How to use the insightface.iresnet.IBasicBlock function in insightface

def iresnet34(pretrained=False, progress=True, **kwargs):
    return _iresnet('iresnet34', IBasicBlock, [3, 4, 6, 3], pretrained, progress,
                    **kwargs)

def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
                 base_width=64, dilation=1):
        super(IBasicBlock, self).__init__()
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.bn1 = nn.BatchNorm2d(inplanes, eps=2e-05, momentum=0.9)
        self.conv1 = conv3x3(inplanes, planes)
        self.bn2 = nn.BatchNorm2d(planes, eps=2e-05, momentum=0.9)
        self.prelu = nn.PReLU(planes)
        self.conv2 = conv3x3(planes, planes, stride)
        self.bn3 = nn.BatchNorm2d(planes, eps=2e-05, momentum=0.9)
        self.downsample = downsample
        self.stride = stride

self.bn2 = nn.BatchNorm2d(512 * block.expansion, eps=2e-05, momentum=0.9)
        self.dropout = nn.Dropout2d(p=0.4, inplace=True)
        self.fc = nn.Linear(512 * block.expansion * self.fc_scale, num_features)
        self.features = nn.BatchNorm1d(num_features, eps=2e-05, momentum=0.9)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, IBasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)