This topic describes how to use a Convolutional Neural Network (CNN) in Data Science Workshop (DSW) of Machine Learning Platform for AI to classify images. The dataset used in this topic is CIFAR10.

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 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', and 'truck'. The images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels in size.

Training an image classifier

  1. Load and normalizing the CIFAR10 training and test datasets using torchvision.
    Using torchvision, it is extremely easy to load CIFAR10.
    %matplotlib inline
    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].
    transform = transforms.Compose(
         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 =, batch_size=4,
                                              shuffle=True, num_workers=2)
    testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                           download=True, transform=transform)
    testloader =, batch_size=4,
                                             shuffle=False, num_workers=2)
    classes = ('plane', 'car', 'bird', 'cat',
               'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
    Let us show some of the training images, for fun.
    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 =
    # show images.
    # print labels.
    print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
    Images for model training
  2. Define a Convolutional Neural Network.
    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, 6, 5)
            self.pool = nn.MaxPool2d(2, 2)
            self.conv2 = nn.Conv2d(6, 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()
  3. Define a Loss function and optimizer.
    Let's use a Classification Cross-Entropy loss and SGD with momentum.
    import torch.optim as optim
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
  4. Train the network on the training data.
    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.
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    # Assuming that we are on a CUDA machine, this should print a CUDA device:
    The output is shown below.
    Use the GPU:
    The output is shown below.
      (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
      (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
      (fc1): Linear(in_features=400, out_features=120, bias=True)
      (fc2): Linear(in_features=120, out_features=84, bias=True)
      (fc3): Linear(in_features=84, out_features=10, bias=True)
    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; data is a list of [inputs, labels]
    #         inputs, labels = data
            inputs, labels = data[0].to(device), data[1].to(device)
            # zero the parameter gradients
            # forward + backward + optimize
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            # 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')
    The output is shown below.
    [1,  2000] loss: 2.192
    [1,  4000] loss: 1.882
    [1,  6000] loss: 1.698
    [1,  8000] loss: 1.564
    [1, 10000] loss: 1.513
    [1, 12000] loss: 1.464
    [2,  2000] loss: 1.391
    [2,  4000] loss: 1.363
    [2,  6000] loss: 1.331
    [2,  8000] loss: 1.296
    [2, 10000] loss: 1.302
    [2, 12000] loss: 1.287
    Finished Training
    Let's quickly save our trained model:
    PATH = './cifar_net.pth', PATH)
    For more details on saving PyTorch models see Serialization semantics.
  5. Test the network on the test data.

    We have trained the network for 2 passes over the training dataset. But we need to check if the network has learnt anything at all. We will check this by predicting the class label that the neural network outputs, and checking it against the ground-truth. If the prediction is correct, we add the sample to the list of correct predictions.

    Okay, first step. Let us display an image from the test set to get familiar.
    dataiter = iter(testloader)
    images, labels =
    # print images.
    print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
    Images in the testing dataset
    Next, let's load back in our saved model.
    Note Saving and re-loading the model wasn't necessary here, we only did it to illustrate how to do so.
    net = Net()
    Okay, now let us see what the neural network thinks these examples above are:
    outputs = net(images)
    The outputs are energies for the 10 classes. The higher the energy for a class, the more the network thinks that the image is of the particular class. So, let's get the index of the highest energy:
    _, predicted = torch.max(outputs, 1)
    print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                                  for j in range(4)))
    The output is shown below.
    Predicted:    cat  ship  ship  ship
    The results seem pretty good.
    Let us look at how the network performs on the whole dataset.
    correct = 0
    total = 0
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            outputs = net(images)
            _, predicted = torch.max(, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('Accuracy of the network on the 10000 test images: %d %%' % (
        100 * correct / total))
    The output is shown below.
    Accuracy of the network on the 10000 test images: 55 %
    That looks way better than chance, which is 10% accuracy (randomly picking a class out of 10 classes). Seems like the network learnt something.
    Hmmm, what are the classes that performed well, and the classes that did not perform well:
    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]))
    The output is shown below.
    Accuracy of plane : 75 %
    Accuracy of   car : 77 %
    Accuracy of  bird : 35 %
    Accuracy of   cat : 29 %
    Accuracy of  deer : 42 %
    Accuracy of   dog : 52 %
    Accuracy of  frog : 46 %
    Accuracy of horse : 69 %
    Accuracy of  ship : 61 %
    Accuracy of truck : 61 %