Dataset和DataLoader一般使用格式

今天也要加油鸭！冲冲冲😊

文章目录

前言

一、代码总体概览

---

一、代码总体概览

代码结合注释应该很好理解哦

import numpy as np
import torch
from torch.utils.data import Dataset, DataLoader
# Dataset是一个抽象的类，我们可以继承这个类来定义我们自己的类
# 准备数据
class DiabetesDataset(Dataset): # DiabetesDatasets继承了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): # 获得数据的索引
        return self.x_data[index], self.y_data[index]

    def __len__(self): # 获得数据的长度
        return self.len

dataset = DiabetesDataset('diabetes.csv.gz') # 构建实例
train_loader = DataLoader( dataset = dataset,
                          batch_size=32
                          shuffle=True
                          num_workers=2)
 # 用类定义模型
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 .sigmoid = torch.nn.Sigmoid()
    def forward( self ,
        x = self . self .linear1(x))
        x = self . self .linear2(x))
        x = self . self .linear3(x))
        return x
model = Model()

# 构建损失函数和优化器
criterion = torch.nn.BCELoss( size_average=True)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

if __name__ == '__main__': # 进行封装
    for epoch in range (100): # Training cycle
        for i, data in enumerate (train_loader, 0): # Loop over all batches
            # 1. Prepare data
            inputs, labels = data
            # 2. Forward
            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()