基于WIN10的64位系统演示
一、写在前面
(1)MLP-Mixer
MLP-Mixer(Multilayer Perceptron Mixer)是Google在2021年提出的一种新型的视觉模型结构。它的主要特点是完全使用多层感知机(MLP)来处理图像,而不是使用常见的卷积(Convolution)或者自注意力(Self-Attention)机制。
MLP-Mixer的结构主要包括两种类型的层:Token Mixing层和Channel Mixing层。在Token Mixing层中,模型会将图像分割成若干个patch(类似于像素块),然后对这些patch进行处理。在Channel Mixing层中,模型会对每个patch的通道进行处理。这两种类型的层交替堆叠,形成了最终的模型结构。
MLP-Mixer的设计目标是探索除卷积和自注意力之外的其他可能的模型结构,以期在保持性能的同时,降低模型的复杂性和计算成本。实验结果显示,MLP-Mixer在一些图像分类任务上的性能可以与ResNet和Transformer等主流模型相媲美。
然而,需要注意的是,虽然MLP-Mixer在某些方面展现出了很好的性能,但它并不意味着会替代卷积或者自注意力模型。实际上,每种模型都有其适用的场景和优势,MLP-Mixer提供了一个新的视角和工具,供我们处理视觉任务。
(2)MLP-Mixer的码源
本文使用 mlp-mixer-pytorch 库来实现MLP-Mixer。
当然,得先安装这个库:
(a)首先,打开Anaconda Prompt。在开始菜单中找到它,或者直接在搜索栏中输入"Anaconda Prompt"。在打开的Anaconda Prompt中,如果你想在一个特定的环境中安装mlp_mixer_pytorch,你需要先激活这个环境。假设你的环境名为myenv,你可以使用以下命令来激活这个环境:
conda activate myenv
(b)接下来,使用pip来安装mlp_mixer_pytorch库。在Anaconda Prompt中输入以下命令并按回车键:
pip install mlp-mixer-pytorch
二、MLP-Mixer迁移学习代码实战
我们继续胸片的数据集:肺结核病人和健康人的胸片的识别。其中,肺结核病人700张,健康人900张,分别存入单独的文件夹中。
(a)导入包
import copy
import torch
import torchvision
import torchvision.transforms as transforms
from torchvision import models
from torch.utils.data import DataLoader
from torch import optim, nn
from torch.optim import lr_scheduler
import os
import matplotlib.pyplot as plt
import warnings
import numpy as np
warnings.filterwarnings("ignore")
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# 设置GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
(b)导入数据集
import torch
from torchvision import datasets, transforms
import os
# 数据集路径
data_dir = "./MTB"
# 图像的大小
img_height = 256
img_width = 256
# 数据预处理
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(img_height),
transforms.RandomHorizontalFlip(),
transforms.RandomVerticalFlip(),
transforms.RandomRotation(0.2),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize((img_height, img_width)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
# 加载数据集
full_dataset = datasets.ImageFolder(data_dir)
# 获取数据集的大小
full_size = len(full_dataset)
train_size = int(0.7 * full_size) # 假设训练集占80%
val_size = full_size - train_size # 验证集的大小
# 随机分割数据集
torch.manual_seed(0) # 设置随机种子以确保结果可重复
train_dataset, val_dataset = torch.utils.data.random_split(full_dataset, [train_size, val_size])
# 将数据增强应用到训练集
train_dataset.dataset.transform = data_transforms['train']
# 创建数据加载器
batch_size = 32
train_dataloader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=4)
val_dataloader = torch.utils.data.DataLoader(val_dataset, batch_size=batch_size, shuffle=True, num_workers=4)
dataloaders = {'train': train_dataloader, 'val': val_dataloader}
dataset_sizes = {'train': len(train_dataset), 'val': len(val_dataset)}
class_names = full_dataset.classes
(c)导入MLPMixer
from mlp_mixer_pytorch import MLPMixer
num_classes = len(class_names) # 根据数据集的类别数量来设置模型的输出类别数量
# 构建MLP-Mixer模型
model = MLPMixer(
image_size = img_height, # 图像的高和宽
channels = 3, # 图像的通道数
patch_size = 16, # MLP-Mixer的patch大小
dim = 512, # MLP-Mixer的维度
depth = 12, # MLP-Mixer的深度
num_classes = num_classes # 输出类别数量
)
# 将模型移动到GPU
model = model.to(device)
# 打印模型摘要
print(model)
说明:mlp-mixer-pytorch库的主要功能就是提供了一个MLP-Mixer的类,可以通过实例化这个类来创建一个MLP-Mixer模型。在创建模型时,可以通过参数来设置图像的大小、通道数、patch的大小、模型的维度、深度以及输出类别的数量等。
需要注意的是,mlp-mixer-pytorch库提供的MLP-Mixer模型默认是随机初始化的,也就是说并没有加载预训练权重。如果你有MLP-Mixer的预训练权重,可以在创建模型后加载。
(d)编译模型
# 定义损失函数
criterion = nn.CrossEntropyLoss()
# 定义优化器
optimizer = optim.Adam(model.parameters())
# 定义学习率调度器
exp_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)
