🍨 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
🏡 我的环境：
语言环境：Python3.10
编译器：Jupyter Lab
深度学习环境：torch==2.5.1 torchvision==0.20.1
------------------------------分割线---------------------------------
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
df = pd.read_csv("data/heart.csv")
df
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
X = 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)
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
from torch.utils.data import TensorDataset, DataLoader
train_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)
class model_rnn(nn.Module):
def __init__(self):
super(model_rnn, self).__init__()
self.rnn0 = nn.RNN(input_size=13 ,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
# 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loss
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss
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loss
target_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 /= size
test_loss /= num_batches
return test_acc, test_loss
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt = torch.optim.Adam(model.parameters(),lr=learn_rate)
epochs = 50
train_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)
import matplotlib.pyplot as plt
from datetime import datetime
#隐藏警告
import warnings
warnings.filterwarnings("ignore") #忽略警告信息
current_time = datetime.now() # 获取当前时间
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
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()
print("==============输入数据Shape为==============")
print("X_test.shape：",X_test.shape)
print("y_test.shape：",y_test.shape)
pred = model(X_test.to(device)).argmax(1).cpu().numpy()
print("\n==============输出数据Shape为==============")
print("pred.shape：",pred.shape)
import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
# 计算混淆矩阵
cm = confusion_matrix(y_test, pred)
plt.figure(figsize=(6,5))
plt.suptitle('')
sns.heatmap(cm, annot=True, fmt="d", cmap="Blues")
# 修改字体大小
plt.xticks(fontsize=10)
plt.yticks(fontsize=10)
plt.title("Confusion Matrix", fontsize=12)
plt.xlabel("Predicted Label", fontsize=10)
plt.ylabel("True Label", fontsize=10)
# 显示图
plt.tight_layout() # 调整布局防止重叠
plt.show()
test_X = X_test[0].reshape(1, -1) # X_test[0]即我们的输入数据
pred = model(test_X.to(device)).argmax(1).item()
print("模型预测结果为：",pred)
print("=="*20)
print("0：不会患心脏病")
print("1：可能患心脏病")
测试集预测准确率为87.1%，为了进一步提高模型性能，做了如下改进：
1、调整数据加载方式（启用Shuffle），打乱训练数据顺序，使每个batch的数据分布更均匀，提升模型泛化能力。
# 修改前（shuffle=False）
train_dl = DataLoader(..., shuffle=False)
# 修改后
train_dl = DataLoader(..., shuffle=True)2、调整优化器和学习率
# 修改前
learn_rate = 1e-4
opt = torch.optim.Adam(model.parameters(), lr=learn_rate)
# 修改后
opt = torch.optim.Adam(model.parameters(), lr=1e-4, weight_decay=1e-5) # 增加L2正则
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(opt, 'max', patience=5) # 动态调整学习率
修改之后预测率最高超过了90%，预测准确率也有所提高
------------------小结---------------------------
循环神经网络（RNN）是一种专门处理序列数据的神经网络模型，其核心特点可归纳如下：
一、序列建模能力
RNN通过循环连接结构处理序列输入（如文本、语音、时间序列），每个时间步的隐藏状态（hidden state）不仅依赖当前输入，还继承前一时间步的状态。这种设计使其能够捕捉时间依赖性，例如句子中单词的上下文关系或股价的历史趋势。
二、参数共享机制
所有时间步共享同一组权重参数（如输入-隐藏层和隐藏-隐藏层矩阵），显著减少模型复杂度并提升泛化能力。这一特性使其能灵活处理变长序列，无需为不同长度输入单独设计网络。
三、记忆性与动态状态
RNN通过隐藏状态的递归更新实现记忆功能，理论上可保留无限长的历史信息。例如，在机器翻译中，模型能利用前文信息生成连贯的译文。但实际中受限于梯度问题，长程依赖能力较弱。
