第R8周：RNN实现阿尔茨海默病诊断（pytorch）

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊
数据集包含 2,149 名患者的广泛健康信息，每名患者的 ID 范围从 4751 到 6900 不等。该数据集包括人口统计详细信息、生活方式因素、病史、临床测量、认知和功能评估、症状以及阿尔茨海默病的诊断。

一、前期准备工作

1. 设置硬件设备

import numpy as np
import pandas as pd
import torch
from torch import nn
import torch.nn.functional as F
import seaborn as sns#设置GPU训练，也可以使用CPU
device=torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

在这里插入图片描述

2. 导入数据

df = pd.read_csv("alzheimers_disease_data.csv")
# 删除第一列和最后一列
df = df.iloc[:, 1:-1]
df

在这里插入图片描述

二、构建数据集

1. 标准化


from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_splitX = df.iloc[:,:-1]
y = df.iloc[:,-1]# 将每一列特征标准化为标准正太分布，注意，标准化是针对每一列而言的
sc = StandardScaler()
X  = sc.fit_transform(X)

2. 划分数据集

X = torch.tensor(np.array(X), dtype=torch.float32)
y = torch.tensor(np.array(y), dtype=torch.int64)X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.1, random_state = 1)X_train.shape, y_train.shape

在这里插入图片描述

3. 构建数据加载器

from torch.utils.data import TensorDataset, DataLoadertrain_dl = DataLoader(TensorDataset(X_train, y_train),batch_size=64, shuffle=False)test_dl  = DataLoader(TensorDataset(X_test, y_test),batch_size=64, shuffle=False)

三、模型训练

在这里插入图片描述

1. 构建模型

class model_rnn(nn.Module):def __init__(self):super(model_rnn, self).__init__()self.rnn0 = nn.RNN(input_size=32, hidden_size=200, num_layers=1, batch_first=True)self.fc0   = nn.Linear(200, 50)self.fc1   = nn.Linear(50, 2)def forward(self, x):out, hidden1 = self.rnn0(x) out    = self.fc0(out) out    = self.fc1(out) return out   model = model_rnn().to(device)
model

在这里插入图片描述

2. 定义训练函数

# 训练循环
def train(dataloader, model, loss_fn, optimizer):size = len(dataloader.dataset)  # 训练集的大小num_batches = len(dataloader)   # 批次数目, (size/batch_size，向上取整)train_loss, train_acc = 0, 0  # 初始化训练损失和正确率for X, y in dataloader:  # 获取图片及其标签X, y = X.to(device), y.to(device)# 计算预测误差pred = model(X)          # 网络输出loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失# 反向传播optimizer.zero_grad()  # grad属性归零loss.backward()        # 反向传播optimizer.step()       # 每一步自动更新# 记录acc与losstrain_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= sizetrain_loss /= num_batchesreturn train_acc, train_loss

3. 定义测试函数

def test (dataloader, model, loss_fn):size        = len(dataloader.dataset)  # 测试集的大小num_batches = len(dataloader)          # 批次数目, (size/batch_size，向上取整)test_loss, test_acc = 0, 0# 当不进行训练时，停止梯度更新，节省计算内存消耗with torch.no_grad():for imgs, target in dataloader:imgs, target = imgs.to(device), target.to(device)# 计算losstarget_pred = model(imgs)loss        = loss_fn(target_pred, target)test_loss += loss.item()test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()test_acc  /= sizetest_loss /= num_batchesreturn test_acc, test_loss

4. 正式训练模型

loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 5e-5   # 学习率
opt        = torch.optim.Adam(model.parameters(),lr=learn_rate)
epochs     = 50train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []for epoch in range(epochs):model.train()epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)model.eval()epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)train_acc.append(epoch_train_acc)train_loss.append(epoch_train_loss)test_acc.append(epoch_test_acc)test_loss.append(epoch_test_loss)# 获取当前的学习率lr = opt.state_dict()['param_groups'][0]['lr']template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss, lr))print("="*20, 'Done', "="*20)

在这里插入图片描述

四、模型评估

1. Loss与Accuracy图

import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显示负号
plt.rcParams['figure.dpi']         = 200        #分辨率from datetime import datetime
current_time = datetime.now() # 获取当前时间epochs_range = range(epochs)plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

在这里插入图片描述

五、个人总结

在这个项目中，我实现了一个简单的循环神经网络（RNN）模型，用于处理序列数据。该模型的核心是一个单层的RNN，输入特征维度为32，隐藏层维度为200。RNN的输出通过两个全连接层（fc0和fc1）进行进一步处理，最终输出维度为2，适用于二分类任务。

改进后的代码示例

class model_rnn_improved(nn.Module):def __init__(self):super(model_rnn_improved, self).__init__()self.rnn0 = nn.LSTM(input_size=32, hidden_size=200, num_layers=2, batch_first=True, bidirectional=True)self.dropout = nn.Dropout(0.5)self.ln = nn.LayerNorm(200)self.fc0 = nn.Sequential(nn.Linear(400, 100),  # 双向LSTM输出维度为hidden_size * 2nn.ReLU(),nn.Linear(100, 50))self.fc1 = nn.Linear(50, 2)def forward(self, x):out, (hidden, cell) = self.rnn0(x)out = self.dropout(out)out = self.ln(out)out = self.fc0(out)out = self.fc1(out)return out   model = model_rnn_improved().to(device)
model