Skip to contents

Generator wrapper

Source: R/generator_folder_collect.R
generator_fasta_label_folder_wrapper.Rd

Combines generators created by generator_initialize into a single generator.

Usage

generator_fasta_label_folder_wrapper(
  val,
  batch_size = NULL,
  path = NULL,
  voc_len = NULL,
  maxlen = NULL,
  gen_list = NULL,
  set_learning = NULL
)

Arguments

val

Train or validation generator.

batch_size

Number of samples in one batch.

path

Path to input files.

voc_len

Length of vocabulary.

maxlen

Length of predictor sequence.

gen_list

List of generator functions.

set_learning

When you want to assign one label to set of samples. Only implemented for train_type = "label_folder". Input is a list with the following parameters

  • samples_per_target: how many samples to use for one target.

  • maxlen: length of one sample.

  • reshape_mode: "time_dist", "multi_input" or "concat".

    • If reshape_mode is "multi_input", generator will produce samples_per_target separate inputs, each of length maxlen (model should have samples_per_target input layers).

    • If reshape_mode is "time_dist", generator will produce a 4D input array. The dimensions correspond to (batch_size, samples_per_target, maxlen, length(vocabulary)).

    • If reshape_mode is "concat", generator will concatenate samples_per_target sequences of length maxlen to one long sequence.

  • If reshape_mode is "concat", there is an additional buffer_len argument. If buffer_len is an integer, the subsequences are interspaced with buffer_len rows. The input length is (maxlen \(*\) samples_per_target) + buffer_len \(*\) (samples_per_target - 1).

Value

A generator function.

Examples

if (FALSE) { # reticulate::py_module_available("tensorflow")
# create two folders with dummy fasta files
path_input_1 <- tempfile()
dir.create(path_input_1)
create_dummy_data(file_path = path_input_1, num_files = 2, seq_length = 5,
                  num_seq = 2, vocabulary = c("a", "c", "g", "t"))
path_input_2 <- tempfile()
dir.create(path_input_2)
create_dummy_data(file_path = path_input_2, num_files = 3, seq_length = 7,
                  num_seq = 5, vocabulary = c("a", "c", "g", "t"))

maxlen <- 5
p <- c(path_input_1, path_input_1)
gen_list <- generator_initialize(directories = p,
                                 batch_size = 4, maxlen = maxlen)
gen <- generator_fasta_label_folder_wrapper(val = FALSE, batch_size = 8,
                                            path = p, voc_len = 4, 
                                            maxlen = maxlen,
                                            gen_list = gen_list)
z <- gen()
dim(z[[1]])
z[[2]]
}