mmedit.models.editors.swinir.swinir_modules 源代码

# Copyright (c) OpenMMLab. All rights reserved.
import math

import torch.nn as nn

from .swinir_utils import to_2tuple


class PatchEmbed(nn.Module):
    r""" Image to Patch Embedding
    Args:
        img_size (int): Image size.  Default: 224.
        patch_size (int): Patch token size. Default: 4.
        in_chans (int): Number of input image channels. Default: 3.
        embed_dim (int): Number of linear projection output channels.
            Default: 96.
        norm_layer (nn.Module, optional): Normalization layer. Default: None
    """

    def __init__(self,
                 img_size=224,
                 patch_size=4,
                 in_chans=3,
                 embed_dim=96,
                 norm_layer=None):
        super().__init__()
        img_size = to_2tuple(img_size)
        patch_size = to_2tuple(patch_size)
        patches_resolution = [
            img_size[0] // patch_size[0], img_size[1] // patch_size[1]
        ]
        self.img_size = img_size
        self.patch_size = patch_size
        self.patches_resolution = patches_resolution
        self.num_patches = patches_resolution[0] * patches_resolution[1]

        self.in_chans = in_chans
        self.embed_dim = embed_dim

        if norm_layer is not None:
            self.norm = norm_layer(embed_dim)
        else:
            self.norm = None

    def forward(self, x):
        """Forward function.

        Args:
            x (Tensor): Input tensor with shape (B, C, Ph, Pw).

        Returns:
            Tensor: Forward results.
        """
        x = x.flatten(2).transpose(1, 2)  # B Ph*Pw C
        if self.norm is not None:
            x = self.norm(x)
        return x


class PatchUnEmbed(nn.Module):
    r""" Image to Patch Unembedding
    Args:
        img_size (int): Image size.  Default: 224.
        patch_size (int): Patch token size. Default: 4.
        in_chans (int): Number of input image channels. Default: 3.
        embed_dim (int): Number of linear projection output channels.
            Default: 96.
        norm_layer (nn.Module, optional): Normalization layer. Default: None
    """

    def __init__(self,
                 img_size=224,
                 patch_size=4,
                 in_chans=3,
                 embed_dim=96,
                 norm_layer=None):
        super().__init__()
        img_size = to_2tuple(img_size)
        patch_size = to_2tuple(patch_size)
        patches_resolution = [
            img_size[0] // patch_size[0], img_size[1] // patch_size[1]
        ]
        self.img_size = img_size
        self.patch_size = patch_size
        self.patches_resolution = patches_resolution
        self.num_patches = patches_resolution[0] * patches_resolution[1]

        self.in_chans = in_chans
        self.embed_dim = embed_dim

    def forward(self, x, x_size):
        """Forward function.

        Args:
            x (Tensor): Input tensor with shape (B, L, C).
            x_size (tuple[int]): Resolution of input feature.

        Returns:
            Tensor: Forward results.
        """
        B, HW, C = x.shape
        x = x.transpose(1, 2).view(B, self.embed_dim, x_size[0],
                                   x_size[1])  # B Ph*Pw C
        return x


class Upsample(nn.Sequential):
    """Upsample module.

    Args:
        scale (int): Scale factor. Supported scales: 2^n and 3.
        num_feat (int): Channel number of intermediate features.
    """

    def __init__(self, scale, num_feat):
        m = []
        if (scale & (scale - 1)) == 0:  # scale = 2^n
            for _ in range(int(math.log(scale, 2))):
                m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1))
                m.append(nn.PixelShuffle(2))
        elif scale == 3:
            m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1))
            m.append(nn.PixelShuffle(3))
        else:
            raise ValueError(f'scale {scale} is not supported. '
                             'Supported scales: 2^n and 3.')
        super(Upsample, self).__init__(*m)


class UpsampleOneStep(nn.Sequential):
    """UpsampleOneStep module (the difference with Upsample is that it always
    only has 1conv + 1pixelshuffle) Used in lightweight SR to save parameters.

    Args:
        scale (int): Scale factor. Supported scales: 2^n and 3.
        num_feat (int): Channel number of intermediate features.
        num_out_ch (int): Channel number for PixelShuffle.
        input_resolution (tuple[int], optional): Input resolution.
            Default: None
    """

    def __init__(self, scale, num_feat, num_out_ch, input_resolution=None):
        self.num_feat = num_feat
        self.input_resolution = input_resolution
        m = []
        m.append(nn.Conv2d(num_feat, (scale**2) * num_out_ch, 3, 1, 1))
        m.append(nn.PixelShuffle(scale))
        super(UpsampleOneStep, self).__init__(*m)