if (!DBI::dbExistsTable(con, "doodles")) {
  DBI::dbCreateTable(
    con = con,
    name = "doodles",
    fields = c(
      "countrycode" = "char(2)",
      "drawing" = "text",
      "key_id" = "bigint",
      "recognized" = "bool",
      "timestamp" = "timestamp",
      "word" = "text"
    )
  )
}

if (!DBI::dbExistsTable(con, "upload_log")) {
  DBI::dbCreateTable(
    con = con,
    name = "upload_log",
    fields = c(
      "id" = "serial",
      "file_name" = "text UNIQUE",
      "uploaded" = "bool DEFAULT false"
    )
  )
}

#' @title Извлечение и загрузка файлов
#'
#' @description
#' Извлечение CSV-файлов из ZIP-архива и загрузка их в базу данных
#'
#' @param con Объект подключения к базе данных (класс `MonetDBEmbeddedConnection`).
#' @param tablename Название таблицы в базе данных.
#' @oaram zipfile Путь к ZIP-архиву.
#' @oaram filename Имя файла внури ZIP-архива.
#' @param preprocess Функция предобработки, которая будет применена извлечённому файлу.
#'   Должна принимать один аргумент `data` (объект `data.table`).
#'
#' @return `TRUE`.
#'
upload_file <- function(con, tablename, zipfile, filename, preprocess = NULL) {
  # Проверка аргументов
  checkmate::assert_class(con, "MonetDBEmbeddedConnection")
  checkmate::assert_string(tablename)
  checkmate::assert_string(filename)
  checkmate::assert_true(DBI::dbExistsTable(con, tablename))
  checkmate::assert_file_exists(zipfile, access = "r", extension = "zip")
  checkmate::assert_function(preprocess, args = c("data"), null.ok = TRUE)

  # Извлечение файла
  path <- file.path(tempdir(), filename)
  unzip(zipfile, files = filename, exdir = tempdir(), 
        junkpaths = TRUE, unzip = getOption("unzip"))
  on.exit(unlink(file.path(path)))

  # Применяем функция предобработки
  if (!is.null(preprocess)) {
    .data <- data.table::fread(file = path)
    .data <- preprocess(data = .data)
    data.table::fwrite(x = .data, file = path, append = FALSE)
    rm(.data)
  }

  # Запрос к БД на импорт CSV
  sql <- sprintf(
    "COPY OFFSET 2 INTO %s FROM '%s' USING DELIMITERS ',','\\n','\"' NULL AS '' BEST EFFORT",
    tablename, path
  )
  # Выполнение запроса к БД
  DBI::dbExecute(con, sql)

  # Добавление записи об успешной загрузке в служебную таблицу
  DBI::dbExecute(con, sprintf("INSERT INTO upload_log(file_name, uploaded) VALUES('%s', true)",
                              filename))

  return(invisible(TRUE))
}

# Список файлов для записи
files <- unzip(zipfile, list = TRUE)$Name

# Список исключений, если часть файлов уже была загружена
to_skip <- DBI::dbGetQuery(con, "SELECT file_name FROM upload_log")[[1L]]
files <- setdiff(files, to_skip)

if (length(files) > 0L) {
  # Запускаем таймер
  tictoc::tic()
  # Прогресс бар
  pb <- txtProgressBar(min = 0L, max = length(files), style = 3)
  for (i in seq_along(files)) {
    upload_file(con = con, tablename = "doodles", 
                zipfile = zipfile, filename = files[i])
    setTxtProgressBar(pb, i)
  }
  close(pb)
  # Останавливаем таймер
  tictoc::toc()
}

# 526.141 sec elapsed - копирование SSD->SSD
# 558.879 sec elapsed - копирование USB->SSD

message("Generate lables")
invisible(DBI::dbExecute(con, "ALTER TABLE doodles ADD label_int int"))
invisible(DBI::dbExecute(con, "UPDATE doodles SET label_int = dense_rank() OVER (ORDER BY word) - 1"))

message("Generate row numbers")
invisible(DBI::dbExecute(con, "ALTER TABLE doodles ADD id serial"))
invisible(DBI::dbExecute(con, "CREATE ORDERED INDEX doodles_id_ord_idx ON doodles(id)"))

library(ggplot2)

set.seed(0)
# Подключение к базе данных
con <- DBI::dbConnect(MonetDBLite::MonetDBLite(), Sys.getenv("DBDIR"))