# 开始训练模型
num_epochs = 20
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
# 初始化记录器
train_loss_history = []
train_acc_history = []
val_loss_history = []
val_acc_history = []
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
# 每个epoch都有一个训练和验证阶段
for phase in ['train', 'val']:
if phase == 'train':
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
# 遍历数据
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device)
labels = labels.to(device)
# 零参数梯度
optimizer.zero_grad()
# 前向
with torch.set_grad_enabled(phase == 'train'):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, labels)
# 只在训练模式下进行反向和优化
if phase == 'train':
loss.backward()
optimizer.step()
# 统计
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
epoch_loss = running_loss / dataset_sizes[phase]
epoch_acc = (running_corrects.double() / dataset_sizes[phase]).item()
# 记录每个epoch的loss和accuracy
if phase == 'train':
train_loss_history.append(epoch_loss)
train_acc_history.append(epoch_acc)
else:
val_loss_history.append(epoch_loss)
val_acc_history.append(epoch_acc)
print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
# 深拷贝模型
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
print()
print('Best val Acc: {:4f}'.format(best_acc))
# 加载最佳模型权重
#model.load_state_dict(best_model_wts)
#torch.save(model, 'shufflenet_best_model.pth')
#print("The trained model has been saved.")
(e)Accuracy和Loss可视化
epoch = range(1, len(train_loss_history)+1)
fig, ax = plt.subplots(1, 2, figsize=(10,4))
ax[0].plot(epoch, train_loss_history, label='Train loss')
ax[0].plot(epoch, val_loss_history, label='Validation loss')
ax[0].set_xlabel('Epochs')
ax[0].set_ylabel('Loss')
ax[0].legend()
ax[1].plot(epoch, train_acc_history, label='Train acc')
ax[1].plot(epoch, val_acc_history, label='Validation acc')
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Accuracy')
ax[1].legend()
#plt.savefig("loss-acc.pdf", dpi=300,format="pdf")
观察模型训练情况:
蓝色为训练集,橙色为验证集。
(f)混淆矩阵可视化以及模型参数
from sklearn.metrics import classification_report, confusion_matrix
import math
import pandas as pd
import numpy as np
import seaborn as sns
from matplotlib.pyplot import imshow
# 定义一个绘制混淆矩阵图的函数
def plot_cm(labels, predictions):
# 生成混淆矩阵
conf_numpy = confusion_matrix(labels, predictions)
# 将矩阵转化为 DataFrame
conf_df = pd.DataFrame(conf_numpy, index=class_names ,columns=class_names)
plt.figure(figsize=(8,7))
sns.heatmap(conf_df, annot=True, fmt="d", cmap="BuPu")
plt.title('Confusion matrix',fontsize=15)
plt.ylabel('Actual value',fontsize=14)
plt.xlabel('Predictive value',fontsize=14)
def evaluate_model(model, dataloader, device):
model.eval() # 设置模型为评估模式
true_labels = []
pred_labels = []
# 遍历数据
for inputs, labels in dataloader:
inputs = inputs.to(device)
labels = labels.to(device)
# 前向
with torch.no_grad():
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
true_labels.extend(labels.cpu().numpy())
pred_labels.extend(preds.cpu().numpy())
return true_labels, pred_labels
# 获取预测和真实标签
true_labels, pred_labels = evaluate_model(model, dataloaders['val'], device)
# 计算混淆矩阵
cm_val = confusion_matrix(true_labels, pred_labels)
a_val = cm_val[0,0]
b_val = cm_val[0,1]
c_val = cm_val[1,0]
d_val = cm_val[1,1]
# 计算各种性能指标
acc_val = (a_val+d_val)/(a_val+b_val+c_val+d_val) # 准确率
error_rate_val = 1 - acc_val # 错误率
sen_val = d_val/(d_val+c_val) # 灵敏度
sep_val = a_val/(a_val+b_val) # 特异度
precision_val = d_val/(b_val+d_val) # 精确度
F1_val = (2*precision_val*sen_val)/(precision_val+sen_val) # F1值
