【pytorch_5】加载数据集

epoch：训练所有的数据集的迭代次数
Bach_size：每一批次训练的数量
Iterations：训练所有数据集的批次

【diabetes.csv.gz数据集】
链接：https://pan.baidu.com/s/1h-_BURzYQPmTF4RuFv5b-w
提取码：zf88

import numpy as np
import torch 
from torch.utils.data import Dataset,DataLoader 

# prepare dataset 
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.gz')
train_loader = DataLoader(dataset=dataset,batch_size=32,shuffle=True,num_workers=2)

# design model using class
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
        
# construct loss and optimizer
model = Model()
criterion = torch.nn.BCELoss()
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)

# Training cycle
if __name__ == '__main__':
    for epoch in range(1000):
        for i ,data in enumerate(train_loader,0):
            # prepare data
            inputs, labels = data
            # forward
            y_pred = model(inputs)
            loss = criterion(y_pred,labels)
            print(epoch,i,loss.item())
            # backward
            optimizer.zero_grad()
            loss.backward()
            # update
            optimizer.step()

参考链接：《PyTorch深度学习实践》完结合集