KDnuggets Home » News » 2017 » Jun » Tutorials, Overviews » Deep Learning with R + Keras ( 17:n25 )

Deep Learning with R + Keras


Keras has grown in popularity and supported on a wide set of platforms including Tensorflow, CNTK, Apple’s CoreML, and Theano. It is becoming the de factor language for deep learning.



By Rajiv Shah, Data Scientist, Professor.

For R users, there hasn’t been a production grade solution for deep learning (sorry MXNET). This post introduces the Keras interface for R and how it can be used to perform image classification. The post ends by providing some code snippets that show Keras is intuitive and powerful.

R + Keras

 

Tensorflow

 
Last January, Tensorflow for R was released, which provided access to the Tensorflow API from R. This was signficant, as Tensorflow is the most popular library for deep learning. However, for most R users, the Tensorflow for R interface was not very R like. Take a look at this code chunk for training a model:

cross_entropy <- tf$reduce_mean(-tf$reduce_sum(y_ * tf$log(y_conv), reduction_indices=1L))
train_step <- tf$train$AdamOptimizer(1e-4)$minimize(cross_entropy)
correct_prediction <- tf$equal(tf$argmax(y_conv, 1L), tf$argmax(y_, 1L))
accuracy <- tf$reduce_mean(tf$cast(correct_prediction, tf$float32))
sess$run(tf$global_variables_initializer())

for (i in 1:20000) {
  batch <- mnist$train$next_batch(50L)
  if (i %% 100 == 0) {
    train_accuracy <- accuracy$eval(feed_dict = dict(
        x = batch[[1]], y_ = batch[[2]], keep_prob = 1.0))
    cat(sprintf("step %d, training accuracy %g\n", i, train_accuracy))
  }
  train_step$run(feed_dict = dict(
    x = batch[[1]], y_ = batch[[2]], keep_prob = 0.5))
}

test_accuracy <- accuracy$eval(feed_dict = dict(
     x = mnist$test$images, y_ = mnist$test$labels, keep_prob = 1.0))
cat(sprintf("test accuracy %g", test_accuracy))


Yikes!

Unless you are familiar with Tensorflow, it’s not readily apparent what is going on. A quick search on Github finds less than a 100 code results using Tensorflow for R. 😔

 

Keras

 
All this is going to change with Keras and R! ☺️

For background, Keras is a high-level neural network API that is designed for experimentation and can run on top of Tensorflow. Keras is what data scientists like to use. 🤓 Keras has grown in popularity and supported on a wide set of platforms including Tensorflow, CNTK, Apple’s CoreML, and Theano. It is becoming the de factor language for deep learning.

As a simple example, here is the code to train a model in Keras:

model_top %>% fit(
        x = train_x, y = train_y,
        epochs=epochs, 
        batch_size=batch_size,
        validation_data=valid)


 

Image Classification with Keras

 
So if you are still with me, let me show you how to build deep learning models using R, Keras, and Tensorflow together. You will find a Github repo at https://github.com/rajshah4/image_keras/ that contains the code and data you will need. Included is an R notebook (and Python notebooks) that walk through buiding an image classifier (telling 🐱 from 🐶), but can easily be generalized to other images. The walk through includes advanced methods that are commonly used for production deep learning work including:

  • augmenting data
  • using the bottleneck features of a pre-trained network
  • fine-tuning the top layers of a pre-trained network
  • saving weights of models

 

Code Snippets of Keras

 
The R interface to Keras truly makes it easy to build deep learning models in R. Here are some code snippets to illustrate how intuitive and useful Keras for R is:

To load 🖼 from a folder:

train_generator <- flow_images_from_directory(train_directory, generator = image_data_generator(), target_size = c(img_width, img_height), color_mode = "rgb",
  class_mode = "binary", batch_size = batch_size, shuffle = TRUE,
  seed = 123)


To define a simple convolutional neural network:

model <- keras_model_sequential()

model %>%
  layer_conv_2d(filter = 32, kernel_size = c(3,3), input_shape = c(img_width, img_height, 3)) %>%
  layer_activation("relu") %>%
  layer_max_pooling_2d(pool_size = c(2,2)) %>% 
  
  layer_conv_2d(filter = 32, kernel_size = c(3,3)) %>%
  layer_activation("relu") %>%
  layer_max_pooling_2d(pool_size = c(2,2)) %>%
  
  layer_conv_2d(filter = 64, kernel_size = c(3,3)) %>%
  layer_activation("relu") %>%
  layer_max_pooling_2d(pool_size = c(2,2)) %>%
  
  layer_flatten() %>%
  layer_dense(64) %>%
  layer_activation("relu") %>%
  layer_dropout(0.5) %>%
  layer_dense(1) %>%
  layer_activation("sigmoid")


To augment data:

augment <- image_data_generator(rescale=1./255,
                               shear_range=0.2,
                               zoom_range=0.2,
                               horizontal_flip=TRUE)


To load a pretrained network:

model_vgg <- application_vgg16(include_top = FALSE, weights = "imagenet")


To save model weights:

save_model_weights_hdf5(model_ft, 'finetuning_30epochs_vggR.h5', overwrite = TRUE)


I believe the Keras for R interface will make it much easier for R users and the R community to build and refine deep learning models with R. This means you don’t have to force everyone to use Python to build, refine, and test your models. I really think this will open up deep learning to a wider audience that was a bit apprehensive on using python. So for now, give it a spin!

Grab my repo, fire up RStudio (or your IDE of choice), and go build a simple classifier using Keras.

 
Bio: Rajiv Shah has a passion for understanding the dynamics between technology and people. He was educated as an electrical engineer, went to law school, but found in communications a home for his research. Rajiv left academia a few years ago and now works as a data scientist. He is always looking for new projects that engage me.

Original. Reposted with permission.

Related: