Producing pictures with Keras and TensorFlow keen execution

The latest announcement of TensorFlow 2.0 names keen execution because the primary central function of the brand new main model. What does this imply for R customers?
As demonstrated in our latest put up on neural machine translation, you should utilize keen execution from R now already, together with Keras customized fashions and the datasets API. It’s good to know you can use it – however why must you? And by which circumstances?

On this and some upcoming posts, we need to present how keen execution could make growing fashions loads simpler. The diploma of simplication will depend upon the duty – and simply how a lot simpler you’ll discover the brand new method may also rely in your expertise utilizing the practical API to mannequin extra advanced relationships.
Even for those who assume that GANs, encoder-decoder architectures, or neural type switch didn’t pose any issues earlier than the appearance of keen execution, you would possibly discover that the choice is a greater match to how we people mentally image issues.

For this put up, we’re porting code from a latest Google Colaboratory pocket book implementing the DCGAN structure.(Radford, Metz, and Chintala 2015)
No prior information of GANs is required – we’ll preserve this put up sensible (no maths) and give attention to learn how to obtain your purpose, mapping a easy and vivid idea into an astonishingly small variety of strains of code.

As within the put up on machine translation with consideration, we first must cowl some conditions.
By the best way, no want to repeat out the code snippets – you’ll discover the whole code in eager_dcgan.R).

Conditions

The code on this put up relies on the most recent CRAN variations of a number of of the TensorFlow R packages. You may set up these packages as follows:

set up.packages(c("tensorflow", "keras", "tfdatasets"))

library(tensorflow)
install_tensorflow()

We’ll additionally use the tfdatasets package deal for our enter pipeline. So we find yourself with the next preamble to set issues up:

That’s it. Let’s get began.

So what’s a GAN?

GAN stands for Generative Adversarial Community(Goodfellow et al. 2014). It’s a setup of two brokers, the generator and the discriminator, that act in opposition to one another (thus, adversarial). It’s generative as a result of the purpose is to generate output (versus, say, classification or regression).

In human studying, suggestions – direct or oblique – performs a central position. Say we needed to forge a banknote (so long as these nonetheless exist). Assuming we will get away with unsuccessful trials, we might get higher and higher at forgery over time. Optimizing our approach, we might find yourself wealthy.
This idea of optimizing from suggestions is embodied within the first of the 2 brokers, the generator. It will get its suggestions from the discriminator, in an upside-down method: If it will probably idiot the discriminator, making it consider that the banknote was actual, all is okay; if the discriminator notices the pretend, it has to do issues in a different way. For a neural community, which means it has to replace its weights.

How does the discriminator know what’s actual and what’s pretend? It too needs to be skilled, on actual banknotes (or regardless of the form of objects concerned) and the pretend ones produced by the generator. So the whole setup is 2 brokers competing, one striving to generate realistic-looking pretend objects, and the opposite, to disavow the deception. The aim of coaching is to have each evolve and get higher, in flip inflicting the opposite to get higher, too.

On this system, there is no such thing as a goal minimal to the loss perform: We wish each parts to be taught and getter higher “in lockstep,” as an alternative of 1 successful out over the opposite. This makes optimization troublesome.
In apply due to this fact, tuning a GAN can appear extra like alchemy than like science, and it typically is smart to lean on practices and “tips” reported by others.

On this instance, identical to within the Google pocket book we’re porting, the purpose is to generate MNIST digits. Whereas that won’t sound like probably the most thrilling job one might think about, it lets us give attention to the mechanics, and permits us to maintain computation and reminiscence necessities (comparatively) low.

Let’s load the info (coaching set wanted solely) after which, have a look at the primary actor in our drama, the generator.

