Image_classification_CNN.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "mount_file_id": "1bLolywYjKjk4nx92b5SaRbqHkqElrWOx",
      "authorship_tag": "ABX9TyO4hCS4EdBs6xriPKb+ISHF"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Image Classification Using Convolutional Neural Networks for MNIST (handwritten dataset)"
      ],
      "metadata": {
        "id": "c5KCM4atpNMJ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt"
      ],
      "metadata": {
        "id": "a2l9GJ4sqAaJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# load dataset MINST from tf \\\n",
        "mnist = tf.keras.datasets.mnist\n",
        "(x_train, y_train), (x_test, y_test) = mnist.load_data()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AZ21dFEmqPOv",
        "outputId": "6994a2d5-a303-43ac-dd68-f2d4ede6d87f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
            "\u001b[1m11490434/11490434\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# view the dataset\n",
        "print(x_train.shape)\n",
        "print(y_train.shape)\n",
        "print(x_test.shape)\n",
        "print(y_test.shape)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SxGyL0OKqjZD",
        "outputId": "932f91e7-3ff1-4280-e778-86a78135de2e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(60000, 28, 28)\n",
            "(60000,)\n",
            "(10000, 28, 28)\n",
            "(10000,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# visualize available data\n",
        "plt.imshow(x_train[10000], cmap='gray')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 430
        },
        "id": "n3DmspwNr6Np",
        "outputId": "55d1d47c-9155-4469-f338-51fefa488ba3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaAAAAGdCAYAAABU0qcqAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAbhElEQVR4nO3df2zU9R3H8dcV6InaXq21vVZ+WPAHk19mTLoOZSgNpTMMkBh0bEFjJGgxKhOXmim6mXWyxDkN6rYsdGaCP7YBk2kTLLbsR4sBJcT9aGjTjTraIk24gyKlaz/7g3jzpKV+j7u+79rnI/kkve/3++737ccvffG9+/KpzznnBADAEEuzbgAAMDIRQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADAx2rqBz+vr69Phw4eVkZEhn89n3Q4AwCPnnI4fP66CggKlpQ18n5N0AXT48GGNHz/eug0AwHlqbW3VuHHjBtyfdG/BZWRkWLcAAIiDwX6eJyyANm7cqCuuuEIXXHCBioqK9N57732hOt52A4DhYbCf5wkJoNdee01r167V+vXr9f7772vmzJkqLS3VkSNHEnE6AEAqcgkwe/ZsV15eHnnd29vrCgoKXGVl5aC1oVDISWIwGAxGio9QKHTOn/dxvwM6ffq09u3bp5KSksi2tLQ0lZSUqL6+/qzju7u7FQ6HowYAYPiLewAdPXpUvb29ysvLi9qel5en9vb2s46vrKxUIBCIDJ6AA4CRwfwpuIqKCoVCochobW21bgkAMATi/u+AcnJyNGrUKHV0dERt7+joUDAYPOt4v98vv98f7zYAAEku7ndA6enpmjVrlmpqaiLb+vr6VFNTo+Li4nifDgCQohKyEsLatWu1cuVKfeUrX9Hs2bP17LPPqqurS3fddVciTgcASEEJCaDly5fr448/1uOPP6729nZdd911qq6uPuvBBADAyOVzzjnrJj4rHA4rEAhYtwEAOE+hUEiZmZkD7jd/Cg4AMDIRQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAEwQQAMAEAQQAMDHaugGMLOPHj/dcU1FR4blm+vTpnmskac6cOZ5rfD6f5xrnnOeaP/zhD55rLrnkEs81kvS3v/3Nc817773nuaaqqspzDYYP7oAAACYIIACAibgH0BNPPCGfzxc1pkyZEu/TAABSXEI+A5o6dareeeed/59kNB81AQCiJSQZRo8erWAwmIhvDQAYJhLyGdDBgwdVUFCgSZMmacWKFTp06NCAx3Z3dyscDkcNAMDwF/cAKioqUlVVlaqrq/Xiiy+qpaVFN954o44fP97v8ZWVlQoEApERy2O6AIDUE/cAKisr02233aYZM2aotLRUb731lo4dO6bXX3+93+MrKioUCoUio7W1Nd4tAQCSUMKfDsjKytLVV1+tpqamfvf7/X75/f5EtwEASDIJ/3dAJ06cUHNzs/Lz8xN9KgBACol7AD388MOqq6vTv/71L/31r3/V0qVLNWrUKN1xxx3xPhUAIIXF/S24jz76SHfccYc6Ozt12WWX6YYbblBDQ4Muu+yyeJ8KAJDCfC6WVRETKBwOKxAIWLcxolx33XUx1T3yyCOea772ta95rhnKJyM7Ozs91zQ2NnquiWUekt3Ro0c91+Tl5SWgEySLUCikzMzMAfezFhwAwAQBBAAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATCf+FdIjdd77zHc81L7zwguea9PR0zzWSNHq098tn165dnmu++c1veq4Z6BcgDqavr89zzX//+1/PNbHMeXV1teeaOXPmeK4Bhgp3QAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAE6yGncQyMzM911x44YUJ6KR/HR0dnmvWrVvnuebAgQOea5JdLCtox7JS91B68803rVtAiuEOCABgggACAJgggAAAJgggAIAJAggAYIIAAgCYIIAAACYIIACACQIIAGCCAAIAmCCAAAAmCCAAgAkWI01iL730kuea1157LQGd9K+np8dzTSgUSkAnqWfq1Kmea6644or4NzKAU6dOea753e9+l4BOMJxxBwQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAEwQQAMAEi5Emsd7eXs81R48eTUAniLf333/fc83o0d7/uMayqKgkPf30055r3n777ZjOhZGLOyAAgAkCCABgwnMA7d69W4sWLVJBQYF8Pp+2bdsWtd85p8cff1z5+fkaO3asSkpKdPDgwXj1CwAYJjwHUFdXl2bOnKmNGzf2u3/Dhg167rnn9NJLL2nPnj266KKLVFpaGvN70QCA4cnzp5plZWUqKyvrd59zTs8++6y+//3va/HixZKkl19+WXl5edq2bZtuv/328+sWADBsxPUzoJaWFrW3t6ukpCSyLRAIqKioSPX19f3WdHd3KxwORw0AwPAX1wBqb2+XJOXl5UVtz8vLi+z7vMrKSgUCgcgYP358PFsCACQp86fgKioqFAqFIqO1tdW6JQDAEIhrAAWDQUlSR0dH1PaOjo7Ivs/z+/3KzMyMGgCA4S+uAVRYWKhgMKiamprItnA4rD179qi4uDiepwIApDjPT8GdOHFCTU1NkdctLS3av3+/srOzNWHCBD344IN66qmndNVVV6mwsFCPPfaYCgoKtGTJknj2DQBIcZ4DaO/evbrpppsir9euXStJWrlypaqqqvTII4+oq6tLq1at0rFjx3TDDTeourpaF1xwQfy6BgCkPJ9zzlk38VnhcFiBQMC6DaS4WD9LXL58ueeaRx991HPNhAkTPNf09PR4rnnqqac815xPHfBZoVDonH8WzZ+CAwCMTAQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAE55/HQNwPi666CLPNb/85S8915SVlXmukWJfRXso/OlPf/Jc8/LLLyegEyA+uAMCAJgggAAAJgggAIAJAggAYIIAAgCYIIAAACYIIACACQIIAGCCAAIAmCCAAAAmCCAAgAkCCABgwuecc9ZNfFY4HFYgELBuAwmSlZXluaa9vd1zTVpabH+3GjVqVEx1yerjjz+Oqa6zs9NzzS9+8QvPNc8//7znmr6+Ps81sBEKhc65wC93QAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEywGCmGpalTp8ZUN3v27Dh30r8HHnjAc8306dMT0ImtXbt2ea5ZsWKF55ojR454rsH5YzFSAEBSIoAAACYIIACACQIIAGCCAAIAmCCAAAAmCCAAgAkCCABgggACAJgggAAAJgggAIAJAggAYILFSAEDY8eO9Vxz7bXXeq4pKSnxXCNJP/rRj2KqGwqLFy/2XLNjx44EdILBsBgpACApEUAAABOeA2j37t1atGiRCgoK5PP5tG3btqj9d955p3w+X9RYuHBhvPoFAAwTngOoq6tLM2fO1MaNGwc8ZuHChWpra4uMLVu2nFeTAIDhZ7TXgrKyMpWVlZ3zGL/fr2AwGHNTAIDhLyGfAdXW1io3N1fXXHON7r33XnV2dg54bHd3t8LhcNQAAAx/cQ+ghQsX6uWXX1ZNTY2efvpp1dXVqaysTL29vf0eX1lZqUAgEBnjx4+Pd0sAgCTk+S24wdx+++2Rr6dPn64ZM2Zo8uTJqq2t1fz58886vqKiQmvXro28DofDhBAAjAAJfwx70qRJysnJUVNTU7/7/X6/MjMzowYAYPhLeAB99NFH6uzsVH5+fqJPBQBIIZ7fgjtx4kTU3UxLS4v279+v7OxsZWdn68knn9SyZcsUDAbV3NysRx55RFdeeaVKS0vj2jgAILV5DqC9e/fqpptuirz+9POblStX6sUXX9SBAwf061//WseOHVNBQYEWLFigH/7wh/L7/fHrGgCQ8liMFBjGfD5fTHVvvfWW55oFCxbEdC6vnnnmGc8169atS0AnGAyLkQIAkhIBBAAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwETcfyU3gOQR62L3SbZIfpTm5mbrFhAn3AEBAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwwWKkwDB22223xVQ3f/78OHcSP++88451C4gT7oAAACYIIACACQIIAGCCAAIAmCCAAAAmCCAAgAkCCABgggACAJgggAAAJgggAIAJAggAYIIAAgCYYDFSIEXccMMNnmuefPLJmM41evTQ/GjYtm2b55q2trb4NwIT3AEBAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwwWKkgIG77rrLc80LL7zguSY9Pd1zTaz+85//eK759re/7bnmk08+8VyD5MQdEADABAEEADDhKYAqKyt1/fXXKyMjQ7m5uVqyZIkaGxujjjl16pTKy8t16aWX6uKLL9ayZcvU0dER16YBAKnPUwDV1dWpvLxcDQ0N2rlzp3p6erRgwQJ1dXVFjnnooYf05ptv6o033lBdXZ0OHz6sW2+9Ne6NAwBSm6eHEKqrq6NeV1VVKTc3V/v27dPcuXMVCoX0q1/9Sps3b9bNN98sSdq0aZO+9KUvqaGhQV/96lfj1zkAIKWd12dAoVBIkpSdnS1J2rdvn3p6elRSUhI5ZsqUKZowYYLq6+v7/R7d3d0Kh8NRAwAw/MUcQH19fXrwwQc1Z84cTZs2TZLU3t6u9PR0ZWVlRR2bl5en9vb2fr9PZWWlAoFAZIwfPz7WlgAAKSTmACovL9eHH36oV1999bwaqKioUCgUiozW1tbz+n4AgNQQ0z9EXbNmjXbs2KHdu3dr3Lhxke3BYFCnT5/WsWPHou6COjo6FAwG+/1efr9ffr8/ljYAACnM0x2Qc05r1qzR1q1btWvXLhUWFkbtnzVrlsaMGaOamprItsbGRh06dEjFxcXx6RgAMCx4ugMqLy/X5s2btX37dmVkZEQ+1wkEAho7dqwCgYDuvvturV27VtnZ2crMzNT999+v4uJinoADAETxFEAvvviiJGnevHlR2zdt2qQ777xTkvTTn/5UaWlpWrZsmbq7u1VaWhrTGlYAgOHN55xz1k18VjgcViAQsG4DI9S1117ruWbNmjWea1atWuW5xufzea6J1dGjRz3X3HLLLZ5r9u7d67kGqSMUCikzM3PA/awFBwAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwEdNvREXyimU157KyspjO9fbbb3uuyc7O9lxTVFTkuWbatGmeayRp6dKlnmsyMjJiOpdXvb29nmv++Mc/xnSu++67z3NNW1tbTOfCyMUdEADABAEEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABM+55yzbuKzwuGwAoGAdRspa+fOnZ5rbr755gR0gnNpaGjwXPOzn/3Mc83rr7/uuQaIl1AopMzMzAH3cwcEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADAxGjrBhBfv/3tbz3XsBjp/3388ceea1asWOG5ZteuXZ5rkmzdYOC8cQcEADBBAAEATBBAAAATBBAAwAQBBAAwQQABAEwQQAAAEwQQAMAEAQQAMEEAAQBMEEAAABMEEADAhM8l2QqH4XBYgUDAug0AwHkKhULKzMwccD93QAAAEwQQAMCEpwCqrKzU9ddfr4yMDOXm5mrJkiVqbGyMOmbevHny+XxRY/Xq1XFtGgCQ+jwFUF1dncrLy9XQ0KCdO3eqp6dHCxYsUFdXV9Rx99xzj9ra2iJjw4YNcW0aAJD6PP1G1Orq6qjXVVVVys3N1b59+zR37tzI9gsvvFDBYDA+HQIAhqXz+gwoFApJkrKzs6O2v/LKK8rJydG0adNUUVGhkydPDvg9uru7FQ6HowYAYARwMert7XW33HKLmzNnTtT2n//85666utodOHDA/eY3v3GXX365W7p06YDfZ/369U4Sg8FgMIbZCIVC58yRmANo9erVbuLEia61tfWcx9XU1DhJrqmpqd/9p06dcqFQKDJaW1vNJ43BYDAY5z8GCyBPnwF9as2aNdqxY4d2796tcePGnfPYoqIiSVJTU5MmT5581n6/3y+/3x9LGwCAFOYpgJxzuv/++7V161bV1taqsLBw0Jr9+/dLkvLz82NqEAAwPHkKoPLycm3evFnbt29XRkaG2tvbJUmBQEBjx45Vc3OzNm/erG984xu69NJLdeDAAT300EOaO3euZsyYkZD/AABAivLyuY8GeJ9v06ZNzjnnDh065ObOneuys7Od3+93V155pVu3bt2g7wN+VigUMn/fksFgMBjnPwb72c9ipACAhGAxUgBAUiKAAAAmCCAAgAkCCABgggACAJgggAAAJgggAIAJAggAYIIAAgCYIIAAACYIIACACQIIAGCCAAIAmCCAAAAmCCAAgAkCCABgggACAJgggAAAJgggAIAJAggAYIIAAgCYIIAAACYIIACACQIIAGCCAAIAmEi6AHLOWbcAAIiDwX6eJ10AHT9+3LoFAEAcDPbz3OeS7Jajr69Phw8fVkZGhnw+X9S+cDis8ePHq7W1VZmZmUYd2mMezmAezmAezmAezkiGeXDO6fjx4yooKFBa2sD3OaOHsKcvJC0tTePGjTvnMZmZmSP6AvsU83AG83AG83AG83CG9TwEAoFBj0m6t+AAACMDAQQAMJFSAeT3+7V+/Xr5/X7rVkwxD2cwD2cwD2cwD2ek0jwk3UMIAICRIaXugAAAwwcBBAAwQQABAEwQQAAAEykTQBs3btQVV1yhCy64QEVFRXrvvfesWxpyTzzxhHw+X9SYMmWKdVsJt3v3bi1atEgFBQXy+Xzatm1b1H7nnB5//HHl5+dr7NixKikp0cGDB22aTaDB5uHOO+886/pYuHChTbMJUllZqeuvv14ZGRnKzc3VkiVL1NjYGHXMqVOnVF5erksvvVQXX3yxli1bpo6ODqOOE+OLzMO8efPOuh5Wr15t1HH/UiKAXnvtNa1du1br16/X+++/r5kzZ6q0tFRHjhyxbm3ITZ06VW1tbZHx5z//2bqlhOvq6tLMmTO1cePGfvdv2LBBzz33nF566SXt2bNHF110kUpLS3Xq1Kkh7jSxBpsHSVq4cGHU9bFly5Yh7DDx6urqVF5eroaGBu3cuVM9PT1asGCBurq6Isc89NBDevPNN/XGG2+orq5Ohw8f1q233mrYdfx9kXmQpHvuuSfqetiwYYNRxwNwKWD27NmuvLw88rq3t9cVFBS4yspKw66G3vr1693MmTOt2zAlyW3dujXyuq+vzwWDQfeTn/wksu3YsWPO7/e7LVu2GHQ4ND4/D845t3LlSrd48WKTfqwcOXLESXJ1dXXOuTP/78eMGePeeOONyDH/+Mc/nCRXX19v1WbCfX4enHPu61//unvggQfsmvoCkv4O6PTp09q3b59KSkoi29LS0lRSUqL6+nrDzmwcPHhQBQUFmjRpklasWKFDhw5Zt2SqpaVF7e3tUddHIBBQUVHRiLw+amtrlZubq2uuuUb33nuvOjs7rVtKqFAoJEnKzs6WJO3bt089PT1R18OUKVM0YcKEYX09fH4ePvXKK68oJydH06ZNU0VFhU6ePGnR3oCSbjHSzzt69Kh6e3uVl5cXtT0vL0///Oc/jbqyUVRUpKqqKl1zzTVqa2vTk08+qRtvvFEffvihMjIyrNsz0d7eLkn9Xh+f7hspFi5cqFtvvVWFhYVqbm7Wo48+qrKyMtXX12vUqFHW7cVdX1+fHnzwQc2ZM0fTpk2TdOZ6SE9PV1ZWVtSxw/l66G8eJOlb3/qWJk6cqIKCAh04cEDf+9731NjYqN///veG3UZL+gDC/5WVlUW+njFjhoqKijRx4kS9/vrruvvuuw07QzK4/fbbI19Pnz5dM2bM0OTJk1VbW6v58+cbdpYY5eXl+vDDD0fE56DnMtA8rFq1KvL19OnTlZ+fr/nz56u5uVmTJ08e6jb7lfRvweXk5GjUqFFnPcXS0dGhYDBo1FVyyMrK0tVXX62mpibrVsx8eg1wfZxt0qRJysnJGZbXx5o1a7Rjxw69++67Ub++JRgM6vTp0zp27FjU8cP1ehhoHvpTVFQkSUl1PSR9AKWnp2vWrFmqqamJbOvr61NNTY2Ki4sNO7N34sQJNTc3Kz8/37oVM4WFhQoGg1HXRzgc1p49e0b89fHRRx+ps7NzWF0fzjmtWbNGW7du1a5du1RYWBi1f9asWRozZkzU9dDY2KhDhw4Nq+thsHnoz/79+yUpua4H66cgvohXX33V+f1+V1VV5f7+97+7VatWuaysLNfe3m7d2pD67ne/62pra11LS4v7y1/+4kpKSlxOTo47cuSIdWsJdfz4cffBBx+4Dz74wElyzzzzjPvggw/cv//9b+eccz/+8Y9dVlaW2759uztw4IBbvHixKywsdJ988olx5/F1rnk4fvy4e/jhh119fb1raWlx77zzjvvyl7/srrrqKnfq1Cnr1uPm3nvvdYFAwNXW1rq2trbIOHnyZOSY1atXuwkTJrhdu3a5vXv3uuLiYldcXGzYdfwNNg9NTU3uBz/4gdu7d69raWlx27dvd5MmTXJz58417jxaSgSQc849//zzbsKECS49Pd3Nnj3bNTQ0WLc05JYvX+7y8/Ndenq6u/zyy93y5ctdU1OTdVsJ9+677zpJZ42VK1c65848iv3YY4+5vLw85/f73fz5811jY6Nt0wlwrnk4efKkW7BggbvsssvcmDFj3MSJE90999wz7P6S1t9/vyS3adOmyDGffPKJu++++9wll1ziLrzwQrd06VLX1tZm13QCDDYPhw4dcnPnznXZ2dnO7/e7K6+80q1bt86FQiHbxj+HX8cAADCR9J8BAQCGJwIIAGCCAAIAmCCAAAAmCCAAgAkCCABgggACAJgggAAAJgggAIAJAggAYIIAAgCYIIAAACb+B0EEzIJl1HwqAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Visualize sample images\n",
        "fig, axes = plt.subplots(1, 10, figsize=(10, 3))\n",
        "for i in range(10):\n",
        "    axes[i].imshow(x_train[i], cmap='gray')\n",
        "    axes[i].axis('off')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 102
        },
        "id": "UvRQEplkr1Gy",
        "outputId": "408edb2f-6628-47bb-e3ec-9641c2d417bf"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x300 with 10 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Normalize the pixel value\n",
        "x_train = x_train / 255.0\n",
        "x_test = x_test / 255.0"
      ],
      "metadata": {
        "id": "5nAN1-JwscqD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# View the data\n",
        "\n",
        "print(x_train[0])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "collapsed": true,
        "id": "605gCLivsq9a",
        "outputId": "13c586d0-59a3-4372-b1c6-600b529852c7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[[0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.01176471 0.07058824 0.07058824 0.07058824 0.49411765 0.53333333\n",
            "  0.68627451 0.10196078 0.65098039 1.         0.96862745 0.49803922\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.11764706 0.14117647 0.36862745 0.60392157\n",
            "  0.66666667 0.99215686 0.99215686 0.99215686 0.99215686 0.99215686\n",
            "  0.88235294 0.6745098  0.99215686 0.94901961 0.76470588 0.25098039\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.19215686 0.93333333 0.99215686 0.99215686 0.99215686\n",
            "  0.99215686 0.99215686 0.99215686 0.99215686 0.99215686 0.98431373\n",
            "  0.36470588 0.32156863 0.32156863 0.21960784 0.15294118 0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.07058824 0.85882353 0.99215686 0.99215686 0.99215686\n",
            "  0.99215686 0.99215686 0.77647059 0.71372549 0.96862745 0.94509804\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.31372549 0.61176471 0.41960784 0.99215686\n",
            "  0.99215686 0.80392157 0.04313725 0.         0.16862745 0.60392157\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.05490196 0.00392157 0.60392157\n",
            "  0.99215686 0.35294118 0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.54509804\n",
            "  0.99215686 0.74509804 0.00784314 0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.04313725\n",
            "  0.74509804 0.99215686 0.2745098  0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.1372549  0.94509804 0.88235294 0.62745098 0.42352941 0.00392157\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.31764706 0.94117647 0.99215686 0.99215686 0.46666667\n",
            "  0.09803922 0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.17647059 0.72941176 0.99215686 0.99215686\n",
            "  0.58823529 0.10588235 0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.0627451  0.36470588 0.98823529\n",
            "  0.99215686 0.73333333 0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.97647059\n",
            "  0.99215686 0.97647059 0.25098039 0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.18039216 0.50980392 0.71764706 0.99215686\n",
            "  0.99215686 0.81176471 0.00784314 0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.15294118 0.58039216 0.89803922 0.99215686 0.99215686 0.99215686\n",
            "  0.98039216 0.71372549 0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.09411765 0.44705882\n",
            "  0.86666667 0.99215686 0.99215686 0.99215686 0.99215686 0.78823529\n",
            "  0.30588235 0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.09019608 0.25882353 0.83529412 0.99215686\n",
            "  0.99215686 0.99215686 0.99215686 0.77647059 0.31764706 0.00784314\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.07058824 0.67058824 0.85882353 0.99215686 0.99215686 0.99215686\n",
            "  0.99215686 0.76470588 0.31372549 0.03529412 0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.21568627 0.6745098\n",
            "  0.88627451 0.99215686 0.99215686 0.99215686 0.99215686 0.95686275\n",
            "  0.52156863 0.04313725 0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.53333333 0.99215686\n",
            "  0.99215686 0.99215686 0.83137255 0.52941176 0.51764706 0.0627451\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]\n",
            " [0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.         0.         0.\n",
            "  0.         0.         0.         0.        ]]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Convert the labels to one-hot encoding\n",
        "y_train = tf.keras.utils.to_categorical(y_train, 10)\n",
        "y_test = tf.keras.utils.to_categorical(y_test, 10)"
      ],
      "metadata": {
        "id": "k6sulgI1s7w3"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(y_train[0])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CcGI0vTatKtB",
        "outputId": "a7a71345-346a-4609-fd4e-ade4e3350246"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[0. 0. 0. 0. 0. 1. 0. 0. 0. 0.]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "# Data Augmentation for artificially improve the model's generalization\n",
        "datagen = ImageDataGenerator(rotation_range=10, zoom_range=0.1)\n",
        "datagen.fit(x_train.reshape(-1, 28, 28, 1))\n"
      ],
      "metadata": {
        "id": "zWNd_-MftPis"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n",
        "\n",
        "# CNN Model Architecture\n",
        "model = Sequential([\n",
        "    Conv2D(32, (3,3), activation='relu', input_shape=(28, 28, 1)),\n",
        "    MaxPooling2D(pool_size=(2,2)),\n",
        "    Conv2D(64, (3,3), activation='relu'),\n",
        "    MaxPooling2D(pool_size=(2,2)),\n",
        "    Flatten(),\n",
        "    Dense(128, activation='relu'),\n",
        "    Dropout(0.5),\n",
        "    Dense(10, activation='softmax')  # Output layer for 10 classes\n",
        "])\n",
        "\n",
        "# Compile Model\n",
        "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "model.summary()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 464
        },
        "id": "eySdmM50tper",
        "outputId": "2f941222-42eb-41a4-8621-0a5bea61aab4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
            "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                        \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape               \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m        Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m32\u001b[0m)          │             \u001b[38;5;34m320\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)         │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m32\u001b[0m)          │               \u001b[38;5;34m0\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m64\u001b[0m)          │          \u001b[38;5;34m18,496\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m)            │               \u001b[38;5;34m0\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1600\u001b[0m)                │               \u001b[38;5;34m0\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)                 │         \u001b[38;5;34m204,928\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)                 │               \u001b[38;5;34m0\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)                  │           \u001b[38;5;34m1,290\u001b[0m │\n",
              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                         </span>┃<span style=\"font-weight: bold\"> Output Shape                </span>┃<span style=\"font-weight: bold\">         Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">26</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">26</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">320</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)         │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)          │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">11</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">11</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)          │          <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)            │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)                    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1600</span>)                │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)                 │         <span style=\"color: #00af00; text-decoration-color: #00af00\">204,928</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)                    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)                 │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)                  │           <span style=\"color: #00af00; text-decoration-color: #00af00\">1,290</span> │\n",
              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m225,034\u001b[0m (879.04 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">225,034</span> (879.04 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m225,034\u001b[0m (879.04 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">225,034</span> (879.04 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Train the model\n",
        "history = model.fit(datagen.flow(x_train.reshape(-1, 28, 28, 1), y_train, batch_size=64),\n",
        "                    epochs=15,\n",
        "                    validation_data=(x_test.reshape(-1, 28, 28, 1), y_test))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UXsVYy93t3XY",
        "outputId": "944789d4-3847-4c31-9512-65d7c1ce049e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:122: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
            "  self._warn_if_super_not_called()\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 27ms/step - accuracy: 0.8297 - loss: 0.5364 - val_accuracy: 0.9837 - val_loss: 0.0492\n",
            "Epoch 2/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m31s\u001b[0m 20ms/step - accuracy: 0.9670 - loss: 0.1114 - val_accuracy: 0.9878 - val_loss: 0.0369\n",
            "Epoch 3/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 20ms/step - accuracy: 0.9762 - loss: 0.0828 - val_accuracy: 0.9896 - val_loss: 0.0319\n",
            "Epoch 4/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 21ms/step - accuracy: 0.9796 - loss: 0.0696 - val_accuracy: 0.9916 - val_loss: 0.0260\n",
            "Epoch 5/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 20ms/step - accuracy: 0.9826 - loss: 0.0559 - val_accuracy: 0.9921 - val_loss: 0.0272\n",
            "Epoch 6/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 21ms/step - accuracy: 0.9848 - loss: 0.0495 - val_accuracy: 0.9919 - val_loss: 0.0246\n",
            "Epoch 7/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 20ms/step - accuracy: 0.9856 - loss: 0.0480 - val_accuracy: 0.9935 - val_loss: 0.0236\n",
            "Epoch 8/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 20ms/step - accuracy: 0.9883 - loss: 0.0397 - val_accuracy: 0.9927 - val_loss: 0.0237\n",
            "Epoch 9/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 22ms/step - accuracy: 0.9875 - loss: 0.0388 - val_accuracy: 0.9920 - val_loss: 0.0253\n",
            "Epoch 10/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 20ms/step - accuracy: 0.9895 - loss: 0.0365 - val_accuracy: 0.9940 - val_loss: 0.0212\n",
            "Epoch 11/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 20ms/step - accuracy: 0.9903 - loss: 0.0324 - val_accuracy: 0.9941 - val_loss: 0.0193\n",
            "Epoch 12/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 20ms/step - accuracy: 0.9903 - loss: 0.0321 - val_accuracy: 0.9938 - val_loss: 0.0221\n",
            "Epoch 13/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 20ms/step - accuracy: 0.9907 - loss: 0.0285 - val_accuracy: 0.9938 - val_loss: 0.0216\n",
            "Epoch 14/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 21ms/step - accuracy: 0.9915 - loss: 0.0271 - val_accuracy: 0.9926 - val_loss: 0.0262\n",
            "Epoch 15/15\n",
            "\u001b[1m938/938\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 22ms/step - accuracy: 0.9911 - loss: 0.0252 - val_accuracy: 0.9935 - val_loss: 0.0222\n"
          ]
        }
      ]
    },
    {
      "source": [
        "# Evaluate the model\n",
        "loss, accuracy = model.evaluate(x_test.reshape(-1, 28, 28, 1), y_test)  # Reshape x_test\n",
        "print(f\"Test Accuracy: {accuracy:.4f}\")"
      ],
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uguYWP1Ovr8P",
        "outputId": "e63997a2-a962-4b8b-9877-b14dcb306ac2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9925 - loss: 0.0253\n",
            "Test Accuracy: 0.9935\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Plot Training and Validation Accuracy\n",
        "plt.plot(history.history['accuracy'], label='Train Accuracy')\n",
        "plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.title('Training and Validation Accuracy')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "Th7bIN37vxyt",
        "outputId": "1e67f93f-bf6b-4462-f807-03b17081b886"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkAAAAHHCAYAAABXx+fLAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAAB4y0lEQVR4nO3dd1xTV+MG8CcJZLD3FEXQihMVkFeto1WLolatddUqorXVqq2l1mq1rg46rfO1rXX0565VqW1ftYijap0ojrpwAIqyHOyZ3N8fgQsRUKJAGM/388knycm5N+cGJI/nnnuORBAEAURERET1iNTQDSAiIiKqbgxAREREVO8wABEREVG9wwBERERE9Q4DEBEREdU7DEBERERU7zAAERERUb3DAERERET1DgMQERER1TsMQETPaMyYMXB3d3+qbefNmweJRFK5DaphYmJiIJFIsHbt2mp/b4lEgnnz5onP165dC4lEgpiYmCdu6+7ujjFjxlRqe57ld4WIKhcDENVZEomkQrcDBw4Yuqn13jvvvAOJRIJr166VW2fWrFmQSCQ4d+5cNbZMf3fu3MG8efMQFRVl6KaU6dKlS5BIJFAqlXj48KGhm0NkMAxAVGetW7dO59arV68yy5s3b/5M77Ny5UpcuXLlqbadPXs2srOzn+n964KRI0cCADZu3FhunU2bNqF169Zo06bNU7/PqFGjkJ2djUaNGj31Pp7kzp07mD9/fpkB6Fl+VyrL+vXr4eTkBAD49ddfDdoWIkMyMnQDiKrK66+/rvP82LFjCA8PL1X+qKysLJiYmFT4fYyNjZ+qfQBgZGQEIyP+M/T390eTJk2wadMmzJkzp9TrR48exc2bN/HFF1880/vIZDLIZLJn2sezeJbflcogCAI2btyI1157DTdv3sSGDRvwxhtvGLRN5cnMzISpqamhm0F1GHuAqF7r3r07WrVqhcjISHTt2hUmJib46KOPAAC//fYb+vbtCxcXFygUCnh6euKTTz6BWq3W2cej4zqKxrx88803+PHHH+Hp6QmFQgE/Pz+cPHlSZ9uyxgBJJBJMnjwZYWFhaNWqFRQKBVq2bIndu3eXav+BAwfg6+sLpVIJT09P/PDDDxUeV3To0CEMGTIEDRs2hEKhgJubG957771SPVJjxoyBmZkZ4uPjMXDgQJiZmcHe3h7Tpk0r9Vk8fPgQY8aMgaWlJaysrBAUFFTh0ywjR47E5cuXcfr06VKvbdy4ERKJBCNGjEBeXh7mzJkDHx8fWFpawtTUFF26dMH+/fuf+B5ljQESBAGffvopGjRoABMTE7zwwgv4999/S217//59TJs2Da1bt4aZmRksLCzQp08fnD17Vqxz4MAB+Pn5AQCCg4PF06xF45/KGgOUmZmJ999/H25ublAoFGjWrBm++eYbCIKgU0+f34vyHDlyBDExMRg+fDiGDx+Ov//+G7dv3y5VT6PRYPHixWjdujWUSiXs7e3Ru3dvnDp1Sqfe+vXr0aFDB5iYmMDa2hpdu3bFX3/9pdPmkmOwijw6vqro53Lw4EG8/fbbcHBwQIMGDQAAsbGxePvtt9GsWTOoVCrY2tpiyJAhZY7jevjwId577z24u7tDoVCgQYMGGD16NFJSUpCRkQFTU1O8++67pba7ffs2ZDIZQkNDK/hJUl3A/3pSvXfv3j306dMHw4cPx+uvvw5HR0cA2j/KZmZmCAkJgZmZGfbt24c5c+YgLS0NX3/99RP3u3HjRqSnp+Ott96CRCLBV199hVdeeQU3btx4Yk/A4cOHsX37drz99tswNzfHkiVLMHjwYMTFxcHW1hYAcObMGfTu3RvOzs6YP38+1Go1FixYAHt7+wod99atW5GVlYWJEyfC1tYWJ06cwNKlS3H79m1s3bpVp65arUZAQAD8/f3xzTffYO/evfj222/h6emJiRMnAtAGiQEDBuDw4cOYMGECmjdvjh07diAoKKhC7Rk5ciTmz5+PjRs3on379jrv/csvv6BLly5o2LAhUlJS8NNPP2HEiBEYP3480tPTsWrVKgQEBODEiRNo27Zthd6vyJw5c/Dpp58iMDAQgYGBOH36NF566SXk5eXp1Ltx4wbCwsIwZMgQNG7cGImJifjhhx/QrVs3XLx4ES4uLmjevDkWLFiAOXPm4M0330SXLl0AAJ06dSrzvQVBwMsvv4z9+/dj3LhxaNu2Lfbs2YMPPvgA8fHx+O6773TqV+T34nE2bNgAT09P+Pn5oVWrVjAxMcGmTZvwwQcf6NQbN24c1q5diz59+uCNN95AQUEBDh06hGPHjsHX1xcAMH/+fMybNw+dOnXCggULIJfLcfz4cezbtw8vvfRShT//kt5++23Y29tjzpw5yMzMBACcPHkS//zzD4YPH44GDRogJiYGK1asQPfu3XHx4kWxtzYjIwNdunTBpUuXMHbsWLRv3x4pKSnYuXMnbt++jbZt22LQoEHYsmULFi5cqNMTuGnTJgiCIJ6KpXpCIKonJk2aJDz6K9+tWzcBgPD999+Xqp+VlVWq7K233hJMTEyEnJwcsSwoKEho1KiR+PzmzZsCAMHW1la4f/++WP7bb78JAITff/9dLJs7d26pNgEQ5HK5cO3aNbHs7NmzAgBh6dKlYln//v0FExMTIT4+XiyLjo4WjIyMSu2zLGUdX2hoqCCRSITY2Fid4wMgLFiwQKduu3btBB8fH/F5WFiYAED46quvxLKCggKhS5cuAgBhzZo1T2yTn5+f0KBBA0GtVotlu3fvFgAIP/zwg7jP3Nxcne0ePHggODo6CmPHjtUpByDMnTtXfL5mzRoBgHDz5k1BEAQhKSlJkMvlQt++fQWNRiPW++ijjwQAQlBQkFiWk5Oj0y5B0P6sFQqFzmdz8uTJco/30d+Vos/s008/1an36quvChKJROd3oKK/F+XJy8sTbG1thVmzZollr732muDt7a1Tb9++fQIA4Z133im1j6LPKDo6WpBKpcKgQYNKfSYlP8dHP/8ijRo10vlsi34uzz//vFBQUKBTt6zf06NHjwoAhP/7v/8Ty+bMmSMAELZv315uu/fs2SMAEHbt2qXzeps2bYRu3bqV2o7qNp4Co3pPoVAgODi4VLlKpRIfp6enIyUlBV26dEFWVhYuX778xP0OGzYM1tbW4vOi3oAbN248cduePXvC09NTfN6mTRtYWFiI26rVauzduxcDBw6Ei4uLWK9Jkybo06fPE/cP6B5fZmYmUlJS0KlTJwiCgDNnzpSqP2HCBJ3nXbp00TmW//3vfzAyMhJ7hADtmJspU6ZUqD2AdtzW7du38ffff4tlGzduhFwux5AhQ8R9yuVyANpTNffv30dBQQF8fX3LPH32OHv37kVeXh6mTJmic9pw6tSppeoqFApIpdo/mWq1Gvfu3YOZmRmaNWum9/sW+d///geZTIZ33nlHp/z999+HIAjYtWuXTvmTfi8eZ9euXbh37x5GjBghlo0YMQJnz57VOeW3bds2SCQSzJ07t9Q+ij6jsLAwaDQazJkzR/xMHq3zNMaPH19qjFbJ39P8/Hzcu3cPTZo0gZWVlc7nvm3bNnh7e2PQoEHltrtnz55wcXHBhg0bxNcuXLiAc+fOPXFsINU9DEBU77m6uopfqCX9+++/GDRoECwtLWFhYQF7e3vxj2RqauoT99uwYUOd50Vh6MGDB3pvW7R90bZJSUnIzs5GkyZNStUrq6wscXFxGDNmDGxsbMRxPd26dQNQ+viKxoGU1x5AO1bD2dkZZmZmOvWaNWtWofYAwPDhwyGTycSrwXJycrBjxw706dNHJ0z+/PPPaNOmDZRKJWxtbWFvb48///yzQj+XkmJjYwEATZs21Sm3t7fXeT9AG7a+++47NG3aFAqFAnZ2drC3t8e5c+f0ft+S7+/i4gJzc3Od8qIrE4vaV+RJvxePs379ejRu3BgKhQLXrl3DtWvX4OnpCRMTE51AcP36dbi4uMDGxqbcfV2/fh1SqRQtWrR44vvqo3HjxqXKsrOzMWfOHHGMVNHn/vDhQ53P/fr162jVqtVj9y+VSjFy5EiEhYUhKysLgPa0oFKpFAM21R8MQFTvlfwfZpGHDx+iW7duOHv2LBYsWIDff/8d4eHh+PLLLwFovwyfpLyrjYRHBrdW9rYVoVar0atXL/z555/48MMPERYWhvDwcHGw7qPHV11XTjk4OKBXr17Ytm0b8vPz8fvvvyM9PV1nbMb69esxZswYeHp6YtWqVdi9ezfCw8Px4osvVujn8rQ+//xzhISEoGvXrli/fj327NmD8PBwtGzZskrft6Sn/b1IS0vD77//jps3b6Jp06birUWLFsjKysLGjRsr7XerIh4dPF+krH+LU6ZMwWeffYahQ4fil19+wV9//YXw8HDY2to+1ec+evRoZGRkICwsTLwqrl+/frC0tNR7X1S7cRA0URkOHDiAe/fuYfv27ejatatYfvPmTQO2qpiDgwOUSmWZEwc+bjLBIufPn8fVq1fx888/Y/To0WJ5eHj4U7epUaNGiIiIQEZGhk4vkL7z3owcORK7d+/Grl27sHHjRlhYWKB///7i67/++is8PDywfft2ndMtZZ2yqUibASA6OhoeHh5ieXJycqlelV9//RUvvPACVq1apVP+8OFD2NnZic/1OQXUqFEj7N27F+np6Tq9QEWnWCtrvqLt27cjJycHK1as0GkroP35zJ49G0eOHMHzzz8PT09P7NmzB/fv3y+3F8jT0xMajQYXL1587KBza2vrUlcB5uXl4e7duxVu+6+//oqgoCB8++23YllOTk6p/Xp6euLChQtP3F+rVq3Qrl07bNiwAQ0aNEBcXByWLl1a4fZQ3cEeIKIyFP1Pu+T/ivPy8vDf//7XUE3SIZPJ0LNnT4SFheHOnTti+bVr10qNGylve0D3+ARBwOLFi5+6TYGBgSgoKMCKFSvEMrVarfeXy8CBA2FiYoL//ve/2LVrF1555RUolcrHtv348eM4evSo3m3u2bMnjI2NsXTpUp39LVq0qFRdmUxWqpdk69atiI+P1ykrmrumIpf/BwYGQq1WY9myZTrl3333HSQSSYXHcz3J+vXr4eHhgQkTJuDVV1/VuU2bNg1mZmbiabDBgwdDEATMnz+/1H6Kjn/gwIGQSqVYsGBBqV6Ykp+Rp6enznguAPjxxx/L7QEqS1mf+9KlS0vtY/DgwTh79ix27NhRbruLjBo1Cn/99RcWLVoEW1vbSvucqXZhDxBRGTp16gRra2sEBQWJyzSsW7euWk8TPMm8efPw119/oXPnzpg4caL4RdqqVasnLsPg5eUFT09PTJs2DfHx8bCwsMC2bdsqNJakPP3790fnzp0xY8YMxMTEoEWLFti+fbve42PMzMwwcOBAcRzQo5cm9+vXD9u3b8egQYPQt29f3Lx5E99//z1atGiBjIwMvd6raD6j0NBQ9OvXD4GBgThz5gx27dpVqqekX79+WLBgAYKDg9GpUyecP38eGzZs0Ok5ArRf+lZWVvj+++9hbm4OU1NT+Pv7lzm+pX///njhhRcwa9YsxMTEwNvbG3/99Rd+++03TJ06VWfA89O6c+cO9u/fX2qgdRGFQoGAgABs3boVS5YswQsvvIBRo0ZhyZIliI6ORu/evaHRaHDo0CG88MILmDx5Mpo0aYJZs2bhk08+QZcuXfDKK69AoVDg5MmTcHFxEefTeeONNzBhwgQMHjwYvXr1wtmzZ7Fnz55Sn+3j9OvXD+vWrYOlpSVatGiBo0ePYu/evaUu+//ggw/w66+/YsiQIRg7dix8fHxw//597Ny5E99//z28vb3Fuq+99hqmT5+OHTt2YOLEiQafoJIMpJqvOiMymPIug2/ZsmWZ9Y8cOSL85z//EVQqleDi4iJMnz5dvIx2//79Yr3yLoP/+uuvS+0Tj1wWXN5l8JMmTSq17aOXDguCIERERAjt2rUT5HK54OnpKfz000/C+++/LyiVynI+hWIXL14UevbsKZiZmQl2dnbC+PHjxcuqS17CHRQUJJiampbavqy237t3Txg1apRgYWEhWFpaCqNGjRLOnDlT4cvgi/z5558CAMHZ2bnMy6w///xzoVGjRoJCoRDatWsn/PHHH6V+DoLw5MvgBUEQ1Gq1MH/+fMHZ2VlQqVRC9+7dhQsXLpT6vHNycoT3339frNe5c2fh6NGjQrdu3UpdQv3bb78JLVq0EKckKDr2stqYnp4uvPfee4KLi4tgbGwsNG3aVPj66691LicvOpaK/l6U9O233woAhIiIiHLrrF27VgAg/Pbbb4IgaKca+PrrrwUvLy9BLpcL9vb2Qp8+fYTIyEid7VavXi20a9dOUCgUgrW1tdCtWzchPDxcfF2tVgsffvihYGdnJ5iYmAgBAQHCtWvXyr0M/uTJk6Xa9uDBAyE4OFiws7MTzMzMhICAAOHy5ctlHve9e/eEyZMnC66uroJcLhcaNGggBAUFCSkpKaX2GxgYKAAQ/vnnn3I/F6rbJIJQg/5LS0TPbODAgfj3338RHR1t6KYQ1ViDBg3C+fPnKzRmjuomjgEiqsUeXbYiOjoa//vf/9C9e3fDNIioFrh79y7+/PNPjBo1ytBNIQNiDxBRLebs7IwxY8bAw8MDsbGxWLFiBXJzc3HmzJlSc9sQ1Xc3b97EkSNH8NNPP+HkyZO4fv06nJycDN0sMhAOgiaqxXr37o1NmzYhISEBCoUCHTt2xOeff87wQ1SGgwcPIjg4GA0bNsTPP//M8FPPsQeIiIiI6h2OASIiIqJ6hwGIiIiI6h2OASqDRqPBnTt3YG5u/kwrGxMREVH1EQQB6enpcHFxgVT6+D4eBqAy3LlzB25uboZuBhERET2FW7duoUGDBo+twwBUhqJFCW/dugULCwsDt4aIiIgqIi0tDW5ubjqLC5eHAagMRae9LCwsGICIiIhqmYoMX+EgaCIiIqp3GICIiIio3mEAIiIionqHAYiIiIjqHQYgIiIiqncYgIiIiKjeYQAiIiKieocBiIiIiOodBiAiIiKqdxiAiIiIqN5hACIiIqJ6hwGIiIiI6h0uhkpERJVHEACNGhDU2ntNQYnHJcplcsBYBRibADJ+FVH1428dEVF9IAhA4r/AjQPA7RNAfnaJgKLR3osBpQDQaEqEl6LXStQTX3uknqDRv20lw5CxCjA2LbwvLJOblHjdpEQ9FSA3LX/bkq9JZZX+kVLtxgBERFRXpd7WBp6iW2aygRsEQGoESGSAOg+AoC1T52lvOalV974yuW54khkDkFTd+z2JsQqwawrYPQfYNwPsmgE2jQvbRdWBAYiIqkdOGnDnDHDnNFCQB1i4ABbOgLmL9rHSEpAY8AupLshJBWIOA9f3awPPvWjd141NgEadgcZdABNbbRCRGgFSaYnHhfcSaYnHT6pX+FzntaLnJfdRYtipIAAFuUB+VuEtW3ufV/J5NpCfWfxafvYjrz/6uIzXS4Wsh9X0w6iAO6d1n0uNARsPwP45bSCyb6YNSHZNtb1ZtVlOqjaQP7wFpN4CHsYBTm2ANkMM1iQGICKqfOoCIOlfID4SuB0JxJ8Ckq9A/DIqi7EJYO5cGIxcCh+76oYkMweeyiipIA+4fbK4hyc+UnsqqohECri0BzxfADy6Aw38ACOFgRr7CIkEMFZqb7CpmvcQBKAg55GAlKl9rCmomvesqOyHQMpV7S35CpASrQ17KVe0N/yuW9+yYYlgVCIgmVTRZ6cPjQbITCoON6m3SjwuDD25ZfTutXyFAYiIajFB0P6hu31K+wUcHwnciQIKskvXtWwINPAB5GZA+l0g7S6QFq/9X3l+FnD/uvZWHokMMHMs3XskBqbCx8aqqjpawxIEIOkScKOwhyfmiPZLsyTbJtqw49EdcO8CqKyqv501hURSPB6oqkJWZdFotP8WUq4AyVd177PuAalx2tu1vbrbmdgV9xSVvLdwrbwe1YI8IO126VCTGqe9T4svPKX5BCobwMoNsCy8uflVTvuekkQQhMf8l6x+SktLg6WlJVJTU2FhYWHo5hDVLNkPtV33Yu9OpPZ/f49SWAKu7QFXH6CBr/bezKHsfeZlFQaiO8X3aXeA9DuFIekOkJGo27vxOEqrEr1Hj/YkFd6rrHVPydRUqfHAzYPFp7Ue/axN7IoDj0d37RcM1S2Z9woD0ZUSPUZXtWGkPMam2lNnOuGonHFGj56eKtmD8/CW9t/e43pvAW1vo7lLiYDToPBxQ+29hSugMHvmj+JJ9Pn+ZgAqAwMQUaGCPO2prJK9OylXS9eTGgGOrQqDTmHYsW1SuQFDowYykh4JRvGPBKa7heM+KkBqBJg6aEOZmWOJe8fSZdXwh1uUk6Ydx3PjgLan59HP20gFNOpUfFrLoWXtCHJU+XIztOO8xB6jwmB0/0b5p/iKxhlZNtAGm/JOTz3KSFUi1BTerErcmzvXiAHcDEDPiAGI6iVBAB7EFAed26eAu2cBdW7putbuxUGnga92MKOxsrpbXJogaP83m14YjtLuPvK4MChl3dNvv8YmFQtKpg6AkVy/favzdcfx3D5VxjiedoU9PC8Abh1qzjgeqpnU+doQlHxF91RaSnT5/0FQWReGmYaP9OAUlpnY1oqLFBiAnhEDED0TQQBy07SninIe6t5nPwBy07W9DzJj7ReZTKH90ix5L5OXLjMqLJfJix8bKQqvsHmKP0xZ97WnsooGKcdHlh0MlFYlTmP5ak9rmdo9yydkeAV52kvCMxK1vUo694WPM5O093kZ+u1bZV0YhuzLD0oQgJuHtIEn9kjp97Dx0IYdj+7aK7ZU1pV04FSvaTTasTzJV7X/MTB3Kg471dnLWYX0+f7mIGiisjwuxJQMM2W9lpP6dJPBPTVJcZASQ9UjIankaxIZkHy57MHGMjng1FobeFx9taHHxqNW/M9PL0ZywNJVe3uS3IziMFRWUMoo8ZomX/t7kf1A+xlXlIkt0Lib9rRW426AdaOnPzai8kil2t4cq4aGbkmNwABE9YdGAySc096yHzw+zFRGiDFSantPVFa69wpz7b7VudqeiJL36nzt3ChlvpZX/FinbYWX+hbk6N9GG0/d3h2nVjy98iiFmfZm4/H4eoKg/T16Uo9SRqL2cmy3DsWntRxbcRwPUTVjAKK67UFMiZlwDwLZ9/XbvrwQU+reunRZVY6JURcUhqPC0KQTmHKLJ317tKzo3rqx9lRWTZhDpK6QSLSfp4kN4OBl6NYQVTuNRkBOgRrZeWpk5z/mvvCxh70pXvRyNFh7GYCobsm6D9z8uzj0PLip+7rcXDv3hKmD4UPMs5AZaW+1fXZYIqoWgiAgT61BVq4aWflqZOcVIDtPg6y8AmTnq5FTGEyy8rThpOTznBLhJavEa9l5uqEmJ1+/XvMBbV0YgIieWn4OcOt48cRwd6KgM1+F1Eg7+23RHCmuPjXiUk0iorJoNAKy8tXaYJKnRmauGtn5BcjMLQwnhY+z89TILKyTVeJxZp423GQVlmflFYihR62pvmueFEZSqOQymBjLoJTLoDIuvMmL730aGXZwv8ED0PLly/H1118jISEB3t7eWLp0KTp06FBm3fz8fISGhuLnn39GfHw8mjVrhi+//BK9e/cW66Snp+Pjjz/Gjh07kJSUhHbt2mHx4sXw8zPsjJNUSTQaIPG8Nuxc3w/EHS099sXeq/gKGvfO2jE3RERVQBAEZOWpkZFboL3lFJT9uPB5Zm4B0nO192JAySsONPr2ojwNuawwnMhLhxKlcXF5ycelXiu8L1m3aJ9KIxmk0pp/4YRBA9CWLVsQEhKC77//Hv7+/li0aBECAgJw5coVODiUnjF29uzZWL9+PVauXAkvLy/s2bMHgwYNwj///IN27doBAN544w1cuHAB69atg4uLC9avX4+ePXvi4sWLcHWtwBUfVPM8iC0+pXXzYOlLtc2ctGGn6AoaC2cDNJKIagtBEJBboCkzsGTmFSC9sCwzV/dxRuHzzEfqV0XHikQCmBjLoJIbwVRRHDZMFUbiYxOFEUyMC+8Lw4eJ/DGPFdoeGSMZB9wDBp4HyN/fH35+fli2bBkAQKPRwM3NDVOmTMGMGTNK1XdxccGsWbMwadIksWzw4MFQqVRYv349srOzYW5ujt9++w19+/YV6/j4+KBPnz749NNPK9QuzgNkYNkPdMfx3L+h+7rcDHB/vvgKGvtmde8ybaI6KjU7H/EPspGVV4C8Ag3y1BrkqwXkqzUlnmsf5xe+JpYXluUVluWXqFu0XX6J13T3JSC/QIPcwrLK/uaTSgAzhZH2ptTemyqMYF7yceFrpoX1igKKSi6D6SNhRWkshYR/1/RWK+YBysvLQ2RkJGbOnCmWSaVS9OzZE0ePHi1zm9zcXCiVuoNSVSoVDh8+DAAoKCiAWq1+bB2qgQpyteN4itY6uhule5m3RKY7jqeBL8fxENVAgiAgLbsAtx5k4faDbNx+kIX4h9mFj7XP03MMvAr7I0zlMjGUiAFFrr03LwwuOo9LBJySj1XGMgaWWsZgASglJQVqtRqOjrojwB0dHXH5ctkTiAUEBGDhwoXo2rUrPD09ERERge3bt0Ot1k4bb25ujo4dO+KTTz5B8+bN4ejoiE2bNuHo0aNo0qRJuW3Jzc1Fbm7xdP9paWmVcIRULo0GSLxQvNZR7NHSK4fbNSte66hRZ0DJnjgiQxMEAanZ+WKYKQ42hWHnQTbSc58ccGxM5bBQGkFuJIWxTHuTG0khl0lhLJM88lwKYyMJ5DJZ4X1heeG2cpmknP1o91X0mlhupC1XGstgJjeqFWNVqGoYfBC0PhYvXozx48fDy8sLEokEnp6eCA4OxurVq8U669atw9ixY+Hq6gqZTIb27dtjxIgRiIyMLHe/oaGhmD9/fnUcQv2k0WgX1Iw9qp32P+YwkJWiW8fMsfiUlkc3wMLFIE0lqs8EQcDDLN2Ao+3BKQ47GRUIOHZmcrham6CBtarwVvjYSgVXaxVM5LXqq4fqKIP9FtrZ2UEmkyExMVGnPDExEU5OTmVuY29vj7CwMOTk5ODevXtwcXHBjBkz4OFRPEOrp6cnDh48iMzMTKSlpcHZ2RnDhg3TqfOomTNnIiQkRHyelpYGNze3ZzzCeqwgT3saK/Yf7e3WMe3MyiUZmxaP4/F8QXvlFruPiapcTr4a15IyEHdf22Oj25OThcw89RP3YWemKB1uCm+uViZQyWXVcCREz8ZgAUgul8PHxwcREREYOHAgAO0g6IiICEyePPmx2yqVSri6uiI/Px/btm3D0KFDS9UxNTWFqakpHjx4gD179uCrr74qd38KhQIKBaf/f2p5mdrVrIt6eG6fKn1KS26mnfq/USftKS1XX/1XzSYiveQVaHAlIR3n4h/iQnwqzt1OxZWEdBQ84bIle3NFqXDjaqV97mqlYsChOsGg/ZAhISEICgqCr68vOnTogEWLFiEzMxPBwcEAgNGjR8PV1RWhoaEAgOPHjyM+Ph5t27ZFfHw85s2bB41Gg+nTp4v73LNnDwRBQLNmzXDt2jV88MEH8PLyEvdJlSD7ARB3rLiH524UoHmkW1xlUxh2OgENOwJObbQzFxNRlchXa3A1MR3nb6fifLz2dvluOvLUpeeVsTYxRmM70xIBxwSuJYKO0pgBh+o+g34jDRs2DMnJyZgzZw4SEhLQtm1b7N69WxwYHRcXB2mJBQJzcnIwe/Zs3LhxA2ZmZggMDMS6detgZWUl1klNTcXMmTNx+/Zt2NjYYPDgwfjss89gbMyrhp5a2l0g7p/CHp5/gKSL0JltGQAsXEsEnk6A3XNc3JGoihSoNbiWnIFzt1PFnp2Ld9OQV1A67FiqjNGmgSVau1pq7xtYwcVSySuWqN4z6DxANVW9ngdIELTrZ8X+U3xK69H1tADAtknx6ayGHQGrhhzDQ1QF1BoBN5IzcL4w6JyPT8W/d1LLnDHYXGmE1q6WaN3AEm1crdDa1RJuNiqGHao3asU8QFRDaDRA8qXi01mx/wAZCY9UkgBOrYrDTqNOgFnpmbqJaoP0nHzcTc2Bylg7q66JXAaFUc2YdE6jEXDzXqbYq3P+diou3ElFVhkDk03lMrQq0avT2tUSjWxMeFk3UQUxANU36nzg7lltz07sUe1aWjkPdetIjQHX9sWns9w6aFdHJ6qlEtNyEH4xEX9dTMTR6ynIV+t2fMukEu0yA4XLBejMyqswgmnh7LymisJ7sVy3vqmi+DWVsQyyx4QRQRAQey9LHK9z7vZDXIhPK/Myc5WxDK1cLdDa1QqtG2jvPexMGXaIngEDUH2hzgci1wIHvwQyk3VfMzYF3PyKe3ga+ALGKoM0k6iyXE/OwF//JuKviwk4E/dQ5zULpRHy1BrxNJJaIyA9p6DSZylWGkvLDEn5ag0u3klDWhnvpzCSoqWLReGpLCu0aWAJT3uzx4YpItIfA1BdJwjApZ3A3vnA/evaMpV18amshp0A5zZcWoJqPY1GwLn4VPz1bwL+upiIa0kZOq+3dbNCQEsn9GrhiCYOZgC0wadoNe6i1bnF+7wCZOUW3pcoz8orQGaeGlm5hfcl6xXeF11lnpOvQU5+Hu5llt1muUyK5s7mxWN2GliiqYMZF6skqgYMQHVZ3DHgr4+B2ye0z03tge4zgPZBDDxUJ+QVaHD85j389W8iwi8mIiEtR3zNWCZBR087vNTCEb1aOMLRQllqe5lUAnOlMcyVlffvoWil8ZJBKjO3MDgV3msEwMvJHM85mkNuxLBDZAgMQHVRSjSwdx5w+Q/tc2MToNMU7U1hbtCmET2rzNwCHLyajL/+TUDE5SSd01amchm6ezngpRaO6N7MAZaq6g/6Eol2nSmlsQy21f7uRFRRDEB1SUYScOAL7VgfQQ1IpED70UD3mYB52cuLENUGKRm5iLiUiL/+TcShayk6893YmcnRq4UjXmrhhE5NbKEw4iR+RPRkDEB1QW4GcHQ5cGQxkF842OC5PkDPeYCDl0GbRvS04u5l4a+LCdjzbwJOxT5AyRnLGtmaIKClE15q4Yh2Da05QJiI9MYAVJupC4Az64ADoUBG4aKyLu2Blz7RLjRKVIsIgoB/76Thr4uJ+OvfBFxOSNd5vbWrJV5q4YiXWjrhOUezGjFvDxHVXgxAtZEgAFd2AXvnAilXtWXW7kCPuUDLQZyRmWqNArUGJ2MeYM+/CQi/mIj4h8WL6MqkEvg3ttEOYm7pBFcrTs1ARJWHAai2uX1Ke2VX3D/a5yoboNuHgO9Yrq5ONV6BWoP0nAKcjLmPPf8mIuJyIh5m5YuvK42l6PacPV5q4YQezR1gZcLfaSKqGgxAtcW960DEAuBimPa5kRL4z9vA81MBpaUhW0Z1mCAIyM5XIyNXewl3Zm5B4eMCnbL0wrKSr2fmFm6XV1xe1vpV1ibG6NHcES+1cESXpvZQyTmImYiqHgNQTZd5D/j7K+DkKkCTD0ACtB0JvPARYOlq6NZRLXPrfhb+uZ6C5PRcZBSGFzG05BXoluUU6EzqV5lcrVR4qaUjAlo6wbeRNSf+I6JqxwBUU+VlAcdXAIcXAblp2rImvbRXdjm1MmTLqBbJyVfjxM37OHAlGQeuJuFGcjlTEj+BRAKYFq6FZaowglnhOljaxzKYKQsfi2Xae1OFTHxcsoyXqhORoTEA1TQaNXB2E7DvMyD9jrbM2RvotQDw6G7QplHtEHsvEwevJuPAlWQcvX4P2fnFK4nLpBL4NLRGYztTMbyYlhFQzAqfF5WpjGVceJOI6hQGoJpCEIBre4HwOUDSRW2ZZUOgxxyg1WBAylMEVLacfDWO3biHA1eScfBqMm6m6PbyOFoo0P05B3RvZo/OTe1gUYnLPhAR1VYMQDXBnTPa4HPzb+1zpRXQ9QPA7w3AuPT6RUQxKZk4cCUJB64m49iNezqDi42kEvg0skb3ZtrQ4+VkzjlziIgewQBkSA9igX2fAOe3ap/LFID/W0CXEO2K7USFsvOKenm0oSf2XpbO686WSnRvZo9uz9mjcxO7Sl3ck4ioLmIAMoSs+8Chb4ETPwLqPG1Zm2HAi7MBq4aGbRvVCIIg4GZKZuHg5WQcv3EPuSXWvzKWSeDbyAbdm9mjezMHzoxMRKQnBqDqlJ+jDT2HvgFyUrVljbtpBzi7tDVo08jwsvIKcPT6PfGKrVv3s3Ved7FUolvhaa3OTexgpuA/XyKip8W/oNXp0LfaOX0AwKEl8NICwLMHl66opwRBwPVk7Vieg1eTcfzmfZ1Vzo1lEnRobCMOYG7iwF4eIqLKwgBUnf4zEbj8B9BpivaUl5RzodQ3uQVqHLqaggNXk3DgSjJuP9Dt5XG1UomntTp52sKUvTxERFWCf12rk4kNMPEf9vjUM0WrnG89dQu/nb2js/aVXCaFv4cNuj2nDT2e9qbs5SEiqgYMQNWNX271xr2MXOw4E49fI2/jckK6WO5koUSvFo7o3sweHT1tYSLnP0MiourGv7xElShfrcGBK8nYeuoW9l1OQkHhQlpyIyleauGIIb5ueL6JHWScVZmIyKAYgIgqwZWEdGw9dQthUfFIycgTy70bWOJVXze83MYFliacm4eIqKZgACJ6Sg+z8vD72TvYGnkb526niuV2ZnIMaueKV33c0MzJ3IAtJCKi8jAAEelBrRFwKDoZWyNvI/zfROSptZetG0kl6NHcAUN83NCtmT2MZVy7jYioJmMAIqqAG8kZ+DXyNrafjkdCWo5Y7uVkjiG+bhjY1gW2ZgoDtpCIiPTBAERUjvScfPx57i62Rt5GZOwDsdzKxBgD27riVZ8GaOliwcvWiYhqIQYgohI0GgHHbtzDr5G38b8Ld8VV1qUSoNtz9hji64YezR2gMOIklkREtRkDEBGAW/ez8GvkbWw7fVtndmZPe1MM8XXDK+1c4WChNGALiYioMhl8pOby5cvh7u4OpVIJf39/nDhxoty6+fn5WLBgATw9PaFUKuHt7Y3du3fr1FGr1fj444/RuHFjqFQqeHp64pNPPoEgCFV9KFTLZOUVYFvkbYz48Ri6fLUfiyOicftBNswVRhjRoSG2v90Je0O6YUI3T4YfIqI6xqA9QFu2bEFISAi+//57+Pv7Y9GiRQgICMCVK1fg4OBQqv7s2bOxfv16rFy5El5eXtizZw8GDRqEf/75B+3atQMAfPnll1ixYgV+/vlntGzZEqdOnUJwcDAsLS3xzjvvVPchUg0jCAIiYx9g66nb+PP8XWTkFgDQTtDd2dMOQ3wbIKClE5TGPMVFRFSXSQQDdo34+/vDz88Py5YtAwBoNBq4ublhypQpmDFjRqn6Li4umDVrFiZNmiSWDR48GCqVCuvXrwcA9OvXD46Ojli1alW5dZ4kLS0NlpaWSE1NhYWFxbMcItUQGo2A8EuJWBIRjX/vpInlDW1M8KpPAwz2aQBXK5UBW0hERM9Kn+9vg/UA5eXlITIyEjNnzhTLpFIpevbsiaNHj5a5TW5uLpRK3VMRKpUKhw8fFp936tQJP/74I65evYrnnnsOZ8+exeHDh7Fw4cKqORCq0TQaAXv+TcDiiGhxPS6VsQx92zhjiE8DdGhsw6u4iIjqIYMFoJSUFKjVajg6OuqUOzo64vLly2VuExAQgIULF6Jr167w9PREREQEtm/fDrVaLdaZMWMG0tLS4OXlBZlMBrVajc8++wwjR44sty25ubnIzc0Vn6elpZVbl2oHtUbArgt3sTTiGq4kaoOPmcIIQZ0aYdzzHrAxlRu4hUREZEi16iqwxYsXY/z48fDy8oJEIoGnpyeCg4OxevVqsc4vv/yCDRs2YOPGjWjZsiWioqIwdepUuLi4ICgoqMz9hoaGYv78+dV1GFSF1BoBf5y7g6X7ruFaUgYAwFxhhODO7hj7fGNYmTD4EBGRAQOQnZ0dZDIZEhMTdcoTExPh5ORU5jb29vYICwtDTk4O7t27BxcXF8yYMQMeHh5inQ8++AAzZszA8OHDAQCtW7dGbGwsQkNDyw1AM2fOREhIiPg8LS0Nbm5uz3qIVI0K1BrsPHsHy/Zdw42UTACAhdIIY59vjODOjWGp4kKkRERUzGABSC6Xw8fHBxERERg4cCAA7SDoiIgITJ48+bHbKpVKuLq6Ij8/H9u2bcPQoUPF17KysiCV6l7dL5PJoNFoyt2fQqGAQsFlDGqjArUGO87EY/n+a4i5lwVAO1PzG883xuhO7rBQMvgQEVFpBj0FFhISgqCgIPj6+qJDhw5YtGgRMjMzERwcDAAYPXo0XF1dERoaCgA4fvw44uPj0bZtW8THx2PevHnQaDSYPn26uM/+/fvjs88+Q8OGDdGyZUucOXMGCxcuxNixYw1yjFQ18tUabD99G8v3X0fcfW3wsTYxxviuHhjd0R1milp1dpeIiKqZQb8lhg0bhuTkZMyZMwcJCQlo27Ytdu/eLQ6MjouL0+nNycnJwezZs3Hjxg2YmZkhMDAQ69atg5WVlVhn6dKl+Pjjj/H2228jKSkJLi4ueOuttzBnzpzqPjyqAnkFGvwaeRvL919D/EPtjM22pnK82dUDr/+nEUwZfIiIqAIMOg9QTcV5gGqe3AI1fjl1Gyv2X8OdVO1q7HZmCkzo5oHX/BvCRM7gQ0RU39WKeYCIKiInX40tJ29hxYHrSEjTBh8HcwUmdPPEa/4NOWMzERE9FQYgqpFy8tXYeDwO3x+8jqR07RxNThZKTOzuiWF+bgw+RET0TBiAqEbJyivAhmNx+OHvG0jJ0AYfF0slJr7QBEN9G0BhxOBDRETPjgGIaoTM3AKsOxaLlX/fwL3MPACAq5UKk15ogld9GkBuJH3CHoiIiCqOAYgMKiO3AD//E4OfDt3Ag6x8ANoFSie/0ASD2rvCWMbgQ0RElY8BiAwiLScfPx+JwaojN/GwMPi425pg8otNMaCtC4MPERFVKQYgqlap2flYc+QmVh++ibScAgCAh70pprzYBP3buMCIwYeIiKoBAxBVm7h7WRix8pg4gWETBzNMebEJ+rVxgUwqMXDriIioPmEAomoRk5KJESuP4W5qDtxsVPiwtxcCWzlDyuBDREQGwABEVe5GcgZGrDyGxLRceNqbYtP4/8DBQmnoZhERUT3GAERV6lpSBl5beQxJ6blo6mCGjeP/A3tzhaGbRURE9RwDEFWZ6MR0jFh5HCkZufByMsf6N/xhZ8bwQ0REhscARFXiSkI6Xlt5DPcy89Dc2QIb3vCHjanc0M0iIiICwABEVeDinTS8vuo47mfmoZWrBdaP84eVCcMPERHVHAxAVKkuxKfi9VXH8TArH20aWGLdWH9YmhgbullEREQ6GICo0py/rQ0/qdn5aOtmhZ/HdoCliuGHiIhqHgYgqhRRtx5i1KrjSM8pQPuGVlg7tgMslAw/RERUMzEA0TM7HfcAQatOID23AH7u1lgT3AFmCv5qERFRzcVvKXomkbH3EbT6JDJyC9ChsQ3WjPGDKcMPERHVcPymoqd24uZ9BK85gcw8NTp62GLVGF+YyPkrRURENR+/reipHL1+D2PXnkR2vhrPN7HDytG+UMllhm4WERFRhTAAkd6OXEvBuJ9PIidfgy5NteFHaczwQ0REtQcDEOnl76vJGP9/p5BboEH3Zvb4/nUfhh8iIqp1GICowg5cScKb6yKRV6BBDy8H/Pf19lAYMfwQEVHtwwBEFbL/chLeWheJPLUGvVo4Yvlr7SE3khq6WURERE+FAYieaO/FREzcEIl8tYA+rZywZEQ7GMsYfoiIqPbitxg91u4LCWL46dvameGHiIjqBPYAUbl2nb+LKZvOoEAjoL+3C74b6g0jhh8iIqoD+G1GZfrj3B1MLgw/g9q5MvwQEVGdwh4gKuW3qHi8tyUKGgEY3L4Bvnq1DWRSiaGbRUREVGn4X3rSsf30bTH8DPN1w9cMP0REVAexB4hEW0/dwvRt5yAIwIgODfHZwFaQMvwQEVEdVCN6gJYvXw53d3colUr4+/vjxIkT5dbNz8/HggUL4OnpCaVSCW9vb+zevVunjru7OyQSSanbpEmTqvpQaq0tJ+PE8PP6fxh+iIiobjN4ANqyZQtCQkIwd+5cnD59Gt7e3ggICEBSUlKZ9WfPno0ffvgBS5cuxcWLFzFhwgQMGjQIZ86cEeucPHkSd+/eFW/h4eEAgCFDhlTLMdU2G4/H4cNt5yEIwJhO7vhkAMMPERHVbRJBEARDNsDf3x9+fn5YtmwZAECj0cDNzQ1TpkzBjBkzStV3cXHBrFmzdHpzBg8eDJVKhfXr15f5HlOnTsUff/yB6OhoSCRP/mJPS0uDpaUlUlNTYWFh8ZRHVjusOxqDj3/7FwAwtnNjfNyveYU+IyIioppGn+9vg/YA5eXlITIyEj179hTLpFIpevbsiaNHj5a5TW5uLpRKpU6ZSqXC4cOHy32P9evXY+zYsfxif8SaIzfF8PNmVw+GHyIiqjcMGoBSUlKgVqvh6OioU+7o6IiEhIQytwkICMDChQsRHR0NjUaD8PBwbN++HXfv3i2zflhYGB4+fIgxY8aU247c3FykpaXp3Oq6nw7dwPzfLwIAJnb3xMw+Xgw/RERUbxh8DJC+Fi9ejKZNm8LLywtyuRyTJ09GcHAwpNKyD2XVqlXo06cPXFxcyt1naGgoLC0txZubm1tVNb9G+PHv6/j0z0sAgCkvNsH0gGYMP0REVK8YNADZ2dlBJpMhMTFRpzwxMRFOTk5lbmNvb4+wsDBkZmYiNjYWly9fhpmZGTw8PErVjY2Nxd69e/HGG288th0zZ85EamqqeLt169bTH1QN9/3B6/j8f5cBAFN7NsX7LzH8EBFR/WPQACSXy+Hj44OIiAixTKPRICIiAh07dnzstkqlEq6urigoKMC2bdswYMCAUnXWrFkDBwcH9O3b97H7UigUsLCw0LnVRQmpOfhytzb8hPR6DlN7PmfgFhERERmGwSdCDAkJQVBQEHx9fdGhQwcsWrQImZmZCA4OBgCMHj0arq6uCA0NBQAcP34c8fHxaNu2LeLj4zFv3jxoNBpMnz5dZ78ajQZr1qxBUFAQjIwMfpg1wtXEdAgC0MTBDO/0aGro5hARERmMwZPBsGHDkJycjDlz5iAhIQFt27bF7t27xYHRcXFxOuN7cnJyMHv2bNy4cQNmZmYIDAzEunXrYGVlpbPfvXv3Ii4uDmPHjq3Ow6nRYu9lAgAa25kauCVERESGZfB5gGqiujoP0Cd/XMSqwzcxvktjzOrbwtDNISIiqlS1Zh4gql5FPUCNbNkDRERE9RsDUD0Scy8LAODOAERERPUcA1A9odYIiCsMQI1sTQzcGiIiIsNiAKonEtJykKfWwFgmgYuVytDNISIiMigGoHoiNkU7/sfNxgQyrvRORET1HANQPcHxP0RERMUYgOqJ4ivAOP6HiIiIAaieiCkMQOwBIiIiYgCqN2J5BRgREZGIAageEASBPUBEREQlMADVA0npucjJ10AmlcDVmpfAExERMQDVAzGFl8A3sFbBWMYfOREREb8N64HY+9rxPw1tOP6HiIgIYACqF2I5/oeIiEgHA1A9EMMrwIiIiHQwANUD7AEiIiLSxQBUxwmCgNiUwmUw7NgDREREBDAA1Xn3M/OQnlsAiQRoYM0AREREBDAA1XlF439cLFVQGssM3BoiIqKagQGojuMiqERERKUxANVxxVeAcQA0ERFREQagOq74CjD2ABERERVhAKrj2ANERERUGgNQHSf2APESeCIiIhEDUB32MCsPD7PyAXAdMCIiopIYgOqw2MLTX44WCpjIjQzcGiIiopqDAagOixEvgef4HyIiopIYgOqwoh4gXgFGRESkiwGoDmMPEBERUdn0DkDu7u5YsGAB4uLiqqI9VImKe4AYgIiIiErSOwBNnToV27dvh4eHB3r16oXNmzcjNze3KtpGz4jLYBAREZXtqQJQVFQUTpw4gebNm2PKlClwdnbG5MmTcfr06apoIz2F9Jx8pGTkAWAAIiIietRTjwFq3749lixZgjt37mDu3Ln46aef4Ofnh7Zt22L16tUQBKFC+1m+fDnc3d2hVCrh7++PEydOlFs3Pz8fCxYsgKenJ5RKJby9vbF79+5S9eLj4/H666/D1tYWKpUKrVu3xqlTp572UGulotNfdmZymCuNDdwaIiKimuWpA1B+fj5++eUXvPzyy3j//ffh6+uLn376CYMHD8ZHH32EkSNHPnEfW7ZsQUhICObOnYvTp0/D29sbAQEBSEpKKrP+7Nmz8cMPP2Dp0qW4ePEiJkyYgEGDBuHMmTNinQcPHqBz584wNjbGrl27cPHiRXz77bewtrZ+2kOtleLuawMQJ0AkIiIqTSJUtKum0OnTp7FmzRps2rQJUqkUo0ePxhtvvAEvLy+xzoULF+Dn54fs7OzH7svf3x9+fn5YtmwZAECj0cDNzQ1TpkzBjBkzStV3cXHBrFmzMGnSJLFs8ODBUKlUWL9+PQBgxowZOHLkCA4dOqTPYelIS0uDpaUlUlNTYWFh8dT7MaT/HriGr3ZfwSvtXLFwWFtDN4eIiKjK6fP9rXcPkJ+fH6Kjo7FixQrEx8fjm2++0Qk/ANC4cWMMHz78sfvJy8tDZGQkevbsWdwYqRQ9e/bE0aNHy9wmNzcXSqVSp0ylUuHw4cPi8507d8LX1xdDhgyBg4MD2rVrh5UrV+p7mLVebAoXQSUiIiqP3usj3LhxA40aNXpsHVNTU6xZs+axdVJSUqBWq+Ho6KhT7ujoiMuXL5e5TUBAABYuXIiuXbvC09MTERER2L59O9RqtU77VqxYgZCQEHz00Uc4efIk3nnnHcjlcgQFBZW539zcXJ0r2dLS0h7b9toghougEhERlUvvHqCkpCQcP368VPnx48erfKDx4sWL0bRpU3h5eUEul2Py5MkIDg6GVFp8GBqNBu3bt8fnn3+Odu3a4c0338T48ePx/fffl7vf0NBQWFpaijc3N7cqPY7qUDQImj1AREREpekdgCZNmoRbt26VKo+Pj9cZm/MkdnZ2kMlkSExM1ClPTEyEk5NTmdvY29sjLCwMmZmZiI2NxeXLl2FmZgYPDw+xjrOzM1q0aKGzXfPmzR87cePMmTORmpoq3so6vtokO0+NhLQcAFwGg4iIqCx6B6CLFy+iffv2pcrbtWuHixcvVng/crkcPj4+iIiIEMs0Gg0iIiLQsWPHx26rVCrh6uqKgoICbNu2DQMGDBBf69y5M65cuaJT/+rVq489badQKGBhYaFzq82KrgCzVBnDykRu4NYQERHVPHoHIIVCUarXBgDu3r0LIyP9hhSFhIRg5cqV+Pnnn3Hp0iVMnDgRmZmZCA4OBgCMHj0aM2fOFOsfP34c27dvx40bN3Do0CH07t0bGo0G06dPF+u89957OHbsGD7//HNcu3YNGzduxI8//qhX71RtJ47/Ye8PERFRmfQeBP3SSy9h5syZ+O2332BpaQkAePjwIT766CP06tVLr30NGzYMycnJmDNnDhISEtC2bVvs3r1bHBgdFxenM74nJycHs2fPxo0bN2BmZobAwECsW7cOVlZWYh0/Pz/s2LEDM2fOxIIFC9C4cWMsWrSoQvMS1RWxXASViIjosfSeByg+Ph5du3bFvXv30K5dOwBAVFQUHB0dER4eXicGENf2eYA+2nEeG4/H4Z0XmyDkpWaGbg4REVG10Of7W+8eIFdXV5w7dw4bNmzA2bNnoVKpEBwcjBEjRsDYmEsu1ATsASIiIno8vQMQoJ3n580336zstlAliSmcBJFzABEREZXtqQIQoL0aLC4uDnl5eTrlL7/88jM3ip5eboEad1K1S5CwB4iIiKhsTzUT9KBBg3D+/HlIJBJx1XeJRAIAOrMyU/W7dT8bggCYKYxga8pL4ImIiMqi92Xw7777Lho3boykpCSYmJjg33//xd9//w1fX18cOHCgCppI+ige/2MihlIiIiLSpXcP0NGjR7Fv3z7Y2dlBKpVCKpXi+eefR2hoKN555x2cOXOmKtpJFRRTuASGO09/ERERlUvvHiC1Wg1zc3MA2uUs7ty5AwBo1KhRqRmYqfqV7AEiIiKisundA9SqVSucPXsWjRs3hr+/P7766ivI5XL8+OOPOmtykWGwB4iIiOjJ9A5As2fPRmamtpdhwYIF6NevH7p06QJbW1ts2bKl0htI+mEPEBER0ZPpHYACAgLEx02aNMHly5dx//59WFtbc9CtgeWrNbj9QHsJvLsde4CIiIjKo9cYoPz8fBgZGeHChQs65TY2Ngw/NUD8g2yoNQKUxlI4mCsM3RwiIqIaS68AZGxsjIYNG3Kunxoq9r52/E8jG1MGUiIiosfQ+yqwWbNm4aOPPsL9+/eroj30DDj+h4iIqGL0HgO0bNkyXLt2DS4uLmjUqBFMTXXHmpw+fbrSGkf6KV4DjON/iIiIHkfvADRw4MAqaAZVBvYAERERVYzeAWju3LlV0Q6qBDGFAYhzABERET2e3mOAqGZSawTcul+0Cjx7gIiIiB5H7x4gqVT62CuMeIWYYdxNzUaeWgO5TApnS5Whm0NERFSj6R2AduzYofM8Pz8fZ86cwc8//4z58+dXWsNIP7GFS2C42aggk/ISeCIiosfROwANGDCgVNmrr76Kli1bYsuWLRg3blylNIz0w/E/REREFVdpY4D+85//ICIiorJ2R3oq6gFqxABERET0RJUSgLKzs7FkyRK4urpWxu7oKcSkFPYA2XEANBER0ZPofQrs0UVPBUFAeno6TExMsH79+kptHFUce4CIiIgqTu8A9N133+kEIKlUCnt7e/j7+8Pa2rpSG0cVo9EIiL1fNAaIPUBERERPoncAGjNmTBU0g55FUnoucvI1MJJK4GrFS+CJiIieRO8xQGvWrMHWrVtLlW/duhU///xzpTSK9FN0BVgDaxWMZJzbkoiI6En0/rYMDQ2FnZ1dqXIHBwd8/vnnldIo0k/xGmAc/0NERFQRegeguLg4NG7cuFR5o0aNEBcXVymNIv3EFA6A5vgfIiKiitE7ADk4OODcuXOlys+ePQtbW9tKaRTphz1ARERE+tE7AI0YMQLvvPMO9u/fD7VaDbVajX379uHdd9/F8OHDq6KN9AQxKYU9QJwDiIiIqEL0vgrsk08+QUxMDHr06AEjI+3mGo0Go0eP5hggAxAEQewBamjDHiAiIqKK0DsAyeVybNmyBZ9++imioqKgUqnQunVrNGrUqCraR0+QkpGHzDw1JBLtQqhERET0ZE99zXTTpk0xZMgQ9OvX75nDz/Lly+Hu7g6lUgl/f3+cOHGi3Lr5+flYsGABPD09oVQq4e3tjd27d+vUmTdvHiQSic7Ny8vrmdpYUxX1/rhYqqAwkhm4NURERLWD3gFo8ODB+PLLL0uVf/XVVxgyZIjeDdiyZQtCQkIwd+5cnD59Gt7e3ggICEBSUlKZ9WfPno0ffvgBS5cuxcWLFzFhwgQMGjQIZ86c0anXsmVL3L17V7wdPnxY77bVBkVLYHD8DxERUcXpHYD+/vtvBAYGlirv06cP/v77b70bsHDhQowfPx7BwcFo0aIFvv/+e5iYmGD16tVl1l+3bh0++ugjBAYGwsPDAxMnTkRgYCC+/fZbnXpGRkZwcnISb2XNXVQX8AowIiIi/ekdgDIyMiCXy0uVGxsbIy0tTa995eXlITIyEj179ixukFSKnj174ujRo2Vuk5ubC6VSqVOmUqlK9fBER0fDxcUFHh4eGDly5GPnKMrNzUVaWprOrbbgHEBERET60zsAtW7dGlu2bClVvnnzZrRo0UKvfaWkpECtVsPR0VGn3NHREQkJCWVuExAQgIULFyI6OhoajQbh4eHYvn077t69K9bx9/fH2rVrsXv3bqxYsQI3b95Ely5dkJ6eXuY+Q0NDYWlpKd7c3Nz0Og5DYg8QERGR/vS+Cuzjjz/GK6+8guvXr+PFF18EAERERGDjxo349ddfK72Bj1q8eDHGjx8PLy8vSCQSeHp6Ijg4WOeUWZ8+fcTHbdq0gb+/Pxo1aoRffvkF48aNK7XPmTNnIiQkRHyelpZWa0JQcQ8QAxAREVFF6R2A+vfvj7CwMHz++ef49ddfoVKp4O3tjX379sHGxkavfdnZ2UEmkyExMVGnPDExEU5OTmVuY29vj7CwMOTk5ODevXtwcXHBjBkz4OHhUe77WFlZ4bnnnsO1a9fKfF2hUEChUOjV9prgYVYeUrPzAQANbXgKjIiIqKKe6jL4vn374siRI8jMzMSNGzcwdOhQTJs2Dd7e3nrtRy6Xw8fHBxEREWKZRqNBREQEOnbs+NhtlUolXF1dUVBQgG3btmHAgAHl1s3IyMD169fh7OysV/tquqLeHycLJVRyXgJPRERUUU89D9Dff/+NoKAguLi44Ntvv8WLL76IY8eO6b2fkJAQrFy5Ej///DMuXbqEiRMnIjMzE8HBwQCA0aNHY+bMmWL948ePY/v27bhx4wYOHTqE3r17Q6PRYPr06WKdadOm4eDBg4iJicE///yDQYMGQSaTYcSIEU97uDVS8fgf9v4QERHpQ69TYAkJCVi7di1WrVqFtLQ0DB06FLm5uQgLC9N7AHSRYcOGITk5GXPmzEFCQgLatm2L3bt3iwOj4+LiIJUW57ScnBzMnj0bN27cgJmZGQIDA7Fu3TpYWVmJdW7fvo0RI0bg3r17sLe3x/PPP49jx47B3t7+qdpYU4lrgHH8DxERkV4kgiAIFanYv39//P333+jbty9GjhyJ3r17QyaTwdjYGGfPnn3qAFQTpaWlwdLSEqmpqbCwsDB0c8oVsiUK28/EY3rvZni7exNDN4eIiMig9Pn+rnAP0K5du/DOO+9g4sSJaNq06TM3kp5dTOEpMPYAERER6afCY4AOHz6M9PR0+Pj4wN/fH8uWLUNKSkpVto2eoGgZDI4BIiIi0k+FA9B//vMfrFy5Enfv3sVbb72FzZs3w8XFRZyMsLxJBqlqpOXk415mHgBOgkhERKQvva8CMzU1xdixY3H48GGcP38e77//Pr744gs4ODjg5Zdfroo2UhniCnt/7MwUMFPoPZ0TERFRvfbUl8EDQLNmzfDVV1/h9u3b2LRpU2W1iSqgePwPT38RERHp65kCUBGZTIaBAwdi586dlbE7qoDi8T88/UVERKSvSglAVP1iUtgDRERE9LQYgGopsQfIjj1ARERE+mIAqqWKxgA14iKoREREemMAqoWy8gqQlJ4LgJMgEhERPQ0GoFqo6PSXlYkxLE2MDdwaIiKi2ocBqBbiFWBERETPhgGoForlHEBERETPhAGoFophDxAREdEzYQCqhdgDRERE9GwYgGohjgEiIiJ6NgxAtUxOvhp3UrMBsAeIiIjoaTEA1TK3H2RBEABzhRFsTOWGbg4REVGtxABUy8SkFC2BYQKJRGLg1hAREdVODEC1jLgEBsf/EBERPTUGoFqmaAA0x/8QERE9PQagWoY9QERERM+OAaiWKe4BYgAiIiJ6WgxAtUhegQa3H/AUGBER0bNiAKpF4h9mQyMAKmMZ7M0Vhm4OERFRrcUAVIsUj//hJfBERETPggGoFolNKVoDjON/iIiIngUDUC0irgJvx/E/REREz4IBqBYpWgW+kQ17gIiIiJ4FA1AtwkkQiYiIKgcDUC1RoNbg1oOiU2DsASIiInoWDEC1xN3UHOSrBciNpHC2UBq6OURERLVajQhAy5cvh7u7O5RKJfz9/XHixIly6+bn52PBggXw9PSEUqmEt7c3du/eXW79L774AhKJBFOnTq2CllefotNfDW1MIJXyEngiIqJnYfAAtGXLFoSEhGDu3Lk4ffo0vL29ERAQgKSkpDLrz549Gz/88AOWLl2KixcvYsKECRg0aBDOnDlTqu7Jkyfxww8/oE2bNlV9GFWuaA4gjv8hIiJ6dgYPQAsXLsT48eMRHByMFi1a4Pvvv4eJiQlWr15dZv1169bho48+QmBgIDw8PDBx4kQEBgbi22+/1amXkZGBkSNHYuXKlbC2tq6OQ6lSsVwElYiIqNIYNADl5eUhMjISPXv2FMukUil69uyJo0ePlrlNbm4ulErdMTAqlQqHDx/WKZs0aRL69u2rs+/y5ObmIi0tTedW08TwCjAiIqJKY9AAlJKSArVaDUdHR51yR0dHJCQklLlNQEAAFi5ciOjoaGg0GoSHh2P79u24e/euWGfz5s04ffo0QkNDK9SO0NBQWFpaijc3N7enP6gqwh4gIiKiymPwU2D6Wrx4MZo2bQovLy/I5XJMnjwZwcHBkEq1h3Lr1i28++672LBhQ6meovLMnDkTqamp4u3WrVtVeQh602iEEnMAMQARERE9K4MGIDs7O8hkMiQmJuqUJyYmwsnJqcxt7O3tERYWhszMTMTGxuLy5cswMzODh4cHACAyMhJJSUlo3749jIyMYGRkhIMHD2LJkiUwMjKCWq0utU+FQgELCwudW02SmJ6D3AINjKQSuFjxEngiIqJnZdAAJJfL4ePjg4iICLFMo9EgIiICHTt2fOy2SqUSrq6uKCgowLZt2zBgwAAAQI8ePXD+/HlERUWJN19fX4wcORJRUVGQyWRVekxVISZF2/vjZmMCI1mt67QjIiKqcYwM3YCQkBAEBQXB19cXHTp0wKJFi5CZmYng4GAAwOjRo+Hq6iqO5zl+/Dji4+PRtm1bxMfHY968edBoNJg+fToAwNzcHK1atdJ5D1NTU9ja2pYqry2Kx/9wADQREVFlMHgAGjZsGJKTkzFnzhwkJCSgbdu22L17tzgwOi4uThzfAwA5OTmYPXs2bty4ATMzMwQGBmLdunWwsrIy0BFUvRiO/yEiIqpUEkEQBEM3oqZJS0uDpaUlUlNTa8R4oInrI7HrQgLm9m+B4M6NDd0cIiKiGkmf728OKKkF2ANERERUuRiAajhBEDgGiIiIqJIxANVwyRm5yMpTQyoBGlgzABEREVUGBqAarmgCRFdrFeRG/HERERFVBn6j1nAxKUWrwHP8DxERUWVhAKrhinqAOP6HiIio8jAA1XAxRQOgbdgDREREVFkYgGo49gARERFVPgagGkwQBLEHyN2OPUBERESVhQGoBnuQlY/0nAIAQEMb9gARERFVFgagGqyo98fZUgmlce1bxZ6IiKimYgCqweI4/oeIiKhKMADVYOL4H84BREREVKkYgGqw4ivAGICIiIgqEwNQDVbcA8RTYERERJWJAagGYw8QERFR1WAAqqFSs/NxPzMPAAdBExERVTYGoBqq6Aowe3MFTBVGBm4NERFR3cIAVENx/A8REVHVYQCqoWKLFkHl+B8iIqJKxwBUQ8UUngJjDxAREVHlYwCqodgDREREVHUYgGqo4h4gBiAiIqLKxgBUA2XmFiA5PRcA0JCnwIiIiCodA1ANVDQBoo2pHJYqYwO3hoiIqO5hAKqBisf/sPeHiIioKjAA1UBF438a2TAAERERVQUGoBqIV4ARERFVLQagGkicBdqOPUBERERVgQGoBuIq8ERERFWLAaiGyclX425qDgDOAURERFRVGIBqmLj72t4fc6URrE14CTwREVFVqBEBaPny5XB3d4dSqYS/vz9OnDhRbt38/HwsWLAAnp6eUCqV8Pb2xu7du3XqrFixAm3atIGFhQUsLCzQsWNH7Nq1q6oPo1LElpgBWiKRGLg1REREdZPBA9CWLVsQEhKCuXPn4vTp0/D29kZAQACSkpLKrD979mz88MMPWLp0KS5evIgJEyZg0KBBOHPmjFinQYMG+OKLLxAZGYlTp07hxRdfxIABA/Dvv/9W12E9Nc4BREREVPUkgiAIhmyAv78//Pz8sGzZMgCARqOBm5sbpkyZghkzZpSq7+LiglmzZmHSpEli2eDBg6FSqbB+/fpy38fGxgZff/01xo0b98Q2paWlwdLSEqmpqbCwsHiKo3p6s8POY/2xOEx+oQmmBTSr1vcmIiKqzfT5/jZoD1BeXh4iIyPRs2dPsUwqlaJnz544evRomdvk5uZCqVTqlKlUKhw+fLjM+mq1Gps3b0ZmZiY6duxY7j7T0tJ0boZSfAUYe4CIiIiqikEDUEpKCtRqNRwdHXXKHR0dkZCQUOY2AQEBWLhwIaKjo6HRaBAeHo7t27fj7t27OvXOnz8PMzMzKBQKTJgwATt27ECLFi3K3GdoaCgsLS3Fm5ubW+Uc4FMongOIV4ARERFVFYOPAdLX4sWL0bRpU3h5eUEul2Py5MkIDg6GVKp7KM2aNUNUVBSOHz+OiRMnIigoCBcvXixznzNnzkRqaqp4u3XrVnUcSil5BRrEP8gGwB4gIiKiqmTQAGRnZweZTIbExESd8sTERDg5OZW5jb29PcLCwpCZmYnY2FhcvnwZZmZm8PDw0Kknl8vRpEkT+Pj4IDQ0FN7e3li8eHGZ+1QoFOIVY0U3Q7j9IAsaATCRy2BvpjBIG4iIiOoDgwYguVwOHx8fREREiGUajQYRERHljtcpolQq4erqioKCAmzbtg0DBgx4bH2NRoPc3NxKaXdVKTkDNC+BJyIiqjpGhm5ASEgIgoKC4Ovriw4dOmDRokXIzMxEcHAwAGD06NFwdXVFaGgoAOD48eOIj49H27ZtER8fj3nz5kGj0WD69OniPmfOnIk+ffqgYcOGSE9Px8aNG3HgwAHs2bPHIMdYUeL4H57+IiIiqlIGD0DDhg1DcnIy5syZg4SEBLRt2xa7d+8WB0bHxcXpjO/JycnB7NmzcePGDZiZmSEwMBDr1q2DlZWVWCcpKQmjR4/G3bt3YWlpiTZt2mDPnj3o1atXdR+eXrgGGBERUfUw+DxANZGh5gEas+YEDlxJxhevtMbwDg2r7X2JiIjqglozDxDpYg8QERFR9WAAqiEK1BrcKlwI1d2OY4CIiIiqEgNQDXHnYQ4KNAIURlI4miufvAERERE9NQagGqLoCrCGNiaQSnkJPBERUVViAKohileB5/gfIiKiqsYAVEPEFA6A5hxAREREVY8BqIYQe4C4CCoREVGVYwCqIdgDREREVH0YgGoAtUZAnBiA2ANERERU1RiAaoCEtBzkqTUwlkngbMlL4ImIiKoaA1ANUDT+x83aBEYy/kiIiIiqGr9ta4DiJTA4/oeIiKg6MADVADGcA4iIiKhaMQDVALEpvAKMiIioOjEA1QAxnAOIiIioWjEAGZggCOIYIF4CT0REVD0YgAwsOT0X2flqyKQSuFqpDN0cIiKiesHI0A2o74pmgHa1UkFuxDxKRM9OrVYjPz/f0M0gqnTGxsaQyWSVsi8GIAMrvgKMA6CJ6NkIgoCEhAQ8fPjQ0E0hqjJWVlZwcnKCRCJ5pv0wABlY0SSIHP9DRM+qKPw4ODjAxMTkmb8giGoSQRCQlZWFpKQkAICzs/Mz7Y8ByMBiOAkiEVUCtVothh9bW1tDN4eoSqhU2rGySUlJcHBweKbTYRx0YmDsASKiylA05sfEhP+Zorqt6Hf8Wce5MQAZkCAIxZMg2vGPFhE9O572orqusn7HGYAM6H5mHtJzCyCRAA2sGYCIiCqLu7s7Fi1aZOhmUA3GAGRAReN/nC2UUBpXzmV9RES1iUQieext3rx5T7XfkydP4s0336yUNm7atAkymQyTJk2qlP1RzcAAZECxXASViOq5u3fvirdFixbBwsJCp2zatGliXUEQUFBQUKH92tvbV9p4qFWrVmH69OnYtGkTcnJyKmWfTysvL8+g71+XMAAZUFEPEMf/EFF95eTkJN4sLS0hkUjE55cvX4a5uTl27doFHx8fKBQKHD58GNevX8eAAQPg6OgIMzMz+Pn5Ye/evTr7ffQUmEQiwU8//YRBgwbBxMQETZs2xc6dO5/Yvps3b+Kff/7BjBkz8Nxzz2H79u2l6qxevRotW7aEQqGAs7MzJk+eLL728OFDvPXWW3B0dIRSqUSrVq3wxx9/AADmzZuHtm3b6uxr0aJFcHd3F5+PGTMGAwcOxGeffQYXFxc0a9YMALBu3Tr4+vrC3NwcTk5OeO2118TLw4v8+++/6NevHywsLGBubo4uXbrg+vXr+Pvvv2FsbIyEhASd+lOnTkWXLl2e+JnUFQxABsQeICKqSoIgICuvwCA3QRAq7ThmzJiBL774ApcuXUKbNm2QkZGBwMBARERE4MyZM+jduzf69++PuLi4x+5n/vz5GDp0KM6dO4fAwECMHDkS9+/ff+w2a9asQd++fWFpaYnXX38dq1at0nl9xYoVmDRpEt58802cP38eO3fuRJMmTQAAGo0Gffr0wZEjR7B+/XpcvHgRX3zxhd6XbkdERODKlSsIDw8Xw1N+fj4++eQTnD17FmFhYYiJicGYMWPEbeLj49G1a1coFArs27cPkZGRGDt2LAoKCtC1a1d4eHhg3bp1Yv38/Hxs2LABY8eO1atttRnnATIgsQeIcwARURXIzlejxZw9BnnviwsCYCKvnK+YBQsWoFevXuJzGxsbeHt7i88/+eQT7NixAzt37tTpfXnUmDFjMGLECADA559/jiVLluDEiRPo3bt3mfU1Gg3Wrl2LpUuXAgCGDx+O999/Hzdv3kTjxo0BAJ9++inef/99vPvuu+J2fn5+AIC9e/fixIkTuHTpEp577jkAgIeHh97Hb2pqip9++glyuVwsKxlUPDw8sGTJEvj5+SEjIwNmZmZYvnw5LC0tsXnzZhgbGwOA2AYAGDduHNasWYMPPvgAAPD7778jJycHQ4cO1bt9tRV7gAyIPUBERE/m6+ur8zwjIwPTpk1D8+bNYWVlBTMzM1y6dOmJPUBt2rQRH5uamsLCwqLUaaOSwsPDkZmZicDAQACAnZ0devXqhdWrVwPQTsZ3584d9OjRo8zto6Ki0KBBA53g8TRat26tE34AIDIyEv3790fDhg1hbm6Obt26AYD4GURFRaFLly5i+HnUmDFjcO3aNRw7dgwAsHbtWgwdOhSmpvXn+4g9QAbyMCsPD7O0kzhxFmgiqgoqYxkuLggw2HtXlke/lKdNm4bw8HB88803aNKkCVQqFV599dUnDhB+NAxIJBJoNJpy669atQr3798XZx8GtL1C586dw/z583XKy/Kk16VSaalThWVN7vfo8WdmZiIgIAABAQHYsGED7O3tERcXh4CAAPEzeNJ7Ozg4oH///lizZg0aN26MXbt24cCBA4/dpq5hADKQ2MLTXw7mikrrJiYiKkkikdTJvy9HjhzBmDFjMGjQIADaHqGYmJhKfY979+7ht99+w+bNm9GyZUuxXK1W4/nnn8dff/2F3r17w93dHREREXjhhRdK7aNNmza4ffs2rl69WmYvkL29PRISEiAIgji5X1RU1BPbdvnyZdy7dw9ffPEF3NzcAACnTp0q9d4///wz8vPzy+0FeuONNzBixAg0aNAAnp6e6Ny58xPfuy6pEafAli9fDnd3dyiVSvj7++PEiRPl1s3Pz8eCBQvg6ekJpVIJb29v7N69W6dOaGgo/Pz8YG5uDgcHBwwcOBBXrlyp6sPQS+z9ovE/9ae7kYioMjRt2hTbt29HVFQUzp49i9dee+2xPTlPY926dbC1tcXQoUPRqlUr8ebt7Y3AwEBxMPS8efPw7bffYsmSJYiOjsbp06fFMUPdunVD165dMXjwYISHh+PmzZvYtWuX+J3VvXt3JCcn46uvvsL169exfPly7Nq164lta9iwIeRyOZYuXYobN25g586d+OSTT3TqTJ48GWlpaRg+fDhOnTqF6OhorFu3Tue7MCAgABYWFvj0008RHBxcWR9drWHwALRlyxaEhIRg7ty5OH36NLy9vREQEFDuednZs2fjhx9+wNKlS3Hx4kVMmDABgwYNwpkzZ8Q6Bw8exKRJk3Ds2DGEh4cjPz8fL730EjIzM6vrsJ4oNqVo/A9PfxER6WPhwoWwtrZGp06d0L9/fwQEBKB9+/aV+h6rV6/GoEGDylx2YfDgwdi5cydSUlIQFBSERYsW4b///S9atmyJfv36ITo6Wqy7bds2+Pn5YcSIEWjRogWmT58OtVoNAGjevDn++9//Yvny5fD29saJEyd05j0qj729PdauXYutW7eiRYsW+OKLL/DNN9/o1LG1tcW+ffuQkZGBbt26wcfHBytXrtTpDZJKpRgzZgzUajVGjx79tB9VrSURKvNaxafg7+8PPz8/LFu2DID2/KqbmxumTJmCGTNmlKrv4uKCWbNm6czIOXjwYKhUKqxfv77M90hOToaDgwMOHjyIrl27PrFNaWlpsLS0RGpqKiwsLJ7yyB7v/V/OYtvp2/ggoBkmvdCkSt6DiOqPnJwc8eokpVJp6OZQLTFu3DgkJydXaE6kmuJxv+v6fH8b9ORwXl4eIiMjMXPmTLFMKpWiZ8+eOHr0aJnb5ObmljpglUqFw4cPl/s+qampALSXTpa3z9zcXPF5WlpahY/haRVfAcYeICIiql6pqak4f/48Nm7cWKvCT2Uy6CmwlJQUqNVqODo66pQ7OjqWmqGySEBAABYuXIjo6GhoNBqEh4dj+/btuHv3bpn1NRoNpk6dis6dO6NVq1Zl1gkNDYWlpaV4KxpUVpWK5wDiGCAiIqpeAwYMwEsvvYQJEybozLFUnxh8DJC+Fi9ejKZNm8LLywtyuRyTJ09GcHAwpNKyD2XSpEm4cOECNm/eXO4+Z86cidTUVPF269atqmo+ACAjtwApGdoep4bsASIiomp24MABZGVl4bvvvjN0UwzGoAHIzs4OMpkMiYmJOuWJiYlwcnIqcxt7e3uEhYUhMzMTsbGxuHz5MszMzMqcXXPy5Mn4448/sH//fjRo0KDcdigUClhYWOjcqlLR6S9bUzkslGVfnkhERERVx6ABSC6Xw8fHBxEREWKZRqNBREQEOnbs+NhtlUolXF1dUVBQgG3btmHAgAHia4IgYPLkydixYwf27dsnTlleUxTNAcTxP0RERIZh8BmyQkJCEBQUBF9fX3To0AGLFi1CZmamOCfB6NGj4erqitDQUADA8ePHER8fj7Zt2yI+Ph7z5s2DRqPB9OnTxX1OmjQJGzduxG+//QZzc3NxPJGlpeUTZ8esDjGFPUAc/0NERGQYBg9Aw4YNQ3JyMubMmYOEhAS0bdsWu3fvFgdGx8XF6YzvycnJwezZs3Hjxg2YmZkhMDAQ69atg5WVlVhnxYoVALSTTJW0Zs0andVyDSU2pagHiAGIiIjIEAwegADtWJ3yVvB9dG2Sbt264eLFi4/dn4GnNnoisQfIjqfAiIiIDKHWXQVWFxSPAWIPEBERkSEwAFWz7Dw1EtJyAACNbNgDRERUGbp3746pU6eKz93d3bFo0aLHbiORSBAWFvbM711Z+6HqxQBUzeIKF0G1UBrByoSXwBNR/da/f3/07t27zNcOHToEiUSCc+fO6b3fkydP4s0333zW5umYN28e2rZtW6r87t276NOnT6W+V3mys7NhY2MDOzs7nRUMSH8MQNWsePyPaZmL7BER1Sfjxo1DeHg4bt++Xeq1NWvWwNfXF23atNF7v/b29jAxqZ5edicnJygUimp5r23btqFly5bw8vIyeK+TIAgoKCgwaBueBQNQNSteA4zjf4iI+vXrJ65uXlJGRga2bt2KcePG4d69exgxYgRcXV1hYmKC1q1bY9OmTY/d76OnwKKjo9G1a1colUq0aNEC4eHhpbb58MMP8dxzz8HExAQeHh74+OOPkZ+fDwBYu3Yt5s+fj7Nnz0IikUAikYhtfvQU2Pnz5/Hiiy9CpVLB1tYWb775JjIyMsTXx4wZg4EDB+Kbb76Bs7MzbG1tMWnSJPG9HmfVqlV4/fXX8frrr2PVqlWlXv/333/Rr18/WFhYwNzcHF26dMH169fF11evXo2WLVtCoVDA2dlZvAApJiYGEokEUVFRYt2HDx9CIpGIFyMdOHAAEokEu3btgo+PDxQKBQ4fPozr169jwIABcHR0hJmZGfz8/LB3716dduXm5uLDDz+Em5sbFAoFmjRpglWrVkEQBDRp0qTUavZRUVGQSCS4du3aEz+Tp1UjrgKrT4rXAOP4HyKqYoIA5GcZ5r2NTYAK9HIbGRlh9OjRWLt2LWbNmiX2jG/duhVqtRojRoxARkYGfHx88OGHH8LCwgJ//vknRo0aBU9PT3To0OGJ76HRaPDKK6/A0dERx48fR2pqqs54oSLm5uZYu3YtXFxccP78eYwfPx7m5uaYPn06hg0bhgsXLmD37t3il7ulpWWpfWRmZiIgIAAdO3bEyZMnkZSUhDfeeAOTJ0/WCXn79++Hs7Mz9u/fj2vXrmHYsGFo27Ytxo8fX+5xXL9+HUePHsX27dshCALee+89xMbGolGjRgCA+Ph4dO3aFd27d8e+fftgYWGBI0eOiL00K1asQEhICL744gv06dMHqampOHLkyBM/v0fNmDED33zzDTw8PGBtbY1bt24hMDAQn332GRQKBf7v//4P/fv3x5UrV9CwYUMA2jn9jh49iiVLlsDb2xs3b95ESkoKJBIJxo4dizVr1mDatGnie6xZswZdu3ZFkyZN9G5fRTEAVTP2ABFRtcnPAj53Mcx7f3QHkFfs79zYsWPx9ddf4+DBg+L8bWvWrMHgwYPFRapLfjlOmTIFe/bswS+//FKhALR3715cvnwZe/bsgYuL9vP4/PPPS43bmT17tvjY3d0d06ZNw+bNmzF9+nSoVCqYmZnByMio3KWaAGDjxo3IycnB//3f/8HUVHv8y5YtQ//+/fHll1+Kc9xZW1tj2bJlkMlk8PLyQt++fREREfHYALR69Wr06dMH1tbWALSLg69Zswbz5s0DACxfvhyWlpbYvHkzjI21Y0yfe+45cftPP/0U77//Pt59912xzM/P74mf36MWLFigs4CqjY0NvL29xeeffPIJduzYgZ07d2Ly5Mm4evUqfvnlF4SHh6Nnz54AoLN81ZgxYzBnzhycOHECHTp0QH5+PjZu3FiqV6iy8RRYNYtJYQ8QEVFJXl5e6NSpE1avXg0AuHbtGg4dOoRx48YBANRqNT755BO0bt0aNjY2MDMzw549exAXF1eh/V+6dAlubm5i+AFQ5nJLW7ZsQefOneHk5AQzMzPMnj27wu9R8r28vb3F8AMAnTt3hkajwZUrV8Syli1bQiaTic+dnZ2RlJRU7n7VajV+/vlnvP7662LZ66+/jrVr10Kj0QDQnjbq0qWLGH5KSkpKwp07d9CjRw+9jqcsvr6+Os8zMjIwbdo0NG/eHFZWVjAzM8OlS5fEzy4qKgoymQzdunUrc38uLi7o27ev+PP//fffkZubiyFDhjxzWx+HPUDVKLdAjTup2QDYA0RE1cDYRNsTY6j31sO4ceMwZcoULF++HGvWrIGnp6f4hfn1119j8eLFWLRoEVq3bg1TU1NMnToVeXl5ldbco0ePYuTIkZg/fz4CAgLEnpRvv/220t6jpEdDikQiEYNMWfbs2YP4+HgMGzZMp1ytViMiIgK9evV67FJPT1oGqmjFhZITCZc3JqlkuAOAadOmITw8HN988w2aNGkClUqFV199Vfz5VGQJqjfeeAOjRo3Cd999hzVr1mDYsGFVPoidPUDV6Nb9bAgCYCqXwc5MbujmEFFdJ5FoT0MZ4qbnVa5Dhw6FVCrFxo0b8X//938YO3asOB7oyJEjGDBgAF5//XV4e3vDw8MDV69erfC+mzdvjlu3buHu3bti2bFjx3Tq/PPPP2jUqBFmzZoFX19fNG3aFLGxsTp15HI51Gr1E9/r7NmzyMzMFMuOHDkCqVSKZs2aVbjNj1q1ahWGDx+OqKgondvw4cPFwdBt2rTBoUOHygwu5ubmcHd311l8vCR7e3sA0PmMSg6IfpwjR45gzJgxGDRoEFq3bg0nJyfExMSIr7du3RoajQYHDx4sdx+BgYEwNTXFihUrsHv3bowdO7ZC7/0sGICqUdz94vE/vASeiKiYmZkZhg0bhpkzZ+Lu3bs66zY2bdoU4eHh+Oeff3Dp0iW89dZbSExMrPC+e/bsieeeew5BQUE4e/YsDh06hFmzZunUadq0KeLi4rB582Zcv34dS5YswY4dO3TquLu74+bNm4iKikJKSkqZ8/CMHDkSSqUSQUFBuHDhAvbv348pU6Zg1KhR4vgffSUnJ+P3339HUFAQWrVqpXMbPXo0wsLCcP/+fUyePBlpaWkYPnw4Tp06hejoaKxbt0489TZv3jx8++23WLJkCaKjo3H69GksXboUgLaX5j//+Q+++OILXLp0CQcPHtQZE/U4TZs2xfbt2xEVFYWzZ8/itdde0+nNcnd3R1BQEMaOHYuwsDDcvHkTBw4cwC+//CLWkclkGDNmDGbOnImmTZuWeYqysjEAVaO07AKYKYy4BhgRURnGjRuHBw8eICAgQGe8zuzZs9G+fXsEBASge/fucHJywsCBAyu8X6lUih07diA7OxsdOnTAG2+8gc8++0ynzssvv4z33nsPkydPRtu2bfHPP//g448/1qkzePBg9O7dGy+88ALs7e3LvBTfxMQEe/bswf379+Hn54dXX30VPXr0wLJly/T7MEooGlBd1vidHj16QKVSYf369bC1tcW+ffuQkZGBbt26wcfHBytXrhRPtwUFBWHRokX473//i5YtW6Jfv36Ijo4W97V69WoUFBTAx8cHU6dOxaefflqh9i1cuBDW1tbo1KkT+vfvj4CAALRv316nzooVK/Dqq6/i7bffhpeXF8aPH6/TSwZof/55eXkIDg7W9yN6KhKhpq8cagBpaWmwtLREamoqLCwsKnXfgiAgt0ADpbHsyZWJiCooJycHN2/eROPGjaFUKg3dHCK9HTp0CD169MCtW7ce21v2uN91fb6/OQi6mkkkEoYfIiKiQrm5uUhOTsa8efMwZMiQpz5VqC+eAiMiIiKD2bRpExo1aoSHDx/iq6++qrb3ZQAiIiIigxkzZgzUajUiIyPh6upabe/LAERERET1DgMQERER1TsMQEREdQgv7KW6rrJ+xxmAiIjqgKK5XrKyDLT6O1E1KfodL2vNM33wMngiojpAJpPByspKXFDTxMSEM85TnSIIArKyspCUlAQrKyudxWSfBgMQEVEd4eTkBACPXVWcqLazsrISf9efBQMQEVEdIZFI4OzsDAcHh3JX8iaqzYyNjZ+556cIAxARUR0jk8kq7UuCqK7iIGgiIiKqdxiAiIiIqN5hACIiIqJ6h2OAylA0yVJaWpqBW0JEREQVVfS9XZHJEhmAypCeng4AcHNzM3BLiIiISF/p6emwtLR8bB2JwHnTS9FoNLhz5w7Mzc0rfSKxtLQ0uLm54datW7CwsKjUfdcG9f34AX4GPP76ffwAP4P6fvxA1X0GgiAgPT0dLi4ukEofP8qHPUBlkEqlaNCgQZW+h4WFRb39xQd4/AA/Ax5//T5+gJ9BfT9+oGo+gyf1/BThIGgiIiKqdxiAiIiIqN5hAKpmCoUCc+fOhUKhMHRTDKK+Hz/Az4DHX7+PH+BnUN+PH6gZnwEHQRMREVG9wx4gIiIiqncYgIiIiKjeYQAiIiKieocBiIiIiOodBqBqtHz5cri7u0OpVMLf3x8nTpwwdJOqTWhoKPz8/GBubg4HBwcMHDgQV65cMXSzDOaLL76ARCLB1KlTDd2UahUfH4/XX38dtra2UKlUaN26NU6dOmXoZlULtVqNjz/+GI0bN4ZKpYKnpyc++eSTCq1ZVFv9/fff6N+/P1xcXCCRSBAWFqbzuiAImDNnDpydnaFSqdCzZ09ER0cbprFV4HHHn5+fjw8//BCtW7eGqakpXFxcMHr0aNy5c8dwDa5kT/r5lzRhwgRIJBIsWrSo2trHAFRNtmzZgpCQEMydOxenT5+Gt7c3AgICkJSUZOimVYuDBw9i0qRJOHbsGMLDw5Gfn4+XXnoJmZmZhm5atTt58iR++OEHtGnTxtBNqVYPHjxA586dYWxsjF27duHixYv49ttvYW1tbeimVYsvv/wSK1aswLJly3Dp0iV8+eWX+Oqrr7B06VJDN63KZGZmwtvbG8uXLy/z9a+++gpLlizB999/j+PHj8PU1BQBAQHIycmp5pZWjccdf1ZWFk6fPo2PP/4Yp0+fxvbt23HlyhW8/PLLBmhp1XjSz7/Ijh07cOzYMbi4uFRTywoJVC06dOggTJo0SXyuVqsFFxcXITQ01ICtMpykpCQBgHDw4EFDN6VapaenC02bNhXCw8OFbt26Ce+++66hm1RtPvzwQ+H55583dDMMpm/fvsLYsWN1yl555RVh5MiRBmpR9QIg7NixQ3yu0WgEJycn4euvvxbLHj58KCgUCmHTpk0GaGHVevT4y3LixAkBgBAbG1s9japG5R3/7du3BVdXV+HChQtCo0aNhO+++67a2sQeoGqQl5eHyMhI9OzZUyyTSqXo2bMnjh49asCWGU5qaioAwMbGxsAtqV6TJk1C3759dX4X6oudO3fC19cXQ4YMgYODA9q1a4eVK1caulnVplOnToiIiMDVq1cBAGfPnsXhw4fRp08fA7fMMG7evImEhASdfwuWlpbw9/ev138XJRIJrKysDN2UaqHRaDBq1Ch88MEHaNmyZbW/PxdDrQYpKSlQq9VwdHTUKXd0dMTly5cN1CrD0Wg0mDp1Kjp37oxWrVoZujnVZvPmzTh9+jROnjxp6KYYxI0bN7BixQqEhITgo48+wsmTJ/HOO+9ALpcjKCjI0M2rcjNmzEBaWhq8vLwgk8mgVqvx2WefYeTIkYZumkEkJCQAQJl/F4teq09ycnLw4YcfYsSIEfVmgdQvv/wSRkZGeOeddwzy/gxAVO0mTZqECxcu4PDhw4ZuSrW5desW3n33XYSHh0OpVBq6OQah0Wjg6+uLzz//HADQrl07XLhwAd9//329CEC//PILNmzYgI0bN6Jly5aIiorC1KlT4eLiUi+On8qXn5+PoUOHQhAErFixwtDNqRaRkZFYvHgxTp8+DYlEYpA28BRYNbCzs4NMJkNiYqJOeWJiIpycnAzUKsOYPHky/vjjD+zfvx8NGjQwdHOqTWRkJJKSktC+fXsYGRnByMgIBw8exJIlS2BkZAS1Wm3oJlY5Z2dntGjRQqesefPmiIuLM1CLqtcHH3yAGTNmYPjw4WjdujVGjRqF9957D6GhoYZumkEU/e2r738Xi8JPbGwswsPD603vz6FDh5CUlISGDRuKfxNjY2Px/vvvw93dvVrawABUDeRyOXx8fBARESGWaTQaREREoGPHjgZsWfURBAGTJ0/Gjh07sG/fPjRu3NjQTapWPXr0wPnz5xEVFSXefH19MXLkSERFRUEmkxm6iVWuc+fOpaY+uHr1Kho1amSgFlWvrKwsSKW6f3JlMhk0Go2BWmRYjRs3hpOTk87fxbS0NBw/frze/F0sCj/R0dHYu3cvbG1tDd2kajNq1CicO3dO52+ii4sLPvjgA+zZs6da2sBTYNUkJCQEQUFB8PX1RYcOHbBo0SJkZmYiODjY0E2rFpMmTcLGjRvx22+/wdzcXDzHb2lpCZVKZeDWVT1zc/NS451MTU1ha2tbb8ZBvffee+jUqRM+//xzDB06FCdOnMCPP/6IH3/80dBNqxb9+/fHZ599hoYNG6Jly5Y4c+YMFi5ciLFjxxq6aVUmIyMD165dE5/fvHkTUVFRsLGxQcOGDTF16lR8+umnaNq0KRo3boyPP/4YLi4uGDhwoOEaXYked/zOzs549dVXcfr0afzxxx9Qq9Xi30UbGxvI5XJDNbvSPOnn/2jgMzY2hpOTE5o1a1Y9Day2681IWLp0qdCwYUNBLpcLHTp0EI4dO2boJlUbAGXe1qxZY+imGUx9uwxeEATh999/F1q1aiUoFArBy8tL+PHHHw3dpGqTlpYmvPvuu0LDhg0FpVIpeHh4CLNmzRJyc3MN3bQqs3///jL/3QcFBQmCoL0U/uOPPxYcHR0FhUIh9OjRQ7hy5YphG12JHnf8N2/eLPfv4v79+w3d9ErxpJ//o6r7MniJINThaUiJiIiIysAxQERERFTvMAARERFRvcMARERERPUOAxARERHVOwxAREREVO8wABEREVG9wwBERERE9Q4DEBFROSQSCcLCwgzdDCKqAgxARFQjjRkzBhKJpNStd+/ehm4aEdUBXAuMiGqs3r17Y82aNTplCoXCQK0horqEPUBEVGMpFAo4OTnp3KytrQFoT0+tWLECffr0gUqlgoeHB3799Ved7c+fP48XX3wRKpUKtra2ePPNN5GRkaFTZ/Xq1WjZsiUUCgWcnZ0xefJknddTUlIwaNAgmJiYoGnTpti5c6f42oMHDzBy5EjY29tDpVKhadOmpQIbEdVMDEBEVGt9/PHHGDx4MM6ePYuRI0di+PDhuHTpEgAgMzMTAQEBsLa2xsmTJ7F161bs3btXJ+CsWLECkyZNwptvvonz589j586daNKkic57zJ8/H0OHDsW5c+cQGBiIkSNH4v79++L7X7x4Ebt27cKlS5ewYsUK2NnZVd8HQERPr9qWXSUi0kNQUJAgk8kEU1NTndtnn30mCIIgABAmTJigs42/v78wceJEQRAE4ccffxSsra2FjIwM8fU///xTkEqlQkJCgiAIguDi4iLMmjWr3DYAEGbPni0+z8jIEAAIu3btEgRBEPr37y8EBwdXzgETUbXiGCAiqrFeeOEFrFixQqfMxsZGfNyxY0ed1zp27IioqCgAwKVLl+Dt7Q1TU1Px9c6dO0Oj0eDKlSuQSCS4c+cOevTo8dg2tGnTRnxsamoKCwsLJCUlAQAmTpyIwYMH4/Tp03jppZcwcOBAdOrU6amOlYiqFwMQEdVYpqampU5JVRaVSlWhesbGxjrPJRIJNBoNAKBPnz6IjY3F//73P4SHh6NHjx6YNGkSvvnmm0pvLxFVLo4BIqJa69ixY6WeN2/eHADQvHlznD17FpmZmeLrR44cgVQqRbNmzWBubg53d3dEREQ8Uxvs7e0RFBSE9evXY9GiRfjxxx+faX9EVD3YA0RENVZubi4SEhJ0yoyMjMSBxlu3boWvry+ef/55bNiwASdOnMCqVasAACNHjsTcuXMRFBSEefPmITk5GVOmTMGoUaPg6OgIAJg3bx4mTJgABwcH9OnTB+np6Thy5AimTJlSofbNmTMHPj4+aNmyJXJzc/HHH3+IAYyIajYGICKqsXbv3g1nZ2edsmbNmuHy5csAtFdobd68GW+//TacnZ2xadMmtGjRAgBgYmKCPXv24N1334Wfnx9MTEwwePBgLFy4UNxXUFAQcnJy8N1332HatGmws7PDq6++WuH2yeVyzJw5EzExMVCpVOjSpQs2b95cCUdORFVNIgiCYOhGEBHpSyKRYMeOHRg4cKChm0JEtRDHABEREVG9wwBERERE9Q7HABFRrcSz90T0LNgDRERERPUOAxARERHVOwxAREREVO8wABEREVG9wwBERERE9Q4DEBEREdU7DEBERERU7zAAERERUb3DAERERET1zv8DTtu7soCovEMAAAAASUVORK5CYII=\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# plot traning and validation accuracy\n",
        "plt.plot(history.history['loss'], label='Train Loss')\n",
        "plt.plot(history.history['val_loss'], label='Validation Loss')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Loss')\n",
        "plt.title('Training and Validation Loss')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 472
        },
        "id": "DVeSwPLyv8VY",
        "outputId": "bb8ecc8f-7e55-4f23-f76f-71a6adeb231f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Save the model\n",
        "model.save('cnn_mnist_model.h5')\n",
        "print(\"Model saved successfully!\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zd5F0zA3xll3",
        "outputId": "e61228c8-7d49-49ea-c5ea-15675df0e87e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model saved successfully!\n"
          ]
        }
      ]
    },
    {
      "source": [
        "# Evaluate the model on Test Data\n",
        "test_loss, test_accuracy = model.evaluate(x_test.reshape(-1, 28, 28, 1), y_test) # Reshape x_test to (num_samples, 28, 28, 1)\n",
        "print(f\"Test Loss: {test_loss:.4f}\")\n",
        "print(f\"Test Accuracy: {test_accuracy:.4f}\")"
      ],
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VCXVJ4736Xan",
        "outputId": "17effa14-9b99-491f-fba8-d5f26d932ec1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - accuracy: 0.9925 - loss: 0.0253\n",
            "Test Loss: 0.0222\n",
            "Test Accuracy: 0.9935\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Predictions for Test Data\n",
        "y_pred = model.predict(x_test)\n",
        "y_pred_classes = np.argmax(y_pred, axis=1)\n",
        "y_true = np.argmax(y_test, axis=1)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "X4utzu9t6bBV",
        "outputId": "8c3fd841-f07e-47ab-b660-0c2f265fad0f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step\n"
          ]
        }
      ]
    },
    {
      "source": [
        "# Import the classification_report function\n",
        "from sklearn.metrics import classification_report\n",
        "\n",
        "# Classification Report (Precision, Recall, F1-score)\n",
        "report = classification_report(y_true, y_pred_classes, digits=4)\n",
        "print(\"Classification Report:\\n\", report)"
      ],
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GqVsdzMa6m3U",
        "outputId": "5cf36a89-fa9e-445a-ab27-ebc50b8247bf"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Classification Report:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0     0.9980    0.9969    0.9974       980\n",
            "           1     0.9956    0.9974    0.9965      1135\n",
            "           2     0.9932    0.9942    0.9937      1032\n",
            "           3     0.9951    0.9970    0.9960      1010\n",
            "           4     0.9909    0.9939    0.9924       982\n",
            "           5     0.9889    0.9944    0.9916       892\n",
            "           6     0.9948    0.9906    0.9927       958\n",
            "           7     0.9932    0.9922    0.9927      1028\n",
            "           8     0.9938    0.9928    0.9933       974\n",
            "           9     0.9910    0.9851    0.9881      1009\n",
            "\n",
            "    accuracy                         0.9935     10000\n",
            "   macro avg     0.9934    0.9935    0.9934     10000\n",
            "weighted avg     0.9935    0.9935    0.9935     10000\n",
            "\n"
          ]
        }
      ]
    },
    {
      "source": [
        "# Import necessary functions from sklearn.metrics\n",
        "from sklearn.metrics import precision_score, recall_score, f1_score\n",
        "\n",
        "# Calculate Precision, Recall, and F1-score\n",
        "precision = precision_score(y_true, y_pred_classes, average='weighted')\n",
        "recall = recall_score(y_true, y_pred_classes, average='weighted')\n",
        "f1 = f1_score(y_true, y_pred_classes, average='weighted')\n",
        "\n",
        "print(f\"Precision: {precision:.4f}\")\n",
        "print(f\"Recall: {recall:.4f}\")\n",
        "print(f\"F1 Score: {f1:.4f}\")"
      ],
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HQ9fW1Oc6z8l",
        "outputId": "278ada1b-32c6-47b8-f84a-76a85ac9e180"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Precision: 0.9935\n",
            "Recall: 0.9935\n",
            "F1 Score: 0.9935\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Training Loss and Accuracy\n",
        "print(\"Training Accuracy: {:.4f}\".format(history.history['accuracy'][-1]))\n",
        "print(\"Training Loss: {:.4f}\".format(history.history['loss'][-1]))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EtXXqp4r66AR",
        "outputId": "23b1278f-277e-4b0c-f94e-e5b997aeb015"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training Accuracy: 0.9914\n",
            "Training Loss: 0.0257\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Validation Loss and Accuracy\n",
        "print(\"Validation Accuracy: {:.4f}\".format(history.history['val_accuracy'][-1]))\n",
        "print(\"Validation Loss: {:.4f}\".format(history.history['val_loss'][-1]))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gzv_5E1G6-N_",
        "outputId": "0a31480f-6370-47e8-dbd4-cd18e201f540"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Validation Accuracy: 0.9935\n",
            "Validation Loss: 0.0222\n"
          ]
        }
      ]
    }
  ]
}