【图像分类】【深度学习】ViT算法Pytorch代码讲解

这篇具有很好参考价值的文章主要介绍了【图像分类】【深度学习】ViT算法Pytorch代码讲解。希望对大家有所帮助。如果存在错误或未考虑完全的地方,请大家不吝赐教,您也可以点击"举报违法"按钮提交疑问。

【图像分类】【深度学习】【Pytorch版本】VisionTransformer模型算法详解


前言

ViT是由谷歌公司的Dosovitskiy, Alexey等人在《 An Image Is Worth 16x16 Words: Transformers For Image Recognition At Scale【ICLR2021】》【论文地址】一文中提出的模型,提出了一种基于transformer结构的模型,摒弃传统的CNN结构,直接将Transformer应用到图像块序列上一样可以达到非常好的性能。


ViT(Vision Transformer)讲解

论文在模型设计方面尽可能和原始Transformer保持一致。这种有意设计简单化的优点在于对NLP的Transformer有良好的扩展性,几乎可以实现“开箱即用”。
【图像分类】【深度学习】ViT算法Pytorch代码讲解
如上面的动态图所示,ViT在分类任务中的分为以下几个基本步骤:

  1. 图片切分为若干图片序列块
  2. 所有序列块经过线性映射后展平为一维向量

以上俩步是 patch embedding过程,成功将一个视觉问题转化为了一个seq2seq问题。

  1. positional embedding:嵌入类别编码和位置编码(用于保留位置信息)
  2. Transformer Encoder:主体编码器部分
  3. MLP

patch embedding


输入图片大小为224x224,将图片切分为固定大小16x16的patch,则每张图像会生成224x224/16x16=196个patch,输出序列为196;196个patch(196x3)通过线性投射层(3x768)之后的维度为196x768,即一共有196个token,每个token的维度是768。

源码其实就是卷积核大小16x16(巧妙切分成固定大小16x16的patch),卷积核通道3×768的卷积操作

通过patch embedding将一个视觉问题转化为了一个seq2seq问题,patch embedding示意图如下图所示:
【图像分类】【深度学习】ViT算法Pytorch代码讲解

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__()
        # 图片分辨率 h w
        img_size = (img_size, img_size)
        # 卷积核大小
        patch_size = (patch_size, patch_size)
        self.img_size = img_size
        self.patch_size = patch_size
        # 分别计算w、h方向上的patch的个数
        self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
        # 一张图片的pacth个数
        self.num_patches = self.grid_size[0] * self.grid_size[1]
        # 卷积的步长巧妙地实现图片切分操作,而后与patch大小一致的卷积核完成线性映射
        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()      # nn.Identity()恒等函数 f(x)=x

    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]
        # 一维展平
        x = self.proj(x).flatten(2).transpose(1, 2)
        x = self.norm(x)
        return x

demo在动态流程图中的对应部分:
【图像分类】【深度学习】ViT算法Pytorch代码讲解

positional embedding

经过patch embedding后输出维度是196x768,concat一个特殊字符cls(1x768),维度变为197x768。ViT同样需要加入位置编码,位置编码可以理解为一张map,map的行数与输入序列个数相同(197),每一行代表一个向量,向量的维度和输入序列embedding的维度相同(768)。位置编码的操作是sum,所以维度依旧保持197x768。

个人理解cls和pos的作用就是ax+b中的b,是可训练的归纳偏置,因为Vision Transformer相比CNN具有更少的针对图像的归纳偏置。position embeddings在初始化时不携带任何2维位置信息,图像块之间的所有空间关系都是从头学习得到的。

positional embedding结构如下图所示:
【图像分类】【深度学习】ViT算法Pytorch代码讲解

class PositionEmbs(nn.Module):
    def __init__(self, num_patches, emb_dim, dropout_rate=0.1):
        super(PositionEmbs, self).__init__()
        self.pos_embedding = nn.Parameter(torch.zeros(1, num_patches + 1, emb_dim))
        if dropout_rate > 0:
            self.dropout = nn.Dropout(dropout_rate)
        else:
            self.dropout = None
    def forward(self, x):
        out = x + self.pos_embedding

        if self.dropout:
            out = self.dropout(out)
        return out

在class VisionTransformer的__init__函数中

# class token
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
# positional embedding
self.pos_embedding = PositionEmbs(num_patches, embed_dim, drop_ratio)

