---
title: "Guide to Keras Basics"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Guide to Keras Basics}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
type: docs
repo: https://github.com/rstudio/keras
menu:
  main:
    name: "Keras basics"
    identifier: "keras-keras-basics"
    parent: "keras-getting-started-top"
    weight: 10
aliases:
  - /keras/articles/guide_keras.html
---

```{r setup, include=FALSE}
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:

  - *User friendly*<br> Keras has a simple, consistent interface
    optimized for common use cases. It provides clear and actionable
    feedback for user errors.
  - *Modular and composable*<br> Keras models are made by connecting
    configurable building blocks together, with few restrictions.
  - *Easy to extend*<br> Write custom building blocks to express new
    ideas for research. Create new layers, loss functions, and develop
    state-of-the-art models.

## Import keras

To get started, load the `keras` library:

```{r}
library(keras)
```



## Build a simple model

### Sequential model

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):

```{r}
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')
```

### Configure the layers

There are many `layers` available with some common constructor
parameters:

  - `activation`: Set the [activation function](https://tensorflow.rstudio.com/reference/keras/#section-activation-layers) 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`](https://tensorflow.rstudio.com/reference/keras/initializer_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:

```{r}
# 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))
```

## Train and evaluate

### Set up training

After the model is constructed, configure its learning process by
calling the `compile` method:

```{r}
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`](https://tensorflow.rstudio.com/reference/keras/optimizer_adam.html), 
    [`rmsprop`](https://tensorflow.rstudio.com/reference/keras/optimizer_rmsprop.html), or
    [`sgd`](https://tensorflow.rstudio.com/reference/keras/optimizer_sgd.html).
  - `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:

```{r}
# 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")
)
```

### Input data

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:

```{r} 

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`:

```{r}
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)
)
```


### Evaluate and predict

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:

```{r, eval = FALSE}
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`:

```{r, eval = FALSE}
model %>% predict(test_data, batch_size = 32)
    
model %>% predict(test_dataset, steps = 30)
```

    

## Build advanced models

### Functional API

The `sequential` model is a simple stack of layers that cannot
represent arbitrary models. Use the [Keras functional
API](functional_api.html)
to build complex model topologies such as:

  - multi-input models,
  - multi-output models,
  - models with shared layers (the same layer called several times),
  - models with non-sequential data flows (e.g., residual connections).

Building a model with the functional API works like this:

1.  A layer instance is callable and returns a tensor.
2.  Input tensors and output tensors are used to define a
    `keras_model` instance.
3.  This model is trained just like the `sequential` model.

The following example uses the functional API to build a simple,
fully-connected network:

```{r}
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
)
```


### Custom layers

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:

```{r}
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:

```{r}
# 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:

```{r}
model <- keras_model_sequential()
model %>% 
  layer_dense(units = 32, input_shape = c(32,32)) %>% 
  layer_custom(output_dim = 32)
```


### Custom models

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.

```{r, eval = FALSE}
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
)
```



## Callbacks

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](training_visualization.html#tensorboard).

To use a `callback`, pass it to the model’s `fit`
method:

```{r}
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 restore

### Weights only

Save and load the weights of a model using `save_model_weights_hdf5` and `load_model_weights_hdf5`, respectively:

```{r}
# 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/')
```


### Configuration only

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:

```{r}
# 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`.

### Entire model

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.

```{r}
# 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/')
```