PyTorch神经网络

        最近在学习《PyTorch官方教程》，跟着教程实现了一个简单的神经网络。

        神经网络可以通过 torch.nn 包来构建，一个典型的神经网络训练过程包括以下几点：

1. 定义一个包含可训练参数的神经网络。
2. 迭代整个输入。
3. 通过神经网络处理输入。
4. 计算损失(loss)。
5. 反向传播梯度到神经网络的参数。
6. 更新网络的参数，典型的用一个简单的更新方法：weight = weight - learning_rate *gradient

        例如，对于实现下面这个神经网络：

        将教程中的代码精简如下：

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)        # 全连接层
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)        # 高斯连接层

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        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:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features

net = Net()
print(net)

# The learnable parameters of a model are returned by ``net.parameters()``
params = list(net.parameters())
print(len(params))
print(params[0].size())  # conv1's .weight

# Let try a random 32x32 input
# 返回一个1行1列的张量，其中每个元素又是一个32行32列的张量
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)

#计算损失函数
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()    #均方误差
loss = criterion(output, target)
print(loss)

# 为了实现反向传播损失，我们所有需要做的事情仅仅是使用 loss.backward()
# 需要清空现存的梯度，要不然它都将会和现存的梯度累计到一起
net.zero_grad() # zeroes the gradient buffers of all parameters
print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)
loss.backward()
print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)

# 更新神经网络参数
learning_rate = 0.01
for f in net.parameters():
    f.data.sub_(f.grad.data * learning_rate)


########################################################################
# 简洁版代码
# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)

# in your training loop:
optimizer.zero_grad()   # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()    # Does the update