# Функция для подготовки запроса на стороне сервера
prep_sql <- function(batch_size) {
  sql <- sprintf("PREPARE SELECT id FROM doodles WHERE id IN (%s)",
                 paste(rep("?", batch_size), collapse = ","))
  res <- DBI::dbSendQuery(con, sql)
  return(res)
}

# Функция для извлечения данных
fetch_data <- function(rs, batch_size) {
  ids <- sample(seq_len(n), batch_size)
  res <- DBI::dbFetch(DBI::dbBind(rs, as.list(ids)))
  return(res)
}

# Проведение замера
res_bench <- bench::press(
  batch_size = 2^(4:10),
  {
    rs <- prep_sql(batch_size)
    bench::mark(
      fetch_data(rs, batch_size),
      min_iterations = 50L
    )
  }
)
# Параметры бенчмарка
cols <- c("batch_size", "min", "median", "max", "itr/sec", "total_time", "n_itr")
res_bench[, cols]

#   batch_size      min   median      max `itr/sec` total_time n_itr
#        <dbl> <bch:tm> <bch:tm> <bch:tm>     <dbl>   <bch:tm> <int>
# 1         16   23.6ms  54.02ms  93.43ms     18.8        2.6s    49
# 2         32     38ms  84.83ms 151.55ms     11.4       4.29s    49
# 3         64   63.3ms 175.54ms 248.94ms     5.85       8.54s    50
# 4        128   83.2ms 341.52ms 496.24ms     3.00      16.69s    50
# 5        256  232.8ms 653.21ms 847.44ms     1.58      31.66s    50
# 6        512  784.6ms    1.41s    1.98s     0.740       1.1m    49
# 7       1024  681.7ms    2.72s    4.06s     0.377      2.16m    49

ggplot(res_bench, aes(x = factor(batch_size), y = median, group = 1)) +
  geom_point() +
  geom_line() +
  ylab("median time, s") +
  theme_minimal()

DBI::dbDisconnect(con, shutdown = TRUE)

r_process_json_str <- function(json, line.width = 3, 
                               color = TRUE, scale = 1) {
  # Парсинг JSON
  coords <- jsonlite::fromJSON(json, simplifyMatrix = FALSE)
  tmp <- tempfile()
  # Удаляем временный файл по завершению функции
  on.exit(unlink(tmp))
  png(filename = tmp, width = 256 * scale, height = 256 * scale, pointsize = 1)
  # Пустой график
  plot.new()
  # Размер окна графика
  plot.window(xlim = c(256 * scale, 0), ylim = c(256 * scale, 0))
  # Цвета линий
  cols <- if (color) rainbow(length(coords)) else "#000000"
  for (i in seq_along(coords)) {
    lines(x = coords[[i]][[1]] * scale, y = coords[[i]][[2]] * scale, 
          col = cols[i], lwd = line.width)
  }
  dev.off()
  # Преобразование изображения в 3-х мерный массив
  res <- png::readPNG(tmp)
  return(res)
}

r_process_json_vector <- function(x, ...) {
  res <- lapply(x, r_process_json_str, ...)
  # Объединение 3-х мерных массивов картинок в 4-х мерный в тензор
  res <- do.call(abind::abind, c(res, along = 0))
  return(res)
}

https://thecoatlessprofessor.com/programming/unofficial-rcpp-api-documentation

https://docs.opencv.org/4.0.1/d7/dbd/group__imgproc.html

https://xtensor.readthedocs.io/en/latest/

https://xtensor.readthedocs.io/en/latest/file_loading.html#loading-json-data-into-xtensor

https://cran.r-project.org/web/packages/RcppThread/vignettes/RcppThread-vignette.pdf

