Class PatchEmbed

mmseg/models/utils/embed.py:77–197

Image to Patch Embedding. We use a conv layer to implement PatchEmbed. Args: in_channels (int): The num of input channels. Default: 3 embed_dims (int): The dimensions of embedding. Default: 768 conv_type (str): The config dict for embedding conv layer ty

class PatchEmbed(BaseModule):
    """Image to Patch Embedding.

    We use a conv layer to implement PatchEmbed.

    Args:
        in_channels (int): The num of input channels. Default: 3
        embed_dims (int): The dimensions of embedding. Default: 768
        conv_type (str): The config dict for embedding
            conv layer type selection. Default: "Conv2d".
        kernel_size (int): The kernel_size of embedding conv. Default: 16.
        stride (int, optional): The slide stride of embedding conv.
            Default: None (Would be set as `kernel_size`).
        padding (int | tuple | string ): The padding length of
            embedding conv. When it is a string, it means the mode
            of adaptive padding, support "same" and "corner" now.
            Default: "corner".
        dilation (int): The dilation rate of embedding conv. Default: 1.
        bias (bool): Bias of embed conv. Default: True.
        norm_cfg (dict, optional): Config dict for normalization layer.
            Default: None.
        input_size (int | tuple | None): The size of input, which will be
            used to calculate the out size. Only work when `dynamic_size`
            is False. Default: None.
        init_cfg (`mmcv.ConfigDict`, optional): The Config for initialization.
            Default: None.
    """

    def __init__(
        self,
        in_channels=3,
        embed_dims=768,
        conv_type="Conv2d",
        kernel_size=16,
        stride=None,
        padding="corner",
        dilation=1,
        bias=True,
        norm_cfg=None,
        input_size=None,
        init_cfg=None,
    ):
        super(PatchEmbed, self).__init__(init_cfg=init_cfg)

        self.embed_dims = embed_dims
        if stride is None:
            stride = kernel_size

        kernel_size = to_2tuple(kernel_size)
        stride = to_2tuple(stride)
        dilation = to_2tuple(dilation)

        if isinstance(padding, str):
            self.adap_padding = AdaptivePadding(
                kernel_size=kernel_size, stride=stride, dilation=dilation, padding=padding
            )
            # disable the padding of conv
            padding = 0