{"metadata":{"language_info":{"name":"R","codemirror_mode":"r","pygments_lexer":"r","mimetype":"text/x-r-source","file_extension":".r","version":"4.0.5"},"kernelspec":{"name":"ir","display_name":"R","language":"R"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This R environment comes with many helpful analytics packages installed\n# It is defined by the kaggle/rstats Docker image: https://github.com/kaggle/docker-rstats\n# For example, here's a helpful package to load\n\nlibrary(tidyverse) # metapackage of all tidyverse packages\nlibrary(keras)\nlibrary(magick)\n\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nlist.files(path = \"../input\")\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session\n\n\ndoglabels <- read_csv(\"../input/dog-breed-identification/labels.csv\")\n\n\n## BREADS\nbreed_list <- doglabels %>% count(breed) %>% arrange(-n) %>% pull(breed)\ndoglabels <- doglabels %>% \n                mutate(from = paste0(\"../input/dog-breed-identification/train/\", id, \".jpg\"), \n                       to = paste0(\"train/\", breed, \"/\", id,\".jpg\")) \n\ndir.create(path = \"train\")\nfor (breed in breed_list) {\n    cat(\"\\nProcessing breed \", breed)\n    dir.create(path = paste0(\"train/\", breed))\n}\n\nfile.copy(from = doglabels %>% pull(from), to = doglabels %>% pull(to), overwrite = TRUE)\n\n\n### \nwidth <- 224\nheight<- 224\ntarget_size <- c(width, height)\nrgb <- 3 #color channels\n\npath_train <- \"train/\"\n\ntrain_data_gen <- image_data_generator(\n    rescale = 1/255, \n    validation_split = .2)\n\ntrain_images <- flow_images_from_directory(\n                      path_train,\n                      train_data_gen,\n                      subset = 'training',\n                      target_size = target_size,\n                      class_mode = \"categorical\",\n                      shuffle=FALSE,\n                      classes = breed_list,\n                      seed = 2021)","metadata":{"_uuid":"bf142425-3ca3-4b18-bf86-b410f1c574d9","_cell_guid":"4df59c02-ae16-4387-be1b-a83eefb90f48","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]}]}