How to use the fvcore.nn.weight_init function in fvcore

self.add_module("mask_fcn{}".format(k + 1), conv)
            self.conv_norm_relus.append(conv)

        self.deconv = ConvTranspose2d(
            conv_dims if num_conv > 0 else input_channels,
            conv_dims,
            kernel_size=2,
            stride=2,
            padding=0,
        )

        num_mask_classes = 1 if cls_agnostic_mask else num_classes
        self.predictor = Conv2d(conv_dims, num_mask_classes, kernel_size=1, stride=1, padding=0)

        for layer in self.conv_norm_relus + [self.deconv]:
            weight_init.c2_msra_fill(layer)
        # use normal distribution initialization for mask prediction layer
        nn.init.normal_(self.predictor.weight, std=0.001)
        if self.predictor.bias is not None:
            nn.init.constant_(self.predictor.bias, 0)

num_branch=num_branch,
            test_branch_idx=test_branch_idx,
            norm=get_norm(norm, bottleneck_channels),
        )

        self.conv3 = Conv2d(
            bottleneck_channels,
            out_channels,
            kernel_size=1,
            bias=False,
            norm=get_norm(norm, out_channels),
        )

        for layer in [self.conv1, self.conv2, self.conv3, self.shortcut]:
            if layer is not None:  # shortcut can be None
                weight_init.c2_msra_fill(layer)

norm=get_norm(norm, conv_dim),
                activation=F.relu,
            )
            self.add_module("conv{}".format(k + 1), conv)
            self.conv_norm_relus.append(conv)
            self._output_size = (conv_dim, self._output_size[1], self._output_size[2])

        self.fcs = []
        for k in range(num_fc):
            fc = nn.Linear(np.prod(self._output_size), fc_dim)
            self.add_module("fc{}".format(k + 1), fc)
            self.fcs.append(fc)
            self._output_size = fc_dim

        for layer in self.conv_norm_relus:
            weight_init.c2_msra_fill(layer)
        for layer in self.fcs:
            weight_init.c2_xavier_fill(layer)

dilation=dilation,
            deformable_groups=deform_num_groups,
            norm=get_norm(norm, bottleneck_channels),
        )

        self.conv3 = Conv2d(
            bottleneck_channels,
            out_channels,
            kernel_size=1,
            bias=False,
            norm=get_norm(norm, out_channels),
        )

        for layer in [self.conv1, self.conv2, self.conv3, self.shortcut]:
            if layer is not None:  # shortcut can be None
                weight_init.c2_msra_fill(layer)

        nn.init.constant_(self.conv2_offset.weight, 0)
        nn.init.constant_(self.conv2_offset.bias, 0)