yolov26改进 | 融合改进篇 | 基于SwinTransformer与轻量化特征增强模块DAMO-YOLO的融合算法（全网独家首发）

import torch
import torch.nn as nn
import numpy as np


class swish(nn.Module):
    def forward(self, x):
        return x * torch.sigmoid(x)

def autopad(k, p=None, d=1):  # kernel, padding, dilation
    """Pad to 'same' shape outputs."""
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p

class Conv(nn.Module):
    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
    default_act = swish()  # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))

class RepConv(nn.Module):
    default_act = swish()  # default activation

    def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
        """Initializes Light Convolution layer with inputs, outputs & optional activation function."""
        super().__init__()
        assert k == 3 and p == 1
        self.g = g
        self.c1 = c1
        self.c2 = c2
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

        self.bn = nn.BatchNorm2d(num_features=c1) if bn and c2 == c1 and s == 1 else None
        self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False)
        self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)

    def forward_fuse(self, x):
        """Forward process."""
        return self.act(self.conv(x))

    def forward(self, x):
        """Forward process."""
        id_out = 0 if self.bn is None else self.bn(x)
        return self.act(self.conv1(x) + self.conv2(x) + id_out)

    def get_equivalent_kernel_bias(self):
        """Returns equivalent kernel and bias by adding 3x3 kernel, 1x1 kernel and identity kernel with their biases."""
        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
        kernelid, biasid = self._fuse_bn_tensor(self.bn)
        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid

    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
        """Pads a 1x1 tensor to a 3x3 tensor."""
        if kernel1x1 is None:
            return 0
        else:
            return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])

    def _fuse_bn_tensor(self, branch):
        """Generates appropriate kernels and biases for convolution by fusing branches of the neural network."""
        if branch is None:
            return 0, 0
        if isinstance(branch, Conv):
            kernel = branch.conv.weight
            running_mean = branch.bn.running_mean
            running_var = branch.bn.running_var
            gamma = branch.bn.weight
            beta = branch.bn.bias
            eps = branch.bn.eps
        elif isinstance(branch, nn.BatchNorm2d):
            if not hasattr(self, 'id_tensor'):
                input_dim = self.c1 // self.g
                kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32)
                for i in range(self.c1):
                    kernel_value[i, i % input_dim, 1, 1] = 1
                self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
            kernel = self.id_tensor
            running_mean = branch.running_mean
            running_var = branch.running_var
            gamma = branch.weight
            beta = branch.bias
            eps = branch.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta - running_mean * gamma / std

    def fuse_convs(self):
        """Combines two convolution layers into a single layer and removes unused attributes from the class."""
        if hasattr(self, 'conv'):
            return
        kernel, bias = self.get_equivalent_kernel_bias()
        self.conv = nn.Conv2d(in_channels=self.conv1.conv.in_channels,
                              out_channels=self.conv1.conv.out_channels,
                              kernel_size=self.conv1.conv.kernel_size,
                              stride=self.conv1.conv.stride,
                              padding=self.conv1.conv.padding,
                              dilation=self.conv1.conv.dilation,
                              groups=self.conv1.conv.groups,
                              bias=True).requires_grad_(False)
        self.conv.weight.data = kernel
        self.conv.bias.data = bias
        for para in self.parameters():
            para.detach_()
        self.__delattr__('conv1')
        self.__delattr__('conv2')
        if hasattr(self, 'nm'):
            self.__delattr__('nm')
        if hasattr(self, 'bn'):
            self.__delattr__('bn')
        if hasattr(self, 'id_tensor'):
            self.__delattr__('id_tensor')

class BasicBlock_3x3_Reverse(nn.Module):
    def __init__(self,
                 ch_in,
                 ch_hidden_ratio,
                 ch_out,
                 shortcut=True):
        super(BasicBlock_3x3_Reverse, self).__init__()
        assert ch_in == ch_out
        ch_hidden = int(ch_in * ch_hidden_ratio)
        self.conv1 = Conv(ch_hidden, ch_out, 3, s=1)
        self.conv2 = RepConv(ch_in, ch_hidden, 3, s=1)
        self.shortcut = shortcut

    def forward(self, x):
        y = self.conv2(x)
        y = self.conv1(y)
        if self.shortcut:
            return x + y
        else:
            return y

class SPP(nn.Module):
    def __init__(
        self,
        ch_in,
        ch_out,
        k,
        pool_size
    ):
        super(SPP, self).__init__()
        self.pool = []
        for i, size in enumerate(pool_size):
            pool = nn.MaxPool2d(kernel_size=size,
                                stride=1,
                                padding=size // 2,
                                ceil_mode=False)
            self.add_module('pool{}'.format(i), pool)
            self.pool.append(pool)
        self.conv = Conv(ch_in, ch_out, k)

    def forward(self, x):
        outs = [x]

        for pool in self.pool:
            outs.append(pool(x))
        y = torch.cat(outs, axis=1)

        y = self.conv(y)
        return y

class CSPStage(nn.Module):
    def __init__(self,
                 ch_in,
                 ch_out,
                 n,
                 block_fn='BasicBlock_3x3_Reverse',
                 ch_hidden_ratio=1.0,
                 act='silu',
                 spp=False):
        super(CSPStage, self).__init__()

        split_ratio = 2
        ch_first = int(ch_out // split_ratio)
        ch_mid = int(ch_out - ch_first)
        self.conv1 = Conv(ch_in, ch_first, 1)
        self.conv2 = Conv(ch_in, ch_mid, 1)
        self.convs = nn.Sequential()

        next_ch_in = ch_mid
        for i in range(n):
            if block_fn == 'BasicBlock_3x3_Reverse':
                self.convs.add_module(
                    str(i),
                    BasicBlock_3x3_Reverse(next_ch_in,
                                           ch_hidden_ratio,
                                           ch_mid,
                                           shortcut=True))
            else:
                raise NotImplementedError
            if i == (n - 1) // 2 and spp:
                self.convs.add_module('spp', SPP(ch_mid * 4, ch_mid, 1, [5, 9, 13]))
            next_ch_in = ch_mid
        self.conv3 = Conv(ch_mid * n + ch_first, ch_out, 1)

    def forward(self, x):
        y1 = self.conv1(x)
        y2 = self.conv2(x)

        mid_out = [y1]
        for conv in self.convs:
            y2 = conv(y2)
            mid_out.append(y2)
        y = torch.cat(mid_out, axis=1)
        y = self.conv3(y)
        return y

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
import numpy as np
from timm.models.layers import DropPath, to_2tuple, trunc_normal_

__all__ = ['SwinTransformer']

class Mlp(nn.Module):
    """ Multilayer perceptron."""

    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):
    """ 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):
        """ Forward function.

        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


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

    Args:
        dim (int): Number of input channels.
        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, 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.num_heads = num_heads
        self.window_size = window_size
        self.shift_size = shift_size
        self.mlp_ratio = mlp_ratio
        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)

        self.H = None
        self.W = None

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

        Args:
            x: Input feature, tensor size (B, H*W, C).
            H, W: Spatial resolution of the input feature.
            mask_matrix: Attention mask for cyclic shift.
        """
        B, L, C = x.shape
        H, W = self.H, self.W
        assert L == H * W, "input feature has wrong size"

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

        # pad feature maps to multiples of window size
        pad_l = pad_t = 0
        pad_r = (self.window_size - W % self.window_size) % self.window_size
        pad_b = (self.window_size - H % self.window_size) % self.window_size
        x = F.pad(x, (0, 0, pad_l, pad_r, pad_t, pad_b))
        _, Hp, Wp, _ = x.shape

        # cyclic shift
        if self.shift_size > 0:
            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
            attn_mask = mask_matrix.type(x.dtype)
        else:
            shifted_x = x
            attn_mask = None

        # 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=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, Hp, Wp)  # 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

        if pad_r > 0 or pad_b > 0:
            x = x[:, :H, :W, :].contiguous()

        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


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

    Args:
        dim (int): Number of input channels.
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
    """
    def __init__(self, dim, norm_layer=nn.LayerNorm):
        super().__init__()
        self.dim = dim
        self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
        self.norm = norm_layer(4 * dim)

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

        Args:
            x: Input feature, tensor size (B, H*W, C).
            H, W: Spatial resolution of the input feature.
        """
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"

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

        # padding
        pad_input = (H % 2 == 1) or (W % 2 == 1)
        if pad_input:
            x = F.pad(x, (0, 0, 0, W % 2, 0, H % 2))

        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


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

    Args:
        dim (int): Number of feature channels
        depth (int): Depths of this stage.
        num_heads (int): Number of attention head.
        window_size (int): Local window size. Default: 7.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4.
        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,
                 depth,
                 num_heads,
                 window_size=7,
                 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.window_size = window_size
        self.shift_size = window_size // 2
        self.depth = depth
        self.use_checkpoint = use_checkpoint

        # build blocks
        self.blocks = nn.ModuleList([
            SwinTransformerBlock(
                dim=dim,
                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(dim=dim, norm_layer=norm_layer)
        else:
            self.downsample = None

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

        Args:
            x: Input feature, tensor size (B, H*W, C).
            H, W: Spatial resolution of the input feature.
        """

        # calculate attention mask for SW-MSA
        Hp = int(np.ceil(H / self.window_size)) * self.window_size
        Wp = int(np.ceil(W / self.window_size)) * self.window_size
        img_mask = torch.zeros((1, Hp, Wp, 1), device=x.device)  # 1 Hp Wp 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))

        for blk in self.blocks:
            blk.H, blk.W = H, W
            if self.use_checkpoint:
                x = checkpoint.checkpoint(blk, x, attn_mask)
            else:
                x = blk(x, attn_mask)
        if self.downsample is not None:
            x_down = self.downsample(x, H, W)
            Wh, Ww = (H + 1) // 2, (W + 1) // 2
            return x, H, W, x_down, Wh, Ww
        else:
            return x, H, W, x, H, W


class PatchEmbed(nn.Module):
    """ Image to Patch Embedding

    Args:
        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, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None):
        super().__init__()
        patch_size = to_2tuple(patch_size)
        self.patch_size = patch_size

        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):
        """Forward function."""
        # padding
        _, _, H, W = x.size()
        if W % self.patch_size[1] != 0:
            x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1]))
        if H % self.patch_size[0] != 0:
            x = F.pad(x, (0, 0, 0, self.patch_size[0] - H % self.patch_size[0]))

        x = self.proj(x)  # B C Wh Ww
        if self.norm is not None:
            Wh, Ww = x.size(2), x.size(3)
            x = x.flatten(2).transpose(1, 2)
            x = self.norm(x)
            x = x.transpose(1, 2).view(-1, self.embed_dim, Wh, Ww)

        return x

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

    Args:
        pretrain_img_size (int): Input image size for training the pretrained model,
            used in absolute postion embedding. Default 224.
        patch_size (int | tuple(int)): Patch size. Default: 4.
        in_chans (int): Number of input image channels. Default: 3.
        embed_dim (int): Number of linear projection output channels. Default: 96.
        depths (tuple[int]): Depths of each Swin Transformer stage.
        num_heads (tuple[int]): Number of attention head of each stage.
        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.
        drop_rate (float): Dropout rate.
        attn_drop_rate (float): Attention dropout rate. Default: 0.
        drop_path_rate (float): Stochastic depth rate. Default: 0.2.
        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.
        out_indices (Sequence[int]): Output from which stages.
        frozen_stages (int): Stages to be frozen (stop grad and set eval mode).
            -1 means not freezing any parameters.
        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
    """

    def __init__(self,
                 factor=0.5,
                 depth_factor=0.5,
                 pretrain_img_size=224,
                 patch_size=4,
                 in_chans=3,
                 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=0.2,
                 norm_layer=nn.LayerNorm,
                 ape=False,
                 patch_norm=True,
                 out_indices=(0, 1, 2, 3),
                 frozen_stages=-1,
                 use_checkpoint=False):
        super().__init__()
        embed_dim = int(embed_dim * factor)
        depths = [max(1, int(dim * depth_factor)) for dim in depths]
        self.pretrain_img_size = pretrain_img_size
        self.num_layers = len(depths)
        self.embed_dim = embed_dim
        self.ape = ape
        self.patch_norm = patch_norm
        self.out_indices = out_indices
        self.frozen_stages = frozen_stages