Rcpp::registerPlugin("opencv", function() {
  # Возможные названия пакета
  pkg_config_name <- c("opencv", "opencv4")
  # Бинарный файл утилиты pkg-config
  pkg_config_bin <- Sys.which("pkg-config")
  # Проврека наличия утилиты в системе
  checkmate::assert_file_exists(pkg_config_bin, access = "x")
  # Проверка наличия файла настроек OpenCV для pkg-config
  check <- sapply(pkg_config_name, 
                  function(pkg) system(paste(pkg_config_bin, pkg)))
  if (all(check != 0)) {
    stop("OpenCV config for the pkg-config not found", call. = FALSE)
  }

  pkg_config_name <- pkg_config_name[check == 0]
  list(env = list(
    PKG_CXXFLAGS = system(paste(pkg_config_bin, "--cflags", pkg_config_name), 
                          intern = TRUE),
    PKG_LIBS = system(paste(pkg_config_bin, "--libs", pkg_config_name), 
                      intern = TRUE)
  ))
})

// [[Rcpp::plugins(cpp14)]]
// [[Rcpp::plugins(opencv)]]
// [[Rcpp::depends(xtensor)]]
// [[Rcpp::depends(RcppThread)]]

#include <xtensor/xjson.hpp>
#include <xtensor/xadapt.hpp>
#include <xtensor/xview.hpp>
#include <xtensor-r/rtensor.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <Rcpp.h>
#include <RcppThread.h>

// Синонимы для типов
using RcppThread::parallelFor;
using json = nlohmann::json;
using points = xt::xtensor<double,2>;     // Извлечённые из JSON координаты точек
using strokes = std::vector<points>;      // Извлечённые из JSON координаты точек
using xtensor3d = xt::xtensor<double, 3>; // Тензор для хранения матрицы изоображения
using xtensor4d = xt::xtensor<double, 4>; // Тензор для хранения множества изображений
using rtensor3d = xt::rtensor<double, 3>; // Обёртка для экспорта в R
using rtensor4d = xt::rtensor<double, 4>; // Обёртка для экспорта в R

// Статические константы
// Размер изображения в пикселях
const static int SIZE = 256;
// Тип линии
// См. https://en.wikipedia.org/wiki/Pixel_connectivity#2-dimensional
const static int LINE_TYPE = cv::LINE_4;
// Толщина линии в пикселях
const static int LINE_WIDTH = 3;
// Алгоритм ресайза
// https://docs.opencv.org/3.1.0/da/d54/group__imgproc__transform.html#ga5bb5a1fea74ea38e1a5445ca803ff121
const static int RESIZE_TYPE = cv::INTER_LINEAR;

// Шаблон для конвертирования OpenCV-матрицы в тензор
template <typename T, int NCH, typename XT=xt::xtensor<T,3,xt::layout_type::column_major>>
XT to_xt(const cv::Mat_<cv::Vec<T, NCH>>& src) {
  // Размерность целевого тензора
  std::vector<int> shape = {src.rows, src.cols, NCH};
  // Общее количество элементов в массиве
  size_t size = src.total() * NCH;
  // Преобразование cv::Mat в xt::xtensor
  XT res = xt::adapt((T*) src.data, size, xt::no_ownership(), shape);
  return res;
}

// Преобразование JSON в список координат точек
strokes parse_json(const std::string& x) {
  auto j = json::parse(x);
  // Результат парсинга должен быть массивом
  if (!j.is_array()) {
    throw std::runtime_error("'x' must be JSON array.");
  }
  strokes res;
  res.reserve(j.size());
  for (const auto& a: j) {
    // Каждый элемент массива должен быть 2-мерным массивом
    if (!a.is_array() || a.size() != 2) {
      throw std::runtime_error("'x' must include only 2d arrays.");
    }
    // Извлечение вектора точек
    auto p = a.get<points>();
    res.push_back(p);
  }
  return res;
}

