mnist_conv.py

# pylint: disable=E0401

import torchvision.datasets as ds
import torchvision.transforms as transforms
from torch.autograd import Variable
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F

transform = transforms.Compose([transforms.ToTensor()])


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x)


model = Net()
model.cuda()

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

trainset = ds.MNIST("./mnist", download=True, train=True, transform=transform)
testset = ds.MNIST("./mnist", download=True, train=False, transform=transform)

train_feeder = torch.utils.data.DataLoader(
    trainset, batch_size=4, shuffle=True, num_workers=2)
test_feeder = torch.utils.data.DataLoader(
    testset, batch_size=4, shuffle=False, num_workers=2)

for epoch in range(3):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(train_feeder, 0):
        # get the inputs
        inputs, labels = data

        # wrap them in Variable
        inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = model(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')

correct = 0
total = 0
for data in test_feeder:
    images, labels = data
    outputs = model(Variable(images.cuda()))
    _, predicted = torch.max(outputs.data, 1)
    total += labels.size(0)
    correct += (predicted == labels.cuda()).sum()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))