SWIN-UNET网络复现（高效无bug）

1.下载并解压工程包-Unet

GitHub - bubbliiiing/unet-pytorch: 这是一个unet-pytorch的源码，可以训练自己的模型

2.在代码中做如下修改

nets文件夹下新建文件nets.swin_unet.py

import math
import warnings
warnings.filterwarnings("ignore")
import torch
import torch.nn as nn
import torch.utils.checkpoint as checkpoint
from einops import rearrange
from timm.models.layers import DropPath, to_2tuple, trunc_normal_


class Mlp(nn.Module):
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)

    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x


def window_partition(x, window_size):
    """
    Args:
        x: (B, H, W, C)
        window_size (int): window size

    Returns:
        windows: (num_windows*B, window_size, window_size, C)
    """
    B, H, W, C = x.shape
    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
    return windows


def window_reverse(windows, window_size, H, W):
    """
    Args:
        windows: (num_windows*B, window_size, window_size, C)
        window_size (int): Window size
        H (int): Height of image
        W (int): Width of image

    Returns:
        x: (B, H, W, C)
    """
    B = int(windows.shape[0] / (H * W / window_size / window_size))
    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
    return x


class WindowAttention(nn.Module):
    r""" Window based multi-head self attention (W-MSA) module with relative position bias.
    It supports both of shifted and non-shifted window.

    Args:
        dim (int): Number of input channels.
        window_size (tuple[int]): The height and width of the window.
        num_heads (int): Number of attention heads.
        qkv_bias (bool, optional):  If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set
        attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
        proj_drop (float, optional): Dropout ratio of output. Default: 0.0
    """

    def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):

        super().__init__()
        self.dim = dim
        self.window_size = window_size  # Wh, Ww
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim ** -0.5

        # define a parameter table of relative position bias
        self.relative_position_bias_table = nn.Parameter(
            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads))  # 2*Wh-1 * 2*Ww-1, nH

        # get pair-wise relative position index for each token inside the window
        coords_h = torch.arange(self.window_size[0])
        coords_w = torch.arange(self.window_size[1])
        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
        relative_coords[:, :, 0] += self.window_size[0] - 1  # shift to start from 0
        relative_coords[:, :, 1] += self.window_size[1] - 1
        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
        self.register_buffer("relative_position_index", relative_position_index)

        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)

        trunc_normal_(self.relative_position_bias_table, std=.02)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x, mask=None):
        """
        Args:
            x: input features with shape of (num_windows*B, N, C)
            mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
        """
        B_, N, C = x.shape
        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple)

        q = q * self.scale
        attn = (q @ k.transpose(-2, -1))

        relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
            self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)  # Wh*Ww,Wh*Ww,nH
        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
        attn = attn + relative_position_bias.unsqueeze(0)

        if mask is not None:
            nW = mask.shape[0]
            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
            attn = attn.view(-1, self.num_heads, N, N)
            attn = self.softmax(attn)
        else:
            attn = self.softmax(attn)

        attn = self.attn_drop(attn)

        x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x

    def extra_repr(self) -> str:
        return f'dim={self.dim}, window_size={self.window_size}, num_heads={self.num_heads}'

    def flops(self, N):
        # calculate flops for 1 window with token length of N
        flops = 0
        # qkv = self.qkv(x)
        flops += N * self.dim * 3 * self.dim
        # attn = (q @ k.transpose(-2, -1))
        flops += self.num_heads * N * (self.dim // self.num_heads) * N
        #  x = (attn @ v)
        flops += self.num_heads * N * N * (self.dim // self.num_heads)
        # x = self.proj(x)
        flops += N * self.dim * self.dim
        return flops


class SwinTransformerBlock(nn.Module):
    r""" Swin Transformer Block.

    Args:
        dim (int): Number of input channels.
        input_resolution (tuple[int]): Input resulotion.
        num_heads (int): Number of attention heads.
        window_size (int): Window size.
        shift_size (int): Shift size for SW-MSA.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float, optional): Stochastic depth rate. Default: 0.0
        act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
    """

    def __init__(self, dim, input_resolution, num_heads, window_size=7, shift_size=0,
                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
                 act_layer=nn.GELU, norm_layer=nn.LayerNorm):
        super().__init__()
        self.dim = dim
        self.input_resolution = input_resolution
        self.num_heads = num_heads
        self.window_size = window_size
        self.shift_size = shift_size
        self.mlp_ratio = mlp_ratio
        if min(self.input_resolution) <= self.window_size:
            # if window size is larger than input resolution, we don't partition windows
            self.shift_size = 0
            self.window_size = min(self.input_resolution)
        assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"

        self.norm1 = norm_layer(dim)
        self.attn = WindowAttention(
            dim, window_size=to_2tuple(self.window_size), num_heads=num_heads,
            qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)

        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)

        if self.shift_size > 0:
            # calculate attention mask for SW-MSA
            H, W = self.input_resolution
            img_mask = torch.zeros((1, H, W, 1))  # 1 H W 1
            h_slices = (slice(0, -self.window_size),
                        slice(-self.window_size, -self.shift_size),
                        slice(-self.shift_size, None))
            w_slices = (slice(0, -self.window_size),
                        slice(-self.window_size, -self.shift_size),
                        slice(-self.shift_size, None))
            cnt = 0
            for h in h_slices:
                for w in w_slices:
                    img_mask[:, h, w, :] = cnt
                    cnt += 1

            mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1
            mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
            attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
            attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
        else:
            attn_mask = None

        self.register_buffer("attn_mask", attn_mask)

    def forward(self, x):
        H, W = self.input_resolution
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"

        shortcut = x
        x = self.norm1(x)
        x = x.view(B, H, W, C)

        # cyclic shift
        if self.shift_size > 0:
            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
        else:
            shifted_x = x

        # partition windows
        x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C

        # W-MSA/SW-MSA
        attn_windows = self.attn(x_windows, mask=self.attn_mask)  # nW*B, window_size*window_size, C

        # merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
        shifted_x = window_reverse(attn_windows, self.window_size, H, W)  # B H' W' C

        # reverse cyclic shift
        if self.shift_size > 0:
            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
        else:
            x = shifted_x
        x = x.view(B, H * W, C)

        # FFN
        x = shortcut + self.drop_path(x)
        x = x + self.drop_path(self.mlp(self.norm2(x)))

        return x

    def extra_repr(self) -> str:
        return f"dim={self.dim}, input_resolution={self.input_resolution}, num_heads={self.num_heads}, " \
               f"window_size={self.window_size}, shift_size={self.shift_size}, mlp_ratio={self.mlp_ratio}"

    def flops(self):
        flops = 0
        H, W = self.input_resolution
        # norm1
        flops += self.dim * H * W
        # W-MSA/SW-MSA
        nW = H * W / self.window_size / self.window_size
        flops += nW * self.attn.flops(self.window_size * self.window_size)
        # mlp
        flops += 2 * H * W * self.dim * self.dim * self.mlp_ratio
        # norm2
        flops += self.dim * H * W
        return flops


class PatchMerging(nn.Module):
    r""" Patch Merging Layer.

    Args:
        input_resolution (tuple[int]): Resolution of input feature.
        dim (int): Number of input channels.
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
    """

    def __init__(self, input_resolution, dim, norm_layer=nn.LayerNorm):
        super().__init__()
        self.input_resolution = input_resolution
        self.dim = dim
        self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
        self.norm = norm_layer(4 * dim)

    def forward(self, x):
        """
        x: B, H*W, C
        """
        H, W = self.input_resolution
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"
        assert H % 2 == 0 and W % 2 == 0, f"x size ({H}*{W}) are not even."

        x = x.view(B, H, W, C)

        x0 = x[:, 0::2, 0::2, :]  # B H/2 W/2 C
        x1 = x[:, 1::2, 0::2, :]  # B H/2 W/2 C
        x2 = x[:, 0::2, 1::2, :]  # B H/2 W/2 C
        x3 = x[:, 1::2, 1::2, :]  # B H/2 W/2 C
        x = torch.cat([x0, x1, x2, x3], -1)  # B H/2 W/2 4*C
        x = x.view(B, -1, 4 * C)  # B H/2*W/2 4*C

        x = self.norm(x)
        x = self.reduction(x)

        return x

    def extra_repr(self) -> str:
        return f"input_resolution={self.input_resolution}, dim={self.dim}"

    def flops(self):
        H, W = self.input_resolution
        flops = H * W * self.dim
        flops += (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim
        return flops


class PatchExpand(nn.Module):
    def __init__(self, input_resolution, dim, dim_scale=2, norm_layer=nn.LayerNorm):
        super().__init__()
        self.input_resolution = input_resolution
        self.dim = dim
        self.expand = nn.Linear(dim, 2 * dim, bias=False) if dim_scale == 2 else nn.Identity()
        self.norm = norm_layer(dim // dim_scale)

    def forward(self, x):
        """
        x: B, H*W, C
        """
        H, W = self.input_resolution
        x = self.expand(x)
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"

        x = x.view(B, H, W, C)
        x = rearrange(x, 'b h w (p1 p2 c)-> b (h p1) (w p2) c', p1=2, p2=2, c=C // 4)
        x = x.view(B, -1, C // 4)
        x = self.norm(x)

        return x


class FinalPatchExpand_X4(nn.Module):
    def __init__(self, input_resolution, dim, dim_scale=4, norm_layer=nn.LayerNorm):
        super().__init__()
        self.input_resolution = input_resolution
        self.dim = dim
        self.dim_scale = dim_scale
        self.expand = nn.Linear(dim, 16 * dim, bias=False)
        self.output_dim = dim
        self.norm = norm_layer(self.output_dim)

    def forward(self, x):
        """
        x: B, H*W, C
        """
        H, W = self.input_resolution
        x = self.expand(x)
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"

        x = x.view(B, H, W, C)
        x = rearrange(x, 'b h w (p1 p2 c)-> b (h p1) (w p2) c', p1=self.dim_scale, p2=self.dim_scale,
                      c=C // (self.dim_scale ** 2))
        x = x.view(B, -1, self.output_dim)
        x = self.norm(x)

        return x


class BasicLayer(nn.Module):
    """ A basic Swin Transformer layer for one stage.

    Args:
        dim (int): Number of input channels.
        input_resolution (tuple[int]): Input resolution.
        depth (int): Number of blocks.
        num_heads (int): Number of attention heads.
        window_size (int): Local window size.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
    """

    def __init__(self, dim, input_resolution, depth, num_heads, window_size,
                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0.,
                 drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False):

        super().__init__()
        self.dim = dim
        self.input_resolution = input_resolution
        self.depth = depth
        self.use_checkpoint = use_checkpoint

        # build blocks
        self.blocks = nn.ModuleList([
            SwinTransformerBlock(dim=dim, input_resolution=input_resolution,
                                 num_heads=num_heads, window_size=window_size,
                                 shift_size=0 if (i % 2 == 0) else window_size // 2,
                                 mlp_ratio=mlp_ratio,
                                 qkv_bias=qkv_bias, qk_scale=qk_scale,
                                 drop=drop, attn_drop=attn_drop,
                                 drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
                                 norm_layer=norm_layer)
            for i in range(depth)])

        # patch merging layer
        if downsample is not None:
            self.downsample = downsample(input_resolution, dim=dim, norm_layer=norm_layer)
        else:
            self.downsample = None

    def forward(self, x):
        for blk in self.blocks:
            if self.use_checkpoint:
                x = checkpoint.checkpoint(blk, x)
            else:
                x = blk(x)
        if self.downsample is not None:
            x = self.downsample(x)
        return x

    def extra_repr(self) -> str:
        return f"dim={self.dim}, input_resolution={self.input_resolution}, depth={self.depth}"

    def flops(self):
        flops = 0
        for blk in self.blocks:
            flops += blk.flops()
        if self.downsample is not None:
            flops += self.downsample.flops()
        return flops


class BasicLayer_up(nn.Module):
    """ A basic Swin Transformer layer for one stage.

    Args:
        dim (int): Number of input channels.
        input_resolution (tuple[int]): Input resolution.
        depth (int): Number of blocks.
        num_heads (int): Number of attention heads.
        window_size (int): Local window size.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
        drop (float, optional): Dropout rate. Default: 0.0
        attn_drop (float, optional): Attention dropout rate. Default: 0.0
        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
        norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
        upsample (nn.Module | None, optional): upsample layer at the end of the layer. Default: None
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
    """

    def __init__(self, dim, input_resolution, depth, num_heads, window_size,
                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0.,
                 drop_path=0., norm_layer=nn.LayerNorm, upsample=None, use_checkpoint=False):

        super().__init__()
        self.dim = dim
        self.input_resolution = input_resolution
        self.depth = depth
        self.use_checkpoint = use_checkpoint

        # build blocks
        self.blocks = nn.ModuleList([
            SwinTransformerBlock(dim=dim, input_resolution=input_resolution,
                                 num_heads=num_heads, window_size=window_size,
                                 shift_size=0 if (i % 2 == 0) else window_size // 2,
                                 mlp_ratio=mlp_ratio,
                                 qkv_bias=qkv_bias, qk_scale=qk_scale,
                                 drop=drop, attn_drop=attn_drop,
                                 drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
                                 norm_layer=norm_layer)
            for i in range(depth)])

        # patch merging layer
        if upsample is not None:
            self.upsample = PatchExpand(input_resolution, dim=dim, dim_scale=2, norm_layer=norm_layer)
        else:
            self.upsample = None

    def forward(self, x):
        for blk in self.blocks:
            if self.use_checkpoint:
                x = checkpoint.checkpoint(blk, x)
            else:
                x = blk(x)
        if self.upsample is not None:
            x = self.upsample(x)
        return x


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

        self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)
        if norm_layer is not None:
            self.norm = norm_layer(embed_dim)
        else:
            self.norm = None

    def forward(self, x):
        B, C, H, W = x.shape
        # FIXME look at relaxing size constraints
        assert H == self.img_size[0] and W == self.img_size[1], \
            f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
        x = self.proj(x).flatten(2).transpose(1, 2)  # B Ph*Pw C
        if self.norm is not None:
            x = self.norm(x)
        return x

    def flops(self):
        Ho, Wo = self.patches_resolution
        flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1])
        if self.norm is not None:
            flops += Ho * Wo * self.embed_dim
        return flops


class SwinTransformerSys(nn.Module):
    r""" Swin Transformer
        A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows`  -
          https://arxiv.org/pdf/2103.14030