// Отрисовка линий
// Цвета HSV
cv::Mat ocv_draw_lines(const strokes& x, bool color = true) {
  // Исходный тип матрицы
  auto stype = color ? CV_8UC3 : CV_8UC1;
  // Итоговый тип матрицы
  auto dtype = color ? CV_32FC3 : CV_32FC1;
  auto bg = color ? cv::Scalar(0, 0, 255) : cv::Scalar(255);
  auto col = color ? cv::Scalar(0, 255, 220) : cv::Scalar(0);
  cv::Mat img = cv::Mat(SIZE, SIZE, stype, bg);
  // Количество линий
  size_t n = x.size();
  for (const auto& s: x) {
    // Количество точек в линии
    size_t n_points = s.shape()[1];
    for (size_t i = 0; i < n_points - 1; ++i) {
      // Точка начала штриха
      cv::Point from(s(0, i), s(1, i));
      // Точка окончания штриха
      cv::Point to(s(0, i + 1), s(1, i + 1));
      // Отрисовка линии
      cv::line(img, from, to, col, LINE_WIDTH, LINE_TYPE);
    }
    if (color) {
      // Меняем цвет линии
      col[0] += 180 / n;
    }
  }
  if (color) {
    // Меняем цветовое представление на RGB
    cv::cvtColor(img, img, cv::COLOR_HSV2RGB);
  }
  // Меняем формат представления на float32 с диапазоном [0, 1]
  img.convertTo(img, dtype, 1 / 255.0);
  return img;
}

// Обработка JSON и получение тензора с данными изображения
xtensor3d process(const std::string& x, double scale = 1.0, bool color = true) {
  auto p = parse_json(x);
  auto img = ocv_draw_lines(p, color);
  if (scale != 1) {
    cv::Mat out;
    cv::resize(img, out, cv::Size(), scale, scale, RESIZE_TYPE);
    cv::swap(img, out);
    out.release();
  }
  xtensor3d arr = color ? to_xt<double,3>(img) : to_xt<double,1>(img);
  return arr;
}

// [[Rcpp::export]]
rtensor3d cpp_process_json_str(const std::string& x, 
                               double scale = 1.0, 
                               bool color = true) {
  xtensor3d res = process(x, scale, color);
  return res;
}

// [[Rcpp::export]]
rtensor4d cpp_process_json_vector(const std::vector<std::string>& x, 
                                  double scale = 1.0, 
                                  bool color = false) {
  size_t n = x.size();
  size_t dim = floor(SIZE * scale);
  size_t channels = color ? 3 : 1;
  xtensor4d res({n, dim, dim, channels});
  parallelFor(0, n, [&x, &res, scale, color](int i) {
    xtensor3d tmp = process(x[i], scale, color);
    auto view = xt::view(res, i, xt::all(), xt::all(), xt::all());
    view = tmp;
  });
  return res;
}

res_bench <- bench::mark(
  r_process_json_str(tmp_data[4, drawing], scale = 0.5),
  cpp_process_json_str(tmp_data[4, drawing], scale = 0.5),
  check = FALSE,
  min_iterations = 100
)
# Параметры бенчмарка
cols <- c("expression", "min", "median", "max", "itr/sec", "total_time", "n_itr")
res_bench[, cols]

#   expression                min     median       max `itr/sec` total_time  n_itr
#   <chr>                <bch:tm>   <bch:tm>  <bch:tm>     <dbl>   <bch:tm>  <int>
# 1 r_process_json_str     3.49ms     3.55ms    4.47ms      273.      490ms    134
# 2 cpp_process_json_str   1.94ms     2.02ms    5.32ms      489.      497ms    243

library(ggplot2)
# Проведение замера
res_bench <- bench::press(
  batch_size = 2^(4:10),
  {
    .data <- tmp_data[sample(seq_len(.N), batch_size), drawing]
    bench::mark(
      r_process_json_vector(.data, scale = 0.5),
      cpp_process_json_vector(.data,  scale = 0.5),
      min_iterations = 50,
      check = FALSE
    )
  }
)

res_bench[, cols]

