OUC暑期培训（深度学习）——第六周学习记录：Vision Transformer &； Swin Transformer

第六周学习：Vision Transformer & Swin Transformer

Part 1 视频学习及论文阅读

1、Vision Transformer

原文链接：https://arxiv.org/abs/2010.11929

Transformer最初提出是针对NLP领域的，尝试将Transformer模型应用到CV领域，展现了相当不错的效果。

下图是Vision Transformer的原型框架：

主要由三部分组成：

（1）Linear Projection of Flattened Patches(Embedding层)

（2）Transformer Encoder(图右侧有给出更加详细的结构)

（3）MLP Head（最终用于分类的层结构）

---

（1）Linear Projection of Flattened Patches(Embedding层)

Transformer模块要求输入为二维矩阵，而图像数据为[H, W, C]的三维矩阵，因此，Embedding层对数据进行变换。

先将图片按给定大小分成一堆Patches，接着通过线性映射将每个Patch映射到一维向量中（该部分用代码实现时直接通过一个卷积层来实现，需要指出的是，每个Patch可以重叠，也可以不重叠，不重叠的话，其stride=卷积核大小）。

在输入Transformer Encoder之前，还需要加上[class]token以及Position Embedding。[class]token是一个可训练的参数，数据格式和其他token一样都是一个向量；Position Embedding就是Transformer中的Positional Encoding（在ViT中使用的是可训练的位置编码）。相比于不加入Position Embedding，准确率大概高了3个点。（如果不加入Position Embedding，我们变换每个Patch的位置，网络仍认为与未变换前相同，而实际图片却是有区别的，因此加上Position Embedding能提高准确率）。

 （2）Position Embedding

Transformer Encoder其实就是重复堆叠Encoder Block L次。

Encoder Block主要包含以下几个部分：

①Layer Norm，这种Normalization方法主要是针对NLP领域提出的，这里是对每个token进行Norm处理

②Multi-Head Attention，将分别通过得到对应的，然后再根据使用的head的数目h进一步把得到的均分成h份（Attention Is All You Need中通过映射得到每个head的，即：）,通过上述方法获得每个对应的，接下来针对每个head使用和self-Attention相同的方法即可获得对应的结果，即。接着将每个head得到的结果进行concat拼接,然后再将拼接之后的结果通过（可学习的参数）进行融合，即,得到最终的结果b。

③Dropout/DropPath，在原论文的代码中是直接使用的Dropout层，在但rwightman实现的代码中使用的是DropPath（stochastic depth），可能后者会更好一点。

④MLP Block，如图右侧所示，由全连接+GELU激活函数+Dropout组成，需要注意的是第一个全连接层会把输入节点个数翻4倍，而第二个全连接层会还原回原节点个数。 

（3）MLP Head

在Transformer Encoder前还有个Drop out层，其后还有一个Layer Norm。Transformer Encode之后，先提取出[class]token生成的对应结果，再通过MLP Head得到我们最终的分类结果。在原论文中，训练ImageNet21K及更大的数据集时，由Linear+tanh激活函数+Linear组成。但在迁移到ImageNet1K上或者自己的数据上时，只用一个Linear即可。

2、Hybrid模型

Hybrid混合模型，就是先使用传统CNN提取特征再用ViT得到最终结果。

主要有三点不同：

（1）卷积层使用的StdConv2d而不是传统的Conv2d

（2）将所有的BatchNorm层替换成了GroupNorm层（BN通常需要比较大的Batch Size，对于比较大型的网络或者GPU显存不够的情况下，通常无法设置较大的batch size，此时可以使用GN。具体步骤：假设某层输出得到x，根据num_groups沿channel方向均分成num_groups份，然后对每一份求均值和方差，接着按照进行计算即可，其中是一个非常小的量（默认），是为了防止分母为零，为训练参数。）

（3）把stage4中的3个Block移至stage3中（如下图，Stage3 Block重复了9次，下采样率只有16）

即先通过如下的部分进行特征提取，然后使用一个卷积层来调整channel，其余与ViT相同

3、Swin Transformer

原文链接：https://arxiv.org/abs/2103.14030

相比于ViT，Swin Transformer主要有两个不同的地方（如下图），一是，其所构建的feature map与卷积神经网络相似，具有层次性，而ViT直接下采样16倍，后面也保持倍率不变，因此Swin Transformer在目标检测以及图像分割方面具有更大的优势（使用层次化构建方法（Hierarchical feature maps））；二是，Swin Transformer是以窗口的形式将feature map分割开，窗口与窗口之间没有重叠，在每个窗口内部进行Multi-Head self-attention计算，能大大降低运算量。（Windows Multi-Head Self-Attention(W-MSA)）

 Swin Transformer的网络架构图如下所示。假设输入的图像的大小是，先经过Patch Partition模块中进行分块并展平，再分别经过stage1、2、3、4，其中Patch Partition+Linear Embeding（包含Layer Norm）与后面的Patch Merging相似，Patch Partition和Linear Embeding都是通过一个卷积层实现的。每个stage中的Swin Transformer Block都重复了偶数次，因为使用的是下图（b）。如果是分类任务，在stage4之后还会在接上一个Layer Norm、全局池化及一个全连接层进行输出。

 接下来介绍Swin Transformer的几个重要结构：

（1）Patch Merging

 Patch Merging起到下采样的作用，经过Patch Merging，特征图的高和宽会下降一般，而channel则会翻倍。

假设输入的为4*4大小的单通道特征图，首先将相邻的2*2的像素划分为同一个patch，再将每个patch中相对应的相同位置的像素拼接到一起，得到4个feature map，将这4个feature map在channel方向拼接到一起并同样在channel方向进行layernorm处理，最后用一个全连接层在深度方向上进行线性映射，最终得到相对于输入高和宽减半，channel加倍的feature map，如下图所示。

（2）W-MSA

W-MSA模块与Multi-Head Attention基本类似，主要的区别在于，W-MSA将feature map划分成几个windows，在每个window的内部进行MSA，而Multi-Head Attention每个像素都与全部的像素进行q，k，v的计算操作。这样做的目的是为了降低计算量，但由于每个窗口之间无法进行信息之间的交互，因此会丧失感受野，降低效果。

计算量差异：

其中，h、w、C分别为feature map的高度宽度和深度，M为W-MSA中，每个窗口的大小。

（3）SW-MSA 

在W-MSA中，每个窗口之间没有信息交互，为解决此，作者提出了Shifted Windows Multi-Head Self-Attention（SW-MSA）模块。

简单理解SW-MSA就是将原来切分windows的方法进行了偏移，使得现切分的windows含有原来不同的windows的部分，因为每个W-MSA和SW-MSA模块是成对使用的，因此能实现原不同windows之间的信息交互。

 将切分windows进行偏移之后，仍要在每个window内进行MSA计算，为简化计算，作者将分割后的window进行了移动和合并，移动可参考下图：

移动前：

移动之后：

 此时，4是一个单独的窗口；5和3合并成一个窗口；7和1合并成一个窗口；8、6、2和0合并成一个窗口。这样又和原来一样是4个4x4的窗口了。

在计算时为了防止移动合并之后的不同的窗口进行本不相关的信息交流，在进行MSA计算时，计算每个像素的q、k、v时，会将原不同window的像素计算所得的a减去100，这样经过softmax之后，其值为0，这样与v相乘时值也为0（参见）。

计算完之后，将移动的区域移回原位置即可。

（4）Relative Position Bias

使用绝对位置偏置，在COCO数据集和ADE20K数据集上准确率反而有所降低。使用相对位置偏置后， 准确率有所升高。

相对位置偏置用在attention的计算中,公式如下：

B即为相对位置偏置，B是由feature map中每个像素所得的相对位置索引经变换后得到的索引到relative position bias table表中搜索得到相对位置偏置参数。

 变换如下：首先在原始的相对位置索引上加上M-1(M为窗口的大小），接着将所有的行标都乘上2M-1，最后将行标和列标进行相加。这样即保证了相对位置关系，也不会出现不同相对位置但索引相同的情况。（这样变换的原因是，将二维索引变为了一维索引）

接着根据索引获得相应的相对位置偏置参数即可。 

4、ConvNeXt

Part 2 代码练习

1、Vision Transformer

"""
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:
        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(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)
        patch_size = (patch_size, patch_size)
        self.img_size = img_size
        self.patch_size = patch_size
        self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
        self.num_patches = self.grid_size[0] * self.grid_size[1]

