sequential_model_input_layer
sequential_model_input_layer(
input_shape = NULL,
batch_size = NULL,
dtype = NULL,
input_tensor = NULL,
sparse = NULL,
name = NULL,
ragged = NULL,
type_spec = NULL,
...,
input_layer_name = NULL
)
an integer vector of dimensions (not including the batch
axis), or a tf$TensorShape
instance (also not including the batch axis).
Optional input batch size (integer or NULL).
Optional datatype of the input. When not provided, the Keras default float type will be used.
Optional tensor to use as layer input. If set, the layer
will use the tf$TypeSpec
of this tensor rather than creating a new
placeholder tensor.
Boolean, whether the placeholder created is meant to be sparse.
Default to FALSE
.
Boolean, whether the placeholder created is meant to be ragged.
In this case, values of 'NULL' in the 'shape' argument represent ragged
dimensions. For more information about RaggedTensors
, see this
guide. Default to
FALSE
.
A tf$TypeSpec
object to create Input from. This
tf$TypeSpec
represents the entire batch. When provided, all other args
except name must be NULL
.
additional arguments passed on to keras$layers$InputLayer
.
Optional name of the input layer (string).