pytorch实现多层神经网络

一.引入模块，读取数据集

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

import torch
import torch.nn as nn
import torch.nn.init as init
import torch.nn.functional as F
import math
from torch.autograd import Variable

#读取数据
data = pd.read_csv('diabetes.csv',delimiter=',',dtype=np.float32)
print(data.head())

data = np.array(data)
x = data[:,0:-1]
y = data[:,-1].reshape(-1,1)

pytorch实现多层神经网络

x = torch.Tensor(torch.from_numpy(x))
y = torch.Tensor(torch.from_numpy(y))

#查看数据维度
print(x.data.shape)
print(y.data.shape)

二.搭建神经网络

#构建模型
class Model(nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        #定义多层神经网络
        self.fc1 = torch.nn.Linear(8,6)
        self.fc2 = torch.nn.Linear(6,4)
        self.fc3 = torch.nn.Linear(4,1)
        
    def forward(self,x):
        x = F.relu(self.fc1(x)) #第一层
        x = F.dropout(x,p=0.5)
        x = F.relu(self.fc2(x)) #第二层
        x = F.dropout(x,p=0.5)
        y_pred = torch.sigmoid(self.fc3(x))
        return y_pred

def weight_init(m):
    classname = m.__class__.__name__
    if classname.find('Linear') != -1:
        m.weight.data = torch.randn(m.weight.data.size()[0],m.weight.data.size()[1])
        m.bias.data = torch.randn(m.bias.data.size()[0])
        

model = Model()
model.apply(weight_init)
#定义损失函数和优化器
criterion = torch.nn.BCELoss()
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)

Loss = []
for epoch in range(200):
    y_pred = model(x)
    loss = criterion(y_pred,y)
    if epoch % 50 == 0:
        print('epoch=',epoch,'loss=',loss.item())
    #梯度清零
    optimizer.zero_grad()
    #反向传播
    loss.backward()
    #更新梯度
    optimizer.step()
    
for i in range(len(y_pred)):
    if(y_pred[i]>0.5):
        y_pred[i] = 1.0
    else:
        y_pred[i] = 0.0

type(y_pred)

三.预测准确率

#求准确率
(y_pred == y).sum().item()/len(y)

pytorch实现多层神经网络