(三) neural networks

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

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        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))
        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)

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)
)

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

10
torch.Size([6, 1, 5, 5])

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

tensor([[ 0.0012, -0.0340, -0.0430, -0.0597,  0.0101,  0.0129,  0.0002,  0.1040,
         -0.0090,  0.0261]], grad_fn=<ThAddmmBackward>)

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

output = net(input)
target = torch.randn(10)
target = target.view(1,-1)
criterion = nn.MSELoss()

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

tensor(1.2767, grad_fn=<MseLossBackward>)

print(loss.grad_fn)
print(loss.grad_fn.next_functions[0][0])
print(loss.grad_fn.next_functions[0][0].next_functions[0][0])

<MseLossBackward object at 0x7f75d76c9c88>
<ThAddmmBackward object at 0x7f75d76c9cf8>
<ExpandBackward object at 0x7f75d76c9c88>

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)

conv1.bias.grad before backward
tensor([0., 0., 0., 0., 0., 0.])
conv1.bias.grad after backward
tensor([ 0.0150,  0.0208, -0.0058,  0.0064,  0.0039, -0.0019])

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

import torch.optim as optim

optimizer = optim.SGD(net.parameters(), lr=0.01)

optimizer.zero_grad()
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()