Class InterpConv

segmentation/backbones/unet.py:151–221

Interpolation upsample module in decoder for UNet. This module uses interpolation to upsample feature map in the decoder of UNet. It consists of one interpolation upsample layer and one convolutional layer. It can be one interpolation upsample layer followed by one convolutional lay

@UPSAMPLE_LAYERS.register_module()
class InterpConv(nn.Module):
    """Interpolation upsample module in decoder for UNet.

    This module uses interpolation to upsample feature map in the decoder
    of UNet. It consists of one interpolation upsample layer and one
    convolutional layer. It can be one interpolation upsample layer followed
    by one convolutional layer (conv_first=False) or one convolutional layer
    followed by one interpolation upsample layer (conv_first=True).

    Args:
        in_channels (int): Number of input channels.
        out_channels (int): Number of output channels.
        with_cp (bool): Use checkpoint or not. Using checkpoint will save some
            memory while slowing down the training speed. Default: False.
        norm_cfg (dict | None): Config dict for normalization layer.
            Default: dict(type='BN').
        act_cfg (dict | None): Config dict for activation layer in ConvModule.
            Default: dict(type='ReLU').
        conv_cfg (dict | None): Config dict for convolution layer.
            Default: None.
        conv_first (bool): Whether convolutional layer or interpolation
            upsample layer first. Default: False. It means interpolation
            upsample layer followed by one convolutional layer.
        kernel_size (int): Kernel size of the convolutional layer. Default: 1.
        stride (int): Stride of the convolutional layer. Default: 1.
        padding (int): Padding of the convolutional layer. Default: 1.
        upsample_cfg (dict): Interpolation config of the upsample layer.
            Default: dict(
                scale_factor=2, mode='bilinear', align_corners=False).
    """

    def __init__(self,
                 in_channels,
                 out_channels,
                 with_cp=False,
                 norm_cfg=dict(type='BN'),
                 act_cfg=dict(type='ReLU'),
                 *,
                 conv_cfg=None,
                 conv_first=False,
                 kernel_size=1,
                 stride=1,
                 padding=0,
                 upsample_cfg=dict(
                     scale_factor=2, mode='bilinear', align_corners=False)):
        super(InterpConv, self).__init__()

        self.with_cp = with_cp
        conv = ConvModule(
            in_channels,
            out_channels,
            kernel_size=kernel_size,
            stride=stride,
            padding=padding,
            conv_cfg=conv_cfg,
            norm_cfg=norm_cfg,
            act_cfg=act_cfg)
        upsample = Upsample(**upsample_cfg)