PVT(Pyramid Vision Transformer)学习记录

引言与启发

自从ViT之后，关于vision transformer的研究呈井喷式爆发，从思路上分主要沿着两大个方向，一是提升ViT在图像分类的效果；二就是将ViT应用在其它图像任务中，比如分割和检测任务上，这里介绍的PVT（Pyramid Vision Transformer）就属于后者。PVT相比ViT引入了和CNN类似的金字塔结构，使得PVT像CNN那样作为backbone应用在dense prediction任务（分割和检测等）。

设计思路

PVT的设计思路是目前在CNN中特征要想获取多尺度特征可以通过FPN（特征金字塔网络），那么Transformer是否也可以这样做呢，由此提出了PVT（Pyramid Vision Transformer）这个模块可以很轻松的与DETR类模型相结合从而实现端到端检测。
其实PVT的思想很简单，就是将Transformer与FPN相结合，通过卷积来将特征图变小，进而减少计算。

结合上图，我们可以看到其主要创新点为：

相较于ViT，其使用了细粒度的图像patch，可以学习高分辨率的特征表示
借鉴于CNN，设计了金字塔结构，可以进行多尺度特征的学习
引入了SRA模块，主要用于改进多头注意力模块来减少QKV的计算量

模型流程

模型的初始化参数，在后面会对其进行讲解

def pvt_small():model = PyramidVisionTransformer(patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4], qkv_bias=True,norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1])

首先我们的输入图片为torch.Size([2, 3, 224, 224])，即batch-size=2，channel=3，W=H=224
随后送入stage1：

        x, (H, W) = self.patch_embed1(x)pos_embed1 = self._get_pos_embed(self.pos_embed1, self.patch_embed1, H, W)x = x + pos_embed1x = self.pos_drop1(x)for blk in self.block1:x = blk(x, H, W)x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()outs.append(x)

Patch操作

首先对输入图片进行patch操作，其完成对图片的切分以及线性映射（维度转换）
stage1时的patchEmbed定义为：

PatchEmbed((proj): Conv2d(3, 64, kernel_size=(4, 4), stride=(4, 4))(norm): LayerNorm((64,), eps=1e-05, elementwise_affine=True)
)

  def forward(self, x):B, C, H, W = x.shapex = self.proj(x).flatten(2).transpose(1, 2)x = self.norm(x)H, W = H // self.patch_size[0], W // self.patch_size[1]return x, (H, W)

可以看到，送入patch_embed模块的向量首先获取其各个参数（B，C，W，H)
随后调用self.proj操作

self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)

其为一个二维卷积：Conv2d(3, 64, kernel_size=(4, 4), stride=(4, 4))

卷积层输出尺寸： o = ⌊(i + 2p - k) / s⌋ + 1

padding默认为0，则输出大小为【2，64，56，56】
随后经过flatten展平操作得到【2，64，56X56】
随后transpose进行维度转换为：【2，56X56，64】即torch.Size([2, 3136, 64])
随后便是归一化操作以及对W，H大小改变并返还，此时W=H=56

位置编码

位置编码方面其使用的是可学习位置编码方式。
pos_embed是由下列方式初始化得到的，此时大小为：torch.Size([1, 3136, 64])

self.pos_embed1 = nn.Parameter(torch.zeros(1, self.patch_embed1.num_patches, embed_dims[0]))

随后进行处理：

pos_embed1 = self._get_pos_embed(self.pos_embed1, self.patch_embed1, H, W)

处理过程为：

def _get_pos_embed(self, pos_embed, patch_embed, H, W):if H * W == self.patch_embed1.num_patches:return pos_embedelse:return F.interpolate(pos_embed.reshape(1, patch_embed.H, patch_embed.W, -1).permute(0, 3, 1, 2),size=(H, W), mode="bilinear").reshape(1, -1, H * W).permute(0, 2, 1)

紧接着将处理的语义特征信息与位置编码信息直接相加，注意：
此时的pos_embed1为：torch.Size([1, 3136, 64]) x 为 torch.Size([2, 3136, 64])，也是可以相加的

x = x + pos_embed1

如下测试，利用广播机制扩充维度进行计算

import torch
data = torch.randn((2, 1, 2, 2))
data1 = torch.randn((1, 1, 2, 2))
print(data)
print(data1)
print(data+data1)