#    expression   batch_size      min   median      max `itr/sec` total_time n_itr
#    <chr>             <dbl> <bch:tm> <bch:tm> <bch:tm>     <dbl>   <bch:tm> <int>
#  1 r                   16   50.61ms  53.34ms  54.82ms    19.1     471.13ms     9
#  2 cpp                 16    4.46ms   5.39ms   7.78ms   192.      474.09ms    91
#  3 r                   32   105.7ms 109.74ms 212.26ms     7.69        6.5s    50
#  4 cpp                 32    7.76ms  10.97ms  15.23ms    95.6     522.78ms    50
#  5 r                   64  211.41ms 226.18ms 332.65ms     3.85      12.99s    50
#  6 cpp                 64   25.09ms  27.34ms  32.04ms    36.0        1.39s    50
#  7 r                  128   534.5ms 627.92ms 659.08ms     1.61      31.03s    50
#  8 cpp                128   56.37ms  58.46ms  66.03ms    16.9        2.95s    50
#  9 r                  256     1.15s    1.18s    1.29s     0.851     58.78s    50
# 10 cpp                256  114.97ms 117.39ms 130.09ms     8.45       5.92s    50
# 11 r                  512     2.09s    2.15s    2.32s     0.463       1.8m    50
# 12 cpp                512  230.81ms  235.6ms 261.99ms     4.18      11.97s    50
# 13 r                 1024        4s    4.22s     4.4s     0.238       3.5m    50
# 14 cpp               1024  410.48ms 431.43ms 462.44ms     2.33      21.45s    50

ggplot(res_bench, aes(x = factor(batch_size), y = median, 
                      group =  expression, color = expression)) +
  geom_point() +
  geom_line() +
  ylab("median time, s") +
  theme_minimal() +
  scale_color_discrete(name = "", labels = c("cpp", "r")) +
  theme(legend.position = "bottom") 

train_generator <- function(db_connection = con,
                            samples_index,
                            num_classes = 340,
                            batch_size = 32,
                            scale = 1,
                            color = FALSE,
                            imagenet_preproc = FALSE) {
  # Проверка аргументов
  checkmate::assert_class(con, "DBIConnection")
  checkmate::assert_integerish(samples_index)
  checkmate::assert_count(num_classes)
  checkmate::assert_count(batch_size)
  checkmate::assert_number(scale, lower = 0.001, upper = 5)
  checkmate::assert_flag(color)
  checkmate::assert_flag(imagenet_preproc)

  # Перемешиваем, чтобы брать и удалять использованные индексы батчей по порядку
  dt <- data.table::data.table(id = sample(samples_index))
  # Проставляем номера батчей
  dt[, batch := (.I - 1L) %/% batch_size + 1L]
  # Оставляем только полные батчи и индексируем
  dt <- dt[, if (.N == batch_size) .SD, keyby = batch]
  # Устанавливаем счётчик
  i <- 1
  # Количество батчей
  max_i <- dt[, max(batch)]

  # Подготовка выражения для выгрузки
  sql <- sprintf(
    "PREPARE SELECT drawing, label_int FROM doodles WHERE id IN (%s)",
    paste(rep("?", batch_size), collapse = ",")
  )
  res <- DBI::dbSendQuery(con, sql)

  # Аналог keras::to_categorical
  to_categorical <- function(x, num) {
    n <- length(x)
    m <- numeric(n * num)
    m[x * n + seq_len(n)] <- 1
    dim(m) <- c(n, num)
    return(m)
  }

  # Замыкание
  function() {
    # Начинаем новую эпоху
    if (i > max_i) {
      dt[, id := sample(id)]
      data.table::setkey(dt, batch)
      # Сбрасываем счётчик
      i <<- 1
      max_i <<- dt[, max(batch)]
    }

    # ID для выгрузки данных
    batch_ind <- dt[batch == i, id]
    # Выгрузка данных
    batch <- DBI::dbFetch(DBI::dbBind(res, as.list(batch_ind)), n = -1)

    # Увеличиваем счётчик
    i <<- i + 1

    # Парсинг JSON и подготовка массива
    batch_x <- cpp_process_json_vector(batch$drawing, scale = scale, color = color)
    if (imagenet_preproc) {
      # Шкалирование c интервала [0, 1] на интервал [-1, 1]
      batch_x <- (batch_x - 0.5) * 2
    }

    batch_y <- to_categorical(batch$label_int, num_classes)
    result <- list(batch_x, batch_y)
    return(result)
  }
}

library(Rcpp)
library(keras)
library(ggplot2)

source("utils/rcpp.R")
source("utils/keras_iterator.R")

con <- DBI::dbConnect(drv = MonetDBLite::MonetDBLite(), Sys.getenv("DBDIR"))

ind <- seq_len(DBI::dbGetQuery(con, "SELECT count(*) FROM doodles")[[1L]])
num_classes <- DBI::dbGetQuery(con, "SELECT max(label_int) + 1 FROM doodles")[[1L]]

