用pytorch创建神经网络的步骤如下:
1.定义有可学习参数的网络
2.用输入数据进行迭代
3.通过网络操作输入
4.计算损失函数
5.反向传播梯度给参数
6.更新权重weight = weight - learning_rate * gradient
1.定义网络:
import torch
import torch.nn as nn
import torch.nn.functional as F#注意是functional 不是function
class Net(nn.Module):#定义网络名称Net,为Module类型
def __init__(self):
super(Net, self).__init__()
# 1 input image channel, 6 output channels, 3x3 square convolution
# kernel
self.conv1 = nn.Conv2d(1, 6, 3)
self.conv2 = nn.Conv2d(6, 16, 3)
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 6 * 6, 120) # 6*6 from image dimension
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))#展开
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)
我们只需要定义前向的过程,反向传播的过程是在使用autograd时候自动定义的。
params = list(net.parameters())
print(len(params))
print(params[0].size()) # conv1's .weight
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)