MCC_val = (d_val*a_val-b_val*c_val) / (np.sqrt((d_val+b_val)*(d_val+c_val)*(a_val+b_val)*(a_val+c_val))) # 马修斯相关系数
# 打印出性能指标
print("验证集的灵敏度为:", sen_val,
"验证集的特异度为:", sep_val,
"验证集的准确率为:", acc_val,
"验证集的错误率为:", error_rate_val,
"验证集的精确度为:", precision_val,
"验证集的F1为:", F1_val,
"验证集的MCC为:", MCC_val)
# 绘制混淆矩阵
plot_cm(true_labels, pred_labels)
# 获取预测和真实标签
train_true_labels, train_pred_labels = evaluate_model(model, dataloaders['train'], device)
# 计算混淆矩阵
cm_train = confusion_matrix(train_true_labels, train_pred_labels)
a_train = cm_train[0,0]
b_train = cm_train[0,1]
c_train = cm_train[1,0]
d_train = cm_train[1,1]
acc_train = (a_train+d_train)/(a_train+b_train+c_train+d_train)
error_rate_train = 1 - acc_train
sen_train = d_train/(d_train+c_train)
sep_train = a_train/(a_train+b_train)
precision_train = d_train/(b_train+d_train)
F1_train = (2*precision_train*sen_train)/(precision_train+sen_train)
MCC_train = (d_train*a_train-b_train*c_train) / (math.sqrt((d_train+b_train)*(d_train+c_train)*(a_train+b_train)*(a_train+c_train)))
print("训练集的灵敏度为:",sen_train,
"训练集的特异度为:",sep_train,
"训练集的准确率为:",acc_train,
"训练集的错误率为:",error_rate_train,
"训练集的精确度为:",precision_train,
"训练集的F1为:",F1_train,
"训练集的MCC为:",MCC_train)
# 绘制混淆矩阵
plot_cm(train_true_labels, train_pred_labels)
效果不错:
(g)AUC曲线绘制
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import imshow
from sklearn.metrics import classification_report, confusion_matrix
import seaborn as sns
import pandas as pd
import math
def plot_roc(name, labels, predictions, **kwargs):
fp, tp, _ = metrics.roc_curve(labels, predictions)
plt.plot(fp, tp, label=name, linewidth=2, **kwargs)
plt.plot([0, 1], [0, 1], color='orange', linestyle='--')
plt.xlabel('False positives rate')
plt.ylabel('True positives rate')
ax = plt.gca()
ax.set_aspect('equal')
# 确保模型处于评估模式
model.eval()
train_ds = dataloaders['train']
val_ds = dataloaders['val']
val_pre_auc = []
val_label_auc = []
for images, labels in val_ds:
for image, label in zip(images, labels):
img_array = image.unsqueeze(0).to(device) # 在第0维增加一个维度并将图像转移到适当的设备上
prediction_auc = model(img_array) # 使用模型进行预测
val_pre_auc.append(prediction_auc.detach().cpu().numpy()[:,1])
val_label_auc.append(label.item()) # 使用Tensor.item()获取Tensor的值
auc_score_val = metrics.roc_auc_score(val_label_auc, val_pre_auc)
train_pre_auc = []
train_label_auc = []
for images, labels in train_ds:
for image, label in zip(images, labels):
img_array_train = image.unsqueeze(0).to(device)
prediction_auc = model(img_array_train)
train_pre_auc.append(prediction_auc.detach().cpu().numpy()[:,1]) # 输出概率而不是标签!
train_label_auc.append(label.item())
auc_score_train = metrics.roc_auc_score(train_label_auc, train_pre_auc)
plot_roc('validation AUC: {0:.4f}'.format(auc_score_val), val_label_auc , val_pre_auc , color="red", linestyle='--')
plot_roc('training AUC: {0:.4f}'.format(auc_score_train), train_label_auc, train_pre_auc, color="blue", linestyle='--')
plt.legend(loc='lower right')
#plt.savefig("roc.pdf", dpi=300,format="pdf")
print("训练集的AUC值为:",auc_score_train, "验证集的AUC值为:",auc_score_val)
ROC曲线如下:
这个ROC曲线也是不错的!全部大于95%!
三、写在最后
截至目前,图像分类领域基本就是CNN、Transformer和MLP三足鼎立了。孰优孰劣,还不好说,中庸之道那就是各有千秋。他们之间的两两组合或者一起融合的话,效果又会如何?
四、数据
链接:https://pan.baidu.com/s/15vSVhz1rQBtqNkNp2GQyVw?pwd=x3jf 文章来源:https://www.toymoban.com/news/detail-603646.html
提取码:x3jf 文章来源地址https://www.toymoban.com/news/detail-603646.html
到了这里,关于第54步 深度学习图像识别:MLP-Mixer建模(Pytorch)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!