How to use the extensions.layers.syncbn.module.BatchNorm2d function in extensions

num_features = num_init_features
        for i, num_layers in enumerate(block_config):
            block = _DenseBlock(num_layers=num_layers, num_input_features=num_features,
                                bn_size=bn_size, growth_rate=growth_rate, drop_rate=drop_rate)
            self.features.add_module('denseblock%d' % (i + 1), block)
            num_features = num_features + num_layers * growth_rate
            if i != len(block_config) - 1:
                trans = _Transition(num_input_features=num_features, num_output_features=num_features // 2)
                avg_pool = nn.AvgPool2d(kernel_size=2, stride=2)
                self.features.add_module('transition%d' % (i + 1), trans)
                self.features.add_module('transition%s_pool' % (i + 1), avg_pool)
                num_features = num_features // 2

        self.num_features = num_features
        # Final batch norm
        self.features.add_module('norm5', BatchNorm2d(num_features))

        # Linear layer
        self.classifier = nn.Linear(num_features, num_classes)

        # Official init from torch repo.
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight)
            elif isinstance(m, BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.constant_(m.bias, 0)

def __init__(self, in_channels, out_channels):
        super(FCNHead, self).__init__()
        inter_channels = in_channels // 4
        from extensions.layers.syncbn.module import BatchNorm2d
        self.conv5 = nn.Sequential(nn.Conv2d(in_channels, inter_channels, 3, padding=1, bias=False),
                                   BatchNorm2d(inter_channels),
                                   nn.ReLU(),
                                   nn.Dropout2d(0.1, False),
                                   nn.Conv2d(inter_channels, out_channels, 1))

def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

)
        self.high_features = nn.Sequential(self.backbone.layer2, self.backbone.layer3)
        self.MG_features = _ResidualBlockMulGrid(inplanes=1024, midplanes=512, outplanes=2048, stride=2,
                                                 dilation=2, mulgrid=multi_grid)
        self.aspp1 = Atrous_module(2048, 256, 256, rate=pyramids[0])
        self.aspp2 = Atrous_module(2048, 256, 256, rate=pyramids[1])
        self.aspp3 = Atrous_module(2048, 256, 256, rate=pyramids[2])
        self.aspp4 = Atrous_module(2048, 256, 256, rate=pyramids[3])
        self.image_pool = nn.Sequential(nn.AdaptiveMaxPool2d(1),
                                        nn.Conv2d(2048, 256, kernel_size=1))

        self.fc1 = nn.Sequential(nn.Conv2d(1280, 256, kernel_size=1),  # 256 * 5 = 1280
                                 BatchNorm2d(256), nn.ReLU(inplace=True))

        self.reduce_conv2 = nn.Sequential(nn.Conv2d(256, 48, kernel_size=1),
                                          BatchNorm2d(48),
                                          nn.ReLU(inplace=True)
                                          )
        self.last_conv = nn.Sequential(nn.Conv2d(304, 256, kernel_size=3, stride=1, padding=1),
                                       BatchNorm2d(256),
                                       nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
                                       BatchNorm2d(256),
                                       nn.ReLU(inplace=True),
                                       nn.Dropout2d(0.1),
                                       nn.Conv2d(256, self.num_classes, kernel_size=1, stride=1))

def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, BatchNorm2d):
                m.weight.data.fill_(1)

def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

self.relu3 = nn.ReLU(inplace=True)

        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)