mnist-pytorch.py

import torch
import torchvision
import torch.nn as nn
import torch.nn.functional as F
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as optim

from torch.autograd import Variable

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 1, 5)
        self.conv2 = nn.Conv2d(1, 1, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(1 * 10 * 10, 100)
        self.fc2 = nn.Linear(100, 10)

    def forward(self, x):
        x = F.relu((self.conv1(x)))
        x = F.relu(F.max_pool2d((self.conv2(x)), 2))
        # x = self.pool(x)
        # x = F.relu(self.conv3(x))
        x = x.view(-1, 1 * 10 * 10)
        # x = F.relu(x)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        return F.log_softmax(x)

def unnormalize(img):
    img = img / 2 + 0.5
    return img

def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))

# Basically re-maps the [0,1] pixel to the [-1,1] range so that mean is 0.
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

# Getting the data

trainset = torchvision.datasets.MNIST(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=50,
                                          shuffle=True, num_workers=2)
testset = torchvision.datasets.MNIST(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=50,
                                         shuffle=False, num_workers=2)

net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.5)

# zero the parameter gradients
optimizer.zero_grad()

for epoch in range(20):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        inputs, labels = data
        # print inputs.numpy().shape

        # 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 % 100 == 99:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 100))
            running_loss = 0.0

print('Finished Training')

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

print('Accuracy of the network on the %d test images: %f %%' % (
    total, 100.0 * correct / total))