Swin Transformer解读

引言:

        Transformer 模型在自然语言处理(NLP)领域已然成为一个新范式,如今越来越多的研究在尝试将 Transformer 模型强大的建模能力应用到计算机视觉(CV)领域。那么未来,Transformer会不会代替CNN在CV领域的作用。

        而swin transformer是一种包含了CNN滑窗理念的一种transformer。将注意力限制在一个窗口中,一方面能引入CNN卷积操作的局部性,另一方面能节省计算量。

整体架构

        我们先看下swin transformer的整体架构:

Swin Transformer解读_第1张图片

        整个模型采取层次化的设计,一共包含4个Stage,每个stage都会缩小输入特征图的分辨率,像CNN一样逐层扩大感受野。

  1. 通过Patch Partition和Linear Emdedding将将图片切成一个个图块,并嵌入到Embedding。

  2. 每个Stage中包含Patch Merging和多个Swin Transformer Block。

  3. 其中Swin Transformer Block主要由LayerNorm,MLP,Window Attention和Shifted Window Attention等组成。

        接下来我将详细的介绍每一个模块。

Patch Partition 和 Linear Emdedding

        在输入到Block前,我们需要将图片切成一个个patch,然后再嵌入向量。具体做法是对原始图片裁成一个个patch_size*patch_size的窗口大小,然后进行嵌入。

'''
通过patch partition将输入图片HxWx3划分为不重合的patch集合,
其中每个patch尺寸为4x4,那么每个patch的特征维度为4x4x3=48,patch块的数量为H/4 x W/4;
Linear Embedding 将输入的hw展开并且移动到第一维度
'''
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)  # -> (img_size, img_size),(224,224)
        patch_size = to_2tuple(patch_size)  # -> (patch_size, patch_size),(4,4)
        patches_resolution = [img_size[0] // patch_size[0], img_size[1] // patch_size[1]]  #每一个方向有多少patch[56,56]
        self.img_size = img_size
        self.patch_size = patch_size
        self.patches_resolution = patches_resolution
        self.num_patches = patches_resolution[0] * patches_resolution[1]  #一共有多少patch,56*56


        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):
        # 假设采取默认参数
        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   //出来的是(B, 96, 224/4, 224/4) 把HW维展开,(B, 96, 56*56)  # 把通道维放到最后 (B, 56*56, 96)
        if self.norm is not None:
            x = self.norm(x)
        return x

Patch Merging

        该模块的作用是在每个Stage开始前做降采样,用于缩小分辨率,调整通道数 进而形成层次化的设计,同时也能节省一定运算量。(在stage1,stage2,stage3的前面使用。stage0使用了Patch Partition 和 Linear Emdedding)。

        每次降采样是两倍,因此在行方向和列方向上,间隔2选取元素。然后拼接在一起作为一整个张量,最后展开。此时通道数是原先的4倍,但通过全连接层调整,使得通道数变为原来的2倍。

#该模块的作用是在每个Stage开始前做降采样,用于缩小分辨率,调整通道数 进而形成层次化的设计,同时也能节省一定运算量。
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                                                #56,56
        B, L, C = x.shape                                                           #B,56*56,96
        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)                                                      #B,56,56,96


        x0 = x[:, 0::2, 0::2, :]  # B H/2 W/2 C  取了2*2范围内的左上角数组成一个新矩阵    #B,28,28,96
        x1 = x[:, 1::2, 0::2, :]  # B H/2 W/2 C  取了2*2范围内的左下角数组成一个新矩阵    #B,28,28,96
        x2 = x[:, 0::2, 1::2, :]  # B H/2 W/2 C  取了2*2范围内的右上角数组成一个新矩阵    #B,28,28,96
        x3 = x[:, 1::2, 1::2, :]  # B H/2 W/2 C  取了2*2范围内的右下角数组成一个新矩阵    #B,28,28,96
        x = torch.cat([x0, x1, x2, x3], -1)  # B H/2 W/2 4*C  矩阵在c维度叠加         #B,28,28,96*4
        x = x.view(B, -1, 4 * C)  # B H/2*W/2 4*C  将H,W维度展平                      #B,28*28,96*4


        x = self.norm(x)
        x = self.reduction(x)  #将4C通过Linear变成2C                                  #B,28*28,96*2


        return x

        下面是一个简单的示意图:

Swin Transformer解读_第2张图片

Window Partition

        Window Partition函数是用于对张量划分窗口,指定窗口大小。将原本的[B,H,W,C],划分为[num_windows*B,window_size,window_size,C],其中num_windows=(H/window_size)*(W/window_size),即H,W大小图像可以划分出多少个window_size窗口。

def window_partition(x, window_size):#将图像划分成固定窗口
    """
    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

        简单示意图H,W=6,window_size=3:

Swin Transformer解读_第3张图片

Window Reverse

        Window Reverse则是Window Partition的逆过程。这两个都将在Swin Transformer Block使用。

def window_reverse(windows, window_size, H, W):#将展开的窗口重新组装成图像
    """
    Args:
        windows: (num_windows*B, window_size, window_size, C)    [64B,7,7,96]
        window_size (int): Window size                            7
        H (int): Height of image                                  56
        W (int): Width of image                                   56


    Returns:
        x: (B, H, W, C)
    """
    B = int(windows.shape[0] / (H * W / window_size / window_size))  #num_windows = (H//window_size)*(W//window_size)  B = windows.shape[0]/num_windows
    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

        简单示意图:

Swin Transformer解读_第4张图片

W-MSA

        这是该文章的关键,之前使用的Transformer都是基于全局来计算注意力机制的。因此计算复杂度十分高。而Swin Transformer则将注意力的计算限制在每个窗口内,不仅减少了计算量。而且更加符合图像信息的性质。因为图像的该点像素也几乎只与附近的领域像素有关,并且此处还用到了相对位置编码。

        先讲一下相对位置编码:

# 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))  # 设置一个形状为(2*(Wh-1) * 2*(Ww-1), nH)的可学习变量,用于后续的位置编码


# 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      #为了让数值都为正
relative_coords[:, :, 1] += self.window_size[1] - 1                               #为了让数值都为正
relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1                           #在x方向再*(2*window_size-1)是为了后续求和后能够区分(1,2)和(2,1)这类坐标
relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
self.register_buffer("relative_position_index", relative_position_index)  #反向传播不需要被optimizer更新的参数

        简单示意图:

Swin Transformer解读_第5张图片

        然后在w和h方向计算relative_coords。计算relative_coords第一步加(window_size-1)是为了让值都为正数,在w方向再*(2*window_size-1)是为了后续求和能区分(0,1)和(1,0)这类坐标。

Swin Transformer解读_第6张图片

        接着我们附上windowsAtention代码,其中mak是为后面的shift windowsAttention准备的,此处可以忽略。

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    #其实是指q,k的维度
        self.scale = qk_scale or head_dim ** -0.5  #对应Attention公式里面的分母


        # 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))  # 设置一个形状为(2*(Wh-1) * 2*(Ww-1), nH)的可学习变量,用于后续的位置编码


        # 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      #为了让数值都为正
        relative_coords[:, :, 1] += self.window_size[1] - 1                               #为了让数值都为正
        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1                           #在x方向再*(2*window_size-1)是为了后续求和后能够区分(1,2)和(2,1)这类坐标
        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
        self.register_buffer("relative_position_index", relative_position_index)  #反向传播不需要被optimizer更新的参数


        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):  #mask只有在shift的时候才会用到
        """
        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
        # [num_windows*B, Wh*Ww, C]--[num_windows*B, Wh*Ww, 3C]--[num_windows*B, Wh*Ww,3, num_heads, C // num_heads]--[3,num_windows*B,num_heads,Wh*Ww,C // num_heads]
        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 = [num_windows*B,num_heads,Wh*Ww,C // num_heads][64B,3,49,32]


        q = q * self.scale
        attn = (q @ k.transpose(-2, -1))  #[num_windows*B,num_heads,N,N][64B,3,49,49]


        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)  #[num_windows*B,num_heads,N,N]


        if mask is not None:
            nW = mask.shape[0]    #[64,49,49]
            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)  #[B,num_windows,num_heads,N,N]+[1,num_windows,1,N,N] = [B,num_windows,num_heads,N,N]
            attn = attn.view(-1, self.num_heads, N, N)  #[num_windows*B,num_heads,N,N]  这样就在对应的mask不应该计算的位置全部加了-100
            attn = self.softmax(attn)  #经过softmax之后就会被相应的忽略掉  [64B,3,49,49]
        else:
            attn = self.softmax(attn)


        attn = self.attn_drop(attn)


        x = (attn @ v).transpose(1, 2).reshape(B_, N, C)   #[num_windows*B,num_heads,N,C // num_heads]--[num_windows*B,N,num_heads,C // num_heads]--[num_windows*B,N,C][64B,49,96]
        x = self.proj(x)
        x = self.proj_drop(x)   #[num_windows*B,N,C]
        return x

1.首先输入特征为[num_windows*B,window_size*window_size,C]

2.然后经过self.qkv将维度增加3倍,进行reshape,调整轴顺序,最终分配给q,k,v。(变化过程[num_windows*B, Wh*Ww, C]--[num_windows*B, Wh*Ww, 3C]--[num_windows*B, Wh*Ww,3, num_heads, C // num_heads]--[3,num_windows*B,num_heads,Wh*Ww,C // num_heads])。

3.根据公式,我们对q乘以一个scale系数,然后与k进行相乘。得到[num_windows*B,num_heads,window_size*window_size,window_size*window_size]的张量。再将相对位置编码加到attn上。

4.接着与普通的transformer一样的softmax,dropout,与v相乘,再经过一层全连接层和dropout。

SW-MSA

        前面的Window Attention是在每个窗口下计算注意力的,为了更好的和其他window进行信息交互,Swin Transformer还引入了shifted window操作。

