pytorch-神经网络-自学笔记1

1.前向传播神经网络

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)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    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)
net = 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)
)

完整代码：

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
定义神经网络
"""

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)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    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)
net = Net()

# 一个模型可训练的参数可以通过调用 net.parameters() 返回：

params = list(net.parameters())
print(len(params))
print(params[0].size())
#6155

#让我们尝试随机生成一个 32x32 的输入。注意：期望的输入维度是 32x32 。为了使用这个网络在 MNIST 数据及上，你需要把数据集中的图片维度修改为 32x32。
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)
#把所有参数梯度缓存器置零，用随机的梯度来反向传播
net.zero_grad()
out.backward(torch.randn(1, 10))
        
    
'''
损失函数

一个损失函数需要一对输入：模型输出和目标，然后计算一个值来评估输出距离目标有多远。

有一些不同的损失函数在 nn 包中。一个简单的损失函数就是 nn.MSELoss ，这计算了均方误差。

'''
    
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)

'''
input -> conv2d -> relu -> maxpool2d -> conv2d -> relu -> maxpool2d
      -> view -> linear -> relu -> linear -> relu -> linear
      -> MSELoss
      -> loss

'''
#随机梯度下降

learning_rate = 0.01
for f in net.parameters():
    f.data.sub_(f.grad.data*learning_rate)
    
'''
如果你是用神经网络，你想使用不同的更新规则，类似于 SGD, Nesterov-SGD, Adam, RMSProp, 等。
为了让这可行，我们建立了一个小包：torch.optim 实现了所有的方法。使用它非常的简单。
'''
# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)

# in your training loop:
optimizer.zero_grad()
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()

输出：

10
torch.Size([6, 1, 5, 5])
tensor([[ 0.0073, -0.0053,  0.0502,  0.1265,  0.1041,  0.0391, -0.0492, -0.0651,
          0.0351, -0.0465]], grad_fn=<AddmmBackward>)
tensor(1.1530, grad_fn=<MseLossBackward>)