Pytorch(七) --加载数据集

主要用到了Pytorch中的Dataset和DataLoadder这两个方法，其中Dataset是抽象类，不能实例化对象，只能继承用于构造数据集，DataLoader是帮助加载数据的，可以做shuffle、batch_size，能拿Mini-batch进行训练。
代码如下：

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('E:\\tmp\\.keras\\datasets\\diabetes.csv\\diabetes.csv')
train_loader = DataLoader(
    dataset=dataset,
    batch_size = 32,
    shuffle = True,
    num_workers=0
)

#定义模型
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.relu = torch.nn.ReLU()
        self.sigmoid = torch.nn.Sigmoid()
    def forward(self,x):
        x = self.relu(self.linear1(x))
        x = self.relu(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x
model = Model()

#构建优化器和损失函数
criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)
#训练
if __name__ == '__main__':
    for epoch in range(1000):
        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()

努力加油a啊