在class VisionTransformer的forward_features函数中

cls_token = self.cls_token.expand(x.shape[0], -1, -1)
# self.dist_token暂时可以忽略
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_embedding(x)

demo在动态流程图中的对应部分:
【图像分类】【深度学习】ViT算法Pytorch代码讲解

Transformer Encoder

Transformer EncoderL个重复堆叠 Encoder Block组成。

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__()
        # 类别个数
        self.num_classes = num_classes
        # embed_dim默认tansformer的base 768
        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
        # 源码distilled是为了其他任务,分类暂时不考虑
        self.num_tokens = 2 if distilled else 1
        # LayerNorm:对每单个batch进行的归一化
        norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
        # act_layer默认tansformer的GELU
        act_layer = act_layer or nn.GELU
        # embed_layer默认是patch embedding,在其他应用中应该会有其他选择
        # patch embedding过程
        self.patch_embed = embed_layer(img_size=img_size, patch_size=patch_size, in_c=in_c, embed_dim=embed_dim)
        # patche个数
        num_patches = self.patch_embed.num_patches
        # class token
        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
        # positional embedding过程
        self.pos_embedding = PositionEmbs(num_patches, embed_dim, drop_ratio)

        # self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
        # self.pos_drop = nn.Dropout(p=drop_ratio)

        # depth是Block的个数
        # 不同block层数 drop_ratio的概率不同,越深度越高
        dpr = [x.item() for x in torch.linspace(0, drop_path_ratio, depth)]  # stochastic depth decay rule
        # blocks搭建
        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
        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)
        # self.dist_token暂时可以忽略
        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_embedding(x)
        # 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

demo在动态流程图中的对应部分:
【图像分类】【深度学习】ViT算法Pytorch代码讲解

Encoder Block

组成 Transformer Encoder的单位,从低到高由LayerNorm (针对NLP领域提出的对每个token进行Norm处理)、Multi-Head Attention、DropPath(可直接换成Dropout)和 MLP等构成。
Block结构如下图所示:
【图像分类】【深度学习】ViT算法Pytorch代码讲解

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)
        # Multi-head attention模块
        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)
        #  MLP模块
        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

Multi-head attention

读者先阅读大佬的博文【Multi-head attention流程与原理参考】。这里博主结合代码也做了自己的总结供大家参考。

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

对于输入到Multi-head attention模块的特征 F(N×E) ,通过attention模块的nn.Linear进一步提取特征获得输出特征 v(value) 。为了考虑 N 个特征之间存在的亲疏和位置关系对于 v 的影响,所以需要一个额外 attn(attention) 或者理解为权重 w(weight)v 进行加权操作,这引出了计算 w 所需的 q(query)k(key)qk 同样是特征 F 通过nn.Linear获取。
博主将 attn习惯了称作权重 weight了,有点误导人!!!,Attention结构如下图所示:
【图像分类】【深度学习】ViT算法Pytorch代码讲解

下图简要展示了q、k和v的作用,便于理解原始特征v和原始特征v经过w加权计算后的特征V。
【图像分类】【深度学习】ViT算法Pytorch代码讲解
( q n {{\rm{q}}_{\rm{n}}} qn, k n {{\rm{k}}_{\rm{n}}} kn, v n {{\rm{v}}_{\rm{n}}} vn)是特征n的经过attention模块后输出的三个特征。 q 1 {{\rm{q}}_{\rm{1}}} q1 k 3 {{\rm{k}}_{\rm{3}}} k3矩阵计算得到权重 w 13 {{\rm{w}}_{\rm{13}}} w13,以此类推。以原始特征 v 1 {{\rm{v}}_{\rm{1}}} v1计算得到加权特征 V 1 {{\rm{V}}_{\rm{1}}} V1的过程为例, v 1 {{\rm{v}}_{\rm{1}}} v1分别于 w 1 x {{\rm{w}}_{\rm{1x}}} w1x w 2 x {{\rm{w}}_{\rm{2x}}} w2x w 3 x {{\rm{w}}_{\rm{3x}}} w3x矩阵运算得到 V 11 {{\rm{V}}_{\rm{11}}} V11 V 12 {{\rm{V}}_{\rm{12}}} V12 V 13 {{\rm{V}}_{\rm{13}}} V13,即最终的 V 1 {{\rm{V}}_{\rm{1}}} V1
因此可以看到任何 V i {{\rm{V}}_{\rm{i}}} Vi都考虑了 FN 个特征之间相互的影响。

Multi-head attention的流程如下图所示(不考虑batchsize):

  1. 首先将每个token的qkv特征维度embed_dim均拆分到每个head的上:
    【图像分类】【深度学习】ViT算法Pytorch代码讲解
  2. 每个head分别通过q和k计算得到权重w,权重w和v得到输出output,合并所有head的output得到最终的output:
    【图像分类】【深度学习】ViT算法Pytorch代码讲解

