Frequently Asked Questions

How should I cite Keras?

Please cite Keras in your publications if it helps your research. Here is an example BibTeX entry:

@misc{chollet2017kerasR,
  title={R Interface to Keras},
  author={Chollet, Fran\c{c}ois and Allaire, JJ and others},
  year={2017},
  publisher={GitHub},
  howpublished={\url{https://github.com/rstudio/keras}},
}

How can I run Keras on a GPU?

Note that installation and configuration of the GPU-based backends can take considerably more time and effort. So if you are just getting started with Keras you may want to stick with the CPU version initially, then install the appropriate GPU version once your training becomes more computationally demanding.

Below are instructions for installing and enabling GPU support for the various supported backends.

Sys.setenv(KERAS_BACKEND = "keras")
Sys.setenv(THEANO_FLAGS = "device=gpu,floatX=float32")
library(keras)

How can I run a Keras model on multiple GPUs?

We recommend doing so using the TensorFlow backend. There are two ways to run a single model on multiple GPUs: data parallelism and device parallelism.

In most cases, what you need is most likely data parallelism.

# Replicates `model` on 8 GPUs.
# This assumes that your machine has 8 available GPUs.
parallel_model <- multi_gpu_model(model, gpus=8)
parallel_model %>% compile(
  loss = "categorical_crossentropy",
  optimizer = "rmsprop"
)

# This `fit` call will be distributed on 8 GPUs.
# Since the batch size is 256, each GPU will process 32 samples.
parallel_model %>% fit(x, y, epochs = 20, batch_size = 256)

# Model where a shared LSTM is used to encode two different sequences in parallel
input_a <- layer_input(shape = c(140, 256))
input_b <- layer_input(shape = c(140, 256))

shared_lstm <- layer_lstm(units = 64)

# Process the first sequence on one GPU
library(tensorflow)
with(tf$device_scope("/gpu:0", {
  encoded_a <- shared_lstm(tweet_a)
}):

# Process the next sequence on another GPU
with(tf$device_scope("/gpu:1", {
  encoded_b <- shared_lstm(tweet_b)
}):

# Concatenate results on CPU
with(tf$device_scope("/cpu:0", {
  merged_vector <- layer_concatenate(list(encoded_a, encoded_b))
}):

What does “sample”, “batch”, “epoch” mean?

Below are some common definitions that are necessary to know and understand to correctly utilize Keras:

• Sample: one element of a dataset.
  • Example: one image is a sample in a convolutional network
  • Example: one audio file is a sample for a speech recognition model
• Batch: a set of N samples. The samples in a batch are processed independently, in parallel. If training, a batch results in only one update to the model.
  • A batch generally approximates the distribution of the input data better than a single input. The larger the batch, the better the approximation; however, it is also true that the batch will take longer to process and will still result in only one update. For inference (evaluate/predict), it is recommended to pick a batch size that is as large as you can afford without going out of memory (since larger batches will usually result in faster evaluating/prediction).
• Epoch: an arbitrary cutoff, generally defined as “one pass over the entire dataset”, used to separate training into distinct phases, which is useful for logging and periodic evaluation.
  • When using evaluation_data or evaluation_split with the fit method of Keras models, evaluation will be run at the end of every epoch.
  • Within Keras, there is the ability to add callbacks specifically designed to be run at the end of an epoch. Examples of these are learning rate changes and model checkpointing (saving).

Why are Keras objects modified in place?

Unlike most R objects, Keras objects are “mutable”. That means that when you modify an object you’re modifying it “in place”, and you don’t need to assign the updated object back to the original name. For example, to add layers to a Keras model you might use this code:

model %>%
  layer_dense(units = 32, activation = 'relu', input_shape = c(784)) %>%
  layer_dense(units = 10, activation = 'softmax')

Rather than this code:

model <- model %>%
  layer_dense(units = 32, activation = 'relu', input_shape = c(784)) %>%
  layer_dense(units = 10, activation = 'softmax')

You need to be aware of this because it makes the Keras API a little different than most other pipelines you may have used, but it’s necessary to match the data structures and behavior of the underlying Keras library.

