{
  "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": [],
      "metadata": {
        "id": "Qx6NcNP7rOs5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Image Classification using Artificial Neural Networks"
      ],
      "metadata": {
        "id": "E3uajpjyr0Ki"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Student Name- Teja Vamsi Devalla<br>\n",
        "Student ID- 2505092<br>\n",
        "Module- Application of Machine Learning<br>\n",
        "Module Code-ACCA7025<br>\n",
        "Lecturer- Mark Huntly<br>\n"
      ],
      "metadata": {
        "id": "gs1XwZgZrQNY"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive #import the google drive module from google colab\n",
        "\n",
        "\n",
        "import zipfile #import the zipfile module\n",
        "import os #Import operating system module for file and directory operations,\n",
        "import tensorflow as tf #import tensorflow library\n",
        "import cv2 #import opernCV library for image processing,\n",
        "import numpy as np # import numpy for numerical operations and array handling,\n",
        "import matplotlib.pyplot as plt #import matplotlib for data visualisation and plotting heapmaps,\n",
        "import pandas as pd #import pandas for data manipulation and analysis,\n",
        "import os #import os module for interacting with the operation system,\n",
        "import warnings #import warnings module to manage warning messages,\n",
        "import random #import ranodm module for generating random values,\n",
        "import matplotlib.pyplot as plt #import matplotlib for plotting graphs\n",
        "import seaborn as sns #import seaborn for advanced statistical visualisation\n",
        "\n",
        "\n",
        "from tensorflow import keras #import keras from tensorflow\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator #import image generator for image preprocessing and augmentation\n",
        "from tensorflow.keras.models import Sequential #import all the required layes and model class from keras,\n",
        "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Dropout, BatchNormalization, GlobalAveragePooling2D, Input\n",
        "from tensorflow.keras.optimizers import Adam #importing adam optimiser from kera,\n",
        "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint #import training callbacks to improve and control model training,\n",
        "\n",
        "\n",
        "from sklearn.metrics import confusion_matrix #import evaluation metrics from scikit learn,\n",
        "from sklearn.metrics import classification_report #import classification report function from scikit learn,\n",
        "\n",
        "\n",
        "warnings.filterwarnings('ignore') #ignore all warning messages,\n",
        "\n",
        "print(tf.__version__) #display the installed tensorflow version\n",
        "print(keras.__version__) #display the installed keras version"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hZCy4VzoOcpq",
        "outputId": "9fabdecd-14f2-429c-f605-e47621db0511"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "2.20.0\n",
            "3.13.2\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Mount Google Drive\n"
      ],
      "metadata": {
        "id": "B8DSiPH6spHg"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ARwxT78dFoWn",
        "outputId": "36c24dda-0ee7-491e-d588-c5d55ddebcc1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "drive.mount('/content/drive') #mounting google drive to the colab environment, this allows access to files stored in google drive\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "zip_path = \"/content/drive/MyDrive/DeepLearning/archive.zip\" #path of the zip file stored in google drive"
      ],
      "metadata": {
        "id": "6g7V6yXwFxzp"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Extract zip file\n"
      ],
      "metadata": {
        "id": "0b4mKyXmtYde"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "with zipfile.ZipFile(zip_path, 'r') as zip_ref: #open the zip file in read mode(r)\n",
        "    zip_ref.extractall('/content/data') #extract all files from zip acrhive and into content/data"
      ],
      "metadata": {
        "id": "saxrgfLSGlhV"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### View Extracted files"
      ],
      "metadata": {
        "id": "x2O0eTT4t5nG"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "print(os.listdir('/content/data')) #Display the list of files and folders inside /content/data"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "V_y0mBUmGon4",
        "outputId": "dc50a688-fcd2-4414-e5ca-93d34c78e0c3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['readme.txt', 'cifar10']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Displaying dataset directories"
      ],
      "metadata": {
        "id": "YT84blLvujlS"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "for root, dirs, files in os.walk('/content/data'): #going to all the folders and subfolders in /content/data\n",
        "  print(root)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "B76MCbu6Gv0p",
        "outputId": "b0c9adff-715b-4267-9d18-54ee08a292ec"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/data\n",
            "/content/data/cifar10\n",
            "/content/data/cifar10/test\n",
            "/content/data/cifar10/test/truck\n",
            "/content/data/cifar10/test/cat\n",
            "/content/data/cifar10/test/automobile\n",
            "/content/data/cifar10/test/dog\n",
            "/content/data/cifar10/test/ship\n",
            "/content/data/cifar10/test/deer\n",
            "/content/data/cifar10/test/frog\n",
            "/content/data/cifar10/test/horse\n",
            "/content/data/cifar10/test/bird\n",
            "/content/data/cifar10/test/airplane\n",
            "/content/data/cifar10/train\n",
            "/content/data/cifar10/train/truck\n",
            "/content/data/cifar10/train/cat\n",
            "/content/data/cifar10/train/automobile\n",
            "/content/data/cifar10/train/dog\n",
            "/content/data/cifar10/train/ship\n",
            "/content/data/cifar10/train/deer\n",
            "/content/data/cifar10/train/frog\n",
            "/content/data/cifar10/train/horse\n",
            "/content/data/cifar10/train/bird\n",
            "/content/data/cifar10/train/airplane\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Load image datasets"
      ],
      "metadata": {
        "id": "8NlY8Il8vMNj"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "train_dataset = tf.keras.utils.image_dataset_from_directory( #load training dataset from directory,\n",
        "    '/content/data/cifar10/train', #path for the training dataset folder,\n",
        "    image_size=(32,32), #resize all the images to 32*32 pixels,\n",
        "    batch_size=32 #number of images to process in one batch,\n",
        ")\n",
        "\n",
        "test_dataset = tf.keras.utils.image_dataset_from_directory( #load testing dataset from directory,\n",
        "    '/content/data/cifar10/test', #path to the testing dataset folder,\n",
        "    image_size=(32,32), #resize all the images to 32*32 pixels\n",
        "    batch_size=32 #number of images to process in one batch\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jPDhvspnHI4g",
        "outputId": "d03a9480-6f7e-4d10-fd21-212f1b360999"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 50000 files belonging to 10 classes.\n",
            "Found 10000 files belonging to 10 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Define dataset paths and class labels"
      ],
      "metadata": {
        "id": "ue70HgIvwKTT"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "root_dir = '/content/data/cifar10' #define the root directory containing the CIFAR-10 dataset,\n",
        "train_dir = os.path.join(root_dir, 'train') #create the path fo the training dataset folder,\n",
        "test_dir = os.path.join(root_dir, 'test') #create the path for the testing dataset folder,\n",
        "\n",
        "target_var = sorted(os.listdir(train_dir)) #get the list of class names and arrange them in alphabetical order,\n",
        "print(target_var) #display the class names,"
      ],
      "metadata": {
        "id": "gRFwa_GnJWIZ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "367de5ef-1d00-4058-ad9d-cd1f86a41709"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Visualise Sample images from each class"
      ],
      "metadata": {
        "id": "1Xnu9kDJwk6o"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "fig, axes = plt.subplots(1, 10, figsize=(40,8)) #create a figure with 1 row and 10 columns of subplots,\n",
        "\n",
        "for i in range(len(target_var)): # loop all class names in the dataset,\n",
        "  folder_path = os.path.join(train_dir, target_var[i]) #create path to the current class folder\n",
        "  files = os.listdir(folder_path) #get the list of image files inside the folder\n",
        "  if files: #check folder contains any file,\n",
        "    image_path = os.path.join(folder_path, files[0]) #selects first image file from the folder,\n",
        "    axes[i].imshow(plt.imread(image_path)) #display the image in that subplot,\n",
        "    axes[i].set_title(target_var[i]) #set the title of the subplot as the class name,\n",
        "    axes[i].axis(\"off\") #remove axis lines and ticks for better visualisation,\n",
        "\n",
        "plt.tight_layout() #adjusts subplot spacing automatically,\n",
        "plt.show() #display the complete figure with images."
