07处理多维特征的输入

处理多维特征的输入

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

xy = np.loadtxt("./datasets/diabetes.csv", delimiter=',', skiprows=1, dtype=np.float32)  # 第一行是名称，所以跳过了
x_data = torch.from_numpy(xy[:, :-1])
y_data = torch.from_numpy(xy[:, [-1]])  # 写中括号是为了保证是一个矩阵，而非向量

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear1 = torch.nn.Linear(8, 6)   # input是N*8
        self.linear2 = torch.nn.Linear(6, 4)
        self.linear3 = torch.nn.Linear(4, 1)
        self.sigmoid = torch.nn.Sigmoid()   # 没有参数。这里是模块
        self.relu = torch.nn.ReLU()
        self.leakyrelu = torch.nn.LeakyReLU()

    def forward(self, x):
        x = self.relu(self.linear1(x))
        x = self.relu(self.linear2(x))
        x = self.sigmoid(self.linear3(x))
        return x

model = Model()

# loss
criterion = torch.nn.BCELoss(size_average=True)

# optimizer
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)

for epoch in range(1000):
    y_pred = model(x_data)
    l = criterion(y_pred, y_data)
    print(f"epoch: {epoch}\tloss: {l.item()}")

    optimizer.zero_grad()
    l.backward()
    optimizer.step()