python神经网络学习利用PyTorch进行回归运算

# 继承torch.nn.Module模型
class Net(torch.nn.Module):
	# 重载初始化函数（我忘了这个是不是叫重载）
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        # Applies a linear transformation to the incoming data: :math:y = xA^T + b
        # 全连接层，公式为y = xA^T + b
        # 在初始化的同时构建两个全连接层（也就是一个隐含层）
        self.hidden = torch.nn.Linear(n_feature, n_hidden)
        self.predict = torch.nn.Linear(n_hidden, n_output)
	# forward函数用于构建前向传递的过程
    def forward(self, x):
        # 隐含层的输出
        hidden_layer = functional.relu(self.hidden(x))
        # 实际的输出
        output_layer = self.predict(hidden_layer)
        return output_layer

net = Net(n_feature=1, n_hidden=10, n_output=1)

# torch.optim是优化器模块
# Adam可以改成其它优化器，如SGD、RMSprop等
optimizer = torch.optim.Adam(net.parameters(), lr=1e-3)

# 均方差lossloss_func = torch.nn.MSELoss() 

prediction = net(x)

loss = loss_func(prediction, y)

# 均方差loss
# 反向传递步骤
# 1、初始化梯度
optimizer.zero_grad()
# 2、计算梯度
loss.backward()
# 3、进行optimizer优化
optimizer.step()

import torch
from torch.autograd import Variable
import torch.nn.functional as functional
import matplotlib.pyplot as plt
import numpy as np
# x的shape为(100,1)
x = torch.from_numpy(np.linspace(-1,1,100).reshape([100,1])).type(torch.FloatTensor)
# y的shape为(100,1)
y = torch.sin(x) + 0.2*torch.rand(x.size())
class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        # Applies a linear transformation to the incoming data: :math:y = xA^T + b
        # 全连接层，公式为y = xA^T + b
        self.hidden = torch.nn.Linear(n_feature, n_hidden)
        self.predict = torch.nn.Linear(n_hidden, n_output)
    def forward(self, x):
        # 隐含层的输出
        hidden_layer = functional.relu(self.hidden(x))
        output_layer = self.predict(hidden_layer)
        return output_layer
# 类的建立
net = Net(n_feature=1, n_hidden=10, n_output=1)
# torch.optim是优化器模块
optimizer = torch.optim.Adam(net.parameters(), lr=1e-3)
# 均方差loss
loss_func = torch.nn.MSELoss() 
for t in range(1000):
    prediction = net(x)
    loss = loss_func(prediction, y)
    # 反向传递步骤
    # 1、初始化梯度
    optimizer.zero_grad()
    # 2、计算梯度
    loss.backward()
    # 3、进行optimizer优化
    optimizer.step()
    if t & 50 == 0:
        print("The loss is",loss.data.numpy())