    Args:
        img_size (int | tuple(int)): Input image size. Default 224
        patch_size (int | tuple(int)): Patch size. Default: 4
        in_chans (int): Number of input image channels. Default: 3
        num_classes (int): Number of classes for classification head. Default: 1000
        embed_dim (int): Patch embedding dimension. Default: 96
        depths (tuple(int)): Depth of each Swin Transformer layer.
        num_heads (tuple(int)): Number of attention heads in different layers.
        window_size (int): Window size. Default: 7
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4
        qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
        qk_scale (float): Override default qk scale of head_dim ** -0.5 if set. Default: None
        drop_rate (float): Dropout rate. Default: 0
        attn_drop_rate (float): Attention dropout rate. Default: 0
        drop_path_rate (float): Stochastic depth rate. Default: 0.1
        norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
        ape (bool): If True, add absolute position embedding to the patch embedding. Default: False
        patch_norm (bool): If True, add normalization after patch embedding. Default: True
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False
    """

    def __init__(self, img_size=224, patch_size=4, in_chans=3, num_classes=1000,
                 embed_dim=96, depths=[2, 2, 2, 2], depths_decoder=[1, 2, 2, 2], num_heads=[3, 6, 12, 24],
                 window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None,
                 drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
                 norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
                 use_checkpoint=False, final_upsample="expand_first", **kwargs):
        super().__init__()

        print(
            "SwinTransformerSys expand initial----depths:{};depths_decoder:{};drop_path_rate:{};num_classes:{}".format(
                depths,
                depths_decoder, drop_path_rate, num_classes))

        self.num_classes = num_classes
        self.num_layers = len(depths)
        self.embed_dim = embed_dim
        self.ape = ape
        self.patch_norm = patch_norm
        self.num_features = int(embed_dim * 2 ** (self.num_layers - 1))
        self.num_features_up = int(embed_dim * 2)
        self.mlp_ratio = mlp_ratio
        self.final_upsample = final_upsample

        # split image into non-overlapping patches
        self.patch_embed = PatchEmbed(
            img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim,
            norm_layer=norm_layer if self.patch_norm else None)
        num_patches = self.patch_embed.num_patches
        patches_resolution = self.patch_embed.patches_resolution
        self.patches_resolution = patches_resolution

        # absolute position embedding
        if self.ape:
            self.absolute_pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim))
            trunc_normal_(self.absolute_pos_embed, std=.02)

        self.pos_drop = nn.Dropout(p=drop_rate)

        # stochastic depth
        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rule

        # build encoder and bottleneck layers
        self.layers = nn.ModuleList()
        for i_layer in range(self.num_layers):
            layer = BasicLayer(dim=int(embed_dim * 2 ** i_layer),
                               input_resolution=(patches_resolution[0] // (2 ** i_layer),
                                                 patches_resolution[1] // (2 ** i_layer)),
                               depth=depths[i_layer],
                               num_heads=num_heads[i_layer],
                               window_size=window_size,
                               mlp_ratio=self.mlp_ratio,
                               qkv_bias=qkv_bias, qk_scale=qk_scale,
                               drop=drop_rate, attn_drop=attn_drop_rate,
                               drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
                               norm_layer=norm_layer,
                               downsample=PatchMerging if (i_layer < self.num_layers - 1) else None,
                               use_checkpoint=use_checkpoint)
            self.layers.append(layer)

        # build decoder layers
        self.layers_up = nn.ModuleList()
        self.concat_back_dim = nn.ModuleList()
        for i_layer in range(self.num_layers):
            concat_linear = nn.Linear(2 * int(embed_dim * 2 ** (self.num_layers - 1 - i_layer)),
                                      int(embed_dim * 2 ** (
                                              self.num_layers - 1 - i_layer))) if i_layer > 0 else nn.Identity()
            if i_layer == 0:
                layer_up = PatchExpand(
                    input_resolution=(patches_resolution[0] // (2 ** (self.num_layers - 1 - i_layer)),
                                      patches_resolution[1] // (2 ** (self.num_layers - 1 - i_layer))),
                    dim=int(embed_dim * 2 ** (self.num_layers - 1 - i_layer)), dim_scale=2, norm_layer=norm_layer)
            else:
                layer_up = BasicLayer_up(dim=int(embed_dim * 2 ** (self.num_layers - 1 - i_layer)),
                                         input_resolution=(
                                             patches_resolution[0] // (2 ** (self.num_layers - 1 - i_layer)),
                                             patches_resolution[1] // (2 ** (self.num_layers - 1 - i_layer))),
                                         depth=depths[(self.num_layers - 1 - i_layer)],
                                         num_heads=num_heads[(self.num_layers - 1 - i_layer)],
                                         window_size=window_size,
                                         mlp_ratio=self.mlp_ratio,
                                         qkv_bias=qkv_bias, qk_scale=qk_scale,
                                         drop=drop_rate, attn_drop=attn_drop_rate,
                                         drop_path=dpr[sum(depths[:(self.num_layers - 1 - i_layer)]):sum(
                                             depths[:(self.num_layers - 1 - i_layer) + 1])],
                                         norm_layer=norm_layer,
                                         upsample=PatchExpand if (i_layer < self.num_layers - 1) else None,
                                         use_checkpoint=use_checkpoint)
            self.layers_up.append(layer_up)
            self.concat_back_dim.append(concat_linear)

