【代码】swin-transformer: Swin Transformer VS Vision Transformer

程序猿的探索之路

已于 2024-08-02 10:54:21 修改

阅读量305

点赞数 3

文章标签： transformer 深度学习人工智能

于 2024-07-13 22:51:13 首次发布

本文链接：https://blog.youkuaiyun.com/nyist_yangguang/article/details/140408229

版权

注1：

self.cls_token.expand(x.shape[0], -1, -1)

-1 表示在对应的维度上不改变大小。

self.cls_token 是一个形状为 (1, 1, embed_dim) 的张量，其中：
第一个维度大小为 1，表示单个 batch。
第二个维度大小为 1，表示单个 token。
第三个维度大小为 embed_dim，表示 token 的嵌入维度。
x.shape[0]:

x.shape[0] 表示输入张量 x 的第一个维度大小，即批量大小（batch size）。
expand 方法:

self.cls_token.expand(x.shape[0], -1, -1) 使用 expand 方法将 self.cls_token 的形状从 (1, 1, embed_dim) 扩展到 (batch_size, 1, embed_dim)，其中 batch_size 是输入张量 x 的批量大小。

注2：

预备知识：

Vision Transformer (ViT)

位置编码：

架构基础：ViT是由Google提出的一种基于Transformer的图像分类模型。它直接将图像划分为一系列不重叠的patches，并将这些patches视为序列数据输入Transformer模型。每个patch都会被映射到一个固定长度的向量，这些向量再通过位置编码后输入到Transformer中进行处理。

模型组成：

Patch Embedding：将输入图像划分为固定大小的patch，并通过线性投影将其映射到高维空间。
位置编码：由于Transformer模型无法处理位置信息，因此需要为每个patch添加位置编码。
Transformer编码器：使用标准的Transformer编码器，对输入的patch序列进行处理，提取特征。
应用场景：主要用于图像分类任务。ViT的设计使其能够处理大规模图像数据集，尤其在使用大型预训练模型时性能表现出色。

Swin Transformer (Swin-ViT)

架构基础：Swin Transformer是一种层次化的视觉Transformer模型，使用移动窗口（Shifted Windows）机制来处理图像数据。其设计目的是通过局部窗口的自注意力机制，捕捉图像中的局部和全局信息。

模型组成：

Patch Embedding：与ViT类似，Swin Transformer也将图像划分为patches，并通过线性投影进行高维映射。
移动窗口注意力：在每个层次上，Swin Transformer将图像划分为固定大小的窗口，并在这些窗口内进行自注意力计算。与ViT不同的是，Swin Transformer会在不同的层次上移动这些窗口，以捕捉跨窗口的依赖关系。
层次化设计：Swin Transformer通过多层的方式，从较小的patch到较大的区域逐步提取特征。
应用场景：除了图像分类外，Swin Transformer在目标检测、图像分割等任务中也表现出色。其层次化的设计使其在处理高分辨率图像时具有优势。

总结
结构设计：
ViT：直接将图像划分为patches，并通过标准的Transformer进行处理。
Swin-ViT：采用层次化设计，通过移动窗口的自注意力机制，逐步从局部到全局提取特征。
应用范围：
ViT：主要用于图像分类任务，在大规模预训练模型上表现优越。
Swin-ViT：除了图像分类，还在目标检测和图像分割等任务中表现出色，适用于处理高分辨率图像。

另外：

Swin Transformer使用了类似卷积神经网络中的层次化构建方法（Hierarchical feature maps），比如特征图尺寸中有对图像下采样4倍的，8倍的以及16倍的，这样的backbone有助于在此基础上构建目标检测，实例分割等任务。而在之前的Vision Transformer中是一开始就直接下采样16倍，后面的特征图也是维持这个下采样率不变。

在Swin Transformer中使用了Windows Multi-Head Self-Attention(W-MSA)的概念，比如在下图的4倍下采样和8倍下采样中，将特征图划分成了多个不相交的区域（Window），并且Multi-Head Self-Attention只在每个窗口（Window）内进行。相对于Vision Transformer中直接对整个（Global）特征图进行Multi-Head Self-Attention，这样做的目的是能够减少计算量的，尤其是在浅层特征图很大的时候。这样做虽然减少了计算量但也会隔绝不同窗口之间的信息传递，所以在论文中作者又提出了 Shifted Windows Multi-Head Self-Attention(SW-MSA)的概念，通过此方法能够让信息在相邻的窗口中进行传递。

ViT:

"""
original code from rwightman:
https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py
"""
from functools import partial
from collections import OrderedDict

import torch
import torch.nn as nn


def drop_path(x, drop_prob: float = 0., training: bool = False):
    """
    Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
    'survival rate' as the argument.
    """
    if drop_prob == 0. or not training: # if there is no throwing or no training
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)  # torch.rand()  [0,1)
    random_tensor.floor_()  # binarize                 # random_tensor.floor_() 会将每个浮点数向下取整
    output = x.div(keep_prob) * random_tensor
    return output

        # x = torch.tensor([[1.0, 2.0],
        #                   [3.0, 4.0],
        #                   [5.0, 6.0],
        #                   [7.0, 8.0]])
        # keep_prob = 1 - drop_prob
        # keep_prob = 1 - 0.5
        # keep_prob = 0.5
        # shape = (x.shape[0],) + (1,) * (x.ndim - 1)
        # shape = (4,) + (1,) * (2 - 1)
        # shape = (4, 1)
        #
        # random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
        # random_tensor = 0.5 + torch.rand((4, 1))
        #
        # # 生成的 random_tensor 可能类似于
        # random_tensor = torch.tensor([[0.8],
        #                               [0.3],
        #                               [0.7],
        #                               [0.1]])
        # random_tensor.floor_()
        # random_tensor = torch.tensor([[1.0],
        #                               [0.0],
        #                               [1.0],
        #                               [0.0]])
        # output = x.div(keep_prob) * random_tensor
        # output = x.div(0.5) * random_tensor
        #
        # # 计算每个元素
        # output = torch.tensor([[1.0 / 0.5, 2.0 / 0.5],
        #                        [3.0 / 0.5, 4.0 / 0.5],
        #                        [5.0 / 0.5, 6.0 / 0.5],
        #                        [7.0 / 0.5, 8.0 / 0.5]]) * random_tensor
        #
        # output = torch.tensor([[2.0, 4.0],
        #                        [6.0, 8.0],
        #                        [10.0, 12.0],
        #                        [14.0, 16.0]]) * random_tensor
        #
        # # 计算结果
        # output = torch.tensor([[2.0, 4.0],
        #                        [0.0, 0.0],
        #                        [10.0, 12.0],
        #                        [0.0, 0.0]])

# 在这个例子中，每个样本的路径被随机丢弃。
# 对于丢弃的路径，输出张量中的对应元素被设置为0，而未丢弃的路径的值按比例放大，以保持整体的期望值不变。
#
# 这种方法在深度学习中的作用类似于 Dropout，但它是对整个路径（例如残差块）进行随机丢弃，而不是对单个神经元。
# 这种技术能够提高模型的鲁棒性和泛化能力。


class DropPath(nn.Module):
    """
    Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """
    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        return drop_path(x, self.drop_prob, self.training)


class PatchEmbed(nn.Module):
    """
    2D Image to Patch Embedding
    """
    def __init__(self, img_size=224, patch_size=16, in_c=3, embed_dim=768, norm_layer=None):
        super().__init__()
        img_size = (img_size, img_size)  # (224,224)
        patch_size = (patch_size, patch_size) # (16,16)
        self.img_size = img_size  # 224
        self.patch_size = patch_size # 16
        self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1]) # (14,14)
        self.num_patches = self.grid_size[0] * self.grid_size[1] # 14*14=196

        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size) # 3,768,16,16
        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()

    def forward(self, x):
        B, C, H, W = x.shape
        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]})."

        # flatten: [B, C, H, W] -> [B, C, HW]
        # transpose: [B, C, HW] -> [B, HW, C]

        x = self.proj(x).flatten(2).transpose(1, 2)
        x = self.norm(x)

        return x


class Attention(nn.Module):
    def __init__(self,
                 dim,   # 输入token的dim
                 num_heads=8,
                 qkv_bias=False,
                 qk_scale=None,
                 attn_drop_ratio=0.,
                 proj_drop_ratio=0.):
        super(Attention, self).__init__()
        self.num_heads = num_heads  # 12
        head_dim = dim // num_heads # 64 = 768 / 12
        self.scale = qk_scale or head_dim ** -0.5 # 这是计算 64 的倒数的平方根
        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)  # on the last dimension of the input tensor
        self.attn_drop = nn.Dropout(attn_drop_ratio)
        # 在训练模式下（model.train()），Dropout 层以 50% 的概率随机将一些神经元的输出置为零。
        # 在评估模式下（model.eval()），Dropout 层不会丢弃任何神经元的输出，但会将所有神经元的输出乘以 0.5（因为丢弃概率为 0.5）。

