pytorch深度学习实践（刘二大人）课堂代码——加载数据集

一、课堂代码

import torch
from torch.utils.data import Dataset   #抽象类，不能实例化，只能被其他的类继承
from torch.utils.data import DataLoader #帮助加载数据
import numpy as np

class DiabetesDataset(Dataset):  #数据小，init时都先加载在内存当中了
    def __init__(self, filepath):
        xy = np.loadtxt(filepath, delimiter=',', dtype=np.float32)
        self.len = xy.shape[0]  #(N,9)，取出N，也就是样本数
        self.x_data = torch.from_numpy(xy[:,:-1])
        self.y_data = torch.from_numpy(xy[:,[-1]])

    def __getitem__(self, index):   #使这个类实例化之后能够进行下标操作
        return self.x_data[index], self.y_data[index]

    def __len__(self):  #用来返回数据条数
        return self.len

dataset = DiabetesDataset('diabetes.csv.gz')
train_loader = DataLoader(dataset=dataset,
                          batch_size=32,
                          shuffle=True,
                          num_workers=0)  #读batch里的数据所并行的进程，win系统设置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(size_average=True)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

'''
windows和linux实现多进程的库不一样
windows用spawn来替代linux的fork来调用多进程，会导致报错RuntimeError
解决方法：把要迭代的loader的代码封装起来
'''

for epoch in range(100):
    for i, data in enumerate(train_loader, 0):  #0表示index从0开始读入,train_loader拿出的（x,y）元组放在data里，自动转tensor
        #1.prepare data
        inputs, labels = data  #也可以直接在上面写 i, (imputs, labels)
        #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()
        
'''
总结：
1.准备数据集：dataset，dataloader
2.设计模型
3.构造损失函数和优化器
4.训练周期
'''

结果：

加载MNIST数据集：

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets

train_dataset = datasets.MNIST(root='./dataset/mnist',
                               train=True,
                               transform=transforms.ToTensor(),
                               download=True)
test_dataset = datasets.MNIST(root='./dataset/mnist',
                               train=False,
                               transform=transforms.ToTensor(),
                               download=True)

train_loader = DataLoader(dataset=train_dataset,
                          batch_size=32,
                          shuffle=True) #训练时要把数据打乱确保随机，测试时模型不变，不用打乱
test_loader = DataLoader(dataset=test_dataset,
                          batch_size=32,
                          shuffle=False)

for batch_idx, (inputs, target) in enumerate(train_loader):
    pass

这节课的课后作业我大概看了一下，比较复杂，还涉及到一些数据分析的内容，我还需要补补课，所以打算分开更~需要参考的话可以关注一下我后续发布的内容~