        self.norm = norm_layer(self.num_features)
        self.norm_up = norm_layer(self.embed_dim)

        if self.final_upsample == "expand_first":
            print("---final upsample expand_first---")
            self.up = FinalPatchExpand_X4(input_resolution=(img_size // patch_size, img_size // patch_size),
                                          dim_scale=4, dim=embed_dim)
            self.output = nn.Conv2d(in_channels=embed_dim, out_channels=self.num_classes, kernel_size=1, bias=False)

        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight, std=.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)

    @torch.jit.ignore
    def no_weight_decay(self):
        return {'absolute_pos_embed'}

    @torch.jit.ignore
    def no_weight_decay_keywords(self):
        return {'relative_position_bias_table'}

    # Encoder and Bottleneck
    def forward_features(self, x):
        x = self.patch_embed(x)
        if self.ape:
            x = x + self.absolute_pos_embed
        x = self.pos_drop(x)
        x_downsample = []

        for layer in self.layers:
            x_downsample.append(x)
            x = layer(x)

        x = self.norm(x)  # B L C

        return x, x_downsample

    # Dencoder and Skip connection
    def forward_up_features(self, x, x_downsample):
        for inx, layer_up in enumerate(self.layers_up):
            if inx == 0:
                x = layer_up(x)
            else:
                x = torch.cat([x, x_downsample[3 - inx]], -1)
                x = self.concat_back_dim[inx](x)
                x = layer_up(x)

        x = self.norm_up(x)  # B L C

        return x

    def up_x4(self, x):
        H, W = self.patches_resolution
        B, L, C = x.shape
        assert L == H * W, "input features has wrong size"

        if self.final_upsample == "expand_first":
            x = self.up(x)
            x = x.view(B, 4 * H, 4 * W, -1)
            x = x.permute(0, 3, 1, 2)  # B,C,H,W
            x = self.output(x)

        return x

    def forward(self, x):
        x, x_downsample = self.forward_features(x)
        x = self.forward_up_features(x, x_downsample)
        x = self.up_x4(x)

        return x

    def flops(self):
        flops = 0
        flops += self.patch_embed.flops()
        for i, layer in enumerate(self.layers):
            flops += layer.flops()
        flops += self.num_features * self.patches_resolution[0] * self.patches_resolution[1] // (2 ** self.num_layers)
        flops += self.num_features * self.num_classes
        return flops


def no_weight_decay():
    return {'absolute_pos_embed'}


def no_weight_decay_keywords():
    return {'relative_position_bias_table'}


def _init_weights(m):
    if isinstance(m, nn.Linear):
        trunc_normal_(m.weight, std=.02)
        if isinstance(m, nn.Linear) and m.bias is not None:
            nn.init.constant_(m.bias, 0)
    elif isinstance(m, nn.LayerNorm):
        nn.init.constant_(m.bias, 0)
        nn.init.constant_(m.weight, 1.0)


# ==================================================添加CoordGate模块的定义
class CoordGate(nn.Module):
    def __init__(self, in_channels, reduction=16):
        super(CoordGate, self).__init__()
        self.h_conv = nn.Conv2d(1, 1, kernel_size=7, stride=1, padding=3)
        self.w_conv = nn.Conv2d(1, 1, kernel_size=7, stride=1, padding=3)
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.mlp = nn.Sequential(
            nn.Linear(in_channels, in_channels // reduction),
            nn.ReLU(inplace=True),
            nn.Linear(in_channels // reduction, in_channels)
        )
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        b, c, h, w = x.size()
        # 生成坐标注意力
        y_coord = torch.linspace(-1, 1, h).view(1, 1, h, 1).expand(b, 1, h, w).to(x.device)
        x_coord = torch.linspace(-1, 1, w).view(1, 1, 1, w).expand(b, 1, h, w).to(x.device)
        y_att = self.h_conv(y_coord)
        x_att = self.w_conv(x_coord)
        coord_att = self.sigmoid(y_att + x_att)
        # 通道注意力
        avg_pool = self.avg_pool(x).view(b, c)
        channel_att = self.sigmoid(self.mlp(avg_pool)).view(b, c, 1, 1)
        # 组合空间和通道注意力
        out = x * coord_att * channel_att
        return out

class Swin_Unet(nn.Module):
    def __init__(self, img_size, patch_size, in_channels, num_classes,
                 embed_dim, depths, num_heads,
                 window_size, mlp_ratio, qkv_bias, qk_scale,
                 drop_rate, attn_drop_rate, drop_path_rate):
        super().__init__()

        self.num_classes = num_classes
        self.num_layers = len(depths)
        self.embed_dim = embed_dim
        self.num_features = int(embed_dim * 2 ** (self.num_layers - 1))
        self.num_features_up = int(embed_dim * 2)
        self.mlp_ratio = mlp_ratio