Coaching information

mnist <- dataset_mnist()
c(train_images, train_labels) %<-% mnist$prepare

train_images <- train_images %>% 
  k_expand_dims() %>%
  k_cast(dtype = "float32")

# normalize pictures to [-1, 1] as a result of the generator makes use of tanh activation
train_images <- (train_images - 127.5) / 127.5

Our full coaching set shall be streamed as soon as per epoch:

buffer_size <- 60000
batch_size <- 256
batches_per_epoch <- (buffer_size / batch_size) %>% spherical()

train_dataset <- tensor_slices_dataset(train_images) %>%
  dataset_shuffle(buffer_size) %>%
  dataset_batch(batch_size)

This enter shall be fed to the discriminator solely.

Generator

Each generator and discriminator are Keras customized fashions.
In distinction to customized layers, customized fashions mean you can assemble fashions as impartial models, full with customized ahead move logic, backprop and optimization. The model-generating perform defines the layers the mannequin (self) desires assigned, and returns the perform that implements the ahead move.

As we’ll quickly see, the generator will get handed vectors of random noise for enter. This vector is reworked to 3d (top, width, channels) after which, successively upsampled to the required output dimension of (28,28,3).

generator <-
  perform(title = NULL) {
    keras_model_custom(title = title, perform(self) {
      
      self$fc1 <- layer_dense(models = 7 * 7 * 64, use_bias = FALSE)
      self$batchnorm1 <- layer_batch_normalization()
      self$leaky_relu1 <- layer_activation_leaky_relu()
      self$conv1 <-
        layer_conv_2d_transpose(
          filters = 64,
          kernel_size = c(5, 5),
          strides = c(1, 1),
          padding = "identical",
          use_bias = FALSE
        )
      self$batchnorm2 <- layer_batch_normalization()
      self$leaky_relu2 <- layer_activation_leaky_relu()
      self$conv2 <-
        layer_conv_2d_transpose(
          filters = 32,
          kernel_size = c(5, 5),
          strides = c(2, 2),
          padding = "identical",
          use_bias = FALSE
        )
      self$batchnorm3 <- layer_batch_normalization()
      self$leaky_relu3 <- layer_activation_leaky_relu()
      self$conv3 <-
        layer_conv_2d_transpose(
          filters = 1,
          kernel_size = c(5, 5),
          strides = c(2, 2),
          padding = "identical",
          use_bias = FALSE,
          activation = "tanh"
        )
      
      perform(inputs, masks = NULL, coaching = TRUE) {
        self$fc1(inputs) %>%
          self$batchnorm1(coaching = coaching) %>%
          self$leaky_relu1() %>%
          k_reshape(form = c(-1, 7, 7, 64)) %>%
          self$conv1() %>%
          self$batchnorm2(coaching = coaching) %>%
          self$leaky_relu2() %>%
          self$conv2() %>%
          self$batchnorm3(coaching = coaching) %>%
          self$leaky_relu3() %>%
          self$conv3()
      }
    })
  }

Discriminator

The discriminator is only a fairly regular convolutional community outputting a rating. Right here, utilization of “rating” as an alternative of “chance” is on function: When you have a look at the final layer, it’s totally linked, of dimension 1 however missing the standard sigmoid activation. It is because in contrast to Keras’ loss_binary_crossentropy, the loss perform we’ll be utilizing right here – tf$losses$sigmoid_cross_entropy – works with the uncooked logits, not the outputs of the sigmoid.

discriminator <-
  perform(title = NULL) {
    keras_model_custom(title = title, perform(self) {
      
      self$conv1 <- layer_conv_2d(
        filters = 64,
        kernel_size = c(5, 5),
        strides = c(2, 2),
        padding = "identical"
      )
      self$leaky_relu1 <- layer_activation_leaky_relu()
      self$dropout <- layer_dropout(charge = 0.3)
      self$conv2 <-
        layer_conv_2d(
          filters = 128,
          kernel_size = c(5, 5),
          strides = c(2, 2),
          padding = "identical"
        )
      self$leaky_relu2 <- layer_activation_leaky_relu()
      self$flatten <- layer_flatten()
      self$fc1 <- layer_dense(models = 1)
      
      perform(inputs, masks = NULL, coaching = TRUE) {
        inputs %>% self$conv1() %>%
          self$leaky_relu1() %>%
          self$dropout(coaching = coaching) %>%
          self$conv2() %>%
          self$leaky_relu2() %>%
          self$flatten() %>%
          self$fc1()
      }
    })
  }

Setting the scene

Earlier than we will begin coaching, we have to create the standard parts of a deep studying setup: the mannequin (or fashions, on this case), the loss perform(s), and the optimizer(s).

