% Generated by roxygen2: do not edit by hand

% Please edit documentation in R/preprocess.R

\name{reshape_tensor}

\alias{reshape_tensor}

\title{Reshape tensors for set learning}

\usage{

reshape_tensor(

  x,

  y,

  new_batch_size,

  samples_per_target,

  buffer_len = NULL,

  reshape_mode = "time_dist",

  check_y = FALSE

)

}

\arguments{

\item{x}{3D input tensor.}

\item{y}{2D target tensor.}

\item{new_batch_size}{Size of first axis of input/targets after reshaping.}

\item{samples_per_target}{How many samples to use for one target}

\item{buffer_len}{Only applies if \code{reshape_mode = "concat"}. If \code{buffer_len} is an integer, the subsequences are interspaced with \code{buffer_len} rows. The reshaped x has

new maxlen: (\code{maxlen} \eqn{*} \code{samples_per_target}) + \code{buffer_len} \eqn{*} (\code{samples_per_target} - 1).}

\item{reshape_mode}{\verb{"time_dist", "multi_input"} or \code{"concat"}

\itemize{

\item If \code{"multi_input"}, will produce \code{samples_per_target} separate inputs, each of length \code{maxlen}.

\item If \code{"time_dist"}, will produce a 4D input array. The dimensions correspond to

\verb{(new_batch_size, samples_per_target, maxlen, length(vocabulary))}.

\item If \code{"concat"}, will concatenate \code{samples_per_target} sequences of length \code{maxlen} to one long sequence

}}

\item{check_y}{Check if entries in \code{y} are consistent with reshape strategy (same label when aggregating).}

}

\value{

A list of 2 tensors.

}

\description{

Reshape input x and target y. Aggregates multiple samples from x and y into single input/target batches.

}

\examples{

\dontshow{if (reticulate::py_module_available("tensorflow")) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}

# create dummy data

batch_size <- 8

maxlen <- 11

voc_len <- 4 

x <- sample(0:(voc_len-1), maxlen*batch_size, replace = TRUE)

x <- keras::to_categorical(x, num_classes = voc_len)

x <- array(x, dim = c(batch_size, maxlen, voc_len))

y <- rep(0:1, each = batch_size/2)

y <- keras::to_categorical(y, num_classes = 2)

y

# reshape data for multi input model

reshaped_data <- reshape_tensor(

  x = x,

  y = y,

  new_batch_size = 2,

  samples_per_target = 4,

  reshape_mode = "multi_input")

length(reshaped_data[[1]])

dim(reshaped_data[[1]][[1]])

reshaped_data[[2]]

\dontshow{\}) # examplesIf}

}