07.Mutipule

import torch
import numpy as np
import matplotlib.pyplot as plt

xy = np.loadtxt("diabetes.csv.gz", dtype=np.float32, delimiter=",")
x = torch.from_numpy(xy[:, :-1])
y = torch.from_numpy(xy[:, [-1]])  # 这里[-1]是为了返回nx1的矩阵，如果只是一个-1的话，是没有维度的
class MyModel(torch.nn.Module):
    def __init__(self):
        super(MyModel, 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()#这里Sigmoid也是继承自Module的模块，只是其没有参数。其也是一个callable的东西
    def forward(self,x):
        x=self.Sigmoid(self.linear1(x))
        x=self.Sigmoid(self.linear3(x))
        x=self.Sigmoid(self.linear3(x))
        return x  #这里最好都只使用这一个变量x。便于调试
        # return self.Sigmoid(self.linear2(self.Sigmoid(self.linear1(x))))
model=MyModel()

criterion=torch.nn.BCELoss()
optimizer=torch.optim.SGD(model.parameters(),lr=0.1)

for epoch in range(1100):
    y_pred=model(x)
    loss=criterion(y_pred,y)
    print("Epoch{}, loss={}".format(epoch, loss.item()))

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()