Layer to be used as an entry point into a graph.
layer_input(
shape = NULL,
batch_shape = NULL,
name = NULL,
dtype = NULL,
sparse = FALSE,
tensor = NULL,
ragged = FALSE
)
A tensor
Shape, not including the batch size. For instance,
shape=c(32)
indicates that the expected input will be batches
of 32-dimensional vectors.
Shape, including the batch size. For instance,
shape = c(10,32)
indicates that the expected input will be batches
of 10 32-dimensional vectors. batch_shape = list(NULL, 32)
indicates
batches of an arbitrary number of 32-dimensional vectors.
An optional name string for the layer. Should be unique in a model (do not reuse the same name twice). It will be autogenerated if it isn't provided.
The data type expected by the input, as a string (float32
,
float64
, int32
...)
Boolean, whether the placeholder created is meant to be sparse.
Existing tensor to wrap into the Input
layer. If set, the
layer will not create a placeholder tensor.
A boolean specifying whether the placeholder to be created is
ragged. Only one of 'ragged' and 'sparse' can be TRUE
In this case, values
of 'NULL' in the 'shape' argument represent ragged dimensions.
Other core layers:
layer_activation()
,
layer_activity_regularization()
,
layer_attention()
,
layer_dense_features()
,
layer_dense()
,
layer_dropout()
,
layer_flatten()
,
layer_lambda()
,
layer_masking()
,
layer_permute()
,
layer_repeat_vector()
,
layer_reshape()