Mannequin creation is only a perform name, with a bit further on high:

generator <- generator()
discriminator <- discriminator()

# https://www.tensorflow.org/api_docs/python/tf/contrib/keen/defun
generator$name = tf$contrib$keen$defun(generator$name)
discriminator$name = tf$contrib$keen$defun(discriminator$name)

defun compiles an R perform (as soon as per completely different mixture of argument shapes and non-tensor objects values)) right into a TensorFlow graph, and is used to hurry up computations. This comes with uncomfortable side effects and probably surprising habits – please seek the advice of the documentation for the small print. Right here, we have been primarily curious in how a lot of a speedup we would discover when utilizing this from R – in our instance, it resulted in a speedup of 130%.

On to the losses. Discriminator loss consists of two elements: Does it accurately determine actual pictures as actual, and does it accurately spot pretend pictures as pretend.
Right here real_output and generated_output include the logits returned from the discriminator – that’s, its judgment of whether or not the respective pictures are pretend or actual.

discriminator_loss <- perform(real_output, generated_output) {
  real_loss <- tf$losses$sigmoid_cross_entropy(
    multi_class_labels = k_ones_like(real_output),
    logits = real_output)
  generated_loss <- tf$losses$sigmoid_cross_entropy(
    multi_class_labels = k_zeros_like(generated_output),
    logits = generated_output)
  real_loss + generated_loss
}

Generator loss relies on how the discriminator judged its creations: It might hope for all of them to be seen as actual.

generator_loss <- perform(generated_output) {
  tf$losses$sigmoid_cross_entropy(
    tf$ones_like(generated_output),
    generated_output)
}

Now we nonetheless have to outline optimizers, one for every mannequin.

discriminator_optimizer <- tf$prepare$AdamOptimizer(1e-4)
generator_optimizer <- tf$prepare$AdamOptimizer(1e-4)

Coaching loop

There are two fashions, two loss features and two optimizers, however there is only one coaching loop, as each fashions depend upon one another.
The coaching loop shall be over MNIST pictures streamed in batches, however we nonetheless want enter to the generator – a random vector of dimension 100, on this case.

Let’s take the coaching loop step-by-step.
There shall be an outer and an internal loop, one over epochs and one over batches.
Initially of every epoch, we create a contemporary iterator over the dataset:

for (epoch in seq_len(num_epochs)) {
  begin <- Sys.time()
  total_loss_gen <- 0
  total_loss_disc <- 0
  iter <- make_iterator_one_shot(train_dataset)

until_out_of_range({
  batch <- iterator_get_next(iter)
  noise <- k_random_normal(c(batch_size, noise_dim))
  with(tf$GradientTape() %as% gen_tape, { with(tf$GradientTape() %as% disc_tape, {
    generated_images <- generator(noise)
    disc_real_output <- discriminator(batch, coaching = TRUE)
    disc_generated_output <-
       discriminator(generated_images, coaching = TRUE)
    gen_loss <- generator_loss(disc_generated_output)
    disc_loss <- discriminator_loss(disc_real_output, disc_generated_output)
  }) })

gradients_of_generator <-
  gen_tape$gradient(gen_loss, generator$variables)
gradients_of_discriminator <-
  disc_tape$gradient(disc_loss, discriminator$variables)
      
generator_optimizer$apply_gradients(purrr::transpose(
  record(gradients_of_generator, generator$variables)
))
discriminator_optimizer$apply_gradients(purrr::transpose(
  record(gradients_of_discriminator, discriminator$variables)
))
      
total_loss_gen <- total_loss_gen + gen_loss
total_loss_disc <- total_loss_disc + disc_loss

