Pytorch实践（刘二大人）7：加载数据集

思路

加载数据集

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
class DiabetesDataset(Dataset):
    def __init__(self, filepath):
        xy = np.loadtxt(filepath,delimiter=',',dtype=np.float32)
        self.len = xy.shape[0]
        self.x_data = torch.from_numpy(xy[:, :-1])
        self.y_data = torch.from_numpy(xy[:, [-1]])

    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index]

    def __len__(self):
        return self.len

dataset = DiabetesDataset('diabetes.csv')
train_loader = DataLoader(dataset=dataset, batch_size=32, shuffle=True, num_workers=0)

filepath是外部传入的参数（数据文件路径）
np.loadtxt从CSV文件加载数据，返回NumPy数组
xy.shape[0]表示数据的第一维大小，即数据集的样本总数（行数）
torch.from_numpy()将NumPy数组转换为PyTorch Tensor
__getitem__
- 允许对象支持下标访问（如dataset[i]）
- 参数index表示要访问的数据索引
- 返回一个元组(x, y)，即特征和标签
shuffle=True表示是否在每个epoch开始时打乱数据顺序。True打乱或False不打乱
num_workers=0表示用于数据加载的子进程数量。

模型定义

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        self.sigmoid = torch.nn.Sigmoid()

    def forward(self, x):
        x = self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x

损失函数与优化器

1
2
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

训练循环

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
for epoch in range(100):
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        y_pred = model(inputs)
        loss = criterion(y_pred, labels)
        print(epoch, i, loss.item())

        optimizer.zero_grad()
        loss.backward()

        optimizer.step()

for i, data in enumerate(train_loader, 0)
- train_loader表示PyTorch的DataLoader对象，用于按批次加载数据
- 0表示索引从0开始计数
- 返回迭代器，i表示当前批次的索引，data表示当前批次的数据
inputs, labes表示元组解包

代码实现

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
import torch
import numpy as np
from torch.utils.data import Dataset
from torch.utils.data import DataLoader

class DiabetesDataset(Dataset):
    def __init__(self, filepath):
        xy = np.loadtxt(filepath,delimiter=',',dtype=np.float32)
        self.len = xy.shape[0]
        self.x_data = torch.from_numpy(xy[:, :-1])
        self.y_data = torch.from_numpy(xy[:, [-1]])

    def __getitem__(self, index):
        return self.x_data[index], self.y_data[index]

    def __len__(self):
        return self.len

dataset = DiabetesDataset('diabetes.csv')
train_loader = DataLoader(dataset=dataset, batch_size=32, shuffle=True, num_workers=0)

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(8, 6)
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        self.sigmoid = torch.nn.Sigmoid()

    def forward(self, x):
        x = self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x

model = Model()

criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

if __name__ == '__main__':
    for epoch in range(100):
        for i, data in enumerate(train_loader, 0):
            inputs, labels = data
            y_pred = model(inputs)
            loss = criterion(y_pred, labels)
            print(epoch, i, loss.item())

            optimizer.zero_grad()
            loss.backward()

            optimizer.step()