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 124
        },
        "id": "ahbVXtm3IYZw",
        "outputId": "009b1eaf-1261-4e26-f3d8-fb775f6ee28a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 4000x800 with 10 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Class distribution of train and test dataset"
      ],
      "metadata": {
        "id": "JVKs6f1Vw25o"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "x_train = np.array([len(os.listdir(os.path.join(train_dir, i))) for i in target_var]) #count the number of training images in each class folder and store the counts numpy array\n",
        "\n",
        "x_test = np.array([len(os.listdir(os.path.join(test_dir, i))) for i in target_var]) #count the number of testing images in each folder and store the counts as a numpy array\n",
        "\n",
        "label = target_var #store class labels\n",
        "\n",
        "fig, axes = plt.subplots(1, 2, figsize=(10,5)) #create a figure with 1 row and 2 columns of subplot\n",
        "\n",
        "axes[0].pie(x_train, labels=label, autopct='%1.1f%%') #create pie chart for training dataset distribution\n",
        "\n",
        "axes[1].pie(x_test, labels=label, autopct='%1.1f%%') #create pie chart for testing dataset distribution\n",
        "\n",
        "axes[0].set_title('Train') #set title for training pie chart,\n",
        "\n",
        "axes[1].set_title('Test') #set title for testing pie chart\n",
        "\n",
        "plt.show() #disp;ay the plot"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 411
        },
        "id": "BqiYt4J-NHmf",
        "outputId": "deec0064-23fd-44ca-e0e0-1f6fc70ebc64"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Data augmentation and train validation split"
      ],
      "metadata": {
        "id": "HW33biXQxLz4"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "train_datagen = ImageDataGenerator( #create image generator for training data,\n",
        "    rescale=1./255, #normalise pixel values to range from 0 to 1,\n",
        "    rotation_range=15, #rotate images upto 10 degrees,\n",
        "    width_shift_range=0.1, #shift images horizontally,\n",
        "    height_shift_range=0.1, #shift images vertically,\n",
        "    horizontal_flip=True, #flip images horizontally,\n",
        "    validation_split=0.1 #split 10% of training data for validation,\n",
        ")\n",
        "\n",
        "val_datagen = ImageDataGenerator( #create image data generator for validation data,\n",
        "    rescale=1./255, #normalise pixel values from 0 to 1,\n",
        "    validation_split=0.1 #use the same validation split\n",
        ")\n",
        "\n",
        "training_set = train_datagen.flow_from_directory( # generate bathces of augmented training images,\n",
        "    train_dir, #path of training dataset,\n",
        "    batch_size=128, #number of images per btch,\n",
        "    target_size=(32,32), #resize all images to 32*32 pixels,\n",
        "    shuffle=True, #shuffle images during training,\n",
        "    color_mode='rgb', #load the images in RGB colour mode,\n",
        "    class_mode='categorical', #use categorical labels for mutli class classification,\n",
        "    subset='training' #select only the training subset,\n",
        ")\n",
        "\n",
        "validation_set = val_datagen.flow_from_directory( #generate batches for validation images\n",
        "    train_dir, #path to training dataset,\n",
        "    batch_size=128, #number of images per batch,\n",
        "    target_size=(32,32), #rresize all images to 32*32 pixels,\n",
        "    shuffle=False, #do not shuffle validation datat,\n",
        "    color_mode='rgb', #load images in RGB colour mode\n",
        "    class_mode='categorical', #use categorical labels for multi class classification\n",
        "    subset='validation' #selec only the validation subset\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "g6sZWJ19NKXd",
        "outputId": "a8d754e9-395d-4543-a3b5-3e0ecea276f6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 45000 images belonging to 10 classes.\n",
            "Found 5000 images belonging to 10 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Build CNN model"
      ],
      "metadata": {
        "id": "R7gYhTK8yROY"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model = Sequential([ #build a sequiential convolutional neural network model,\n",
        "    Input(shape=(32,32,3)), #define input shape as 32*32 RGB images,\n",
        "\n",
        "    #first convolution block with 32 filters,\n",
        "    Conv2D(32, (3,3), activation='relu', padding='same'),\n",
        "    BatchNormalization(),\n",
        "    Conv2D(32, (3,3), activation='relu', padding='same'),\n",
        "    BatchNormalization(),\n",
        "    MaxPooling2D(),\n",
        "    Dropout(0.25),\n",
        "\n",
        "    #second convolutional block with 64 filters,\n",
        "    Conv2D(64, (3,3), activation='relu', padding='same'),\n",
        "    BatchNormalization(),\n",
        "    Conv2D(64, (3,3), activation='relu', padding='same'),\n",
        "    BatchNormalization(),\n",
        "    MaxPooling2D(),\n",
        "    Dropout(0.30),\n",
        "\n",
        "    #third convolutional block with 128 filters,\n",
        "    Conv2D(128, (3,3), activation='relu', padding='same'),\n",
        "    BatchNormalization(),\n",
        "    Conv2D(128, (3,3), activation='relu', padding='same'),\n",
        "    BatchNormalization(),\n",
        "    MaxPooling2D(),\n",
        "    Dropout(0.40),\n",
        "\n",
        "\n",
        "    GlobalAveragePooling2D(), #global average pooling reduces feature maps to a sngle vector\n",
        "    Dense(128, activation='relu'), #fully connected dense layer,\n",
        "    Dropout(0.5),\n",
        "    Dense(10, activation='softmax') #output layer for 10 class classification\n",
        "])\n",
        "\n",
        "model.summary() #display model architecture summary,"
      ],
      "metadata": {
        "id": "HToEgSsfJesZ",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 959
        },
        "outputId": "66ca34fc-8838-4483-e288-a8bc1a9e20e2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;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             │ (\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",
              "│ conv2d_1 (\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_1           │ (\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",
              "│ max_pooling2d (\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 (\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_2 (\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_2           │ (\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",
              "│ conv2d_3 (\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_3           │ (\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",
              "│ max_pooling2d_1 (\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_1 (\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_4 (\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_4           │ (\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",
              "│ conv2d_5 (\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_5           │ (\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",
              "│ max_pooling2d_2 (\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_2 (\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        │ (\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 (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m16,512\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)             │         \u001b[38;5;34m1,290\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">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             │ (<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",
              "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">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_1           │ (<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",
              "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">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 (<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_2 (<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_2           │ (<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",
              "│ conv2d_3 (<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_3           │ (<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",
              "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">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_1 (<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_4 (<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_4           │ (<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",
              "│ conv2d_5 (<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_5           │ (<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",
              "│ max_pooling2d_2 (<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_2 (<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        │ (<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 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">16,512</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,290</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m306,602\u001b[0m (1.17 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\">306,602</span> (1.17 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m305,706\u001b[0m (1.17 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\">305,706</span> (1.17 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m896\u001b[0m (3.50 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\">896</span> (3.50 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Compile the model\n"
