Basic Image Classification

Setup the layers

The basic building block of a neural network is the layer. Layers extract representations from the data fed into them. And, hopefully, these representations are more meaningful for the problem at hand.

Most of deep learning consists of chaining together simple layers. Most layers, like layer_dense, have parameters that are learned during training.

model <- keras_model_sequential()
model %>%
  layer_flatten(input_shape = c(28, 28)) %>%
  layer_dense(units = 128, activation = 'relu') %>%
  layer_dense(units = 10, activation = 'softmax')

The first layer in this network, layer_flatten, transforms the format of the images from a 2d-array (of 28 by 28 pixels), to a 1d-array of 28 * 28 = 784 pixels. Think of this layer as unstacking rows of pixels in the image and lining them up. This layer has no parameters to learn; it only reformats the data.

After the pixels are flattened, the network consists of a sequence of two dense layers. These are densely-connected, or fully-connected, neural layers. The first dense layer has 128 nodes (or neurons). The second (and last) layer is a 10-node softmax layer —this returns an array of 10 probability scores that sum to 1. Each node contains a score that indicates the probability that the current image belongs to one of the 10 digit classes.

Compile the model

Before the model is ready for training, it needs a few more settings. These are added during the model’s compile step:

• Loss function — This measures how accurate the model is during training. We want to minimize this function to “steer” the model in the right direction.
• Optimizer — This is how the model is updated based on the data it sees and its loss function.
• Metrics —Used to monitor the training and testing steps. The following example uses accuracy, the fraction of the images that are correctly classified.

model %>% compile(
  optimizer = 'adam', 
  loss = 'sparse_categorical_crossentropy',
  metrics = c('accuracy')
)

Train the model

Training the neural network model requires the following steps:

• Feed the training data to the model — in this example, the train_images and train_labels arrays.
• The model learns to associate images and labels.
• We ask the model to make predictions about a test set — in this example, the test_images array. We verify that the predictions match the labels from the test_labels array.

To start training, call the fit method — the model is “fit” to the training data:

model %>% fit(train_images, train_labels, epochs = 5, verbose = 2)

## Train on 60000 samples
## Epoch 1/5
## 60000/60000 - 2s - loss: 0.4945 - accuracy: 0.8262
## Epoch 2/5
## 60000/60000 - 2s - loss: 0.3751 - accuracy: 0.8643
## Epoch 3/5
## 60000/60000 - 2s - loss: 0.3354 - accuracy: 0.8758
## Epoch 4/5
## 60000/60000 - 2s - loss: 0.3135 - accuracy: 0.8854
## Epoch 5/5
## 60000/60000 - 2s - loss: 0.2956 - accuracy: 0.8918

As the model trains, the loss and accuracy metrics are displayed. This model reaches an accuracy of about 0.88 (or 88%) on the training data.

Evaluate accuracy

Next, compare how the model performs on the test dataset:

score <- model %>% evaluate(test_images, test_labels, verbose = 0)

cat('Test loss:', score$loss, "\n")

## Test loss: 0.3870942

cat('Test accuracy:', score$acc, "\n")

## Test accuracy: 0.8644

10000/10000 [==============================] - 0s 19us/step
Test loss: 0.3755946 
Test accuracy: 0.8644 

It turns out, the accuracy on the test dataset is a little less than the accuracy on the training dataset. This gap between training accuracy and test accuracy is an example of overfitting. Overfitting is when a machine learning model performs worse on new data than on their training data.

Make predictions

With the model trained, we can use it to make predictions about some images.

predictions <- model %>% predict(test_images)

Here, the model has predicted the label for each image in the testing set. Let’s take a look at the first prediction:

predictions[1, ]

##  [1] 5.465935e-06 1.288366e-07 3.570543e-06 1.659937e-08 2.075325e-05
##  [6] 1.836076e-02 2.499909e-06 1.217376e-01 2.614871e-05 8.598431e-01

A prediction is an array of 10 numbers. These describe the “confidence” of the model that the image corresponds to each of the 10 different articles of clothing. We can see which label has the highest confidence value:

which.max(predictions[1, ])

## [1] 10

Alternatively, we can also directly get the class prediction:

class_pred <- model %>% predict_classes(test_images)
class_pred[1:20]

##  [1] 9 2 1 1 6 1 4 6 5 7 4 5 5 3 4 1 2 2 8 0

As the labels are 0-based, this actually means a predicted label of 9 (to be found in class_names[9]). So the model is most confident that this image is an ankle boot. And we can check the test label to see this is correct:

test_labels[1]

## [1] 9

Let’s plot several images with their predictions. Correct prediction labels are green and incorrect prediction labels are red.

par(mfcol=c(5,5))
par(mar=c(0, 0, 1.5, 0), xaxs='i', yaxs='i')
for (i in 1:25) { 
  img <- test_images[i, , ]
  img <- t(apply(img, 2, rev)) 
  # subtract 1 as labels go from 0 to 9
  predicted_label <- which.max(predictions[i, ]) - 1
  true_label <- test_labels[i]
  if (predicted_label == true_label) {
    color <- '#008800' 
  } else {
    color <- '#bb0000'
  }
  image(1:28, 1:28, img, col = gray((0:255)/255), xaxt = 'n', yaxt = 'n',
        main = paste0(class_names[predicted_label + 1], " (",
                      class_names[true_label + 1], ")"),
        col.main = color)
}

Finally, use the trained model to make a prediction about a single image.

# Grab an image from the test dataset
# take care to keep the batch dimension, as this is expected by the model
img <- test_images[1, , , drop = FALSE]
dim(img)

## [1]  1 28 28

Now predict the image:

predictions <- model %>% predict(img)
predictions

##              [,1]         [,2]         [,3]         [,4]         [,5]
## [1,] 5.465944e-06 1.288367e-07 3.570535e-06 1.659934e-08 2.075324e-05
##            [,6]         [,7]      [,8]         [,9]    [,10]
## [1,] 0.01836077 2.499906e-06 0.1217377 2.614871e-05 0.859843

predict returns a list of lists, one for each image in the batch of data. Grab the predictions for our (only) image in the batch:

# subtract 1 as labels are 0-based
prediction <- predictions[1, ] - 1
which.max(prediction)

## [1] 10

Or, directly getting the class prediction again:

class_pred <- model %>% predict_classes(img)
class_pred

## [1] 9

And, as before, the model predicts a label of 9.