{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "50680cbc",
   "metadata": {},
   "source": [
    "Read/load the cifar10 dataset using tf.keras.datasets\n",
    "- Display the first 25 images\n",
    "- Convert them to greyscale images by reducing the 3 colors (r,g,b) to  \n",
    "  one greyscale\n",
    "  using the formula gray = 0.2989 * r + 0.5870 * g + 0.1140 * b\n",
    "- Display the first 25 images in greyscale"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2dc5ea2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e846355a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the CIFAR-10 dataset\n",
    "(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "85a493d2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# In case of special pictures\n",
    "selectPicture = -1    # -1 for all or number for a class starting from 0\n",
    "\n",
    "# Define a list of class names for CIFAR-10\n",
    "class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4eacb734",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the indices of images with a special label in the training set\n",
    "special_indices = np.where(y_train == selectPicture)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "be2d0cd2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Display the first 25 images in the training set\n",
    "plt.figure(figsize=(10,10))\n",
    "for i in range(25):\n",
    "    plt.subplot(5, 5, i+1)\n",
    "    if selectPicture == -1 :\n",
    "         plt.imshow(x_train[i])   # all images\n",
    "         plt.title(class_names[y_train[i][0]])\n",
    "    else :     \n",
    "         plt.imshow(x_train[special_indices[i]])  # special Picture only\n",
    "         plt.title(class_names[selectPicture])   \n",
    "    plt.xticks([])\n",
    "    plt.yticks([])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "938e632d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert images to grayscale\n",
    "train_images_gray = np.dot(x_train[..., :3], [0.2989, 0.5870, 0.1140])\n",
    "test_images_gray = np.dot(x_test[..., :3], [0.2989, 0.5870, 0.1140])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "96333686",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Normalize pixel values to [0, 1]\n",
    "train_images_gray = train_images_gray / 255.0\n",
    "test_images_gray = test_images_gray / 255.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "64d3d2ae",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Display the first 25 images in the training set\n",
    "plt.figure(figsize=(10,10))\n",
    "for i in range(25):\n",
    "    plt.subplot(5, 5, i+1)\n",
    "    if selectPicture == -1 :\n",
    "         plt.imshow(train_images_gray[i],cmap='gray')   # all images\n",
    "         plt.title(class_names[y_train[i][0]])\n",
    "    else :     \n",
    "         plt.imshow(train_images_gray[special_indices[i]],cmap='gray')  # special Picture only\n",
    "         plt.title(class_names[selectPicture])   \n",
    "    plt.xticks([])\n",
    "    plt.yticks([])\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}