R/model.R

keras_model_sequential

Keras Model composed of a linear stack of layers

Description

Keras Model composed of a linear stack of layers

Usage

 
keras_model_sequential(layers = NULL, name = NULL, ...)

Arguments

Arguments Description
layers List of layers to add to the model
name Name of model
… Arguments passed on to sequential_model_input_layer

input_shape
an integer vector of dimensions (not including the batch


batch_size
Optional input batch size (integer or NULL).


dtype
Optional datatype of the input. When not provided, the Keras


input_tensor
Optional tensor to use as layer input. If set, the layer


sparse
Boolean, whether the placeholder created is meant to be sparse.


ragged
Boolean, whether the placeholder created is meant to be ragged.


type_spec
A


input_layer_name,name
Optional name of the input layer (string).

Note

If any arguments are provided to ..., then the sequential model is initialized with a InputLayer instance. If not, then the first layer passed to a Sequential model should have a defined input shape. What that means is that it should have received an input_shape or batch_input_shape argument, or for some type of layers (recurrent, Dense…) an input_dim argument.

Examples

library(keras) 
 
model <- keras_model_sequential() 
model %>% 
  layer_dense(units = 32, input_shape = c(784)) %>% 
  layer_activation('relu') %>% 
  layer_dense(units = 10) %>% 
  layer_activation('softmax') 
 
model %>% compile( 
  optimizer = 'rmsprop', 
  loss = 'categorical_crossentropy', 
  metrics = c('accuracy') 
) 
 
# alternative way to provide input shape 
model <- keras_model_sequential(input_shape = c(784)) %>% 
  layer_dense(units = 32) %>% 
  layer_activation('relu') %>% 
  layer_dense(units = 10) %>% 
  layer_activation('softmax')

See Also

Other model functions: compile.keras.engine.training.Model(), evaluate.keras.engine.training.Model(), evaluate_generator(), fit.keras.engine.training.Model(), fit_generator(), get_config(), get_layer(), keras_model(), multi_gpu_model(), pop_layer(), predict.keras.engine.training.Model(), predict_generator(), predict_on_batch(), predict_proba(), summary.keras.engine.training.Model(), train_on_batch()