PyTorch的深度学习入门教程之构建神经网络

import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F


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 (

 (conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))

 (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))

 (fc1): Linear (400 ->120)

 (fc2): Linear (120 ->84)

 (fc3): Linear (84 ->10)

)

params = list(net.parameters())
print(len(params))
print(params[0].size()) # conv1's .weight

input = Variable(torch.randn(1, 1, 32, 32))
out = net(input)
print(out)

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

output = net(input)
target = Variable(torch.arange(1, 11)) # a dummy target, for example
criterion = nn.MSELoss()

loss = criterion(output, target)
print(loss)

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

print(loss.grad_fn) # MSELoss
print(loss.grad_fn.next_functions[0][0]) # Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0]) # ReLU

<torch.autograd.function.MSELossBackwardobjectat0x7fb3c0dcf4f8>

<torch.autograd.function.AddmmBackwardobjectat0x7fb3c0dcf408>

<AccumulateGradobjectat0x7fb3c0db79e8>

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)

weight = weight - learning_rate * gradient

learning_rate = 0.01
for f in net.parameters():
  f.data.sub_(f.grad.data * learning_rate)

import torch.optim as optim

# 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