Pytorch官方教程练习之神经网络

神经网络
Pytorch中使用torch.nn模块构建神经网络。
nn.Module包括神经网络的各层；forward(input)用来返回输出output。本章记录神经网络的构建及其训练过程的步骤。具体训练过程在后续章节记录。

1.定义神经网络

import torch
import torch.nn as nn
import torch.nn.functional as F
# 定义网络
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)# 输入1输出6通道；卷积核大小5x5。
        self.conv2 = nn.Conv2d(6, 16, 5)
        # 全连接层
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
    # 前向传播
    def forward(self, x):
        # 卷积+relu+最大池化2x2
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
    def num_flat_features(self, x):
        size = x.size()[1:]  
        num_features = 1
        for s in size:
            num_features *= s
        return num_features
net = Net()
print(net)
# 输出
Net(
  (conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear(in_features=400, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)

查看模型参数

params = list(net.parameters())
print(len(params))
print(params[0].size())  # conv1's .weight
# 输出
10
torch.Size([6, 1, 5, 5])

2.更新网络参数
随机生成一个 32x32 的输入，输入网络，得到输出。

input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)
# 输出
tensor([[-0.0233,  0.0159, -0.0249,  0.1413,  0.0663,  0.0297, -0.0940, -0.0135,
          0.1003, -0.0559]], grad_fn=<AddmmBackward>)

将所有参数梯度归零，用随机的梯度进行反向传播。

net.zero_grad()
out.backward(torch.randn(1, 10))

3.损失函数
损失函数需要一对输入，分别为模型输出值和目标值。然后计算两者之间损失值，评估输出离目标值有多远。

output = net(input)
target = torch.randn(10)  # a dummy target, for example
target = target.view(1, -1)  # make it the same shape as output
criterion = nn.MSELoss()

loss = criterion(output, target)
print(loss)
# 输出
tensor(1.3389, grad_fn=<MseLossBackward>)

4.反向传播

net.zero_grad()# 首先清空现存的梯度
print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)

loss.backward()

print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)
# conv1.bias.grad before backward
tensor([0., 0., 0., 0., 0., 0.])
conv1.bias.grad after backward
tensor([-0.0054,  0.0011,  0.0012,  0.0148, -0.0186,  0.0087])

5.更新神经网络参数

import torch.optim as optim

# 随机梯度下降
optimizer = optim.SGD(net.parameters(), lr=0.01)

# 在循环迭代中运用：
optimizer.zero_grad()   # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()    # Does the update

参考：
http://pytorch123.com/SecondSection/neural_networks/