1.网络架构
分为三个部分：
- Linear Projection of Flattened Patches（Embedding层）
- Transformer Encoder（图右侧有给出更加详细的结构）
- MLP Head（最终用于分类的层结构）
2.论文中的实验结果
3.ViT参数
- Layes是Transformer Encoder中重复堆叠Encoder Block的次数
- Hidden Size是通过Embedding层后每个token的dim（向量的长度）
- MLP size是Transformer Encoder中MLP Block第一个全连接的节点个数（是Hidden Size的四倍）
- Heads代表Transformer中Multi-Head Attention的heads数
4.网络搭建
from functools import partial
from collections import OrderedDict
from turtle import forward
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
# work with diff dim tensors, not just 2D ConvNets
shape = (x.shape[0],)+(1,)*(x.ndim - 1)
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) -> 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) -> 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.
) -> None:
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]
# make torchscript happy (cannot use tensor as tuple)
q, k, v = qkv[0], qkv[1], qkv[2]
# 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) -> None:
super(Mlp, self).__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
) -> None:
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) -> 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
# num_features for consistency with other models
self.num_features = self.embed_dim = embed_dim
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)
# stochastic depth decay rule
dpr = [x.item() for x in torch.linspace(0, drop_path_ratio, depth)]
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
5.网络训练
import os
import math
import argparse
import torch
import torch.optim as optim
import torch.optim.lr_scheduler as lr_scheduler
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
from my_dataset import MyDataSet
from vit_model import vit_base_patch16_224_in21k as create_model
from utils import read_split_data, train_one_epoch, evaluate
def main(args):
device = torch.device(args.device if torch.cuda.is_available() else "cpu")
if os.path.exists("./weights") is False:
os.makedirs("./weights")
tb_writer = SummaryWriter()
train_images_path, train_images_label, val_images_path, val_images_label = read_split_data(
args.data_path)
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])]),
"val": transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])}
# 实例化训练数据集
train_dataset = MyDataSet(images_path=train_images_path,
images_class=train_images_label,
transform=data_transform["train"])
# 实例化验证数据集
val_dataset = MyDataSet(images_path=val_images_path,
images_class=val_images_label,
transform=data_transform["val"])
batch_size = args.batch_size
# number of workers
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
pin_memory=True,
num_workers=nw,
collate_fn=train_dataset.collate_fn)
val_loader = torch.utils.data.DataLoader(val_dataset,
batch_size=batch_size,
shuffle=False,
pin_memory=True,
num_workers=nw,
collate_fn=val_dataset.collate_fn)
model = create_model(num_classes=5, has_logits=False).to(device)
if args.weights != "":
assert os.path.exists(
args.weights), "weights file: '{}' not exist.".format(args.weights)
weights_dict = torch.load(args.weights, map_location=device)
# 删除不需要的权重
del_keys = ['head.weight', 'head.bias'] if model.has_logits \
else ['pre_logits.fc.weight', 'pre_logits.fc.bias', 'head.weight', 'head.bias']
for k in del_keys:
del weights_dict[k]
print(model.load_state_dict(weights_dict, strict=False))
if args.freeze_layers:
for name, para in model.named_parameters():
# 除head, pre_logits外，其他权重全部冻结
if "head" not in name and "pre_logits" not in name:
para.requires_grad_(False)
else:
print("training {}".format(name))
pg = [p for p in model.parameters() if p.requires_grad]
optimizer = optim.SGD(pg, lr=args.lr, momentum=0.9, weight_decay=5E-5)
# Scheduler https://arxiv.org/pdf/1812.01187.pdf
def lf(x): return ((1 + math.cos(x * math.pi / args.epochs)) / 2) * \
(1 - args.lrf) + args.lrf # cosine
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
for epoch in range(args.epochs):
# train
train_loss, train_acc = train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_loader,
device=device,
epoch=epoch)
scheduler.step()
# validate
val_loss, val_acc = evaluate(model=model,
data_loader=val_loader,
device=device,
epoch=epoch)
tags = ["train_loss", "train_acc",
"val_loss", "val_acc", "learning_rate"]
tb_writer.add_scalar(tags[0], train_loss, epoch)
tb_writer.add_scalar(tags[1], train_acc, epoch)
tb_writer.add_scalar(tags[2], val_loss, epoch)
tb_writer.add_scalar(tags[3], val_acc, epoch)
tb_writer.add_scalar(tags[4], optimizer.param_groups[0]["lr"], epoch)
torch.save(model.state_dict(), "./weights/model-{}.pth".format(epoch))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--num_classes', type=int, default=5)
parser.add_argument('--epochs', type=int, default=10)
parser.add_argument('--batch-size', type=int, default=8)
parser.add_argument('--lr', type=float, default=0.001)
parser.add_argument('--lrf', type=float, default=0.01)
# 数据集所在根目录
# https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz
parser.add_argument('--data-path', type=str,
default="./data/flower_photos")
parser.add_argument('--model-name', default='', help='create model name')
# 预训练权重路径，如果不想载入就设置为空字符
parser.add_argument('--weights', type=str, default='./vit_base_patch16_224_in21k.pth',
help='initial weights path')
# 是否冻结权重
parser.add_argument('--freeze-layers', type=bool, default=True)
parser.add_argument('--device', default='cuda:0',
help='device id (i.e. 0 or 0,1 or cpu)')
opt = parser.parse_args(args=[])
main(opt)
6.网络验证
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from vit_model import vit_base_patch16_224_in21k as create_model
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
data_transform = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
])
# load image
img_path = "./tulip.jpg"
assert os.path.exists(img_path),"file:'{}' does not exist.".format(img_path)
img = Image.open(img_path)
plt.imshow(img)
# [N,C,H,W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img,dim=0)
# read class_indict
json_path = "./class_indices.json"
assert os.path.exists(json_path),"file:'{}' does not exist.".format(json_path)
with open(json_path,"r") as f:
class_indict = json.load(f)
# create model
model = create_model(num_classes=5,has_logits=False).to(device)
# load modelweights
model_weight_path = "./weights/model-9.pth"
model.load_state_dict(torch.load(model_weight_path,map_location=device))
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output,dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class:{} prob:{:.3f}".format(class_indict[str(predict_cla)],predict[predict_cla].numpy())
plt.title(print_res)
for i in range(len(predict)):
print("class:{:10} prob:{:.3}".format(class_indict[str(i)],predict[i].numpy()))
plt.show()
if __name__ == '__main__':
main()7.预测结果
扫一扫
1373
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