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

        # absolute position embedding
        if self.ape:
            pretrain_img_size = to_2tuple(pretrain_img_size)
            patch_size = to_2tuple(patch_size)
            patches_resolution = [pretrain_img_size[0] // patch_size[0], pretrain_img_size[1] // patch_size[1]]

            self.absolute_pos_embed = nn.Parameter(torch.zeros(1, embed_dim, patches_resolution[0], patches_resolution[1]))
            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 layers
        self.layers = nn.ModuleList()
        for i_layer in range(self.num_layers):
            layer = BasicLayer(
                dim=int(embed_dim * 2 ** i_layer),
                depth=depths[i_layer],
                num_heads=num_heads[i_layer],
                window_size=window_size,
                mlp_ratio=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)

        num_features = [int(embed_dim * 2 ** i) for i in range(self.num_layers)]
        self.num_features = num_features

        # add a norm layer for each output
        for i_layer in out_indices:
            layer = norm_layer(num_features[i_layer])
            layer_name = f'norm{i_layer}'
            self.add_module(layer_name, layer)
        self.width_list = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]

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

        Wh, Ww = x.size(2), x.size(3)
        if self.ape:
            # interpolate the position embedding to the corresponding size
            absolute_pos_embed = F.interpolate(self.absolute_pos_embed, size=(Wh, Ww), mode='bicubic')
            x = (x + absolute_pos_embed).flatten(2).transpose(1, 2)  # B Wh*Ww C
        else:
            x = x.flatten(2).transpose(1, 2)
        x = self.pos_drop(x)

        outs = []
        for i in range(self.num_layers):
            layer = self.layers[i]
            x_out, H, W, x, Wh, Ww = layer(x, Wh, Ww)

            if i in self.out_indices:
                norm_layer = getattr(self, f'norm{i}')
                x_out = norm_layer(x_out)

                out = x_out.view(-1, H, W, self.num_features[i]).permute(0, 3, 1, 2).contiguous()
                outs.append(out)

        return outs

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs
  m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs
  l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs
  x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs

# YOLO26n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, SwinTransformer, [0.25,0.5]] # 0-4 P1/2 这里是四层大家不要被yaml文件限制住了思维，不会画图进群看视频.
  # 上面的参数0.75支持大家自由根据v26的 0.25 0.50 0.75 1.00 1.5 进行放缩我只尝试过这几个如果你设置一些比较特殊的数字可能会报错.
  # 所以本文有至少 5 x 5 = 25种组合方式.
  - [-1, 1, SPPF, [1024, 5]] # 5
  - [-1, 2, C2PSA, [1024]] # 6

# YOLO26n head
head:
  - [-1, 1, Conv, [512, 1, 1]] # 7
  - [3, 1, Conv, [512, 3, 2]]
  - [[-1, -2], 1, Concat, [1]]
  - [-1, 2, C3k2, [512, True]] # 10

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']] #11
  - [2, 1, Conv, [256, 3, 2]] # 12
  - [[-2, -1, 3], 1, Concat, [1]]
  - [-1, 2, C3k2, [512, True]] # 14

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 2], 1, Concat, [1]]
  - [-1, 2, C3k2, [256, True]] # 17

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 14], 1, Concat, [1]]
  - [-1, 2, C3k2, [512, True]] # 20

  - [14, 1, Conv, [256, 3, 2]] # 21
  - [20, 1, Conv, [256, 3, 2]] # 22
  - [[10, 21, -1], 1, Concat, [1]]
  - [-1, 2, C3k2, [1024, True, 0.5, True]] # 24

  - [[17, 20, 24], 1, Detect, [nc]]  # Detect(P3, P4, P5)