      ],
      "metadata": {
        "id": "7DF8XkiOycH2"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#compile the model with optimiser, loss function and evaluation metrics,\n",
        "model.compile(\n",
        "    optimizer=Adam(learning_rate=0.001),\n",
        "    loss='categorical_crossentropy',\n",
        "    metrics=['accuracy']\n",
        ")"
      ],
      "metadata": {
        "id": "Ub3EY69ZKrae"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Train the model with callbacks"
      ],
      "metadata": {
        "id": "BRZxsimMyid8"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "callbacks = [\n",
        "    EarlyStopping(patience=8, restore_best_weights=True), #stop training early if validation loss does not improve for 8 epoches\n",
        "    ReduceLROnPlateau(patience=3, factor=0.5), #reduce learning rate by half if validation loss does not change for 3 epoches,\n",
        "    ModelCheckpoint(\"best_cifar10_model.keras\", save_best_only=True) #save the best model based on validation performance,\n",
        "]\n",
        "\n",
        "#train the model using training and validation datasets,\n",
        "history = model.fit(\n",
        "    training_set, #training data generator,\n",
        "    validation_data=validation_set, #validation dta generator,\n",
        "    epochs=20, #nummber of training epoches,\n",
        "    callbacks=callbacks #apply callbacks during training,\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GaqBzxIeNX6p",
        "outputId": "95f4d76a-b954-4adf-9635-1b7447f7d536"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m466s\u001b[0m 1s/step - accuracy: 0.3886 - loss: 1.6769 - val_accuracy: 0.1772 - val_loss: 3.0846 - learning_rate: 0.0010\n",
            "Epoch 2/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m466s\u001b[0m 1s/step - accuracy: 0.5440 - loss: 1.2855 - val_accuracy: 0.5688 - val_loss: 1.2212 - learning_rate: 0.0010\n",
            "Epoch 3/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m465s\u001b[0m 1s/step - accuracy: 0.6046 - loss: 1.1259 - val_accuracy: 0.5630 - val_loss: 1.2358 - learning_rate: 0.0010\n",
            "Epoch 4/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m463s\u001b[0m 1s/step - accuracy: 0.6456 - loss: 1.0141 - val_accuracy: 0.6842 - val_loss: 0.9112 - learning_rate: 0.0010\n",
            "Epoch 5/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m497s\u001b[0m 1s/step - accuracy: 0.6783 - loss: 0.9331 - val_accuracy: 0.6460 - val_loss: 1.1271 - learning_rate: 0.0010\n",
            "Epoch 6/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m456s\u001b[0m 1s/step - accuracy: 0.7009 - loss: 0.8701 - val_accuracy: 0.7014 - val_loss: 0.8980 - learning_rate: 0.0010\n",
            "Epoch 7/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m457s\u001b[0m 1s/step - accuracy: 0.7174 - loss: 0.8214 - val_accuracy: 0.7254 - val_loss: 0.8419 - learning_rate: 0.0010\n",
            "Epoch 8/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m464s\u001b[0m 1s/step - accuracy: 0.7315 - loss: 0.7889 - val_accuracy: 0.7238 - val_loss: 0.8435 - learning_rate: 0.0010\n",
            "Epoch 9/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m465s\u001b[0m 1s/step - accuracy: 0.7461 - loss: 0.7499 - val_accuracy: 0.7422 - val_loss: 0.7616 - learning_rate: 0.0010\n",
            "Epoch 10/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m456s\u001b[0m 1s/step - accuracy: 0.7537 - loss: 0.7234 - val_accuracy: 0.7732 - val_loss: 0.6752 - learning_rate: 0.0010\n",
            "Epoch 11/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m455s\u001b[0m 1s/step - accuracy: 0.7625 - loss: 0.7000 - val_accuracy: 0.7702 - val_loss: 0.6873 - learning_rate: 0.0010\n",
            "Epoch 12/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m451s\u001b[0m 1s/step - accuracy: 0.7698 - loss: 0.6794 - val_accuracy: 0.7562 - val_loss: 0.7451 - learning_rate: 0.0010\n",
            "Epoch 13/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 1s/step - accuracy: 0.7773 - loss: 0.6604 - val_accuracy: 0.7316 - val_loss: 0.8447 - learning_rate: 0.0010\n",
            "Epoch 14/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m454s\u001b[0m 1s/step - accuracy: 0.7915 - loss: 0.6186 - val_accuracy: 0.7990 - val_loss: 0.6105 - learning_rate: 5.0000e-04\n",
            "Epoch 15/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 1s/step - accuracy: 0.8011 - loss: 0.5916 - val_accuracy: 0.7798 - val_loss: 0.6779 - learning_rate: 5.0000e-04\n",
            "Epoch 16/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m454s\u001b[0m 1s/step - accuracy: 0.8025 - loss: 0.5842 - val_accuracy: 0.8146 - val_loss: 0.5444 - learning_rate: 5.0000e-04\n",
            "Epoch 17/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m457s\u001b[0m 1s/step - accuracy: 0.8066 - loss: 0.5771 - val_accuracy: 0.8070 - val_loss: 0.5811 - learning_rate: 5.0000e-04\n",
            "Epoch 18/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 1s/step - accuracy: 0.8108 - loss: 0.5661 - val_accuracy: 0.7974 - val_loss: 0.6357 - learning_rate: 5.0000e-04\n",
            "Epoch 19/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m452s\u001b[0m 1s/step - accuracy: 0.8116 - loss: 0.5592 - val_accuracy: 0.8178 - val_loss: 0.5475 - learning_rate: 5.0000e-04\n",
            "Epoch 20/20\n",
            "\u001b[1m352/352\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m451s\u001b[0m 1s/step - accuracy: 0.8202 - loss: 0.5328 - val_accuracy: 0.8166 - val_loss: 0.5551 - learning_rate: 2.5000e-04\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### plot training history - accuracy and loss"
      ],
      "metadata": {
        "id": "p8wPZCKxyotk"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#define a function to plot training and validation performance,\n",
        "def plot_history(history):\n",
        "    acc = history.history[\"accuracy\"] #extract training accuracy values,\n",
        "    loss = history.history[\"loss\"] #extract training values,\n",
        "    val_loss = history.history[\"val_loss\"] #extract validation loss values,\n",
        "    val_accuracy = history.history[\"val_accuracy\"] #extract validation accuracy values,\n",
        "\n",
        "    x = range(1, len(acc) + 1) #create a range of epoches\n",
        "\n",
        "    plt.figure(figsize=(12,5)) #create a figure,\n",
        "\n",
        "    #first subplot- accuracy,\n",
        "    plt.subplot(1, 2, 1)\n",
        "    plt.plot(x, acc, \"b\", label=\"training_acc\")\n",
        "    plt.plot(x, val_accuracy, \"r\", label=\"validation_acc\")\n",
        "    plt.title(\"Accuracy\")\n",
        "    plt.legend(('training_acc', 'validation_acc'))\n",
        "\n",
        "    #second subplot- loss,\n",
        "    plt.subplot(1, 2, 2)\n",
        "    plt.plot(x, loss, \"b\", label=\"training_loss\")\n",
        "    plt.plot(x, val_loss, \"r\", label=\"training_loss\")\n",
        "    plt.title(\"Loss\")\n",
        "    plt.legend(('training_loss', 'validation_loss'))\n",
        "\n",
        "    plt.tight_layout() #adjust layout to prevent overlap,\n",
        "    plt.show() #display the plots\n",
        "\n",
        "plot_history(history) #call the function to visualise training history,\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 430
        },
        "id": "CiEzNtZ9Tw-Y",
        "outputId": "f8f575f0-e0e9-466f-b41d-3b28614efd6c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Prepare Test dataset"
      ],
      "metadata": {
        "id": "a3k0oFxgy6uk"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#create image data generator for test data, only rescaling but no augmentation for test data,\n",
        "test_datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "test_set = test_datagen.flow_from_directory( #load test dataset from directory,\n",
        "    test_dir, #path to test dataset folder,\n",
        "    batch_size=64, #number of images per batch\n",
        "    target_size=(32,32), #resize all images to 32*32 pixels,\n",
        "    shuffle=False, #do not shuffel so predictions match to labels order,\n",
        "    color_mode='rgb', #load image in RGB mode,\n",
        "    class_mode='categorical' #use categorical labels,\n",
        ")"
      ],
      "metadata": {
        "id": "bhFglkpPKzwJ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "41c98445-1220-4f0f-faa5-ac18e031d02e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 10000 images belonging to 10 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Get test class labels mapping"
      ],
      "metadata": {
        "id": "kP9uMGgjzBVX"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "test_labels = test_set.class_indices #get the mapping of class names to numeric indices,\n",
        "\n",
        "test_labels = {v: k for k, v in test_labels.items()} #reverse the dictionary to map indices back to class names,\n",
        "\n",
        "print(test_labels) #print the index to class mapping\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aOYXQY2NUHMO",
