2021-04-14

08.加载数据集（dataest and dataLoader）

-------------------------------------------------

构造加载数据集

mini batch

batch是一个一个小组

-------------------------------------------------------

准备数据，构造模型，构造损失和优化器，训练循环

 

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

class DiabetesDataset(Dataest):               #继承自dataest
    def __init__(self,filepath):    #filepath是文件来自哪里
        xy = np.loadtxt('diabetes.csv.gz', delimiter=',', dtype=np.float32)  # 逗号分割
        self.len = xy.shape[0]          #n行几列到时候直接把n取出来就ok了
        self.x_data = torch.from_numpy(xy[:, :-1])  # 最后一列不要
        self.y_data = torch.from_numpy(xy[:, [-1]])  # 要-1那一列，加中括号是为了保证拿出来的那一列是矩阵

    def __getitem__(self, index):               #支持索引
        return self.x_data[index],self.y_data[index]

    def __len__(self):             #数据条数进行反馈
        return len

dataest = DiabetesDataset('diabetes.csv.gz')
train_loader = DataLoader(dataset=dataest,batch_size=32,shuffle=True,num_workers=2)         #加载器：数据集，大小，是否打乱，要几个并行


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)  # 维度依次降低
        self.sigmoid = torch.nn.Sigmoid()

    def forward(self, x):
        x = self.sigmoid(self.linear1(x))  # 每次都重新定义x避免一次有错误而难以查出
        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=0.1)

for epoch in range(100):
    for i,data in enumerate(train_loader,0):          #直接对train_loader做迭代
        #1.准备数据、
        inputs,labels = data                   #x，y
        # forward
        y_pred = model(inputs)
        loss = criterion(y_pred, labels)
        print(epoch,i, loss.item())

        # backward
        optimizer.zero_grad()
        loss.backward()

        # updata
        optimizer.step()