pytorch深度学习实践-多维特征输入0106

目录

1、多维特征的输入实践-糖尿病数据预测

2、torch.nn.BCELoss相关参数含义

3、更换激活函数对比效果

---

1、多维特征的输入实践-糖尿病数据预测

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

# prepare dataset
xy = np.loadtxt('diabetes.csv', delimiter=',', dtype=np.float32)
# 创建两个tensor
x_data = torch.from_numpy(xy[:, :-1])
y_data = torch.from_numpy(xy[:, [-1]])  # 只填-1得到的是向量，[-1]最后得到的是个矩阵


# design model using class
class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        # 三个线性模型
        self.linear1 = torch.nn.Linear(8, 6)  # 输入数据x的特征是8维，x有8个特征
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        self.sigmoid = torch.nn.Sigmoid()  # 有所区别

    def forward(self, x):
        x = self.sigmoid(self.linear1(x))  # 第一个输出x作为第二个函数的输入
        x = self.sigmoid(self.linear2(x))
        x = self.sigmoid(self.linear3(x))  # y hat
        return x


model = Model()

# construct loss and optimizer
criterion = torch.nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

epoch_list = []
loss_list = []

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

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

plt.plot(epoch_list, loss_list)
plt.ylabel('loss')
plt.xlabel('epoch')
plt.show()