1. 定义一个拥有可学习参数的神经网络
2. 遍历训练数据集
3. 处理输入数据使其流经神经网络
4. 计算损失值
5. 将网络参数的梯度进行反向传播
6. 以一定的规则更新网络的权重
导包
from __future__ import print_function
import torch
import torch.nn as nn
import torch.nn.functional as F
建立神经网络类
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# 定义第一层卷积神经网络,输入通道为3,输出通道为6,卷积核大小为5*5
self.conv1 = nn.Conv2d(3, 6, 5)
# 定义第二层卷积神经网络,输入通道为6,输出通道为16,卷积核大小为5*5
self.conv2 = nn.Conv2d(6, 16, 5)
# 定义全连接层
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
# 在池化层窗口下进行池化操作
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:] # 除去批处理维度的其他所有维度
num_features = 1
for s in size:
num_features *= s
return num_features
使用
net=Net()
param=list(net.parameters())
print(len(param))
print(param[0].size())
input=torch.randn(1,3,32,32)
out=net(input)
print(out)