def init_network_weights()

in Dassl.pytorch/dassl/utils/torchtools.py [0:0]

• 26 lines of code
• 14 McCabe index (conditional complexity)

def init_network_weights(model, init_type="normal", gain=0.02):

    def _init_func(m):
        classname = m.__class__.__name__

        if hasattr(m, "weight") and (
            classname.find("Conv") != -1 or classname.find("Linear") != -1
        ):
            if init_type == "normal":
                nn.init.normal_(m.weight.data, 0.0, gain)
            elif init_type == "xavier":
                nn.init.xavier_normal_(m.weight.data, gain=gain)
            elif init_type == "kaiming":
                nn.init.kaiming_normal_(m.weight.data, a=0, mode="fan_in")
            elif init_type == "orthogonal":
                nn.init.orthogonal_(m.weight.data, gain=gain)
            else:
                raise NotImplementedError
            if hasattr(m, "bias") and m.bias is not None:
                nn.init.constant_(m.bias.data, 0.0)

        elif classname.find("BatchNorm") != -1:
            nn.init.constant_(m.weight.data, 1.0)
            nn.init.constant_(m.bias.data, 0.0)

        elif classname.find("InstanceNorm") != -1:
            if m.weight is not None and m.bias is not None:
                nn.init.constant_(m.weight.data, 1.0)
                nn.init.constant_(m.bias.data, 0.0)

    model.apply(_init_func)