        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop_ratio)

    def forward(self, x):
        # [batch_size, num_patches + 1, total_embed_dim]
        B, N, C = x.shape
        # print(x.shape) # torch.Size([8, 197, 768])
        # print(self.qkv(x).shape) # torch.Size([8, 197, 2304])
        # print(self.num_heads) # 12
        # print(self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).shape)# torch.Size([8, 197, 3, 12, 64])
        # input()

        # qkv(): -> [batch_size, num_patches + 1, 3 * total_embed_dim]
        # reshape: -> [batch_size, num_patches + 1, 3, num_heads, embed_dim_per_head] # # torch.Size([8, 197, 3, 12, 64])
        # permute: -> [3, batch_size, num_heads, num_patches + 1, embed_dim_per_head] # # torch.Size([3, 8, 12, 197, 64])
        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        # [batch_size, num_heads, num_patches + 1, embed_dim_per_head]
        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple) # torch.Size([8, 12, 197, 64])

        # print(q.shape)  # torch.Size([8, 12, 197, 64])
        # print(q.transpose(-2,-1).shape) # torch.Size([8, 12, 64, 197])
        # print((q.permute(0,1,3,2)).shape) # torch.Size([8, 12, 64, 197])
        #
        # # print(q.permute(-2,-1)) # error: i.e. input.dim() = 4 is not equal to len(dims) = 2
        #
        # print("***")
        #
        # print((q @ k.transpose(-2, -1)) .shape) # torch.Size([8, 12, 197, 197])
        #
        # input()

        # print(64 ** -0.5) # 这是计算 64 的倒数的平方根。
        # input()

        # transpose: -> [batch_size, num_heads, embed_dim_per_head, num_patches + 1]
        # @: multiply -> [batch_size, num_heads, num_patches + 1, num_patches + 1]
        attn = (q @ k.transpose(-2, -1)) * self.scale  # torch.Size([8, 12, 197, 197])
        attn = attn.softmax(dim=-1)  # softmax 是一种常用的激活函数，通常用于多分类任务的输出层。它将输入的向量转换为概率分布，即输出的每个元素都在 0 到 1 之间，并且这些元素的总和为 1
        attn = self.attn_drop(attn)

        # @: multiply -> [batch_size, num_heads, num_patches + 1, embed_dim_per_head] # torch.Size([8, 12, 197, 64])
        # transpose: -> [batch_size, num_patches + 1, num_heads, embed_dim_per_head] # torch.Size([8, 197, 12, 64])
        # reshape: -> [batch_size, num_patches + 1, total_embed_dim] # torch.Size([8, 197, 768])
        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
        x = self.proj(x) # torch.Size([8, 197, 768])
        x = self.proj_drop(x)
        return x


class Mlp(nn.Module):
    """
    MLP as used in Vision Transformer, MLP-Mixer and related networks
    """
    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


class Block(nn.Module):
    def __init__(self,
                 dim,
                 num_heads,
                 mlp_ratio=4.,
                 qkv_bias=False,
                 qk_scale=None,
                 drop_ratio=0.,
                 attn_drop_ratio=0.,
                 drop_path_ratio=0.,
                 act_layer=nn.GELU,
                 norm_layer=nn.LayerNorm):   # 对每个样本的所有通道计算均值和标准差
        super(Block, self).__init__()
        self.norm1 = norm_layer(dim)
        self.attn = Attention(dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
                              attn_drop_ratio=attn_drop_ratio, proj_drop_ratio=drop_ratio)
        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
        self.drop_path = DropPath(drop_path_ratio) if drop_path_ratio > 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_ratio)

    def forward(self, x):

        # torch.Size([8, 197, 768])  # Batch=8 对每个样本的所有通道计算均值和标准差

        x = x + self.drop_path(self.attn(self.norm1(x)))  # Attention input(x): torch.Size([8,197,768]) output: torch.Size([8,197,768])
        x = x + self.drop_path(self.mlp(self.norm2(x)))
        return x


class VisionTransformer(nn.Module):
    def __init__(self, img_size=224, patch_size=16, in_c=3, num_classes=1000,
                 embed_dim=768, depth=12, num_heads=12, mlp_ratio=4.0, qkv_bias=True,
                 qk_scale=None, representation_size=None, distilled=False, drop_ratio=0.,
                 attn_drop_ratio=0., drop_path_ratio=0., embed_layer=PatchEmbed, norm_layer=None,
                 act_layer=None):
        """
        Args:
            img_size (int, tuple): input image size
            patch_size (int, tuple): patch size
            in_c (int): number of input channels
            num_classes (int): number of classes for classification head
            embed_dim (int): embedding dimension
            depth (int): depth of transformer
            num_heads (int): number of attention heads
            mlp_ratio (int): ratio of mlp hidden dim to embedding dim
            qkv_bias (bool): enable bias for qkv if True
            qk_scale (float): override default qk scale of head_dim ** -0.5 if set
            representation_size (Optional[int]): enable and set representation layer (pre-logits) to this value if set
            distilled (bool): model includes a distillation token and head as in DeiT models
            drop_ratio (float): dropout rate
            attn_drop_ratio (float): attention dropout rate
            drop_path_ratio (float): stochastic depth rate
            embed_layer (nn.Module): patch embedding layer
            norm_layer: (nn.Module): normalization layer
        """
        super(VisionTransformer, self).__init__()
        self.num_classes = num_classes
        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
        self.num_tokens = 2 if distilled else 1
        norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
        act_layer = act_layer or nn.GELU

        self.patch_embed = embed_layer(img_size=img_size, patch_size=patch_size, in_c=in_c, embed_dim=embed_dim)
        num_patches = self.patch_embed.num_patches

        self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
        # 定义一个可训练的分类标记（classification token，简称 cls_token）。这个标记用于表示整个输入序列或图像的全局信息，通常用于分类任务。
        self.dist_token = nn.Parameter(torch.zeros(1, 1, embed_dim)) if distilled else None
        # 定义了一个形状为 (1, 1, embed_dim) 的全零张量，并将其转换为可训练的参数（如果 distilled 为 True）。
        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
        self.pos_drop = nn.Dropout(p=drop_ratio)

        dpr = [x.item() for x in torch.linspace(0, drop_path_ratio, depth)]  # stochastic depth decay rule
        self.blocks = nn.Sequential(*[
            Block(dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, qk_scale=qk_scale,
                  drop_ratio=drop_ratio, attn_drop_ratio=attn_drop_ratio, drop_path_ratio=dpr[i],
                  norm_layer=norm_layer, act_layer=act_layer)
            for i in range(depth)
        ])
        self.norm = norm_layer(embed_dim)

        # Representation layer
        if representation_size and not distilled:
            self.has_logits = True
            self.num_features = representation_size
            self.pre_logits = nn.Sequential(OrderedDict([
                ("fc", nn.Linear(embed_dim, representation_size)),
                ("act", nn.Tanh())
            ]))
        else:
            self.has_logits = False
            self.pre_logits = nn.Identity()

        # Classifier head(s)
        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()
        self.head_dist = None
        if distilled:
            self.head_dist = nn.Linear(self.embed_dim, self.num_classes) if num_classes > 0 else nn.Identity()

        # Weight init
        nn.init.trunc_normal_(self.pos_embed, std=0.02)
        if self.dist_token is not None:
            nn.init.trunc_normal_(self.dist_token, std=0.02)

        nn.init.trunc_normal_(self.cls_token, std=0.02)
        self.apply(_init_vit_weights)

    def forward_features(self, x):
        # [B, C, H, W] -> [B, num_patches, embed_dim]

        x = self.patch_embed(x)  # [B, 196, 768]

        # [1, 1, 768] -> [B, 1, 768]
        cls_token = self.cls_token.expand(x.shape[0], -1, -1)
        if self.dist_token is None:
            x = torch.cat((cls_token, x), dim=1)  # [B, 197, 768]
        else:
            x = torch.cat((cls_token, self.dist_token.expand(x.shape[0], -1, -1), x), dim=1)

        x = self.pos_drop(x + self.pos_embed)
        x = self.blocks(x)
        x = self.norm(x)
        if self.dist_token is None:
            return self.pre_logits(x[:, 0])
        else:
            return x[:, 0], x[:, 1]
        # x[:, 0] 是每个样本的分类标记
        # x[:, 1] 是每个样本的蒸馏标记（dist_token）

    def forward(self, x):
        x = self.forward_features(x)
        if self.head_dist is not None:
            x, x_dist = self.head(x[0]), self.head_dist(x[1])
            if self.training and not torch.jit.is_scripting():
                # during inference, return the average of both classifier predictions
                return x, x_dist
            else:
                return (x + x_dist) / 2
        else:
            x = self.head(x)
        return x


def _init_vit_weights(m):
    """
    ViT weight initialization
    :param m: module
    """
    if isinstance(m, nn.Linear):
        nn.init.trunc_normal_(m.weight, std=.01)
        if m.bias is not None:
            nn.init.zeros_(m.bias)
    elif isinstance(m, nn.Conv2d):
        nn.init.kaiming_normal_(m.weight, mode="fan_out")
        if m.bias is not None:
            nn.init.zeros_(m.bias)
    elif isinstance(m, nn.LayerNorm):
        nn.init.zeros_(m.bias)
        nn.init.ones_(m.weight)


def vit_base_patch16_224(num_classes: int = 1000):
    """
    ViT-Base model (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    weights ported from official Google JAX impl:
    链接: https://pan.baidu.com/s/1zqb08naP0RPqqfSXfkB2EA  密码: eu9f
    """
    model = VisionTransformer(img_size=224,
                              patch_size=16,
                              embed_dim=768,
                              depth=12,
                              num_heads=12,
                              representation_size=None,
                              num_classes=num_classes)
    return model


def vit_base_patch16_224_in21k(num_classes: int = 21843, has_logits: bool = True):
    """
    ViT-Base model (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    weights ported from official Google JAX impl:
    https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_patch16_224_in21k-e5005f0a.pth
    """
    model = VisionTransformer(img_size=224,
                              patch_size=16,
                              embed_dim=768,
                              depth=12,
                              num_heads=12,
                              representation_size=768 if has_logits else None,
                              num_classes=num_classes)
    return model


def vit_base_patch32_224(num_classes: int = 1000):
    """
    ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    weights ported from official Google JAX impl:
    链接: https://pan.baidu.com/s/1hCv0U8pQomwAtHBYc4hmZg  密码: s5hl
    """
    model = VisionTransformer(img_size=224,
                              patch_size=32,
                              embed_dim=768,
                              depth=12,
                              num_heads=12,
                              representation_size=None,
                              num_classes=num_classes)
    return model


def vit_base_patch32_224_in21k(num_classes: int = 21843, has_logits: bool = True):
    """
    ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    weights ported from official Google JAX impl:
    https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_patch32_224_in21k-8db57226.pth
    """
    model = VisionTransformer(img_size=224,
                              patch_size=32,
                              embed_dim=768,
                              depth=12,
                              num_heads=12,
                              representation_size=768 if has_logits else None,
                              num_classes=num_classes)
    return model


def vit_large_patch16_224(num_classes: int = 1000):
    """
    ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-1k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    weights ported from official Google JAX impl:
    链接: https://pan.baidu.com/s/1cxBgZJJ6qUWPSBNcE4TdRQ  密码: qqt8
    """
    model = VisionTransformer(img_size=224,
                              patch_size=16,
                              embed_dim=1024,
                              depth=24,
                              num_heads=16,
                              representation_size=None,
                              num_classes=num_classes)
    return model


def vit_large_patch16_224_in21k(num_classes: int = 21843, has_logits: bool = True):
    """
    ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    weights ported from official Google JAX impl:
    https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch16_224_in21k-606da67d.pth
    """
    model = VisionTransformer(img_size=224,
                              patch_size=16,
                              embed_dim=1024,
                              depth=24,
                              num_heads=16,
                              representation_size=1024 if has_logits else None,
                              num_classes=num_classes)
    return model


def vit_large_patch32_224_in21k(num_classes: int = 21843, has_logits: bool = True):
    """
    ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    weights ported from official Google JAX impl:
    https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch32_224_in21k-9046d2e7.pth
    """
    model = VisionTransformer(img_size=224,
                              patch_size=32,
                              embed_dim=1024,
                              depth=24,
                              num_heads=16,
                              representation_size=1024 if has_logits else None,
                              num_classes=num_classes)
    return model


def vit_huge_patch14_224_in21k(num_classes: int = 21843, has_logits: bool = True):
    """
    ViT-Huge model (ViT-H/14) from original paper (https://arxiv.org/abs/2010.11929).
    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
    NOTE: converted weights not currently available, too large for github release hosting.
    """
    model = VisionTransformer(img_size=224,
                              patch_size=14,
                              embed_dim=1280,
                              depth=32,
                              num_heads=16,
                              representation_size=1280 if has_logits else None,
                              num_classes=num_classes)
    return model

Swin Transformer:

""" Swin Transformer
A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows`
    - https://arxiv.org/pdf/2103.14030

Code/weights from https://github.com/microsoft/Swin-Transformer

"""

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
import numpy as np
from typing import Optional


def drop_path_f(x, drop_prob: float = 0., training: bool = False):
    """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
    'survival rate' as the argument.

    """
    if drop_prob == 0. or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()  # binarize
    output = x.div(keep_prob) * random_tensor
    return output


class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """
    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        return drop_path_f(x, self.drop_prob, self.training)


def window_partition(x, window_size: int):
    """
    将feature map按照window_size划分成一个个没有重叠的window
    Args:
        x: (B, H, W, C)
        window_size (int): window size(M)

    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)
    # permute: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H//Mh, W//Mh, Mw, Mw, C]
    # view: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B*num_windows, Mh, Mw, 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: int, H: int, W: int):
    """
    将一个个window还原成一个feature map
    Args:
        windows: (num_windows*B, window_size, window_size, C)
        window_size (int): Window size(M)
        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))
    # view: [B*num_windows, Mh, Mw, C] -> [B, H//Mh, W//Mw, Mh, Mw, C]
    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
    # permute: [B, H//Mh, W//Mw, Mh, Mw, C] -> [B, H//Mh, Mh, W//Mw, Mw, C]
    # view: [B, H//Mh, Mh, W//Mw, Mw, C] -> [B, H, W, C]
    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
    return x


class PatchEmbed(nn.Module):
    """
    2D Image to Patch Embedding
    """
    def __init__(self, patch_size=4, in_c=3, embed_dim=96, norm_layer=None):
        super().__init__()
        patch_size = (patch_size, patch_size)
        self.patch_size = patch_size
        self.in_chans = in_c
        self.embed_dim = embed_dim
        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size)
        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()

    def forward(self, x):
        _, _, H, W = x.shape

        # padding
        # 如果输入图片的H，W不是patch_size的整数倍，需要进行padding
        pad_input = (H % self.patch_size[0] != 0) or (W % self.patch_size[1] != 0)
        if pad_input:
            # to pad the last 3 dimensions,
            # (W_left, W_right, H_top,H_bottom, C_front, C_back)
            x = F.pad(x, (0, self.patch_size[1] - W % self.patch_size[1],
                          0, self.patch_size[0] - H % self.patch_size[0],
                          0, 0))

        # 下采样patch_size倍
        x = self.proj(x)
        _, _, H, W = x.shape
        # flatten: [B, C, H, W] -> [B, C, HW]
        # transpose: [B, C, HW] -> [B, HW, C]
        x = x.flatten(2).transpose(1, 2)
        x = self.norm(x)
        return x, H, W


class PatchMerging(nn.Module):
    r""" 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):
        """
        x: B, H*W, C
        """
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"

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

        # padding
        # 如果输入feature map的H，W不是2的整数倍，需要进行padding
        pad_input = (H % 2 == 1) or (W % 2 == 1)
        if pad_input:
            # to pad the last 3 dimensions, starting from the last dimension and moving forward.
            # (C_front, C_back, W_left, W_right, H_top, H_bottom)
            # 注意这里的Tensor通道是[B, H, W, C]，所以会和官方文档有些不同
            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)  # [B, H/2*W/2, 2*C]

        return x


class Mlp(nn.Module):
    """ MLP as used in Vision Transformer, MLP-Mixer and related networks
    """
    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.drop1 = nn.Dropout(drop)
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop2 = nn.Dropout(drop)

    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop1(x)
        x = self.fc2(x)
        x = self.drop2(x)
        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
        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, attn_drop=0., proj_drop=0.):

        super().__init__()
        self.dim = dim
        self.window_size = window_size  # [Mh, Mw]
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = 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*Mh-1 * 2*Mw-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], indexing="ij"))  # [2, Mh, Mw]
        coords_flatten = torch.flatten(coords, 1)  # [2, Mh*Mw]
        # [2, Mh*Mw, 1] - [2, 1, Mh*Mw]
        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # [2, Mh*Mw, Mh*Mw]
        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # [Mh*Mw, Mh*Mw, 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)  # [Mh*Mw, Mh*Mw]
        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)