This ends the loop over batches. End off the loop over epochs displaying present losses and saving a number of of the generator’s art work:

cat("Time for epoch ", epoch, ": ", Sys.time() - begin, "n")
cat("Generator loss: ", total_loss_gen$numpy() / batches_per_epoch, "n")
cat("Discriminator loss: ", total_loss_disc$numpy() / batches_per_epoch, "nn")
if (epoch %% 10 == 0)
  generate_and_save_images(generator,
                           epoch,
                           random_vector_for_generation)

Right here’s the coaching loop once more, proven as an entire – even together with the strains for reporting on progress, it’s remarkably concise, and permits for a fast grasp of what’s going on:

prepare <- perform(dataset, epochs, noise_dim) {
  for (epoch in seq_len(num_epochs)) {
    begin <- Sys.time()
    total_loss_gen <- 0
    total_loss_disc <- 0
    iter <- make_iterator_one_shot(train_dataset)
    
    until_out_of_range({
      batch <- iterator_get_next(iter)
      noise <- k_random_normal(c(batch_size, noise_dim))
      with(tf$GradientTape() %as% gen_tape, { with(tf$GradientTape() %as% disc_tape, {
        generated_images <- generator(noise)
        disc_real_output <- discriminator(batch, coaching = TRUE)
        disc_generated_output <-
          discriminator(generated_images, coaching = TRUE)
        gen_loss <- generator_loss(disc_generated_output)
        disc_loss <-
          discriminator_loss(disc_real_output, disc_generated_output)
      }) })
      
      gradients_of_generator <-
        gen_tape$gradient(gen_loss, generator$variables)
      gradients_of_discriminator <-
        disc_tape$gradient(disc_loss, discriminator$variables)
      
      generator_optimizer$apply_gradients(purrr::transpose(
        record(gradients_of_generator, generator$variables)
      ))
      discriminator_optimizer$apply_gradients(purrr::transpose(
        record(gradients_of_discriminator, discriminator$variables)
      ))
      
      total_loss_gen <- total_loss_gen + gen_loss
      total_loss_disc <- total_loss_disc + disc_loss
      
    })
    
    cat("Time for epoch ", epoch, ": ", Sys.time() - begin, "n")
    cat("Generator loss: ", total_loss_gen$numpy() / batches_per_epoch, "n")
    cat("Discriminator loss: ", total_loss_disc$numpy() / batches_per_epoch, "nn")
    if (epoch %% 10 == 0)
      generate_and_save_images(generator,
                               epoch,
                               random_vector_for_generation)
    
  }
}

Right here’s the perform for saving generated pictures…

generate_and_save_images <- perform(mannequin, epoch, test_input) {
  predictions <- mannequin(test_input, coaching = FALSE)
  png(paste0("images_epoch_", epoch, ".png"))
  par(mfcol = c(5, 5))
  par(mar = c(0.5, 0.5, 0.5, 0.5),
      xaxs = 'i',
      yaxs = 'i')
  for (i in 1:25) {
    img <- predictions[i, , , 1]
    img <- t(apply(img, 2, rev))
    picture(
      1:28,
      1:28,
      img * 127.5 + 127.5,
      col = grey((0:255) / 255),
      xaxt = 'n',
      yaxt = 'n'
    )
  }
  dev.off()
}

… and we’re able to go!

num_epochs <- 150
prepare(train_dataset, num_epochs, noise_dim)

Outcomes

Listed below are some generated pictures after coaching for 150 epochs:

As they are saying, your outcomes will most actually range!

Conclusion

Whereas actually tuning GANs will stay a problem, we hope we have been in a position to present that mapping ideas to code shouldn’t be troublesome when utilizing keen execution. In case you’ve performed round with GANs earlier than, you will have discovered you wanted to pay cautious consideration to arrange the losses the appropriate method, freeze the discriminator’s weights when wanted, and many others. This want goes away with keen execution.
In upcoming posts, we’ll present additional examples the place utilizing it makes mannequin improvement simpler.