How to use the mmdet.models.builder.build_loss function in mmdet

raise ValueError(
                'Invalid upsample method {}, accepted methods '
                'are "deconv", "nearest", "bilinear"'.format(upsample_method))
        self.num_convs = num_convs
        self.roi_feat_size = roi_feat_size  # WARN: not used and reserved
        self.in_channels = in_channels
        self.conv_kernel_size = conv_kernel_size
        self.conv_out_channels = conv_out_channels
        self.upsample_method = upsample_method
        self.upsample_ratio = upsample_ratio
        self.num_classes = num_classes
        self.class_agnostic = class_agnostic
        self.conv_cfg = conv_cfg
        self.norm_cfg = norm_cfg
        self.fp16_enabled = False
        self.loss_mask = build_loss(loss_mask)

        self.convs = nn.ModuleList()
        for i in range(self.num_convs):
            in_channels = (
                self.in_channels if i == 0 else self.conv_out_channels)
            padding = (self.conv_kernel_size - 1) // 2
            self.convs.append(
                ConvModule(
                    in_channels,
                    self.conv_out_channels,
                    self.conv_kernel_size,
                    padding=padding,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg))
        upsample_in_channels = (
            self.conv_out_channels if self.num_convs > 0 else in_channels)

'Invalid upsample method {}, accepted methods '
                'are "deconv", "nearest", "bilinear"'.format(upsample_method))
        self.num_convs = num_convs
        # WARN: roi_feat_size is reserved and not used
        self.roi_feat_size = _pair(roi_feat_size)
        self.in_channels = in_channels
        self.conv_kernel_size = conv_kernel_size
        self.conv_out_channels = conv_out_channels
        self.upsample_method = upsample_method
        self.upsample_ratio = upsample_ratio
        self.num_classes = num_classes
        self.class_agnostic = class_agnostic
        self.conv_cfg = conv_cfg
        self.norm_cfg = norm_cfg
        self.fp16_enabled = False
        self.loss_mask = build_loss(loss_mask)

        self.convs = nn.ModuleList()
        for i in range(self.num_convs):
            in_channels = (
                self.in_channels if i == 0 else self.conv_out_channels)
            padding = (self.conv_kernel_size - 1) // 2
            self.convs.append(
                ConvModule(
                    in_channels,
                    self.conv_out_channels,
                    self.conv_kernel_size,
                    padding=padding,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg))
        upsample_in_channels = (
            self.conv_out_channels if self.num_convs > 0 else in_channels)

type='SmoothL1Loss', beta=1.0, loss_weight=1.0)):
        super(BBoxHead, self).__init__()
        assert with_cls or with_reg
        self.with_avg_pool = with_avg_pool
        self.with_cls = with_cls
        self.with_reg = with_reg
        self.roi_feat_size = _pair(roi_feat_size)
        self.roi_feat_area = self.roi_feat_size[0] * self.roi_feat_size[1]
        self.in_channels = in_channels
        self.num_classes = num_classes
        self.target_means = target_means
        self.target_stds = target_stds
        self.reg_class_agnostic = reg_class_agnostic
        self.fp16_enabled = False

        self.loss_cls = build_loss(loss_cls)
        self.loss_bbox = build_loss(loss_bbox)

        in_channels = self.in_channels
        if self.with_avg_pool:
            self.avg_pool = nn.AvgPool2d(self.roi_feat_size)
        else:
            in_channels *= self.roi_feat_area
        if self.with_cls:
            self.fc_cls = nn.Linear(in_channels, num_classes)
        if self.with_reg:
            out_dim_reg = 4 if reg_class_agnostic else 4 * num_classes
            self.fc_reg = nn.Linear(in_channels, out_dim_reg)
        self.debug_imgs = None

type='SmoothL1Loss', beta=1.0, loss_weight=1.0)):
        super(BBoxHead, self).__init__()
        assert with_cls or with_reg
        self.with_avg_pool = with_avg_pool
        self.with_cls = with_cls
        self.with_reg = with_reg
        self.roi_feat_size = roi_feat_size
        self.in_channels = in_channels
        self.num_classes = num_classes
        self.target_means = target_means
        self.target_stds = target_stds
        self.reg_class_agnostic = reg_class_agnostic
        self.fp16_enabled = False

        self.loss_cls = build_loss(loss_cls)
        self.loss_bbox = build_loss(loss_bbox)

        in_channels = self.in_channels
        if self.with_avg_pool:
            self.avg_pool = nn.AvgPool2d(roi_feat_size)
        else:
            in_channels *= (self.roi_feat_size * self.roi_feat_size)
        if self.with_cls:
            self.fc_cls = nn.Linear(in_channels, num_classes)
        if self.with_reg:
            out_dim_reg = 4 if reg_class_agnostic else 4 * num_classes
            self.fc_reg = nn.Linear(in_channels, out_dim_reg)
        self.debug_imgs = None

type='CrossEntropyLoss',
                     use_sigmoid=True,
                     loss_weight=1.0),
                 conv_cfg=None,
                 norm_cfg=dict(type='GN', num_groups=32, requires_grad=True)):
        super(PolarMask_Head, self).__init__()

        self.num_classes = num_classes
        self.cls_out_channels = num_classes - 1
        self.in_channels = in_channels
        self.feat_channels = feat_channels
        self.stacked_convs = stacked_convs
        self.strides = strides
        self.regress_ranges = regress_ranges
        self.loss_cls = build_loss(loss_cls)
        self.loss_bbox = build_loss(loss_bbox)
        self.loss_mask = build_loss(loss_mask)
        self.loss_centerness = build_loss(loss_centerness)
        self.conv_cfg = conv_cfg
        self.norm_cfg = norm_cfg
        self.fp16_enabled = False
        # xez add for polarmask
        self.use_dcn = use_dcn
        self.mask_nms = mask_nms