# Индексы для обучающей выборки
train_ind <- sample(ind, floor(length(ind) * 0.995))
# Индексы для проверочной выборки
val_ind <- ind[-train_ind]
rm(ind)
# Коэффициент масштаба
scale <- 0.5

# Проведение замера
res_bench <- bench::press(
  batch_size = 2^(4:10),
  {
    it1 <- train_generator(
      db_connection = con,
      samples_index = train_ind,
      num_classes = num_classes,
      batch_size = batch_size,
      scale = scale
    )
    bench::mark(
      it1(),
      min_iterations = 50L
    )
  }
)
# Параметры бенчмарка
cols <- c("batch_size", "min", "median", "max", "itr/sec", "total_time", "n_itr")
res_bench[, cols]

#   batch_size      min   median      max `itr/sec` total_time n_itr
#        <dbl> <bch:tm> <bch:tm> <bch:tm>     <dbl>   <bch:tm> <int>
# 1         16     25ms  64.36ms   92.2ms     15.9       3.09s    49
# 2         32   48.4ms 118.13ms 197.24ms     8.17       5.88s    48
# 3         64   69.3ms 117.93ms 181.14ms     8.57       5.83s    50
# 4        128  157.2ms 240.74ms 503.87ms     3.85      12.71s    49
# 5        256  359.3ms 613.52ms 988.73ms     1.54       30.5s    47
# 6        512  884.7ms    1.53s    2.07s     0.674      1.11m    45
# 7       1024     2.7s    3.83s    5.47s     0.261      2.81m    44

ggplot(res_bench, aes(x = factor(batch_size), y = median, group = 1)) +
    geom_point() +
    geom_line() +
    ylab("median time, s") +
    theme_minimal()

DBI::dbDisconnect(con, shutdown = TRUE)

test_generator <- function(dt,
                           batch_size = 32,
                           scale = 1,
                           color = FALSE,
                           imagenet_preproc = FALSE) {

  # Проверка аргументов
  checkmate::assert_data_table(dt)
  checkmate::assert_count(batch_size)
  checkmate::assert_number(scale, lower = 0.001, upper = 5)
  checkmate::assert_flag(color)
  checkmate::assert_flag(imagenet_preproc)

  # Проставляем номера батчей
  dt[, batch := (.I - 1L) %/% batch_size + 1L]
  data.table::setkey(dt, batch)
  i <- 1
  max_i <- dt[, max(batch)]

  # Замыкание
  function() {
    batch_x <- cpp_process_json_vector(dt[batch == i, drawing], 
                                       scale = scale, color = color)
    if (imagenet_preproc) {
      # Шкалирование c интервала [0, 1] на интервал [-1, 1]
      batch_x <- (batch_x - 0.5) * 2
    }
    result <- list(batch_x)
    i <<- i + 1
    return(result)
  }
}

library(keras)

top_3_categorical_accuracy <- custom_metric(
    name = "top_3_categorical_accuracy",
    metric_fn = function(y_true, y_pred) {
         metric_top_k_categorical_accuracy(y_true, y_pred, k = 3)
    }
)

layer_sep_conv_bn <- function(object, 
                              filters,
                              alpha = 1,
                              depth_multiplier = 1,
                              strides = c(2, 2)) {