Swin Transformer解读_第7张图片

        左边是没有重叠的Window Attention,而右边则是将窗口进行移位的Shift Window Attention。可以看到移位后的窗口包含了原本相邻窗口的元素。

        在实际代码里,我们是通过对特征图移位,并给Attention设置mask来间接实现的。能在保持原有的window个数下,最后的计算结果等价。

Swin Transformer解读_第8张图片

特征图移位:

        代码中特征移位是通过torch.roll来实现的

# cyclic shift
        if self.shift_size > 0:
            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))  #roll操作#B,56,56,96
        else:
            shifted_x = x                 #B,56,56,96

        简单示意图如下所示:

Swin Transformer解读_第9张图片

Attention Mask

        通过设置合理的mask,让注意力机制任然只计算原图中领域。

        由于窗口重新划分,但是为了不考虑滑动过去的,不是领域的数据对结果产生影响,因此出现了mask。从而不计算那些不相关的数据。

if self.shift_size > 0:
    # calculate attention mask for SW-MSA
    H, W = self.input_resolution                       #第一次56,56
    img_mask = torch.zeros((1, H, W, 1))  # 1 H W 1    [1,56,56,1]
    h_slices = (slice(0, -self.window_size),
                slice(-self.window_size, -self.shift_size),
                slice(-self.shift_size, None))         #([0:-7],[-7:-3],[-3:0])
    w_slices = (slice(0, -self.window_size),
                slice(-self.window_size, -self.shift_size),
                slice(-self.shift_size, None))         #([0:-7],[-7:-3],[-3:0])
    cnt = 0
    for h in h_slices:
        for w in w_slices:
            img_mask[:, h, w, :] = cnt
            cnt += 1                                   #将区域一块块的分好[1,56,56,1]


    mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1   [64,7,7,1]
    mask_windows = mask_windows.view(-1, self.window_size * self.window_size)  # nW, window_size*window_size   [64,49]
    attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)  #nW ,window_size*window_size,window_size*window_size  这个操作mask一样的就会变成0,mask不同的就会不等于0,mask_windows.unsqueeze(1)等价于q矩阵mask,mask_windows.unsqueeze(2)等价于k矩阵mask
    attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))  #nW ,window_size*window_size,window_size*window_size  [64,49,49]
else:
    attn_mask = None

        简单示意图:

Swin Transformer解读_第10张图片

Swin Transformer解读_第11张图片

Swin Transformer解读_第12张图片

Swin Transformer解读_第13张图片

        实质上就是对应颜色的q与k要相乘,不是同一个颜色的q,k就变成了了0。因为要保证是领域的才有用,不是领域的就没什么用。

Transformer Block整体架构

Swin Transformer解读_第14张图片

        两个连续的Block架构如上图所示,需要注意的是一个Stage包含的Block个数必须是偶数,因为需要交替包含一个含有Window Attention的Layer和含有Shifted Window Attention的Layer。

Block前向代码:

def forward(self, x):
    H, W = self.input_resolution       #假设第一次block,H,W =56,56
    B, L, C = x.shape                  #B,56*56,96
    assert L == H * W, "input feature has wrong size"


    shortcut = x                      #B,56*56,96
    x = self.norm1(x)                 #B,56*56,96
    x = x.view(B, H, W, C)            #B,56,56,96


    # cyclic shift
    if self.shift_size > 0:
        shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))  #roll操作#B,56,56,96
    else:
        shifted_x = x                 #B,56,56,96


    # partition windows
    x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C[B*64,7,7,96]
    x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C    [B*64,49,96]


    # 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)  #[nW*B, window_size,window_size, C]
    shifted_x = window_reverse(attn_windows, self.window_size, H, W)  # B H' W' C   变回[B,56,56,96]


    # reverse cyclic shift
    if self.shift_size > 0:
        x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))  #将数据反向roll回去
    else:
        x = shifted_x
    x = x.view(B, H * W, C)      #[B,56*56,96]


    # FFN
    x = shortcut + self.drop_path(x)    #[B,56*56,96]
    x = x + self.drop_path(self.mlp(self.norm2(x)))  #[B,56*56,96]


    return x

        整体的流程如下:

1.先对特征图进行LayerNorm

2.通过self.shift_size决定是否需要对特征图进行shift

3.然后将特征图切成一个个窗口

4.计算Attention,通过self.attn_mask来区分Window Attention还是Shift Window Attention

5.将各个窗口合并回来

6.如果之前有做shift操作,此时进行reverse shift,把之前的shift操作恢复

7.做dropout和残差连接

8.再通过一层LayerNorm+全连接层,以及dropout和残差连接

总结

        这篇文章引入window这一个概念,将CNN的局部性引入还减少了计算量。在Shift Window Attention部分,扩大了感受野,在实现部分用mask也十分的巧妙。

你可能感兴趣的:(python,计算机视觉,人工智能,卷积,深度学习)