PyTorch 深度学习实践第七讲(处理多维特征的输入)

基本原理

降维基本原理

备注：读文档和基本架构能力很重要，具备此技能能够拥有强的泛化能力

上课代码

import torch
import numpy as np
import torch.nn.functional as F
import matplotlib.pyplot as plt
from sklearn import datasets

xy = np.loadtxt('diabetes.csv.gz',delimiter = ',',dtype = np.float32)    #以","为分隔符，加载训练集
x_data = torch.from_numpy(xy[:,:-1])    #取前八列
y_data = torch.from_numpy(xy[:,[-1]])    #取最后一列，拿出的是一个矩阵

test = np.loadtxt('./data/Diabetes_class.csv.gz',delimiter = ',',dtype = np.float32)  #加载测试集
test_x = torch.from_numpy(test)

class Model(torch.nn.Module):
    def __init__(self):  #构造函数
        super(Model,self).__init__()
        #进行降维
        self.linear1 = torch.nn.Linear(8,6)
        self.linear1 = torch.nn.Linear(6,4)
        self.linear1 = torch.nn.Linear(4,1)
        self.sigmoid = torch.nn.Sigmoid()     #改变激活函数
        
    def forward(self,x):
        x = self.sigmoid(self.linear1(x))     #加入逻辑变换
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x   #全程只用一个x
    
model = Model()     #模型实例化

criterion = torch.nn.BCELoss(size_average = False)   #将原来MSE变为BCE
optimizer = torch.optim.SGD(model.parameters(),lr = 0.01)   #优化器

for epoch in range(1000):   #training cycle
    #forward
    y_pred = model(x_data)
    loss = criterion(y_pred,y_data)
    print(epoch,loss.item())
    #backward
    optimizer.zero_grad()
    loss.backward()
    #update
    optimizer.step()
    
y_pred = model(x_data)

print(y_pred.detach().numpy())

y_pred2 = model(test_x)
print(y_pred2.data.item())