Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import torch
- from torch.autograd import Variable
- import torch.optim as optim
- import torch.nn as nn
- import torch.nn.functional as F
- import torchvision
- import torchvision.transforms as transforms
- # The output of torchvision datasets are PILImage images of range [0, 1].
- # We transform them to Tensors of normalized range [-1, 1]
- transform=transforms.Compose([transforms.ToTensor(),
- transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
- ])
- trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
- trainloader = torch.utils.data.DataLoader(trainset, batch_size=1,
- shuffle=True, num_workers=2)
- testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
- testloader = torch.utils.data.DataLoader(testset, batch_size=1,
- shuffle=False, num_workers=2)
- classes = ('plane', 'car', 'bird', 'cat',
- 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
- class Net(nn.Module):
- def __init__(self):
- super(Net, self).__init__()
- self.dconv1 = nn.Conv2d(3, 6, 5)
- self.dpool = nn.MaxPool2d(2,2)
- self.dconv2 = nn.Conv2d(6, 16, 5)
- self.dfc1 = nn.Linear(16*5*5, 16*6*5*5)
- self.conv1 = nn.Conv2d(3, 6, 5)
- self.pool = nn.MaxPool2d(2,2)
- self.fc1 = nn.Linear(16*5*5, 120)
- self.fc2 = nn.Linear(120, 84)
- self.fc3 = nn.Linear(84, 10)
- def forward(self, x):
- y = x.clone()
- x = self.pool(F.relu(self.dconv1(x)))
- x = self.pool(F.relu(self.dconv2(x)))
- x = x.view(-1, 16*5*5)
- x = F.relu(self.dfc1(x))
- x=x.view(16,6,5,5)
- conv2 = nn.Conv2d(6,16,5)
- conv2.weight.copy_(x)
- conv2.bias.data.zero_()
- y = self.pool(F.relu(self.conv1(y)))
- y = self.pool(F.relu(conv2(y)))
- y = y.view(-1, 16*5*5)
- y = F.relu(self.fc1(y))
- y = F.relu(self.fc2(y))
- y = self.fc3(y)
- return y
- net = Net()
- criterion = nn.CrossEntropyLoss() # use a Classification Cross-Entropy loss
- optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
- for epoch in range(2): # loop over the dataset multiple times
- running_loss = 0.0
- for i, data in enumerate(trainloader, 0):
- # get the inputs
- inputs, labels = data
- # wrap them in Variable
- inputs, labels = Variable(inputs), Variable(labels)
- # zero the parameter gradients
- optimizer.zero_grad()
- # forward + backward + optimize
- outputs = net(inputs)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
- # print statistics
- running_loss += loss.data[0]
- if i % 2000 == 1999: # print every 2000 mini-batches
- print('[%d, %5d] loss: %.3f' % (epoch+1, i+1, running_loss / 2000))
- running_loss = 0.0
- print('Finished Training')
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement