神经网络应用示例--鸢尾花分类

data_loader.py

from torch.utils.data import Dataset
import os
import pandas as pd
import numpy as np
import torch

class IrisDataLoader(Dataset):
    def __init__(self, data_path):
        self.data_path = data_path

        # 检查文件路径是否存在
        if not os.path.exists(self.data_path):
            raise FileNotFoundError(f"Data path {self.data_path} does not exist.")

        try:
            # 读取 CSV 文件
            df = pd.read_csv(self.data_path, names=[0, 1, 2, 3, 4])
        except Exception as e:
            # 处理读取文件时可能出现的异常
            raise ValueError(f"Error reading file: {e}")

        # 映射类别标签为整数
        d = {"Iris-setosa": 0, "Iris-versicolor": 1, "Iris-virginica": 2}
        df[4] = df[4].map(d)

        # 分离特征和标签
        data = df.iloc[:, :4]
        label = df.iloc[:, 4:]

        # 防止标准差为零导致除零错误
        epsilon = 1e-8
        # 对每列（特征）进行标准化处理
        data = (data - data.mean(axis=0)) / (data.std(axis=0) + epsilon)

        # 将数据转换为 numpy 数组并指定数据类型
        self.data = torch.from_numpy(np.array(data, dtype=np.float32))
        self.label = torch.from_numpy(np.array(label, dtype=np.int64)).long()

        # 记录数据集大小
        self.data_num = len(label)
        print(f"Dataset size: {self.data_num}")

    def __len__(self):
        return self.data_num

    def __getitem__(self, index):
        return self.data[index], self.label[index]

nn.py

import os
import sys
from torch.utils.data import DataLoader
from tqdm import tqdm

import torch
import torch.nn as nn
import torch.optim as optim

from data_loader import IrisDataLoader

class NN(nn.Module):
    def __init__(self, input_size, hidden_size1, hidden_size2, output_size):
        super().__init__()
        self.fc1 = nn.Linear(input_size, hidden_size1)
        self.relu1 = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size1, hidden_size2)
        self.relu2 = nn.ReLU()
        self.fc3 = nn.Linear(hidden_size2, output_size)

    def forward(self, x):
        x = self.fc1(x)
        x = self.relu1(x)
        x = self.fc2(x)
        x = self.relu2(x)
        x = self.fc3(x)
        return x
    
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

custom_dataset = IrisDataLoader("iris.data")
train_size = int(len(custom_dataset) * 0.7)
val_size = int(len(custom_dataset) * 0.2)
test_size = len(custom_dataset) - train_size - val_size

train_dataset, val_dataset, test_dataset = torch.utils.data.random_split(custom_dataset, [train_size, val_size, test_size])

train_loader = DataLoader(train_dataset, batch_size=16, shuffle=True)
val_loader = DataLoader(val_dataset, batch_size=1, shuffle=False)
test_loader = DataLoader(test_dataset, batch_size=1, shuffle=False)

print("Train dataset size:", len(train_dataset))
print("Validation dataset size:", len(val_dataset))
print("Test dataset size:", len(test_dataset))

# 定义一个推理函数，来计算并返回准确率
def infer(model, dataloader, device):
    model.eval()
    acc_num = 0
    total_samples = 0
    with torch.no_grad():
        for data in dataloader:
            datas, label = data
            outputs = model(datas.to(device))
            predict_y = torch.max(outputs, dim=1)[1]
            acc_num += torch.eq(predict_y, label.to(device)).sum().item()
            total_samples += label.size(0)
    acc = acc_num / total_samples
    return acc

def main(lr=0.005, epochs=20):
    input_size = 4
    hidden_size1 = 10
    hidden_size2 = 5
    output_size = 3

    model = NN(input_size, hidden_size1, hidden_size2, output_size).to(device)
    loss_f = nn.CrossEntropyLoss()

    pg = [p for p in model.parameters() if p.requires_grad]
    optimizer = optim.Adam(pg, lr=lr)

    save_path = os.path.join(os.getcwd(), "results/weights")
    if not os.path.exists(save_path):
        os.makedirs(save_path)

    for epoch in range(epochs):
        model.train()
        acc_num = torch.zeros(1).to(device)
        sample_num = 0

        train_bar = tqdm(train_loader, file=sys.stdout, ncols=100)
        for datas in train_bar:
            data, label = datas
            label = label.squeeze(-1)
            sample_num += data.shape[0]

            optimizer.zero_grad()
            outputs = model(data.to(device))
            pre_class = torch.max(outputs, dim=1)[1]
            acc_num += torch.eq(pre_class, label.to(device)).sum()

            loss = loss_f(outputs, label.to(device))
            loss.backward()
            optimizer.step()

