Pytorch学习（八）——数据集加载

代码

import numpy as np
import torch 
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]#Nx9,拿出第0个元素可知有多少样本数
        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]
      #实现对数据的下标操作，有索引
    def __len__(self):
        return self.len
    #能够使用len()计算长度
    
dataset123 = DiabetesDataset('diabetes.csv.gz')#数据集在老师给的课件包里
train_loader = DataLoader(dataset = dataset123, batch_size=32, shuffle=True, num_workers=0)#一个小批量的容量，打乱，不使用多进程

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.activate = torch.nn.Sigmoid()
    def forward(self, x):
        x = self.activate(self.linear1(x))
        x = self.activate(self.linear2(x))
        x = self.activate(self.linear3(x))
        return x
    
model = Model()   
criterion = torch.nn.BCELoss(size_average = True)#返回loss均值 
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)

for epoch in range(100):
    for i, data in enumerate(train_loader, 0):#train_loader中的x y 放到data中  32个样本为一组放入
            #1 data Pre
        inputs, labels = data# x y 都是张量
            #2 foward
        y_pred = model(inputs)
        loss = criterion(y_pred, labels)
        print(epoch, i, loss.item())
            #3 backward
        optimizer.zero_grad()
        loss.backward()
            #4 update
        optimizer.step()

问题

将num_workers设置为2时会出现报错

runtimeerror: dataloader worker (pid(s) 14128) exited unexpectedly

所以最后将num_workers设置为0，不使用多线程进行

如果后续要使用多进程进行，该如何解决这个问题？

结果

loss在0.6~0.75之间