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

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

        # transpose: -> [batch_size*num_windows, num_heads, embed_dim_per_head, Mh*Mw]
        # @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, Mh*Mw]
        q = q * self.scale
        attn = (q @ k.transpose(-2, -1))

        # relative_position_bias_table.view: [Mh*Mw*Mh*Mw,nH] -> [Mh*Mw,Mh*Mw,nH]
        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)
        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # [nH, Mh*Mw, Mh*Mw]
        attn = attn + relative_position_bias.unsqueeze(0)

        if mask is not None:
            # mask: [nW, Mh*Mw, Mh*Mw]
            nW = mask.shape[0]  # num_windows
            # attn.view: [batch_size, num_windows, num_heads, Mh*Mw, Mh*Mw]
            # mask.unsqueeze: [1, nW, 1, Mh*Mw, Mh*Mw]
            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)

        # @: multiply -> [batch_size*num_windows, num_heads, Mh*Mw, embed_dim_per_head]
        # transpose: -> [batch_size*num_windows, Mh*Mw, num_heads, embed_dim_per_head]
        # reshape: -> [batch_size*num_windows, Mh*Mw, total_embed_dim]
        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):
    r""" 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
        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, 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=(self.window_size, self.window_size), num_heads=num_heads, qkv_bias=qkv_bias,
            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)

    def forward(self, x, attn_mask):
        H, W = self.H, self.W
        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)

        # pad feature maps to multiples of window size
        # 把feature map给pad到window size的整数倍
        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))
        else:
            shifted_x = x
            attn_mask = None

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

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

        # merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)  # [nW*B, Mh, Mw, 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:
            # 把前面pad的数据移除掉
            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 BasicLayer(nn.Module):
    """
    A basic Swin Transformer layer for one stage.

    Args:
        dim (int): Number of input channels.
        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
        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,
                 mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0.,
                 drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False):
        super().__init__()
        self.dim = dim
        self.depth = depth
        self.window_size = window_size
        self.use_checkpoint = use_checkpoint
        self.shift_size = window_size // 2

        # 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 self.shift_size,
                mlp_ratio=mlp_ratio,
                qkv_bias=qkv_bias,
                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 create_mask(self, x, H, W):
        # calculate attention mask for SW-MSA
        # 保证Hp和Wp是window_size的整数倍
        Hp = int(np.ceil(H / self.window_size)) * self.window_size
        Wp = int(np.ceil(W / self.window_size)) * self.window_size
        # 拥有和feature map一样的通道排列顺序，方便后续window_partition
        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, Mh, Mw, 1]
        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)  # [nW, Mh*Mw]
        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)  # [nW, 1, Mh*Mw] - [nW, Mh*Mw, 1]
        # [nW, Mh*Mw, Mh*Mw]
        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
        return attn_mask

    def forward(self, x, H, W):
        attn_mask = self.create_mask(x, H, W)  # [nW, Mh*Mw, Mh*Mw]
        for blk in self.blocks:
            blk.H, blk.W = H, W
            if not torch.jit.is_scripting() and self.use_checkpoint:
                x = checkpoint.checkpoint(blk, x, attn_mask)
            else:
                x = blk(x, attn_mask)
        if self.downsample is not None:
            x = self.downsample(x, H, W)
            H, W = (H + 1) // 2, (W + 1) // 2

        return x, H, W


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

    Args:
        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
        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.
        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, patch_size=4, in_chans=3, num_classes=1000,
                 embed_dim=96, depths=(2, 2, 6, 2), num_heads=(3, 6, 12, 24),
                 window_size=7, mlp_ratio=4., qkv_bias=True,
                 drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
                 norm_layer=nn.LayerNorm, patch_norm=True,
                 use_checkpoint=False, **kwargs):
        super().__init__()

        self.num_classes = num_classes
        self.num_layers = len(depths)
        self.embed_dim = embed_dim
        self.patch_norm = patch_norm
        # stage4输出特征矩阵的channels
        self.num_features = int(embed_dim * 2 ** (self.num_layers - 1))
        self.mlp_ratio = mlp_ratio