            train_acc = acc_num.item() / sample_num
            train_bar.desc = f"train epoch[{epoch + 1}/{epochs}] loss:{loss.item():.3f}"

        val_acc = infer(model, val_loader, device)
        print(f"epoch[{epoch + 1}/{epochs}] train acc: {train_acc:.3f} val acc: {val_acc:.3f}")
        torch.save(model.state_dict(), os.path.join(save_path, f"model_epoch_{epoch}.pth"))

    print("Training complete!")
    test_acc = infer(model, test_loader, device)
    print(f"Test accuracy: {test_acc:.3f}")

if __name__ == "__main__":
    main(lr=0.005, epochs=20)

iris.data

5.1,3.5,1.4,0.2,Iris-setosa
4.9,3.0,1.4,0.2,Iris-setosa
4.7,3.2,1.3,0.2,Iris-setosa
4.6,3.1,1.5,0.2,Iris-setosa
5.0,3.6,1.4,0.2,Iris-setosa
5.4,3.9,1.7,0.4,Iris-setosa
4.6,3.4,1.4,0.3,Iris-setosa
5.0,3.4,1.5,0.2,Iris-setosa
4.4,2.9,1.4,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
5.4,3.7,1.5,0.2,Iris-setosa
4.8,3.4,1.6,0.2,Iris-setosa
4.8,3.0,1.4,0.1,Iris-setosa
4.3,3.0,1.1,0.1,Iris-setosa
5.8,4.0,1.2,0.2,Iris-setosa
5.7,4.4,1.5,0.4,Iris-setosa
5.4,3.9,1.3,0.4,Iris-setosa
5.1,3.5,1.4,0.3,Iris-setosa
5.7,3.8,1.7,0.3,Iris-setosa
5.1,3.8,1.5,0.3,Iris-setosa
5.4,3.4,1.7,0.2,Iris-setosa
5.1,3.7,1.5,0.4,Iris-setosa
4.6,3.6,1.0,0.2,Iris-setosa
5.1,3.3,1.7,0.5,Iris-setosa
4.8,3.4,1.9,0.2,Iris-setosa
5.0,3.0,1.6,0.2,Iris-setosa
5.0,3.4,1.6,0.4,Iris-setosa
5.2,3.5,1.5,0.2,Iris-setosa
5.2,3.4,1.4,0.2,Iris-setosa
4.7,3.2,1.6,0.2,Iris-setosa
4.8,3.1,1.6,0.2,Iris-setosa
5.4,3.4,1.5,0.4,Iris-setosa
5.2,4.1,1.5,0.1,Iris-setosa
5.5,4.2,1.4,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
5.0,3.2,1.2,0.2,Iris-setosa
5.5,3.5,1.3,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
4.4,3.0,1.3,0.2,Iris-setosa
5.1,3.4,1.5,0.2,Iris-setosa
5.0,3.5,1.3,0.3,Iris-setosa
4.5,2.3,1.3,0.3,Iris-setosa
4.4,3.2,1.3,0.2,Iris-setosa
5.0,3.5,1.6,0.6,Iris-setosa
5.1,3.8,1.9,0.4,Iris-setosa
4.8,3.0,1.4,0.3,Iris-setosa
5.1,3.8,1.6,0.2,Iris-setosa
4.6,3.2,1.4,0.2,Iris-setosa
5.3,3.7,1.5,0.2,Iris-setosa
5.0,3.3,1.4,0.2,Iris-setosa
7.0,3.2,4.7,1.4,Iris-versicolor
6.4,3.2,4.5,1.5,Iris-versicolor
6.9,3.1,4.9,1.5,Iris-versicolor
5.5,2.3,4.0,1.3,Iris-versicolor
6.5,2.8,4.6,1.5,Iris-versicolor
5.7,2.8,4.5,1.3,Iris-versicolor
6.3,3.3,4.7,1.6,Iris-versicolor
4.9,2.4,3.3,1.0,Iris-versicolor
6.6,2.9,4.6,1.3,Iris-versicolor
5.2,2.7,3.9,1.4,Iris-versicolor
5.0,2.0,3.5,1.0,Iris-versicolor
5.9,3.0,4.2,1.5,Iris-versicolor
6.0,2.2,4.0,1.0,Iris-versicolor
6.1,2.9,4.7,1.4,Iris-versicolor
5.6,2.9,3.6,1.3,Iris-versicolor
6.7,3.1,4.4,1.4,Iris-versicolor
5.6,3.0,4.5,1.5,Iris-versicolor
5.8,2.7,4.1,1.0,Iris-versicolor