        # =============================================CoordGate模块
        self.coord_gates = nn.ModuleList([
            CoordGate(int(embed_dim * 2 ** i))
            for i in range(len(depths))
        ])

        # split image into non-overlapping patches
        self.patch_embed = PatchEmbed(
            img_size, patch_size, in_channels, embed_dim,
            norm_layer=nn.LayerNorm)
        patches_resolution = self.patch_embed.patches_resolution
        self.patches_resolution = patches_resolution
        # absolute position embedding，
        self.pos_drop = nn.Dropout(p=drop_rate)
        # stochastic depth
        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]

        # build encoderStages and bottleneck layers，每个BasicLayer包含两个Swin Transformer Block和一个下采样
        self.layers = nn.ModuleList()
        for i_layer in range(self.num_layers):
            layer = BasicLayer(dim=int(embed_dim * 2 ** i_layer),
                               input_resolution=(patches_resolution[0] // (2 ** i_layer),
                                                 patches_resolution[1] // (2 ** i_layer)),
                               depth=depths[i_layer],
                               num_heads=num_heads[i_layer],
                               window_size=window_size,
                               mlp_ratio=self.mlp_ratio,
                               qkv_bias=qkv_bias, qk_scale=qk_scale,
                               drop=drop_rate, attn_drop=attn_drop_rate,
                               drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
                               norm_layer=nn.LayerNorm,
                               downsample=PatchMerging if (i_layer < self.num_layers - 1) else None) # bottleneck没有下采样
            self.layers.append(layer)

        # build decoder layers，解码器每个Stage
        self.layers_up = nn.ModuleList()
        self.concat_back_dim = nn.ModuleList()
        for i_layer in range(self.num_layers):
            concat_linear = nn.Linear(2 * int(embed_dim * 2 ** (self.num_layers - 1 - i_layer)),
                                      int(embed_dim * 2 ** (
                                              self.num_layers - 1 - i_layer))) if i_layer > 0 else nn.Identity()
            if i_layer == 0:
                layer_up = PatchExpand(
                    input_resolution=(patches_resolution[0] // (2 ** (self.num_layers - 1 - i_layer)),
                                      patches_resolution[1] // (2 ** (self.num_layers - 1 - i_layer))),
                    dim=int(embed_dim * 2 ** (self.num_layers - 1 - i_layer)), dim_scale=2, norm_layer=nn.LayerNorm)
            else:
                layer_up = BasicLayer_up(dim=int(embed_dim * 2 ** (self.num_layers - 1 - i_layer)),
                                         input_resolution=(
                                             patches_resolution[0] // (2 ** (self.num_layers - 1 - i_layer)),
                                             patches_resolution[1] // (2 ** (self.num_layers - 1 - i_layer))),
                                         depth=depths[(self.num_layers - 1 - i_layer)],
                                         num_heads=num_heads[(self.num_layers - 1 - i_layer)],
                                         window_size=window_size,
                                         mlp_ratio=self.mlp_ratio,
                                         qkv_bias=qkv_bias, qk_scale=qk_scale,
                                         drop=drop_rate, attn_drop=attn_drop_rate,
                                         drop_path=dpr[sum(depths[:(self.num_layers - 1 - i_layer)]):sum(
                                             depths[:(self.num_layers - 1 - i_layer) + 1])],
                                         norm_layer=nn.LayerNorm,
                                         upsample=PatchExpand if (i_layer < self.num_layers - 1) else None)
            self.layers_up.append(layer_up)
            self.concat_back_dim.append(concat_linear)

        self.norm = nn.LayerNorm(self.num_features)
        self.norm_up = nn.LayerNorm(self.embed_dim)

        self.up = FinalPatchExpand_X4(input_resolution=(img_size // patch_size, img_size // patch_size),
                                      dim_scale=4, dim=embed_dim)
        self.output = nn.Conv2d(in_channels=embed_dim, out_channels=self.num_classes, kernel_size=1, bias=False)

        self.apply(_init_weights)

    # Encoder and Bottleneck
    def forward_features(self, x):
        x = self.patch_embed(x)
        if self.ape:
            x = x + self.absolute_pos_embed
        x = self.pos_drop(x)
        x_down_sample = []

        for layer in self.layers:
            x_down_sample.append(x)
            x = layer(x)

        x = self.norm(x)  # B L C

        return x, x_down_sample

    # Decoder and Skip connection
    def forward_up_features(self, x, x_down_sample):
        for inx, layer_up in enumerate(self.layers_up):
            if inx == 0:
                x = layer_up(x)
            else:
                x = torch.cat([x, x_down_sample[3 - inx]], -1)
                x = self.concat_back_dim[inx](x)
                x = layer_up(x)

        x = self.norm_up(x)  # B L C

        return x

    def up_x4(self, x):
        H, W = self.patches_resolution
        B, L, C = x.shape
        assert L == H * W, "input features has wrong size"

        x = self.up(x)
        x = x.view(B, 4 * H, 4 * W, -1)
        x = x.permute(0, 3, 1, 2)  # B,C,H,W
        x = self.output(x)

        return x

    def forward(self, x):
        x, x_down_sample = self.forward_features(x)
        # =========================================在每个stage后应用CoordGate
        for i, gate in enumerate(self.coord_gates):
            if i < len(x_down_sample):
                # 将特征图从(B, L, C)转换为(B, C, H, W)格式
                h = w = int(math.sqrt(x_down_sample[i].shape[1]))
                feat = x_down_sample[i].transpose(1, 2).view(-1, self.embed_dim * 2 ** i, h, w)
                feat = gate(feat)
                # 转换回原始格式
                x_down_sample[i] = feat.flatten(2).transpose(1, 2)
        x = self.forward_up_features(x, x_down_sample)
        x = self.up_x4(x)
        return x

    def flops(self):
        flops = 0
        flops += self.patch_embed.flops()
        for i, layer in enumerate(self.layers):
            flops += layer.flops()
        flops += self.num_features * self.patches_resolution[0] * self.patches_resolution[1] // (2 ** self.num_layers)
        flops += self.num_features * self.num_classes
        return flops

还要修改nets文件夹下unet.py文件，如下

import math
import torch
import torch.nn as nn
from nets.resnet import resnet50
from nets.vgg import VGG16
from nets.swin_unet import Swin_Unet
from torch.hub import load_state_dict_from_url

def swin_unet(pretrained=False, **kwargs):
    model = Swin_Unet(img_size=224, patch_size=4, in_channels=3, num_classes=7,
            embed_dim=96, depths=[2, 2, 6, 2], num_heads=[3, 6, 12, 24],
            window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None,
            drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1, **kwargs)
    if pretrained:
        state_dict = load_state_dict_from_url("https://github.com/SwinTransformer/storage/releases/download/v1.0.8/swin_tiny_patch4_window7_224_22k.pth", model_dir="./model_data")
        model.load_state_dict(state_dict)
    return model

class unetUp(nn.Module):
    def __init__(self, in_size, out_size):
        super(unetUp, self).__init__()
        self.conv1  = nn.Conv2d(in_size, out_size, kernel_size = 3, padding = 1)
        self.conv2  = nn.Conv2d(out_size, out_size, kernel_size = 3, padding = 1)
        self.up     = nn.UpsamplingBilinear2d(scale_factor = 2)
        self.relu   = nn.ReLU(inplace = True)

    def forward(self, inputs1, inputs2):
        outputs = torch.cat([inputs1, self.up(inputs2)], 1)#[2,384,14,14]
        outputs = self.conv1(outputs)
        outputs = self.relu(outputs)
        outputs = self.conv2(outputs)
        outputs = self.relu(outputs)
        return outputs

class unetUp_1(nn.Module):
    def __init__(self, in_size, out_size):
        super(unetUp_1, self).__init__()
        self.conv1  = nn.Conv2d(in_size, out_size, kernel_size = 3, padding = 1)
        self.conv2  = nn.Conv2d(out_size, out_size, kernel_size = 3, padding = 1)
        self.up     = nn.UpsamplingBilinear2d(scale_factor = 2)
        self.relu   = nn.ReLU(inplace = True)

    def forward(self, inputs1, inputs2):
        outputs = torch.cat([inputs1, inputs2], 1)#[2,384,14,14]
        outputs = self.conv1(outputs)
        outputs = self.relu(outputs)
        outputs = self.conv2(outputs)
        outputs = self.relu(outputs)
        return outputs

class Unet(nn.Module):
    def __init__(self, num_classes = 7, pretrained = False, backbone ='vgg'):
        super(Unet, self).__init__()
        if backbone == 'vgg':
            self.vgg    = VGG16(pretrained = pretrained)
            in_filters  = [192, 384, 768, 1024]
        elif backbone == 'resnet50':
            self.resnet = resnet50(pretrained = pretrained)
            in_filters  = [192, 512, 1024, 3072]
        elif backbone == 'swin':
            self.swin   = swin_unet(pretrained = pretrained)
            in_filters  = [224,448,896,768]
        else:
            raise ValueError('Unsupported backbone - `{}`, Use vgg, resnet50.'.format(backbone))
        out_filters = [64, 128, 256, 512]
        #out_filters = [48,96,192,384]
            # upsampling
            # 64,64,512
        self.up_concat4 = unetUp(in_filters[3], out_filters[3])
            # 128,128,256
        self.up_concat3 = unetUp(in_filters[2], out_filters[2])
            # 256,256,128
        self.up_concat2 = unetUp(in_filters[1], out_filters[1])
            # 512,512,64
        self.up_concat1 = unetUp(in_filters[0], out_filters[0])

