Minifier.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "import PIL\n",
    "from PIL import Image, ImageFile\n",
    "from tqdm import tqdm\n",
    "\n",
    "\n",
    "# Needed for some images in Pinterest and Wikimedia dataset\n",
    "PIL.Image.MAX_IMAGE_PIXELS = 3000000000\n",
    "# Some images are \"broken\" in Wikimedia dataset\n",
    "ImageFile.LOAD_TRUNCATED_IMAGES = True\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from torchvision import transforms\n",
    "\n",
    "images_transforms = transforms.Compose([\n",
    "    transforms.Resize(256),\n",
    "    transforms.CenterCrop(224),\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Parameters\n",
    "INPUT_DIR = os.path.join(\"images\", \"img\")\n",
    "OUTPUT_DIR = os.path.join(\"mini-images-224-224-v2\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create OUTPUT_DIR if not exists\n",
    "os.makedirs(OUTPUT_DIR, exist_ok=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for file in tqdm(os.listdir(INPUT_DIR)[::-1]):\n",
    "    input_path = os.path.join(INPUT_DIR, file)\n",
    "    if not os.path.isfile(input_path):\n",
    "        print(\"input_path is not file\", input_path)\n",
    "        continue\n",
    "    output_path = os.path.join(OUTPUT_DIR, file)\n",
    "    if os.path.exists(output_path):\n",
    "        continue\n",
    "    image = Image.open(input_path).convert(\"RGB\")\n",
    "    # image = image.resize(TARGET_SIZE, resample=PIL.Image.BILINEAR)\n",
    "    image = images_transforms(image)\n",
    "    image.save(output_path)\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "3.8.5",
   "language": "python",
   "name": "3.8.5"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}