch.nn.Module):
def __init__(self, in_channels, hidden_channels, out_channels, dropout, prop, **kwargs):
super(Network, self).__init__()
What is not clear to me is, why in the super constructor people write the name of the class (Network in this case) itself? I would have better interpreted something like
super().__init__()
so just inheriting attributes of the parent class..