How can I save a Keras model?

save_model_hdf5(model, 'my_model.h5')
model <- load_model_hdf5('my_model.h5')

json_string <- model_to_json(model)
yaml_string <- model_to_yaml(model)

model <- model_from_json(json_string)
model <- model_from_yaml(yaml_string)

save_model_weights_hdf5('my_model_weights.h5')

model %>% load_model_weights_hdf5('my_model_weights.h5')

model %>% load_model_weights_hdf5('my_model_weights.h5', by_name = TRUE)

# assuming the original model looks like this:
#   model <- keras_model_sequential()
#   model %>%
#     layer_dense(units = 2, input_dim = 3, name = "dense 1") %>%
#     layer_dense(units = 3, name = "dense_3") %>%
#     ...
#   save_model_weights(model, fname)

# new model
model <- keras_model_sequential()
model %>%
  layer_dense(units = 2, input_dim = 3, name = "dense 1") %>%  # will be loaded
  layer_dense(units = 3, name = "dense_3")                     # will not be loaded

# load weights from first model; will only affect the first layer, dense_1.
load_model_weights(fname, by_name = TRUE)

Why is the training loss much higher than the testing loss?

A Keras model has two modes: training and testing. Regularization mechanisms, such as Dropout and L1/L2 weight regularization, are turned off at testing time.

Besides, the training loss is the average of the losses over each batch of training data. Because your model is changing over time, the loss over the first batches of an epoch is generally higher than over the last batches. On the other hand, the testing loss for an epoch is computed using the model as it is at the end of the epoch, resulting in a lower loss.

How can I obtain the output of an intermediate layer?

One simple way is to create a new Model that will output the layers that you are interested in:

model <- ...  # create the original model

layer_name <- 'my_layer'
intermediate_layer_model <- keras_model(inputs = model$input,
                                        outputs = get_layer(model, layer_name)$output)
intermediate_output <- predict(intermediate_layer_model, data)

How can I use Keras with datasets that don’t fit in memory?

sampling_generator <- function(X_data, Y_data, batch_size) {
  function() {
    rows <- sample(1:nrow(X_data), batch_size, replace = TRUE)
    list(X_data[rows,], Y_data[rows,])
  }
}

model %>%
  fit_generator(sampling_generator(X_train, Y_train, batch_size = 128),
                steps_per_epoch = nrow(X_train) / 128, epochs = 10)

data_files_generator <- function(dir) {

  files < list.files(dir)
  next_file <- 0

  function() {

    # move to the next file (note the <<- assignment operator)
    next_file <<- next_file + 1

    # if we've exhausted all of the files then start again at the
    # beginning of the list (keras generators need to yield
    # data infinitely -- termination is controlled by the epochs
    # and steps_per_epoch arguments to fit_generator())
    if (next_file > length(files))
      next_file <<- 1

    # determine the file name
    file <- files[[next_file]]

    # process and return the data in the file. note that in a
    # real example you'd further subdivide the data within the
    # file into appropriately sized training batches. this
    # would make this function much more complicated so we
    # don't demonstrated it here
    file_to_training_data(file)
  }
}

How can I interrupt training when the validation loss isn’t decreasing anymore?

You can use an early stopping callback:

early_stopping <- callback_early_stopping(monitor = 'val_loss', patience = 2)
model %>% fit(X, y, validation_split = 0.2, callbacks = c(early_stopping))

Find out more in the callbacks documentation.

How is the validation split computed?

If you set the validation_split argument in fit to e.g. 0.1, then the validation data used will be the last 10% of the data. If you set it to 0.25, it will be the last 25% of the data, etc. Note that the data isn’t shuffled before extracting the validation split, so the validation is literally just the last x% of samples in the input you passed.

The same validation set is used for all epochs (within a same call to fit).

Is the data shuffled during training?

Yes, if the shuffle argument in fit is set to TRUE (which is the default), the training data will be randomly shuffled at each epoch.

Validation data is never shuffled.