        # split image into non-overlapping patches
        self.patch_embed = PatchEmbed(
            patch_size=patch_size, in_c=in_chans, embed_dim=embed_dim,
            norm_layer=norm_layer if self.patch_norm else None)
        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):
            # 注意这里构建的stage和论文图中有些差异
            # 这里的stage不包含该stage的patch_merging层，包含的是下个stage的
            layers = BasicLayer(dim=int(embed_dim * 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,
                                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(layers)

        self.norm = norm_layer(self.num_features)
        self.avgpool = nn.AdaptiveAvgPool1d(1)
        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()

        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            nn.init.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)

    def forward(self, x):
        # x: [B, L, C]
        x, H, W = self.patch_embed(x)
        x = self.pos_drop(x)

        for layer in self.layers:
            x, H, W = layer(x, H, W)

        x = self.norm(x)  # [B, L, C]
        x = self.avgpool(x.transpose(1, 2))  # [B, C, 1]
        x = torch.flatten(x, 1)
        x = self.head(x)
        return x


def swin_tiny_patch4_window7_224(num_classes: int = 1000, **kwargs):
    # trained ImageNet-1K
    # https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth
    model = SwinTransformer(in_chans=3,
                            patch_size=4,
                            window_size=7,
                            embed_dim=96,
                            depths=(2, 2, 6, 2),
                            num_heads=(3, 6, 12, 24),
                            num_classes=num_classes,
                            **kwargs)
    return model


def swin_small_patch4_window7_224(num_classes: int = 1000, **kwargs):
    # trained ImageNet-1K
    # https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth
    model = SwinTransformer(in_chans=3,
                            patch_size=4,
                            window_size=7,
                            embed_dim=96,
                            depths=(2, 2, 18, 2),
                            num_heads=(3, 6, 12, 24),
                            num_classes=num_classes,
                            **kwargs)
    return model


def swin_base_patch4_window7_224(num_classes: int = 1000, **kwargs):
    # trained ImageNet-1K
    # https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224.pth
    model = SwinTransformer(in_chans=3,
                            patch_size=4,
                            window_size=7,
                            embed_dim=128,
                            depths=(2, 2, 18, 2),
                            num_heads=(4, 8, 16, 32),
                            num_classes=num_classes,
                            **kwargs)
    return model


def swin_base_patch4_window12_384(num_classes: int = 1000, **kwargs):
    # trained ImageNet-1K
    # https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384.pth
    model = SwinTransformer(in_chans=3,
                            patch_size=4,
                            window_size=12,
                            embed_dim=128,
                            depths=(2, 2, 18, 2),
                            num_heads=(4, 8, 16, 32),
                            num_classes=num_classes,
                            **kwargs)
    return model


def swin_base_patch4_window7_224_in22k(num_classes: int = 21841, **kwargs):
    # trained ImageNet-22K
    # https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22k.pth
    model = SwinTransformer(in_chans=3,
                            patch_size=4,
                            window_size=7,
                            embed_dim=128,
                            depths=(2, 2, 18, 2),
                            num_heads=(4, 8, 16, 32),
                            num_classes=num_classes,
                            **kwargs)
    return model


def swin_base_patch4_window12_384_in22k(num_classes: int = 21841, **kwargs):
    # trained ImageNet-22K
    # https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384_22k.pth
    model = SwinTransformer(in_chans=3,
                            patch_size=4,
                            window_size=12,
                            embed_dim=128,
                            depths=(2, 2, 18, 2),
                            num_heads=(4, 8, 16, 32),
                            num_classes=num_classes,
                            **kwargs)
    return model


def swin_large_patch4_window7_224_in22k(num_classes: int = 21841, **kwargs):
    # trained ImageNet-22K
    # https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window7_224_22k.pth
    model = SwinTransformer(in_chans=3,
                            patch_size=4,
                            window_size=7,
                            embed_dim=192,
                            depths=(2, 2, 18, 2),
                            num_heads=(6, 12, 24, 48),
                            num_classes=num_classes,
                            **kwargs)
    return model


def swin_large_patch4_window12_384_in22k(num_classes: int = 21841, **kwargs):
    # trained ImageNet-22K
    # https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22k.pth
    model = SwinTransformer(in_chans=3,
                            patch_size=4,
                            window_size=12,
                            embed_dim=192,
                            depths=(2, 2, 18, 2),
                            num_heads=(6, 12, 24, 48),
                            num_classes=num_classes,
                            **kwargs)
    return model