        if backbone == 'resnet50':
            self.up_conv = nn.Sequential(
                nn.UpsamplingBilinear2d(scale_factor = 2), 
                nn.Conv2d(out_filters[0], out_filters[0], kernel_size = 3, padding = 1),
                nn.ReLU(),
                nn.Conv2d(out_filters[0], out_filters[0], kernel_size = 3, padding = 1),
                nn.ReLU(),
            )
        else:
            self.up_conv = None
        self.final = nn.Conv2d(out_filters[0], num_classes, 1)
        self.backbone = backbone

    def forward(self, inputs):
        if self.backbone == "vgg":
            [feat1, feat2, feat3, feat4, feat5] = self.vgg.forward(inputs)
            up4 = self.up_concat4(feat4, feat5)
            up3 = self.up_concat3(feat3, up4)
            up2 = self.up_concat2(feat2, up3)
            up1 = self.up_concat1(feat1, up2)
        elif self.backbone == "resnet50":
            [feat1, feat2, feat3, feat4, feat5] = self.resnet.forward(inputs)
            up4 = self.up_concat4(feat4, feat5)
            up3 = self.up_concat3(feat3, up4)
            up2 = self.up_concat2(feat2, up3)
            up1 = self.up_concat1(feat1, up2)
        elif self.backbone == "swin": #===================================
            # 通过Swin Transformer提取特征
            x = self.swin.patch_embed(inputs)  # 修正拼写错误 pathch_embed -> patch_embed
            B, L, C = x.shape
            H = W = int(math.sqrt(L))  # 计算特征图的高度和宽度

            # 将特征转换为4D张量以便于后续处理
            feat = x.view(B, H, W, C).permute(0, 3, 1, 2)  # B,C,H,W

            # 依次通过Swin Transformer的各层
            x1 = self.swin.layers[0](x)
            x2 = self.swin.layers[1](x1)
            x3 = self.swin.layers[2](x2)
            x4 = self.swin.layers[3](x3)

            # 将特征转换为4D张量
            B, L, C = x1.shape
            H1 = W1 = int(math.sqrt(L))
            feat1 = x1.view(B, H1, W1, -1).permute(0, 3, 1, 2)

            B, L, C = x2.shape
            H2 = W2 = int(math.sqrt(L))
            feat2 = x2.view(B, H2, W2, -1).permute(0, 3, 1, 2)

            B, L, C = x3.shape
            H3 = W3 = int(math.sqrt(L))
            feat3 = x3.view(B, H3, W3, -1).permute(0, 3, 1, 2)

            B, L, C = x4.shape
            H4 = W4 = int(math.sqrt(L))
            feat4 = x4.view(B, H4, W4, -1).permute(0, 3, 1, 2)
            self.up_concat4 = unetUp_1(1536, 512)
            up4 = self.up_concat4(feat3, feat4)
            up3 = self.up_concat3(feat2, up4)
            up2 = self.up_concat2(feat1, up3)
            up1 = self.up_concat1(feat, up2)  # 假设feat1是最低层的特征

        if self.up_conv != None:
            up1 = self.up_conv(up1)
        final = self.final(up1)        
        return final

    def freeze_backbone(self):
        if self.backbone == "vgg":
            for param in self.vgg.parameters():
                param.requires_grad = False
        elif self.backbone == "resnet50":
            for param in self.resnet.parameters():
                param.requires_grad = False
        elif self.backbone == "swin":
            for param in self.swin.parameters():
                param.requires_grad = False


    def unfreeze_backbone(self):
        if self.backbone == "vgg":
            for param in self.vgg.parameters():
                param.requires_grad = True
        elif self.backbone == "resnet50":
            for param in self.resnet.parameters():
                param.requires_grad = True 
        elif self.backbone == "swin":
            for param in self.swin.parameters():
                param.requires_grad = True 

3.修改输入图像大小

    model_path  = "E:/unet-pytorch-main/swin_tiny_patch4_window7_224.pth"

    #-----------------------------------------------------#

    #   input_shape     输入图片的大小，32的倍数

    #-----------------------------------------------------#

    input_shape = [224, 224]###swin 224*224

注意，所有的地方都要改

4.train.py下需要修改如下：

        #------------------------------------------------------#
        #   根据预训练权重的Key和模型的Key进行加载
        #------------------------------------------------------#
        # 加快模型训练的效率
        print('Loading weights into state dict...')
        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
        model_dict = model.state_dict()
        pretrained_dict = torch.load(model_path, map_location=device)
        a = {}
        for k, v in pretrained_dict.items():
            try:    
                if np.shape(model_dict[k]) ==  np.shape(v):
                    a[k]=v
            except:
                pass
        model_dict.update(a)
        model.load_state_dict(model_dict)
        print('Finished!')
        #------------------------------------------------------#
        #   显示没有匹配上的Key
        #------------------------------------------------------#

用于替换原先的，解决修改网络参数不匹配的问题

5.nets/unet_training.py文件下所有的Loss类函数的mode参数改为mode="bicubic"，避免报linear参数不接受4D张量的错误

6.点击train.py训练即可。