How can I record the training / validation loss / accuracy at each epoch?

The model.fit method returns an History callback, which has a history attribute containing the lists of successive losses and other metrics.

hist <- model %>% fit(X, y, validation_split=0.2)
hist$history

How can I “freeze” Keras layers?

To “freeze” a layer means to exclude it from training, i.e. its weights will never be updated. This is useful in the context of fine-tuning a model, or using fixed embeddings for a text input.

You can pass a trainable argument (boolean) to a layer constructor to set a layer to be non-trainable:

frozen_layer <- layer_dense(units = 32, trainable = FALSE)

Additionally, you can set the trainable property of a layer to TRUE or FALSE after instantiation. For this to take effect, you will need to call compile() on your model after modifying the trainable property. Here’s an example:

x <- layer_input(shape = c(32))
layer <- layer_dense(units = 32)
layer$trainable <- FALSE
y <- x %>% layer

frozen_model <- keras_model(x, y)
# in the model below, the weights of `layer` will not be updated during training
frozen_model %>% compile(optimizer = 'rmsprop', loss = 'mse')

layer$trainable <- TRUE
trainable_model <- keras_model(x, y)
# with this model the weights of the layer will be updated during training
# (which will also affect the above model since it uses the same layer instance)
trainable_model %>% compile(optimizer = 'rmsprop', loss = 'mse')

frozen_model %>% fit(data, labels)  # this does NOT update the weights of `layer`
trainable_model %>% fit(data, labels)  # this updates the weights of `layer`

Finally, you can freeze or unfreeze the weights for an entire model (or a range of layers within the model) using the freeze_weights() and unfreeze_weights() functions. For example:

# instantiate a VGG16 model
conv_base <- application_vgg16(
  weights = "imagenet",
  include_top = FALSE,
  input_shape = c(150, 150, 3)
)

# freeze it's weights
freeze_weights(conv_base)

# create a composite model that includes the base + more layers
model <- keras_model_sequential() %>%
  conv_base %>%
  layer_flatten() %>%
  layer_dense(units = 256, activation = "relu") %>%
  layer_dense(units = 1, activation = "sigmoid")

# compile
model %>% compile(
  loss = "binary_crossentropy",
  optimizer = optimizer_rmsprop(lr = 2e-5),
  metrics = c("accuracy")
)

# unfreeze weights from "block5_conv1" on
unfreeze_weights(conv_base, from = "block5_conv1")

# compile again since we froze or unfroze layers
model %>% compile(
  loss = "binary_crossentropy",
  optimizer = optimizer_rmsprop(lr = 2e-5),
  metrics = c("accuracy")
)

How can I use stateful RNNs?

Making a RNN stateful means that the states for the samples of each batch will be reused as initial states for the samples in the next batch.

When using stateful RNNs, it is therefore assumed that:

• all batches have the same number of samples
• If X1 and X2 are successive batches of samples, then X2[[i]] is the follow-up sequence to X1[[i], for every i.

To use statefulness in RNNs, you need to:

• explicitly specify the batch size you are using, by passing a batch_size argument to the first layer in your model. E.g. batch_size=32 for a 32-samples batch of sequences of 10 timesteps with 16 features per timestep.
• set stateful=TRUE in your RNN layer(s).
• specify shuffle=FALSE when calling fit().

To reset the states accumulated in either a single layer or an entire model use the reset_states() function.

Notes that the methods predict(), fit(), train_on_batch(), predict_classes(), etc. will all update the states of the stateful layers in a model. This allows you to do not only stateful training, but also stateful prediction.

How can I remove a layer from a Sequential model?

You can remove the last added layer in a Sequential model by calling pop_layer():

model <- keras_model_sequential()
model %>%
  layer_dense(units = 32, activation = 'relu', input_shape = c(784)) %>%
  layer_dense(units = 32, activation = 'relu') %>%
  layer_dense(units = 32, activation = 'relu')

length(model$layers)     # "3"
model %>% pop_layer()
length(model$layers)     # "2"

How can I use pre-trained models in Keras?