        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):
        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
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim ** -0.5
        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop_ratio)
        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

        # qkv(): -> [batch_size, num_patches + 1, 3 * total_embed_dim]
        # reshape: -> [batch_size, num_patches + 1, 3, num_heads, embed_dim_per_head]
        # permute: -> [3, batch_size, num_heads, num_patches + 1, 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_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)

        # 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
        attn = attn.softmax(dim=-1)
        attn = self.attn_drop(attn)

        # @: multiply -> [batch_size, num_heads, num_patches + 1, embed_dim_per_head]
        # transpose: -> [batch_size, num_patches + 1, num_heads, embed_dim_per_head]
        # reshape: -> [batch_size, num_patches + 1, 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 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):
        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):
        x = x + self.drop_path(self.attn(self.norm1(x)))
        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))
        self.dist_token = nn.Parameter(torch.zeros(1, 1, embed_dim)) if distilled else None
        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]

    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

2、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

3、ConvNeXt

"""
original code from facebook research:
https://github.com/facebookresearch/ConvNeXt
"""

import torch
import torch.nn as nn
import torch.nn.functional as F


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:
        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(x, self.drop_prob, self.training)


class LayerNorm(nn.Module):
    r""" LayerNorm that supports two data formats: channels_last (default) or channels_first.
    The ordering of the dimensions in the inputs. channels_last corresponds to inputs with
    shape (batch_size, height, width, channels) while channels_first corresponds to inputs
    with shape (batch_size, channels, height, width).
    """

    def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(normalized_shape), requires_grad=True)
        self.bias = nn.Parameter(torch.zeros(normalized_shape), requires_grad=True)
        self.eps = eps
        self.data_format = data_format
        if self.data_format not in ["channels_last", "channels_first"]:
            raise ValueError(f"not support data format '{self.data_format}'")
        self.normalized_shape = (normalized_shape,)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        if self.data_format == "channels_last":
            return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
        elif self.data_format == "channels_first":
            # [batch_size, channels, height, width]
            mean = x.mean(1, keepdim=True)
            var = (x - mean).pow(2).mean(1, keepdim=True)
            x = (x - mean) / torch.sqrt(var + self.eps)
            x = self.weight[:, None, None] * x + self.bias[:, None, None]
            return x


class Block(nn.Module):
    r""" ConvNeXt Block. There are two equivalent implementations:
    (1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N, C, H, W)
    (2) DwConv -> Permute to (N, H, W, C); LayerNorm (channels_last) -> Linear -> GELU -> Linear; Permute back
    We use (2) as we find it slightly faster in PyTorch

    Args:
        dim (int): Number of input channels.
        drop_rate (float): Stochastic depth rate. Default: 0.0
        layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
    """
    def __init__(self, dim, drop_rate=0., layer_scale_init_value=1e-6):
        super().__init__()
        self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim)  # depthwise conv
        self.norm = LayerNorm(dim, eps=1e-6, data_format="channels_last")
        self.pwconv1 = nn.Linear(dim, 4 * dim)  # pointwise/1x1 convs, implemented with linear layers
        self.act = nn.GELU()
        self.pwconv2 = nn.Linear(4 * dim, dim)
        self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim,)),
                                  requires_grad=True) if layer_scale_init_value > 0 else None
        self.drop_path = DropPath(drop_rate) if drop_rate > 0. else nn.Identity()

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        shortcut = x
        x = self.dwconv(x)
        x = x.permute(0, 2, 3, 1)  # [N, C, H, W] -> [N, H, W, C]
        x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.pwconv2(x)
        if self.gamma is not None:
            x = self.gamma * x
        x = x.permute(0, 3, 1, 2)  # [N, H, W, C] -> [N, C, H, W]

        x = shortcut + self.drop_path(x)
        return x


class ConvNeXt(nn.Module):
    r""" ConvNeXt
        A PyTorch impl of : `A ConvNet for the 2020s`  -
          https://arxiv.org/pdf/2201.03545.pdf
    Args:
        in_chans (int): Number of input image channels. Default: 3
        num_classes (int): Number of classes for classification head. Default: 1000
        depths (tuple(int)): Number of blocks at each stage. Default: [3, 3, 9, 3]
        dims (int): Feature dimension at each stage. Default: [96, 192, 384, 768]
        drop_path_rate (float): Stochastic depth rate. Default: 0.
        layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
        head_init_scale (float): Init scaling value for classifier weights and biases. Default: 1.
    """
    def __init__(self, in_chans: int = 3, num_classes: int = 1000, depths: list = None,
                 dims: list = None, drop_path_rate: float = 0., layer_scale_init_value: float = 1e-6,
                 head_init_scale: float = 1.):
        super().__init__()
        self.downsample_layers = nn.ModuleList()  # stem and 3 intermediate downsampling conv layers
        stem = nn.Sequential(nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
                             LayerNorm(dims[0], eps=1e-6, data_format="channels_first"))
        self.downsample_layers.append(stem)

        # 对应stage2-stage4前的3个downsample
        for i in range(3):
            downsample_layer = nn.Sequential(LayerNorm(dims[i], eps=1e-6, data_format="channels_first"),
                                             nn.Conv2d(dims[i], dims[i+1], kernel_size=2, stride=2))
            self.downsample_layers.append(downsample_layer)

        self.stages = nn.ModuleList()  # 4 feature resolution stages, each consisting of multiple blocks
        dp_rates = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]
        cur = 0
        # 构建每个stage中堆叠的block
        for i in range(4):
            stage = nn.Sequential(
                *[Block(dim=dims[i], drop_rate=dp_rates[cur + j], layer_scale_init_value=layer_scale_init_value)
                  for j in range(depths[i])]
            )
            self.stages.append(stage)
            cur += depths[i]

        self.norm = nn.LayerNorm(dims[-1], eps=1e-6)  # final norm layer
        self.head = nn.Linear(dims[-1], num_classes)
        self.apply(self._init_weights)
        self.head.weight.data.mul_(head_init_scale)
        self.head.bias.data.mul_(head_init_scale)

    def _init_weights(self, m):
        if isinstance(m, (nn.Conv2d, nn.Linear)):
            nn.init.trunc_normal_(m.weight, std=0.2)
            nn.init.constant_(m.bias, 0)

    def forward_features(self, x: torch.Tensor) -> torch.Tensor:
        for i in range(4):
            x = self.downsample_layers[i](x)
            x = self.stages[i](x)

        return self.norm(x.mean([-2, -1]))  # global average pooling, (N, C, H, W) -> (N, C)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.forward_features(x)
        x = self.head(x)
        return x


def convnext_tiny(num_classes: int):
    # https://dl.fbaipublicfiles.com/convnext/convnext_tiny_1k_224_ema.pth
    model = ConvNeXt(depths=[3, 3, 9, 3],
                     dims=[96, 192, 384, 768],
                     num_classes=num_classes)
    return model


def convnext_small(num_classes: int):
    # https://dl.fbaipublicfiles.com/convnext/convnext_small_1k_224_ema.pth
    model = ConvNeXt(depths=[3, 3, 27, 3],
                     dims=[96, 192, 384, 768],
                     num_classes=num_classes)
    return model


def convnext_base(num_classes: int):
    # https://dl.fbaipublicfiles.com/convnext/convnext_base_1k_224_ema.pth
    # https://dl.fbaipublicfiles.com/convnext/convnext_base_22k_224.pth
    model = ConvNeXt(depths=[3, 3, 27, 3],
                     dims=[128, 256, 512, 1024],
                     num_classes=num_classes)
    return model


def convnext_large(num_classes: int):
    # https://dl.fbaipublicfiles.com/convnext/convnext_large_1k_224_ema.pth
    # https://dl.fbaipublicfiles.com/convnext/convnext_large_22k_224.pth
    model = ConvNeXt(depths=[3, 3, 27, 3],
                     dims=[192, 384, 768, 1536],
                     num_classes=num_classes)
    return model


def convnext_xlarge(num_classes: int):
    # https://dl.fbaipublicfiles.com/convnext/convnext_xlarge_22k_224.pth
    model = ConvNeXt(depths=[3, 3, 27, 3],
                     dims=[256, 512, 1024, 2048],
                     num_classes=num_classes)
    return model

Part 3 其他

1、问题

没找到StdConv2d相对于Conv2d的区别。

另外，在swin transformer中，进行SW-MSA时，每个window加上position embadding是不是可以保留原有的位置信息？