  # NB! depth_multiplier !=  resolution multiplier
  # https://github.com/keras-team/keras/issues/10349

  layer_depthwise_conv_2d(
    object = object,
    kernel_size = c(3, 3), 
    strides = strides,
    padding = "same",
    depth_multiplier = depth_multiplier
  ) %>%
  layer_batch_normalization() %>% 
  layer_activation_relu() %>%
  layer_conv_2d(
    filters = filters * alpha,
    kernel_size = c(1, 1), 
    strides = c(1, 1)
  ) %>%
  layer_batch_normalization() %>% 
  layer_activation_relu() 
}

get_mobilenet_v1 <- function(input_shape = c(224, 224, 1),
                             num_classes = 340,
                             alpha = 1,
                             depth_multiplier = 1,
                             optimizer = optimizer_adam(lr = 0.002),
                             loss = "categorical_crossentropy",
                             metrics = c("categorical_crossentropy",
                                         top_3_categorical_accuracy)) {

  inputs <- layer_input(shape = input_shape)

  outputs <- inputs %>%
    layer_conv_2d(filters = 32, kernel_size = c(3, 3), strides = c(2, 2), padding = "same") %>%
    layer_batch_normalization() %>% 
    layer_activation_relu() %>%
    layer_sep_conv_bn(filters = 64, strides = c(1, 1)) %>%
    layer_sep_conv_bn(filters = 128, strides = c(2, 2)) %>%
    layer_sep_conv_bn(filters = 128, strides = c(1, 1)) %>%
    layer_sep_conv_bn(filters = 256, strides = c(2, 2)) %>%
    layer_sep_conv_bn(filters = 256, strides = c(1, 1)) %>%
    layer_sep_conv_bn(filters = 512, strides = c(2, 2)) %>%
    layer_sep_conv_bn(filters = 512, strides = c(1, 1)) %>%
    layer_sep_conv_bn(filters = 512, strides = c(1, 1)) %>%
    layer_sep_conv_bn(filters = 512, strides = c(1, 1)) %>%
    layer_sep_conv_bn(filters = 512, strides = c(1, 1)) %>%
    layer_sep_conv_bn(filters = 512, strides = c(1, 1)) %>%
    layer_sep_conv_bn(filters = 1024, strides = c(2, 2)) %>%
    layer_sep_conv_bn(filters = 1024, strides = c(1, 1)) %>%
    layer_global_average_pooling_2d() %>%
    layer_dense(units = num_classes) %>%
    layer_activation_softmax()

    model <- keras_model(
      inputs = inputs,
      outputs = outputs
    )

    model %>% compile(
      optimizer = optimizer,
      loss = loss,
      metrics = metrics
    )

    return(model)
}

get_model <- function(name = "mobilenet_v2",
                      input_shape = NULL,
                      weights = "imagenet",
                      pooling = "avg",
                      num_classes = NULL,
                      optimizer = keras::optimizer_adam(lr = 0.002),
                      loss = "categorical_crossentropy",
                      metrics = NULL,
                      color = TRUE,
                      compile = FALSE) {
  # Проверка аргументов
  checkmate::assert_string(name)
  checkmate::assert_integerish(input_shape, lower = 1, upper = 256, len = 3)
  checkmate::assert_count(num_classes)
  checkmate::assert_flag(color)
  checkmate::assert_flag(compile)

  # Получаем объект из пакета keras
  model_fun <- get0(paste0("application_", name), envir = asNamespace("keras"))
  # Проверка наличия объекта в пакете
  if (is.null(model_fun)) {
    stop("Model ", shQuote(name), " not found.", call. = FALSE)
  }

  base_model <- model_fun(
    input_shape = input_shape,
    include_top = FALSE,
    weights = weights,
    pooling = pooling
  )

  # Если изображение не цветное, меняем размерность входа
  if (!color) {
    base_model_conf <- keras::get_config(base_model)
    base_model_conf$layers[[1]]$config$batch_input_shape[[4]] <- 1L
    base_model <- keras::from_config(base_model_conf)
  }

  predictions <- keras::get_layer(base_model, "global_average_pooling2d_1")$output
  predictions <- keras::layer_dense(predictions, units = num_classes, activation = "softmax")
  model <- keras::keras_model(
    inputs = base_model$input,
    outputs = predictions
  )

  if (compile) {
    keras::compile(
      object = model,
      optimizer = optimizer,
      loss = loss,
      metrics = metrics
    )
  }

  return(model)
}

FROM tensorflow/tensorflow:1.12.0-gpu

MAINTAINER Artem Klevtsov <a.a.klevtsov@gmail.com>

SHELL ["/bin/bash", "-c"]