注意力计算

进入注意力计算模块，每个stage中的注意力层有多个

for blk in self.block1:x = blk(x, H, W)

随后开始注意力的计算：
Q构造：经过一个linear进行构造，并进行分头计算（多头注意力）

self.q = nn.Linear(dim, dim, bias=qkv_bias)q = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)

得到q为：torch.Size([2, 1, 3136, 64])
随后进入到其创新的模块了，其是对K，V进行下采样，减小其数量：self.sr_ratio是缩小规模
x为torch.Size([2, 3136, 64])，首先经过permute进行维度变换为torch.Size([2, 64,3136]),随后经过reshape为：torch.Size([2, 64, 56, 56])

x_ = x.permute(0, 2, 1).reshape(B, C, H, W)

然后通过卷积操作进行降维：

self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio)
x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)

self.sr为：Conv2d(64, 64, kernel_size=(8, 8), stride=(8, 8))
通过 卷积层输出尺寸： o = ⌊(i + 2p - k) / s⌋ + 1
可得输出尺寸为：7即49 对应的tensor为：torch.Size([2, 49, 64])

然后便是使用x_来获取kv

self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias)
kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)

得到kv为torch.Size([2, 2, 1, 49, 64])，k,v皆为torch.Size([2, 1, 49, 64])，但数值上不同
完整代码如下：

  if self.sr_ratio > 1:x_ = x.permute(0, 2, 1).reshape(B, C, H, W)x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)x_ = self.norm(x_)kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)else:kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)

然后便是进行一系列计算了：

x = (attn @ v).transpose(1, 2).reshape(B, N, C)
@实际为x@y=x.matmul(y)

最终计算得到注意力机制的结果x结果仍为torch.Size([2, 3136, 64])

注意力机制模块完整代码如下：

def forward(self, x, H, W):B, N, C = x.shapeq = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)if self.sr_ratio > 1:x_ = x.permute(0, 2, 1).reshape(B, C, H, W)x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)x_ = self.norm(x_)kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)else:kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)k, v = kv[0], kv[1]attn = (q @ k.transpose(-2, -1)) * self.scaleattn = attn.softmax(dim=-1)attn = self.attn_drop(attn)x = (attn @ v).transpose(1, 2).reshape(B, N, C)x = self.proj(x)x = self.proj_drop(x)return x

最终得到x经过reshape恢复为2维结果，再次进入下一个stage进行计算

x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()

随后经过卷积缩小特征图大小，在空间上的损失由维度进行补偿，下一个阶段x为：

torch.Size([2, 784, 128])

通过依次该过程，便将其大小进行缩减，通过也将其获取了多尺度信息。值得注意的是，只有stage1上patch=4，在后面的三个stage上patch都为2，这样也就参考卷积，其是一个二倍大小的关系。