6.2,2.2,4.5,1.5,Iris-versicolor
5.6,2.5,3.9,1.1,Iris-versicolor
5.9,3.2,4.8,1.8,Iris-versicolor
6.1,2.8,4.0,1.3,Iris-versicolor
6.3,2.5,4.9,1.5,Iris-versicolor
6.1,2.8,4.7,1.2,Iris-versicolor
6.4,2.9,4.3,1.3,Iris-versicolor
6.6,3.0,4.4,1.4,Iris-versicolor
6.8,2.8,4.8,1.4,Iris-versicolor
6.7,3.0,5.0,1.7,Iris-versicolor
6.0,2.9,4.5,1.5,Iris-versicolor
5.7,2.6,3.5,1.0,Iris-versicolor
5.5,2.4,3.8,1.1,Iris-versicolor
5.5,2.4,3.7,1.0,Iris-versicolor
5.8,2.7,3.9,1.2,Iris-versicolor
6.0,2.7,5.1,1.6,Iris-versicolor
5.4,3.0,4.5,1.5,Iris-versicolor
6.0,3.4,4.5,1.6,Iris-versicolor
6.7,3.1,4.7,1.5,Iris-versicolor
6.3,2.3,4.4,1.3,Iris-versicolor
5.6,3.0,4.1,1.3,Iris-versicolor
5.5,2.5,4.0,1.3,Iris-versicolor
5.5,2.6,4.4,1.2,Iris-versicolor
6.1,3.0,4.6,1.4,Iris-versicolor
5.8,2.6,4.0,1.2,Iris-versicolor
5.0,2.3,3.3,1.0,Iris-versicolor
5.6,2.7,4.2,1.3,Iris-versicolor
5.7,3.0,4.2,1.2,Iris-versicolor
5.7,2.9,4.2,1.3,Iris-versicolor
6.2,2.9,4.3,1.3,Iris-versicolor
5.1,2.5,3.0,1.1,Iris-versicolor
5.7,2.8,4.1,1.3,Iris-versicolor
6.3,3.3,6.0,2.5,Iris-virginica
5.8,2.7,5.1,1.9,Iris-virginica
7.1,3.0,5.9,2.1,Iris-virginica
6.3,2.9,5.6,1.8,Iris-virginica
6.5,3.0,5.8,2.2,Iris-virginica
7.6,3.0,6.6,2.1,Iris-virginica
4.9,2.5,4.5,1.7,Iris-virginica
7.3,2.9,6.3,1.8,Iris-virginica
6.7,2.5,5.8,1.8,Iris-virginica
7.2,3.6,6.1,2.5,Iris-virginica
6.5,3.2,5.1,2.0,Iris-virginica
6.4,2.7,5.3,1.9,Iris-virginica
6.8,3.0,5.5,2.1,Iris-virginica
5.7,2.5,5.0,2.0,Iris-virginica
5.8,2.8,5.1,2.4,Iris-virginica
6.4,3.2,5.3,2.3,Iris-virginica
6.5,3.0,5.5,1.8,Iris-virginica
7.7,3.8,6.7,2.2,Iris-virginica
7.7,2.6,6.9,2.3,Iris-virginica
6.0,2.2,5.0,1.5,Iris-virginica
6.9,3.2,5.7,2.3,Iris-virginica
5.6,2.8,4.9,2.0,Iris-virginica
7.7,2.8,6.7,2.0,Iris-virginica
6.3,2.7,4.9,1.8,Iris-virginica
6.7,3.3,5.7,2.1,Iris-virginica
7.2,3.2,6.0,1.8,Iris-virginica
6.2,2.8,4.8,1.8,Iris-virginica
6.1,3.0,4.9,1.8,Iris-virginica
6.4,2.8,5.6,2.1,Iris-virginica
7.2,3.0,5.8,1.6,Iris-virginica
7.4,2.8,6.1,1.9,Iris-virginica
7.9,3.8,6.4,2.0,Iris-virginica
6.4,2.8,5.6,2.2,Iris-virginica
6.3,2.8,5.1,1.5,Iris-virginica
6.1,2.6,5.6,1.4,Iris-virginica
7.7,3.0,6.1,2.3,Iris-virginica
6.3,3.4,5.6,2.4,Iris-virginica
6.4,3.1,5.5,1.8,Iris-virginica
6.0,3.0,4.8,1.8,Iris-virginica
6.9,3.1,5.4,2.1,Iris-virginica
6.7,3.1,5.6,2.4,Iris-virginica
6.9,3.1,5.1,2.3,Iris-virginica
5.8,2.7,5.1,1.9,Iris-virginica
6.8,3.2,5.9,2.3,Iris-virginica
6.7,3.3,5.7,2.5,Iris-virginica
6.7,3.0,5.2,2.3,Iris-virginica
6.3,2.5,5.0,1.9,Iris-virginica
6.5,3.0,5.2,2.0,Iris-virginica
6.2,3.4,5.4,2.3,Iris-virginica
5.9,3.0,5.1,1.8,Iris-virginica