"""
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):
"""
深度随机
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):
"""
Patch Embedding 将输入图片拉长
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])
# 224/16
self.num_patches = self.grid_size[0] * self.grid_size[1]
# 14*14*768
#然后卷积函数 卷积核16*16 个数768
self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size)
#当有模型中有norm_layer,就初始化,如果没有不处理
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高, W宽 -> [B, C, HW] 高度宽度展平
# transpose: [B, C, HW] -> [B, HW, C]//有 transpose:
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,#生成qkv的时候,是否使用偏置于
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#公式
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):#正向传播
# [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)
# 通过上一行得到[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)拿到qkv
# 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#@是矩阵乘法
attn = attn.softmax(dim=-1)#dim=-1行处理
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.,#原论文drop_pote
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)))
#图中first加和
x = x + self.drop_path(self.mlp(self.norm2(x)))
#图中second加和
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):#embed_layer就是对应PatchEmbed depth就是第一张图中的L
"""
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#1
norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)#norm_layer
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#构建patch的层
#加class
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
# 加位置编码器
self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
self.pos_drop = nn.Dropout(p=drop_ratio)
# 加上位置编码器之后Dropout层
# 堆叠L
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()#如果
# 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_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
整个项 目(模型是训练好的)的资源已经绑定这篇文章,自定义训练集的教程在pytorch中自定义dataset读取数据_哔哩哔哩_bilibili,但是我们今天主要了解一下关于vit的代码
原理部分主要是这图上的内容,我们将图像分为16*16的patche,然后想办法把它转化transfor可以接受的形式(196*768)因为要+Classtoken所以我们要夸大一行(196*768)
class PatchEmbed(nn.Module): """ Patch Embedding 将输入图片拉长 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]) # 224/16 self.num_patches = self.grid_size[0] * self.grid_size[1] # 14*14*768 #然后卷积函数 卷积核16*16 个数768 self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size) #当有模型中有norm_layer,就初始化,如果没有不处理 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高, W宽 -> [B, C, HW] 高度宽度展平 # transpose: [B, C, HW] -> [B, HW, C]//有 transpose: x = self.proj(x).flatten(2).transpose(1, 2) x = self.norm(x) return x
然后我们要想着如何写Attention
class Attention(nn.Module): def __init__(self, dim, # 输入token的dim num_heads=8, qkv_bias=False,#生成qkv的时候,是否使用偏置于 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#公式 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):#正向传播 # [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) # 通过上一行得到[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)拿到qkv # 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#@是矩阵乘法 attn = attn.softmax(dim=-1)#dim=-1行处理 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
然后思考MLP层
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 比较简单
然后用一个encode bloke将这两个模块放在一块
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.,#原论文drop_pote 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))) #图中first加和 x = x + self.drop_path(self.mlp(self.norm2(x))) #图中second加和 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):#embed_layer就是对应PatchEmbed """ 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#1 norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)#norm_layer 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#构建patch的层 #加class 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 # 加位置编码器 self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim)) self.pos_drop = nn.Dropout(p=drop_ratio) # 加上位置编码器之后Dropout层 # 堆叠depth 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()#如果 # 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权重初始化 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)#拼接 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)#layernore 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 = self.head(x) #self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity(),然后输出num_classes个节点 return x