        # debug vis img
        self.vis_num = 1000
        self.count = 0

        # test
        self.angles = torch.range(0, 350, 10).cuda() / 180 * math.pi

self.anchor_base_sizes = list(
            anchor_strides) if anchor_base_sizes is None else anchor_base_sizes
        self.target_means = target_means
        self.target_stds = target_stds

        self.use_sigmoid_cls = loss_cls.get('use_sigmoid', False)
        self.sampling = loss_cls['type'] not in ['FocalLoss', 'GHMC']
        if self.use_sigmoid_cls:
            self.cls_out_channels = num_classes - 1
        else:
            self.cls_out_channels = num_classes

        if self.cls_out_channels <= 0:
            raise ValueError('num_classes={} is too small'.format(num_classes))

        self.loss_cls = build_loss(loss_cls)
        self.loss_bbox = build_loss(loss_bbox)
        self.fp16_enabled = False

        self.anchor_generators = []
        for anchor_base in self.anchor_base_sizes:
            self.anchor_generators.append(
                AnchorGenerator(anchor_base, anchor_scales, anchor_ratios))

        self.num_anchors = len(self.anchor_ratios) * len(self.anchor_scales)
        self._init_layers()

self.octave_ratios))
            # Generators for squares
            self.square_generators.append(
                AnchorGenerator(anchor_base, [self.octave_base_scale], [1.0]))
        # one anchor per location
        self.num_anchors = 1
        self.use_sigmoid_cls = loss_cls.get('use_sigmoid', False)
        self.cls_focal_loss = loss_cls['type'] in ['FocalLoss']
        self.loc_focal_loss = loss_loc['type'] in ['FocalLoss']
        if self.use_sigmoid_cls:
            self.cls_out_channels = self.num_classes - 1
        else:
            self.cls_out_channels = self.num_classes

        # build losses
        self.loss_loc = build_loss(loss_loc)
        self.loss_shape = build_loss(loss_shape)
        self.loss_cls = build_loss(loss_cls)
        self.loss_bbox = build_loss(loss_bbox)

        self.fp16_enabled = False

        self._init_layers()

self.point_feat_channels, 1)))
                so_trans.append(
                    nn.Sequential(
                        nn.Conv2d(
                            self.point_feat_channels,
                            self.point_feat_channels,
                            5,
                            1,
                            2,
                            groups=self.point_feat_channels),
                        nn.Conv2d(self.point_feat_channels,
                                  self.point_feat_channels, 1)))
            self.forder_trans.append(fo_trans)
            self.sorder_trans.append(so_trans)

        self.loss_grid = build_loss(loss_grid)

type='CrossEntropyLoss',
                     use_sigmoid=True,
                     loss_weight=1.0),
                 conv_cfg=None,
                 norm_cfg=dict(type='GN', num_groups=32, requires_grad=True)):
        super(FCOS_Instance_Head_MIOU_MSKCTNESS, self).__init__()

        self.num_classes = num_classes
        self.cls_out_channels = num_classes - 1
        self.in_channels = in_channels
        self.feat_channels = feat_channels
        self.stacked_convs = stacked_convs
        self.strides = strides
        self.regress_ranges = regress_ranges
        self.loss_cls = build_loss(loss_cls)
        self.loss_bbox = build_loss(loss_bbox)
        self.loss_mask = build_loss(loss_mask)
        self.loss_centerness = build_loss(loss_centerness)
        self.conv_cfg = conv_cfg
        self.norm_cfg = norm_cfg
        self.fp16_enabled = False
        # xez add for polarmask
        self.center_sample = True
        self.use_mask_center = True
        self.use_dcn = use_dcn

        # debug vis img
        self.vis_num = 1000
        self.count = 0

        # test
        self.angles = torch.range(0, 350, 10).cuda() / 180 * math.pi

self.anchor_scales = anchor_scales
        self.anchor_ratios = anchor_ratios
        self.anchor_strides = anchor_strides
        # self.anchor_base_sizes被置为self.anchor_strides即降采样步长（如果不设置anchor_base_sizes的固定尺寸）
        self.anchor_base_sizes = list(
            anchor_strides) if anchor_base_sizes is None else anchor_base_sizes
        self.target_means = target_means
        self.target_stds = target_stds
        
        self.use_sigmoid_cls = loss_cls.get('use_sigmoid', False) # 查看是否使用sigmoid，如果没写默认False
        self.sampling = loss_cls['type'] not in ['FocalLoss', 'GHMC'] # 如果不是focal或者GHMC则采样标志为True，否则不可直接采样
        if self.use_sigmoid_cls:
            self.cls_out_channels = num_classes - 1
        else:
            self.cls_out_channels = num_classes
        self.loss_cls = build_loss(loss_cls)
        self.loss_bbox = build_loss(loss_bbox)
        self.fp16_enabled = False

        self.anchor_generators = []
        for anchor_base in self.anchor_base_sizes:
            self.anchor_generators.append(
                AnchorGenerator(anchor_base, anchor_scales, anchor_ratios))

        self.num_anchors = len(self.anchor_ratios) * len(self.anchor_scales)
        self._init_layers()