ARG LOCALE="en_US.UTF-8"
ARG APT_PKG="libopencv-dev r-base r-base-dev littler"
ARG R_BIN_PKG="futile.logger checkmate data.table rcpp rapidjsonr dbi keras jsonlite curl digest remotes"
ARG R_SRC_PKG="xtensor RcppThread docopt MonetDBLite"
ARG PY_PIP_PKG="keras"
ARG DIRS="/db /app /app/data /app/models /app/logs"

RUN source /etc/os-release &&     echo "deb https://cloud.r-project.org/bin/linux/ubuntu ${UBUNTU_CODENAME}-cran35/" > /etc/apt/sources.list.d/cran35.list &&     apt-key adv --keyserver keyserver.ubuntu.com --recv-keys E084DAB9 &&     add-apt-repository -y ppa:marutter/c2d4u3.5 &&     add-apt-repository -y ppa:timsc/opencv-3.4 &&     apt-get update &&     apt-get install -y locales &&     locale-gen ${LOCALE} &&     apt-get install -y --no-install-recommends ${APT_PKG} &&     ln -s /usr/lib/R/site-library/littler/examples/install.r /usr/local/bin/install.r &&     ln -s /usr/lib/R/site-library/littler/examples/install2.r /usr/local/bin/install2.r &&     ln -s /usr/lib/R/site-library/littler/examples/installGithub.r /usr/local/bin/installGithub.r &&     echo 'options(Ncpus = parallel::detectCores())' >> /etc/R/Rprofile.site &&     echo 'options(repos = c(CRAN = "https://cloud.r-project.org"))' >> /etc/R/Rprofile.site &&     apt-get install -y $(printf "r-cran-%s " ${R_BIN_PKG}) &&     install.r ${R_SRC_PKG} &&     pip install ${PY_PIP_PKG} &&     mkdir -p ${DIRS} &&     chmod 777 ${DIRS} &&     rm -rf /tmp/downloaded_packages/ /tmp/*.rds &&     rm -rf /var/lib/apt/lists/*

COPY utils /app/utils
COPY src /app/src
COPY tests /app/tests
COPY bin/*.R /app/

ENV DBDIR="/db"
ENV CUDA_HOME="/usr/local/cuda"
ENV PATH="/app:${PATH}"

WORKDIR /app

VOLUME /db
VOLUME /app

CMD bash

#!/bin/sh

DBDIR=${PWD}/db
LOGSDIR=${PWD}/logs
MODELDIR=${PWD}/models
DATADIR=${PWD}/data
ARGS="--runtime=nvidia --rm -v ${DBDIR}:/db -v ${LOGSDIR}:/app/logs -v ${MODELDIR}:/app/models -v ${DATADIR}:/app/data"

if [ -z "$1" ]; then
    CMD="Rscript /app/train_nn.R"
elif [ "$1" = "bash" ]; then
    ARGS="${ARGS} -ti"
else
    CMD="Rscript /app/train_nn.R $@"
fi

docker run ${ARGS} doodles-tf ${CMD}

# Шаблон имени файла лога
log_file_tmpl <- file.path("logs", sprintf(
  "%s_%d_%dch_%s.csv",
  model_name,
  dim_size,
  channels,
  format(Sys.time(), "%Y%m%d%H%M%OS")
))
# Шаблон имени файла модели
model_file_tmpl <- file.path("models", sprintf(
  "%s_%d_%dch_{epoch:02d}_{val_loss:.2f}.h5",
  model_name,
  dim_size,
  channels
))

callbacks_list <- list(
  keras::callback_csv_logger(
    filename = log_file_tmpl
  ),
  keras::callback_early_stopping(
    monitor = "val_loss",
    min_delta = 1e-4,
    patience = 8,
    verbose = 1,
    mode = "min"
  ),
  keras::callback_reduce_lr_on_plateau(
    monitor = "val_loss",
    factor = 0.5, # уменьшаем lr в 2 раза
    patience = 4,
    verbose = 1,
    min_delta = 1e-4,
    mode = "min"
  ),
  keras::callback_model_checkpoint(
    filepath = model_file_tmpl,
    monitor = "val_loss",
    save_best_only = FALSE,
    save_weights_only = FALSE,
    mode = "min"
  )
)