这是一个略复杂的入门例子，涵盖了一个典型神经网络的训练过程。


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

# Define the network structure
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1,6,3) # Convolutions
        self.conv2 = nn.Conv2d(6,16,3)
        self.fc1 = nn.Linear(16*6*6,120) # Full connections
        self.fc2 = nn.Linear(120,84)
        self.fc3 = nn.Linear(84, 10)
    def forward(self, x):
        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)) # rectified linear unit
        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)

# Processing inputs and calling backward
input = torch.randn(1,1,32,32)
out = net(input)
print(out)

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

# Computing the loss
output = net(input)
target = torch.randn(10)
target = target.view(1,-1)
criterion = nn.MSELoss()
loss = criterion(output, target)
print(loss)

# Backprop
net.zero_grad()
print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)
loss.backward()
print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)

# Updating the weights of the network
# weight = weight - learning_rate * gradient
learning_rate = 0.01
for f in net.parameters():
    f.data.sub_(f.grad.data*learning_rate)

# torch.optim
import torch.optim as optim
optimizer = option.SGD(net.parameters(), lr=0.01)
optimizer = optim.SGD(net.parameters(), lr=0.01)
optimizer.zero_grad()
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()

Source
DEEP LEARNING WITH PYTORCH: A 60 MINUTE BLITZ