In [1]:
%matplotlib inline

Training a classifier

This is it. You have seen how to define neural networks, compute loss and make updates to the weights of the network.

Now you might be thinking,

What about data?

Generally, when you have to deal with image, text, audio or video data, you can use standard python packages that load data into a numpy array. Then you can convert this array into a torch.*Tensor.

  • For images, packages such as Pillow, OpenCV are useful.
  • For audio, packages such as scipy and librosa
  • For text, either raw Python or Cython based loading, or NLTK and SpaCy are useful.

Specifically for vision, we have created a package called torchvision, that has data loaders for common datasets such as Imagenet, CIFAR10, MNIST, etc. and data transformers for images, viz., torchvision.datasets and torch.utils.data.DataLoader.

This provides a huge convenience and avoids writing boilerplate code.

For this tutorial, we will use the CIFAR10 dataset. It has the classes: ‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels in size.

.. figure:: /_static/img/cifar10.png :alt: cifar10

cifar10

Training an image classifier

We will do the following steps in order:

  1. Load and normalizing the CIFAR10 training and test datasets using torchvision
  2. Define a Convolution Neural Network
  3. Define a loss function
  4. Train the network on the training data
  5. Test the network on the test data

  6. Loading and normalizing CIFAR10 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Using torchvision, it’s extremely easy to load CIFAR10.


In [2]:
import torch
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]


In [3]:
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=4,
                                          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=4,
                                         shuffle=False, num_workers=2)

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


Files already downloaded and verified
Files already downloaded and verified

Let us show some of the training images, for fun.


In [4]:
import matplotlib.pyplot as plt
import numpy as np

# functions to show an image


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


# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))


  dog plane truck truck
  1. Define a Convolution Neural Network ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Copy the neural network from the Neural Networks section before and modify it to take 3-channel images (instead of 1-channel images as it was defined).

In [20]:
from torch.autograd import Variable
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(3, 16, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(16, 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 = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


net = Net()
  1. Define a Loss function and optimizer ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Let's use a Classification Cross-Entropy loss and SGD with momentum

In [21]:
import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
  1. Train the network ^^^^^^^^^^^^^^^^^^^^

This is when things start to get interesting. We simply have to loop over our data iterator, and feed the inputs to the network and optimize


In [25]:
for epoch in range(5):  # 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')


[1,  2000] loss: 0.878
[1,  4000] loss: 0.874
[1,  6000] loss: 0.853
[1,  8000] loss: 0.884
[1, 10000] loss: 0.883
[1, 12000] loss: 0.918
[2,  2000] loss: 0.790
[2,  4000] loss: 0.807
[2,  6000] loss: 0.835
[2,  8000] loss: 0.846
[2, 10000] loss: 0.853
[2, 12000] loss: 0.883
[3,  2000] loss: 0.762
[3,  4000] loss: 0.771
[3,  6000] loss: 0.777
[3,  8000] loss: 0.817
[3, 10000] loss: 0.815
[3, 12000] loss: 0.844
[4,  2000] loss: 0.720
[4,  4000] loss: 0.739
[4,  6000] loss: 0.751
[4,  8000] loss: 0.770
[4, 10000] loss: 0.787
[4, 12000] loss: 0.816
[5,  2000] loss: 0.691
[5,  4000] loss: 0.723
[5,  6000] loss: 0.711
[5,  8000] loss: 0.737
[5, 10000] loss: 0.751
[5, 12000] loss: 0.786
Finished Training

In [26]:
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
for data in testloader:
    images, labels = data
    outputs = net(Variable(images))
    _, predicted = torch.max(outputs.data, 1)
    c = (predicted == labels).squeeze()
    for i in range(4):
        label = labels[i]
        class_correct[label] += c[i]
        class_total[label] += 1


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


Accuracy of plane : 79 %
Accuracy of   car : 78 %
Accuracy of  bird : 58 %
Accuracy of   cat : 30 %
Accuracy of  deer : 65 %
Accuracy of   dog : 62 %
Accuracy of  frog : 82 %
Accuracy of horse : 70 %
Accuracy of  ship : 62 %
Accuracy of truck : 66 %

Okay, so what next?

How do we run these neural networks on the GPU?

Training on GPU

Just like how you transfer a Tensor on to the GPU, you transfer the neural net onto the GPU. This will recursively go over all modules and convert their parameters and buffers to CUDA tensors:

.. code:: python

net.cuda()


Remember that you will have to send the inputs and targets at every step to the GPU too:

::

    inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())

Why dont I notice MASSIVE speedup compared to CPU? Because your network is realllly small.

Exercise: Try increasing the width of your network (argument 2 of the first nn.Conv2d, and argument 1 of the second nn.Conv2d – they need to be the same number), see what kind of speedup you get.

Goals achieved:

  • Understanding PyTorch's Tensor library and neural networks at a high level.
  • Train a small neural network to classify images

Where do I go next?

  • :doc:Train neural nets to play video games </intermediate/reinforcement_q_learning>
  • Train a state-of-the-art ResNet network on imagenet_
  • Train an face generator using Generative Adversarial Networks_
  • Train a word-level language model using Recurrent LSTM networks_
  • More examples_
  • More tutorials_
  • Discuss PyTorch on the Forums_
  • Chat with other users on Slack_

In [ ]: