{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "\n",
        "!pip install tensorflow scikit-learn matplotlib seaborn\n",
        "\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import pandas as pd\n",
        "import os\n",
        "\n",
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras import layers, regularizers\n",
        "from tensorflow.keras.datasets import cifar10\n",
        "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\n",
        "from sklearn.metrics import classification_report, confusion_matrix\n",
        "\n",
        "print(\"TensorFlow version:\", tf.__version__)\n",
        "print(\"GPU available:\", tf.config.list_physical_devices('GPU'))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bFZNDhHoYxqg",
        "outputId": "f4f96700-a5ae-4860-d9e7-bb3c15944d8b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: tensorflow in /usr/local/lib/python3.12/dist-packages (2.20.0)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.12/dist-packages (1.6.1)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.12/dist-packages (3.10.0)\n",
            "Requirement already satisfied: seaborn in /usr/local/lib/python3.12/dist-packages (0.13.2)\n",
            "Requirement already satisfied: absl-py>=1.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.4.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers>=24.3.25 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (25.12.19)\n",
            "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (0.7.0)\n",
            "Requirement already satisfied: google_pasta>=0.1.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (0.2.0)\n",
            "Requirement already satisfied: libclang>=13.0.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (18.1.1)\n",
            "Requirement already satisfied: opt_einsum>=2.3.2 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.4.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from tensorflow) (26.1)\n",
            "Requirement already satisfied: protobuf>=5.28.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (5.29.6)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.32.4)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from tensorflow) (75.2.0)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.17.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.3.0)\n",
            "Requirement already satisfied: typing_extensions>=3.6.6 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (4.15.0)\n",
            "Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.1.2)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (1.80.0)\n",
            "Requirement already satisfied: tensorboard~=2.20.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.20.0)\n",
            "Requirement already satisfied: keras>=3.10.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.13.2)\n",
            "Requirement already satisfied: numpy>=1.26.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (2.0.2)\n",
            "Requirement already satisfied: h5py>=3.11.0 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (3.16.0)\n",
            "Requirement already satisfied: ml_dtypes<1.0.0,>=0.5.1 in /usr/local/lib/python3.12/dist-packages (from tensorflow) (0.5.4)\n",
            "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (1.16.3)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (1.5.3)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn) (3.6.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.3.3)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (4.62.1)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.5.0)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (11.3.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (3.3.2)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (2.9.0.post0)\n",
            "Requirement already satisfied: pandas>=1.2 in /usr/local/lib/python3.12/dist-packages (from seaborn) (2.2.2)\n",
            "Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.12/dist-packages (from astunparse>=1.6.0->tensorflow) (0.47.0)\n",
            "Requirement already satisfied: rich in /usr/local/lib/python3.12/dist-packages (from keras>=3.10.0->tensorflow) (13.9.4)\n",
            "Requirement already satisfied: namex in /usr/local/lib/python3.12/dist-packages (from keras>=3.10.0->tensorflow) (0.1.0)\n",
            "Requirement already satisfied: optree in /usr/local/lib/python3.12/dist-packages (from keras>=3.10.0->tensorflow) (0.19.0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.2->seaborn) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.2->seaborn) (2026.1)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (3.4.7)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (3.13)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (2.5.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests<3,>=2.21.0->tensorflow) (2026.4.22)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.12/dist-packages (from tensorboard~=2.20.0->tensorflow) (3.10.2)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from tensorboard~=2.20.0->tensorflow) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from tensorboard~=2.20.0->tensorflow) (3.1.8)\n",
            "Requirement already satisfied: markupsafe>=2.1.1 in /usr/local/lib/python3.12/dist-packages (from werkzeug>=1.0.1->tensorboard~=2.20.0->tensorflow) (3.0.3)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich->keras>=3.10.0->tensorflow) (4.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich->keras>=3.10.0->tensorflow) (2.20.0)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich->keras>=3.10.0->tensorflow) (0.1.2)\n",
            "TensorFlow version: 2.20.0\n",
            "GPU available: [PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "(X_train, y_train), (X_test, y_test) = cifar10.load_data()\n",
        "\n",
        "print(\"Training images shape:\", X_train.shape)\n",
        "print(\"Test images shape:    \", X_test.shape)\n",
        "print(\"Pixel value range:    \", X_train.min(), \"to\", X_train.max())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2ILpnwSzY8VA",
        "outputId": "1466d09b-631e-43f3-effe-e56c769c5ffd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training images shape: (50000, 32, 32, 3)\n",
            "Test images shape:     (10000, 32, 32, 3)\n",
            "Pixel value range:     0 to 255\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "CLASS_NAMES = [\"airplane\", \"automobile\", \"bird\", \"cat\", \"deer\",\n",
        "               \"dog\", \"frog\", \"horse\", \"ship\", \"truck\"]\n",
        "\n",
        "\n",
        "X_train = X_train.astype(\"float32\") / 255.0\n",
        "X_test  = X_test.astype(\"float32\")  / 255.0\n",
        "\n",
        "\n",
        "y_train_ohe = keras.utils.to_categorical(y_train, 10)\n",
        "y_test_ohe  = keras.utils.to_categorical(y_test,  10)\n",
        "\n",
        "print(\"Label before one-hot:\", y_train[0])\n",
        "print(\"Label after one-hot: \", y_train_ohe[0])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "w5Fer_FUZeZm",
        "outputId": "6b2849d2-ecd3-4799-9b2f-f6b7ba9bb4c5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Label before one-hot: [6]\n",
            "Label after one-hot:  [0. 0. 0. 0. 0. 0. 1. 0. 0. 0.]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "fig, axes = plt.subplots(4, 4, figsize=(8, 8))\n",
        "\n",
        "for i, ax in enumerate(axes.flat):\n",
        "    ax.imshow(X_train[i])\n",
        "    ax.set_title(CLASS_NAMES[int(y_train[i])], fontsize=9)\n",
        "    ax.axis(\"off\")\n",
        "\n",
        "plt.suptitle(\"Sample CIFAR-10 Training Images\", fontsize=13, fontweight=\"bold\")\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 860
        },
        "id": "Pk2GZaf2Zi4F",
        "outputId": "93f01a90-c7c3-42d6-9206-322dfb38ff88"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipykernel_5020/2192835459.py:5: DeprecationWarning: Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)\n",
            "  ax.set_title(CLASS_NAMES[int(y_train[i])], fontsize=9)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x800 with 16 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def build_cnn(dropout_rate=0.3, l2_reg=1e-4):\n",
        "    reg = regularizers.l2(l2_reg)\n",
        "\n",
        "\n",
        "    augmentation = keras.Sequential([\n",
        "        layers.RandomFlip(\"horizontal\"),\n",
        "        layers.RandomRotation(0.1),\n",
        "        layers.RandomZoom(0.1),\n",
        "    ])\n",
        "\n",
        "    inputs = keras.Input(shape=(32, 32, 3))\n",
        "    x = augmentation(inputs)\n",
        "\n",
        "\n",
        "    x = layers.Conv2D(32, 3, padding=\"same\", kernel_regularizer=reg)(x)\n",
        "    x = layers.BatchNormalization()(x)\n",
        "    x = layers.Activation(\"relu\")(x)\n",
        "    x = layers.Conv2D(32, 3, padding=\"same\", kernel_regularizer=reg)(x)\n",
        "    x = layers.BatchNormalization()(x)\n",
        "    x = layers.Activation(\"relu\")(x)\n",
        "    x = layers.MaxPooling2D(2)(x)\n",
        "    x = layers.Dropout(dropout_rate)(x)\n",
        "\n",
        "\n",
        "    x = layers.Conv2D(64, 3, padding=\"same\", kernel_regularizer=reg)(x)\n",
        "    x = layers.BatchNormalization()(x)\n",
        "    x = layers.Activation(\"relu\")(x)\n",
        "    x = layers.Conv2D(64, 3, padding=\"same\", kernel_regularizer=reg)(x)\n",
        "    x = layers.BatchNormalization()(x)\n",
        "    x = layers.Activation(\"relu\")(x)\n",
        "    x = layers.MaxPooling2D(2)(x)\n",
        "    x = layers.Dropout(dropout_rate)(x)\n",
        "\n",
        "\n",
        "    x = layers.Conv2D(128, 3, padding=\"same\", kernel_regularizer=reg)(x)\n",
        "    x = layers.BatchNormalization()(x)\n",
        "    x = layers.Activation(\"relu\")(x)\n",
        "    x = layers.Conv2D(128, 3, padding=\"same\", kernel_regularizer=reg)(x)\n",
        "    x = layers.BatchNormalization()(x)\n",
        "    x = layers.Activation(\"relu\")(x)\n",
        "    x = layers.MaxPooling2D(2)(x)\n",
        "    x = layers.Dropout(dropout_rate)(x)\n",
        "\n",
        "\n",
        "    x = layers.GlobalAveragePooling2D()(x)\n",
        "    x = layers.Dense(256, kernel_regularizer=reg)(x)\n",
        "    x = layers.BatchNormalization()(x)\n",
        "    x = layers.Activation(\"relu\")(x)\n",
        "    x = layers.Dropout(dropout_rate + 0.1)(x)\n",
        "    outputs = layers.Dense(10, activation=\"softmax\")(x)\n",
        "\n",
        "    return keras.Model(inputs, outputs, name=\"CIFAR10_CNN\")\n",
        "\n",
        "model = build_cnn()\n",
        "model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "iAp1Yw8nZxA0",
        "outputId": "ad227879-88e3-45e6-f437-00c9c5ffc65a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"CIFAR10_CNN\"\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: \"CIFAR10_CNN\"</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",
              "│ input_layer_2 (\u001b[38;5;33mInputLayer\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m3\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ sequential_1 (\u001b[38;5;33mSequential\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m3\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │           \u001b[38;5;34m896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_7           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │           \u001b[38;5;34m128\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_7 (\u001b[38;5;33mActivation\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │         \u001b[38;5;34m9,248\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_8           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │           \u001b[38;5;34m128\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_8 (\u001b[38;5;33mActivation\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_4 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_8 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_9           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │           \u001b[38;5;34m256\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_9 (\u001b[38;5;33mActivation\u001b[0m)       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_9 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m36,928\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_10          │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │           \u001b[38;5;34m256\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_10 (\u001b[38;5;33mActivation\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_5 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_10 (\u001b[38;5;33mConv2D\u001b[0m)              │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │        \u001b[38;5;34m73,856\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_11          │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │           \u001b[38;5;34m512\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_11 (\u001b[38;5;33mActivation\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_11 (\u001b[38;5;33mConv2D\u001b[0m)              │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │       \u001b[38;5;34m147,584\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_12          │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │           \u001b[38;5;34m512\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_12 (\u001b[38;5;33mActivation\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_5 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_6 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d_1      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │        \u001b[38;5;34m33,024\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_13          │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │         \u001b[38;5;34m1,024\u001b[0m │\n",
              "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_13 (\u001b[38;5;33mActivation\u001b[0m)      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_7 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_3 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)             │         \u001b[38;5;34m2,570\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",
              "│ input_layer_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ sequential_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Sequential</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_6 (<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\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_7           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_7 (<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\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │         <span style=\"color: #00af00; text-decoration-color: #00af00\">9,248</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_8           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_8 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_3 (<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\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_4 (<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\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_8 (<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\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_9           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_9 (<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\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">36,928</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_10          │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_10 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_4 (<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\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_5 (<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\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_10 (<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\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_11          │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_11 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_11 (<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\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │       <span style=\"color: #00af00; text-decoration-color: #00af00\">147,584</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_12          │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_12 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_5 (<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\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_6 (<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\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ global_average_pooling2d_1      │ (<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",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_2 (<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\">256</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">33,024</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ batch_normalization_13          │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ activation_13 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_7 (<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\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_3 (<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\">2,570</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m325,418\u001b[0m (1.24 MB)\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\">325,418</span> (1.24 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m324,010\u001b[0m (1.24 MB)\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\">324,010</span> (1.24 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m1,408\u001b[0m (5.50 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\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,408</span> (5.50 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(\n",
        "    optimizer=keras.optimizers.Adam(learning_rate=0.001),\n",
        "    loss=\"categorical_crossentropy\",\n",
        "    metrics=[\"accuracy\"]\n",
        ")\n",
        "\n",
        "callbacks = [\n",
        "\n",
        "    EarlyStopping(monitor=\"val_accuracy\", patience=10,\n",
        "                  restore_best_weights=True, verbose=1),\n",
        "\n",
        "\n",
        "    ReduceLROnPlateau(monitor=\"val_loss\", factor=0.5,\n",
        "                      patience=5, min_lr=1e-6, verbose=1),\n",
        "\n",
        "\n",
        "    ModelCheckpoint(\"best_model.keras\", save_best_only=True,\n",
        "                    monitor=\"val_accuracy\", verbose=0),\n",
        "]\n",
        "\n",
        "history = model.fit(\n",
        "    X_train, y_train_ohe,\n",
        "    validation_data=(X_test, y_test_ohe),\n",
        "    batch_size=64,\n",
        "    epochs=50,\n",
        "    callbacks=callbacks,\n",
        "    verbose=1\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nqJ2YE6oZ6GM",
        "outputId": "5b9ddf76-a47c-423b-eb98-d23c7bab7650"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 26ms/step - accuracy: 0.3853 - loss: 1.7489 - val_accuracy: 0.5227 - val_loss: 1.3997 - learning_rate: 0.0010\n",
            "Epoch 2/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 35ms/step - accuracy: 0.5232 - loss: 1.3868 - val_accuracy: 0.5070 - val_loss: 1.5132 - learning_rate: 0.0010\n",
            "Epoch 3/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 24ms/step - accuracy: 0.5762 - loss: 1.2578 - val_accuracy: 0.5515 - val_loss: 1.4157 - learning_rate: 0.0010\n",
            "Epoch 4/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.6088 - loss: 1.1804 - val_accuracy: 0.5860 - val_loss: 1.3764 - learning_rate: 0.0010\n",
            "Epoch 5/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.6371 - loss: 1.1184 - val_accuracy: 0.6370 - val_loss: 1.1504 - learning_rate: 0.0010\n",
            "Epoch 6/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.6578 - loss: 1.0716 - val_accuracy: 0.5642 - val_loss: 1.4977 - learning_rate: 0.0010\n",
            "Epoch 7/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.6725 - loss: 1.0304 - val_accuracy: 0.6781 - val_loss: 1.0398 - learning_rate: 0.0010\n",
            "Epoch 8/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.6891 - loss: 1.0039 - val_accuracy: 0.7163 - val_loss: 0.9180 - learning_rate: 0.0010\n",
            "Epoch 9/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.6978 - loss: 0.9823 - val_accuracy: 0.6828 - val_loss: 1.0466 - learning_rate: 0.0010\n",
            "Epoch 10/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7057 - loss: 0.9658 - val_accuracy: 0.6881 - val_loss: 1.0806 - learning_rate: 0.0010\n",
            "Epoch 11/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.7151 - loss: 0.9442 - val_accuracy: 0.6227 - val_loss: 1.2666 - learning_rate: 0.0010\n",
            "Epoch 12/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 24ms/step - accuracy: 0.7215 - loss: 0.9344 - val_accuracy: 0.6925 - val_loss: 1.1218 - learning_rate: 0.0010\n",
            "Epoch 13/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7285 - loss: 0.9215 - val_accuracy: 0.7498 - val_loss: 0.8548 - learning_rate: 0.0010\n",
            "Epoch 14/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7342 - loss: 0.9108 - val_accuracy: 0.7523 - val_loss: 0.8602 - learning_rate: 0.0010\n",
            "Epoch 15/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.7398 - loss: 0.8962 - val_accuracy: 0.7039 - val_loss: 1.0120 - learning_rate: 0.0010\n",
            "Epoch 16/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7414 - loss: 0.8944 - val_accuracy: 0.6956 - val_loss: 1.0799 - learning_rate: 0.0010\n",
            "Epoch 17/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7471 - loss: 0.8854 - val_accuracy: 0.7035 - val_loss: 1.0389 - learning_rate: 0.0010\n",
            "Epoch 18/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - accuracy: 0.7528 - loss: 0.8668\n",
            "Epoch 18: ReduceLROnPlateau reducing learning rate to 0.0005000000237487257.\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 24ms/step - accuracy: 0.7491 - loss: 0.8783 - val_accuracy: 0.7030 - val_loss: 1.0849 - learning_rate: 0.0010\n",
            "Epoch 19/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.7689 - loss: 0.8191 - val_accuracy: 0.8011 - val_loss: 0.7241 - learning_rate: 5.0000e-04\n",
            "Epoch 20/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 25ms/step - accuracy: 0.7740 - loss: 0.7980 - val_accuracy: 0.8147 - val_loss: 0.6871 - learning_rate: 5.0000e-04\n",
            "Epoch 21/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7757 - loss: 0.7900 - val_accuracy: 0.8158 - val_loss: 0.6838 - learning_rate: 5.0000e-04\n",
            "Epoch 22/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7807 - loss: 0.7753 - val_accuracy: 0.7993 - val_loss: 0.7246 - learning_rate: 5.0000e-04\n",
            "Epoch 23/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.7824 - loss: 0.7740 - val_accuracy: 0.7941 - val_loss: 0.7403 - learning_rate: 5.0000e-04\n",
            "Epoch 24/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7843 - loss: 0.7593 - val_accuracy: 0.7677 - val_loss: 0.8299 - learning_rate: 5.0000e-04\n",
            "Epoch 25/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7856 - loss: 0.7547 - val_accuracy: 0.8121 - val_loss: 0.6717 - learning_rate: 5.0000e-04\n",
            "Epoch 26/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7873 - loss: 0.7502 - val_accuracy: 0.7953 - val_loss: 0.7365 - learning_rate: 5.0000e-04\n",
            "Epoch 27/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.7897 - loss: 0.7432 - val_accuracy: 0.8173 - val_loss: 0.6760 - learning_rate: 5.0000e-04\n",
            "Epoch 28/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 26ms/step - accuracy: 0.7905 - loss: 0.7393 - val_accuracy: 0.7969 - val_loss: 0.7453 - learning_rate: 5.0000e-04\n",
            "Epoch 29/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.7930 - loss: 0.7341 - val_accuracy: 0.7980 - val_loss: 0.7248 - learning_rate: 5.0000e-04\n",
            "Epoch 30/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - accuracy: 0.7932 - loss: 0.7268\n",
            "Epoch 30: ReduceLROnPlateau reducing learning rate to 0.0002500000118743628.\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 26ms/step - accuracy: 0.7923 - loss: 0.7299 - val_accuracy: 0.8089 - val_loss: 0.7166 - learning_rate: 5.0000e-04\n",
            "Epoch 31/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.8052 - loss: 0.6973 - val_accuracy: 0.8188 - val_loss: 0.6678 - learning_rate: 2.5000e-04\n",
            "Epoch 32/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m22s\u001b[0m 25ms/step - accuracy: 0.8063 - loss: 0.6846 - val_accuracy: 0.8310 - val_loss: 0.6156 - learning_rate: 2.5000e-04\n",
            "Epoch 33/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.8119 - loss: 0.6728 - val_accuracy: 0.8286 - val_loss: 0.6349 - learning_rate: 2.5000e-04\n",
            "Epoch 34/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 25ms/step - accuracy: 0.8140 - loss: 0.6663 - val_accuracy: 0.8196 - val_loss: 0.6621 - learning_rate: 2.5000e-04\n",
            "Epoch 35/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 25ms/step - accuracy: 0.8120 - loss: 0.6621 - val_accuracy: 0.8325 - val_loss: 0.6135 - learning_rate: 2.5000e-04\n",
            "Epoch 36/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 24ms/step - accuracy: 0.8167 - loss: 0.6578 - val_accuracy: 0.8234 - val_loss: 0.6410 - learning_rate: 2.5000e-04\n",
            "Epoch 37/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.8137 - loss: 0.6564 - val_accuracy: 0.8260 - val_loss: 0.6281 - learning_rate: 2.5000e-04\n",
            "Epoch 38/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 25ms/step - accuracy: 0.8152 - loss: 0.6551 - val_accuracy: 0.8281 - val_loss: 0.6202 - learning_rate: 2.5000e-04\n",
            "Epoch 39/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 24ms/step - accuracy: 0.8154 - loss: 0.6512 - val_accuracy: 0.8390 - val_loss: 0.5896 - learning_rate: 2.5000e-04\n",
            "Epoch 40/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 26ms/step - accuracy: 0.8153 - loss: 0.6490 - val_accuracy: 0.8407 - val_loss: 0.5808 - learning_rate: 2.5000e-04\n",
            "Epoch 41/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m18s\u001b[0m 23ms/step - accuracy: 0.8179 - loss: 0.6447 - val_accuracy: 0.8404 - val_loss: 0.5847 - learning_rate: 2.5000e-04\n",
            "Epoch 42/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.8171 - loss: 0.6398 - val_accuracy: 0.8286 - val_loss: 0.6268 - learning_rate: 2.5000e-04\n",
            "Epoch 43/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.8179 - loss: 0.6415 - val_accuracy: 0.8403 - val_loss: 0.5824 - learning_rate: 2.5000e-04\n",
            "Epoch 44/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 25ms/step - accuracy: 0.8204 - loss: 0.6377 - val_accuracy: 0.8377 - val_loss: 0.5896 - learning_rate: 2.5000e-04\n",
            "Epoch 45/50\n",
            "\u001b[1m780/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - accuracy: 0.8233 - loss: 0.6257\n",
            "Epoch 45: ReduceLROnPlateau reducing learning rate to 0.0001250000059371814.\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 23ms/step - accuracy: 0.8216 - loss: 0.6293 - val_accuracy: 0.8277 - val_loss: 0.6253 - learning_rate: 2.5000e-04\n",
            "Epoch 46/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 25ms/step - accuracy: 0.8257 - loss: 0.6164 - val_accuracy: 0.8359 - val_loss: 0.6041 - learning_rate: 1.2500e-04\n",
            "Epoch 47/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.8272 - loss: 0.6087 - val_accuracy: 0.8433 - val_loss: 0.5743 - learning_rate: 1.2500e-04\n",
            "Epoch 48/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 25ms/step - accuracy: 0.8303 - loss: 0.6048 - val_accuracy: 0.8458 - val_loss: 0.5642 - learning_rate: 1.2500e-04\n",
            "Epoch 49/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 24ms/step - accuracy: 0.8315 - loss: 0.5975 - val_accuracy: 0.8452 - val_loss: 0.5722 - learning_rate: 1.2500e-04\n",
            "Epoch 50/50\n",
            "\u001b[1m782/782\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 25ms/step - accuracy: 0.8295 - loss: 0.5973 - val_accuracy: 0.8352 - val_loss: 0.5957 - learning_rate: 1.2500e-04\n",
            "Restoring model weights from the end of the best epoch: 48.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "fig, axes = plt.subplots(1, 2, figsize=(14, 5))\n",
        "\n",
        "\n",
        "axes[0].plot(history.history[\"accuracy\"],     label=\"Train\")\n",
        "axes[0].plot(history.history[\"val_accuracy\"], label=\"Validation\")\n",
        "axes[0].set_title(\"Accuracy over Epochs\")\n",
        "axes[0].set_xlabel(\"Epoch\")\n",
        "axes[0].set_ylabel(\"Accuracy\")\n",
        "axes[0].legend()\n",
        "axes[0].grid(True, alpha=0.3)\n",
        "\n",
        "\n",
        "axes[1].plot(history.history[\"loss\"],     label=\"Train\")\n",
        "axes[1].plot(history.history[\"val_loss\"], label=\"Validation\")\n",
        "axes[1].set_title(\"Loss over Epochs\")\n",
        "axes[1].set_xlabel(\"Epoch\")\n",
        "axes[1].set_ylabel(\"Loss\")\n",
        "axes[1].legend()\n",
        "axes[1].grid(True, alpha=0.3)\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 400
        },
        "id": "nSxHYZKTdvsB",
        "outputId": "af955ce6-de7d-4e9f-c630-4436fead8e64"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "loss, acc = model.evaluate(X_test, y_test_ohe, verbose=0)\n",
        "print(f\"Test Accuracy: {acc*100:.2f}%\")\n",
        "print(f\"Test Loss:     {loss:.4f}\")\n",
        "\n",
        "y_pred = np.argmax(model.predict(X_test), axis=1)\n",
        "y_true = y_test.flatten()\n",
        "print(classification_report(y_true, y_pred, target_names=CLASS_NAMES))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5f4Tf7-Rd7PS",
        "outputId": "fe6bda1d-cfa4-421f-e8c3-ca9eed7c17ba"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Test Accuracy: 84.58%\n",
            "Test Loss:     0.5642\n",
            "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 8ms/step\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "    airplane       0.90      0.81      0.85      1000\n",
            "  automobile       0.90      0.94      0.92      1000\n",
            "        bird       0.85      0.77      0.81      1000\n",
            "         cat       0.75      0.68      0.72      1000\n",
            "        deer       0.85      0.82      0.84      1000\n",
            "         dog       0.81      0.76      0.78      1000\n",
            "        frog       0.79      0.94      0.86      1000\n",
            "       horse       0.91      0.88      0.90      1000\n",
            "        ship       0.89      0.92      0.91      1000\n",
            "       truck       0.81      0.94      0.87      1000\n",
            "\n",
            "    accuracy                           0.85     10000\n",
            "   macro avg       0.85      0.85      0.84     10000\n",
            "weighted avg       0.85      0.85      0.84     10000\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\n",
        "\n",
        "plt.figure(figsize=(10, 8))\n",
        "sns.heatmap(cm, annot=True, fmt=\"d\", cmap=\"Blues\",\n",
        "            xticklabels=CLASS_NAMES, yticklabels=CLASS_NAMES)\n",
        "plt.xlabel(\"Predicted\")\n",
        "plt.ylabel(\"True\")\n",
        "plt.title(f\"Confusion Matrix  (Accuracy: {acc*100:.2f}%)\")\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 807
        },
        "id": "4nDB1jAod77T",
        "outputId": "fdb94232-5804-4341-9eb2-41c192fd970a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA6AAAAMWCAYAAADvVuvZAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs3XVcFOkfB/DP0h3SGICULSYgYnd33tl9nomBnooYmKhgNyp299l63nkqtoKKiYFKiEgjzO8PztUVVJaf7MD6eb9e+3q5zzwz853HYXaf/T7zjEQQBAFERERERERE+UxF7ACIiIiIiIjo58AOKBERERERESkEO6BERERERESkEOyAEhERERERkUKwA0pEREREREQKwQ4oERERERERKQQ7oERERERERKQQ7IASERERERGRQrADSkRERERERArBDigR0Q8UHh6ORo0awdDQEBKJBHv37v2h23/y5AkkEgnWr1//Q7dbmNWpUwd16tTJ9/1kZmaiXLlymDFjRr7vi35O6enpKF68OJYuXSp2KERE+YYdUCJSOg8fPsTAgQNRsmRJaGlpwcDAAB4eHli0aBGSk5Pzdd89e/bErVu3MGPGDGzcuBFVq1bN1/0pUq9evSCRSGBgYJBjO4aHh0MikUAikWDevHlyb//ly5fw8fHB9evXf0C0P96WLVvw7NkzDB06NMflS5cuhUQigaurq4IjU07bt2+Hm5sbjIyMYGJigtq1a+PQoUPfXCc4OBgSiQR6enq52sf69eul5+yXr1evXsnUTUlJgZ+fH8qUKQMdHR0ULVoUHTt2xJ07d2TqhYaGwtPTE/r6+qhatSouXLiQbb/+/v4oW7YsPnz4IFOurq6OUaNGYcaMGUhJScnVMRARFTZqYgdARPQjHTp0CB07doSmpiZ69OiBcuXKIS0tDefPn8eYMWNw584drFy5Ml/2nZycjAsXLmDixIlf7aT8v2xsbJCcnAx1dfV82f73qKmpISkpCQcOHECnTp1klgUHB0NLSyvPX5xfvnyJqVOnwtbWFi4uLrle79ixY3nan7zmzp2LLl26wNDQMMflwcHBsLW1xaVLl/DgwQM4ODgoJC5lFBgYiGHDhqF58+aYNWsWUlJSsH79erRo0QK7du1Cu3btsq2TkJCAsWPHQldXV+79+fr6ws7OTqbMyMhI5n337t2xf/9+9O/fH5UrV8bLly+xZMkSuLu749atW7CxsUFGRgbatWuHIkWKYO7cudi/fz9at26NBw8ewMDAAADw5s0b+Pr6Yvv27VBTy/41rHfv3hg/fjw2b96MPn36yH0sREQFnkBEpCQePXok6OnpCaVKlRJevnyZbXl4eLiwcOHCfNv/06dPBQDC3Llz820fYurZs6egq6srNGrUSGjTpk225Y6OjkL79u3z3AaXL18WAAjr1q3LVf3ExES595FXV69eFQAIJ06cyHH5o0ePBADC7t27BTMzM8HHx0dhsckrISFB7BC+y9HRUahWrZqQmZkpLXv37p2gp6cntGrVKsd1xo0bJzg7Owvdu3cXdHV1c7WfdevWCQCEy5cvf7Pe8+fPBQCCl5eXTPmpU6cEAIK/v78gCIIQFhYmABCePn0qCELWOaqtrS0cPXpUuk7fvn2Fli1bfnN/LVq0EDw9PXN1DEREhQ2H4BKR0pgzZw4SEhKwZs0aWFlZZVvu4OCA4cOHS99/+PAB06ZNg729PTQ1NWFra4sJEyYgNTVVZj1bW1u0aNEC58+fR/Xq1aGlpYWSJUtiw4YN0jo+Pj6wsbEBAIwZMwYSiQS2trYAsoaufvz353x8fCCRSGTKjh8/jpo1a8LIyAh6enpwdnbGhAkTpMu/dg/oqVOn4OnpCV1dXRgZGaF169YICwvLcX8PHjxAr169YGRkBENDQ/Tu3RtJSUlfb9gvdOvWDUeOHEFcXJy07PLlywgPD0e3bt2y1Y+NjYWXlxfKly8PPT09GBgYoGnTprhx44a0zpkzZ1CtWjUAWRmgj8MgPx5nnTp1UK5cOVy5cgW1atWCjo6OtF2+vAe0Z8+e0NLSynb8jRs3hrGxMV6+fJnrY/1o79690NDQQK1atXJcHhwcDGNjYzRv3hwdOnRAcHBwjvXi4uIwcuRI2NraQlNTE8WKFUOPHj0QHR0trZOSkgIfHx84OTlBS0sLVlZWaNeuHR4+fChtK4lEgjNnzshsO6dzo1evXtDT08PDhw/RrFkz6Ovro3v37gCAv/76Cx07dkSJEiWgqamJ4sWLY+TIkTkOr7579y46deoEMzMzaGtrw9nZGRMnTgQAnD59GhKJBHv27Mm23ubNmyGRSHDhwgW8e/cOd+/exbt3777e0P+Jj4+Hubm5zN+HgYEB9PT0oK2tna1+eHg4FixYAH9//xyzirnx/v17ZGRkfHUZAFhYWMiUf7zOfIzpY9sZGxsDAHR0dKCtrS39+7p69SqCg4Ph7+//zVgaNmyI8+fPIzY2Nk/HQkRUkLEDSkRK48CBAyhZsiRq1KiRq/r9+vXD5MmTUblyZSxYsAC1a9eGn58funTpkq3ugwcP0KFDBzRs2BDz58+HsbExevXqJb3/q127dliwYAEAoGvXrti4cSMWLlwoV/x37txBixYtkJqaCl9fX8yfPx+tWrXC33///c31Tpw4gcaNG+PNmzfw8fHBqFGj8M8//8DDwwNPnjzJVr9Tp054//49/Pz80KlTJ6xfvx5Tp07NdZzt2rWDRCLB7t27pWWbN29GqVKlULly5Wz1Hz16hL1796JFixbw9/fHmDFjcOvWLdSuXVvaGSxdujR8fX0BAAMGDMDGjRuxceNGmQ5fTEwMmjZtChcXFyxcuBB169bNMb5FixbBzMwMPXv2lHYoVqxYgWPHjiEwMBDW1ta5PtaP/vnnH5QrV+6rQ5+Dg4PRrl07aGhooGvXrggPD8fly5dl6iQkJMDT0xOBgYFo1KgRFi1ahEGDBuHu3bt4/vw5ACAjIwMtWrTA1KlTUaVKFcyfPx/Dhw/Hu3fvcPv2bbnjBrJ+aGncuDHMzc0xb948tG/fHgCwY8cOJCUlYfDgwQgMDETjxo0RGBiIHj16yKx/8+ZNuLq64tSpU+jfvz8WLVqENm3a4MCBAwCyfgAoXrx4jp3u4OBg2Nvbw93dHXv27EHp0qVz7Kh+qU6dOjh69CgCAwPx5MkT3L17F7/99hvevXsn8yPSRyNGjEDdunXRrFmzvDQR6tatCwMDA+jo6KBVq1YIDw+XWW5vb49ixYph/vz5OHDgAJ4/f45Lly5h0KBBsLOzk14znJycYGhoCB8fHzx9+hRz585FfHy89O9i2LBhGDp06HeHZ1epUgWCIOCff/7J0/EQERVoYqdgiYh+hHfv3gkAhNatW+eq/vXr1wUAQr9+/WTKvby8BADCqVOnpGU2NjYCAOHcuXPSsjdv3giamprC6NGjpWWPHz/Ocfhpz549BRsbm2wxTJkyRfj8MrxgwQIBgBAVFfXVuD/u4/Nhqi4uLoK5ubkQExMjLbtx44agoqIi9OjRI9v++vTpI7PNtm3bCiYmJl/d5+fH8XFoY4cOHYT69esLgiAIGRkZgqWlpTB16tQc2yAlJUXIyMjIdhyampqCr6+vtOxbQ3Br164tABCWL1+e47LatWvLlP35558CAGH69OnSodk5DRvOrWLFignt27fPcVlISIgAQDh+/LggCIKQmZkpFCtWTBg+fLhMvcmTJ0uH6X7p41DTtWvXygzpzKnO6dOnBQDC6dOnZZbndG707NlTACCMHz8+2/aSkpKylfn5+QkSiUQ6hFQQBKFWrVqCvr6+TNnn8QiCIHh7ewuamppCXFyctOzNmzeCmpqaMGXKFEEQPg13zc0Q69evXwv169cXAEhfpqamwj///JOt7sGDBwU1NTXhzp070mPO7RDcbdu2Cb169RKCgoKEPXv2CH/88Yego6MjmJqaChERETJ1L168KNjb28vEVKVKFSEyMlKm3ubNmwVtbW0BgKCqqirMmzdPEARBCA4OFiwsLIR37959N66XL18KAITZs2fn6jiIiAoTZkCJSCnEx8cDAPT19XNV//DhwwCAUaNGyZSPHj0aALLNtlmmTBl4enpK35uZmcHZ2RmPHj3Kc8xf+jjpyb59+5CZmZmrdSIjI3H9+nX06tULRYoUkZZXqFABDRs2lB7n5wYNGiTz3tPTEzExMdI2zI1u3brhzJkzePXqFU6dOoVXr17lOPwWADQ1NaGikvVxk5GRgZiYGOnw4qtXr+Z6n5qamujdu3eu6jZq1AgDBw6Er68v2rVrBy0tLaxYsSLX+/pSTEyMdFjll4KDg2FhYSHNyEokEnTu3Blbt26VGdK5a9cuVKxYEW3bts22jY9DTXft2gVTU1P8/vvvX62TF4MHD85W9vlQ1sTERERHR6NGjRoQBAHXrl0DAERFReHcuXPo06cPSpQo8dV4evTogdTUVOzcuVNatm3bNnz48AG//PILgKzhwIIgoFevXt+NV0dHB87OzujZsyd27NiBtWvXSociP3jwQFovLS0NI0eOxKBBg1CmTJncNcZnOnXqhHXr1qFHjx5o06YNpk2bhj///BMxMTHZHrdjbGwMFxcXjB8/Hnv37sW8efPw5MkTdOzYUWbira5du+LFixe4cOECXrx4gdGjRyMpKQnjxo3DjBkzoKenh6lTp6JkyZKoUKFCjhnhj+fa50OziYiUBTugRKQUPs4w+fFere95+vQpVFRUsg2Fs7S0hJGREZ4+fSpT/uWXbyDrS+Lbt2/zGHF2nTt3hoeHB/r16wcLCwt06dIF27dv/2Zn9GOczs7O2ZaVLl0a0dHRSExMlCn/8lg+ftmV51g+3k+4bds2BAcHo1q1al8dVpiZmYkFCxbA0dERmpqaMDU1hZmZGW7evJmr+wE/Klq0KDQ0NHJdf968eShSpAiuX7+OgIAAmJub53rdnAiCkK0sIyMDW7duRd26dfH48WM8ePAADx48gKurK16/fo2TJ09K6z58+BDlypX75j4ePnwIZ2fnPN/HmBM1NTUUK1YsW3lERIT0hws9PT2YmZmhdu3aACD9f/n4A8v34i5VqhSqVasmMww3ODgYbm5ueZoNuGPHjoiIiMD69evRoUMH9O7dG2fOnEFaWpr03lMAWLBgAaKjo+UaQv49NWvWhKurK06cOCEte/fuHTw9PeHu7g4/Pz+0bt0ao0ePxq5du3D+/HmsW7dOZhvGxsZwc3OT3jPq5+cHc3Nz9O7dG2vXrsXy5cuxevVqjBgxAp07d5bpVAOfzrX/50cHIqKCih1QIlIKBgYGsLa2lvs+udx+wVNVVc2xPKdOSW738eWEJ9ra2jh37hxOnDiBX3/9FTdv3kTnzp3RsGHDr06Okhf/z7F8pKmpiXbt2iEoKAh79uz5avYTAGbOnIlRo0ahVq1a2LRpE/78808cP34cZcuWzXWmF0COk898y7Vr1/DmzRsAwK1bt+Ra90smJiY5dtBPnTqFyMhIbN26FY6OjtLXx0fUfG0yov9Hbs+njz7PQH9et2HDhjh06BDGjRuHvXv34vjx49IJjOT5f/moR48eOHv2LJ4/f46HDx/i33//lWY/5fHo0SMcPXoUrVq1kikvUqQIatasKb0n+t27d5g+fTr69++P+Ph4PHnyBE+ePEFCQgIEQcCTJ0+k///yKl68uMwEQLt27cLr16+zxVS7dm0YGBh88z7tJ0+eYP78+Vi0aBFUVFSwZcsWDBw4EPXq1UOfPn3g7u6OrVu3yqzz8VwzNTXNU/xERAUZnwNKREqjRYsWWLlyJS5cuAB3d/dv1rWxsUFmZibCw8NRunRpafnr168RFxcnndH2RzA2NpaZMfajL7OsAKCiooL69eujfv368Pf3x8yZMzFx4kScPn0aDRo0yPE4AODevXvZlt29exempqZ5ei5ibnTr1g1r166FiopKjhM3fbRz507UrVsXa9askSmPi4uT+YL9I7M9iYmJ6N27N8qUKYMaNWpgzpw5aNu2rXSmXXmVKlUKjx8/zlYeHBwMc3NzLFmyJNuy3bt3Y8+ePVi+fDm0tbVhb2//3R9I7O3tcfHiRaSnp391wqOPGesvz6mczqevuXXrFu7fv4+goCCZSYeOHz8uU69kyZIAkKsfdrp06YJRo0Zhy5Yt0mfVdu7cOdcxffT69WsAOXeo09PT8eHDBwBZnbSEhATMmTMHc+bMyVbXzs4OrVu3xt69e+WO4dGjRzAzM/tuTIIgICMjQxpTTry8vNCqVSvUrFkTQNbzbj+fCMva2hovXryQWefjufb5tYmISFkwA0pESuPjQ+j79esn/cL4uYcPH2LRokUAIJ0t88uZaj8+HqF58+Y/LC57e3u8e/cON2/elJZFRkZmu/crp0cuuLi4AEC2R8N8ZGVlBRcXFwQFBcl0SG7fvo1jx47leVbQ3Khbty6mTZuGxYsXw9LS8qv1VFVVs2VXd+zYke1L98eOck6ddXmNGzcOERERCAoKgr+/P2xtbdGzZ8+vtuP3uLu74/bt2zLrJycnY/fu3WjRogU6dOiQ7TV06FC8f/8e+/fvBwC0b98eN27cyPGev4/t0759e0RHR2Px4sVfrWNjYwNVVVWcO3dOZvnSpUtzfTwfs+Cf/78IgiD9+/jIzMwMtWrVwtq1axEREZFjPB+ZmpqiadOm2LRpE4KDg9GkSROZHxhy+xgWBwcHqKioYNu2bTL7eP78Of766y9UqlQJAGBubo49e/Zke9WtWxdaWlrYs2cPvL29petHRkbi7t27SE9Pl5ZFRUVl2//hw4dx5coVNGnSRFrm5OQEANkylfv370diYqI0pi+dPn0ahw8flukgW1hY4O7du9L3YWFh2f5+rly5AolE8t0f0oiICiNmQIlIadjb22Pz5s3o3LkzSpcujR49eqBcuXJIS0vDP//8gx07dkgnQKlYsSJ69uyJlStXIi4uDrVr18alS5cQFBSENm3afPURH3nRpUsXjBs3Dm3btsWwYcOQlJSEZcuWwcnJSWYSHl9fX5w7dw7NmzeHjY0N3rx5g6VLl6JYsWLS7ElO5s6di6ZNm8Ld3R19+/ZFcnIyAgMDpY+DyC8qKir4448/vluvRYsW8PX1Re/evVGjRg3cunULwcHB0uzaR/b29jAyMsLy5cuhr68PXV1duLq6ws7OTq64Tp06haVLl2LKlCnSx1+sW7cOderUwaRJk3LMln1P69atMW3aNJw9exaNGjUCkNX5eP/+fbZhmR+5ubnBzMwMwcHB6Ny5M8aMGYOdO3eiY8eO6NOnD6pUqYLY2Fjs378fy5cvR8WKFdGjRw9s2LABo0aNwqVLl+Dp6YnExEScOHECQ4YMQevWrWFoaIiOHTsiMDAQEokE9vb2OHjwoFzDTUuVKgV7e3t4eXnhxYsXMDAwwK5du3IcZhwQEICaNWuicuXKGDBgAOzs7PDkyRMcOnQI169fl6nbo0cPdOjQAQAwbdo0mWV79uxB7969sW7dum9ORGRmZoY+ffpg9erVqF+/Ptq1a4f3799j6dKlSE5OlnYqdXR00KZNm2zr7927F5cuXcq2zNvbG0FBQXj8+LH0ubw1atRApUqVULVqVRgaGuLq1atYu3YtihcvLvP83ZYtW6Js2bLw9fXF06dP4ebmhgcPHmDx4sWwsrJC3759s8WRkZGBESNGYMyYMTL3XXfo0AFjx46FmZkZnj59Kv17+Nzx48fh4eEBExOTr7YTEVGhJcLMu0RE+er+/ftC//79BVtbW0FDQ0PQ19cXPDw8hMDAQCElJUVaLz09XZg6dapgZ2cnqKurC8WLFxe8vb1l6ghC1mNYmjdvnm0/Xz7+42uPYREEQTh27JhQrlw5QUNDQ3B2dhY2bdqU7TEsJ0+eFFq3bi1YW1sLGhoagrW1tdC1a1fh/v372fbx5aMsTpw4IXh4eAja2tqCgYGB0LJlSyE0NFSmzsf9ffmYl4+Px3j8+PFX21QQcvd4i689hmX06NGClZWVoK2tLXh4eAgXLlzI8fEp+/btE8qUKSOoqanJHGft2rWFsmXL5rjPz7cTHx8v2NjYCJUrVxbS09Nl6o0cOVJQUVERLly48M1j+JoKFSoIffv2lb5v2bKloKWlJSQmJn51nV69egnq6upCdHS0IAiCEBMTIwwdOlQoWrSooKGhIRQrVkzo2bOndLkgZD0eZeLEidLz0tLSUujQoYPw8OFDaZ2oqCihffv2go6OjmBsbCwMHDhQuH37do6PYfna/1loaKjQoEEDQU9PTzA1NRX69+8v3LhxI8fz6/bt20Lbtm0FIyMjQUtLS3B2dhYmTZqUbZupqamCsbGxYGhoKCQnJ8ssk+cxLOnp6UJgYKDg4uIi6OnpCXp6ekLdunVlHo/0NV875o+PpPn8PJ84caLg4uIiGBoaCurq6kKJEiWEwYMHC69evcq2fmxsrDBy5EjByclJ0NTUFExNTYUuXboIjx49yjGOJUuWCMWKFct2fqSnpwujRo0STE1NBRsbGyEoKEhmeVxcnKChoSGsXr36u8dKRFQYSQRBjlkniIiIflIbN27Eb7/9hoiICOkjc0jWhw8fYG1tjZYtW2a755dyZ+HChZgzZw4ePnwo98RbRESFAe8BJSIiyoXu3bujRIkSOU44RFn27t2LqKgomYmNKPfS09Ph7++PP/74g51PIlJazIASERHR/+XixYu4efMmpk2bBlNTU5l7m4mIiD7HDCgRERH9X5YtW4bBgwfD3NwcGzZsEDscIiIqwJgBJSIiIiIiIoVgBpSIiIiIiIgUgh1QIiIiIiIiUgh2QImIiIiIiEgh1MQOgPKHbsd1YodQ4Lze1EvsEAqcTN4Cno2qikTsEAocFQnb5Etskux4OclOABvlS0mpGWKHUODwcyc7Yx1VsUPINe1KQ0Xdf/K1xaLuPy+YASUiIiIiIiKFYAeUiIiIiIiIFIJDcImIiIiIiPJCwnyevNhiREREREREpBDMgBIREREREeUFZ6WTGzOgREREREREpBDsgBIREREREZFCcAguERERERFRXnASIrmxxYiIiIiIiEghmAElIiIiIiLKC05CJDdmQImIiIiIiEgh2AElIiIiIiIiheAQXCIiIiIiorzgJERyY4sRERERERGRQjADSkRERERElBechEhuzIASERERERGRQrADSkRERERERArBIbhERERERER5wUmI5MYWIyIiIiIiIoVgBpSIiIiIiCgvOAmR3JgBJSIiIiIiIoVgB5SIiIiIiIgUgkNwiYiIiIiI8oKTEMmNLUZEREREREQK8dN1QJ88eQKJRILr16//39vq1asX2rRp839vh4iIiIiICiGJRNxXIfTTdUCLFy+OyMhIlCtXTuxQCiUVFQkmda6EO0s6IDr4V9wKbI9x7SvK1GlV3Qb7/2iEiLVdkbijNyrYFvnmNvdMaIjEHb3RolqJ/AxdYdauXoFfu3aAp1tlNKhdA6OG/4Ynjx/J1ElNTcWsGb6o5+mKmq6VMWbk74iJiRYpYsXYuX0LunZojTo1qqJOjaro82sX/H3+nHR5amoqZs/0RYNabqjlVgVjRw1T+ja5EnIZw4cOQqN6nqhcvhROnzwhs3zKxPGoXL6UzOu3Qf1EilZ8a1evhEs5Z8yZNUPsUES1ZtUKdOvUHu7VKqGOpztG/D4k2zXmZ8bz5JPExATMnTUTTRvWg1uViujZvQvu3LoldlgKsWbFEnhUKSvz6tquBQAg8uWLbMs+vk4d/1PkyBVnw9pVcKtUBgvm+knLBvfrCbdKZWRes6f7iBckKaWf7h5QVVVVWFpafnW5IAjIyMiAmtpP1zS5Mqp1efRrVAoDlvyFsGdxqGxvguVDPBGflIZlR8IAALpaavjn7mvs+ucxlg6u+c3tDW1eBoKgiMgV52rIZXTs0g1ly5ZHRkYGFgcswG+D+mHnnoPQ1tEBAMyf44fzf53FrHmLoK+vh9kzp2HMyN+xdsMWkaPPP+bmlhg6fBSKl7CBIAg4dGAfvIYPxaZtu2Dv4IgFc/1w/q9z8Ju7EHr6+pjrNw1jRw3DmqDNYoeeb1KSk+HkVAqt27aH14jfc6xTw8MTPtNnSt9rqGsoKrwC5fatm9i5YyucnJzFDkV0IZcvoXPX7ihbvjwyPmQgcJE/BvXvi937D0Hnv2vMz4rniSzfyZPw4EE4pvvNhpm5OQ4f2I9B/Xtj175DMLewEDu8fGdn74BFS1dL36uqZn23M7ewxP4/z8jU3bd7BzZvXAc3j29/b1EWoXduYc+u7XBwzP630rpdRwwYPFT6XktLW5Gh0U9AKTOgR48eRc2aNWFkZAQTExO0aNECDx8+BJB9CO6ZM2cgkUhw5MgRVKlSBZqamjh//jx8fHzg4uKCFStWoHjx4tDR0UGnTp3w7t27PO33833v3r0bdevWhY6ODipWrIgLFy7IbOf8+fPw9PSEtrY2ihcvjmHDhiExMfHHN1QeuDmb41BIBP68+hwRUQnY++9TnLzxAlUdzKR1tpx7iFk7b+D0rchvbquCbREMa1kOg5edz++wFWrx8tVo1bod7B0c4eRcClOn+eFV5EuEhd4BALx//x779uzCKK9xqO7qhtJlymHKND/cuH4Nt25cFzf4fFSrTl14eNZGCRtb2NjaYcjvI6Cjo4PbN28g4f177NuzGyO9xqGaqxtKlymLyb4zcfP6Ndy6eV3s0PONh2ct/DZsBOrVb/jVOhoaGjA1NZO+DAwNFRhhwZCUlIgJ48dgss906Bv8fMf/pWUr16B123ZwcHCEc6lS8J0xC5GfXWN+VjxPZKWkpODkiWMYMcoLVapWQ4kSNhj02+8oXqIEdmxT3h87P6eqqgoTUzPpy8jYOMdyE1MznDtzEvUbNoGOjq7IUee/pKRETJkwFt6TpkLfwCDbci0tLZm20dXTEyHKQkSiIu6rECqcUX9HYmIiRo0ahZCQEJw8eRIqKipo27YtMjMzv7rO+PHjMWvWLISFhaFChQoAgAcPHmD79u04cOAAjh49imvXrmHIkCH/934nTpwILy8vXL9+HU5OTujatSs+fPgAAHj48CGaNGmC9u3b4+bNm9i2bRvOnz+PoUOH5rRLhfv33hvUKWcFB6usC1Z5G2PUKGWBY9eey7UdbQ1VrB1eGyNX/4vXccn5EWqBkZDwHgCkHYew0Dv48CEdrm41pHXs7ErC0soaN5W4s/W5jIwMHDtyCMnJSShf0UXaJtVd3aV1bO1KwtLKSqk75bkREnIJ9WvXQNuWTTBzmg/i4t6KHZLCzZzuC89ateHmXuP7lX9CCe9lrzE/K54nsjIyPiAjIwMampoy5ZqaWrh29YpIUSnW84gItGpcBx1bNYbPxLF4Ffkyx3p3w+4g/N5dtGjdTsERimOe33R4eNZGdbec/1b+PHwQjevWQLcOrbA0wB8pycr9PY0UTynHmbZv317m/dq1a2FmZobQ0FDofeVXHF9fXzRsKJuFSElJwYYNG1C0aFEAQGBgIJo3b4758+fnOIz3W/v9/J5TLy8vNG/eHAAwdepUlC1bFg8ePECpUqXg5+eH7t27Y8SIEQAAR0dHBAQEoHbt2li2bBm0tLTka4wfbP7emzDQUce1he2QkSlAVUWCqVuuYNt5+e4/mt3LFRfvvcGhkIh8irRgyMzMxLw5M1GxUmU4ODoBAGKio6Curp7tV0cTExPERCv3PY8Pwu+jz69dkZaWCm0dHcxdEIiS9g64f+9ujm1SpIip0rfJt9So6Yl6DRrBumhRPH/2DIsDFuD3wQOwftNWqKqqih2eQhw9fAh3w0IRvHWn2KEUSJmZmZgzeyZcKlWG43/XmJ8Rz5PsdHX1UKGiC1YtXwq7kiVhYmKKo4cP4eaN6yheQjnmXPiWMuUqYKLPDJSwtUVMVBTWrlqGIf16YOP2fdDVlc1yHty7C7Z2JVG+YiWRolWc40cP497dUKzdtD3H5Y2bNoellTVMzczxIPwelizyx9OnTzB7foCCIy1ECulEQGJSyg5oeHg4Jk+ejIsXLyI6OlqagYyIiECZMmVyXKdq1arZykqUKCHtfAKAu7s7MjMzce/evRw7oN/a7+cd0I8ZVgCwsrICALx58walSpXCjRs3cPPmTQQHB0vrCIKAzMxMPH78GKVLl86239TUVKSmpsqUCRnpkKiq53is/4/27nboXNMevRedRdjzOFSwLYLZvaoj8m0ygs8+yNU2mlUtjtrlrFBj7L4fHl9BM2uGLx4+CMea9cp7H6M8bGxtEbx9NxISEnDy+J/wmeSNFWs2iB1WgdW4aXPpvx2dnOHo5IxWzRoi5PIluLq5f2NN5fAqMhJzZs3A8lVroflFFoeyzJw+FQ/Dw7F+4897jeF58nXT/ebAZ/IENK5XG6qqqihVugyaNG3+UwzXdvfwlP7bwdEZZcpXQPvmDXHq+FG0bPMpYZCakoLjRw+jV79BYoSpUK9fRcJ/rh8Clq3+6t9Km/adpP92cHSCqakZhg7sg+fPIlCsuPL/cEGKoZQd0JYtW8LGxgarVq2CtbU1MjMzUa5cOaSlpX11nS9/DcvP/aqrf+oYSv771eRjZzUhIQEDBw7EsGHDsm2/xFd+sfTz88PUqVNlytRKt4JG2Tb/z+HkaMav1TB/703s/OcxAOBOxFsUN9XD6Lblc90BrVPOCiUt9PFyfXeZ8s1edfF32Gs09Tn6w+MWw+yZvjh/7gxWrdsEi89+sDAxNUN6ejrex8fLZPxiYmJgYmoqRqgKo66ugeIlbAAApcuUReidW9gavBENGzfNsU1iY6OVvk3kUax4cRgZG+NZxNOfogMaGnoHsbEx6Nrp07C4jIwMXL1yGdu2BOPS1Vs/TSY4JzOn++Lc2TNYGyR7jfnZ8Dz5uuIlSmDN+k1ITkpCQmICzMzMMW70SBQtVlzs0BROX98AxW1s8PyZ7Mir0yePISUlGU1atBIpMsW5G3YHb2Nj0KtbB2lZRkYGrl8Nwc5tm3Hu4vVsfytly2clTdgBpR9J6TqgMTExuHfvHlatWgVPz6xfv86fz9skNxEREXj58iWsra0BAP/++y9UVFTg7Jx9xrAftd/KlSsjNDQUDg4OuV7H29sbo0aNkimz7LVV7n3nhramKjK/mLY2MzMTKnIMP5i/9xbWn7wvU3bZvy3Grb+Ew1ee/ZA4xSQIAub4TcPpUyewcs0GFC1WTGZ56TJloaamjksXL6B+w8YAgCePH+FV5EtUqOAiQsTiETIFpKWnSdvk8qV/Ua9BIwDAkyeP8SoyEuUruogbZAHy+tUrvIuLg5mZudihKISrmxt27jkgUzb5D2/Y2ZVE7779f9pOhSAI8JsxDadOHsea9RtR7CfsTHyO58n3aevoQFtHB/Hv3uGff85jxCgvsUNSuKSkRLx4/gxNmsl2NA/u242atevC2Pjbj4xTBlWruyN4h+zos+lTJsLGzg6/9uqX49/K/Xt3AWT9eE5fUUgnAhKT0nVAjY2NYWJigpUrV8LKygoREREYP358nralpaWFnj17Yt68eYiPj8ewYcPQqVOnHIff/qj9jhs3Dm5ubhg6dCj69esHXV1dhIaG4vjx41i8eHGO62hqamYbSpEfw28B4MiVZxjbriKeRSci7FkcKtoVwdCW5bDxVLi0jrGeBoqb6sHKOOtxAI7WWRNjvI5Llnl96Vl0Ip6+SciXuBVp1gxfHD1yEP6LlkBHVxfR0VEAAD09fWhpaUFfXx+t27aH/7zZMDA0hJ6eHub4TUeFii5K3dlavMgfNWp6wtLSGklJiTh6+CCuhFxC4LJV0NPXR+u27bBg3iwYGBhCV08Pc2dNR/mKLiivxJ3ypKREPIv49Gv8ixfPce9uGAwMDWFoaIgVy5agfoNGMDU1xbNnz7DIfy6KlygB95/kMQG6unrSe6c/0tbWgaGRUbbyn8nMaVNx5PBBLAxcCl0dXURH/XeN0dcXfZ4AMfA8+bp//v4LggDY2trhWcRTLJg/F3Z2JdGqjfJPtrN4wVx41KoDSytrREe9weoVS6CqoooGTZpJ6zx/9hTXr4ZgXsAyESNVHF1dXdg7OMqUaWlrw9DQCPYOjnj+LALHjhxCjZq1YGBkhAf372HR/NmoVLkqHPloI/qBlK4DqqKigq1bt2LYsGEoV64cnJ2dERAQgDp16si9LQcHB7Rr1w7NmjVDbGwsWrRogaVLl+brfitUqICzZ89i4sSJ8PT0hCAIsLe3R+fOneWOPz+MXvMvJnepjIX93GFmqIXI2CSsPX4PfjuvS+s0r1oCK377dO/FhpF1AAAztl/DzB3Xoex2bs+a3n5Anx4y5VOmzUSr/2bYGz3WGyoqKhg7ajjS0tLg7lET4ydOVnisivQ2NgY+f4xHdFQU9PT04eDkhMBlq+Dq7gEAGDnGGxIVFYwbndUmbjU8ME7J2yT0zm0M6NNT+t5/7iwAQMtWbeA9yQfh9+/h4P69eB//HmbmZnBz98CQocOhofFzPguUsmz/7xEafXv9KlPuO90Prdsqf8eCci/hfQICF/rj9etXMDQ0Qv2GDfHbsJEytwIpqzdvXmPKhDGIfxcHI+MiqOBSGSvWb5bJdB7ctwfm5hao7uYhYqQFh7q6Oi5fvICtmzcgJTkZ5haWqFO/Ifr8BPfH/l+YAZWbRBC+GE9JAAAfHx/s3btX+rzQwka34zqxQyhwXm/qJXYIBc6Xw6kJUFXhbHZfkmeI/c+CTZIdLyfZCWCjfCkpNUPsEAocfu5kZ6xTeIbOa9f2FXX/yWcL34/17LITERERERGRQijdEFwiIiIiIiKFYAZbbsyAfoWPj0+hHX5LRERERERUEDEDSkRERERElBechEhubDEiIiIiIiJSCHZAiYiIiIiISCE4BJeIiIiIiCgv+FwuuTEDSkRERERERArBDCgREREREVFecBIiubHFiIiIiIiISCHYASUiIiIiIiKF4BBcIiIiIiKivOAkRHJjBpSIiIiIiIgUghlQIiIiIiKivOAkRHJjixEREREREZFCsANKRERERERECsEhuERERERERHnBSYjkxgwoERERERERKQQzoERERERERHnBSYjkxhYjIiIiIiIihWAHlIiIiIiIiBSCQ3CJiIiIiIjygpMQyY0ZUCIiIiIiIlIIZkCJiIiIiIjygpMQyY0tRkRERERERArBDigREREREREpBIfgEhERERER5QUnIZIbO6BKKmZLb7FDKHCMqw8TO4QC5+2lALFDICIlwe9g2UnARvmSjqaq2CEUOClpmWKHQKRQ7IASERERERHlBSchkhtbjIiIiIiIiBSCHVAiIiIiIiJSCA7BJSIiIiIiygsOwZUbW4yIiIiIiIgUghlQIiIiIiKivOAU4HJjBpSIiIiIiIgUgh1QIiIiIiIiUggOwSUiIiIiIsoLTkIkN7YYERERERERKQQzoERERERERHnBSYjkxgwoERERERERKQQ7oERERERERKQQHIJLRERERESUF5yESG5sMSIiIiIiIlIIZkCJiIiIiIjygpMQyY0ZUCIiIiIiIlIIdkCJiIiIiIhIITgEl4iIiIiIKA8kHIIrN2ZAiYiIiIiISCGYASUiIiIiIsoDZkDlxwwoERERERERKQQ7oERERERERKQQHIJLRERERESUFxyBKzdmQH+g9evXw8jI6Jt1fHx84OLiIn3fq1cvtGnTJl/jIiIiIiIiKggKdQc0Nx2+gsbLywsnT54UO4x8tWbVCnTr1B7u1Sqhjqc7Rvw+BE8ePxI7rHylp6OJuV7tcO+QD2L/mYfT60aiSpkS0uUTBzbF9V0TEf33XLw8MwuHlv2GauVsZLbhUMIM2/3749nJmXh9bg5OrhmOWlUdFX0oCrd1czCaNqyHapXKo3uXjrh186bYIYmObZId2yQ7tsknP+PnTm7xPPkkIyMDSwIXoXnj+nCrUhEtmzTEyuVLIQiC2KEpxOrli+FeuYzMq3O75tLlqampmOs3DY3ruqOeRxV4ew1HbEy0iBEXDhKJRNRXYVSoO6CFkZ6eHkxMTMQOI1+FXL6Ezl27Y+OW7Vixah0+fPiAQf37IikpSezQ8s2yyV1Rz9UZfSZtRNXOs3Di37s4tOw3WJsZAgAePH2DkbN3oGqnWajfZyGevozFgSVDYGqkJ93G7kUDoaaqgqaDFqNG97m4Gf4SuxcNgIWJvliHle+OHjmMeXP8MHDIb9i6Yw+cnUth8MC+iImJETs00bBNsmObZMc2kfUzfu7kBs8TWevXrMLObVswfsIk7N5/CMNGjUbQ2tXYErxR7NAUpqS9Aw4eOyt9rVizSbps0fxZ+Puv05gxewGWrtqA6Kg3GO81XMRoSVmJ2gE9evQoatasCSMjI5iYmKBFixZ4+PAhAODMmTOQSCSIi4uT1r9+/TokEgmePHmCM2fOoHfv3nj37p30FwAfHx8AwNu3b9GjRw8YGxtDR0cHTZs2RXh4uHQ7HzOnBw8ehLOzM3R0dNChQwckJSUhKCgItra2MDY2xrBhw5CRkSFd73vb/Wjv3r1wdHSElpYWGjdujGfPnkmXfTkE90uZmZnw8/ODnZ0dtLW1UbFiRezcuTOPLSyOZSvXoHXbdnBwcIRzqVLwnTELkZEvERZ6R+zQ8oWWpjra1KuIiYv24e+rD/HoWTRmrDiCh8+j0b9jTQDAtqNXcPrSfTx5EYOwR68wzn8PDPW1Uc7JGgBgYqQLRxtzzF9/HLfDX+LhsyhMCtgPXW1NlLG3EvPw8tXGoHVo16ET2rRtD3sHB/wxZSq0tLSwd/cusUMTDdskO7ZJdmwTWT/b505u8TyRdeP6NdSuWx+etevAumgxNGzUBG41PHDn1i2xQ1MYVVVVmJiaSV9GxsYAgIT373Fg7y4MGzUOVau7oVSZspjoMwO3blzD7Zs3RI6alI2oHdDExESMGjUKISEhOHnyJFRUVNC2bVtkZmZ+d90aNWpg4cKFMDAwQGRkJCIjI+Hl5QUg677KkJAQ7N+/HxcuXIAgCGjWrBnS09Ol6yclJSEgIABbt27F0aNHcebMGbRt2xaHDx/G4cOHsXHjRqxYsUKm85fb7c6YMQMbNmzA33//jbi4OHTp0iXXbeLn54cNGzZg+fLluHPnDkaOHIlffvkFZ8+ezfU2CpqE9+8BAAaGhiJHkj/UVFWgpqaKlLQPMuUpKWmo4VIyW311NVX0bVcDce+TcOv+CwBATFwi7j1+jW7Nq0NHSwOqqiro194Dr2PicS3sWbZtKIP0tDSEhd6Bm3sNaZmKigrc3Grg5o1rIkYmHrZJdmyT7Ngm36fsnzu5wfMku4oulXDp4gU8ffIYAHDv7l1cv3oVHp61RI5McZ5FRKBlo9po37IRpkwcg1eRLwEAd8Pu4MOHD6jm6i6ta2tXEpaWVrh187pI0RYOhWUIbkZGBiZNmiRNctnb22PatGkyQ9AFQcDkyZNhZWUFbW1tNGjQIFuyLTY2Ft27d4eBgQGMjIzQt29fJCQkyNVmos6C2759e5n3a9euhZmZGUJDQ7+7roaGBgwNDSGRSGBpaSktDw8Px/79+/H333+jRo2si25wcDCKFy+OvXv3omPHjgCA9PR0LFu2DPb29gCADh06YOPGjXj9+jX09PRQpkwZ1K1bF6dPn0bnzp3l2u7ixYvh6uoKAAgKCkLp0qVx6dIlVK9e/ZvHlJqaipkzZ+LEiRNwd8+6AJQsWRLnz5/HihUrULt27e+2S0GTmZmJObNnwqVSZTg6OokdTr5ISErFvzcew7tfY9x79AqvY9+jU5MqcK1gh4fPoqT1mnqWxQa/XtDRUser6Hi0GLwUMXGJ0uXNBy/BNv9+iDo/B5mZAqLeJqD10OWIe58sxmHlu7dxb5GRkZFtSLqJiQke/6T3brFNsmObZMc2+baf4XMnN3ieZNe73wAkJCaibctmUFVVRUZGBn4bNgLNWrQUOzSFKFu+Av6YOgM2NnaIjo7CmpVLMbjvr9i0Yz9iYqKhrq4OfX0DmXWMTUx5H6iSmD17NpYtW4agoCCULVsWISEh6N27NwwNDTFs2DAAwJw5cxAQEICgoCDY2dlh0qRJaNy4MUJDQ6GlpQUA6N69OyIjI3H8+HGkp6ejd+/eGDBgADZv3pzrWETtgIaHh2Py5Mm4ePEioqOjpZnPiIgI6Ojo5GmbYWFhUFNTk3YAgayLrbOzM8LCwqRlOjo60s4nAFhYWMDW1hZ6enoyZW/evJFru2pqaqhWrZr0falSpWBkZISwsLDvdkAfPHiApKQkNGzYUKY8LS0NlSpV+up6qampSE1NlSkTVDWhqan5zf0pwszpU/EwPBzrN+b+pCyM+kzaiBVTuuHRsen48CED1+8+x/Y/r6BS6eLSOmcvh8O162yYGumhd1t3bJrdG7V6zEfU26xfjRaM74io2Pdo0HcRklPT0auNO3YtHICav87Dq+h4sQ6NiKhQ+Vk+d0h+x44ewZGDBzBz9jzYOzjg3t27mDd7JszMzdGqdVuxw8t37h6fMr0OTs4oW74C2jZvgJPHjxaI74yFVWGZCOiff/5B69at0bx51sRTtra22LJlCy5dugQgK/u5cOFC/PHHH2jdujUAYMOGDbCwsMDevXvRpUsXhIWF4ejRo7h8+TKqVq0KAAgMDESzZs0wb948WFtb5yoWUYfgtmzZErGxsVi1ahUuXryIixcvAsjqcKmoZIX2eVr486Gu/y91dXWZ9xKJJMey3AwH/lE+pq8PHTqE69evS1+hoaHfvA/Uz88PhoaGMq+5s/0UFfZXzZzui3Nnz2DVuiBYfJalVkaPn0ejUf8AmNTwgmOzKfDsMR/qaqp4/PzTRA9JKWl49Cwal249wWDfLfiQkYGebbIy3XWqO6GZZ1n08A7ChRuPcf3uc4yYtQPJqWn4pcW3f7gorIyNjKGqqpptMoyYmBiYmpqKFJW42CbZsU2yY5t83c/0ufM9PE+yWzh/Lnr3648mzZrD0ckZLVq1RvcevbBu9UqxQxOFvr4BSpSwxfNnT2FiYor09HS8fy/7g/fbmGgUMfk5zxdlU6NGDZw8eRL3798HANy4cQPnz59H06ZNAQCPHz/Gq1ev0KBBA+k6hoaGcHV1xYULFwAAFy5cgJGRkbTzCQANGjSAioqKtB+XG6J1QGNiYnDv3j388ccfqF+/PkqXLo23b99Kl5uZmQEAIiMjpWXXr1+X2YaGhobMJEEAULp0aXz48EGmET7uq0yZMnmON7fb/fDhA0JCQqTv7927h7i4OJQuXfq7+yhTpgw0NTUREREBBwcHmVfx4sW/up63tzfevXsn8xozzjuPR/r/EwQBM6f74tTJ41i1NgjFin09dmWTlJKGV9HxMNLXRgP3Ujh49usTG6hIVKCpkTUIQUdLAwCy/eCRmSlAolI4flmTl7qGBkqXKYuL/16QlmVmZuLixQuoUPHrGX9lxjbJjm2SHdsku5/5c+dreJ5kl5KSDIlE9quvioqKQpMNBUlSUiKeP4+AqakZSpUuCzU1NYRc+le6/OmTx3j1KhLlK7iIFyR9V2pqKuLj42VeX46MBIDx48ejS5cuKFWqFNTV1VGpUiWMGDEC3bt3BwC8evUKQNYI0M9ZWFhIl7169Qrm5uYyy9XU1FCkSBFpndwQbQiusbExTExMsHLlSlhZWSEiIgLjx4+XLv/Y6fLx8cGMGTNw//59zJ8/X2Ybtra2SEhIwMmTJ1GxYkXo6OjA0dERrVu3Rv/+/bFixQro6+tj/PjxKFq0qDSdnBe53a66ujp+//13BAQEQE1NDUOHDoWbm9t3h98CgL6+Pry8vDBy5EhkZmaiZs2aePfuHf7++28YGBigZ8+eOa6nqZl9uG3KhxyrKsTMaVNx5PBBLAxcCl0dXURHZd0HqaevLx0/rmwauJeCRCLB/SevYV/cDDNHtMb9J2+wYf+/0NHSwLh+jXDo7G28in4HEyM9DOzkCWtzQ+w+njURxMWbj/E2PgmrfX/BzJVHkZyajj7tasC2qAmO/qW8szj+2rM3Jk0Yh7Jly6Fc+QrYtDEIycnJaNO2ndihiYZtkh3bJDu2iayf8XMnN3ieyKpVpy7WrFoOKysr2Ds44G5YGDZtWI82bdt/f2UlELBgDmrWqgsrK2tERb3B6uWLoaqiioZNmkNPXx8t27RHwPzZMDAwhK6uHubPmYFyFVxQrkJFsUMv0MQeguvn54epU6fKlE2ZMkX6dJCPtm/fjuDgYGzevBlly5bF9evXMWLECFhbW3+1j5FfROuAqqioYOvWrRg2bBjKlSsHZ2dnBAQEoE6dOgCyOnJbtmzB4MGDUaFCBVSrVg3Tp0+XTvYDZKWSBw0ahM6dOyMmJkba2OvWrcPw4cPRokULpKWloVatWjh8+HC2Ibbyys12dXR0MG7cOHTr1g0vXryAp6cn1qxZk+t9TJs2DWZmZvDz88OjR49gZGSEypUrY8KECf9X7Iq0fdsWAEDfXr/KlPtO90NrJf3QM9TThu/QlihqYYTYd4nYd+oGpiw5iA8fMqGqkglnWwv80qI6TIz0EPsuESF3ItCg7yKEPcr6tSgmLhGthy6Dz9AWOLLid6irqSLsUSQ6jlyFW+EvRT66/NOkaTO8jY3F0sUBiI6OgnOp0li6YjVMftLhYQDbJCdsk+zYJrJ+xs+d3OB5ImvchD+wNDAAM6f74m1sDMzMzNGhY2cMGDxE7NAUIur1a0zx9sK7d3EwMi6Cii6VsSpoC4yNiwAAho8eD4lEBd5jhiM9LR2u7h4Y4z1J5Kjpe7y9vTFq1CiZspzu6R0zZow0CwoA5cuXx9OnT+Hn54eePXtKJ3V9/fo1rKw+PQLw9evX0kdIWlpaSufH+ejDhw+IjY2VmRT2eyTC5zdZktIQMwNaUBlXHyZ2CAXO20sBYodAREQ/kUx+7cwmJe3nHAL8LUV0VcUOIdcMu20Udf/vNv/6/UrImjx1+vTpGDx4sLTMz88P69atw/379yEIAqytreHl5YXRo0cDAOLj42Fubo7169dLJyEqU6YMQkJCUKVKFQDAsWPH0KRJEzx//jzXkxCJOgsuERERERER5a+WLVtixowZKFGiBMqWLYtr167B398fffr0AZA1lHjEiBGYPn06HB0dpY9hsba2Rps2bQBkzYnTpEkT9O/fH8uXL0d6ejqGDh2KLl265LrzCbADSkREREREpNQCAwMxadIkDBkyBG/evIG1tTUGDhyIyZMnS+uMHTsWiYmJGDBgAOLi4lCzZk0cPXpU5l764OBgDB06FPXr14eKigrat2+PgAD5RtRxCK6S4hDc7DgENzsOwSUiIkXiENzsOAQ3u8I0BNeo+yZR9x8X/Iuo+88LUZ8DSkRERERERD8PDsElIiIiIiLKA7Efw1IYMQNKRERERERECsEOKBERERERESkEh+ASERERERHlAYfgyo8ZUCIiIiIiIlIIZkCJiIiIiIjygBlQ+TEDSkRERERERArBDigREREREREpBIfgEhERERER5QVH4MqNGVAiIiIiIiJSCGZAiYiIiIiI8oCTEMmPGVAiIiIiIiJSCHZAiYiIiIiISCE4BJeIiIiIiCgPOARXfsyAEhERERERkUIwA0pERERERJQHzIDKjxlQIiIiIiIiUgh2QImIiIiIiEghOASXiIiIiIgoLzgCV27MgBIREREREZFCMANKRERERESUB5yESH7MgBIREREREZFCsANKRERERERECsEhuEoq7UOm2CEUOG8vBYgdQoFTYsB2sUMocB4u7SB2CAVOhiCIHUKBI+GsE9mkfsgQO4QCR0+TX7O+xOGK2WmqMx9UmPGclh/PeCIiIiIiIlII/jRHRERERESUB8yAyo8ZUCIiIiIiIlIIdkCJiIiIiIhIITgEl4iIiIiIKA84BFd+zIASERERERGRQjADSkRERERElBdMgMqNGVAiIiIiIiJSCHZAiYiIiIiISCE4BJeIiIiIiCgPOAmR/JgBJSIiIiIiIoVgBpSIiIiIiCgPmAGVHzOgREREREREpBDsgBIREREREZFCcAguERERERFRHnAIrvyYASUiIiIiIiKFYAaUiIiIiIgoL5gAlRszoERERERERKQQ7IASERERERGRQnAILhERERERUR5wEiL5MQNKRERERERECsEMKBERERERUR4wAyo/ZkCJiIiIiIhIIdgBJSIiIiIiIoVgB/QHqVOnDkaMGPHV5ba2tli4cKHc2/Xx8YGLi0ue4yIiIiIiovwhkUhEfRVGvAdUQS5fvgxdXV2xw8gXO7dvwa7tWxH58gUAoKS9A/oOHAKPmrUAADN9p+DSxQuIjnoDbR0dVKhYCb+PGA1bu5Jihq1Qa1atwMnjx/D48SNoamnBxaUSRozyUto2CJnTHCVMs5/va089wPhNVwEAVe1N4N2uHCqXNEFmpoDbEXHo7H8OKekZ0voNKlhhdKsyKFPMEKnpmbhwLwo9F/+tsOPIT+vWrMTpk8fx5PEjaGpqoYLLf38XtnYAgJcvXqBVswY5rjtr7gI0aNREkeEqxK7tW7F7x1a8/PxaMmAwatSshZcvXqBt84Y5rjdzjj/qK2F7AFnX1907Pl1f7ewd0G/AENT47/r6kSAIGDF0IC78/Rfm+AeiTr2czx1lEfXmNZYF+uPiP+eRkpKCYsVKwHvKNJQqUw4A4Fm1XI7rDR42Ct169FFkqApzJeQyNqxfg9DQO4iOioL/wsWoW//TebB8aSD+PHIYr16/grqaOkqXKYuhw0agfIWKIkatWMuWBGLFssUyZbZ2dth74KhIESnex/Mk7L/zZP4X5wkAPHr0EAEL5uFqyGV8yMhAyZL2mLsgAFZW1iJFTcqGHVAFMTMz++by9PR0qKurKyiaH8vc3BJDh49C8RI2EAQBhw7sg9fwodi0bRfsHRxRqkxZNGneApaW1oiPj8PKZUswdFA/7Dt8HKqqqmKHrxAhly+hc9fuKFu+PDI+ZCBwkT8G9e+L3fsPQUdHR+zwfrjG005A9bNf5UoVM8BOrzrYf/kZgKzO59aRnlh0+C4mBF/Dh0wBZYsbIlMQpOu0qFIU83tWxczdt/FX2GuoqaqgVFEDhR9LfrkachkdO3dDmbLlkJGRgSWBCzB0UF/s2H0Q2jo6sLC0xNGT52TW2bNzOzYGrUWNmp4iRZ2/zC0sMGTYSBQvYQMAOLR/L8aMGIqNW3fBxq4kDp84K1N/z64dCA5aC3clbQ8AsLCwxG/D/ru+QsCh/fvg9V+b2Ds4Sutt2RSEwvk7uPzex7/DkL6/olLV6pi7aDmMjI3x/NlT6Bt8uj7sPXpGZp1///kLs6dNRp16Of+IoQySk5Ph5FQKrdu2x+gRv2dbbmNji3ETJqFYseJITU3Bpo1BGDKwL/YdOoYiRYqIELE47B0csWL1Oun7n+V7yEcpn50nXjmcJ8+eRaBvj25o3a4DBg35Hbp6enj04AE0NTRFiLZwKKxZSDGxA/oDffjwAUOHDsXGjRuhrq6OwYMHw9fXFxKJBLa2thgxYoR0mK5EIsHSpUtx5MgRnDx5EmPGjIGPjw9mzZqFBQsWICkpCZ06dfpux7UgqFWnrsz7Ib+PwK7tW3H75g3YOziiXYdO0mXWRYti8NDh6NaxDSJfvkCx4iUUHa4olq1cI/Ped8Ys1PV0R1joHVSpWk2kqPJPzPtUmfe/VyyFx6/f4597UQAA3y4uWHXyAQIP35XWefjqvfTfqioSTO9aCVN33MTmvx5Ly++/jM/nyBUncNkqmfc+vn5oWNcDYWF3ULlKNaiqqsLUVPbv//Spk2jQqAl0dJRzNIVnbdlryeDfR2D3jq24fesmSjo4wuSL9jh76gTqK3F7ANnbZIi0TW5IO6D374Zh88b1WL95B5o1qJXTZpRKcNBamFtYYsKU6dIy66LFZOqYmJrKvD9/9jQqVa0O62LFFRKjGGp61kJNz6///zdt3lLm/egx47F3906E378HVzf3/A6vwMjp2voz8fCsBY9vnCdLAhbCw7M2RowaIy0r/pN8VyPF4T2gP1BQUBDU1NRw6dIlLFq0CP7+/li9evVX6/v4+KBt27a4desW+vTpg+3bt8PHxwczZ85ESEgIrKyssHTpUgUewf8vIyMDx44cQnJyEspXdMm2PDkpCQf27YZ10WKwsLRUfIAFRML7rM6WgaGhyJHkP3VVFXRws8Hm808AAKb6mqhqb4Lo+BQcmlAPdxa0wt5xdeDq+OkLYwUbY1gX0UGmIODklIa45d8SW0Z6KlUG9EsJCf+dEwY5nxNhoXdw/14YWrftoMiwRJORkYFjRw8jOTkZ5XIYIpjVHnfRqk17EaITR1ab/Hd9reACICubMWnCGIzxnvTTfKk+f+40nEuXxaRxo9CyYS306dYB+/fs/Gr92JhoXDh/Di1at1NglAVbenoadu/cBj19fTg5lxI7HIWKiHiKhnVronmT+vAeNxqRkS/FDqnAyMzMxPlzZ2BjY4shA/uifu0a6NGtE06fPCF2aKRkmAH9gYoXL44FCxZAIpHA2dkZt27dwoIFC9C/f/8c63fr1g29e/eWvu/SpQv69u2Lvn37AgCmT5+OEydOICUlRSHx/z8ehN9Hn1+7Ii0tFdo6Opi7IBAl7R2ky3ds24zABfORnJwEG1s7LFmxBurqGiJGLJ7MzEzMmT0TLpUqw9HRSexw8l3TytYw1FHH1r+zMpk2ZlnZqjGty8Jn+w3cjohDpxq22OlVG7Um/YnHbxI+1WlVFlO2XUdEdBIGN3bCnrF14T7hCOIS00Q7nvyQmZmJ+XP8UNGlMhy+ck7s27MTdiXtUdGlkoKjU6wH4ffRr0dXpKWlQVtbB7P9A2SuJR8d2LMLtiVLooKStweQ1SZ9e/x3fdXWwRz/T9fXBfNmoXxFF9SuW1/kKBUn8sVz7Nu1DZ2698CvvfvjbuhtLJrnB3V1dTRt0Tpb/SMH90NHVwe16ir3fbG5ce7saYwfMxopKckwNTPD8pVrYWxsLHZYClO+QgX4TveDra0doqOjsHzpEvTp0R079x6Arq6e2OGJLjY2BklJSVi3dhWGDB2O4SO98M/5v+A18nesXBOEKtWqix1iwcQRuHJjBvQHcnNzkxkH7u7ujvDwcGRkZORYv2rVqjLvw8LC4OrqKlPm7v79YTGpqamIj4+XeaWmpn53vR/JxtYWwdt3Y92mbWjfsQt8Jnnj0cMH0uVNm7XEpm27sGLtBpSwsYX3mJEKj7GgmDl9Kh6Gh2POvAVih6IQ3T1L4uStV3gdl/VDisp/fyMbzjzC1vNPcDsiDpO3XsfDV+/RzdNOps7CQ2E4eOUFbj59i+FrL0OAgFZVi+W8o0Js9kxfPHwYjplz5ue4PCUlBUePHELrnyDbZ2Nri43bdmPNxq1o16kzfCdPkLmWAFnt8eeRQz9N9tPG1habtu3G2o3b0L5TF0ydnHV9PXfmFEIu/YtRY7zFDlGhMjMz4VSqNAb+NgJOpUqjVbuOaNmmPfbt2p5j/cP796BhkxbQ1OQ9bNWquWLrzj1Yv3ELanh4YqzXCMTGxIgdlsLU9KyNRo2bwsm5FGp4eGLxspV4/z4ex44eETu0AkHIzAQA1KlTD7/06AXnUqXRu98AeNaug507toocHSkTdkBF9KNmxfXz84OhoaHMy3/urB+y7dxSV9dA8RI2WbPqDR8FRydnbA3eKF2up6+PEja2qFylGmbPX4gnjx/jzKmfb0jHzOm+OHf2DFatC/ophiAXM9FBrTLmCD73SFr2+l1WR/T+y3cyde9HxqNYEZ3/6iT/V+fTPZ9pHzLxNCoRRU2Ua9Km2TOn4fy5s1i+KggWFjmfEyeP/4mU5BQ0b5k9u6NsPr+W/DYs61qybfNGmTqnThxDSkoymuWQ7VJGX2uTkEv/4vnzZ6jv6Qr3KuXgXiVr5tfxXsMxqG8PkaPOPyamZrCxs5cps7EridevIrPVvXHtCiKePkbLNhx+CwDaOjooUcIGFSq6wMd3BlRV1bDnG8OXlZ2BgQFK2NjiWUSE2KEUCEbGxlBTU8s26sTOzh6vIrP/fVEWPoZFfhyC+wNdvHhR5v2///4LR0fHXM+wVrp0aVy8eBE9enz64vDvv/9+dz1vb2+MGjVKpixVEHdGXSFTQFp6zsMkBQEQICAtTbmGUX6LIAjwmzENp04ex5r1G1FMiSfC+FzXmnaIjk/F8ZufPrgiohMR+TYJ9lay93PaW+jj5K1XAIAbT94iJT0D9pb6uBgeDQBQU5WghIkunsckKe4A8pEgCJjjNx1nTp3AijVBKFrs65ndfXt3oVadujD+iWaq/CgzU0B6WrpM2YE9u+BZp95P2R5AVpukpaWh/+ChaN1O9p7grh1aY6TXeNT8YvIiZVK+YiU8e/pEpuzZ06ewtLLKVvfgvt1wLl0GDk4/132OuSVkZiL9J/os/lJSUiKeP3sG05Y/x/3T36OuroEyZcvhyZPHMuURT5/wESz0Q7ED+gNFRERg1KhRGDhwIK5evYrAwEDMn5/zkLqcDB8+HL169ULVqlXh4eGB4OBg3LlzByVLfvtZkZqamtmGFsWnZObpGPJi8SJ/1KjpCUtLayQlJeLo4YO4EnIJgctW4fnzZzj+5xG4uXvA2NgYr1+/RtDaVdDS1JQ+J/RnMHPaVBw5fBALA5dCV0cX0VFZs8Hq6etDS0tL5Ojyh0QCdPGwxbZ/niAjU5BZtuToPYxtXRZ3IuJw51kcOnnYwsFKH32X/gMASEj5gKAzDzG2dVm8jE3Cs5gk/NbEGQCkj3Ip7GbP9MXRI4cwf+Fi6OjqIjr6v3NCT/aceBbxFNeuhGDRkhVihaowSwL8UcOjFiwsrZCUlIg/jxzE1ZBLWLT004zBzyKe4trVECxYvFzESBVnSYA/3D0+XV8/tknA0lUwNTXLceIhC0srFC2qfEPVP+rU7VcM7vMrNqxdiXoNmyDszi0c2LMTYyZOkamXmJCAMyeO4bcRXiJFqlhJSYkymbwXL57j3t0wGBgawsjQCKtXLUftOvVgamaGuLdvsX3rZrx58xoNlfQZujnxnzsbterUhZW1NaLevMGyJYFQVVVBk2YtxA5NYb51nlhZWaNH774Y7zUKlatURdXqrvjn/F84d/Y0Vq7dIGLUpGzYAf2BevTogeTkZFSvXh2qqqoYPnw4BgwYkOv1O3fujIcPH2Ls2LFISUlB+/btMXjwYPz555/5GPX/721sDHz+GI/oqCjo6enDwckJgctWwdXdA1Fv3uD61RBs3bQB8fHxKGJigkpVqmL1hi0oYmIidugKs33bFgBA316/ypT7TvdD67bKOTSsdhkLFDfVlXmMykcrj4dDU10V07q6wEhXA6HP4tBp/jk8iUqU1pm6/QYyMgQs6ecKLQ1VXH0Ug3Zzz+BdUnq27RVGO7dn3U8zsG9PmfIpvjPRsnVb6fv9e3fD3MISbu4eCo1PDG9jYzH1j/GIjv50LVm0dBVc3WtI6xzYuxvmFhZw/QnaA8iaFOTLNglYuuqnOf6clC5bHjPmLcTKxYsQtHo5rKyL4vfR49CoqWwn4uSxIxAEAQ2aNBMpUsUKvXMb/ft8up7M/+9WnJat2mDi5Kl48vgxDuwfhri3b2FoZISyZctjbVCwzPNkld3r16/gPXYU4uLiYFykCCpVqoINwdt/queght65jQGfnSf+n50nU2fMQr36DTFhsg/WrV6JubNmwMbWDnP9A1CpchWxQi7wCuswWDFJBEEQvl+NChtFZkALCw013vL8pRIDcp6042f2cOnP8ZgTeWTwYyIbCac9zCb1Q84T7v3M9DT5O/+X+GU9u0xeY7PR1Sg854n9aHEnsXo4v6mo+88LXhmJiIiIiIjygL+pyI8pISIiIiIiIlIIdkCJiIiIiIhIITgEl4iIiIiIKA94X7P8mAElIiIiIiIihWAGlIiIiIiIKA+YAJUfM6BERERERESkEOyAEhERERERkUJwCC4REREREVEecBIi+TEDSkRERERERArBDCgREREREVEeMAEqP2ZAiYiIiIiISCHYASUiIiIiIiKF4BBcIiIiIiKiPFBR4RhceTEDSkRERERERArBDCgREREREVEecBIi+TEDSkRERERERArBDigREREREREpBIfgEhERERER5YGEY3DlxgwoERERERERKQQzoERERERERHnABKj8mAElIiIiIiIihWAHlIiIiIiIiBSCQ3CJiIiIiIjygJMQyY8ZUCIiIiIiIlIIZkCJiIiIiIjygBlQ+TEDSkRERERERArBDKiSUlPhrzFfyswUxA6hwHm4rIPYIRQ41aYcFzuEAufilIZih1DgxCenix1CgaOlrip2CAUOP3WyEwS2ypcy+P0kB/weq8zYASUiIiIiIsoDjsCVH4fgEhERERERkUIwA0pERERERJQHnIRIfsyAEhERERERkUKwA0pEREREREQKwSG4REREREREecARuPJjBpSIiIiIiIgUghlQIiIiIiKiPOAkRPJjBpSIiIiIiIgUgh1QIiIiIiIiUggOwSUiIiIiIsoDjsCVHzOgREREREREpBDMgBIREREREeUBJyGSHzOgREREREREpBDsgBIREREREZFCcAguERERERFRHnAErvyYASUiIiIiIiKFYAaUiIiIiIgoDzgJkfyYASUiIiIiIiKFYAeUiIiIiIiIFIJDcImIiIiIiPKAI3DlxwwoERERERERKQQzoERERERERHnASYjkxwwoERERERERKQQ7oERERERERKQQHIJbgPn4+GDv3r24fv262KF805WQy9iwfg1CQ+8gOioK/gsXo279BgCA9PR0LA1chPN/ncXzF8+hp6cHV7caGDZiFMzNLUSOPP98q00AYPnSQPx55DBevX4FdTV1lC5TFkOHjUD5ChVFjDr/rFu9EqdPHseTx4+gqamFCi6V8PuI0bC1s5PWGdCnB66GXJZZr13HzpgwyUfB0eYfcwNNeDV1Qi0nU2hpqCIiJgkTdtzG7RfxAAAdDVWMbuKE+mXNYaSjjuexydj4z1Nsu/g8x+2t7F0ZtZzN8NuGazgZ+kaRh5Ivdm7fgt07tiLy5QsAgJ29A/oNGIIaNWtJ69y8cQ3LFi/CnVs3oaqqAkfnUghYuhpaWlpihf3D3bwWgu3B6xF+Lwwx0VGYOmshPGrXky4XBAFBq5bi8P5dSHj/HmUruGD42D9QrLgNAOBV5AtsWrsS169cRGxMDEzMzNCgcXN06zUA6urqYh3WDxX15jWWBfrj33/+QkpKCooVK4EJU6ajVJlyAIAZPhNw5OA+mXWqu3vAP3ClGOEqxMfPnbD/Pnfmf/G5k5SUiIAF83Hm1Em8excH66LF0LX7r+jQqYuIUeev77XJlInjcWD/Xpl13D1qYsny1QqOVDF2bt+CXds/XWNL2jug78Ah8PjvGpuamoqF82fj+NHDSEtLh1sND4ybOBkmJqZihl3gcQSu/NgBpf9bcnIynJxKoXXb9hg94neZZSkpKQgLC0X/gUPg5OyM+Ph4zJ09EyN+H4LN23aJFHH++1abAICNjS3GTZiEYsWKIzU1BZs2BmHIwL7Yd+gYihQpIkLE+etqyGV07NINZcqWQ0ZGBpYELMDQQX2xY89BaOvoSOu1bd8RA3/71F5aWtpihJsvDLTVsGWwKy4+jEX/dVcRm5gGW1MdvEtOl9YZ39wZrvYmGLvtJl68TYaHoykmty6NN/GpOB0WJbO9njVtIAiKPor8ZWFhid+GjULxEjYQIODQ/n3wGjEUG7fugr2DI27euIbhvw1Arz4D4DVuItTU1HD/3l2oqCjXYJ6UlGSUdHRGkxZt4eM9MtvybZvWYc+OzRg7aTqsrIti3crFGD9iENZu3gsNTU1EPHkMQcjEiHGTYV2sBJ48Coe/31SkJCdj4DAvEY7ox4qPf4fBfX9B5arVMW/RchgZF8HzZ0+hb2AgU8+1Rk1MmDxd+l5dQ0PRoSpUymefO145fO7MnzMLly9dxPRZc2BtXRQX/vkbs2b4wszMHLXr1sthi4Xf99oEAGp4eMJn+kzpew115T1PzM0tMXT4f9dYQcChA/vgNXwoNm3LusYumOuH83+dg9/chdDT18dcv2kYO2oY1gRtFjt0UjLsgOazzMxMzJs3DytXrsSzZ89gYWGBgQMHYuLEiRg3bhz27NmD58+fw9LSEt27d8fkyZOhrq6O9evXY+rUqQA+3dy8bt069OrVS8SjyVlNz1qo6Vkrx2X6+vpYvmqtTNn4CZPwS9eOiIx8CSsra0WEqHDfahMAaNq8pcz70WPGY+/unQi/fw+ubu75HZ7CBS5fJfPeZ5ofGtbxQFjoHVSuWk1arqWlBVNTM0WHpxD9atshMi4FE3belpa9eJssU8fFxgh7r77ApUdvAQDbLz1H5+rFUKG4oUwHtJSVPnp72qJD4AWc/6OuYg5AATxryx7LkN9HYPeOrbh96wbsHRyxcN4sdO76C3r26S+tY2Nr9+VmCr3q7p6o7u6Z4zJBELB72yZ079UfHrWy2mvc5Bno2Lwu/j53CnUbNkV195qo7l5Tuo510WJ49vQJDuzZrhQd0OCgNTC3sMSEKTOkZdZFi2Wrp6GuARMlvZ7kxMOzFjy+8blz88Z1tGzVBlWruQIA2nfsjF07tuH2rZtK2wH9XpsAgIaGhtJ+7nypVp3s19hd27fi9s0bsLCwxL49uzF91lxUc3UDAEz2nYmObZrj1s3rKF/BRYSICwdOQiQ/5frZuADy9vbGrFmzMGnSJISGhmLz5s2wsMgaeqqvr4/169cjNDQUixYtwqpVq7BgwQIAQOfOnTF69GiULVsWkZGRiIyMROfOncU8lB/m/fv3kEgk0Nc3+H7ln0B6ehp279wGPX19ODmXEjschUhIeA8AMDA0lCk/cvgg6tdyR6e2LbF4kT9SkpNzWr1QqlfaHLdfvMPCbhXx9x91sHuYOzpWk/3SfP1pHOqVNoe5gSYAwLVkEdia6eLv8BhpHS11FczrUgG++0IRnZCm0GNQpIyMDBw7egjJyUkoX8EFsbExuH3rJoyLmKBvj65oUq8mBvb9FdevXRE7VIWKfPkCsTHRqFzNTVqmp6eP0mXKI/T2ja+ul5iYAAMDw68uL0z+PncapUqXxR/jRqJFQ0/07tYe+/fsyFbv2pXLaNHQE13bNcc8P1+8i4tTfLAFSIWKLjh75hTevH4NQRBw+dK/iHj6BG41PMQOTVQhIZdQv3YNtG3ZBDOn+SAu7q3YISlERkYGjh357xpb0QVhoXfw4UM6qrt++hHc1q4kLK2scOvGdfECJaXEDGg+ev/+PRYtWoTFixejZ8+eAAB7e3vUrJn1y/Qff/whrWtrawsvLy9s3boVY8eOhba2NvT09KCmpgZLS0tR4s8PqampCFgwD02aNoeenp7Y4Yjq3NnTGD9mNFJSkmFqZoblK9fC2NhY7LDyXWZmJubP8UPFSpXh4OgkLW/SrAWsrKxhZmaO8PB7CFwwH0+fPMbcBYEiRvvjFC+ija6uxbH+/FOsOPMI5YsZYmKrUkjPyMTeqy8BANP2h2Fau7I4N6EO0jMyIQjApN13EPL40xci7xalcC0iDqdCo762q0LtQfh99O3RFWlpqdDW1sEc/0CUtHfArZvXAQCrli/G8JFj4VSqFA4d2IffBvTGlp37UcLGVtS4FeVtTDQAwLiIiUy5URETxMbE5LQKXjyLwN4dWzDw91H5Hp8ivHzxHHt3bUPn7j3Ro/cAhIXewsJ5flBXV0fTFm0AAK7uNVG7bgNYFS2GF8+fYeWShfAaNhDL122GqqqquAcgknETJmH61Elo0qA21NTUIJFIMMlnGqp8NgrlZ1OjpifqNWgE66JF8fzZMywOWIDfBw/A+k1blfY8eRB+H31+/e8aq6ODuQuyrrH3792Furp6tqHsRYqYIiY6WqRoSVmxA5qPwsLCkJqaivr16+e4fNu2bQgICMDDhw+RkJCADx8+wMBA/qxgamoqUlNTZcoyJBrQ1NTMU9z5JT09HWO9RkAAlGpimbyqVs0VW3fuQdzbt9i9awfGeo3AxuDtKGJi8v2VC7HZM3zx8EE4Vq8Plilv16GT9N8OTk4wNTXD4P698fxZBIoVL6HoMH84iUSCOy/eYcGf4QCAsJfv4Wihhy6uxaUd0F9r2KBiCSMMDrqKF2+TUc2uyH/3gKbgwoNY1C1tBlf7ImgXcEHMQ8lXNra22LRtNxISEnDqxJ+YOtkby1dvgJCZdcNru/ad0bJNOwCAc6kyCLn0Lw7s243fhilH5+pHi37zGt4jB6N2vYZo3rqD2OH8EJmZmShVphwG/jYCAOBUqjQeP3yAvbu2SzugDRo3k9a3d3CCvYMTOrdpgmtXLqNqdbcctqr8tm7eiFs3b2BB4FJYWRXF1SuXpfeAurrXEDs8UTRu2lz6b0cnZzg6OaNVs4YIuXxJKW+HAbKuscHbs66xJ4//CZ9J3lixZoPYYRVqHIErPw7BzUfa2l+fQOXChQvo3r07mjVrhoMHD+LatWuYOHEi0tLkH1Ln5+cHQ0NDmde8OX7/T+g/XHp6OsZ5jUTky5dYtnLNT5/9BABtHR2UKGGDChVd4OM7A6qqatizZ6fYYeWr2TOn4fy5s1i+OggW38nslytfAQDwLCJCEaHlu6j3qXjwJlGm7OGbRFgZZc3eqqmmghGNHTHr4F2cDovC/VcJCL4QgcM3X6GPZ9Z9jm72JihRRAeXptTD7RkNcXtGQwBAwC8u2DBAObIY6uoaKF7CBqXLlMVvw0bB0ckZ2zZvhIlZ1j1advb2MvVt7UriVWSkGKGKwvi/2SjfxspmO+NiY7L9eBUd9Qajh/ZDmfIVMXL8FIXFmN9MTM1gayd7HtjYlcTrV18/D4oWKw4jI2M8f6Yc1xN5paSkYPGihRg1Zjxq16kHJ2dndOn2Cxo1aYYNQWu/v4GfRLHixWFkbIxnEU/FDiXffH6NHTo86xq7NXgjTExMkZ6ejvfx8TL1Y2OjYWLKWXDpx2IGNB85OjpCW1sbJ0+eRL9+/WSW/fPPP7CxscHEiROlZU+fyl7wNDQ0kJGR8d39eHt7Y9Qo2V//MyQFZxa3j53PiIinWLkmCEZGyj/MNC+EzEyk5+EHiMJAEATM8ZuOM6dOYMWaIBQtln3CkC/du3cXAGBqphyTQ1x7Ggc7U12ZMlszHbyMy7rPVU1VAg01FWR+MbNtZqYAlf9+XV115hF2XpZ9JMuBkR6YdfAuToUp55DczEwBaWlpsLYuCjMzczx98lhmecTTp6jhkfOEPcrIyrooipiY4lrIRTg4Zd0znpiYgLDQW2jZ7tMogug3rzF6aD84lSqNMX9MU6qZgstXrISIp7LnwbOnT2D5jUnt3rx+hXfv4mD6k36R/vDhAz58SIeKRPY8UFFRgZCZKVJUBc/rV6/wLi4OZmbmYoeiMEKmgLT0NJQuUxZqauq4fOlf1GvQCADw5MljvIqMRPmKLuIGWcBxEiL5sQOaj7S0tDBu3DiMHTsWGhoa8PDwQFRUFO7cuQNHR0dERERg69atqFatGg4dOoQ9e/bIrG9ra4vHjx/j+vXrKFasGPT19XMcVqupqZmtPClNcc9nSEpKlMlSvXjxHPfuhsHA0BCmpmYYM2o47oaFYtGS5cjMzEB0dNYXZUNDQ6gr6XTn32oTI0MjrF61HLXr1IOpmRni3r7F9q2b8ebNazRs1ETEqPPP7Bm+OHrkEOYvWgwdXV3pOaCnpw8tLS08fxaBo4cPwsOzNgwNjRB+/x78585C5SpV4ejkLHL0P8b680+wZbArBtaxw5Fbr1GhmCE6VS+GybtDAQCJqRm49CgWY5o5IfVDBl68TUH1ksZoXdkasw7eAwBEJ6TlOPHQy7iUbDPqFkZLAvzh7uEJS0trJCUl4s8jB3E15BIClq6CRCLBLz37YOXyxXB0KgUn51I4dGAvnj55hFnzFood+g+VnJSEF88/XT8iX77Ag/t3oW9gCAtLK7Tr/AuC169E0eIlYGlVFOtXLYGJqRk8amXNZBr95jVG/9YX5pZWGDh0NN59NqlKESV4nl/nbj0wqM8v2LB2Jeo1bIzQO7ewf89OjJ3oAyDr+rtu1TLUrtcQJiamePH8GZYGzEfR4iVkZgdWNt/63LGyskaVqtWw0H8uNLU0YWVVFFdCLuHQgX0YNWa8iFHnr2+1iaGhIVYsW4L6DRrB1NQUz549wyL/uSheogTcPZTzPFm8yB81an66xh49fBBXQi4hcNkq6Onro3XbdlgwbxYMDAyhq6eHubOmo3xFF86ASz+cRBCU7UlyBUtmZib8/PywatUqvHz5ElZWVhg0aBC8vb0xduxYrF27FqmpqWjevDnc3Nzg4+ODuP9m6ktNTUX37t1x8uRJxMXFyfUYFkV2QEMuX0T/Pj2zlbds1QaDhgxF8yYNclgLWLU2SDodvLL5VptMnDwVE8Z54datG4h7+xaGRkYoW7Y8+g8cjLLlyis0zgwF/flXrVA6x/Ip02aiZeu2ePUqEpO9x+Lhg3AkJyfDwtISdeo1QN8BgxU+XLvalOP5tu06pcwwqokjbEx08PxtMtb/9RQ7PstomuppYFQTJ3g4msBQRx0v3yZj+6XnWH/+68PB7s5qjN82XMPJ0Df5FvfFKQ3zbdufm+YzESEX/0V0dBT09PTh4OSEHr36wdX90yydQWtXYce2zYh/9w6OTs74faQXXCpVUUh8n4v/7PmtP9r1q5fh9VvfbOWNmrXC2EnTIQgCglYtxaF9O5GQ8B7lKlTC8DETUayELQDgz0P7MHf6pBy3feLCzXyLW0tdcZO2/P3XGaxYvBDPnz2FlXUxdO7eA63adgQApKakwNvrd9y/dxcJ7+NhamaOam410H/Q7wrvgOtoKq5NQi5fxICvfO5MnTEL0dFRCFzoj38v/I34d+9gZWWNdh06oXuPXkqbwflWm3hP8sGo4b/h3t0wvI9/DzNzM7i5e2DI0OEKH3Ka8eXQl3wybcpEXL70L6KjPl1je/b+dI1NTU3FwvmzcezIYaSlpcGthgfGTZwsymNqDLQKz6gNz/nnRd3/X6ML3w8m7IAqKUV2QKnwUlQHtDDJzw5oYaWoDmhhkp8d0MJKkR3QwkKRHVAqvBTVAS1MClMHtJb/36Lu/9yowvcopcLzv0tERERERER58uLFC/zyyy8wMTGBtrY2ypcvj5CQEOlyQRAwefJkWFlZQVtbGw0aNEB4eLjMNmJjY9G9e3cYGBjAyMgIffv2RUJCglxxsANKRERERESUBxKJuK/cevv2LTw8PKCuro4jR44gNDQU8+fPl3kG/Zw5cxAQEIDly5fj4sWL0NXVRePGjZGSkiKt0717d9y5cwfHjx/HwYMHce7cOQwYMECuNuMkREREREREREps9uzZKF68ONatWycts7Ozk/5bEAQsXLgQf/zxB1q3bg0A2LBhAywsLLB371506dIFYWFhOHr0KC5fvoyqVasCAAIDA9GsWTPMmzcP1tZfn438c8yAEhERERERKbH9+/ejatWq6NixI8zNzVGpUiWsWrVKuvzx48d49eoVGjT4NHmooaEhXF1dceHCBQDAhQsXYGRkJO18AkCDBg2goqKCixcv5joWdkCJiIiIiIjyQCKRiPpKTU1FfHy8zCs1NTVbnI8ePcKyZcvg6OiIP//8E4MHD8awYcMQFBQEAHj16hUAwMLCQmY9CwsL6bJXr17B3Fz2OblqamooUqSItE5usANKRERERERUCPn5+cHwv2fbfnz5+fllq5eZmYnKlStj5syZqFSpEgYMGID+/ftj+fLlCo+ZHVAiIiIiIqI8EHsSIm9vb7x7907m5e3tnS1OKysrlClTRqasdOnSiIiIAABYWloCAF6/fi1T5/Xr19JllpaWePNG9rnjHz58QGxsrLRObrADSkREREREVAhpamrCwMBA5qWpqZmtnoeHB+7duydTdv/+fdjY2ADImpDI0tISJ0+elC6Pj4/HxYsX4e7uDgBwd3dHXFwcrly5Iq1z6tQpZGZmwtXVNdcxcxZcIiIiIiIiJTZy5EjUqFEDM2fORKdOnXDp0iWsXLkSK1euBJB1L+uIESMwffp0ODo6ws7ODpMmTYK1tTXatGkDICtj2qRJE+nQ3fT0dAwdOhRdunTJ9Qy4ADugREREREREeSKR52GcIqpWrRr27NkDb29v+Pr6ws7ODgsXLkT37t2ldcaOHYvExEQMGDAAcXFxqFmzJo4ePQotLS1pneDgYAwdOhT169eHiooK2rdvj4CAALlikQiCIPywI6MCIymN/630fRn888+m2pTjYodQ4Fyc0lDsEAqc+OR0sUMocLTUVcUOocDR0WSb0PdlZPKz+EsGWoXnLsF6ARdE3f+pYe6i7j8vmAElIiIiIiLKg0KSAC1QCs/PC0RERERERFSosQNKRERERERECsEhuERERERERHmgwjG4cmMGlIiIiIiIiBSCGVAiIiIiIqI8YAJUfsyAEhERERERkUKwA0pEREREREQKwSG4REREREREeSDhGFy5MQNKRERERERECsEMKBERERERUR6oMAEqN2ZAiYiIiIiISCHYASUiIiIiIiKF4BBcIiIiIiKiPOAkRPJjBpSIiIiIiIgUghlQIiIiIiKiPGACVH7sgCopDgfIjk2SXVp6ptghFDiXfBqKHUKBY9FtndghFDgxW/uIHUKBk8LrSTaZgiB2CAWOmgoH331Joip2BESKxasAERERERERKQQzoERERERERHkgAYfYyYsZUCIiIiIiIlIIZkCJiIiIiIjyQIUJULkxA0pEREREREQKwQ4oERERERERKQSH4BIREREREeUBH30oP2ZAiYiIiIiISCGYASUiIiIiIsoDJkDlxwwoERERERERKQQ7oERERERERKQQHIJLRERERESUByocgys3ZkCJiIiIiIhIIZgBJSIiIiIiygMmQOXHDCgREREREREpBDugREREREREpBAcgktERERERJQHEo7BlRszoERERERERKQQzIASERERERHlAROg8mMGlIiIiIiIiBSCHVAiIiIiIiJSCA7BJSIiIiIiygMVjsGVGzOgREREREREpBDMgBIREREREeUB85/yYwb0B6pTpw5GjBghdhhEREREREQFEjOg9MMtWxKIFcsWy5TZ2tlh74GjIkUkvjWrVuDk8WN4/PgRNLW04OJSCSNGecHWrqTYoSnEru1bsXvHVrx8+QIAUNLeAX0HDEaNmrUAAM+fRSDAfy5uXL+KtLQ0uNeoidHjJ8LExFTMsPPdzu1bsGv7VkR+3i4Dh8Djv3ZJTU3FwvmzcfzoYaSlpcOthgfGTZysNO2ioiLBH50roWstB1gYaSPybRI2ng7HrB3XAQBqqhL4dKuKxpWLwc5CH/FJaTh18yUmbQxB5Nsk6XZ2eDdARVsTmBlq4W1iGk7feIk/Nl6WqVOYXQm5jA3r1yA09A6io6Lgv3Ax6tZvAABIT0/H0sBFOP/XWTx/8Rx6enpwdauBYSNGwdzcQuTI88fq5YuxZuVSmbIStnbYtvsQgKy/mwD/OThx7DDS09Lg6l4TY7wnoYiS/N3kZN3qlTh98jiePH4ETU0tVHCphN9HjIatnZ20zoA+PXA15LLMeu06dsaEST4KjrZgWLt6JQIWzke3X3pg7PiJYoejMFdCLmPDus+uJ4s+XU8AQBAELFsSiD07d+D9+3hUrFQZEyZNgY2NrXhBk9JhB7QQSUtLg4aGhthh5Iq9gyNWrF4nfa+qqipiNOILuXwJnbt2R9ny5ZHxIQOBi/wxqH9f7N5/CDo6OmKHl+/MLSwwZNhIFC9hAwA4tH8vxowYio1bd8GqaFEMG9wfjk7OWLIy65xZsSQAXsN+w5qNW6CiorwDNczNLTF0+CgUL2EDQRBw6MA+eA0fik3bdsHewREL5vrh/F/n4Dd3IfT09THXbxrGjhqGNUGbxQ79hxjdtgL6Ny6N/oHnEBrxFlUcTLFiqCfiE9Ow9HAodDTV4FLSBLN2XMfNJ7Ew1tPAvD5u2OHdADXH7pdu59ytSMzddQOv3ibDuogO/HpWx+Yx9VB3wkERj+7HSU5OhpNTKbRu2x6jR/wusywlJQVhYaHoP3AInJydER8fj7mzZ2LE70OwedsukSLOfyXtHRCwbI30varqp68zi+bPwj/nz2LG7AXQ09PH/NnTMd5rOFauCxYjVIW4GnIZHbt0Q5my5ZCRkYElAQswdFBf7NhzENqffca0bd8RA3/7dA5paWmLEa7obt+6iZ07tsLJyVnsUBQuOTkZTs45X08AYP3a1dgSvBG+M2ahaNFiWLp4EX4b2A+79h2CpqamCBEXfBJOQiQ3dkDzKDExEYMHD8bu3buhr68PLy8vmeWpqamYOHEitmzZgri4OJQrVw6zZ89GnTp1pHXOnz8Pb29vhISEwNTUFG3btoWfnx90dXUBALa2tujbty/Cw8Oxd+9etGvXDuvXr1fgUeadqqoqTE3NxA6jwFi2co3Me98Zs1DX0x1hoXdQpWo1kaJSHM/adWXeD/59BHbv2Irbt27izZs3iHz5Ahu27oKenh4AYMo0PzSo5YaQS/+iulsNMUJWiFp1ZNtlyO8jsGv7Vty+eQMWFpbYt2c3ps+ai2qubgCAyb4z0bFNc9y6eR3lK7iIEPGP5eZsjoOXnuLolWcAgIioBHSqWRJVHbOuHfFJ6WgxVXbkxMjVF3B+TmsUN9XFs+hEAEDgwTvS5RFRCZi35ya2j2sANVUJPmQICjqa/FPTsxZqetbKcZm+vj6Wr1orUzZ+wiT80rUjIiNfwsrKWhEhKpyqqipMcviMSXj/Hgf27sLUmXNRtXrW381Enxno2r4Fbt+8gXIVKio6VIUIXL5K5r3PND80rOOBsNA7qPzZZ4yWltZP/9mclJSICePHYLLPdKxasUzscBTuW9cTQRCweeMG9B8wCHXr1QcATJs5Gw1qe+D0yRNo0qy5IkMlJaa8qYV8NmbMGJw9exb79u3DsWPHcObMGVy9elW6fOjQobhw4QK2bt2KmzdvomPHjmjSpAnCw8MBAA8fPkSTJk3Qvn173Lx5E9u2bcP58+cxdOhQmf3MmzcPFStWxLVr1zBp0iSFHuP/IyLiKRrWrYnmTerDe9xoREa+FDukAiXh/XsAgIGhociRKF5GRgaOHT2M5ORklKtQEenpaZBIJDLZfQ1NTaioqODGtavf2JJyycjIwLEjh5CcnITyFV0QFnoHHz6ko7qru7SOrV1JWFpZ4daN6+IF+gP9e+8N6lawhoOVAQCgvG0RuJe2xLFrz7+6joGOBjIzBcQlpuW43FhPA11q2ePfe6+VovOZF+/fv4dEIoG+voHYoeSbZxERaNmoNtq3bIQpE8fg1X+fMXfD7uDDhw+o9uXfjaUVbt28LlK0ipeQkPNnzJHDB1G/ljs6tW2JxYv8kZKcLEZ4opo53ReetWrDzV15f9zMqxfPnyM6Ogqun7WNvr4+ylWogJtK8rmTH1Qk4r4KI2ZA8yAhIQFr1qzBpk2bUL9+1i9EQUFBKFasGAAgIiIC69atQ0REBKyts3599vLywtGjR7Fu3TrMnDkTfn5+6N69u3TSIkdHRwQEBKB27dpYtmwZtLS0AAD16tXD6NGjFX+Q/4fyFSrAd7ofbG3tEB0dheVLl6BPj+7YufcAdHX1xA5PdJmZmZgzeyZcKlWGo6OT2OEozIPw++jXoyvS0tKgra2D2f4BKGnvAGPjItDS1sbihfMx5PcRECBgySJ/ZGRkIDo6Suyw892D8Pvo82tXpKWlQltHB3MXBKKkvQPu37sLdXV16BvIdiKKFDFFTHS0SNH+WPN234CBtjpuBHZARqYAVRUJpmwOwdZzD3Osr6muium/VsP28w/xPjldZtn0X6thUNPS0NVSx8V7b9BuxjFFHEKBk5qaioAF89CkaXPpiAJlU7Z8BfwxdQZsbLI+Y9asXIrBfX/Fph37ERMTnfV380Xn29jEFLExyvF38z2ZmZmYP8cPFStVhsNnnzFNmrWAlZU1zMzMER5+D4EL5uPpk8eYuyBQxGgV6+jhQ7gbForgrTvFDqVA+viZW8TERKbcxER5PneoYGAHNA8ePnyItLQ0uLq6SsuKFCkCZ+esewlu3bqFjIwMODnJdi5SU1Nh8t8f9Y0bN3Dz5k0EB3+6J0UQBGRmZuLx48coXbo0AKBq1arfjSc1NRWpqakyZZkqmqKN1a/pWVv6byfnUihXviKaNaqLY0ePoG37jqLEVJDMnD4VD8PDsX6jctzHl1s2trbYuG03EhIScOrEn/CdPAHLVgehpL0DZs5ZgDkzfbF9yyaoqKigYZNmcC5dRqnv//zIxtYWwduz2uXk8T/hM8kbK9ZsEDsshehQoyS61LJHrwVnEPrsLSrYmWBuH1dExiYh+MwDmbpqqhJs8qoLiQQYtuKfbNtasPcm1p+4hxLmepjYqRJWD6/903VC09PTMdZrBARAqSeWcff4NHzQwckZZctXQNvmDXDy+FHeowZg9gxfPHwQjtXrZe95bdehk/TfDk5OMDU1w+D+vfH8WQSKFS+h6DAV7lVkJObMmoHlq9byPCESGTug+SAhIQGqqqq4cuVKtsl3Pv4inZCQgIEDB2LYsGHZ1i9R4tMHwcf7Qb/Fz88PU6dOlSmb8McU/DHZJw/R/3gGBgYoYWOLZxERYociupnTfXHu7BmsDdoEC0tLscNRKHV1DekkRKXLlEXYndvYtnkjvCdNhVsND+w++Cfi3r6Fqqoq9A0M0LS+J6yLNhU56vz3ZbuE3rmFrcEb0bBxU6Snp+N9fLxMFjQ2Nhompsoxm+fMntUwb/dN7Pj7EQDgTsRblDDTw5h2FWU6oGqqEgR71UMJMz00nXwkW/YTAGLepyLmfSoeRMbj3vM4PFjVFa5O5rh4/43CjkdM6enpGOc1EpEvX2LlmvVKm/3Mib6+AUqUsMXzZ09R3bVG1t/N+3iZLOjbmGilngX3o9kzp+H8ubNYuW7jdz9jypWvACBrOPPP0AENDb2D2NgYdO3UTlqWkZGBq1cuY9uWYFy6euunnzDx4/3BsTExMDMzl5bHxETD2bm0WGEVeJyESH7sgOaBvb091NXVcfHiRWln8e3bt7h//z5q166NSpUqISMjA2/evIGnp2eO26hcuTJCQ0Ph4ODwf8fj7e2NUaNGyZRlqhScX/eSkhLx/NkzmLb8eSc+EAQBfjOm4dTJ41izfiOKFSsudkiiy8wUkJ4m25EwMjYGAIRc+hdvY2NRq049MUITlZApIC09DaXLlIWamjouX/oX9Ro0AgA8efIYryIjUb6ii7hB/iDammrIFGTv08zIzITKZze1fOx82lsZosnkw4hNSP1yM9mo/PdlQENd+TPowKfOZ0TEU6xcEwQjI2OxQ1KopKREPH8egSbNW6JU6bJQU1NDyKV/Ubd+1t/N0yeP8epVpFJM3PU1giBgjt90nDl1AivWBKHof7cEfcu9e3cBAKZmP8dns6ubG3buOSBTNvkPb9jZlUTvvv1/+s4nABQtVgympma4+O8FOJfK6nAmJCTg9s2b6Nipq8jRkTJhBzQP9PT00LdvX4wZMwYmJiYwNzfHxIkTpcMFnZyc0L17d/To0QPz589HpUqVEBUVhZMnT6JChQpo3rw5xo0bBzc3NwwdOhT9+vWDrq4uQkNDcfz4cSxevPg7EcjS1Mw+3DaHBIHC+M+djVp16sLK2hpRb95g2ZJAqKqqoEmzFuIFJbKZ06biyOGDWBi4FLo6uoiOyrrPQk9fX3q/rzJbEuCPGh61YGFphaSkRPx55CCuhlzCoqVZMzce2LsbtiXtYWxsjFs3r8N/jh+6/tIDNrZ239ly4bZ4kT9q1PSEpaU1kpIScfTwQVwJuYTAZaugp6+P1m3bYcG8WTAwMISunh7mzpqO8hVdlOaL9OHLERjXwQXPohMRGvEWLiVNMKxlOWw4lTVZm5qqBJvH1EelkiZoN/M4VFUksDDKemxEbEIq0j9kopqjGao4mOKfsNeIS0yDnYU+pnSrgoeR8bh4Tzmyn0lJiTIjSF68eI57d8NgYGgIU1MzjBk1HHfDQrFoyXJkZn66d9rQ0BDq6oXj0V3yCFgwBzVr1YWVlTWiot5g9fLFUFVRRcMmzaGnr4+WbdojYP7srL8bXT3MnzMD5Sq4KO0MuEDWsNujRw5h/qLF0NHVlZ4DenpZnzHPn0Xg6OGD8PCsDUNDI4Tfvwf/ubNQuUpVOP4kjyLR1dWTuScWALS1dWBoZJStXJl963piZWWNbr/2wOqVy1HCxhZFixbF0sUBMDM3l3lWKMliAlR+7IDm0dy5c5GQkICWLVtCX18fo0ePxrt376TL161bh+nTp2P06NF48eIFTE1N4ebmhhYtsjphFSpUwNmzZzFx4kR4enpCEATY29ujc+fOYh3SD/P69St4jx2FuLg4GBcpgkqVqmBD8HYUKVJE7NBEs33bFgBA316/ypT7TvdD67btclpFqbyNjcXUP8YjOjoKenr6cHBywqKlq6Qz7UU8fYKlgQsQ/+4drKyLone/gej6S0+Ro85/b2Nj4PPHeERHfWqXwGWr4OruAQAYOcYbEhUVjBs9HGlpaXCr4YFxEyeLHPWPM2r1v5jSrTIWDagBMwMtRL5Nwppj9zBzxzUAgHURXbSsnjU8+ZJ/W5l1G006hL/uvEJS6ge0drPFH10qQ1dTDa/eJuPYteeYvfM60j5kKvyY8kPondvo3+fT38P8ubMAAC1btcGgIUNx9swpAECXDm1k1lu1NghVq7lC2US9fo0p3l549y4ORsZFUNGlMlYFbYGxcdZnzPDR4yGRqMB7zHCkp6XD1d0DY7wLzyzyebFz+1YAwMA+stfNKdNmomXrtlBTV8elfy9gy6YNSE5OhoWlJeo1aIi+AwaLES6JKPT2F9eTOf9dT1q3ge+MWejVpx+Sk5Mx3Wcy3r+Ph0vlKliyfBXvm6UfSiIIws85T72SEzMDWlDxF6rsUtIzxA6hwFHhiZKNRbd1YodQ4MRs7SN2CAVOSrpydPh/JHU1Xk++pPYTTC4nLwH8Kv4lHfXC87fza/ANUfe/sXvhG93BDCgREREREVEecBIi+fFnKCIiIiIiIlIIZkCJiIiIiIjyQIUJULkxA0pEREREREQKwQ4oERERERERKQSH4BIREREREeUBJyGSHzOgREREREREpBDMgBIREREREeUB85/yYwaUiIiIiIiIFIIdUCIiIiIiIlIIDsElIiIiIiLKAxVOQiQ3ZkCJiIiIiIhIIZgBJSIiIiIiygMmQOXHDCgREREREREpRJ46oH/99Rd++eUXuLu748WLFwCAjRs34vz58z80OCIiIiIiIlIecndAd+3ahcaNG0NbWxvXrl1DamoqAODdu3eYOXPmDw+QiIiIiIioIJJIJKK+CiO5O6DTp0/H8uXLsWrVKqirq0vLPTw8cPXq1R8aHBERERERESkPuSchunfvHmrVqpWt3NDQEHFxcT8iJiIiIiIiogKvkCYhRSV3BtTS0hIPHjzIVn7+/HmULFnyhwRFREREREREykfuDmj//v0xfPhwXLx4ERKJBC9fvkRwcDC8vLwwePDg/IiRiIiIiIiIlIDcQ3DHjx+PzMxM1K9fH0lJSahVqxY0NTXh5eWF33//PT9iJCIiIiIiKnBUOAZXbnJ3QCUSCSZOnIgxY8bgwYMHSEhIQJkyZaCnp5cf8REREREREZGSkLsD+pGGhgbKlCnzI2MhIiIiIiIqNJgAlZ/cHdC6det+85kzp06d+r8CIiIiIiIiIuUkdwfUxcVF5n16ejquX7+O27dvo2fPnj8qLiIiIiIiIlIycndAFyxYkGO5j48PEhIS/u+AiIiIiIiICoNvjQylnMn9GJav+eWXX7B27doftTkiIiIiIiJSMnmehOhLFy5cgJaW1o/aHNEPlykIYodQ4Gio/bDfoJRGVHya2CEUOG829xY7hALHbshOsUMocO4GtBM7hAKHj2fIjk2SXUaG2BHQ/4PfpOQndwe0XTvZDxhBEBAZGYmQkBBMmjTphwVGREREREREykXuDqihoaHMexUVFTg7O8PX1xeNGjX6YYERERERERGRcpGrA5qRkYHevXujfPnyMDY2zq+YiIiIiIiICjxOQiQ/uYYtq6qqolGjRoiLi8uncIiIiIiIiEhZyX3fbLly5fDo0aP8iIWIiIiIiKjQUJGI+yqM5O6ATp8+HV5eXjh48CAiIyMRHx8v8yIiIiIiIiLKSa7vAfX19cXo0aPRrFkzAECrVq1kxjwLggCJRIIMziVNREREREREOch1B3Tq1KkYNGgQTp8+nZ/xEBERERERFQqFdRismHLdARUEAQBQu3btfAuGiIiIiIiIlJdcj2HhNMNERERERERZ2D+Sn1wdUCcnp+82cmxs7P8VEBERERERESknuTqgU6dOhaGhYX7FQkREREREREpMrg5oly5dYG5unl+xEBERERERFRqchEh+uX4OKMc3ExERERER0f9D7llwiYiIiIiICGCOTn657oBmZmbmZxxERERERESk5HI9BJeIiIiIiIjo/yHXJERERERERESURYVjcOXGDCgREREREREpBDOgREREREREecBsnvzYZkRERERERKQQ7IASERERERGRQnAILhERERERUR5wDiL5MQNKRERERERECsEOqALUqVMHI0aMEDsMIiIiIiL6gVQkElFfhRGH4FK+W7t6JQIWzke3X3pg7PiJYocjioyMDCxfuhiHD+5HTHQ0zMzM0bJNW/QfOBiSQnrxkNeVkMvYsG4NQkPvIDoq6n/t3XVcVFkfBvBnaEkRQbEASREwXxW71k7cstu1sLtQDGyxExXXXl11zdVFRdfAQCwQWwwQREUJiWHeP1hndwRdYeEeYJ7v++HzOufemXnm7tSZ37nnYPHSFWjUpKlye8CJ49izeyfCQm8jLi4OO/fsg6NTBYGJc9+Na1fwy/bNuBcehtevYuDl44s6DRort/95+g8c2vcL7oWH4v27OKzevBu2Dk4qt5GSnIy1yxfi9B/HkJqaguo1a8NzzBSYFjOT+uHkuk1+63Aq4AQeP3oIXV09uFWuAs8Ro2FtbaOy343r17Bq+VLcunkDmpoacHB0wvLVG6Cnpycoee65PLcVyhU3yNS+8eR9TNx+Db+ObYA6jhYq2/xPP8C4rcEqbT/UtsLAZg4oX8II8Ump+O3KM0zcfi1Ps4uyZeN6rFq+BD906Y6RYyciLu4t1q9egUsXz+NlVCSKmpqifsMm+GnwMBgaGYmOm2euXrmMLZv9EPbXe+wiX9X32MTEBCxbsginTwYgLu4tSpUug85du+Pb738UmFpau3dux+5dO/Di+XMAgK2dPX4aNBh16zUQnEwaGzeszfQeO2zEaFjblAcAxMW9xdpVy3Hx/DlERUWiqGkxNGzcBIOGDIdRIX7tkPTYAaU8devmDez5ZSccHBxFRxFqs9967Nm1A96z58LWzg63b9/C9CmTYGhoiC7deoiOJ4mkpCQ4ODqhfcdOGD3CM8vtlatWwzfNW2Lm9KkCEua9Dx+SUN7OEc3bdIT3xJGZtyclwaVSFTRo0gxL5s7I8jbWLJuPoPNnMWXWQhgYGmHlojmYMXEkfNduyev4eS74ymV890MXOFd0gVwux8rlSzB0YF/88ushFNHXB5DR+fQcPAC9+wzA2AmToamlhXvhd6ChUTgG9LSY9Qc0NP7+UapCaRP8MroBDl59pmz7OfAh5h24pbyclCJXuY2fvrHHoGaO8P7lOq4+eg0DXS2UNdPP+/AChN6+iX17d8PO/u/PmFcxMXgVEwPPkWNhU94WUZEvMG/2DLyKiYHPQl9xYfPYh6QkODhkvMeOyeI9dtH8ubh8KQiz5s5HqVKlceH8Ocyd7Q1zcws0aNQ4i1ssfCxKlMTwkWNQzsoKCoUCBw/sx/ChQ7Br7z7Y2dmLjpfngq9cxnc/dkHFiq6Qy+VYsWwJhgzshz37Mt5jY6KjERMdjRGjx8HG1g6RL17AZ5YXXkVHY/7iZaLjUyHCDmguS0hIwKBBg/Drr7/CyMgIY8aMUdn+5s0bDB8+HAcPHkRycjIaNGiAZcuWwd7+7ze+9evXw9vbG7GxsWjevDnq1asHb29vvH37VuJH898kJiZg0oSxmDZ9FtavXS06jlDXQ66hQaMmqNegIQCgVOkyOHbkMG7fvCk2mITq1quPuvXqf3Z7m3btAQAvnj/77D4FXQ33eqjhXu+z25u2bAsAiIp8nuX2hPj3OHZwHyZMn4sq1WsCAEZPnol+Xdoj7NZ1VHCplPuhJbR89XqVy9O9ffBNozoIC7uNqtX+BwBYvGAufuzcDb369lfu92mFtCCLjU9RuTyspSUeRcfjfHiMsi0pJQ0x75KzvL6JvjYmdHBBj+XncPZOtLI99Flc3gQWKDExAV6TxmHi1BnYtGGtst3Wzh5zFy1VXi5TthwGDh2O6ZPHIy0tDVpahfOrT5169VHnC++xN66HoG27Dqj+v4z3jk7f/YC9v+zCrZs31KYD2vCTx+k5fCR279yBG9dD1KIDumLNBpXLM2b6oGnD2ggLvY2q1f8HO3sHLFiyXLm9bNlyGOw5ElMnji3Ur53/Sk0GsuWqwvGTcT4yduxYBAYG4sCBAzh+/DhOnz6N4OC/h0b16tULV65cwW+//YYLFy5AoVCgVatWSE1NBQCcO3cOAwcOxPDhwxESEoJvvvkGs2fPFvVw/pM5s7xRr34D1HKvLTqKcJUqV8GloAt48vgRACD8zh2EBAd/8csC0afu3glFWloaqv6vlrKtnLUNLEpYIvTWDYHJ8kZ8/HsAgLGxCQDgdWwsbt28AdNiZujTozOaNaqLAX26IyT4qsiYeUZbU4ZOtayw489HKu0etawQuqQdAmc0w2QPFxTR0VRua+BcAhoaMpQ0LYKzM5vj2vzWWPdTLZQyLSJ1/Dy30GcW6tRrgBq1/v0zJv59PAwMDNX6C7RbpcoIPH0S0S9fQqFQ4PKli4h48hi1atcRHU0IuVyOo0cOIykpEZUqVREdRwjle6yJyef3ef8eBobq/dqh3MdnUy6Kj4+Hn58ftm7diiZNmgAA/P39UaZMGQDAvXv38Ntvv+HcuXOoXTvjA3Pbtm0oW7Ys9u/fj++++w7Lly9Hy5YtlZVTBwcHnD9/HocOHRLzoHLo2JHDuBMWim0794iOki/07jcA8QkJ6Ni2FTQ1NSGXyzFk2Ai0atNWdDQqQN68fgVtbW0YGhmrtJsWM8Ob2FeCUuWN9PR0LJrvg0qVq8LO3gEA8Pz5UwDA+jUrMHzUODg4OuHwoQMYNKA3du39DeWsrAUmzn0tq5SGib42dp57rGzbFxSBp7GJePk2Cc5limJKJ1fYljRCn1UXAABW5gbQkMkwvJUTpuwMwfukVEzo4ILdo+qj0fTjSJUrBD2a3HXi2BGE3wnFxq27/3Xft2/eYNP61Wjf6TsJkuVf4ydNxawZU9GiaQNoaWlBJpNh6vSZqFb9f6KjSere3XB07/IjUlKSoa+vjyXLVsLWzk50LMmlp6dj4fw5qFTl7/fYT7158wYb1q2GR6fvJU5XsGiwAppt7IDmogcPHiAlJQU1a9ZUthUrVgyOjhnnpoSFhUFLS0tlu5mZGRwdHREWFgYACA8PR8eOHVVut0aNGl/sgCYnJyM5WXU4VrqGLnR1df/zY8qJqMhIzJ87G2vWbxSWIb85fuwojh46iDnzFsLWzg7hd+5g4bw5MLewQLv2Hf/9BojUzLw53njw4B42bN6mbEtPz+g8eXz7A9p18AAAOFVwxuWgi/ht/68YOnyUkKx5pUtdG5y8FYWXcR+UbT+f+bsaGvb8HV7GJWHvmIawMjfAk5gEaMhk0NHSwOQdIQgMfQkAGLjuIm4uboc6ThY4fful5I8jt72MisTiBT5YtnrDv37GJMTHY9SwgbAub4v+Pw2RKGH+tHP7z7h54zqWLF8FS8vSCL56WXkOaE01GqlkbW2D3Xv3Iz7+PU4c/x1TJ42H3+atatcJnTvbGw/u34Pf5u1Zbo+Pj8fwIT+hfHlbDBg0VOJ0VNixA1oI+Pj4YMYM1QlLJk3xwpRp04XkCQ29jdevY9H5ew9lm1wuR/DVy9i1YxsuBd+EpqbmF26h8PFdtAC9+/VHi1atAQD2Do6IjHyBTRvWsQNKX820WHGkpqYi/v07lSrom9exMDUrLjBZ7po3Zyb+PBOIdRt/RokSJZXtxYubAwBsytuq7G9jUx5RUZGSZsxrZYrpo75zCfRZdf6L+wU/fA0AsLEwxJOYBGVn9W7kO+U+sfEpeB2fjDLFCsdERHfCbuPN61j06vKtsk0ulyMk+Ar27NqOM0Eh0NTUREJCAkYMGQB9fQPMW7wcWtraAlOL9eHDB6xY6otFS5ejXv2GAAAHR0fcDb+DLf4b1aoDqq2jg3JWVgAA54ouuH3rJrZt3YJp070FJ5POvDne+PPMaazftBUlSpbMtD0hIR6eg/rBwMAAC31XQFuNXzuUN9gBzUW2trbQ1tZGUFAQypUrByBj+MLdu3fRoEEDVKhQAWlpaQgKClIOwY2NjUV4eDicnZ0BAI6Ojrh8+bLK7X56+VMTJ07EqFGqv/yna4irPNasVQt79h1UaZs2ZSJsbMqjd9/+atf5BDJmP5XJVE+51tDQQHp6uqBEVBA5ODlDS0sL164EoV6jbwAAT588QvTLSDi7uAlO998pFArM95mF0yf/wFo/f5T+6/SFj0qVLg1zcwvludQfPXnyBHXqfn5yp4Lox7rWePXuA07c+HLHumK5ogCA6L86npfuZwzFtithhMg3SQCAogbaKGaoi6exiXkXWELVa7hj2y8HVNpmeU2GlY0Nuvfql9H5jI/H8MH9oa2jg4W+K9V+NE5aWhrS0lKhkcXnkELNP4fS09ORmpLy7zsWAhnvsTNx6uQfWOe3JdN7LJBR+Rw6sC90dHSweNkqtX/tfI2CuhanSOyA5iJDQ0P07dsXY8eOhZmZGSwsLDB58mTl8gD29vZo3749+vfvj7Vr18LIyAgTJkxA6dKl0b59xgygnp6eqF+/PhYvXoy2bdvi5MmTOHr06BfXitTVzTzcNik17x7nvzEwMMx0PkGRIvowKVr0s+cZFHb1GzaC3/o1sLS0hK2dHe6EhWHrls3o0LGT6GiSSUxMwNOICOXl58+fIfxOGIxNTGBpWQpxcW8RFRmJ6OiMmTsfP8roZJgVL66sfBV0SYmJePHs72MQFfkcD+7egZGxCSxKWuLduzjEREUi9lXGjKdPIx4DAEzNiqOYWXEYGBqhRduOWLtsIYyMTaBvYIhVi33g7FKpwM+AC2T8Kn/s6GEs8l0BfQMDvPrrOBgaGkFPTw8ymQzde/XB2tUrYO/oBEdHJxz6bT+ePH6I+Yt8xYbPRTIZ8GMda+y+8ATy9L/P2bQyN4BHzXIIuBmJN/EpcC5jAu8fKuN8eIxyltuHL+Nx9NpzzOpcGaO3XEV8Uiomd3LFvch3OBce/bm7LFAMDAxg+8mMpXpFisDEpChs7eyREB+PYYP74cOHD5g+ex4SEuKRkBAPAChqWqzQ/gj6b++x1ar/D76LF0BXTxeWlqVx9colHD54AKPGThCYWlpLlyxC3Xr1UdLSEokJCThy+BCuXL6E1ev8REeTxNzZ3jh29BAWL12Z5XtsfHw8hvzUFx8+JGGmzwKV145pIX7tkPRkCoWicMxIkE/Ex8erLMMyevRoHD58GJUrV4avr69yGZbffvsNKSkpqF+/PpYvX55pGZYZM2bg9evXaN68OapXr44VK1YgMvLrh5iJ7IBmpW+v7nB0csK4CZOFZVBA3FM9ISEeq5Yvw8mAP/DmdSzMzS3QolVrDBg0GNraOsJySenKpSD079MzU3vb9h3gPXsuftv/K7ymTMq0/adBQzBwSOY17fJKzLu8+yX8evBljB3aN1P7N63aYeyUWTh++AAWzs68Bmq3PgPRo99gAEBKcjLWLl+I0yeOIiU1BdVr1oHnmMkolodDcIsZSDP8qnqlClm2e3nPQdt/DFXf7Lcev+zajri4ODg4OmLYiDGoXLWaJBk/shu6N89uu4FzCeweVR/uk4/i4ct4ZXsp0yJY2a8mnEobQ19XCy9eJ+LItedYcigM8R/SlPsZ6mlh5g+V0apqaaQrFLhwNwZTdoTgxV8V0bxyZ5nHv++URwb16wkHRyeMHDsRV69cwpD+vbLc79fDJ1CqVGnJculoSbfYwJXLQRiQ1Xtsuw6YMXsuXr2KwXLfxbh44RzexcXB0rIUPL79Hl179Prij9y5TVPgjC1eUyfh0sWLiImJhqGRERwcHNG7b3+4C54JOE2iycGquTll2e41cw7atffAlctB+Klv5ucQABw8+gdKlc5cMc0rhroFp6o484/7Qu9/atOCd/4yO6AFQP/+/XHnzh2cPXv2q6+T3zqg+YHIDigVHHnZAS2opOqAFiR52QEtqER2QPMrKTugBYXIDmh+JVUHtCBhB/TrFcQOKIfg5kMLFy7EN998AwMDAxw9ehT+/v5YtWqV6FhERERERET/CTug+dClS5cwf/58vH//HuXLl8eyZcvQr18/0bGIiIiIiOgfWNTPPnZA86Hdu/99YW0iIiIiIqKChh1QIiIiIiKiHJCBJdDs4tnxREREREREJAl2QImIiIiIiEgSHIJLRERERESUA5yEKPtYASUiIiIiIiJJsANKRERERESUAxoysX85NXfuXMhkMowYMULZ9uHDBwwZMgRmZmYwNDREp06d8PLlS5XrRUREoHXr1tDX14eFhQXGjh2LtLS07B2znMcmIiIiIiKiguTy5ctYu3Yt3NzcVNpHjhyJgwcP4pdffkFgYCBevHgBDw8P5Xa5XI7WrVsjJSUF58+fh7+/PzZv3oxp06Zl6/7ZASUiIiIiIlID8fHx6Nq1K9avXw9TU1Nle1xcHPz8/LB48WI0btwY1apVw6ZNm3D+/HlcvHgRAHD8+HGEhoZi69atqFy5Mlq2bImZM2di5cqVSElJ+eoM7IASERERERHlgEwmE/qXnJyMd+/eqfwlJyd/Nu+QIUPQunVrNG3aVKX96tWrSE1NVWl3cnJCuXLlcOHCBQDAhQsX4OrqihIlSij3ad68Od69e4fbt29/9TFjB5SIiIiIiKgA8vHxgYmJicqfj49Plvvu3LkTwcHBWW6PioqCjo4OihYtqtJeokQJREVFKff5Z+fz4/aP274Wl2EhIiIiIiLKAdHLsEycOBGjRo1SadPV1c2039OnTzF8+HCcOHECenp6UsXLEiugREREREREBZCuri6MjY1V/rLqgF69ehXR0dGoWrUqtLS0oKWlhcDAQCxbtgxaWlooUaIEUlJS8PbtW5XrvXz5EiVLlgQAlCxZMtOsuB8vf9zna7ADSkREREREVIg1adIEN2/eREhIiPKvevXq6Nq1q/Lf2traCAgIUF4nPDwcERERcHd3BwC4u7vj5s2biI6OVu5z4sQJGBsbw9nZ+auzcAguERERERFRDsgED8H9WkZGRnBxcVFpMzAwgJmZmbK9b9++GDVqFIoVKwZjY2N4enrC3d0dtWrVAgA0a9YMzs7O6N69O+bPn4+oqChMmTIFQ4YMybLq+jnsgBIREREREam5JUuWQENDA506dUJycjKaN2+OVatWKbdramri0KFDGDRoENzd3WFgYICePXvC29s7W/cjUygUitwOT+IlpYpOkP8owKc6/buYd1+/jpW6KGagLTpCvmM3dK/oCPnOnWUe/76TmtHR4plOn9IUPWNLPpQm5/eTTxnqFpznie/ZR0Lvf0Q9G6H3nxN8ZyQiIiIiIiJJsANKREREREREkuA5oERERERERDnAUeXZxwooERERERERSYIVUCIiIiIiohwoKMuw5CesgBIREREREZEk2AElIiIiIiIiSXAILhERERERUQ5ogGNws4sd0EKK49GzoOBB+ZRCwcWvP1XcSEd0hHyH7yeZPVnznegI+Y5pzeGiI+Q7b4KWio6Q76TzcycTDY5HJDXDDigREREREVEO8Efa7ONvLkRERERERCQJdkCJiIiIiIhIEhyCS0RERERElAMaHIKbbayAEhERERERkSRYASUiIiIiIsoBDc5ClG2sgBIREREREZEk2AElIiIiIiIiSXAILhERERERUQ5wBG72sQJKREREREREkmAFlIiIiIiIKAc4CVH2sQJKREREREREkmAHlIiIiIiIiCTBIbhEREREREQ5wBG42ccKKBEREREREUmCFVAiIiIiIqIcYDUv+3jMiIiIiIiISBLsgBIREREREZEkOASXiIiIiIgoB2SchSjbWAElIiIiIiIiSbACSkRERERElAOsf2YfK6BEREREREQkCXZAiYiIiIiISBIcgktERERERJQDGpyEKNtYAc0lCoUCAwYMQLFixSCTyRASEiI6EhERERERUb7CCmguOXbsGDZv3ozTp0+jfPnyKF68uOhIwvitX4uAE8fx6NFD6OrpoXLlKhgxagysbcqLjibM6pXLsXb1CpU2axsb7D94TFAi6V29chlbNvshNPQ2XsXEYLHvCjRq0hQAkJqailXLl+LPs4F49vwZDA0NUbNWbQwbMQoWFiUEJ887H49J2F/HZNE/jslHDx8+wLIlCxF85TLS5HKUL2+LBUuWwdKylKDU0pLL5VizagWOHPoNsa9ewdzcAm07dET/nwap7dT3u3dux+5dO/Di+XMAgK2dPX4aNBh16zUQnCzvGOrrwmtQK7Rr5AZzU0NcD3+OMQt/xdXQCADA5AEt8F3zqihToihSUuW4FvYU01cdxuVbT5S3cefgNFiVMlO53anLD2Lh5j8kfSxS27l9G/w3+eHVqxg4ODphwqSpcHVzEx1LCL6f/PW5s+kfn8VLVT93Ak4cx57dOxEWehtxcXHYuWcfHJ0qCEyc/6nHMyd3sQOaSx48eABLS0vUrl07y+0pKSnQ0dGROJUYVy5fwg+du6KiqyvkaXIsX7oYA/v3xa+/HYa+vr7oeMLY2tlj7YZNysuampoC00gvKSkJDg5OaN+xE0aP8FTZ9uHDB4SFhaL/T4Ph4OiId+/eYcG8ORjhORjbd+0VlDjvffjHMRnzyTEBgKdPI9C3Rxe09/gWAwd7wsDQEA/v34eujq6AtGJs9luPPbt2wHv2XNja2eH27VuYPmUSDA0N0aVbD9HxhLAoURLDR45BOSsrKBQKHDywH8OHDsGuvftgZ2cvOl6eWD31RzjbWqLP1K2IjIlD51bVcXj1YFT91gcvYuJwPyIGI+ftwaPnsSiiqw3Prg1xcOUguLSfiVdvE5S3M2P1YWzad0F5+X1CsoiHI5ljR49g4XwfTPGaAVfXStj2sz8G/dQXBw4dg5mZ2b/fQCHD95O/Posds/4s/ri9ctVq+KZ5S8ycPlVAQlIH7IDmgl69esHf3x9AxmK0VlZWsLa2houLC7S0tLB161a4urri1KlTCAwMxNixY3H9+nUUK1YMPXv2xKxZs6CllfGf4v379xg4cCD2798PY2NjjBs3DgcOHEDlypXh6+sr8FF+vdXr/FQue8+ei0b13BEWehvVqv9PUCrxNDU1Uby4uegYwtStVx9169XPcpuRkRHWrN+o0jZh0lR06/wdIiNfFNpqX5169VHnM8cEAFYu80Wdeg0wYtRYZVvZsuWkiJZvXA+5hgaNmqBeg4YAgFKly+DYkcO4ffOm2GACNWzUWOWy5/CR2L1zB25cDymUHVA9XW10aFwJ343egHPXHgAAZq87hlb1XdD/2zqYsfoIdh27qnKd8Yv3oXcHd7jYl8bpy3eV7fEJyXgZ+17S/CL97L8JHt9+jw4dOwEApnjNwJkzp7H/173o23+A4HTS4/vJlz+LAaBNu/YAgBfPn0kVidQQzwHNBUuXLoW3tzfKlCmDyMhIXL58GQDg7+8PHR0dnDt3DmvWrMHz58/RqlUr/O9//8P169exevVq+Pn5YdasWcrbGjVqFM6dO4fffvsNJ06cwNmzZxEcHCzqoeWK+PcZH/bGJiaCk4gVEfEE3zSqi9YtmmDi+NGIjHwhOlK+9v79e8hkMhgZGYuOIkR6ejr+PHMaVlbWGPxTXzRpUBs9unyPUwGFe7jgpypVroJLQRfw5PEjAED4nTsICQ7+Ysddncjlchw9chhJSYmoVKmK6Dh5QktTA1pamviQnKbS/iE5FbUrZz61Q1tLE309auPt+0TcvPdcZdvoXk3xLGAOLmwbi5HdG0NTs/B+DUpNSUFY6G3Ucv97ZJaGhgZq1aqNG9evCUwmDt9PKC/IZGL/CiJWQHOBiYkJjIyMoKmpiZIlSyrb7e3tMX/+fOXlyZMno2zZslixYgVkMhmcnJzw4sULjB8/HtOmTUNCQgL8/f2xfft2NGnSBACwadMmlCpVcKs/6enpmD9vDipXqQp7ewfRcYRxdXOD9ywfWFvb4NWrGKxZtRJ9enTFnv0HYWBgKDpevpOcnIxlSxaiRcvWMDRUz+Pz+nUsEhMTsWnjegweOhzDR47B+T/PYsxIT6zz80e1/9UQHVESvfsNQHxCAjq2bQVNTU3I5XIMGTYCrdq0FR1NqHt3w9G9y49ISUmGvr4+lixbCVs7O9Gx8kR8YjIuXn+Eif2aIfxRFF6+fo/vm1dDTVdrPHgao9yvZb2K2DKnJ/T1tBH16h3aDF6N2H8Mv1218wyu3XmGN3GJqFXJBt5D26BkcWOMX7JfwKPKe2/evoFcLs801NbMzAyPHj0UlEosvp8Q5Q/sgOahatWqqVwOCwuDu7u7yonuderUQXx8PJ49e4Y3b94gNTUVNWr8/cXSxMQEjo6OX7yf5ORkJCernsei0NSFrq7488TmzJqBB/fuYfPP20VHEeqfk4M4ODrBxbUSWjVrhOPHjqJjp+8EJst/UlNTMW7MCCgATJo6XXQcYRTp6QCAhg0bo1uPXgAAR6cKuH79Gvb8slNtOqDHjx3F0UMHMWfeQtja2SH8zh0snDcH5hYWaNe+o+h4wlhb22D33v2Ij3+PE8d/x9RJ4+G3eWuh7YT2mfYz1k7rgoe/z0Ramhwhd55h9+/BqFKhjHKfwMv3ULPzfBQvaoDeHWtj69xeqN9zMWLexAMAlm07rdz31v0XSElNw4rJP2DqioNISZVL/ZBIAL6fUF5QlwmsclPhHXuSDxgYGEhyPz4+PjAxMVH5WzDPR5L7/pI5s7xxJvA01m/yR4l/VIYJMDY2RjkrazyNiBAdJV9JTU3F+DEjEfniBVav81Pb6icAFDU1hZaWFsrbqnYobGxsERUZKSiV9HwXLUDvfv3RolVr2Ds4ok279ujaoxc2bVgnOppQ2jo6KGdlBeeKLhg+cjQcHJ2wbesW0bHyzKNnsWg2YDnM6oyFfevpqNdzMbS1NPDoeaxyn8QPKXj47BUu3XqCQTN3IE2ejp4dan32Ni/fegJtLc1MM+MWFqZFTaGpqYnY2FiV9tjYWLWdqZ/vJ0T5AzugEqpQoQIuXLgAhUKhbDt37hyMjIxQpkwZlC9fHtra2spzSAEgLi4Od+/ezermlCZOnIi4uDiVv7HjJ+bZ4/g3CoUCc2Z542TACazf6I8yZcoKy5JfJSYm4NnTpyhurr6TEn3qY+czIuIJ1qzfhKJFTUVHEkpbWwfOFV3w+K9zlT6KePK40E7KlJUPH5Igk6l+VGloaCD9rwoxZUhPT0dqSoroGHku8UMKol69Q1GjImjq7oRDpz8/eYyGhgy62p8f6FXJsTTk8nTEvC6ckxJp6+iggnNFBF38e9bf9PR0BAVdgFshPV/43/D9hCh/4BBcCQ0ePBi+vr7w9PTE0KFDER4eDi8vL4waNQoaGhowMjJCz549MXbsWBQrVgwWFhbw8vKChobGF8v7urqZh9t+SPvMzhKYM3MGjh45BN/lq2Cgb4BXMRnn6BgaGUFPT09cMIEWL5iH+g0bwbJUKcRER2P1yuXQ1NRAi1ZtREeTTGJigkrF9/nzZwi/EwZjExMUL26OsaOG405YKJauXIP0dDlevcp43piYmEBbu3AuYfSlY2JpWQo9evfFhDGjULVadVSvURPn/zyLM4GnsG5j4a10fap+w0bwW78GlpaWsLWzw52wMGzdslk5q6c6WrpkEerWq4+SlpZITEjAkcOHcOXypUwzkBcmTd2dIANw90k0bMuaY87wdrj7OBpbDgZBX08H4/s2w+HAm4h69Q5mRQ3w0/f1UMrcBL/+EQIAqOlqjf+5WCHwyj28T0xGLTdrzBvVETuOXsHb90lCH1te6t6zN6ZOGo+KFV3g4uqGrT/7IykpCR06eoiOJgTfT/79cycu7i2iIiMRHR0NAHj8KONHULPixdV6Jv8vYTUv+2SKf5bjKMd8fX3h6+uLx48fAwAaNmyY5dIpOVmGZefOnWjcuDF8fL5+WK3IDmililmfs+o9ywftBX7oiXymjx8zEsFXL+Pt27cwLVYMVapUw9BhI1G2nNglNaR8+V+5HIT+fXpmam/brgMGDh6K1i2aZnEtYP1Gf1T/X828jqck5dPkyuUgDPjMMZkxey4AYP++vdi0YR2iX0bBytoGAwd7omHjJhKmFDvLXkJCPFYtX4aTAX/gzetYmJtboEWr1hgwaLDQHyY0BB4Ur6mTcOniRcTERMPQyAgODo7o3bc/3GvXEZYJAExrDs+z2+70TWV4D22L0hZF8fpdAg4EXIfXqsN4F/8Bujpa8J/dA/9zsYJZUUO8jkvAldsRmOd3HFdDM75oV3Yqg6UTvoODtQV0tbXw+MVrbD9yGcu2nsrT8z/fBC3Ns9v+Wju2bYX/Jj+8ehUDR6cKGD9pCtzcKgnLky7wwzi/vp9I6cqlz3wWt+8A79lz8dv+X+E1ZVKm7T8NGoKBQzKvG5pX9LULznmVu649//ed8tAPVUoLvf+cYAc0n0tISEDp0qWxaNEi9O3b96uvJ7IDml/xmZ4ZX/6Z8YhkxvkVMhPZAc2v8rIDWlDlhw5ofiOyA0oFR0HqgO4OEbus3veVC95pORyCm89cu3YNd+7cQY0aNRAXFwdvb28AQPv27QUnIyIiIiIi+m/YAc2HFi5ciPDwcOjo6KBatWo4e/as2s5YR0REREREhQc7oPlMlSpVcPXqVdExiIiIiIjoXxScwcL5ByduIiIiIiIiIkmwAkpERERERJQDX1oqkbLGCigRERERERFJgh1QIiIiIiIikgSH4BIREREREeUAq3nZx2NGREREREREkmAFlIiIiIiIKAc4CVH2sQJKREREREREkmAHlIiIiIiIiCTBIbhEREREREQ5wAG42ccKKBEREREREUmCFVAiIiIiIqIc4BxE2ccKKBEREREREUmCHVAiIiIiIiKSBIfgEhERERER5YAGpyHKNlZAiYiIiIiISBKsgBIREREREeUAJyHKPlZAiYiIiIiISBLsgBIREREREZEkOASXiIiIiIgoB2SchCjbWAElIiIiIiIiSbACSkRERERElAOchCj7WAElIiIiIiIiSbADSkRERERERJLgEFxSGxwikZlCdIB8SJEuOkH+k57OZ8qn5DIek0/FXvQVHSHfMW0+R3SEfOf1sUmiI+Q76Qq+nxRkGpyEKNtYASUiIiIiIiJJsAJKRERERESUAxxhl32sgBIREREREZEk2AElIiIiIiIiSXAILhERERERUQ5wCG72sQJKREREREREkmAFlIiIiIiIKAdkXIYl21gBJSIiIiIiIkmwA0pERERERESS4BBcIiIiIiKiHNDgCNxsYwWUiIiIiIiIJMEKKBERERERUQ5wEqLsYwWUiIiIiIiIJMEOKBEREREREUmCQ3CJiIiIiIhyQMYRuNnGCigRERERERFJghVQIiIiIiKiHOAkRNnHCigRERERERFJgh1QIiIiIiIikgSH4BIREREREeWABkfgZhsroERERERERCQJVkCJiIiIiIhygJMQZR8roERERERERCQJdkCJiIiIiIhIEuyAfkHDhg0xYsQI0TGIiIiIiCgfksnE/hVEPAeUct3unduxe9cOvHj+HABga2ePnwYNRt16DQQnE4fHBLh65TK2bPJDaOhtvIqJweKlK9CoSVPldoVCgdUrl2Pfnl/w/v07VKpSFZOmesHKylpc6Dy0ccNanAo4gcePHkJXVw9ulatg2IjRsLYpDwCIi3uLtauW4+L5c4iKikRR02Jo2LgJBg0ZDiMjI8Hp88Ymv3WZjonniNGwtrZR7vPsaQR8F81HSEgwUlNS4F6nHsZOmAwzs+ICk+edTRs+c0xs/j4mA/r0QPCVyyrX8/juB0yaOl3itOLI5XKsWbUCRw79hthXr2BuboG2HTqi/0+DICuo39C+QENDhik96qFzUxeUKGaAyNh4/Pz7Dczdek65T1LApCyvO2ltAJbsDgIAVLYvgVn9G6OaoyXk6enYfyYc41f/gYQPqZI8DpE2bliHZb6L0KVbD4ybMFl0HMlcvXIZWzb7Ieyvz+JFvqqfxVVdnbK83vBRY9Gzd1+pYlIhxw6ohFJSUqCjoyM6Rp6zKFESw0eOQTkrKygUChw8sB/Dhw7Brr37YGdnLzqeEDwmQFJSEhwcndC+YyeMHuGZafvmjRuwY9vP8J49F6VLl8GqFUsx5Kd+2HvgMHR1dQUkzlvBVy7jux+7oGJFV8jlcqxYtgRDBvbDnn2HUERfHzHR0YiJjsaI0eNgY2uHyBcv4DPLC6+iozF/8TLR8fNE8JXL+O6HLnCu6AK5XI6Vy5dg6MC++OXXjGOSlJiIIQP7wcHBEWvWbwYArF65DCM9B2Pz1p3Q0Ch8g3o+Pk+Ux2TZX8fkr+fJRx07fYefhvz9utLTKyIirjCb/dZjz64d8J49F7Z2drh9+xamT5kEQ0NDdOnWQ3S8XDf6R3f0b1cV/ecdROjjV6jmaIm1Y1vjXUIyVu27AgCw/napynWa1bDFmjGtse9sOADA0swQh+d3wZ7TYRi57HcYG+hiweCmWD++LbrM+FXyxySlWzdvYM8vO+Hg4Cg6iuQ+JCXBwSHjs3hMFp/Fx0+dVbl87uwZeHtNQZOmzaSKWOAUvp+48l7h+7TOZenp6Rg3bhyKFSuGkiVLYvr06cptERERaN++PQwNDWFsbIzvv/8eL1++VG6fPn06KleujA0bNsDGxgZ6enoAgD179sDV1RVFihSBmZkZmjZtioSEBOX1NmzYgAoVKkBPTw9OTk5YtWqVZI83NzRs1Bj16jeAlZU1rK1t4Dl8JPT19XHjeojoaMLwmAB169XHkGEj0LjpN5m2KRQKbP95C/oPGIhGjZvAwdERM+fMQ0x0NE4F/CEgbd5bsWYD2rX3gK2dPRwcnTBjpg+iIl8gLPQ2AMDO3gELlixH/YaNUbZsOdSoWQuDPUfiTOAppKWlCU6fN5avXo+27Tsqj8l0bx9ERUYiLCzjmFwPuYbIF8/hNdMHdvYOsLN3wIyZPggLvYXLly4KTp83lq/55JjM/OuY/PU8+UhPTw/Fi5sr/wwNDQUlFuN6yDU0aNQE9Ro0RKnSZfBNsxaoVbsObt+8KTpanqhVsTQOnb+LY0EPEPEyDvvO3EHAlUeo7lRKuc/LNwkqf23r2CMw5AkeR74FALSsZYdUeTpGLDuGe89e42p4JDx9j6FjfSeUL2Uq6JHlvcTEBEyaMBbTps+CkbGJ6DiSq/Pxs7hJ5s9iACrvI8WLmyPw1ElUr1ETZcqWlTgpFWbsgP4Lf39/GBgYICgoCPPnz4e3tzdOnDiB9PR0tG/fHq9fv0ZgYCBOnDiBhw8f4ocfflC5/v3797F37178+uuvCAkJQWRkJDp37ow+ffogLCwMp0+fhoeHBxQKBQBg27ZtmDZtGmbPno2wsDDMmTMHU6dOhb+/v4iH/5/J5XIcPXIYSUmJqFSpiug4+QKPSWbPnz3Dq1cxqOleW9lmZGQEFzc3temkx8e/BwAYm3z+C1H8+/cwMDSElpZ6DF5RHpO/viSmpKRAJpOpjCTR0dWFhoYGQq4FC8kotc89T44eOYQm9d3xfce2WLF0MT4kJYmIJ0ylylVwKegCnjx+BAAIv3MHIcHBqFOvvuBkeePi7edoVMUadmWKAQBcy1vA3bUsjl96kOX+FqYGaFHTDv5HQ5RtutpaSE2V46+vHwCApOSMH7dqu5bJs+yizZnljXr1G6DWPz5vKGuxr17hz7OB6NCxk+goVMiox7eY/8DNzQ1eXl4AAHt7e6xYsQIBAQEAgJs3b+LRo0co+9evQlu2bEHFihVx+fJl/O9//wOQ8YVpy5YtMDc3BwAEBwcjLS0NHh4esLKyAgC4uroq78/LywuLFi2Ch4cHAMDGxgahoaFYu3YtevbsKc2DzgX37oaje5cfkZKSDH19fSxZthK2dnaiYwnFY/J5r17FAACKmZmptJuZFUfsq1ciIkkqPT0dC+fPQaUqVWFn75DlPm/evMGGdavh0el7idOJkZ6ejkXzfVCp8t/HxNWtEvSKFMFy34UY4jkSCoUCy5cuhlwux6uYGMGJ857ymHzyPGnRqg0sLUvB3NwC9+6FY/mSRXjy+BEWLFkuMK20evcbgPiEBHRs2wqampqQy+UYMmwEWrVpKzpanli44zyM9XVwfdNPkKenQ1NDA14bT2NnwO0s9+/WzBXvE1Ow/6/htwBw+tpjzBvUBCO/r4kVv16GgZ4OZvVvBAAoWaxwVtCPHTmMO2Gh2LZzj+goBcLB3/ZDX98AjTn89os0CuF55nmNHdB/4ebmpnLZ0tIS0dHRCAsLQ9myZZWdTwBwdnZG0aJFERYWpuyAWllZKTufAFCpUiU0adIErq6uaN68OZo1a4Zvv/0WpqamSEhIwIMHD9C3b1/0799feZ20tDSYfKEqkpycjOTkZJU2haau0PPmrK1tsHvvfsTHv8eJ479j6qTx8Nu8Va07XDwm9DlzZ3vjwf178Nu8Pcvt8fHxGD7kJ5Qvb4sBg4ZKnE6MeXO88eDBPWzYvE3ZZlqsGOYt8IXP7BnYuX0rNDQ00KxFKzhVcIaGRuH/AjDvr+fJP48JAHh8+/ePEnYODihe3ByD+vfGs6cRKFO2nNQxhTh+7CiOHjqIOfMWwtbODuF37mDhvDkwt7BAu/YdRcfLdd82dMaPTVzQa84BhD6OgZttCSwY0hSRsfHYdjzzsOMeLSphV8BtJKfKlW1hT16h/7yDmDuoKbz7NYJcno5V+64g6nW8clRWYRIVGYn5c2djzfqNhXJegbzw2769aNm6DY8X5Tp2QP+Ftra2ymWZTIb09PSvvr6BgYHKZU1NTZw4cQLnz5/H8ePHsXz5ckyePBlBQUHQ/2tCifXr16NmzZqZrvc5Pj4+mDFjhkrb5KlemDJt+lfnzG3aOjoo91eF17miC27fuoltW7dg2nRvYZlE4zH5vOLFM36keR0bC3NzC2V7bOwrODpWEBVLEvPmeOPPM6exftNWlChZMtP2hIR4eA7qBwMDAyz0XZHpPakwmjdnJv48E4h1G39GiRKqx6RW7To4cPg43r55A01NTRgZG6N543ooXaZwn5+kPCabfs7yefJPLq4ZP5w+jVCfDqjvogXo3a8/WrRqDQCwd3BEZOQLbNqwrlB2QOcMaIyFOy/gl1OhAIDbj2JQroQJxnaunakDWse1LBzLmaH7zH2ZbmfXyVDsOhkKC1MDJCSlQAFg2Lc18OjFWwkehbRCQ2/j9etYdP7eQ9kml8sRfPUydu3YhkvBN7/4XUvdBF+9gsePH2HuwiWio+R7hf/nz9zHDmgOVahQAU+fPsXTp0+VVdDQ0FC8ffsWzs7OX7yuTCZDnTp1UKdOHUybNg1WVlbYt28fRo0ahVKlSuHhw4fo2rXrV2eZOHEiRo0apdKm0Mxfv1alp6cjNSVFdIx8hcfkb6XLlEHx4uYIungBjk4ZHc74+HjcunED333fWXC6vKFQKDDfZyZOnfwD6/y2oHSZzOdcxcfHY+jAvtDR0cHiZasK/a/QGcdkFk6f/ANr/fyzPCYfFTXNmCTlctBFvH4di/oNG0sVU1LZOSYfhYffAQAU/8fom8Luw4ckyGSq01poaGhk6wfjgqSInhbS01WrlPL0dGQ1EXTPlpVwNTwSNx9Gf/b2ot9kTITYo4UbPqSkIeDqo1zNmx/UrFULe/YdVGmbNmUibGzKo3ff/ux8fuLAr3tQwbkiHByzXpaF6L9gBzSHmjZtCldXV3Tt2hW+vr5IS0vD4MGD0aBBA1SvXv2z1wsKCkJAQACaNWsGCwsLBAUFISYmBhUqZHzpnjFjBoYNGwYTExO0aNECycnJuHLlCt68eZOpk/mRrm7m4bYfBE6SuXTJItStVx8lLS2RmJCAI4cP4crlS1i9zk9cKMF4TDJmHnwaEaG8/Pz5M4TfCYOxiQksLUuhS/ce2LBuDcpZWaN06dJYtWIZzC0sVNYnK0zmzvbGsaOHsHjpSugbGCjPgzU0NIKenh7i4+Mx5Ke++PAhCTN9FiAhIR4JCfEAAFPTYoXyy9K8Od44dvQwFvmuyPKYAMBv+3+FTfnyMDUthhvXQ7Bo/hx06dZTZa3QwmTe7L+OydKsj8mzpxE4duQQ6tRrABOTorh3NxyLF8xF1WrVYa9GS0zUb9gIfuvXwNLSErZ2drgTFoatWzYX2slTjly4j/Fda+NpdBxCH79CZbsSGPZtTWw5dl1lPyN9HXjUd8KENQFZ3s7A9tVwMfQZ4pNS0aSaDeYMaIypG04hLiE5y/0LMgMDw0zn2Bcpog+TokU/e+59YfRvn8VAxo+fJ078jlFjxouKSYUcO6A5JJPJcODAAXh6eqJ+/frQ0NBAixYtsHz5lyd9MDY2xpkzZ+Dr64t3797BysoKixYtQsuWLQEA/fr1g76+PhYsWICxY8fCwMAArq6uGDFihASPKne8fh2LKRPHIyYmGoZGRnBwcMTqdX5wr11HdDRheEyA0Fu30L/P3xNpLZo/FwDQtn0HeM+ei159+iEpKQmzpk/D+/fvULlqNaxcs77QVv327N4BABjQR3WNQq+Zc9CuvQfuhN3GrZsZXyY7tFadAOLg0T9QqnThm6Vyz+6dAICf+qpOuOblPQdt/xpG+eTxI6xctgRxcXEoVaoUevcbiK7dC84EbdmlPCZ9PjkmMzOOiZa2Ni5dvIAdW7cgKSkJJUqWROOm36DvgEEi4gozftIUrFq+DHNmeePN64yh/N9+9wMGDBosOlqeGLX8OLx618fS4S1gXlQfkbHx8Dt0DXN+Vl3D8btGzpDJZNj911DdT1V3KoUpverBUE8H4U9jMXTJUez445YUD4EECb19CwP+8X6yeMFfn8XtOmDG7Ix//370MKBQoHnL1kIyFjgcg5ttMkVhPNOchFZAqeBI58s/k0I6Yu8/4cdEFviFIxNNNZgIKrvMWviIjpDvvD42SXSEfIefxZkZ6BSc95OLD94Kvf9atkWF3n9OsAJKRERERESUAzL+IpltWZyuTkRERERERJT72AElIiIiIiIiSXAILhERERERUQ7IOAI321gBJSIiIiIiIkmwAkpERERERJQDLIBmHyugREREREREJAl2QImIiIiIiEgSHIJLRERERESUExyDm22sgBIREREREZEkWAElIiIiIiLKARlLoNnGCigRERERERFJgh1QIiIiIiIikgSH4BIREREREeWAjCNws40VUCIiIiIiIpIEO6BEREREREQ5IBP897V8fHzwv//9D0ZGRrCwsECHDh0QHh6uss+HDx8wZMgQmJmZwdDQEJ06dcLLly9V9omIiEDr1q2hr68PCwsLjB07FmlpadlIwg4oERERERFRoRYYGIghQ4bg4sWLOHHiBFJTU9GsWTMkJCQo9xk5ciQOHjyIX375BYGBgXjx4gU8PDyU2+VyOVq3bo2UlBScP38e/v7+2Lx5M6ZNm5atLDKFQqHItUdG+caH7P0QQWoqnS//TNLTRSfIf/gxkQWe85OJpgYPyqfMWviIjpDvvD42SXSEfIefxZkZ6BSc95Pgx++E3n9Va+McXS8mJgYWFhYIDAxE/fr1ERcXB3Nzc2zfvh3ffvstAODOnTuoUKECLly4gFq1auHo0aNo06YNXrx4gRIlSgAA1qxZg/HjxyMmJgY6Ojpfdd+sgBIREREREeVEQRmD+4m4uDgAQLFixQAAV69eRWpqKpo2barcx8nJCeXKlcOFCxcAABcuXICrq6uy8wkAzZs3x7t373D79u2vvm/OgktERERERFQAJScnIzk5WaVNV1cXurq6n71Oeno6RowYgTp16sDFxQUAEBUVBR0dHRQtWlRl3xIlSiAqKkq5zz87nx+3f9z2tVgBJSIiIiIiygGZ4P/5+PjAxMRE5c/H58vD/4cMGYJbt25h586dEh0lVayAEhERERERFUATJ07EqFGjVNq+VP0cOnQoDh06hDNnzqBMmTLK9pIlSyIlJQVv375VqYK+fPkSJUuWVO5z6dIlldv7OEvux32+BiugREREREREBZCuri6MjY1V/rLqgCoUCgwdOhT79u3DyZMnYWNjo7K9WrVq0NbWRkBAgLItPDwcERERcHd3BwC4u7vj5s2biI6OVu5z4sQJGBsbw9nZ+aszswJKRERERESUA7ICMmHvkCFDsH37dhw4cABGRkbKczZNTExQpEgRmJiYoG/fvhg1ahSKFSsGY2NjeHp6wt3dHbVq1QIANGvWDM7OzujevTvmz5+PqKgoTJkyBUOGDPli1fVT7IASEREREREVYqtXrwYANGzYUKV906ZN6NWrFwBgyZIl0NDQQKdOnZCcnIzmzZtj1apVyn01NTVx6NAhDBo0CO7u7jAwMEDPnj3h7e2drSxcB7SQ4jqg9DW49lhmXAc0M35MZKGA/OItJa4DmhnXAc2M64Bmxs/izArSOqDXI94Lvf9K5YyE3n9O8BxQIiIiIiIikgSH4BZSqWks43xKg7/OZ8KKRWYamqIT5D8KBZ8nnyoo5/yQWG9+Z7XvU6Z1xoqOkO9EB84THSEf4ptsYcYOKBERERERUU6wr5xtHIJLREREREREkmAFlIiIiIiIKAdkLIFmGyugREREREREJAl2QImIiIiIiEgSHIJLRERERESUA5wVPftYASUiIiIiIiJJsAJKRERERESUAyyAZh8roERERERERCQJdkCJiIiIiIhIEhyCS0RERERElBMcg5ttrIASERERERGRJFgBJSIiIiIiygEZS6DZxgooERERERERSYIdUCIiIiIiIpIEh+ASERERERHlgIwjcLONFVAiIiIiIiKSBCugREREREREOcACaPaxAkpERERERESSYAeUiIiIiIiIJMEhuERERERERDnBMbjZxgooERERERERSYIVUCIiIiIiohyQsQSabayAEhERERERkSTYAc1DvXr1QocOHb64j7W1NXx9fSXJQ0REREREJBKH4Ap2+fJlGBgYiI6RY5v81uFUwAk8fvQQurp6cKtcBZ4jRsPa2kZlvxvXr2HV8qW4dfMGNDU14ODohOWrN0BPT09Q8rx19cplbNnsh7DQ23gVE4NFvivQqElT5XavyRNw8Lf9Ktdxr1MXK9dskDipOLt3bsfuXTvw4vlzAICtnT1+GjQYdes1EJxMHB6TL9u4YR2W+S5Cl249MG7CZNFxhLl65TI2b/RDWOgtxMTEYMmylWj8j/cXdcTXzuft3L4N/pv88OpVDBwcnTBh0lS4urmJjpUnDPV14fVTc7Rr4AJzU0Ncv/scYxYfwNWwZwCA9g1d0M/DHVWcSsPMxAA1uy3BjXsvVG7DprQZ5g5rA/dK1tDV0cKJC+EYtWg/ol/Hi3hIuYrf2fKGjCNws40VUMHMzc2hr68vOkaOBV+5jO9+6IJNP+/EyrV+SEtLxdCBfZGUmKjc58b1a/AcPAC13OvAf9su+G//Bd//2BUaGoX36fchKQkODk6YMHnaZ/epXacejp86q/zzmbdIwoTiWZQoieEjx2DHL79i++69qFGzFoYPHYL79++JjiYMj8nn3bp5A3t+2QkHB0fRUYRLSkqEo6MjJk7xEh0l3+BrJ2vHjh7Bwvk++GnwEOz8ZR8cHZ0w6Ke+iI2NFR0tT6ye9C0a17BHn+k7UL3rIvwRdBeHVwxAKXNjAIB+ER2cv/4IU1YcyfL6+nraOLSsPxQKBVoOWYvG/VdCR1sTexf2hqwQ9DL4nY3yCz6bcsGePXvg6uqKIkWKwMzMDE2bNkVCQoJy+8KFC2FpaQkzMzMMGTIEqampym2fDsGVyWRYvXo1WrZsiSJFiqB8+fLYs2ePlA8nW5avXo+27TvC1s4eDo5OmO7tg6jISISF3Vbus3jBXPzYuRt69e0PWzt7WFvb4JvmLaGjoyMwed6qU68+hgwbgcZNvvnsPjo6Oihe3Fz5Z2xiImFC8Ro2aox69RvAysoa1tY28Bw+Evr6+rhxPUR0NGF4TLKWmJiASRPGYtr0WTAyVq/XSVbq1muAocNHoknTz7+/qBu+drL2s/8meHz7PTp07ARbOztM8ZoBPT097P91r+houU5PVwsdGrli8orDOBfyCA+fxWL2hhN48CwW/T3cAQA7jgbDx+8PnLyc9Q8T7pVsYGVpiv4zd+H2gyjcfhCFfjN2oWqFMmhY3U7Kh5Mn+J0tb8gE/xVE7ID+R5GRkejcuTP69OmDsLAwnD59Gh4eHlAoFACAU6dO4cGDBzh16hT8/f2xefNmbN68+Yu3OXXqVHTq1AnXr19H165d8eOPPyIsLEyCR/Pfxce/BwAY//Ul8XVsLG7dvAHTYmbo06MzmjWqiwF9uiMk+KrImPnClSuX0KRBbXRs2wJzZk7H27dvREcSRi6X4+iRw0hKSkSlSlVEx8kXeEz+NmeWN+rVb4Ba7rVFR6ECgK+dDKkpKQgLva3yutHQ0ECtWrVx4/o1gcnyhpamJrS0NPEhOU2l/UNyKmpXsvnMtVTpamtCoVAgOeXv2/iQkor0dAVqV7LOzbj5Ar+zkSg8B/Q/ioyMRFpaGjw8PGBlZQUAcHV1VW43NTXFihUroKmpCScnJ7Ru3RoBAQHo37//Z2/zu+++Q79+/QAAM2fOxIkTJ7B8+XKsWrUqbx/Mf5Seno5F831QqXJV2Nk7AACeP38KAFi/ZgWGjxoHB0cnHD50AIMG9Mauvb+hnJW1wMTi1K5bD42bNkOp0qXx7OlTrFi2BJ6DBmDz1p3Q1NQUHU8y9+6Go3uXH5GSkgx9fX0sWbYStnYF/1fm/4LHRNWxI4dxJywU23bm35EglD/wtaPqzds3kMvlMDMzU2k3MzPDo0cPBaXKO/GJybh44zEm9mmK8MfRePn6Pb5vVgU1Xazw4Nmrr7qNS7cikPAhBbOHtsa0VUchkwGzhrSClpYmShY3zuNHIC1+ZyOR2AH9jypVqoQmTZrA1dUVzZs3R7NmzfDtt9/C1NQUAFCxYkWVDoWlpSVu3rz5xdt0d3fPdDkkJOSz+ycnJyM5OVmlLUWhDV1d3Ww+mv9m3hxvPHhwDxs2b1O2padnVII9vv0B7Tp4AACcKjjjctBF/Lb/VwwdPkrSjPlF85atlf+2d3CEvYMj2rX6BlcuX0LNWu5fuGbhYm1tg9179yM+/j1OHP8dUyeNh9/mrWr9pZHH5G9RkZGYP3c21qzfKPn7GRU8fO1Qn+k7sXbKd3h4eCrS0uQICX+O3cdDUMWp9Fdd/9XbBHSdtBXLxnlg8Pd1kJ6uwO4TIQi+80z5faaw4He2XFRQx8EKxCG4/5GmpiZOnDiBo0ePwtnZGcuXL4ejoyMePXoEANDW1lbZXyaTIT09PVcz+Pj4wMTEROVv0YK5uXof/2benJn480wg1qz3R4kSJZXtxYubAwBsytuq7G9jUx5RUZGSZszPypQti6Kmpnga8UR0FElp6+ignJUVnCu6YPjI0XBwdMK2rVtExxKKx+RvoaG38fp1LDp/74FqlZxRrZIzrl65hB3bfka1Ss6Qy+WiI1I+wteOKtOiptDU1Mw04VBsbCyKFy8uKFXeevQ8Fs0GrYFZg0mwbzcb9fosh7aWBh69eP3VtxEQdBcVO81FuRYzUKb5dPSdvhOlzE3w+EXhmbiJ39lINHZAc4FMJkOdOnUwY8YMXLt2DTo6Oti3b1+Ob+/ixYuZLleoUOGz+0+cOBFxcXEqf6PHTsjx/WeHQqHAvDkzcfrkH1i9fhNKlymjsr1U6dIwN7fAk8ePVNqfPHkCS8tSkmQsCF5GRSHu7VuYm1uIjiJUeno6UlNSRMfIV9T5mNSsVQt79h3Erj37lX/OFV3QqnVb7NqzX62Gq1P2qfNrB8jokFdwroigixeUbenp6QgKugC3Qn5ubOKHVETFvkdRoyJoWssRh87c/vcrfSI2LhFx8R/QoJotLEwNcOhMaB4klRa/s+UNmeD/FUQcgvsfBQUFISAgAM2aNYOFhQWCgoIQExODChUq4MaNGzm6zV9++QXVq1dH3bp1sW3bNly6dAl+fn6f3V9XVzfT8LT3H3K3yvo58+Z449jRw1jkuwL6BgZ49SoGAGBoaAQ9PT3IZDJ079UHa1evgL2jExwdnXDot/148vgh5i/ylSSjCImJCXgaEaG8/Pz5M4TfCYPxXxXqtatXoknTZihevDiePn2KpYsXoGy5cnCvU1dgamktXbIIdevVR0lLSyQmJODI4UO4cvkSVq/7/HO9sOMxUWVgYKg8N+mjIkX0YVK0aKZ2dZKYkICIf76/PHuGO2FhMDExgWUp9fySyNdO1rr37I2pk8ajYkUXuLi6YevP/khKSkKHjh6io+WJpjUdIJPJcPdJNGzLFscczza4+yQaWw5eBgCYGhdB2RKmsPxrWRYHq4yK38vY93j5OmNCnu5tqiP8cTRi3iSgpqsVFo5qh+U7zuJeRIyYB5WL+J2N8gt2QP8jY2NjnDlzBr6+vnj37h2srKywaNEitGzZErt27crRbc6YMQM7d+7E4MGDYWlpiR07dsDZ2TmXk+eOPbt3AgB+6ttTpd3Lew7atu8IAOjSrSdSklOwZMFcxMXFwcHRESvX+KFM2XKS55VK6O1bGNDn72Oy+K8h0W3bdcDEqdNx7244Dv22H+/fvYe5hTlqudfB4KHD1Wqa89evYzFl4njExETD0MgIDg6OWL3OD+6164iOJgyPCX2N27dvoV/vHsrLC+f7AADate+ImXOkPf0iv+BrJ2stWrbCm9evsWrFMrx6FQNHpwpYtXYDzArpEFwTQz14D26F0hYmeP0uEQdO3YTX6mNIk2f8KN+6XkWsn/aDcv+fZ3cDAMxafxyzN5wAADiUM4f34FYoZlwETyLfYP6mk1i244z0DyYP8Dsb5Rcyxcf1QihfkMlk2LdvHzp06PCfbkeqCmhBoqFRMIcp5CVNHhP6CvyUyKwQrElPJIRpnbGiI+Q70YHzREfId4z0Cs5Zgvejk4Tev51FEaH3nxMF578uERERERERFWgcgktERERERJQDHBCTfeyA5jMcEU1ERERERIUVh+ASERERERGRJFgBJSIiIiIiygmOwc02VkCJiIiIiIhIEqyAEhERERER5YCMJdBsYwWUiIiIiIiIJMEOKBEREREREUmCQ3CJiIiIiIhyQMYRuNnGCigRERERERFJghVQIiIiIiKiHGABNPtYASUiIiIiIiJJsANKREREREREkuAQXCIiIiIiopzgGNxsYwWUiIiIiIiIJMEKKBERERERUQ7IWALNNlZAiYiIiIiISBLsgBIREREREZEkOASXiIiIiIgoB2QcgZttrIASERERERGRJFgBJSIiIiIiygEWQLOPFVAiIiIiIiKSBDugREREREREJAkOwSUiIiIiIsoBTkKUfayAEhERERERkSRYASUiIiIiIsoRlkCzS6ZQKBSiQ1DuS0oVnSD/SU6Ti46Q7+hpa4qOQEREaoTfOjMrVmOo6Aj5TtK1FaIjfLVnb1KE3n8ZUx2h958THIJLREREREREkuAQXCIiIiIiohzgJETZxwooERERERERSYIVUCIiIiIiohxgATT7WAElIiIiIiIiSbADSkRERERERJLgEFwiIiIiIqIc4CRE2ccKKBEREREREUmCFVAiIiIiIqIckHEaomxjBZSIiIiIiIgkwQ4oERERERERSYJDcImIiIiIiHKCI3CzjRVQIiIiIiIikgQroERERERERDnAAmj2sQJKREREREREkmAHlIiIiIiIiCTBIbhEREREREQ5IOMY3GxjBZSIiIiIiIgkwQooERERERFRDsg4DVG2sQJKREREREREkmAHlIiIiIiIiCTBIbhEREREREQ5wRG42cYKKBEREREREUmCFVAiIiIiIqIcYAE0+1gBzWceP34MmUyGkJAQ0VGIiIiIiIhyFTugX6lhw4YYMWKE6BgFwuqVy1HZxVHlr0PbFqJjCeO/cT1qVnbG4vk+yrbk5GTMnzMT3zRwR0P3ahg/ejhiY18JTCnOzu3b0PKbxvhfFVd0/fE73LxxQ3QkYfzWr0WX7zvB/X9V0LCeO0Z4DsbjRw9Fx8oX+Dz529Url+E5eCCaNqyLShUdcTLgD9GRhONr5/P42lH18uVLTBo/Bg3q1ETNam74tmNb3L51U3SsPGOor4sFYzoh/Ig3Xl9YjFObR6Gac7ks9102+UckXVuBoV0aZrldR1sLF3dOQNK1FXBzKJ2HqamwYwc0lygUCqSlpYmOkW/Y2tnjj9N/Kv82bdkuOpIQobduYt+e3bBzcFRp9104F3+eOQWfBUuw2m8LXsVEY8Ko4YJSinPs6BEsnO+DnwYPwc5f9sHR0QmDfuqL2NhY0dGEuHL5En7o3BU/79iNtes3IS0tDQP790ViYqLoaELxeaIqKSkRjo6OmDjFS3SUfIOvnazxtaPqXVwcenXvDC1tbaxYsx6/HjiMUWPGw9jYRHS0PLN6Whc0ruWEPlP8Uf37Ofjjwh0cXuOJUuaqj7ldIzfUcLXGi+i3n72tOSPaIzImLo8TFzwymdi/gogd0K/Qq1cvBAYGYunSpZDJZJDJZNi8eTNkMhmOHj2KatWqQVdXF3/++Sd69eqFDh06qFx/xIgRaNiwofJyeno65s+fDzs7O+jq6qJcuXKYPXt2lvctl8vRp08fODk5ISIiIg8fZe7S1NRE8eLmyj9T02KiI0kuMTEB0yaNw6RpM2BsZKxsj3//Hr/t24vho8ejeo1aqOBcEVNnzMaN69dw88Z1gYml97P/Jnh8+z06dOwEWzs7TPGaAT09Pez/da/oaEKsXueH9h09YGdnD0cnJ3jPnovIyBcIC70tOppQfJ6oqluvAYYOH4kmTb8RHSXf4Gsna3ztqNq0cT1KliwJ71k+cHV1Q+kyZVG7Tl2ULZd1RbCg09PVRocmlTHZdz/OBT/Aw6evMHvtETx4GoP+39VT7lfK3ASLx3+H3pM2IzVNnuVtNavjjCa1KmDikn1SxadCjB3Qr7B06VK4u7ujf//+iIyMRGRkJMqWLQsAmDBhAubOnYuwsDC4ubl91e1NnDgRc+fOxdSpUxEaGort27ejRIkSmfZLTk7Gd999h5CQEJw9exblCtAbZETEE3zTqC5at2iCieNHIzLyhehIklswZxbq1GuAGrVqq7TfCbuNtLQ01KjprmyztimPkpaWuHU9ROKU4qSmpCAs9DZquf99fDQ0NFCrVm3cuH5NYLL8I/79ewCAsUnh/XX+3/B5QjnB1w5fO1kJPHUSzhVdMGbUMDSq744fvu2AvXt2i46VZ7Q0NaClpYkPKakq7R+SU1G7ii0AQCaTwW9WDyzxD0DYw6gsb8eimBFWTe2MvlO3IDEpJc9zFzQywf8riDgL7lcwMTGBjo4O9PX1UbJkSQDAnTt3AADe3t745puv/xX6/fv3WLp0KVasWIGePXsCAGxtbVG3bl2V/eLj49G6dWskJyfj1KlTMClAH6Kubm7wnuUDa2sbvHoVgzWrVqJPj67Ys/8gDAwMRceTxPFjRxB+JxSbtmX+YIt99Qra2towMjZWaS9WrLhanQf65u0byOVymJmZqbSbmZnhEc/dyhgpMW8OKlepCnt7B9FxhOHzhLKLr50MfO1k9uzZU/yyawe69eiNfv0H4tatm5jvMwva2tpo176j6Hi5Lj4xGRevP8TE/i0R/uglXsa+w/ctqqOmmw0ePI0BAIzu/Q3S5OlYueP0Z29nnXc3rN/zJ4JDI1DOUv1GtFHuYwf0P6pevXq29g8LC0NycjKaNGnyxf06d+6MMmXK4OTJkyhSpMgX901OTkZycrJKW7qGLnR1dbOVLbfUrddA+W8HRye4uFZCq2aNcPzYUXTs9J2QTFJ6GRWJxfN9sHzNBmH/DajgmzNrBh7cu4fNP6vn+dNEOcXXDn1OeroCzhVdMGzEKACAUwVnPLh3D3t27yyUHVAA6DNlC9ZO74qHx2cjLU2OkDtPsfvYFVSpUA5VKpTFkM4NUbvLvM9ef3DnBjDS18OCjcclTE2FHYfg/kcGBgYqlzU0NKBQKFTaUlP/Hvrwb53Jj1q1aoUbN27gwoUL/7qvj48PTExMVP4WzPP51+tJxdjYGOWsrPG0AJ3D+l/cCb2NN69j0bPzt6hdzRW1q7ki+Opl7N6xFbWruaKYmRlSU1Px/t07leu9fv0KZmbFBaWWnmlRU2hqamaaDCM2NhbFi6vPccjKnFneOBN4Gus3+aPEX6Mu1BWfJ5QdfO38ja+dzMzNzWFra6vSZlO+fKE+TejRs1do1m8pzNxHwb7lVNTrvhDaWpp49PwV6lSxhUUxQ9w94o33l5fi/eWlsCplhrmjPHDn8AwAQMP/OaCmmw3ignzx/vJS3P4tY/Kzc9vGYb13d5EPLd/gJETZxwroV9LR0YFcnvWJ2f9kbm6OW7duqbSFhIRAW1sbAGBvb48iRYogICAA/fr1++ztDBo0CC4uLmjXrh0OHz6MBg0afHbfiRMnYtSoUSpt6Rr5p/KWmJiAZ0+fonhbc9FRJFG9pju27zmg0jZz2mRY2digR+9+KFGiJLS0tHD50kU0btoMAPDk8SNERUbCpVJlAYnF0NbRQQXnigi6eAGNmzQFkDF0LijoAn7s3E1wOjEUCgV8Zs/EyYAT8Nv8M8qUKSs6knB8ntDX4GsnM752MqtUpSoeP36k0vbkyWNYWhb+JUUSP6Qg8UMKihoVQdPaFTDZ9wD2B4TgZFC4yn4HVw3B9sOXsOXARQDA6Pl7MH3lIeV2S3MTHFo9FN0nbMLlm4+lfAhUiLAD+pWsra0RFBSEx48fw9DQEOnp6Vnu17hxYyxYsABbtmyBu7s7tm7dilu3bqFKlSoAAD09PYwfPx7jxo2Djo4O6tSpg5iYGNy+fRt9+/ZVuS1PT0/I5XK0adMGR48ezXSe6Ee6upmH2yalZrmrJBYvmIf6DRvBslQpxERHY/XK5dDU1ECLVm3EhZKQgYEBbO3sVdqKFCkCE5OiyvZ2HTth6aJ5MDYxgYGBIRbNnQ1Xt8pwdaskIrIw3Xv2xtRJ41GxogtcXN2w9Wd/JCUloUNHD9HRhJgzcwaOHjkE3+WrYKBvgFcxGefoGBoZQU9PT3A6cfg8UZWYkKAyK/rzZ89wJywMJiYmsCxVSmAycfjayRpfO6q6de+JXt07Y8O6NWjWoiVu3byBvXt2Y6qXt+hoeaapewXIZMDdx9GwLWuOOSM74O6jl9jy2wWkpaXjdVyCyv6paXK8fPUO955EAwCeRr1R2R6fmHHK18OnMXj+hSVbiL6EHdCvNGbMGPTs2RPOzs5ISkrCpk2bstyvefPmmDp1KsaNG4cPHz6gT58+6NGjB27e/HuR46lTp0JLSwvTpk3DixcvYGlpiYEDB2Z5eyNGjEB6ejpatWqFY8eOoXbt2lnul5+8fBmFieNG4e3btzAtVgxVqlTDlm27UawYT1z/aMSYCZDJNDBx9HCkpKSiVu06GDdpquhYkmvRshXevH6NVSuW4dWrGDg6VcCqtRtgpqbDw3bv2gEA6NtLdViT9ywftFfTL4wAnyefun37Fvr17qG8vHB+xikX7dp3xMw5c0XFEoqvnazxtaPKxdUNi31XYNnSxVi3ZiVKly6DseMnoXWbdqKj5RkTQz14e7ZD6RJF8TouEQcCQuC18iDS0rIupBBJQab49IRFKhREVkDzq+TPrG2lzvS0NUVHICIiNcJvnZkVqzFUdIR8J+naCtERvtqbRLHfL031C953OVZAiYiIiIiIcqCgTgQkEmfBJSIiIiIiIkmwAkpERERERJQDMrAEml2sgBIREREREZEk2AElIiIiIiIiSXAILhERERERUQ5wEqLsYwWUiIiIiIiIJMEKKBERERERUQ6wAJp9rIASERERERGRJNgBJSIiIiIiIklwCC4REREREVFOcAxutrECSkRERERERJJgBZSIiIiIiCgHZCyBZhsroERERERERCQJdkCJiIiIiIhIEhyCS0RERERElAMyjsDNNlZAiYiIiIiISBKsgBIREREREeUAC6DZxwooERERERERSYIdUCIiIiIiIpIEh+ASERERERHlBMfgZhsroERERERERCQJVkCJiIiIiIhyQMYSaLaxAkpERERERKQGVq5cCWtra+jp6aFmzZq4dOmS5BnYASUiIiIiIirkdu3ahVGjRsHLywvBwcGoVKkSmjdvjujoaElzsANKRERERESUAzKZ2L/sWLx4Mfr374/evXvD2dkZa9asgb6+PjZu3Jg3B+cz2AElIiIiIiIqgJKTk/Hu3TuVv+Tk5Ez7paSk4OrVq2jatKmyTUNDA02bNsWFCxekjAwoiPLIhw8fFF5eXooPHz6IjpJv8JhkxmOSGY9JZjwmmfGYZMZjkhmPSWY8JpnxmBRcXl5eCgAqf15eXpn2e/78uQKA4vz58yrtY8eOVdSoUUOitBlkCoVCIW2Xl9TFu3fvYGJigri4OBgbG4uOky/wmGTGY5IZj0lmPCaZ8ZhkxmOSGY9JZjwmmfGYFFzJycmZKp66urrQ1dVVaXvx4gVKly6N8+fPw93dXdk+btw4BAYGIigoSJK8AJdhISIiIiIiKpCy6mxmpXjx4tDU1MTLly9V2l++fImSJUvmVbws8RxQIiIiIiKiQkxHRwfVqlVDQECAsi09PR0BAQEqFVEpsAJKRERERERUyI0aNQo9e/ZE9erVUaNGDfj6+iIhIQG9e/eWNAc7oJRndHV14eXl9VXDAtQFj0lmPCaZ8ZhkxmOSGY9JZjwmmfGYZMZjkhmPiXr44YcfEBMTg2nTpiEqKgqVK1fGsWPHUKJECUlzcBIiIiIiIiIikgTPASUiIiIiIiJJsANKREREREREkmAHlIiIiIiIiCTBDigRERERERFJgh1QIiIiIiIikgQ7oJQnUlJSEB4ejrS0NNFR8oWzZ8+iW7ducHd3x/PnzwEAP//8M/7880/BySi/2LJlC5KTkzO1p6SkYMuWLQISiZWamoo+ffrg0aNHoqMQERU6z549++y2ixcvSpiE1BGXYaFclZiYCE9PT/j7+wMA7t69i/Lly8PT0xOlS5fGhAkTBCeU3t69e9G9e3d07doVP//8M0JDQ1G+fHmsWLECR44cwZEjR0RHpHxAU1MTkZGRsLCwUGmPjY2FhYUF5HK5oGTimJiYICQkBDY2NqKj5BumpqaQyWSZ2mUyGfT09GBnZ4devXpJvqi4SKNGjcqy/Z/HpH379ihWrJjEySi/CQ8Px/LlyxEWFgYAqFChAjw9PeHo6Cg4mfScnZ3x559/ZnpdnDt3Dq1bt8bbt2/FBCO1wAoo5aqJEyfi+vXrOH36NPT09JTtTZs2xa5duwQmE2fWrFlYs2YN1q9fD21tbWV7nTp1EBwcLDCZtKpUqYKqVat+1Z86UigUWXYsnj17BhMTEwGJxOvQoQP2798vOka+Mm3aNGhoaKB169aYMWMGZsyYgdatW0NDQwNDhgyBg4MDBg0ahPXr14uOKplr167Bz88P69atQ2BgIAIDA7F+/Xr4+fkhICAAo0aNgp2dHUJDQ0VHldTPP/+MOnXqoFSpUnjy5AkAwNfXFwcOHBCcTIy9e/fCxcUFV69eRaVKlVCpUiUEBwfDxcUFe/fuFR1PcrVq1UKzZs3w/v17ZduZM2fQqlUreHl5CUxG6kBLdAAqXPbv349du3ahVq1aKl+mK1asiAcPHghMJk54eDjq16+fqd3ExEStfmHs0KGD8t8fPnzAqlWr4OzsDHd3dwAZQ35u376NwYMHC0ooRpUqVSCTySCTydCkSRNoaf39tiyXy/Ho0SO0aNFCYEJx7O3t4e3tjXPnzqFatWowMDBQ2T5s2DBBycT5888/MWvWLAwcOFClfe3atTh+/Dj27t0LNzc3LFu2DP379xeUUlofq5ubNm2CsbExACAuLg79+vVD3bp10b9/f3Tp0gUjR47E77//LjitNFavXo1p06ZhxIgRmD17tnIERdGiReHr64v27dsLTii9cePGYeLEifD29lZp9/Lywrhx49CpUydBycTYsGEDvv32W7Rt2xa///47zp8/j3bt2mHWrFkYPny46HhUyHEILuUqfX193Lp1C+XLl4eRkRGuX7+O8uXL4/r166hfvz7i4uJER5Rc+fLlsW7dOjRt2lTlmGzZsgVz585Vu1/lAaBfv36wtLTEzJkzVdq9vLzw9OlTbNy4UVAy6c2YMUP5/6NHj4ahoaFym46ODqytrdGpUyfo6OiIiijMl4beymQyPHz4UMI0+YOhoSFCQkJgZ2en0n7//n1UrlwZ8fHxePDgAdzc3JCQkCAopbRKly6NEydOwNnZWaX99u3baNasGZ4/f47g4GA0a9YMr169EpRSWs7OzpgzZw46dOig8rlz69YtNGzYUG2Owz/p6+vjxo0bmV479+7dQ6VKlZCYmCgomTgpKSlo3bo1EhMTcePGDfj4+GDo0KGiY5EaYAWUclX16tVx+PBheHp6AoCyCrphwwZlpUvd9O/fH8OHD8fGjRshk8nw4sULXLhwAWPGjMHUqVNFxxPil19+wZUrVzK1d+vWDdWrV1erDujHoU7W1tb44YcfVIauqztOQJRZsWLFcPDgQYwcOVKl/eDBg8pzuRISEmBkZCQinhBxcXGIjo7O1AGNiYnBu3fvAGRU/lJSUkTEE+LRo0eoUqVKpnZdXV21+WHiUw0bNsTZs2czdUD//PNP1KtXT1Aqad24cSNT2/Tp09G5c2d069YN9evXV+7j5uYmdTxSI+yAUq6aM2cOWrZsidDQUKSlpWHp0qUIDQ3F+fPnERgYKDqeEBMmTEB6ejqaNGmCxMRE1K9fH7q6uhgzZoyyo65uihQpgnPnzsHe3l6l/dy5c2rbAevZs6foCPlWSkoKHj16BFtbW5Uhyupo6tSpGDRoEE6dOoUaNWoAAC5fvowjR45gzZo1AIATJ06gQYMGImNKqn379ujTpw8WLVqE//3vfwAyjsmYMWOUQ/8vXboEBwcHgSmlZWNjg5CQEFhZWam0Hzt2DBUqVBCUSqx27dph/PjxuHr1KmrVqgUg49SPX375BTNmzMBvv/2msm9hVLlyZchkMvxz8OPHy2vXrsW6deuU8xGo48R3JB0OwaVc9+DBA8ydOxfXr19HfHw8qlativHjx8PV1VV0NKFSUlJw//59xMfHw9nZWWWopbqZO3cuZsyYgf79+yu/RAcFBWHjxo2YOnWqWs6WLJfLsWTJEuzevRsRERGZqjWvX78WlEwczqqdtXPnzmHFihUIDw8HADg6OsLT0xO1a9cWnEyM+Ph4jBw5Elu2bFEu/aWlpYWePXtiyZIlMDAwQEhICICML+DqYMOGDZg+fToWLVqEvn37YsOGDXjw4AF8fHywYcMG/Pjjj6IjSk5D4+vm3SzMna+Pk1F9jU9/vCDKTeyAEpEQu3fvxtKlS1Wmwx8+fDi+//57wcnEmDZtGjZs2IDRo0djypQpmDx5Mh4/foz9+/dj2rRpajnhzvDhw3Hu3Dn4+vqiRYsWuHHjBsqXL48DBw5g+vTpuHbtmuiIlI/Ex8crzwsuX768Wv/IBwDbtm3D9OnTlRMAlipVCjNmzEDfvn0FJyMidccOKOW69PR03L9/H9HR0UhPT1fZltVssIWRh4fHV+/766+/5mGS/CctLQ1z5sxBnz59UKZMGdFx8g1bW1ssW7YMrVu3hpGREUJCQpRtFy9exPbt20VHlJyVlZVyVu1/TqRy//59VK1aVXl+n7qRy+XYv3+/8sebihUrol27dtDU1BScTLxnz54BAN9b/iExMRHx8fGZ1hgm9ebj44MSJUqgT58+Ku0bN25ETEwMxo8fLygZqQP1PpmGct3FixfRpUsXPHnyBJ/+tlGYh7V8Sl3XbfwaWlpamD9/Pnr06CE6Sr4SFRWlHKZuaGionDG6TZs2ajtZVUxMTJZfmhMSErJcM1Ud3L9/H61atcLz58/h6OgIIOOLZNmyZXH48GHY2toKTii99PR0zJo1C4sWLUJ8fDwAwMjICKNHj8bkyZO/euhlYZKUlASFQgF9fX3o6+sjJiYGvr6+cHZ2RrNmzUTHk8yyZcswYMAA6OnpYdmyZV/cV91GmaxduzbLHzYrVqyIH3/8kR1QylPsgFKuGjhwoHImXEtLS7X9krhp0ybREfK1Jk2aIDAwENbW1qKj5BtlypRBZGQkypUrB1tbWxw/fhxVq1bF5cuXoaurKzqeEJxVO7Nhw4bB1tYWFy9eVM56Gxsbi27dumHYsGE4fPiw4ITSmzx5Mvz8/DB37lzUqVMHQMbMptOnT8eHDx8we/ZswQml1759e3h4eGDgwIF4+/YtatSoAR0dHbx69QqLFy/GoEGDREeUxJIlS9C1a1fo6elhyZIln91PJpOpXQc0KioKlpaWmdrNzc0RGRkpIBGpE3ZAKVfdu3cPe/bsyTTNOdE/tWzZEhMmTMDNmzdRrVo1GBgYqGwvrDMQfknHjh0REBCAmjVrwtPTE926dYOfnx8iIiIyLbmhLjirdmaBgYEqnU8AMDMzU+l8qRt/f39s2LBB5X3Dzc0NpUuXxuDBg9WyAxocHKzscO3ZswclS5bEtWvXsHfvXkybNk1tOqD/XMqJyzqpKlu2LM6dO5dpveVz586hVKlSglKRumAHlHJVzZo1cf/+fbXvgFatWhUBAQEwNTVFlSpVvlgJDg4OljBZ/jB48GAAwOLFizNtU6eh2v80d+5c5b9/+OEHWFlZ4fz587C3t0fbtm0FJhOnbt26CAkJwdy5c+Hq6qqsCl+4cEFtZ9XW1dXF+/fvM7XHx8dDR0dHQCLxXr9+DScnp0ztTk5Oajl7NJBx3ufHtWCPHz8ODw8PaGhooFatWtmaCZUKr/79+2PEiBFITU1F48aNAQABAQEYN24cRo8eLTgdFXbsgFKu8vT0xOjRo5Xns2lra6tsV5eFjdu3b68cNvlxHTr626eTU1HmCSFq1aqFWrVqYePGjZg3b57ano9ja2uL9evXi46Rb7Rp0wYDBgyAn5+fyhJGAwcOVMuRAwBQqVIlrFixItM5fitWrEClSpUEpRLLzs4O+/fvR8eOHfH7778rR1FER0fD2NhYcDox5HI5Nm/ejICAgCwnSTx58qSgZGKMHTsWsbGxGDx4sHLZLz09PYwfPx4TJ04UnI4KO86CS7kqq8kePi5yrK6VLaKvYW1tje3bt2dayzEoKAg//vij2g4fe/DgATZt2oSHDx/C19cXFhYWOHr0KMqVK4eKFSuKjie5t2/fomfPnjh48KDyB77U1FS0b98emzZtQtGiRcUGFCAwMBCtW7dGuXLllOcGX7hwAU+fPsWRI0dQr149wQmlt2fPHnTp0gVyuRxNmjTB8ePHAWT80HXmzBkcPXpUcELpDR06FJs3b0br1q2znKPiS+eIFmbx8fEICwtDkSJFYG9vr7ZzDpC02AGlXPVvQ3vUeWHjK1euKJdNcHZ2RrVq1QQnkhZnI/wyPT09hIWFZTof5+HDh3B2dsaHDx8EJRMnMDAQLVu2RJ06dXDmzBmEhYWhfPnymDt3Lq5cuYI9e/aIjijM/fv3VdbQVffTHl68eIGVK1fizp07ADKOyeDBg9X6XLaoqChERkaiUqVKyh+HL126BGNj4yyHLBd2xYsXx5YtW9CqVSvRUYjUHjugRHns2bNn6Ny5M86dO6esTrx9+xa1a9fGzp071Wa9OhsbG1y5cgVmZmaZOln/JJPJlIvJqxN7e3t4eXmhW7duKu0///wzvLy81PKYuLu747vvvsOoUaNU1gG9dOkSPDw8lGs+FnajRo366n2zOq+6MEtNTUWLFi2wZs0a2Nvbi46TL6SmpqJIkSIICQmBi4uL6Dj5RqlSpXD69Gk4ODiIjpIvNGrU6IvzU6jbkGSSFs8BpTwRGhqKiIgI5XkFH6njOUr9+vVDamoqwsLClOv2hYeHo3fv3ujXrx+OHTsmOKE0Pjcb4cffwNR1yZ6POCFEZjdv3sxynToLCwu8evVKQCIxrl27pnI5ODgYaWlpyveTu3fvQlNTU+1GVQCAtrY2bty4ITpGvqKtrY1y5crxlJdPjB49GkuXLsWKFSvU/vMGACpXrqxyOTU1FSEhIbh16xZ69uwpJhSpDXZAKVc9fPgQHTt2xM2bN5XnfgJ/dy7U8QMxMDAQ58+fV35ZBABHR0csX75cLc9N+sjPzw9LlizBvXv3AGRUAEeMGIF+/foJTiYGJ4TIrGjRooiMjMxUMb927RpKly4tKJX0Tp06pfz34sWLYWRkBH9/f5iamgIA3rx5g969e6vt+8nHJYv+OZO0ups8eTImTZqEn3/+WWXJHnXj4eGhcvnkyZM4evQoKlasmGmSxF9//VXKaMJ97pzX6dOnIz4+XuI0pG44BJdyVdu2baGpqYkNGzbAxsYGly5dQmxsLEaPHo2FCxeq5RckBwcHbN26VTlj5UeXLl1Cly5dcP/+fUHJxJk2bRoWL14MT09PlUlDVqxYgZEjR8Lb21twQnE4IcTfxowZg6CgIPzyyy9wcHBAcHAwXr58iR49eqBHjx7w8vISHVFypUuXxvHjxzNNwHTr1i00a9YML168EJRMHE9PT2zZsgX29vZZriusbsOSAaBKlSq4f/8+UlNTYWVllemYqMvyX7179/7qfTdt2pSHSQqO+/fvo0aNGmq7hBFJgxVQylUXLlzAyZMnUbx4cWhoaEBDQwN169aFj48Phg0blmkomTpYsGABPD09sXLlSlSvXh1AxoREw4cPx8KFCwWnE2P16tVYv349OnfurGxr164d3Nzc4OnpqdYdUENDQ/zvf/8THSNfmDNnDoYMGYKyZctCLpfD2dkZaWlp6Nq1K6ZMmSI6nhDv3r1DTExMpvaYmJgs1wctrG7cuAEXFxdoaGjg1q1bqFq1KoCM4cj/pK5DLbn8V4Z/diqTkpKQnp6u7Iw/fvwY+/fvR4UKFdC8eXNREfOdCxcuQE9PT3QMKuRYAaVcZWpqiuDgYNjY2MDW1hYbNmxAo0aN8ODBA7i6uiIxMVF0REmYmpqqfPFJSEhAWloatLQyfvP5+G8DAwO1/JWxaNGiuHz5cqZJQ+7evYsaNWrg7du3YoJRvvT06VPcvHkT8fHxqFKlilpPNtOjRw+cPXsWixYtUlkHdOzYsahXrx78/f0FJ5SGpqYmIiMjYWFhgfLly+Py5cswMzMTHYvysWbNmsHDwwMDBw7E27dv4eTkBG1tbbx69QqLFy/GoEGDREeU1KfDkxUKBSIjI3HlyhVMnTpVLUeYkHRYAaVc5eLiguvXr8PGxgY1a9bE/PnzoaOjg3Xr1qF8+fKi40nG19dXdIR8rXv37li9enWmoXHr1q1D165dBaWi/ODfZny9ePGi8t/qOLRyzZo1GDNmDLp06YLU1FQAgJaWFvr27YsFCxYITiedokWL4tGjR7CwsMDjx4+Rnp4uOlK+dPXqVeVyPRUrVkSVKlUEJxInODhYed7jnj17UKJECVy7dg179+7FtGnT1K4DamJionJZQ0MDjo6O8Pb2RrNmzQSlInXBCijlqt9//x0JCQnw8PDA/fv30aZNG9y9exdmZmbYtWuXcnZPUj//7FikpaVh8+bNKFeuHGrVqgUgo4oTERGBHj16YPny5aJikmCNGjVSufylGV/VeZmAhIQEPHjwAABga2ub6Ry/wm7AgAHYsmULLC0tERERgTJlykBTUzPLfdVxCaPo6Gj8+OOPOH36tMryX40aNcLOnTthbm4uNqAA+vr6uHPnDsqVK4fvv/8eFStWhJeXF54+fQpHR0e1GaEFZEwIee7cObi6uionMyOSEjuglOdev36daUiqupHL5di/f7/KL9Ht2rX77BemwujTjsXnyGQyte5Y0N8WL16M06dPf3bGV3VdnoYyHDt2DPfv38ewYcPg7e0NIyOjLPcbPny4xMnE++GHH/Dw4UNs2bIFFSpUAJCxPFrPnj1hZ2eHHTt2CE4oPTc3N/Tr1w8dO3aEi4sLjh07Bnd3d1y9ehWtW7dGVFSU6IiS0tPTQ1hY2BfX5SbKK+yAEuWx+/fvo1WrVnj+/LnKOqBly5bF4cOHYWtrKzghUf7EGV/pa/Tu3RvLli37bAdUHZmYmOCPP/7INKHZpUuX0KxZM7U8z37Pnj3o0qUL5HI5mjRpguPHjwMAfHx8cObMGRw9elRwQmlVr14d8+bNQ5MmTURHITXEc0DpP/v0RPYvUbd1tgBg2LBhsLW1xcWLF5XrscXGxqJbt24YNmwYDh8+LDghUf7EGV/pa3D5jMzS09MzrXMJANra2mp7vuy3336LunXrIjIyEpUqVVK2N2nSBB07dhSYTIxZs2ZhzJgxmDlzZpbLFxkbGwtKRuqAFVD6z7jO1pcZGBjg4sWLcHV1VWm/fv066tSpwwWfiT6DM74S5Uz79u3x9u1b7NixA6VKlQIAPH/+HF27doWpqSn27dsnOCGJpqGhofz3P0+RUigUkMlkkMvlImKRmmAFlP4zdexUZoeurm6W1Zr4+Hjo6OgISERUMHDGV6KcWbFiBdq1awdra2uULVsWABAREQFXV1ds3bpVcDrKDzZt2oSyZctmmosiPT0dERERglKRumAFlPJEdHQ0wsPDAQCOjo6wsLAQnEicHj16IDg4GH5+fipVnP79+6NatWrYvHmz2IBE+Zy6z/hKlBMKhQIBAQHKye8qVKiApk2bCk5F+cU/19L9p9jYWFhYWLACSnmKHVDKVe/evcOQIUOwc+dO5ZuXpqYmfvjhB6xcuTLTulPq4O3bt+jZsycOHjyoPCcnLS0N7dq1w+bNm9XymBARUd4KCAhAQEAAoqOjM533uXHjRkGpKL/Q0NDAy5cvMy3J8+TJEzg7OyMhIUFQMlIHHIJLuap///64du0aDh06BHd3dwDAhQsXMHz4cPz000/YuXOn4ITSK1q0KA4cOIB79+7hzp07ADJ+ibazsxOcjIiICqMZM2bA29sb1atXh6WlpVovg0aqPq7JLZPJMHXqVOjr6yu3yeVyBAUFoXLlyoLSkbpgBZRylYGBAX7//XfUrVtXpf3s2bNo0aIFf1EjIiLKY5aWlpg/fz66d+8uOgrlMx/X5A4MDIS7u7vKXBQ6OjqwtrbGmDFjYG9vLyoiqQFWQClXmZmZZTmk1MTERLmQvLpRKBTYs2cPTp06leVQKHVcmoaIiPJOSkoKateuLToG5UOnTp0CkLGCwdKlS7ncCgmh8e+7EH29KVOmYNSoUYiKilK2RUVFYezYsZg6darAZOKMGDEC3bt3x6NHj2BoaAgTExOVPyIiotzUr18/bN++XXQMysc2bdrEzicJwyG4lKuqVKmC+/fvIzk5GeXKlQOQMfW7rq5upuEcwcHBIiJKrlixYti6dStatWolOgoRERVSH8/tAzKW0vD394ebmxvc3NyUE+B9tHjxYqnjEREpcQgu5aoOHTqIjpDvmJiYoHz58qJjEBFRIXbt2jWVyx8nkrl165ZKOyckIiLRWAGlXCOXy3Hu3Dm4ubmhaNGiouPkG/7+/jh27Bg2btyIIkWKiI5DRERERCQMO6CUq/T09BAWFgYbGxvRUfKNpKQkdOzYEefOnYO1tXWmoVDqMhSZiIiIiIhDcClXubi44OHDh+yA/kPPnj1x9epVdOvWDSVKlODwJyIiIiJSW6yAUq46duwYJk6ciJkzZ6JatWowMDBQ2a6OM659bm1UIiIiIiJ1ww4o5SoNjb9X9vlnpU+hUEAmk0Eul4uIJZSTkxN2794NNzc30VGIiIiIiITiEFzKVR8XOKa/LVq0COPGjcOaNWtgbW0tOg4RERERkTCsgBLlMVNTUyQmJiItLQ36+vqZJiF6/fq1oGRERERERNJiBZT+sxs3bsDFxQUaGhq4cePGF/dVx2Govr6+oiMQEREREeULrIDSf6ahoYGoqChYWFhAQ0MDMpkMWT2t1PUcUCIiIiIiysAKKP1njx49grm5ufLflJlcLsf+/fsRFhYGAKhYsSLatWsHTU1NwcmIiIiIiKTDCijlidDQUERERCAlJUXZJpPJ0LZtW4GpxLh//z5atWqF58+fw9HREQAQHh6OsmXL4vDhw7C1tRWckIiIiIhIGuyAUq56+PAhOnbsiJs3b6oMxf24JIs6DsFt1aoVFAoFtm3bhmLFigEAYmNj0a1bN2hoaODw4cOCExIRERERSUPj33ch+nrDhw+HjY0NoqOjoa+vj1u3buHMmTOoXr06Tp8+LTqeEIGBgZg/f76y8wkAZmZmmDt3LgIDAwUmIyIiIiKSFs8BpVx14cIFnDx5EsWLF4eGhgY0NTVRt25d+Pj4YNiwYbh27ZroiJLT1dXF+/fvM7XHx8dDR0dHQCIiIiIiIjFYAaVcJZfLYWRkBAAoXrw4Xrx4AQCwsrJCeHi4yGjCtGnTBgMGDEBQUBAUCgUUCgUuXryIgQMHol27dqLjERERERFJhhVQylUuLi64fv06bGxsULNmTcyfPx86OjpYt24dypcvLzqeEMuWLUPPnj3h7u4ObW1tAEBaWhratWvHNUKJiIiISK1wEiLKVb///jsSEhLg4eGB+/fvo02bNrh79y7MzMywa9cuNG7cWHREYe7fv69chqVChQqws7MTnIiIiIiISFrsgFKee/36NUxNTZUz4aobb29vjBkzBvr6+irtSUlJWLBgAaZNmyYoGRERERGRtNgBJcpjmpqaiIyMhIWFhUp7bGwsLCws1HJpGiIiIiJST5yEiCiPKRSKLKu/169fV1mahYiIiIiosOMkRER55OOwY5lMBgcHB5VOqFwuR3x8PAYOHCgwIRERERGRtDgElyiP+Pv7Q6FQoE+fPvD19YWJiYlym46ODqytreHu7i4wIRERERGRtNgBJcpjgYGBqF27tnIJFiIiIiIidcUOKFEei4iI+OL2cuXKSZSEiIiIiEgsdkCJ8piGhsYXl6DhLLhEREREpC44CRFRHrt27ZrK5dTUVFy7dg2LFy/G7NmzBaUiIiIiIpIeK6BEghw+fBgLFizA6dOnRUchIiIiIpIE1wElEsTR0RGXL18WHYOIiIiISDIcgkuUx969e6dyWaFQIDIyEtOnT4e9vb2gVERERERE0mMHlCiPFS1aNNMkRAqFAmXLlsXOnTsFpSIiIiIikh7PASXKY4GBgSqXNTQ0YG5uDjs7O2hp8TcgIiIiIlIf7IASSSQ0NBQRERFISUlRaW/Xrp2gRERERERE0mL5hSiPPXz4EB4eHrhx4wZkMhk+/ubzcVgu1wElIiIiInXBWXCJ8tjw4cNhbW2N6Oho6Ovr49atWzhz5gyqV6/OJViIiIiISK1wCC5RHitevDhOnjwJNzc3mJiY4NKlS3B0dMTJkycxevRoXLt2TXREIiIiIiJJsAJKlMfkcjmMjIwAZHRGX7x4AQCwsrJCeHi4yGhERERERJLiOaBEeczFxQXXr1+HjY0Natasifnz50NHRwfr1q1D+fLlRccjIiIiIpIMh+AS5bHff/8dCQkJ8PDwwP3799GmTRvcvXsXZmZm2LVrFxo3biw6IhERERGRJNgBJRLg9evXMDU1Vc6ES0RERESkDtgBJSIiIiIiIklwEiIiIiIiIiKSBDugREREREREJAl2QImIiIiIiEgS7IASERERERGRJNgBJSIi+oxevXqhQ4cOyssNGzbEiBEjJM9x+vRpyGQyvH37VvL7JiIiyk3sgBIRUYHTq1cvyGQyyGQy6OjowM7ODt7e3khLS8vT+/31118xc+bMr9qXnUYiIqLMtEQHICIiyokWLVpg06ZNSE5OxpEjRzBkyBBoa2tj4sSJKvulpKRAR0cnV+6zWLFiuXI7RERE6ooVUCIiKpB0dXVRsmRJWFlZYdCgQWjatCl+++035bDZ2bNno1SpUnB0dAQAPH36FN9//z2KFi2KYsWKoX379nj8+LHy9uRyOUaNGoWiRYvCzMwM48aNw6dLZX86BDc5ORnjx49H2bJloaurCzs7O/j5+eHx48do1KgRAMDU1BQymQy9evUCAKSnp8PHxwc2NjYoUqQIKlWqhD179qjcz5EjR+Dg4IAiRYqgUaNGKjmJiIgKMnZAiYioUChSpAhSUlIAAAEBAQgPD8eJEydw6NAhpKamonnz5jAyMsLZs2dx7tw5GBoaokWLFsrrLFq0CJs3b8bGjRvx559/4vXr19i3b98X77NHjx7YsWMHli1bhrCwMKxduxaGhoYoW7Ys9u7dCwAIDw9HZGQkli5dCgDw8fHBli1bsGbNGty+fRsjR45Et27dEBgYCCCjo+zh4YG2bdsiJCQE/fr1w4QJE/LqsBEREUmKQ3CJiKhAUygUCAgIwO+//w5PT0/ExMTAwMAAGzZsUA693bp1K9LT07FhwwbIZDIAwKZNm1C0aFGcPn0azZo1g6+vLyZOnAgPDw8AwJo1a/D7779/9n7v3r2L3bt348SJE2jatCkAoHz58srtH4frWlhYoGjRogAyKqZz5szBH3/8AXd3d+V1/vzzT6xduxYNGjTA6tWrYWtri0WLFgEAHB0dcfPmTcybNy8XjxoREZEY7IASEVGBdOjQIRgaGiI1NRXp6eno0qULpk+fjiFDhsDV1VXlvM/r16/j/v37MDIyUrmNDx8+4MGDB4iLi0NkZCRq1qyp3KalpYXq1atnGob7UUhICDQ1NdGgQYOvznz//n0kJibim2++UWlPSUlBlSpVAABhYWEqOQAoO6tEREQFHTugRERUIDVq1AirV6+Gjo4OSpUqBS2tvz/SDAwMVPaNj49HtWrVsG3btky3Y25unqP7L1KkSLavEx8fDwA4fPgwSpcurbJNV1c3RzmIiIgKEnZAiYioQDIwMICdnd1X7Vu1alXs2rULFhYWMDY2znIfS0tLBAUFoX79+gCAtLQ0XL16FVWrVs1yf1dXV6SnpyMwMFA5BPefPlZg5XK5ss3Z2Rm6urqIiIj4bOW0QoUK+O2331TaLl68+O8PkoiIqADgJERERFTode3aFcWLF0f79u1x9uxZPHr0CKdPn8awYcPw7NkzAMDw4cMxd+5c7N+/H3fu3MHgwYO/uIantbU1evbsiT59+mD//v3K29y9ezcAwMrKCjKZDIcOHUJMTAzi4+NhZGSEMWPGYKMkfXMAAAFgSURBVOTIkfD398eDBw8QHByM5cuXw9/fHwAwcOBA3Lt3D2PHjkV4eDi2b9+OzZs35/UhIiIikgQ7oEREVOjp6+vjzJkzKFeuHDw8PFChQgX07dsXHz58UFZER48eje7du6Nnz55wd3eHkZEROnbs+MXbXb16Nb799lsMHjwYTk5O6N+/PxISEgAApUuXxowZMzBhwgSUKFECQ4cOBQDMnDkTU6dOhY+PDypUqIAWLVrg8OHDsLGxAQCUK1cOe/fuxf79+1GpUiWsWbMGc+bMycOjQ0REJB2Z4nOzKxARERERERHlIlZAiYiIiIiISBLsgBIREREREZEk2AElIiIiIiIiSbADSkRERERERJJgB5SIiIiIiIgkwQ4oERERERERSYIdUCIiIiIiIpIEO6BEREREREQkCXZAiYiIiIiISBLsgBIREREREZEk2AElIiIiIiIiSbADSkRERERERJL4P6Sbl0CF2Yt/AAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "9mQLWAFHeAK2"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}