为了便于理解Multi-head self-attention的作用,可以类比卷积网络,单一的attention就类似于普通卷积,Multi-head self-attention则类似深度可分卷积。

demo在动态流程图中的对应部分:
【图像分类】【深度学习】ViT算法Pytorch代码讲解

不考虑全连接的偏置,下图简单举例了3个Linear(3,2)和1个nn.Linear(3,6)再切片没有本质区别。
【图像分类】【深度学习】ViT算法Pytorch代码讲解
因此,无论q、k、v是特征F分别与3个Linear(dim,dim)操作获得,还是和一个nn.Linear(dim,3×dim)操作再切片获得,没有任何区别。

MLP

MLP结构如下图所示(不考虑batchsize):
【图像分类】【深度学习】ViT算法Pytorch代码讲解

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

demo在动态流程图中的对应部分:
【图像分类】【深度学习】ViT算法Pytorch代码讲解


完整代码

"""
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)  # (shape[0],1,1,1)
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)   # rand范围在[0~1]之间, +keep_prob在[keep_prob~keep_prob+1]之间
    random_tensor.floor_()  # 只保留0或者1
    output = x.div(keep_prob) * random_tensor   # x.div(keep_prob)个人理解是为了强化保留部分的x
    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__()
        # 图片分辨率 h w
        img_size = (img_size, img_size)
        # 卷积核大小
        patch_size = (patch_size, patch_size)
        self.img_size = img_size
        self.patch_size = patch_size
        # 分别计算w、h方向上的patch的个数
        self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
        # 一张图片的pacth个数
        self.num_patches = self.grid_size[0] * self.grid_size[1]
        # 卷积的步长巧妙地实现图片切分操作,而后与patch大小一致的卷积核完成线性映射
        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()      # nn.Identity()恒等函数 f(x)=x

    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]
        # 一维展平
        x = self.proj(x).flatten(2).transpose(1, 2)
        x = self.norm(x)
        return x

class PositionEmbs(nn.Module):
    def __init__(self, num_patches, emb_dim, dropout_rate=0.1):
        super(PositionEmbs, self).__init__()
        self.pos_embedding = nn.Parameter(torch.zeros(1, num_patches + 1, emb_dim))
        if dropout_rate > 0:
            self.dropout = nn.Dropout(dropout_rate)
        else:
            self.dropout = None
        nn.init.trunc_normal_(self.pos_embedding, std=0.02)
    def forward(self, x):
        out = x + self.pos_embedding

        if self.dropout:
            out = self.dropout(out)
        return out


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)
        # Multi-head attention模块
        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)
        #  MLP模块
        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__()
        # 类别个数
        self.num_classes = num_classes
        # embed_dim默认tansformer的base 768
        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
        # 源码distilled是为了其他任务,分类暂时不考虑
        self.num_tokens = 2 if distilled else 1
        # LayerNorm:对每单个batch进行的归一化
        norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
        # act_layer默认tansformer的GELU
        act_layer = act_layer or nn.GELU
        # embed_layer默认是patch embedding,在其他应用中应该会有其他选择
        # patch embedding过程
        self.patch_embed = embed_layer(img_size=img_size, patch_size=patch_size, in_c=in_c, embed_dim=embed_dim)
        # patche个数
        num_patches = self.patch_embed.num_patches
        # class token
        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
        # positional embedding过程
        self.pos_embedding = PositionEmbs(num_patches, embed_dim, drop_ratio)

        # self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
        # self.pos_drop = nn.Dropout(p=drop_ratio)

        # depth是Block的个数
        # 不同block层数 drop_ratio的概率不同,越深度越高
        dpr = [x.item() for x in torch.linspace(0, drop_path_ratio, depth)]  # stochastic depth decay rule
        # blocks搭建
        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
        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)
        # self.dist_token暂时可以忽略
        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_embedding(x)
        # 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

总结

尽可能简单、详细的介绍了深度可分卷积的原理和卷积过程,讲解了ViT模型的结构和pytorch代码。文章来源地址https://www.toymoban.com/news/detail-478324.html

到了这里,关于【图像分类】【深度学习】ViT算法Pytorch代码讲解的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处: 如若内容造成侵权/违法违规/事实不符,请点击违法举报进行投诉反馈,一经查实,立即删除!

领支付宝红包 赞助服务器费用

相关文章

  • 第62步 深度学习图像识别:多分类建模(Pytorch)

    一、写在前面 上期我们基于TensorFlow环境做了图像识别的多分类任务建模。 本期以健康组、肺结核组、COVID-19组、细菌性(病毒性)肺炎组为数据集,基于Pytorch环境,构建SqueezeNet多分类模型,因为它建模速度快。 同样,基于GPT-4辅助编程,这次改写过程就不展示了。 二、多

    2024年02月11日
    浏览(40)
  • 第64步 深度学习图像识别:多分类建模误判病例分析(Pytorch)