总体来看，Pyramid Version Transformer的设计还是较为容易理解的，下面博主从代码入手，来详细讲解PVT的构建过程。

完整代码如下：

import torch
import torch.nn as nn
import torch.nn.functional as F
from functools import partialfrom timm.models.layers import DropPath, to_2tuple, trunc_normal_
from timm.models.registry import register_model
from timm.models.vision_transformer import _cfgclass Mlp(nn.Module):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_featureshidden_features = hidden_features or in_featuresself.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 xclass Attention(nn.Module):def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., sr_ratio=1):super().__init__()assert dim % num_heads == 0, f"dim{dim}should be divided by num_heads{num_heads}."self.dim = dimself.num_heads = num_headshead_dim = dim // num_headsself.scale = qk_scale or head_dim ** -0.5self.q = nn.Linear(dim, dim, bias=qkv_bias)self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias)self.attn_drop = nn.Dropout(attn_drop)self.proj = nn.Linear(dim, dim)self.proj_drop = nn.Dropout(proj_drop)self.sr_ratio = sr_ratioif sr_ratio > 1:self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio)self.norm = nn.LayerNorm(dim)def forward(self, x, H, W):B, N, C = x.shapeq = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)if self.sr_ratio > 1:x_ = x.permute(0, 2, 1).reshape(B, C, H, W)x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1)x_ = self.norm(x_)kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)else:kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)k, v = kv[0], kv[1]attn = (q @ k.transpose(-2, -1)) * self.scaleattn = attn.softmax(dim=-1)attn = self.attn_drop(attn)x = (attn @ v).transpose(1, 2).reshape(B, N, C)x = self.proj(x)x = self.proj_drop(x)return xclass Block(nn.Module):def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, sr_ratio=1):super().__init__()self.norm1 = norm_layer(dim)self.attn = Attention(dim,num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,attn_drop=attn_drop, proj_drop=drop, sr_ratio=sr_ratio)# NOTE: drop path for stochastic depth, we shall see if this is better than dropout hereself.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, H, W):x = x + self.drop_path(self.attn(self.norm1(x), H, W))x = x + self.drop_path(self.mlp(self.norm2(x)))return xclass PatchEmbed(nn.Module):""" Image to Patch Embedding"""def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768):super().__init__()img_size = to_2tuple(img_size)patch_size = to_2tuple(patch_size)self.img_size = img_sizeself.patch_size = patch_sizeassert img_size[0] % patch_size[0] == 0 and img_size[1] % patch_size[1] == 0, \f"img_size{img_size}should be divided by patch_size{patch_size}."self.H, self.W = img_size[0] // patch_size[0], img_size[1] // patch_size[1]self.num_patches = self.H * self.Wself.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)self.norm = nn.LayerNorm(embed_dim)def forward(self, x):B, C, H, W = x.shapex = self.proj(x).flatten(2).transpose(1, 2)x = self.norm(x)H, W = H // self.patch_size[0], W // self.patch_size[1]return x, (H, W)class PyramidVisionTransformer(nn.Module):def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dims=[64, 128, 256, 512],num_heads=[1, 2, 4, 8], mlp_ratios=[4, 4, 4, 4], qkv_bias=False, qk_scale=None, drop_rate=0.,attn_drop_rate=0., drop_path_rate=0., norm_layer=nn.LayerNorm,depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1], F4=False):super().__init__()self.num_classes = num_classesself.depths = depthsself.F4 = F4# patch_embedself.patch_embed1 = PatchEmbed(img_size=img_size, patch_size=patch_size, in_chans=in_chans,embed_dim=embed_dims[0])self.patch_embed2 = PatchEmbed(img_size=img_size // 4, patch_size=2, in_chans=embed_dims[0],embed_dim=embed_dims[1])self.patch_embed3 = PatchEmbed(img_size=img_size // 8, patch_size=2, in_chans=embed_dims[1],embed_dim=embed_dims[2])self.patch_embed4 = PatchEmbed(img_size=img_size // 16, patch_size=2, in_chans=embed_dims[2],embed_dim=embed_dims[3])# pos_embedself.pos_embed1 = nn.Parameter(torch.zeros(1, self.patch_embed1.num_patches, embed_dims[0]))self.pos_drop1 = nn.Dropout(p=drop_rate)self.pos_embed2 = nn.Parameter(torch.zeros(1, self.patch_embed2.num_patches, embed_dims[1]))self.pos_drop2 = nn.Dropout(p=drop_rate)self.pos_embed3 = nn.Parameter(torch.zeros(1, self.patch_embed3.num_patches, embed_dims[2]))self.pos_drop3 = nn.Dropout(p=drop_rate)self.pos_embed4 = nn.Parameter(torch.zeros(1, self.patch_embed4.num_patches + 1, embed_dims[3]))self.pos_drop4 = nn.Dropout(p=drop_rate)# transformer encoderdpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rulecur = 0self.block1 = nn.ModuleList([Block(dim=embed_dims[0], num_heads=num_heads[0], mlp_ratio=mlp_ratios[0], qkv_bias=qkv_bias, qk_scale=qk_scale,drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,sr_ratio=sr_ratios[0])for i in range(depths[0])])cur += depths[0]self.block2 = nn.ModuleList([Block(dim=embed_dims[1], num_heads=num_heads[1], mlp_ratio=mlp_ratios[1], qkv_bias=qkv_bias, qk_scale=qk_scale,drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,sr_ratio=sr_ratios[1])for i in range(depths[1])])cur += depths[1]self.block3 = nn.ModuleList([Block(dim=embed_dims[2], num_heads=num_heads[2], mlp_ratio=mlp_ratios[2], qkv_bias=qkv_bias, qk_scale=qk_scale,drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,sr_ratio=sr_ratios[2])for i in range(depths[2])])cur += depths[2]self.block4 = nn.ModuleList([Block(dim=embed_dims[3], num_heads=num_heads[3], mlp_ratio=mlp_ratios[3], qkv_bias=qkv_bias, qk_scale=qk_scale,drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[cur + i], norm_layer=norm_layer,sr_ratio=sr_ratios[3])for i in range(depths[3])])# init weightstrunc_normal_(self.pos_embed1, std=.02)trunc_normal_(self.pos_embed2, std=.02)trunc_normal_(self.pos_embed3, std=.02)trunc_normal_(self.pos_embed4, std=.02)self.apply(self._init_weights)def init_weights(self, pretrained=True):import torch# if isinstance(pretrained, str):#     logger = get_root_logger()#     load_checkpoint(self, pretrained, map_location='cpu', strict=False, logger=logger)def reset_drop_path(self, drop_path_rate):dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(self.depths))]cur = 0for i in range(self.depths[0]):self.block1[i].drop_path.drop_prob = dpr[cur + i]cur += self.depths[0]for i in range(self.depths[1]):self.block2[i].drop_path.drop_prob = dpr[cur + i]cur += self.depths[1]for i in range(self.depths[2]):self.block3[i].drop_path.drop_prob = dpr[cur + i]cur += self.depths[2]for i in range(self.depths[3]):self.block4[i].drop_path.drop_prob = dpr[cur + i]def _init_weights(self, m):if isinstance(m, nn.Linear):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 _get_pos_embed(self, pos_embed, patch_embed, H, W):if H * W == self.patch_embed1.num_patches:return pos_embedelse:return F.interpolate(pos_embed.reshape(1, patch_embed.H, patch_embed.W, -1).permute(0, 3, 1, 2),size=(H, W), mode="bilinear").reshape(1, -1, H * W).permute(0, 2, 1)def forward_features(self, x):outs = []B = x.shape[0]# stage 1x, (H, W) = self.patch_embed1(x)pos_embed1 = self._get_pos_embed(self.pos_embed1, self.patch_embed1, H, W)x = x + pos_embed1x = self.pos_drop1(x)for blk in self.block1:x = blk(x, H, W)x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()outs.append(x)# stage 2x, (H, W) = self.patch_embed2(x)pos_embed2 = self._get_pos_embed(self.pos_embed2, self.patch_embed2, H, W)x = x + pos_embed2x = self.pos_drop2(x)for blk in self.block2:x = blk(x, H, W)x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()outs.append(x)# stage 3x, (H, W) = self.patch_embed3(x)pos_embed3 = self._get_pos_embed(self.pos_embed3, self.patch_embed3, H, W)x = x + pos_embed3x = self.pos_drop3(x)for blk in self.block3:x = blk(x, H, W)x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()outs.append(x)# stage 4x, (H, W) = self.patch_embed4(x)pos_embed4 = self._get_pos_embed(self.pos_embed4[:, 1:], self.patch_embed4, H, W)x = x + pos_embed4x = self.pos_drop4(x)for blk in self.block4:x = blk(x, H, W)x = x.reshape(B, H, W, -1).permute(0, 3, 1, 2).contiguous()outs.append(x)return outsdef forward(self, x):x = self.forward_features(x)if self.F4:x = x[3:4]return xdef _conv_filter(state_dict, patch_size=16):""" convert patch embedding weight from manual patchify + linear proj to conv"""out_dict = {}for k, v in state_dict.items():if 'patch_embed.proj.weight' in k:v = v.reshape((v.shape[0], 3, patch_size, patch_size))out_dict[k] = vreturn out_dictdef pvt_small():model = PyramidVisionTransformer(patch_size=4, embed_dims=[64, 128, 320, 512], num_heads=[1, 2, 5, 8], mlp_ratios=[8, 8, 4, 4], qkv_bias=True,norm_layer=partial(nn.LayerNorm, eps=1e-6), depths=[3, 4, 6, 3], sr_ratios=[8, 4, 2, 1])return modelmodel = pvt_small()
data = torch.randn((2, 3, 224, 224))
feature = model(data)
print(model)
for out in feature:print(out.shape)