knitr::opts_chunk$set(echo = TRUE, eval = FALSE)
Keras is a high-level API to build and train deep learning models. It’s used for fast prototyping, advanced research, and production, with three key advantages:
To get started, load the keras
library:
library(keras)
In Keras, you assemble layers to build models. A model is (usually)
a graph of layers. The most common type of model is a stack of layers:
the sequential
model.
To build a simple, fully-connected network (i.e., a multi-layer perceptron):
model <- keras_model_sequential() model %>% # Adds a densely-connected layer with 64 units to the model: layer_dense(units = 64, activation = 'relu') %>% # Add another: layer_dense(units = 64, activation = 'relu') %>% # Add a softmax layer with 10 output units: layer_dense(units = 10, activation = 'softmax')
There are many layers
available with some common constructor
parameters:
activation
: Set the activation function for the layer. By default, no activation is applied.kernel_initializer
and bias_initializer
: The initialization
schemes that create the layer’s weights (kernel and bias). This defaults to the
Glorot uniform
initializer.kernel_regularizer
and bias_regularizer
: The regularization
schemes that apply to the layer’s weights (kernel and bias), such as L1
or L2 regularization. By default, no regularization is applied.The following instantiates dense
layers using
constructor arguments:
# Create a sigmoid layer: layer_dense(units = 64, activation ='sigmoid') # A linear layer with L1 regularization of factor 0.01 applied to the kernel matrix: layer_dense(units = 64, kernel_regularizer = regularizer_l1(0.01)) # A linear layer with L2 regularization of factor 0.01 applied to the bias vector: layer_dense(units = 64, bias_regularizer = regularizer_l2(0.01)) # A linear layer with a kernel initialized to a random orthogonal matrix: layer_dense(units = 64, kernel_initializer = 'orthogonal') # A linear layer with a bias vector initialized to 2.0: layer_dense(units = 64, bias_initializer = initializer_constant(2.0))
After the model is constructed, configure its learning process by
calling the compile
method:
model %>% compile( optimizer = 'adam', loss = 'categorical_crossentropy', metrics = list('accuracy') )
compile
takes three important arguments:
optimizer
: This object specifies the training procedure. Commonly used optimizers are e.g.adam
,
rmsprop
, or
sgd
.loss
: The function to minimize during optimization. Common choices
include mean square error (mse
), categorical_crossentropy
, and
binary_crossentropy
.metrics
: Used to monitor training. In classification, this usually is accuracy.The following shows a few examples of configuring a model for training:
# Configure a model for mean-squared error regression. model %>% compile( optimizer = 'adam', loss = 'mse', # mean squared error metrics = list('mae') # mean absolute error ) # Configure a model for categorical classification. model %>% compile( optimizer = optimizer_rmsprop(lr = 0.01), loss = "categorical_crossentropy", metrics = list("categorical_accuracy") )
You can train keras models directly on R matrices and arrays (possibly created from R data.frames
).
A model is fit to the training data using the fit
method:
data <- matrix(rnorm(1000 * 32), nrow = 1000, ncol = 32) labels <- matrix(rnorm(1000 * 10), nrow = 1000, ncol = 10) model %>% fit( data, labels, epochs = 10, batch_size = 32 )
fit
takes three important arguments:
epochs
: Training is structured into epochs. An epoch is one
iteration over the entire input data (this is done in smaller
batches).batch_size
: When passed matrix or array data, the model slices the data into
smaller batches and iterates over these batches during training.
This integer specifies the size of each batch. Be aware that the
last batch may be smaller if the total number of samples is not
divisible by the batch size.validation_data
: When prototyping a model, you want to easily
monitor its performance on some validation data. Passing this
argument — a list of inputs and labels — allows the model to display
the loss and metrics in inference mode for the passed data, at the
end of each epoch.Here’s an example using validation_data
:
data <- matrix(rnorm(1000 * 32), nrow = 1000, ncol = 32) labels <- matrix(rnorm(1000 * 10), nrow = 1000, ncol = 10) val_data <- matrix(rnorm(1000 * 32), nrow = 100, ncol = 32) val_labels <- matrix(rnorm(100 * 10), nrow = 100, ncol = 10) model %>% fit( data, labels, epochs = 10, batch_size = 32, validation_data = list(val_data, val_labels) )
Same as fit
, the evaluate
and predict
methods can
use raw R data as well as a dataset
.
