Quick start: PyTorch, Training Classifier - Neutral Network

1-input.py

# Import libraries required for neutral network
import torch
# Vision-specific library which will contain our dataset and help us define how our images are loaded
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim

# Create image transform when we load the dataset of PIL images
transform = transforms.Compose(
    [transforms.ToTensor(), #Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor.
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) # Normalize a tensor image with mean and standard deviation.

# Load of of the prepared datasets and define train (create training dataset), transform (function to transform our PIL images), and others
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=8,
                                          shuffle=True, num_workers=2)
# Re-do same procedure for our test set
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=8,
                                         shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# notice that the labels variable is a tensor with index for each class
labels
# images is a tensor-type object of length 8
print(type(images), len(images))

# Repeat the same for our test data
dataiter = iter(testloader)
imagestest, labelstest = dataiter.next()

imshow(torchvision.utils.make_grid(imagestest))
print(','.join('%5s' % classes[labelstest[j]] for j in range(8)))

2-process.py

# loss function which is to be used in evaluating our model
criterion = nn.CrossEntropyLoss()
# define optimizer parameters
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

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

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

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize use our neural network class
        outputs = net(inputs)
        # we use our nn.CrossEntropyLoss()
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        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')
print('Note: look carefully at the loss pattern of each for loop and epoch')

3-output.py

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

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

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1

for i in range(10):
    print('Accuracy of %5s : %2d %%' % (
        classes[i], 100 * class_correct[i] / class_total[i]))