    一、写在前面 上期我们基于TensorFlow环境介绍了多分类建模的误判病例分析。 本期以健康组、肺结核组、COVID-19组、细菌性(病毒性)肺炎组为数据集,基于Pytorch环境,构建SqueezeNet多分类模型,分析误判病例,因为它建模速度快。 同样,基于GPT-4辅助编程。 二、误判病例分

    2024年02月10日
    浏览(44)
  • 深度学习图像分类实战——pytorch搭建卷积神经网络(AlexNet, LeNet, ResNet50)进行场景图像分类(详细)

    目录 1  一、实验过程 1.1  实验目的 1.2  实验简介 1.3  数据集的介绍 1.4  一、LeNet5网络模型 1.5  二、AlexNet网络模型 1.6  三、ResNet50(残差网络)网络模型  二、实验代码 导入实验所需要的库  参数配置 数据预处理 重新DataSet 加载数据转为DataLoader函数 可视化一批训练

    2024年02月05日
    浏览(66)
  • 图像分类传统算法和深度学习算法简单介绍

    图像分类是计算机视觉领域的一项基本任务,旨在根据输入图像将其预测到一个或多个类别中。本文档将详细介绍一些常用的图像分类算法,包括传统方法和深度学习方法。 在深度学习技术兴起之前,计算机视觉领域的研究者们使用传统的机器学习方法来进行图像分类。这些

    2024年02月16日
    浏览(43)
  • 竞赛 深度学习卷积神经网络垃圾分类系统 - 深度学习 神经网络 图像识别 垃圾分类 算法 小程序

    🔥 优质竞赛项目系列,今天要分享的是 深度学习卷积神经网络垃圾分类系统 该项目较为新颖,适合作为竞赛课题方向,学长非常推荐! 🧿 更多资料, 项目分享: https://gitee.com/dancheng-senior/postgraduate 近年来,随着我国经济的快速发展,国家各项建设都蒸蒸日上,成绩显著。

    2024年02月08日
    浏览(47)
  • pytorch实战-图像分类(二)(模型训练及验证)(基于迁移学习(理解+代码))

    目录 1.迁移学习概念 2.数据预处理  3.训练模型(基于迁移学习) 3.1选择网络,这里用resnet 3.2如果用GPU训练,需要加入以下代码 3.3卷积层冻结模块 3.4加载resnet152模 3.5解释initialize_model函数 3.6迁移学习网络搭建 3.7优化器 3.8训练模块(可以理解为主函数) 3.9开始训练 3.10微调

    2024年02月14日
    浏览(48)
  • 竞赛选题 深度学习卷积神经网络垃圾分类系统 - 深度学习 神经网络 图像识别 垃圾分类 算法 小程序

    🔥 优质竞赛项目系列,今天要分享的是 深度学习卷积神经网络垃圾分类系统 该项目较为新颖,适合作为竞赛课题方向,学长非常推荐! 🧿 更多资料, 项目分享: https://gitee.com/dancheng-senior/postgraduate 近年来,随着我国经济的快速发展,国家各项建设都蒸蒸日上,成绩显著。

    2024年02月07日
    浏览(52)
  • 基于深度学习的裂纹图像分类研究(Matlab代码实现)

     💥💥💞💞 欢迎来到本博客 ❤️❤️💥💥 🏆博主优势: 🌞🌞🌞 博客内容尽量做到思维缜密,逻辑清晰,为了方便读者。 ⛳️ 座右铭: 行百里者,半于九十。 📋📋📋 本文目录如下: 🎁🎁🎁 目录 💥1 概述 📚2 运行结果 🎉3 参考文献 🌈4 Matlab代码实现 基于深

    2024年02月15日
    浏览(43)
  • 图像分类保姆级教程-深度学习入门教程(附代码)

    图像分类是计算机视觉领域中的一个重要任务。它的目的是将输入的图像归类到预定义的类别中。这个任务在过去被认为是非常具有挑战性的,因为图像的特征非常复杂,而且存在很多种不同的变化方式,例如光照、角度、遮挡等等。 然而,随着深度学习的发展,图像分类问

    2024年01月22日
    浏览(56)
  • 度学习pytorch实战六:ResNet50网络图像分类篇自建花数据集图像分类(5类)超详细代码

    1.数据集简介、训练集与测试集划分 2.模型相关知识 3.model.py——定义ResNet50网络模型 4.train.py——加载数据集并训练,训练集计算损失值loss,测试集计算accuracy,保存训练好的网络参数 5.predict.py——利用训练好的网络参数后,用自己找的图像进行分类测试 1.自建数据文件夹

    2024年02月09日
    浏览(41)

觉得文章有用就打赏一下文章作者

支付宝扫一扫打赏

博客赞助

微信扫一扫打赏

请作者喝杯咖啡吧~博客赞助

支付宝扫一扫领取红包,优惠每天领

二维码1

领取红包

二维码2

领红包