To evaluate the inference-mode loss and metrics for the data provided:
model %>% evaluate(test_data, test_labels, batch_size = 32) model %>% evaluate(test_dataset, steps = 30)
And to predict the output of the last layer in inference for the data
provided, again as R data as well as a dataset
:
model %>% predict(test_data, batch_size = 32) model %>% predict(test_dataset, steps = 30)
The sequential
model is a simple stack of layers that cannot
represent arbitrary models. Use the Keras functional
API
to build complex model topologies such as:
Building a model with the functional API works like this:
keras_model
instance.sequential
model.The following example uses the functional API to build a simple, fully-connected network:
inputs <- layer_input(shape = (32)) # Returns a placeholder tensor predictions <- inputs %>% layer_dense(units = 64, activation = 'relu') %>% layer_dense(units = 64, activation = 'relu') %>% layer_dense(units = 10, activation = 'softmax') # Instantiate the model given inputs and outputs. model <- keras_model(inputs = inputs, outputs = predictions) # The compile step specifies the training configuration. model %>% compile( optimizer = optimizer_rmsprop(lr = 0.001), loss = 'categorical_crossentropy', metrics = list('accuracy') ) # Trains for 5 epochs model %>% fit( data, labels, batch_size = 32, epochs = 5 )
To create a custom Keras layer, you create an R6 class derived from KerasLayer
. There are three methods to implement (only one of which, call()
, is required for all types of layer):
build(input_shape)
: This is where you will define your weights. Note that if your layer doesn’t define trainable weights then you need not implement this method.call(x)
: This is where the layer’s logic lives. Unless you want your layer to support masking, you only have to care about the first argument passed to call: the input tensor.compute_output_shape(input_shape)
: In case your layer modifies the shape of its input, you should specify here the shape transformation logic. This allows Keras to do automatic shape inference. If you don’t modify the shape of the input then you need not implement this method.Here is an example custom layer that performs a matrix multiplication:
library(keras) CustomLayer <- R6::R6Class("CustomLayer", inherit = KerasLayer, public = list( output_dim = NULL, kernel = NULL, initialize = function(output_dim) { self$output_dim <- output_dim }, build = function(input_shape) { self$kernel <- self$add_weight( name = 'kernel', shape = list(input_shape[[2]], self$output_dim), initializer = initializer_random_normal(), trainable = TRUE ) }, call = function(x, mask = NULL) { k_dot(x, self$kernel) }, compute_output_shape = function(input_shape) { list(input_shape[[1]], self$output_dim) } ) )
In order to use the custom layer within a Keras model you also need to create a wrapper function which instantiates the layer using the create_layer()
function. For example:
# define layer wrapper function layer_custom <- function(object, output_dim, name = NULL, trainable = TRUE) { create_layer(CustomLayer, object, list( output_dim = as.integer(output_dim), name = name, trainable = trainable )) }
You can now use the layer in a model as usual:
model <- keras_model_sequential() model %>% layer_dense(units = 32, input_shape = c(32,32)) %>% layer_custom(output_dim = 32)
In addition to creating custom layers, you can also create a custom model. This might be necessary if you wanted to use TensorFlow eager execution in combination with an imperatively written forward pass.
In cases where this is not needed, but flexibility in building the architecture is required, it is recommended to just stick with the functional API.
A custom model is defined by calling keras_model_custom()
passing a function that specifies the layers to be created and the operations to be executed on forward pass.
my_model <- function(input_dim, output_dim, name = NULL) { # define and return a custom model keras_model_custom(name = name, function(self) { # create layers we'll need for the call (this code executes once) # note: the layers have to be created on the self object! self$dense1 <- layer_dense(units = 64, activation = 'relu', input_shape = input_dim) self$dense2 <- layer_dense(units = 64, activation = 'relu') self$dense3 <- layer_dense(units = 10, activation = 'softmax') # implement call (this code executes during training & inference) function(inputs, mask = NULL) { x <- inputs %>% self$dense1() %>% self$dense2() %>% self$dense3() x } }) } model <- my_model(input_dim = 32, output_dim = 10) model %>% compile( optimizer = optimizer_rmsprop(lr = 0.001), loss = 'categorical_crossentropy', metrics = list('accuracy') ) # Trains for 5 epochs model %>% fit( data, labels, batch_size = 32, epochs = 5 )
A callback is an object passed to a model to customize and extend its
behavior during training. You can write your own custom callback, or use
the built-in callbacks
that include:
callback_model_checkpoint
: Save checkpoints of your model
at regular intervals.callback_learning_rate_scheduler
: Dynamically change the
learning rate.callback_early_stopping
: Interrupt training when
validation performance has stopped improving.callbacks_tensorboard
: Monitor the model’s behavior using
TensorBoard.To use a callback
, pass it to the model’s fit
method:
callbacks <- list( callback_early_stopping(patience = 2, monitor = 'val_loss'), callback_tensorboard(log_dir = './logs') ) model %>% fit( data, labels, batch_size = 32, epochs = 5, callbacks = callbacks, validation_data = list(val_data, val_labels) )
Save and load the weights of a model using save_model_weights_hdf5
and load_model_weights_hdf5
, respectively:
# save in SavedModel format model %>% save_model_weights_tf('my_model/') # Restore the model's state, # this requires a model with the same architecture. model %>% load_model_weights_tf('my_model/')
A model’s configuration can be saved - this serializes the model architecture without any weights. A saved configuration can recreate and initialize the same model, even without the code that defined the original model. Keras supports JSON and YAML serialization formats:
# Serialize a model to JSON format json_string <- model %>% model_to_json() # Recreate the model (freshly initialized) fresh_model <- model_from_json(json_string) # Serializes a model to YAML format yaml_string <- model %>% model_to_yaml() # Recreate the model fresh_model <- model_from_yaml(yaml_string)
Caution: Custom models are not serializable because their
architecture is defined by the R code in the function passed to keras_model_custom
.
The entire model can be saved to a file that contains the weight values, the model’s configuration, and even the optimizer’s configuration. This allows you to checkpoint a model and resume training later —from the exact same state —without access to the original code.
# Save entire model to the SavedModel format model %>% save_model_tf('my_model/') # Recreate the exact same model, including weights and optimizer. model <- load_model_tf('my_model/')
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.