Code and pre-trained weights are available for the following image classification models:

• Xception
• VGG16
• VGG19
• ResNet50
• InceptionV3
• InceptionResNetV2
• MobileNet
• MobileNetV2
• DenseNet
• NASNet

For example:

model <- application_vgg16(weights = 'imagenet', include_top = TRUE)

For a few simple usage examples, see the documentation for the Applications module.

The VGG16 model is also the basis for the Deep dream Keras example script.

How can I use other Keras backends?

By default the Keras Python and R packages use the TensorFlow backend. Other available backends include Theano or CNTK. To learn more about using alternatate backends (e.g. Theano or CNTK) see the article on Keras backends.

How can I use the PlaidML backend?

PlaidML is an open source portable deep learning engine that runs on most existing PC hardware with OpenCL-capable GPUs from NVIDIA, AMD, or Intel. PlaidML includes a Keras backend which you can use as described below.

First, build and install PlaidML as described on the project website. You must be sure that PlaidML is correctly installed, setup, and working before proceeding further!

Then, to use Keras with the PlaidML backend you do the following:

library(keras)
use_backend("plaidml")

This should automatically discover and use the Python environment where plaidml and plaidml-keras were installed. If this doesn’t work as expected you can also force the selection of a particular Python environment. For example, if you installed PlaidML in conda environment named “plaidml” you would do this:

library(keras)
use_condaenv("plaidml")
use_backend("plaidml")

How can I use Keras in another R package?

# testthat utilty for skipping tests when Keras isn't available
skip_if_no_keras <- function(version = NULL) {
  if (!is_keras_available(version))
    skip("Required keras version not available for testing")
}

# use the function within a test
test_that("keras function works correctly", {
  skip_if_no_keras()
  # test code here
})

# Keras Python module
keras <- NULL

# Obtain a reference to the module from the keras R package
.onLoad <- function(libname, pkgname) {
  keras <<- keras::implementation()
}

How can I obtain reproducible results using Keras during development?

During development of a model, sometimes it is useful to be able to obtain reproducible results from run to run in order to determine if a change in performance is due to an actual model or data modification, or merely a result of a new random sample.

The use_session_with_seed() function establishes a common random seed for R, Python, NumPy, and TensorFlow. It furthermore disables hash randomization, GPU computations, and CPU parallelization, which can be additional sources of non-reproducibility.

To use the function, call it immediately after you load the keras package:

library(keras)
use_session_with_seed(42)

# ...rest of code follows...

This function takes all measures known to promote reproducible results from Keras sessions, however it’s possible that various individual features or libraries used by the backend escape its effects. If you encounter non-reproducible results please investigate the possible sources of the problem. The source code for use_session_with_seed() is here: https://github.com/rstudio/tensorflow/blob/main/R/seed.R. Contributions via pull request are very welcome!

Please note again that use_session_with_seed() disables GPU computations and CPU parallelization by default (as both can lead to non-deterministic computations) so should generally not be used when model training time is paramount. You can re-enable GPU computations and/or CPU parallelism using the disable_gpu and disable_parallel_cpu arguments. For example:

library(keras)
use_session_with_seed(42, disable_gpu = FALSE, disable_parallel_cpu = FALSE)

Where is the Keras configuration filed stored?

The default directory where all Keras data is stored is:

~/.keras/

In case Keras cannot create the above directory (e.g. due to permission issues), /tmp/.keras/ is used as a backup.

The Keras configuration file is a JSON file stored at $HOME/.keras/keras.json. The default configuration file looks like this:

{
    "image_data_format": "channels_last",
    "epsilon": 1e-07,
    "floatx": "float32",
    "backend": "tensorflow"
}

It contains the following fields:

• The image data format to be used as default by image processing layers and utilities (either channels_last or channels_first).
• The epsilon numerical fuzz factor to be used to prevent division by zero in some operations.
• The default float data type.
• The default backend (this will always be “tensorflow” in the R interface to Keras)

Likewise, cached dataset files, such as those downloaded with get_file(), are stored by default in $HOME/.keras/datasets/.