        "outputId": "fed0c2a5-a9cb-49ab-d065-b5024b8a6710"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "{0: 'airplane', 1: 'automobile', 2: 'bird', 3: 'cat', 4: 'deer', 5: 'dog', 6: 'frog', 7: 'horse', 8: 'ship', 9: 'truck'}\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Model evaluation with confusion matrix and classification report"
      ],
      "metadata": {
        "id": "n95NwSWzzHa1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "test_set.reset() #reset the test generator to ensure predictions start from the first batch,\n",
        "\n",
        "y_proba = model.predict(test_set) #get predicted probabilities for each class,\n",
        "y_pred = np.argmax(y_proba, axis=1) #convert probabilities to predicted class labels\n",
        "\n",
        "y_test_full = test_set.classes #get the true class labelsfrom the test generator,\n",
        "\n",
        "print(confusion_matrix(y_test_full, y_pred)) #compute and display confusion matrix,\n",
        "#compute and diplay detailed classification report\n",
        "print(classification_report(\n",
        "    y_test_full,\n",
        "    y_pred,\n",
        "    target_names=list(test_set.class_indices.keys())\n",
        "))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gfFZ2ZvqUHNH",
        "outputId": "971b1c5d-339d-477a-eb8d-715d54b3995f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m157/157\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 164ms/step\n",
            "[[849  26  41   1  10   0   8   2  32  31]\n",
            " [  2 944   1   0   0   0   3   0   2  48]\n",
            " [ 29   2 783  15  53  12  75   8   4  19]\n",
            " [ 33  10  57 588  65  54 118  23  13  39]\n",
            " [ 13   3  46  15 828   5  58  25   3   4]\n",
            " [ 11   5  49 126  50 609  69  54   7  20]\n",
            " [  7   3  21  12   9   1 942   2   1   2]\n",
            " [ 14   4  26  19  46   8  20 829   3  31]\n",
            " [ 37  27   5   2   2   0   5   0 887  35]\n",
            " [ 12  55   3   2   1   0   1   1   8 917]]\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "    airplane       0.84      0.85      0.85      1000\n",
            "  automobile       0.87      0.94      0.91      1000\n",
            "        bird       0.76      0.78      0.77      1000\n",
            "         cat       0.75      0.59      0.66      1000\n",
            "        deer       0.78      0.83      0.80      1000\n",
            "         dog       0.88      0.61      0.72      1000\n",
            "        frog       0.73      0.94      0.82      1000\n",
            "       horse       0.88      0.83      0.85      1000\n",
            "        ship       0.92      0.89      0.91      1000\n",
            "       truck       0.80      0.92      0.85      1000\n",
            "\n",
            "    accuracy                           0.82     10000\n",
            "   macro avg       0.82      0.82      0.81     10000\n",
            "weighted avg       0.82      0.82      0.81     10000\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Confusion Matrix heatmap visualisation"
      ],
      "metadata": {
        "id": "XjHL2S3VzTID"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "cm = confusion_matrix(y_test_full, y_pred) #compute confusion matric using true and predicted labels,\n",
        "\n",
        "class_names = list(test_set.class_indices.keys()) #get class names from the test data generator,\n",
        "\n",
        "plt.figure(figsize=(10,8)) #create a figure,\n",
        "sns.heatmap(\n",
        "    cm,\n",
        "    annot=True, #show numbers inside each cell,\n",
        "    fmt='d', #format values as integer,\n",
        "    cmap='Blues', #color theme,\n",
        "    xticklabels=class_names, #x-axis label (predicted classes),\n",
        "    yticklabels=class_names #y-axis labels (true labels),\n",
        ")\n",
        "\n",
        "plt.xlabel(\"Predicted Label\") #labels x-axis,\n",
        "plt.ylabel(\"True Label\") #label y-axis,\n",
        "plt.title(\"Confusion Matrix Heatmap\") #plot title,\n",
        "plt.show() #display the plot,"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 783
        },
        "id": "UjTUDFi5UHP2",
        "outputId": "e5ec7622-81ec-4a6b-c054-8c4ca5d810a0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x800 with 2 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1UAAAL+CAYAAABFUz5fAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAA/EdJREFUeJzs3XVYVGkbBvCb7hJQQCWk7FqDFOzu1l27F7sbUcEODFRsxe5e2/3cNcAWUDExUEJBuma+P1hHRzHGAY4D9++6uC7mPWfOPO/MmTnznOc97yiJxWIxiIiIiIiI6KcoCx0AERERERGRImNSRUREREREJAcmVURERERERHJgUkVERERERCQHJlVERERERERyYFJFREREREQkByZVREREREREcmBSRUREREREJAcmVURERERERHJgUkVEJICIiAg0atQIBgYGUFJSwoEDB/J0+0+fPoWSkhI2btyYp9tVZJ6envD09BQ6DCIiKoSYVBFRkfXo0SMMHDgQZcqUgaamJvT19eHq6oqlS5ciNTU1Xx+7Z8+euHPnDmbPno0tW7agRo0a+fp4BalXr15QUlKCvr5+rs9jREQElJSUoKSkhAULFsi8/VevXsHb2xs3b97Mg2h/npKSEry8vHJdtnHjRigpKSEkJCTfHv9XeR6IiAhQFToAIiIhHD16FB07doSGhgZ69OiBihUrIiMjAxcvXsTYsWMRGhqKNWvW5Mtjp6am4tKlS5g8efJXv5TLy8rKCqmpqVBTU8uX7X+PqqoqUlJScPjwYXTq1ElqWVBQEDQ1NZGWlvZT23716hVmzJgBa2trVK1a9Yfvd/LkyZ96vF/Vzz4PRESU95hUEVGR8+TJE3Tp0gVWVlY4e/YszM3NJcv+/PNPPHz4EEePHs23x4+JiQEAGBoa5ttjKCkpQVNTM9+2/z0aGhpwdXXF9u3bv0iqtm3bhubNm2Pv3r0FEktKSgq0tbWhrq5eII9HRERFD4f/EVGRM2/ePCQlJWHdunVSCdUHdnZ2GD58uOR2VlYWZs6cCVtbW2hoaMDa2hqTJk1Cenq61P2sra3RokULXLx4EbVq1YKmpibKlCmDzZs3S9bx9vaGlZUVAGDs2LFQUlKCtbU1gJxhcx/+/5S3tzeUlJSk2k6dOgU3NzcYGhpCV1cXjo6OmDRpkmT5166pOnv2LNzd3aGjowNDQ0O0bt0a4eHhuT7ew4cP0atXLxgaGsLAwAC9e/dGSkrK15/Yz3Tr1g3Hjx9HfHy8pC04OBgRERHo1q3bF+u/ffsWY8aMQaVKlaCrqwt9fX00bdoUt27dkqxz/vx51KxZEwDQu3dvyTDCD/309PRExYoVce3aNdSpUwfa2tqS5+Xza6p69uwJTU3NL/rfuHFjGBkZ4dWrVz/c1x917949dOjQAcWKFYOmpiZq1KiBQ4cO5dvzcPv2bXh4eEBbWxt2dnbYs2cPAODChQuoXbs2tLS04OjoiNOnT0vF8OzZMwwZMgSOjo7Q0tKCsbExOnbsiKdPn0qt92GY499//42BAwfC2NgY+vr66NGjB969e5fHzx4R0a+LSRURFTmHDx9GmTJl4OLi8kPr9+vXD9OmTUP16tWxePFieHh4wM/PD126dPli3YcPH6JDhw5o2LAhFi5cCCMjI/Tq1QuhoaEAgHbt2mHx4sUAgK5du2LLli1YsmSJTPGHhoaiRYsWSE9Ph4+PDxYuXIhWrVrhn3/++eb9Tp8+jcaNGyM6Ohre3t4YNWoU/v33X7i6un7xZRkAOnXqhMTERPj5+aFTp07YuHEjZsyY8cNxtmvXDkpKSti3b5+kbdu2bShbtiyqV6/+xfqPHz/GgQMH0KJFCyxatAhjx47FnTt34OHhIUlwypUrBx8fHwDAgAEDsGXLFmzZsgV16tSRbCcuLg5NmzZF1apVsWTJEtStWzfX+JYuXQpTU1P07NkT2dnZAIDVq1fj5MmTWLZsGSwsLL7bx7S0NMTGxn7xl5SU9MW6oaGhcHJyQnh4OCZMmICFCxdCR0cHbdq0wf79+/P8eXj37h1atGiB2rVrY968edDQ0ECXLl2wc+dOdOnSBc2aNcOcOXOQnJyMDh06IDExUXLf4OBg/Pvvv+jSpQv8/f0xaNAgnDlzBp6enrkm1l5eXggPD4e3tzd69OiBoKAgtGnTBmKx+LvPIRFRoSAmIipCEhISxADErVu3/qH1b968KQYg7tevn1T7mDFjxADEZ8+elbRZWVmJAYj//vtvSVt0dLRYQ0NDPHr0aEnbkydPxADE8+fPl9pmz549xVZWVl/EMH36dPGnH9eLFy8WAxDHxMR8Ne4Pj7FhwwZJW9WqVcXFixcXx8XFSdpu3bolVlZWFvfo0eOLx+vTp4/UNtu2bSs2Njb+6mN+2g8dHR2xWCwWd+jQQVy/fn2xWCwWZ2dni83MzMQzZszI9TlIS0sTZ2dnf9EPDQ0NsY+Pj6QtODj4i7594OHhIQYgXrVqVa7LPDw8pNr++usvMQDxrFmzxI8fPxbr6uqK27Rp890+isViMYDv/gUHB0vWr1+/vrhSpUritLQ0SZtIJBK7uLiI7e3t8+V52LZtm6Tt3r17YgBiZWVl8eXLl794Dj7dTkpKyhfbvHTpkhiAePPmzZK2DRs2iAGIf/vtN3FGRoakfd68eWIA4oMHD37t6SMiKlRYqSKiIuX9+/cAAD09vR9a/9ixYwCAUaNGSbWPHj0aAL649qp8+fJwd3eX3DY1NYWjoyMeP3780zF/7sO1WAcPHoRIJPqh+0RFReHmzZvo1asXihUrJmmvXLkyGjZsKOnnpwYNGiR1293dHXFxcZLn8Ed069YN58+fx+vXr3H27Fm8fv0616F/QM51WMrKOYel7OxsxMXFSYY2Xr9+/YcfU0NDA7179/6hdRs1aoSBAwfCx8cH7dq1g6amJlavXv3Dj9W6dWucOnXqi7+xY8dKrff27VucPXtWUv37UNGKi4tD48aNERERgZcvX0riz4vnQVdXV6qa6ujoCENDQ5QrVw61a9eWtH/4/9N9VEtLS/J/ZmYm4uLiYGdnB0NDw1xjGDBggNSkKIMHD4aqqmqu+xURUWHEpIqIihR9fX0AkBrq9C3Pnj2DsrIy7OzspNrNzMxgaGiIZ8+eSbVbWlp+sQ0jI6M8vb6kc+fOcHV1Rb9+/VCiRAl06dIFu3bt+maC9SFOR0fHL5aVK1cOsbGxSE5Olmr/vC9GRkYAIFNfmjVrBj09PezcuRNBQUGoWbPmF8/lByKRCIsXL4a9vT00NDRgYmICU1NT3L59GwkJCT/8mCVLlpRpUooFCxagWLFiuHnzJvz9/VG8ePEfvm+pUqXQoEGDL/7Kly8vtd7Dhw8hFosxdepUmJqaSv1Nnz4dABAdHQ0g756HUqVKfXEtnoGBAUqXLv1FGyD9uqampmLatGkoXbq0VAzx8fG5xmBvby91W1dXF+bm5rkOKyUiKow4+x8RFSn6+vqwsLDA3bt3Zbrf519Ov0ZFRSXXdvEPXFvytcf4cL3PB1paWvj7779x7tw5HD16FCdOnMDOnTtRr149nDx58qsxyEqevnygoaGBdu3aYdOmTXj8+DG8vb2/uq6vry+mTp2KPn36YObMmShWrBiUlZUxYsSIH67IAdJVlh9x48YNSUJz584ddO3aVab7/4gP8Y8ZMwaNGzfOdZ0PyWZePQ9fe/1+5HUdOnQoNmzYgBEjRsDZ2VnyI9VdunSRKQYioqKCSRURFTktWrTAmjVrcOnSJTg7O39zXSsrK4hEIkRERKBcuXKS9jdv3iA+Pl4yk19eMDIykpop74PPq2EAoKysjPr166N+/fpYtGgRfH19MXnyZJw7dw4NGjTItR8AcP/+/S+W3bt3DyYmJtDR0ZG/E7no1q0b1q9fD2Vl5Vwn9/hgz549qFu3LtatWyfVHh8fDxMTE8ntH01wf0RycjJ69+6N8uXLw8XFBfPmzUPbtm0lM+vllTJlygAA1NTUcn19PiXE85BbDD179sTChQslbWlpabnun0DODzp/OiFIUlISoqKi0KxZs3yLkYjoV8Lhf0RU5IwbNw46Ojro168f3rx588XyR48eYenSpQAg+VL4+Qx9ixYtAgA0b948z+KytbVFQkICbt++LWmLioqSmhkOyLk+53Mffvz182nePzA3N0fVqlWxadMmqS/Gd+/excmTJ/P1y2/dunUxc+ZMLF++HGZmZl9dT0VF5Ysq2O7duyXXGn3wIfn72hd8WYwfPx6RkZHYtGkTFi1aBGtra/Ts2fOrz+PPKl68ODw9PbF69WpERUV9sfzDb5cBwjwPn8sthmXLln1RNf1gzZo1yMzMlNwOCAhAVlYWmjZtmuexERH9ilipIqIix9bWFtu2bUPnzp1Rrlw59OjRAxUrVkRGRgb+/fdf7N69G7169QIAVKlSBT179sSaNWsQHx8PDw8PXL16FZs2bUKbNm2+Ol33z+jSpQvGjx+Ptm3bYtiwYUhJSUFAQAAcHBykJgfw8fHB33//jebNm8PKygrR0dFYuXIlSpUqBTc3t69uf/78+WjatCmcnZ3Rt29fpKamYtmyZTAwMPjmsDx5KSsrY8qUKd9dr0WLFvDx8UHv3r3h4uKCO3fuICgoSFLl+cDW1haGhoZYtWoV9PT0oKOjg9q1a8PGxkamuM6ePYuVK1di+vTpkineN2zYAE9PT0ydOhXz5s2TaXvfs2LFCri5uaFSpUro378/ypQpgzdv3uDSpUt48eKF5HeoCvp5yE2LFi2wZcsWGBgYoHz58rh06RJOnz4NY2PjXNfPyMhA/fr10alTJ9y/fx8rV66Em5sbWrVqJXcsRESKgEkVERVJrVq1wu3btzF//nwcPHgQAQEB0NDQQOXKlbFw4UL0799fsu7atWtRpkwZbNy4Efv374eZmRkmTpwomWAgrxgbG2P//v0YNWoUxo0bBxsbG/j5+SEiIkIqqWrVqhWePn2K9evXIzY2FiYmJvDw8MCMGTMkkw7kpkGDBjhx4gSmT5+OadOmQU1NDR4eHpg7d26efBGX16RJk5CcnIxt27Zh586dqF69Oo4ePYoJEyZIraempoZNmzZh4sSJGDRoELKysrBhwwaZ+pCYmIg+ffqgWrVqmDx5sqTd3d0dw4cPx8KFC9GuXTs4OTnlWf/Kly+PkJAQzJgxAxs3bkRcXByKFy+OatWqYdq0aZL1CvJ5+JqlS5dCRUUFQUFBSEtLg6urq+R3znKzfPlyBAUFYdq0acjMzETXrl3h7++fr0MUiYh+JUpiWa44JiIiIvrPxo0b0bt3bwQHB6NGjRpCh0NEJBheU0VERERERCQHJlVERERERERyYFJFREREREQkB15TRUREREREJAdWqoiIiIiIiOTApIqIiIiIiEgOTKqIiIiIiIjkwB//LaS0mvsLHYIgovd6CR2CILJERfPSSC11FaFDEISoiF4Kq1xEf0iWr3fRkpElEjoEKkD6mr9ufUOrmjDfqVJvLBfkceX1676SRERERERECoBJFRERERERkRw4/I+IiIiIiKQpsfYiCz5bREREREREcmClioiIiIiIpBXRyWJ+FitVREREREREcmClioiIiIiIpPGaKpnw2SIiIiIiIpIDkyoiIiIiIiI5cPgfERERERFJ40QVMmGlioiIiIiISA6sVBERERERkTROVCETPltERERERERyYFJFREREREQkBw7/IyIiIiIiaZyoQiasVBEREREREcmBlSoiIiIiIpLGiSpkwmeLiIiIiIhIDqxUERERERGRNF5TJRNWqoiIiIiIiOTApIqIiIiIiEgOHP5HRERERETSOFGFTPhsERERERERyaHIJVVPnz6FkpISbt68Kfe2evXqhTZt2si9HSIiIiKiX4qSkjB/CqrIJVWlS5dGVFQUKlasKHQoCkNZWQnTfndC+LqeeLtvCELX9sSELjW/ur7/n3WRenQYvFpXlWqvamuKI7PaIGrnQLzY3h/Lh9aDjqZaPkefdzasW4Me3TqijvNvaOjpitEjvPD06ZMv1rt96wYG9esFt9rV4eFSA/17/460tDQBIs4fm9cHwqlaeSye7ydpO7B3Fwb364l6bjXhVK08EhPfCxhh/rkWEoyhQwahgacbqlRwxNkzp4UOKV9cCwnG8D8HoWFdd1SrWBbnPuunWCzGyuX+aOjpDqffqmBgv9549uypMMHmsx3bgtC0YT3UrFYJ3bt0xJ3bt4UOKV9lZ2djxbKlaN64Ppx+q4KWTRpizaqVEIvFQoeWr9YFrka3Tu3hXLMaPN2dMWLoEDx98ljosPLcnl3b0bVDa3i61ICnSw30+aML/rn4NwAgISEe8/1moX2rpnCrVRUtGtfDgjmzkZSYKHDU8vtWvwFg355dGNi3BzxdaqBmlXJIfF84j2GUv4pcUqWiogIzMzOoquZ+OZlYLEZWVlYBR/VrG93hN/RvVgkjV11A1UFbMGXDPxjV/jcMaVnli3VbOZdBrbJmeBWbJNVuXkwHR2e3xaNX8agzaidaTzuI8pbFEDiyYUF1Q27XQ4LRsXM3bNiyAytWr0NWVia8BvVFakqKZJ3bt25g6JABcHJ2xaagndi0bTc6dekOZeXC8VYLC72D/Xt3wc7eUao9LS0Nzi5u6NVngECRFYzU1BQ4Ojpi4pTpQoeSr1JTU+HgWBYTJ0/LdfnG9WuxPWgLJk3zxuZtu6ClpYU/B/ZDenp6AUeav04cP4YF8/wwcMif2LF7Pxwdy2LwwL6Ii4sTOrR8s3FdIPbs3I4Jk6Zi36GjGDZqNDb993oXZiHBV9G5a3ds2b4LqwM3ICsrC4P690XKJ5/vhUHx4mbwGj4Km7fvwaZtu1GjlhPGDPfCo4cRiImORkxMNIaPGocdew9huo8vLv3zP8z0niJ02HL7Vr8BIC0tFc4u7ujVd6DAkZIiKxzf9D5z4sQJuLm5wdDQEMbGxmjRogUePXoE4Mvhf+fPn4eSkhKOHz+O3377DRoaGrh48SK8vb1RtWpVrF69GqVLl4a2tjY6deqEhISEn3rcTx973759qFu3LrS1tVGlShVcunRJajsXL16Eu7s7tLS0ULp0aQwbNgzJycl5/0T9IKdy5jhy5TFOBD9FZHQi9v/zEGduRKKGYwmp9SyMdbBokCd6z/8LmdkiqWVNa1kjM0uEEQHnEfEyHtciojF0+Tm0dbNDGXODguzOT1sWEIiWrdvC1s4eDo5l4e3jh9dRUQgPD5Wss2j+HHTp+jt69e0PWzt7WFvboGHjplBXVxcw8ryRkpKM6ZPGYeLUGdDT15da1qV7D/To0x8VKn+ZaBcmbu4e8Bo+EvUbKM7JgJ/h5l4Hfw4bgXq59FMsFmPbls3oP2AQ6tarDwdHR8z0nYuY6OgvKlqKbsumDWjXoRPatG0PWzs7TJk+A5qamjiwb6/QoeWbWzdvwKNufbh7eMKiZCk0bNQETi6uCL1zR+jQ8lXAmnVo3bYd7Ozs4Vi2LHxmz0FU1CuEh4V+/84KpI5nXbi6e8DSyhpW1jYYMnQEtLW1cff2LdjZO2DeIn/U8ayLUqUtUbO2EwYPHYH/XTin8Cebv9VvAOj2e0/06tsflQr5MUxmSsrC/CkoxY38G5KTkzFq1CiEhITgzJkzUFZWRtu2bSESib56nwkTJmDOnDkIDw9H5cqVAQAPHz7Erl27cPjwYZw4cQI3btzAkCFD5H7cyZMnY8yYMbh58yYcHBzQtWtXyQfWo0eP0KRJE7Rv3x63b9/Gzp07cfHiRXh5eeXBM/NzLodHoW6V0rCzMAQAVLIxgXN5C5wMeSZZR0kJWDe6ERbvvYbwyLdfbENDTQWZWdn4dARJakZOn10qWORr/PklKSlnSIS+fk5S+DYuDnfv3IZRMWP06dEVjeq6YUCfP3Dz+jUhw8wzC/xmwdXdA7WcXIQOhQT08sULxMbGoLbzx/1AT08PFStXxu1bN4ULLI9lZmQgPCwUTp/0U1lZGU5OLrh964aAkeWvKlWr4eqVS3j239Dm+/fu4eb163B1ryNwZAXrw5A3fQPFOOn3M7Kzs3Hy+FGkpqagUpWqua6TlJQIHV3dr47uUUQ/0m+in1F43iWfaN++vdTt9evXw9TUFGFhYdDV1c31Pj4+PmjYUPqsbFpaGjZv3oySJUsCAJYtW4bmzZtj4cKFMDMzk+lxP72Ga8yYMWjevDkAYMaMGahQoQIePnyIsmXLws/PD927d8eIESMAAPb29vD394eHhwcCAgKgqakp25ORBxbsDoG+tjpurf4D2SIRVJSVMX3zJew4f1+yzugONZCVLcaKQ7dy3cb5Wy8wt587RrarjuWHbkJHUw2zerkCAMyMdAqkH3lJJBJh4Tw/VKlaHXb2DgCAly+fAwACVy3H8FHj4OBYFkePHMTgAb2xc+8hWFpZCxixfE6dOIb798KwfusuoUMhgcXGxgAAihkbS7UbG5sgLjZWiJDyxbv4d8jOzobxF/00xpNCeK3NB737DUBScjLatmwGFRUVZGdn489hI9CsRUuhQyswIpEI8+b6omq16rD/7/O9MHkY8QB9/uiKjIx0aGlrY/7iZShja/fFevHv3mHdmgC0bd9JgCjz3o/2mz6hwJNGCKFQJlURERGYNm0arly5gtjYWEmlKDIyEuXLl8/1PjVq1PiizdLSUpJQAYCzszNEIhHu37+fa1L1rcf9NKn6UAkDAHNzcwBAdHQ0ypYti1u3buH27dsICgqSrCMWiyESifDkyROUK1fui8dNT0//4loGcXYWlFTy5uXt4G6PLp6O6DX/BMKevUXlMqaYP8AdUW+TEHTmHqrZmeLP1lXgMmzHV7cRHvkW/Redwpz+7vDp5YJskRgrD93E63fJCnkB9FxfHzx6FIG1Gz++TiJRTj/adeiMVm3aAQDKliuP4CuXcejAPngNHyVIrPJ68zoKi+b7wT9gLTQ0NIQOh4jy0ckTx3H8yGH4zl0AWzs73L93Dwvm+sK0eHG0at1W6PAKhO+sGXgUEYGNW7YJHUq+sLK2RtCufUhKSsKZU3/Be+pErF63WSrBSEpKwgivQbApY4cBg/4UMNq88yP9JpJHoUyqWrZsCSsrKwQGBsLCwgIikQgVK1ZERkbGV++joyN/teRHH1dN7eOMd0r/nQX4kIAlJSVh4MCBGDZs2Bfbt7S0zPVx/fz8MGPGDKk2FbsmUHNoKld/PvDt44YFu69h9985F3SGPouDZXE9jO1YA0Fn7sG1QkkUN9DGg429JfdRVVHGnL5u8GpdFWX7bAQA7LzwADsvPEBxQy0kp2VBLBZjWJtqePL669ep/Yrm+s7Exb8vYM36LShR4mNybWJiCgCwKWMrtb6NTRm8fh1VoDHmpXvhoXj3Ng69unWQtGVnZ+Pm9RDs2bkNf1+5CRUVFQEjpIL0YT9/GxcHU9Pikva4uFg4On550kdRGRkaQUVF5YtJKeLi4mBiYiJQVPlvycL56N2vP5o0yxlNYe/giKioV9iwdk2RSKp8Z/ng7wvnsX7TVpTI5eRpYaCmpo7SllYAgHLlKyAs9A52BG3BpGk53yOSk5MxbEh/aOvkVHNU1RRnlt5v+V6/ieRV6JKquLg43L9/H4GBgXB3dweQM/HDz4iMjMSrV69gYZFzzc/ly5ehrKwMR0fHL9bNq8etXr06wsLCYGf342dOJk6ciFGjpKsgxTutlfmxv0ZLQxWiz6pJ2SIxlJVzEsJtZ+/h7M1IqeWHfdpg27l72Hwq7IvtRcenAgB6NCyPtMxsnLkR+cU6vyKxWIx5frNw/uxprF63CSVLlZJablGyJExNi0uuRfjg2bNncHVzL8hQ81SNWs4I2n1Qqm3W9MmwsrHBH736MaEqYkqWKgUTE1NcuXwJjmVzkqikpCTcvX0bHTt1FTi6vKOmro5y5SvgyuVLqFe/AYCck19XrlxCl66/Cxxd/klLS4XSZxeKKysrf/Oa5MJALBbDb/ZMnD1zCus2bkGpUqWFDqnAiEViZGTmnPxNSkrCsMH9oKaujkVLVxbq0Qmf9pu+QoEnjRBCoUuqjIyMYGxsjDVr1sDc3ByRkZGYMGHCT21LU1MTPXv2xIIFC/D+/XsMGzYMnTp1ynXoX1497vjx4+Hk5AQvLy/069cPOjo6CAsLw6lTp7B8+fJc76OhofHFB19eDf0DgGNXn2B855p4HpOIsGdxqGprimFtq2HzqZxZkd4mpuFtovTvMGVmi/DmXQoiXsZL2ga1qIzL4VFISs1E/WqW8O3jiqkb/0VCsmJ8qM319cGJ40excMlyaOvoSK4t0dXVg6amJpSUlPBHrz5YHbAc9o5l4ehYFkcOHcCzp48xb+ESYYOXg46ODmzt7KXaNLW0YGBgKGmPi41BXFwsXkTmJMiPIh5AW0cHJczMYWBgWNAh55uU5GRERn48CfDyxQvcCw+HgYEBzC0Uc8KV3KSkJOP5p/18+QL374VD38AA5uYW6PZHD6xdswqWVtYoWbIkVi73h2nx4qj7X/JRWPzRszemThqPChUqomKlyti6ZRNSU1PRpm07oUPLN3U862Jd4CqYm5vD1s4O98LDsXXzRrRp2/77d1ZgvjNn4PixI1iybCV0tHUQG/Pf57ueniDXMueX5UsXwcXNHWZmFkhJScaJY0dwLeQqlgUEIikpCUMH9UVaWhp8fOchKTkJSck5P49iZFRMoU+gfavfQM61onGxsXj+PGcCrocPH0BbWwdm5oXrGEb5q9AlVcrKytixYweGDRuGihUrwtHREf7+/vD09JR5W3Z2dmjXrh2aNWuGt2/fokWLFli5cmW+Pm7lypVx4cIFTJ48Ge7u7hCLxbC1tUXnzp1ljj+vjFp1AdN/d8LSIZ4wNdBG1NtkrDt+B77br8q0nRoOJTCle23oaqnj/vO38Fp+DtvP3cunqPPenl0514wN7NtTqn26jy9a/jcsptvvPZGRnoHF8+cgISEBDo6OWLFqHUqVzn3oZmGxb89OrFv98b0xqG8PAMCUGbPRolXhGTIUGnoX/Xr3kNxeMC/nB5BbtW6Lmb5zhAorz4XdvYv+fT7u5wvn5fStZes28Jk9B7369ENqaipmeU9DYuJ7VK3+G1asCix0Z7WbNG2Gd2/fYuVyf8TGxsCxbDmsXL0WxoV4+N/4SVOwcpk/fGf54N3bnCGeHTp2xoDBX5/5tjDYtXM7AKBvrz+k2n1m+aF1IUqi372Ng/eUCYiNiYGurh7sHBywLCAQtZ1dcS34Ku7eyflx67YtGkvd7+Cx07D45BpzRfOtfgPAvt07EbhqhWT9Ab1z9oNpnxzfiyRWqmSiJFbEWQIKgLe3Nw4cOCD5PStFo9XcX+gQBBG9V7ip54WUJSqab2MtdcU9cyqPz4fjFhXKRXQmKr7eRUtGVuEeaknS9DV/3cRFy8NHkMdNvZD7D8//6gpdpYqIiIiIiOSkXDRPbPysXzc9JiIiIiIiUgBMqr7C29tbYYf+ERERERFRweHwPyIiIiIiksaJKmTCZ4uIiIiIiEgOrFQREREREZG0IjoD589ipYqIiIiIiEgOTKqIiIiIiIjkwOF/REREREQkjRNVyITPFhERERERkRxYqSIiIiIiImmcqEImrFQRERERERHJgZUqIiIiIiKSxmuqZMJni4iIiIiISA5MqoiIiIiIiOTA4X9ERERERCSNE1XIhJUqIiIiIiIiObBSRURERERE0jhRhUz4bBEREREREcmBSRUREREREZEcOPyPiIiIiIikcaIKmbBSRUREREREJAdWqoiIiIiISBonqpAJny0iIiIiIiI5sFJFRERERETSeE2VTFipIiIiIiIikgMrVYXUu4PDhA5BEEY1vYQOQRDvgpcLHQIVIGWePSxS+HoXLeqqRfN8d0p6ttAhEMmFSRUREREREUnjRBUy4bNFREREREQkB1aqiIiIiIhIGitVMuGzRUREREREJAcmVURERERERHLg8D8iIiIiIpLGmUdlwkoVERERERGRHFipIiIiIiIiaZyoQiZ8toiIiIiIiOTAShUREREREUnjNVUyYaWKiIiIiIhIDkyqiIiIiIiI5MDhf0REREREJI0TVciEzxYREREREZEcWKkiIiIiIiJpnKhCJqxUERERERERyYFJFRERERERkRw4/I+IiIiIiKQocfifTFipIiIiIiIikgMrVUREREREJIWVKtmwUkVERERERCQHVqqIiIiIiEgaC1UyYaWKiIiIiIhIDkyq8tDGjRthaGj4zXW8vb1RtWpVye1evXqhTZs2+RoXERERERHlH4VOqn4kifnVjBkzBmfOnBE6jDy1LnA1unVqD+ea1eDp7owRQ4fg6ZPHQoclN11tDcwf0x73j/ng7aVFOLdxFH4rb5nruv6TuyD1xnJ4dfPMdbm6miou75iA1BvLUdmhZD5GXTCuhQRj6JBBaODphioVHHH2zGmhQyowO7YFoWnDeqhZrRK6d+mIO7dvCx1SgWC/i0a/d+3Yhg5tW8KlVnW41KqOP7p1xsX/XRA6rAJT1F7vwnr8/p7NGwLhXL08Fs/3k7TFxcZgxpTxaN7QHXVdfkPPbu1x7sxJAaMUnpKSkiB/ikqhkypFpKurC2NjY6HDyFMhwVfRuWt3bNm+C6sDNyArKwuD+vdFSkqK0KHJJWBaN9RzKos+UzahRidfnL50D0dXDYWFqYHUeq3qVkatStZ4FR3/1W35jmiNqJiEfI644KSmpsDR0RETp0wXOpQCdeL4MSyY54eBQ/7Ejt374ehYFoMH9kVcXJzQoeUr9rvo9Lt4CTMMHzkG23fvw7Zde1GrthOGe/2Jhw8jhA4t3xXF17uwHr+/JSz0Dg7s3QU7e0epdp9pE/Hs2VPMW7wCW3cdgGe9hpgyfhTu3wsTKFJSNIImVSdOnICbmxsMDQ1hbGyMFi1a4NGjRwCA8+fPQ0lJCfHx8ZL1b968CSUlJTx9+hTnz59H7969kZCQIMlsvb29AQDv3r1Djx49YGRkBG1tbTRt2hQRER8PCB8qXEeOHIGjoyO0tbXRoUMHpKSkYNOmTbC2toaRkRGGDRuG7Oxsyf2+t90PDhw4AHt7e2hqaqJx48Z4/vy5ZNnnw/8+JxKJ4OfnBxsbG2hpaaFKlSrYs2fPTz7DBSNgzTq0btsOdnb2cCxbFj6z5yAq6hXCw0KFDu2naWqooU39qpi85AD+uf4Ij5/HYvbqY3j0PAb9O7pL1rMwNcCi8R3Re9JGZGZl57qtRq7lUd+pHCYu3l9Q4ec7N3cPeA0fifoNGgodSoHasmkD2nXohDZt28PWzg5Tps+ApqYmDuzbK3Ro+Yr9Ljr99qxbD+51PGBlZQ1raxsMHT4S2trauH3rptCh5bui+HoXxuP3t6SkJMN78jhMmDoDevr6Usvu3LqBjp27o0LFyihZqjR69xsEXT093A8vukkVK1WyETSpSk5OxqhRoxASEoIzZ85AWVkZbdu2hUgk+u59XVxcsGTJEujr6yMqKgpRUVEYM2YMgJzrlEJCQnDo0CFcunQJYrEYzZo1Q2ZmpuT+KSkp8Pf3x44dO3DixAmcP38ebdu2xbFjx3Ds2DFs2bIFq1evlkpofnS7s2fPxubNm/HPP/8gPj4eXbp0+eHnxM/PD5s3b8aqVasQGhqKkSNH4vfff8eFC4oz/CIpMREAoG9g8J01f12qKspQVVVBWkamVHtaeiZcqtkCyPmwWTerBxZvOoPwx69z3U7xYnpYObUr+k7djJTUjHyPm/JPZkYGwsNC4eTsImlTVlaGk5MLbt+6IWBk+Yv9Llr9/lR2djaOHzuK1NQUVKlSTehw8hVf7xyF4fj9LQvmzIKLmwdq1Xb5YlmlKtVw+uRxJCTEQyQS4dRfx5CRnoFqv9UUIFL6UdnZ2Zg6daqkGGFra4uZM2dCLBZL1hGLxZg2bRrMzc2hpaWFBg0afFEUefv2Lbp37w59fX0YGhqib9++SEpKkikWQadUb9++vdTt9evXw9TUFGFh3z8roK6uDgMDAygpKcHMzEzSHhERgUOHDuGff/6Bi0vOmyYoKAilS5fGgQMH0LFjRwBAZmYmAgICYGub8wW5Q4cO2LJlC968eQNdXV2UL18edevWxblz59C5c2eZtrt8+XLUrl0bALBp0yaUK1cOV69eRa1atb7Zp/T0dPj6+uL06dNwdnYGAJQpUwYXL17E6tWr4eHh8d3nRWgikQjz5vqiarXqsLd3EDqcn5aUko7Ltx5jYv+muP/kDd7EvUenJjVQu7INHj2PAQCM7t0QWdkirNh+/qvbWePzOwL3XMT1sEhYmhcroOgpP7yLf4fs7Owvhu8aGxvjSSG+BoH9Llr9BoCIB/fxR7cuyMhIh7a2Nhb7r4CtnZ3QYeWrovx6f1BYjt9fc+qvY7h/Lwzrt+zKdfmsuYswdfxoNKnrAhVVVWhqamLOQn+UtrQq4EhJFnPnzkVAQAA2bdqEChUqICQkBL1794aBgQGGDRsGAJg3bx78/f2xadMm2NjYYOrUqWjcuDHCwsKgqakJAOjevTuioqJw6tQpZGZmonfv3hgwYAC2bdv2w7EImlRFRERg2rRpuHLlCmJjYyUVqsjISGhra//UNsPDw6GqqipJaoCcD0VHR0eEh4dL2rS1tSUJFQCUKFEC1tbW0NXVlWqLjo6WabuqqqqoWfPjWY2yZcvC0NAQ4eHh302qHj58iJSUFDRsKD2kKiMjA9Wqff0sYXp6OtLT06XaxCoa0NDQ+Obj5QffWTPwKCICG7f8+E74q+ozZTNWe3fH45OzkZWVjZv3nmPXiRBUK2eJauVK48+unnDpNver9x/S1QN62pqYv75oX+hKRIrF2toGu/YeQFJSIk6d/AtTJ43Huo1bC31iVdQVpuP35968jsLi+X7wX7n2q9+N1qz0R2LSe/gHrIOhkRH+PncGU8aPQsC6LbArhEnmj1CEoXj//vsvWrdujebNmwMArK2tsX37dly9ehVATpVqyZIlmDJlClq3bg0A2Lx5M0qUKIEDBw6gS5cuCA8Px4kTJxAcHIwaNWoAAJYtW4ZmzZphwYIFsLCw+KFYBE2qWrZsCSsrKwQGBsLCwgIikQgVK1ZERkaGJLn5tHz36TA7eampqUndVlJSyrXtR4Yi5pUPZcajR4+iZEnpGeK+lSD5+flhxowZUm2Tp07HlGneeR7jt/jO8sHfF85j/aatKPFJ9VBRPXkRi0b9lkJbUx36upp4HfseW+b0xpOXsXCtZovixXTx4JiPZH1VVRXMGdUOXt3romzz6fCs6YDalW2QcGWJ1Hb/CRqHHcdD0H/algLuEcnDyNAIKioqX1y0HhcXBxMTE4Giyn/sd9HqNwCoqavD0irn7Hz5ChURevcOgrZuxjRvn+/cU3EV5dcbKHzH78/dCw/Fu7dx6NW9g6QtOzsbN6+HYO+ubdix7yj27NyGoN0HUcbWHgBg71AWN29cw95d2zB+srdAkRdNuRULNDRyLxa4uLhgzZo1ePDgARwcHHDr1i1cvHgRixYtAgA8efIEr1+/RoMGDST3MTAwQO3atXHp0iV06dIFly5dgqGhoSShAoAGDRpAWVkZV65cQdu2bX8obsGSqri4ONy/fx+BgYFwd8+58P/ixYuS5aampgCAqKgoGBkZAciZqOJT6urqUhNJAEC5cuWQlZWFK1euSIbpfXis8uXL/3S8P7rdrKwshISESKpS9+/fR3x8PMqVK/fdxyhfvjw0NDQQGRkp01C/iRMnYtSoUVJtYpWCq1KJxWL4zZ6Js2dOYd3GLShVqnSBPXZBSEnLQEpaBgz1tNDApRwmLzmIA2du4uyV+1LrHV75J7YdvYrNBy8DAEbP2wPvFUcky81NDXAkwAt/TNiA4DtPC7ILlAfU1NVRrnwFXLl8CfXq53w4i0QiXLlyCV26/i5wdPmH/S5a/c6NSCRCZkbhvia0qL7ehf34/UGNWs7YuuugVNts78mwsrbB7736IS0tDQCgrCQ91YCKsgrEIjGKKqEqVbkVC6ZPny6ZkO5TEyZMwPv371G2bFmoqKggOzsbs2fPRvfu3QEAr1/nXPNeokQJqfuVKFFCsuz169coXry41HJVVVUUK1ZMss6PECypMjIygrGxMdasWQNzc3NERkZiwoQJkuV2dnYoXbo0vL29MXv2bDx48AALFy6U2oa1tTWSkpJw5swZVKlSBdra2rC3t0fr1q3Rv39/rF69Gnp6epgwYQJKliwpKfv9jB/drpqaGoYOHQp/f3+oqqrCy8sLTk5O3x36BwB6enoYM2YMRo4cCZFIBDc3NyQkJOCff/6Bvr4+evbsmev9csve07J+uqsy8505A8ePHcGSZSuho62D2Jica4509fQkY1UVUQPnclBSAh48jYZtaVP4jmyDB0/eYPOhS8jKEuFtQrLU+plZ2XgT+x4Rz3KGjD5//U5qeVJKzlmXx89j8PIb068rgpTkZERGRkpuv3zxAvfCw2FgYADzHyyTK6I/evbG1EnjUaFCRVSsVBlbt2xCamoq2rRtJ3Ro+Yr9Ljr9Xrp4Idzc68DM3Bwpyck4dvQIQoKvImDNOqFDy3dF8fUurMfvz+no6MDWzl6qTVNLC/oGhrC1s0dWZiZKlbbE3Nne8Bo5FgYGhvj7/BlcvfIvFixdKVDURVduxYKvjdjatWsXgoKCsG3bNlSoUAE3b97EiBEjYGFh8dXvzflFsKRKWVkZO3bswLBhw1CxYkU4OjrC398fnp6eAHKSk+3bt2Pw4MGoXLkyatasiVmzZkkmhABySn6DBg1C586dERcXJ8liN2zYgOHDh6NFixbIyMhAnTp1cOzYsS+G98nqR7arra2N8ePHo1u3bnj58iXc3d2xbt2PH4xmzpwJU1NT+Pn54fHjxzA0NET16tUxadIkuWLPT7t2bgcA9O31h1S7zyw/tFbgg5GBriZ8hrZCyRKGeJuQgoNnbmL6isPIyiq4IaG/qtDQu+jXu4fk9oJ5OT+g2Kp1W8z0nSNUWPmuSdNmePf2LVYu90dsbAwcy5bDytVrYVzIhwex30Wn32/fxmHKxPGIiYmGrp4eHBwcEbBmHZxdXIUOLd8Vxde7sB6/ZaWqpoZFy1Zhpf9ijB3xJ1JTUlCqtCWmzvCDi9uvP0lYvhHokqqvDfXLzdixYzFhwgTJTNuVKlXCs2fP4Ofnh549e0oms3vz5g3Mzc0l93vz5o3kJ47MzMwkcyh8kJWVhbdv30pNhvc9SuJPL1qiQqMgK1W/EqOaXkKHIIh3wcuFDoGIiOinpaTn/luPhV0xHRWhQ/gqg27CXPudsO2P76/0H2NjY8yaNQuDBw+WtPn5+WHDhg148OABxGIxLCwsMGbMGIwePRoA8P79exQvXhwbN26UTFRRvnx5hISE4LfffgMAnDx5Ek2aNMGLFy8UY6IKIiIiIiKin9GyZUvMnj0blpaWqFChAm7cuIFFixahT58+AHKuCxsxYgRmzZoFe3t7yZTqFhYWaNOmDYCceROaNGmC/v37Y9WqVcjMzISXlxe6dOnywwkVwKSKiIiIiIg+owhTqi9btgxTp07FkCFDEB0dDQsLCwwcOBDTpk2TrDNu3DgkJydjwIABiI+Ph5ubG06cOCF13WBQUBC8vLxQv359KCsro3379vD395cpFg7/K6Q4/K9o4fA/IiJSZBz+9+sx7L5VkMeND1LMGTdZqSIiIiIiIimKUKn6lSh/fxUiIiIiIiL6GiZVREREREREcuDwPyIiIiIiksLhf7JhpYqIiIiIiEgOrFQREREREZEUVqpkw0oVERERERGRHJhUERERERERyYHD/4iIiIiISBpH/8mElSoiIiIiIiI5sFJFRERERERSOFGFbFipIiIiIiIikgMrVUREREREJIWVKtmwUkVERERERCQHJlVERERERERy4PA/IiIiIiKSwuF/smGlioiIiIiISA6sVBERERERkTQWqmTCShUREREREZEcmFQRERERERHJgcP/iIiIiIhICieqkA0rVURERERERHJgpaqQyswSCR2CIN4FLxc6BEFY9N4mdAiCeL6uq9AhCCItM1voEAShpaYidAiCeJ+WJXQIgtDXKppfUZSK6OwA6qo8z/+rYaVKNtyDiYiIiIiI5FA0TwMREREREdFXsVIlG1aqiIiIiIiI5MCkioiIiIiISA4c/kdERERERFI4/E82rFQRERERERHJgZUqIiIiIiKSxkKVTFipIiIiIiIikgOTKiIiIiIiIjlw+B8REREREUnhRBWyYaWKiIiIiIhIDqxUERERERGRFFaqZMNKFRERERERkRxYqSIiIiIiIimsVMmGlSoiIiIiIiI5MKkiIiIiIiKSA4f/ERERERGRNI7+kwkrVURERERERHJgpYqIiIiIiKRwogrZsFJFREREREQkByZVREREREREcuDwPyIiIiIiksLhf7JhpYqIiIiIiEgOTKryiKenJ0aMGPHV5dbW1liyZInM2/X29kbVqlV/Oi4iIiIiIlkpKSkJ8qeoOPyvgAQHB0NHR0foMPLEhnVrcO7MKTx98hgaGpqoXLUaho4YDWtrG8k6L55HYsnCebh58zoyMzLg7OqOsRMmw9jYRMDI89a6wNU4c+oknjx5DA1NTVStWg0jRo2BtU0ZoUOTy81FrWBpqvtF+9rTDzBuUwiKG2hiRpdq8KxoBl0tNTyMeo9FB0NxOOS5ZN2gkXVQydIIJvqaiE/JwIW7rzFj5028jk8tyK7I7VpIMDZvXIfwsFDExsRg4ZLlqFu/gWT59MkTcPjQAan7OLu6YcWqtQUcad5Zu2oF1q9ZKdVmaW2DHfuOAADmzvJG8NXLiI2JhraWNipWqYohw0Yp/H4PfHy9w/57vRd98npnZmZi5bKluPi/C3jx8gV0dXVR28kFw0aMQvHiJQSO/Od1btUIr6NefdHepkMXjBw/BcMH9sLN6yFSy1q164jRE6cXVIgFIjs7G6tWLsexI4cQFxsLU9PiaNmmLfoPHKzQX/JktX7tGvgvWYhuv/fAuAmThQ4nz1z/8FkenvPeXrBkOerW+/hZHhcXC//FC3D50j9ITExE9eo1MG7iFFhaWQsXNCkcJlUFxNTU9JvLMzMzoaamVkDRyOd6SDA6du6G8hUqIjs7GyuWLYbXoL7Yve8ItLS1kZqSgj8H9YODgyNWBW4EAASs8MfIoUOwcesOKCsXjgJpSPBVdO7aHRUqVUJ2VjaWLV2EQf37Yt+ho9DW1hY6vJ9Wf/pfUFH++CWiXCkD7J9QHwevRAIAAgY6Q19bHd0X/424xDR0cLHG+qGuqDftL9x59g4AcDH8DRYfCsXr+FRYFNOGT9dq2DjMDU18TgnSp5+VlpoKB4eyaN22PcaMGJrrOi6u7vCe5Su5ra6mXlDh5RsbWzv4B3xMDFVUPh4qHMuVR6OmLWBmbo73CQlYt3oFRv7ZH3sOn4SKiooQ4eaZ1E9e79Gfvd5paWkIDw9D/4FD4ODoiPfv32P+XF+MGDoE23buFShi+a3etAPZ2SLJ7SePIjDaqz88GzSStLVo0wF9BnpJbmtqahZojAVh47pA7Nm5HT6z58DWzg6hoXfhPWUSdHV10e33HkKHVyDu3rmNPbt3wMHBUehQ8lxqaiocHMuiVdv2GDtS+r0tFosxevifUFVVw6KlK6Gjo4OgLRsxeEAf7Nmf872mqCpKJxTyApOqPJSVlQUvLy9s2bIFampqGDx4MHx8fKCkpARra2uMGDFCMkRQSUkJK1euxPHjx3HmzBmMHTsW3t7emDNnDhYvXoyUlBR06tTpu8mYEJYFBErd9vbxQ8O6rggPD0X132ri1s0biHr1EkE790FXN6fiMWOmH+q610bw1cuo7eQiRNh5LmDNOqnbPrPnoK67M8LDQvFbjZoCRSW/uMR0qdsjWpTH4zeJ+OdeNACgpr0JxmwMxvXHcQCAhQdDMbhxWVS1LiZJqgJO3Jfc/0VcCpYcDsPWEXWgqqKErGxxAfVEfq7udeDqXueb66irq8PE5Nd7n8pDVUUFxl/pU5v2nST/m1uUxIAhw9CjSztEvXqJUqUtCyrEfOHmXgduX3m99fT0sCpwvVTbhElT8XvXjoiKegVzc4uCCDHPGRoVk7q9bdNalCxVGlWrf/wM09TUhLFJ4RllkJtbN2/Ao259uHt4AgAsSpbCiWNHEXrnjrCBFZCUlGRMmjAW07xnIXB1gNDh5LlvfZZHPnuKO7dvYde+w7C1swcATJzijUZ13XDi+FG0bd+xIEMlBVY4Sga/iE2bNkFVVRVXr17F0qVLsWjRIqxd+/VhQN7e3mjbti3u3LmDPn36YNeuXfD29oavry9CQkJgbm6OlStXfvX+v4qkpEQAgL6+AQAgIyMDSkpKUFf/eMZeXUMDysrKuHnjuiAxFoSkxP+eBwMDgSPJO2oqyujoao2gC48kbcERsWhb2wqGOupQUgLaOVlBQ10FF8Pf5LoNQx11dHSxxtWIGIVKqH5USMhV1PdwQduWTeA70xvx8e+EDkluzyMj0aqRJzq0bAzvyeNyHR4GAKmpKTh6aD8sSpZCCTOzAo5SeImJiVBSUoKenr7QoeSJzMxMnDp+BE1btZU6Q33qxFG0auCGXp3bYM3yxUhLU6xhvD+iStVquHrlEp49fQIAuH/vHm5ev/7dkyqFhe8sH7jX8YCTc+E46SmLjIwMADnfUz5QVlaGuro6bt64JlRYpIBYqcpDpUuXxuLFi6GkpARHR0fcuXMHixcvRv/+/XNdv1u3bujdu7fkdpcuXdC3b1/07dsXADBr1iycPn0aaWlpBRL/zxCJRFg4zw9VqlaHnb0DAKBS5SrQ1NLCsiUL8OfQkRCLxVi2dBGys7MRGxMjcMT5QyQSYd5cX1StVh32/z0PhUHz30rBQFsd2//3RNLWe/lFrP/TDY9XdUBmlgipGVnoseRvPIlOkrrv9M5V0a+hA3Q0VBEcEYsui84XcPT5z8XNHfUaNIJFyZJ48fw5lvsvxtDBA7Bx6w6FHQpXoVJlTJkxG5ZW1oiNjcH6NQEY3LcHtu4+KLkudO+u7Vi5dCFSU1NhaW2DJSsDoVYIhj3KIj09Hf6LF6BJ0+aSiryi+9/5M0hKSkTTFm0kbfUbN4eZuQWMTU3xOOIBVi9fjMhnTzFr/lLhAs0HvfsNQFJyMtq2bAYVFRVkZ2fjz2Ej0KxFS6FDy3cnjh3FvfAwBO3YI3QogrC2KQMzcwssX7oIk6fNgJaWFoK2bMKbN68RG1s4v7P8MI7+kwmTqjzk5OQkdXbP2dkZCxcuRHZ2dq7r16hRQ+p2eHg4Bg0aJNXm7OyMc+fOffNx09PTkZ4uPWQrQ6wGjU/OuuSXub4+ePQoAms3BknajIoVw9z5S+A3ewZ2bNsKZWVlNGrSDGXLlYeycuF8h/rOmoFHERHYuGWb0KHkqd89bHH6dpTUBBOT2leGgY4a2vidQVxSOpr/VgrrvdzQbNYphL9IkKy37Gg4tl54hNImOhjXpiICBjqjy8ILQnQj3zRu2lzyv72DI+wdHNGqWUOEBF9FbSdnASP7ec6u7pL/7RwcUaFSZbRr3hBnT51AyzbtAQCNm7ZALScXxMbEYPuWDZg6fjRWbdhaIJ85v4LMzEyMGzMCYgCTpnoLHU6eOXZoH2o5u8HEtLikrVW7j0OfbO0cYGxiipFD+uLli0iULKXYwz0/dfLEcRw/chi+cxfA1s4O9+/dw4K5vjAtXhytWrcVOrx88zoqCvPmzMaqwPVF5v37OTU1NSxY7A+f6VNQ1602VFRUUKu2M1zd6kAsLnyjKyj/MKkSUF7NBujn54cZM2ZItU2YPA2TpuTv7ExzfWfi4t8XsGb9FpQoIT30x8nFFQePnkT8u3dQUVGBnr4+GtdzR8lSpfM1JiH4zvLB3xfOY/2mrYVqCFQpY214VCyBHkv/J2mzLq6LAY0c4TLhKO69zEmgQiPj4eRQHP0aOGD0xmDJum+T0vE2KR2PXifiwcsE3PVvi5p2Jgh+GFvgfSkopUqXhqGREZ5HPlPYpOpzenr6KG1phRfPIyVtunp60NXTQ2lLK1SsXBmNPVxw4dxpNGrS/BtbKhwyMzMxfsxIRL16hTXrNhaaKtXrqFe4dvUyZs5b8s31ylWsBAB4+fx5oUqqliycj979+qNJs5x92N7BEVFRr7Bh7ZpCnVSFhYXi7ds4dO3UTtKWnZ2N69eCsXN7EK5ev6OwVXdZlCtfEdt3H0BiYiKyMjNhVKwYenTrhPIVKgodmqA4UYVsmFTloStXrkjdvnz5Muzt7X/4A6lcuXK4cuUKevT4ONPQ5cuXv3u/iRMnYtSoUVJtGeL8m0lQLBZjnt8snD97GqvXbULJUqW+uq6hkREAIPjKZbx9G4c6nvXyLa6CJhaL4Td7Js6eOYV1G7egVCFLGLvXsUXM+3ScvPnxehot9Zx9WfTZ2TuRSPzNKqTSf8vUVQv3ZZxvXr9GQnw8TD8506/oUlKS8fLFczRp3irX5WIxIIYYmf9dl1CYfUioIiOfYc26TTA0NBI6pDxz/PB+GBoVg5Prt68hevjgHgAUuokr0tJSoaQk/fmkrKwMkUj0lXsUDrWdnLBn/2GptmlTJsLGpgx69+1fJBKqT+np6QHImbwiPOwuBnsNEzgiUiRMqvJQZGQkRo0ahYEDB+L69etYtmwZFi5c+MP3Hz58OHr16oUaNWrA1dUVQUFBCA0NRZky3/79Fw0NjS/K9olp+XcgmOvrgxPHj2LhkuXQ1tGRjDnW1dWTTLV76MA+2JQpAyOjYrh96yYWzvNFt997Sv2WlaLznTkDx48dwZJlK6GjrSO5XkxXT0/hpxxWUgK61SmDHf97jGzRxwQqIuo9Hr1OxKLetTBt+w28/W/4n2dFM3RZlDO07zdbY1SzMcblB9GIT86ATQk9TGpfGY/fJCpclSolJRnPIz9WaF6+fIH798Khb2AAAwMDrA5YgfoNGsHExATPnz/H0kXzUdrSEs6ubgJGLZ9li+fDrY4nzMwtEBsTjbWrVkBFWQUNmzTDyxfPcebkCdRycoGhkRFiot9gy4a10NDQgLOb4l/Q/63X28TEFGNHDce98DAsXbEKIlG25LPPwMBAoa8pE4lEOH74AJo0bw1V1Y9fC16+iMTpE8fg5OoOfQNDPI54gOWL56JKtRqwtS9c027X8ayLdYGrYG5uDls7O9wLD8fWzRvRpm17oUPLVzo6upLroT/Q0tKGgaHhF+2K7PP39qtP3tvm5hY4dfIEjIyMYGZugYcRD7Bg7mx41q0PZxfF/SyngsekKg/16NEDqampqFWrFlRUVDB8+HAMGDDgh+/fuXNnPHr0COPGjUNaWhrat2+PwYMH46+//srHqGW3Z9cOAMDAvj2l2qf7+KLlf8Mknj19ghX+i5GQkAALCwv07jcI3f/o+cW2FNmundsBAH17/SHV7jPLD63btsvtLgrDs4IZSpvoIOjvx1LtWdlidF5wHtM7V8G2UXWgo6mGJ28SMWTNJZy+lVPRSknPQouapTChXSVoa6jiTUIqztyOwsLld5GRpVhnfcNC72JAn4/77aL5cwAALVu1wcSp3oh4cB9HDh1A4vtEmBY3hZOzK4Z4DZea+VLRRL95g+kTxyIhIR6GRsVQuWp1rNm0DUZGxZCVlYVbN65h57YtSHyfgGLGJqha/Tes3hCEYsWMhQ5dbmGhd9H/k9d74Sev96AhXrhw/iwAoEuHNlL3C1y/CTVq1i6wOPPatauX8OZ1FJq1kh7mpqaqhmtXL2PPji1IS02FaQkz1KnXED36DBQo0vwzftIUrFzmD99ZPnj3Ng6mpsXRoWNnDBg8ROjQKA+Ehd6V+s7y4bO8Ras2mDFrDmJjorF4/hzExcXBxNQUzVu2Rv+Bg4UK95fB4X+yURLzKrxCKT8rVb8ytUI+vOxrLHoXrgkyftTzdV2FDkEQaZm5T35T2GmpFa2hSB+8T8sSOgRB6GsVzfO+SkV0yrVPR0UUJboav+7rbTv6uCCP+2hhU0EeV15F8xOLiIiIiIi+ioUq2RTN0/pERERERER5hJUqIiIiIiKSwmuqZMNKFRERERERkRyYVBEREREREcmBw/+IiIiIiEgKR//JhpUqIiIiIiIiObBSRUREREREUjhRhWxYqSIiIiIiIpIDkyoiIiIiIiI5cPgfERERERFJ4eg/2bBSRUREREREJAdWqoiIiIiISIqyMktVsmClioiIiIiISA6sVBERERERkRReUyUbVqqIiIiIiIjkwKSKiIiIiIhIDhz+R0REREREUpQ4/k8mrFQRERERERHJgZUqIiIiIiKSwkKVbFipIiIiIiIikgOTKiIiIiIiIjlw+B8REREREUnhRBWyYaWKiIiIiIhIDqxUERERERGRFFaqZMNKFRERERERkRxYqSqkxEIHIBCRuGj2/EFAJ6FDEESr1ZeFDkEQO3rVFDoEQaRmZgsdgiBSM4pmv3U0VIQOQRAqRbQ4kCUSCR2CQIrmfl4YMakiIiIiIiIpHP0nGw7/IyIiIiIikgMrVUREREREJIUTVciGlSoiIiIiIiI5sFJFRERERERSWKiSDStVREREREREcmBSRUREREREJAcO/yMiIiIiIimcqEI2rFQRERERERHJgZUqIiIiIiKSwkKVbFipIiIiIiIikgOTKiIiIiIiIjlw+B8REREREUnhRBWyYaWKiIiIiIhIDqxUERERERGRFBaqZMNKFRERERERkRxYqSIiIiIiIim8pko2rFQRERERERHJgUkVERERERGRHDj8j4iIiIiIpHD0n2xYqSIiIiIiIpIDK1VERERERCSFE1XIhpUqIiIiIiIiOTCpIiIiIiIikgOH//3CvL29ceDAAdy8eVPoUKTs2bUde3ftQNSrlwCAMrZ26DtwCFzd6gAAfH2m4+qVS4iNiYaWtjYqV6mGoSNGw9qmjJBh54lrIcHYvGEdwsJCERsTg0VLl6Nu/QaS5WKxGAErlmH/nt1ITHyPKtWqY9LU6bCyshYuaDmtW70C69eslGqztLLB9n1HEPXqJTq0bJTr/WbOWYR6DRsXRIh5oketUuhZu7RUW+S7VPTeehMAYKSthoGuVvittAG01FXw4l0qgkJe4n+P3krWL2WoiQGuVqhorgdVFSU8jk3BxsvPcfPl+4Lsitxiot8gYNkiXP73f0hLS0OpUpaYNH0WypavCACY7T0Jx48clLpPLWdXLFq2Rohw88TaVbns59Y22LHviFSbWCzG6KGDcPnfi/Bb6A+PuvULMky53bl5DXu2bUTEvXC8jYvBNL/FcKlTT7L84vnTOHZgNyLuhyPxfQJWbNgJW4eyUtt4GxeLtSsW4UbwZaSkJKOUpTW69ugPt7oNPn+4X9aGtWtw7swpPH3yGBoamqhc9cNxykayzmyf6bh6WfpYNmyk4h/LroUEY/PGT45jS6SPY6tWLsNfx4/h9ZvXUFNVQ7nyFeA1bAQqVa4iYNTy2btrB/bt3oFXn35vGTAYLv99b3nxPBL+i+bj1s3ryMjIgLOLG0ZPmAxjYxMhwxYcR//JhkkVyax4cTN4DR+F0pZWEIvFOHr4IMYM98LWnXtha2ePsuUroEnzFjAzs8D79/FYE7ACXoP64eCxU1BRURE6fLmkpqbCwbEsWrdtj9Ejhn6xfOP6tdgetAU+s+egZMlSWLl8Kf4c2A97Dx6FhoaGABHnDRtbOyxduVZyW0Ul56OjeAkzHPrrvNS6B/ftxrYtG+Dk6laQIeaJJ3EpGHsgTHI7WySW/D+hoR10NVQx5eh9vE/NRD0HE0xt4oAhO2/jYWwKAGB2i7J4kZCGMfvDkJ4lQvuq5pjVsiz+2HwD71IyC7w/P+P9+wQM7vs7qteohQVLV8HQqBhePH8GPX19qfVqu7hh0rRZkttq6uoFHWqes7G1g3/Al/v5p3YGbVbo6wzSUlNhY+eIRs3bYOakUV8uT0tFhcrV4F6vMZbOnZHrNhbMnIykpER4z10KfQMjnDt1DL7TxsJ/3TbYOZTL7y7kieshwejYpRvKV6iI7OxsrPBfDK9BfbF7/xFoaWsDAMqVr4CmzVrAzNwC7xPisTpgBf4c2A+Hjiv2sSw1NRUODl8/jllZWWP8pKkoVao00tPTsHXLJgwZ2BcHj55EsWLFBIhYfsVLlMCQYSNR2tIKAHD00AGMHeGFLTv2wrxkSQwb3B/2Do5YsWYDAGD1Cn+MGfYn1m3ZDmVlDuqiH8OkKp+JRCIsWLAAa9aswfPnz1GiRAkMHDgQkydPxvjx47F//368ePECZmZm6N69O6ZNmwY1NTVs3LgRM2bkHNA+HMA3bNiAXr16CdibHHU860rdHjJ0BPbu2oG7t2/B1s4e7Tp0kiyzKFkSg72Go1vHNoh69RKlSlsWdLh5ys29Dtzc6+S6TCwWY9uWzeg/YBDq1ss5ez3Tdy4aeLji3JnTaNKseUGGmqdUVFRgbGL6Q+1/nz+D+g2bQFtbp6DCyzPZIvFXk58KZnpYcv4x7r9JAgAEhbxEh6rmcCiui4exKdDXVEUpIy0sOPsIj+NykqzAf5+hdWUz2Bhr411KQoH1Qx5Bm9aheAkzTJo+W9JmUbLUF+upq6nnuk8oMtWv7OcfPLgfju1bN2H91p1o2ciz4ALLQzWd3VDT+esnPBo0aQkAeB318qvrhN29Ba8xk+FYvhIAoFuvAdi/cysi7oUrTFK1bFWg1G3vmX5o6OmK8LBQVK9REwC+OJYNGTocXTso/rHsW8cxAGjavKXU7dFjJ+DAvj2IeHAftZ2c8zu8fOHuIf29ZfDQEdi3ewfu3rmN6OhoRL16ic079kJXVxcAMH2mHxrUcULI1cuo5eQiRMi/BEU+gSQEJlX5bOLEiQgMDMTixYvh5uaGqKgo3Lt3DwCgp6eHjRs3wsLCAnfu3EH//v2hp6eHcePGoXPnzrh79y5OnDiB06dPAwAMDAyE7EqusrOzcebkCaSmpqBSlapfLE9NScHhg/tgUbIUSpiZFXyABejlixeIjY1BbeePH8B6enqoWLkybt+6qdBJ1YvISLRq7AkNDQ1UqFQFg7xGwMzc4ov17oWHIuL+PYweP0WAKOVX0lATO3v/hoxsEcJeJ2Ldv5GITsoAAIS+TkRdexNceRqPpPQseNobQ01VWTK0731aFiLfpaJhWVNERCcjI1uEFhVL4F1KBh5EJwnZLZn88/c51HJyxZTxI3HzeghMTYujbccuaNW2o9R6N64Fo0VDd+jp6eO3mrXRf/AwGBgaChN0HnkeGYlWjTyhrqGBipWl9/O01FR4TxqH0ROmFLpkUlblK1bB32f+Qm2XOtDR1cPfZ/9CRkY6qlSvIXRoPy0pKREAoP+V42xqSgoOHdiHkkXgWPapzMwM7NuzE7p6enBwLPv9OyiA7OxsnDn1F1JTU1GxchW8fPEcSkpKUP+k2q6uoQFlZWXcunG9SCdVJBsmVfkoMTERS5cuxfLly9GzZ08AgK2tLdzccs4STpny8YuntbU1xowZgx07dmDcuHHQ0tKCrq4uVFVVYfYLfoA/jHiAPn90RUZGOrS0tTF/8TKUsbWTLN+9cxuWLV6I1NQUWFnbYMXqdVBTU/zhQd8SGxsDAChmbCzVbmxsgrjYWCFCyhPlK1bGZO/ZsLS2RlxMDNYHBmBIvx7YsusgdHSkq1FHDuyFtU0ZVKpSTaBof969N0mYd/ohXrxLQzEdNfSoVRpL2ldE3203kZopgs/xB5jaxAEHBtREVrYIaVkiTD96H68S0iTbGLs/DD7NHXF4UC2IxcC7lExMOBiOpPRsAXsmm1cvX+DA3p3o3L0nevQegPCwO1iywA9qampo2qINAKC2sxs86jaAeclSePniOdasWIIxwwZi1YZtCjssqkKlypgyYzYsrawRGxuD9WsCMLhvD2zdnbOfL104F5WqVEMdz3rf31ghN2nmfPhOG4eOTetARUUVGpqamOa7GBalFLN6IxKJsHCeH6pUqw47ewepZbt3bIP/p8eyNYX/WAYAf184hwljRyMtLRUmpqZYtWY9jIyMhA5LLg8jHqBfj67IyMiAlpY25i7yRxlbOxgZFYOmlhaWL1mIIUNHQAwxVixdhOzsbMlxvahioUo2TKryUXh4ONLT01G/fu4XMu/cuRP+/v549OgRkpKSkJWVBf3Prlv4Eenp6UhPT5duE6vl6zU8VtbWCNq1D0lJSThz6i94T52I1es2SxKrps1aoraTC2JjY7B10wZMHDsSazdtU+jriooqZ1d3yf929o4oX6ky2jdviLOnTqBlm/aSZelpaTh14hh69RskRJhyu/osXvL/4zgg/HUStvWqDk97ExwPi0Zvp9LQ1VDBmP2hSEjLgmuZYpjW1AEj9obiyX/D/YZ52iA+NRMj9oYiI0uEpuWLY1bLshiy8w7eKsg1VSKRCGXLV8TAP0cAABzKlsOTRw9xYO8uSVLVoHEzyfq2dg6wtXNA5zZNcONaMGrUchIgavlJ7ecOjqhQqTLa/befGxoZ4VrwFWzcvkfACH8dmwNXIDkpEX5L18DAwBD//u8cfKeNw4KVG2Bjay90eDKbO9sHjx5GYO3GoC+WNW3eErWdXRAbE4MtmzZgwpiRWLe58B/LatasjR179iP+3Tvs27sb48aMwJagXV+cNFQkVtbW2LIz53vL2dN/wWfaJASs3YQytnbwnbcY83x9sGv7VigrK6Nhk2ZwLFee11ORTLi35CMtLa2vLrt06RK6d++OZs2a4ciRI7hx4wYmT56MjIwMmR/Hz88PBgYGUn+L5s+RJ/TvUlNTR2lLq5xZgYaPgr2DI3YEbZEs19XTg6WVNar/VhNzFy7B0ydPcP7s6XyNSWgm/w0JehsXJ9UeFxcLY5PCM4OQnp4+SltZ4cXzSKn2c2dOIi0tFU1atBIosryVnJGNF/FpsDDQhLm+BtpWMcf8M49w48V7PI5NwZarL3A/OgmtK5UAAFQrpQ8nayPMOhGB0KhERMQkw//CE6RnidConOIMFzM2MYW1ja1Um5VNGbx5HfXV+5QsVRqGhkZf7BOKTE9PH6Utc/bza1ev4OWL52js4Qz3mpXhXrMyAGDy2BH4s38vYQMtYK9ePMehvTswcuIMVKtRG2XsHfF7n0GwL1seh/fuEDo8mc31nYmLf1/AqrWbch3WJzmW1aiJeYtyjmXnzhTuYxkAaGlrw9LSCpWrVIW3z2yoqKhi/37FPqnw6feWP4flfG/ZuS3ne4uTiyv2HfkLJ85exF/n/sGM2XMRE/0m1+tJib6Glap8ZG9vDy0tLZw5cwb9+vWTWvbvv//CysoKkydPlrQ9e/ZMah11dXVkZ39/2NDEiRMxapT0LE7pYjU5IpedWCRGRmbuCaFYDIgh/qmEUZGULFUKJiamuHL5EhzL5lysnZSUhLu3b6Njp64CR5d3UlKS8fLFczRpJp08HTm4D24edWFkpJizQ31OU00ZFgaaOH0vBppqOUPaxGLpdUSijxfyaqrmrCOC9EpiMaCsQGMoKlWphshnT6Tanj97mus1dB9Ev3mNhIR4mBSikweS/bx5K9Rv2Bgt23aQWv5HpzYYNno83Op4ChOgQNLTc4a7fn4GX1lZGeLP3yC/MLFYjHl+s3D+7GmsXrcJJUt9/8vzh2NZ5leOdYWZWCRCZiE7hotEYmRmSI8gMPxviGPI1ct49/ZtkR/uy4kqZMOkKh9pampi/PjxGDduHNTV1eHq6oqYmBiEhobC3t4ekZGR2LFjB2rWrImjR49i//79Uve3trbGkydPcPPmTZQqVQp6enq5DjnQ0ND4ov19mijf+rV86SK4uLnDzMwCKSnJOHHsCK6FXMWygEC8ePEcp/46DidnVxgZGeHNmzfYtD4Qmhoakt+xUmQpKcl4HvnxbPzLly9w/1449A0MYG5ugW5/9MDaNatgaWWNkiVLYuVyf5gWLy71GyCKZvni+XCt4wkzcwvExkRj7eoVUFFWQYMmH4eAvXj+DDevh2CBf4CAkcpnoKsVLj15hzeJ6TDWUUOv2qUhEotx9kEskjKy8SI+FSPrlsGqf57hfWom3GyL4TdLA0w+nDPxTOjrRCSlZ2F8AztsCX6BjCwRmlUoATN9DVx++k7g3v24zt16YFCf37F5/RrUa9gYYaF3cGj/Hoyb7A0g5z2wITAAHvUawtjYBC9fPMdK/4UoWdoStb4xq9yvbtni+XD7dD9flbOfN2zSDEZGxXKdnKKEmbnCnclOTUnBqxcfP8Nev3qJRw/uQU/fAMXNzJH4PgHRr6MQ99+1JC8inwIAjIxNUMzYBKWtrGFRyhL+82aiv9co6Okb4tL/zuJG8GXMmLdMiC79lLmzfXDi+FEsXLoc2jo6kmtndHX1oKmpmXMsO3EcTi4fj2Ub1xWOY9m3jmOGBoZYG7gKHp71YGJqivh377BrxzZER79Bw0ZNBIxaPiv8F8HFtQ5KmJkjJSUZfx0/gushV7F0Zc4skIcP7IN1GVsYGRnhzu2bWDTPD11/7wEra5vvbJnoIyWxIp1aUkAikQh+fn4IDAzEq1evYG5ujkGDBmHixIkYN24c1q9fj/T0dDRv3hxOTk7w9vZGfHw8gJxrpbp3744zZ84gPj5epinV8zOpmjl9MoKvXkZsTAx0dfVg5+CAnr37obazK2KiozFrxhTcCwvD+/fvUczYGNV+q4F+A4fAugA+nFRV8vesSsjVK+jfp+cX7S1bt4HP7DmSH//dt3sXEhPfo2r13zBpyrR8/2BOyceJEKZNHIOb10PwPiEehkbFULlqdQwYMkxqSuFVy5fg5LHD2HPkVIGOQe+8ITjPtjWlsT0qWehDX0sVCamZuPsqEesuRSLqfc71iiUNNNHPxRKVLPSgqaaCVwlp2HX9FU7f/zgJiUNxHfRxsoRjcR2oqCjhWVwqtgS/kLpeKy/s6FUzT7f3uX/+dx6rly/Bi+fPYG5RCp2795DM/peeloaJY4biwf17SEp8DxPT4qjp5IL+g4aiWD7/UGZ+7lpTJ4zBreshSPhkPx/457CvTp3tUr1Cgf347/vUrDzb1q3rwRg/tN8X7Q2atsKYKTNx8uhBLPKd9sXy7n0G4Y++gwEAL58/w/qApQi9fQOpqSmwKGWJ9l17SKZjzysmevk3IUSNyrlP/T59pi9atm6LmOhozPT+eCwz/vRYZpO/n+cq+VwdCAn+ynGsVRtMnjYDk8aPwZ07txD/7h0MDA1RoUIl9B84GBUqVsrXuDKy8+97yyzvKQi5chmxsR+/t/zRq59ktt4VSxfhyKH9eJ+QAHOLkmjXsTO6/t6zQCo1hlq/7uQ+dRb9I8jj/j3KVZDHlReTqkIqP5OqX1l+J1W/qvxMqn5leZlUKZL8Tqp+VUX1mvG8TKoUSX4mVb+y/E6qflX5mVT9yphUfUnWpOrly5cYP348jh8/jpSUFNjZ2WHDhg2oUSPnZx7EYjGmT5+OwMBAxMfHw9XVFQEBAbC3/zixztu3bzF06FAcPnwYysrKaN++PZYuXSr57bIfUUQPUUREREREpMjevXsHV1dXqKmp4fjx4wgLC8PChQulfgJg3rx58Pf3x6pVq3DlyhXo6OigcePGSEv7+JMo3bt3R2hoKE6dOoUjR47g77//xoABA2SKhddUERERERGRFEUoms6dOxelS5fGhg0bJG02nwzRFYvFWLJkCaZMmYLWrVsDADZv3owSJUrgwIED6NKlC8LDw3HixAkEBwdLqlvLli1Ds2bNsGDBAlhYfH2ipk+xUkVERERERArn0KFDqFGjBjp27IjixYujWrVqCAwMlCx/8uQJXr9+jQYNPk4YZmBggNq1a+PSpUsAcn7myNDQUJJQAUCDBg2grKyMK1eu/HAsTKqIiIiIiEiKkpKSIH/p6el4//691F96enquMT5+/FhyfdRff/2FwYMHY9iwYdi0aRMA4PXr1wCAEiVKSN2vRIkSkmWvX79G8eLFpZarqqqiWLFiknV+BJMqIiIiIiL6Jfj5+cHAwEDqz8/PL9d1RSIRqlevDl9fX1SrVg0DBgxA//79sWrVqgKOmkkVERERERF9RklJmL+JEyciISFB6m/ixIm5xmhubo7y5ctLtZUrVw6R//0Wm5mZGQDgzZs3Uuu8efNGsszMzAzR0dFSy7OysvD27VvJOj+CSRUREREREf0SNDQ0oK+vL/WnoaGR67qurq64f/++VNuDBw9gZWUFIGfSCjMzM5w5c0ay/P3797hy5QqcnZ0BAM7OzoiPj8e1a9ck65w9exYikQi1a9f+4bg5+x8RERERESmckSNHwsXFBb6+vujUqROuXr2KNWvWYM2aNQByrgsbMWIEZs2aBXt7e9jY2GDq1KmwsLBAmzZtAORUtpo0aSIZNpiZmQkvLy906dLlh2f+A5hUERERERHRZ5QUYE71mjVrYv/+/Zg4cSJ8fHxgY2ODJUuWoHv37pJ1xo0bh+TkZAwYMADx8fFwc3PDiRMnoKmpKVknKCgIXl5eqF+/vuTHf/39/WWKRUksFovzrGf0y3ifVjR/mVxV5df/AMgPKenZQocgiM4bgoUOQRA7etUUOgRBKBfRAevvU7OEDkEQJnrqQocgCBUF+CKbHzKyi+b3FkMtFaFD+Kp6/pcEedyzw5wFeVx5sVJFRERERERSimh+/9OK6Hk/IiIiIiKivMGkioiIiIiISA4c/kdERERERFKUOf5PJqxUERERERERyYGVKiIiIiIiksJClWxYqSIiIiIiIpIDK1VERERERCRFEX7891fCShUREREREZEcmFQRERERERHJgcP/iIiIiIhIijJH/8mElSoiIiIiIiI5sFJFRERERERSOFGFbFipIiIiIiIikgOTKiIiIiIiIjlw+B8REREREUnh6D/ZMKkqpFSL6JQtykX0E0CliL7ehwY6CR2CIEw6rxM6BEG83dVP6BAEIRYLHQEVJOUi+nmuoaQidAhEcmFSRUREREREUpRQNBP8n8VrqoiIiIiIiOTAShUREREREUkpoiNRfxorVURERERERHJgUkVERERERCQHDv8jIiIiIiIpSkV0RuWfxUoVERERERGRHFipIiIiIiIiKSxUyYaVKiIiIiIiIjkwqSIiIiIiIpIDh/8REREREZEUZY7/kwkrVURERERERHJgpYqIiIiIiKSwUCUbVqqIiIiIiIjkwKSKiIiIiIhIDhz+R0REREREUpQ4/k8mrFQRERERERHJgZUqIiIiIiKSwkKVbFipIiIiIiIikgMrVUREREREJIU//isbVqqIiIiIiIjkwKSKiIiIiIhIDhz+R0REREREUjj4TzasVOUhT09PjBgxQugwiIiIiIioALFSRT/lWkgwNm9ch7CwUMTGxGDRkuWoW7+BZPmqlcvw1/FjeP3mNdRU1VCufAV4DRuBSpWrCBh13tq1Yxt27dyOVy9fAgBs7ewxcPAQuLl7CBxZ/tq8PhArly1G525/YOTYiZL2O7duYtWKpQi9cxvKKspwcCiLJSsDoampKWC08vmwn4f/t58v/Gw/nz55Ag4fOiB1H2dXN6xYtbaAI/15yspKmNK5Orp62KGEoRai3qVgy9kHmLP7JgBAVUUJ3t1qoPFvpWFTQg/vUzJw9tYrTN0SjKh3KZLt2Fnow7dnbTiXLQF1VWXcffYWM7Zdw993owTqmXwCVizD6oDlUm3WNjY4cPiEQBHlj3WrV2D9mpVSbZZWNti+7wgAIC42BiuWLkTwlX+RkpwCSytr9Og7AHXrNxIi3DyzYe0anDtzCk+fPIaGhiYqV62GoSNGw9rGRrLOgD49cD0kWOp+7Tp2xqSp3gUcbf4pqsexz61fuwb+Sxai2+89MG7CZKHD+WXwx39lw6RKgWRkZEBdXV3oMAAAqampcHAoi9Zt22P0iKFfLLeyssb4SVNRqlRppKenYeuWTRgysC8OHj2JYsWKCRBx3itewgzDR46BpZUVxGIxDh88gOFef2Ln3v2ws7MXOrx8ERZ6B/v37oKdvaNU+51bNzHCawB69u6P0eMnQUVFFREP7kFZWbGL4Wmf7OdjctnPAcDF1R3es3wlt9XVfo336I8a3bYy+jcph/7+FxAW+Q6/2Zlg9dA6eJ+SiZVHQ6GtoYqqZUwwZ9cN3H76Fka66ljQ1xm7JzWE29iDku3sm9wYD18loOm0Y0jNyIJXy4rYN7kRKgzehTfxqQL28OfZ2tlj9doNktsqKioCRpN/bGztsHTlxxMBKiofvxrMnDYJSUnvMXfRchgYGuHUiaOYNmE01m3ZBYey5YQIN09cDwlGxy7dUL5CRWRnZ2OF/2J4DeqL3fuPQEtbW7Je2/YdMfDPj+99TU0tIcLNN0XxOPa5u3duY8/uHXBwcPz+ykTf8ENJ1e3bt394g5UrV/7pYBRJcnIyBg8ejH379kFPTw9jxoyRWp6eno7Jkydj+/btiI+PR8WKFTF37lx4enpK1rl48SImTpyIkJAQmJiYoG3btvDz84OOjg4AwNraGn379kVERAQOHDiAdu3aYePGjQXYy69zc68DN/c6X13etHlLqdujx07AgX17EPHgPmo7Oed3eAXCs249qdtDh4/Erh3bcfvWzUJ5MEpJScb0SeMwceoMbFi7WmrZkoVz0KnL7+jRp7+kzcra5vNNKBxX9zpw/cZ+DgDq6uowMTEtoIjynlPZEjhy9RlOXHsOAIiMSUInd1vUsM/p0/uUTLSYcVzqPiMD/8XF+W1Q2kQHz2OTYaynAXsLAwxe/jfuPnsLAJi6ORiDmpZHeUsjhU2qVFRUFPq1/VEqKiow/ko/796+gTETp6F8xZxje69+g7Bz22bcCw9V6KRq2apAqdveM/3Q0NMV4WGhqF6jpqRdU1OzUO8DRe049rmUlGRMmjAW07xnIXB1gNDhkIL7odPIVatWRbVq1VC1atVc/z4sq1atWn7H+8sYO3YsLly4gIMHD+LkyZM4f/48rl+/Llnu5eWFS5cuYceOHbh9+zY6duyIJk2aICIiAgDw6NEjNGnSBO3bt8ft27exc+dOXLx4EV5eXlKPs2DBAlSpUgU3btzA1KlTC7SPeSUzMwP79uyErp4eHBzLCh1OvsjOzsbxY0eRmpqCKlUK5/tggd8suLp7oJaTi1T727dxCL1zG0bFiqF/z25oWt8dg/v2wM0b1wSKtGCFhFxFfQ8XtG3ZBL4zvREf/07okGRy+d4b1K1sATsLfQBAJeticC5nhpPXn3/1Pvra6hCJxIhPzgAAxCWm4/6LeHSraw9tDVWoKCuhX+OyeBOfihuPYgukH/khMvIZGtZ1Q/Mm9TFx/GhERb0SOqR88SIyEq0ae6Jjq8bwnjwOrz/pZ8XK1XDm5Am8T4iHSCTC6b+OISM9QyrxKAySkhIBAPoGBlLtx48dQf06zujUtiWWL12EtFTFPEHwI4rCcexzvrN84F7HA07OLt9fuQhSVhLmT1H9UKXqyZMn+R2HQklKSsK6deuwdetW1K9fHwCwadMmlCpVCgAQGRmJDRs2IDIyEhYWFgCAMWPG4MSJE9iwYQN8fX3h5+eH7t27Sya2sLe3h7+/Pzw8PBAQECC5DqVevXoYPXr0N+NJT09Henq6VFu2kjo0NDTystsy+/vCOUwYOxppaakwMTXFqjXrYWRkJGhMeS3iwX380a0LMjLSoa2tjcX+K2BrZyd0WHnu1IljuH8vDOu37vpi2asXLwAAa1evwLCRY2HvWBbHjxzC0IF9ELT7ICytrAs42oLj4uaOeg0awaJkSbx4/hzL/Rdj6OAB2Lh1h8IMFVuw7xb0tdVxa1lHZIvEUFFWwvSgEOz4+1Gu62uoqWBWj1rY9b9HSEzNlLQ39z6GnRMaImZbT4jEYsQkpKK1zwlJ4qVoKlWuDJ9ZfrC2tkFsbAxWrVyBPj26Y8+Bw9DR0RU6vDxTvmJlTPaeDUtra8TFxGB9YACG9OuBLbsOQkdHBzPnLsS0CaPRtJ4rVFRUoampCd8FS1GqtJXQoecZkUiEhfP8UKVaddjZO0jamzRrAXNzC5iaFkdExH0sW7wQz54+wfzFywSMNu8VlePY504cO4p74WEI2rFH6FCokPihpMrKqvB8eOaFR48eISMjA7Vr15a0FStWDI6OOeNx79y5g+zsbDg4OEjdLz09HcbGxgCAW7du4fbt2wgKCpIsF4vFEIlEePLkCcqVyxlWUaNGje/G4+fnhxkzZki1TZoyDZMFvpi2Zs3a2LFnP+LfvcO+vbsxbswIbAnahWL/PQeFgbW1DXbtPYCkpEScOvkXpk4aj3UbtxaqA9Kb11FYNN8P/gFrc03URSIRAKBt+05o0bodAMCxbHkEX72MIwf3YciwUQUab0Fq3LS55H97B0fYOziiVbOGCAm+qjDDXDu4lkGXOrbotfgcwiLfobKNMeb3dULUuxQEnYuQWldVRQlbx9SDEoBhq/+RWrZ4gCtiEtLQYPIRpGZkoVcDR+yd1Ahu4w7g9TvFO7v/6YX6Do5lUbFSFTRrVBcnTxxH2/YdBYwsbzm7ukv+t7N3RPlKldG+eUOcPXUCLdu0R2DAMiQlJmJpwDoYGBrif+fPYtqE0Vi5djNs7R2+sWXFMXe2Dx49jMDajUFS7e06dJL8b+fgABMTUwzu3xsvnkeiVGnLgg4z3xSF49jnXkdFYd6c2VgVuF7wE9C/Mk5UIZufmqhiy5YtWLVqFZ48eYJLly7BysoKS5YsgY2NDVq3bp3XMSqcpKQkqKio4Nq1a1+crdbV1ZWsM3DgQAwbNuyL+1tafvyw/nB91bdMnDgRo0ZJf3HNVhL+YnktbW1YWlrB0tIKlatURavmjbF//x707TdQ6NDyjJq6Oiz/O+lQvkJFhN69g6CtmzHN20fgyPLOvfBQvHsbh17dOkjasrOzcfN6CPbs3Iad+48CAKzL2Erdz9qmDF6/VsyZ335WqdKlYWhkhOeRzxQmqfLtWQsL9t3C7ouPAQChke9gaaqLse2qSCVVqipKCBpTH5amumg6/ZhUlcqzkgWa/VYa5n9skbSPWPMv6lcpid/r2mPBvh+/LvdXpa+vD0srazyPjBQ6lHylp6eP0lZWePE8Ei+eR2Lvzm3YsusgytjmfMG2dyiLWzeuYe/u7Rg3abrA0cpvru9MXPz7AtZs2IISZmbfXLdipZzryp5HFq6kqigcxz4XFhaKt2/j0LVTO0lbdnY2rl8Lxs7tQbh6/Y7CjDagX4fMSVVAQACmTZuGESNGYPbs2cjOzgYAGBoaYsmSJUUiqbK1tYWamhquXLkiSYDevXuHBw8ewMPDA9WqVUN2djaio6Ph7u6e6zaqV6+OsLAw2OXBmSANDY0vzrSkZIjl3m5eE4tEyMxQzKFAP0pUCPtYo5YzgnYflGqbNX0yrGxs8EevfihZqjRMTYsj8ulTqXWeP3sqdRa8KHjz+jUS4uNhalpc6FB+mJaGKv4rNkpki8RQ/mRg+4eEytZCH02mHsPbROnhxtoaOYcSkVj6c0ckFheaM50pKcl48fw5TFoW3kkLgJx+vnzxHE2atUJ6WhoASO0LObeVIf58p1EwYrEY8/xm4fzZ01i9bhNK/jd8/1vu378HADAxLdz7QGE8jn2utpMT9uw/LNU2bcpE2NiUQe++/ZlQ/aeQfHwXGJmTqmXLliEwMBBt2rTBnDlzJO01atT4Yga8wkpXVxd9+/bF2LFjYWxsjOLFi2Py5MmS6aMdHBzQvXt39OjRAwsXLkS1atUQExODM2fOoHLlymjevDnGjx8PJycneHl5oV+/ftDR0UFYWBhOnTqF5cuXfycC4aWkJEudsX358gXu3wuHvoEBDA0MsTZwFTw868HE1BTx795h145tiI5+g4aNmggYdd5aungh3NzrwMzcHCnJyTh29AhCgq8iYM06oUPLUzo6OrD9bBYoTS0tGBgYStq79+yDwFXLc4bAOZbFscMH8ezpE/jOXyJAxHnnW/u5gYEBVgesQP0GjWBiYoLnz59j6aL5KG1pCWdXNwGjls2x4EiM71AVz2OTEBb5DlXLGGNYq4rYfOYBgJyEatu4BqhWxhjtZp+EirISShjmTCv9NikdmVkiXLn/Bu+SM7B2mAd8d91AakYW+jQsC+viepJZBRXNovlzUcezLswtLBATHY2AFcugoqKMJs1aCB1anlq+eD5c63jCzNwCsTHRWLt6BVSUVdCgSTPo6eqhVGlLzJs9A14jxkDfIGf4X/CVS5i3ZOX3N/4LmzvbByeOH8XCpcuhraOD2NgYAICurh40NTXx4nkkThw7Ald3DxgYGCLiwX0smj8H1X+rAftCNPV2UTmOfU5HR1fq+jkA0NLShoGh4RftRD9K5qTqyZMnuc7yp6GhgeTk5DwJShHMnz8fSUlJaNmyJfT09DB69GgkJCRIlm/YsAGzZs3C6NGj8fLlS5iYmMDJyQktWuQckCtXrowLFy5g8uTJcHd3h1gshq2tLTp37ixUl2QSFnoX/fv0lNxeOD8nwW7Zqg0mT5uBp0+e4PChYYh/9w4GhoaoUKES1m8K+uLLuSJ7+zYOUyaOR0xMdM7Mhg6OCFizDs4urkKHVuC6dO+BjPR0LFk4F+8TEmDv4IilAWsVfohMWOhdDPhkP1/0yX4+cao3Ih7cx5FDB5D4PhGmxU3h5OyKIV7Df5nfk/sRowIvYXq337B0gAtMDXJ+/HfdyXvw3XUDAGBRTActa+UMDbq6uJ3UfRtNOYr/hUYhLjEdrX1OwLt7DRz3aQY1FWWEP3+HjnNO4c7TtwXep7zw5s1rTBw3CvHx8TAqVgzVqv2GzUG7Cs3v7H0QHf0G0yeNxfuEeBgaFUPlqtWxeuM2GBnl9HOB/yoELFuEcSO9kJqSglKlS2PKDF+4uH37pwZ+dXt27QAADPzk/Q0A02f6omXrtlBVU8PVy5ewfetmpKamooSZGeo1aIi+AwYLEW6+4XGMKO8oicVimcaJlS9fHn5+fmjdujX09PRw69YtlClTBsuWLcOGDRukphUn4fyKw/8KwufDVIqK1IxsoUMQhLqqYv+48M8y6Vy4zyJ/zdtd/YQOQRDJ6VlChyAIDbWi+f5WUyma/Zbt22jhoaUmdARf12ObMNfDbu6mmL95K3OlatSoUfjzzz+RlpYGsViMq1evYvv27fDz88PatWu/vwEiIiIiIqJCROakql+/ftDS0sKUKVOQkpKCbt26wcLCAkuXLkWXLl3yI0YiIiIiIipARXTwz0/7qSnVu3fvju7duyMlJQVJSUkoXlxxZroiIiIiIiLKSz+VVAFAdHQ07t+/DyDnx8FMC/kUo0RERERERLmR+WrIxMRE/PHHH7CwsICHhwc8PDxgYWGB33//XWr2OyIiIiIiUkxKSkqC/CkqmZOqfv364cqVKzh69Cji4+MRHx+PI0eOICQkBAMHDsyPGImIiIiIiH5ZMg//O3LkCP766y+4uX38ccvGjRsjMDAQTZoUnh92JSIiIiIqqhS3ZiQMmStVxsbGMDAw+KLdwMAARkZGeRIUERERERGRopA5qZoyZQpGjRqF169fS9pev36NsWPHYurUqXkaHBERERERFTxlJSVB/hTVDw3/q1atmtSFYxEREbC0tISlpSUAIDIyEhoaGoiJieF1VUREREREVKT8UFLVpk2bfA6DiIiIiIhIMf1QUjV9+vT8joOIiIiIiH4RCjwSTxAyX1NFREREREREH8k8pXp2djYWL16MXbt2ITIyEhkZGVLL3759m2fBERERERFRwVPkH+IVgsyVqhkzZmDRokXo3LkzEhISMGrUKLRr1w7Kysrw9vbOhxCJiIiIiIh+XTInVUFBQQgMDMTo0aOhqqqKrl27Yu3atZg2bRouX76cHzESERERERH9smROql6/fo1KlSoBAHR1dZGQkAAAaNGiBY4ePZq30RERERERUYFTUhLmT1HJnFSVKlUKUVFRAABbW1ucPHkSABAcHAwNDY28jY6IiIiIiOgXJ/NEFW3btsWZM2dQu3ZtDB06FL///jvWrVuHyMhIjBw5Mj9iJCIiIiKiAqSsyGUjAcicVM2ZM0fyf+fOnWFlZYV///0X9vb2aNmyZZ4GR0RERERE9KuT+3eqnJycMGrUKNSuXRu+vr55ERMREREREQmI11TJJs9+/DcqKgpTp07Nq80REREREREphDxLqoiIiIiIiIoima+pIiIiIiKiwk1JkcfiCYCVKiIiIiIiIjn8cKVq1KhR31weExMjdzCUh4royQWxWOgIhFFU+/06IU3oEATxcmtvoUMQRCP/i0KHIIi9A2oLHYIgMrJEQocgCFXlonm+O1tURA9kv/AXtqK5J/68H06qbty48d116tSpI1cwREREREREiuaHk6pz587lZxxEREREREQKiRNVEBERERGRFE5UIRsOlyQiIiIiIpIDK1VERERERCRFmYUqmbBSRUREREREJAdWqoiIiIiISAorVbL5qUrV//73P/z+++9wdnbGy5cvAQBbtmzBxYtF8zdEiIiIiIio6JI5qdq7dy8aN24MLS0t3LhxA+np6QCAhIQE+Pr65nmAREREREREvzKZk6pZs2Zh1apVCAwMhJqamqTd1dUV169fz9PgiIiIiIio4CkpKQnyp6hkTqru37+POnXqfNFuYGCA+Pj4vIiJiIiIiIhIYcicVJmZmeHhw4dftF+8eBFlypTJk6CIiIiIiEg4ykrC/CkqmZOq/v37Y/jw4bhy5QqUlJTw6tUrBAUFYcyYMRg8eHB+xEhERERERPTLknlK9QkTJkAkEqF+/fpISUlBnTp1oKGhgTFjxmDo0KH5ESMREREREdEvS+akSklJCZMnT8bYsWPx8OFDJCUloXz58tDV1c2P+IiIiIiIqIAp8JwRgvjpH/9VV1dH+fLl8zIWIiIiIiIihSNzUlW3bt1vTnd49uxZuQIiIiIiIiJhKbNUJROZk6qqVatK3c7MzMTNmzdx9+5d9OzZM6/iIiIiIiIiUggyJ1WLFy/Otd3b2xtJSUlyB0RERERERMKSeYrwIi7Pnq/ff/8d69evz6vNERERERERKYQ8S6ouXboETU3NvNocERERERGRQpB5+F+7du2kbovFYkRFRSEkJARTp07Ns8CIiIiIiEgYnKdCNjInVQYGBlK3lZWV4ejoCB8fHzRq1CjPAiMiIiIiIlIEMiVV2dnZ6N27NypVqgQjI6P8iqnQ8fT0RNWqVbFkyRKhQyEiIiIi+i5OqS4bmZIqFRUVNGrUCOHh4UyqirBrIcHYvGEdwsJCERsTg0VLl6Nu/QaS5WdOncSeXTsQHhaKhIQE7NizH45lywkYcf4IWLEMqwOWS7VZ29jgwOETAkVUMDZvCETAssXo1PUPjBw7EQDw4nkkli2Zj9s3riMjMwNOLm4YPW4yihmbCBztj7tz8xr2btuEh/fD8TYuBlN8F8GlTj0AQFZWJjavWYHgyxfx+tUL6OjooWqN2ug9eBiMTYpLbefqv39j24Y1ePooAurq6qhY7TdM81siQI9+ztpVy7FuzUqpNktrG+zcdxQAkJ6eDv9F83D65DFkZmSgtrMbxk6cqlCv9QcmuuoY7G6N2jZG0FRVxov4NPj9FYH7bz7OZNvXxRItK5lBV0MFd14lYuHph3gRnyZZ7lBcB4PqWKNsCT2IxGJciIjD8vOPkZopEqJLPyUm+g0Cli3ClX8vIi0tDaVKWWLi9JkoW74iAOBtXCwCli1G8OV/kZSYiCrVf8OIsZNQ2tJK4Mh/3tpVK7A+l/18x74jUm1isRijhw7C5X8vwm+hPzzq1i/IMAtE00b1EPXq5Rftnbp0w6Qp0wWIKO+tX7sa586cwtMnj6GhoYnKVath2IjRsLYpI1knPT0dixfMxckTR5GRkQlnF1dMmDIdxgr42UbCkHn4X8WKFfH48WPY2NjkRzykAFJTU+HgWBat27bH6BFDc11etfpvaNi4KWZ6F+7r7Gzt7LF67QbJbRUVFQGjyX9hoXdwYO8u2Nk7StpSU1Mw4s/+sLN3xLLVOc9FYIA/xoz4E2s3bYeysmJMypqWmgobOwc0at4GsyaPklqWnpaGhw/C0bVnf5Sxd0TS+/dYtXQeZowfAf912yTrXTx/Gv5zfdBz4FBUqV4LouwsPH38sKC7IrcytnbwD1gnua2i8vFQsXThHPx78QJmz10MXV09LJw7CxPGDMeaDUFChPrTdDVUsLJLZdx4noCx+0IRn5KJUkZaSEzLkqzTrWZJtK9mAd8TDxCVkIa+rlZY2L4i/th4DRnZYhjrqGNxh4o4ez8Wi888ho66CobVLYNJTRww9fA9AXv34xLfJ2BI3z9QrUYtzF+6CoZGRnjx/Bn09PUB5CQVk8YMh6qqKvwW+kNHRxc7gzZj5JB+2LL7ILS0tAXuwc+zsbWDf8Baye1P9/MPdgZthlIhP1sftGMPRKJsye2HEREY1L83GjZqImBUeet6SDA6dumGChUqITs7G8v9F+PPQf2wZ/8RaGnn7MML5/nh4v8uYM6CpdDT08Vc35kYO3Io1m/eLnD0pChkTqpmzZqFMWPGYObMmfjtt9+go6MjtVz/vw/ioio5ORmDBw/Gvn37oKenhzFjxkgtf/fuHYYPH47Dhw8jPT0dHh4e8Pf3h729vWSdwMBA+Pj4IC4uDo0bN4a7uzt8fHwQHx9fwL3JnZt7Hbi51/nq8hatWgMAXr18UVAhCUZFRQUmJqZCh1EgUlKS4T15HCZMnYGNa1dL2m/fvIGoVy+xadte6OjqAgCmzvBDI08nhARfRq3aLkKFLJOazm6o6eyW6zIdXT34Llkt1TZk1ASM6P87ol9HobiZObKzsrB66Tz0/XMkGrdoK1nP0sY2X+PODyoqKjDOZb9OSkzE4QN7McN3PmrUcgIATPaeja7tW+Du7VuoWLlKQYf607rXKoXoxHT4/RUhaYt6ny61TqfqJbH5ynNcfPQWADD7+AMcHFwb7nbGOHM/Fi5ljJAlEmPRmUcQ/3efBacfYlPP6ihpqImXn1S0flVBm9ajeAkzTJo+S9JmUbKU5P/nkc8QeucWNu88ABtbOwDA6IlT0bqxJ07/dQwt23Qo8JjziupX9vMPHtwPx/atm7B+6060bORZcIEVsGLFikndXr92DUqXtkSNmrUEiijvLV+1Vur2jJl+aODpgvCwUFSvUROJiYk4uH8vZs+Zj1q1cz7bps/0Q4fWzXDn1k1UqlJVgKiFV8jPJ+S5Hz6F7OPjg+TkZDRr1gy3bt1Cq1atUKpUKRgZGcHIyAiGhoYcEghg7NixuHDhAg4ePIiTJ0/i/PnzuH79umR5r169EBISgkOHDuHSpUsQi8Vo1qwZMjMzAQD//PMPBg0ahOHDh+PmzZto2LAhZs+eLVR36DsiI5+hYV03NG9SHxPHj0ZU1CuhQ8o3C+bMgoubxxdJUkZGBpSUlKCmri5pU9fQgLKyMm7fuP75ZgqN5KQkKCkpQVdPDwDw8EE44mKioaSkBK/endG9dQNMHf2nQlaqnkdGomUjD7Rv2QjTJ4/F6//263vhocjKykLN2s6Sda1tysDMzBx3bt8UKNqf42ZrjPtvkuDToiwODa6FdX9URctKJSTLzQ00YKyrjpBn8ZK25IxshEclooJFzslDdVVlZIrEkoQKANKzcob9VS6pGCcYL/59Do7lKmDq+FFo2bAO+nTrgEP790iWZ2ZmAADUNT6+v5WVlaGurobbN28UeLx56XlkJFo18kSHlo3hPXmcZD8HcirX3pPGYfSEKd9MvAqbzMwMHDtyCK3bti/UFbqkpEQAgP5/k6+Fh4UiKysTtZ0+Ht9sbMrAzNwCtxXss42E88OVqhkzZmDQoEE4d+5cfsaj0JKSkrBu3Tps3boV9evnjLvetGkTSpXKOesXERGBQ4cO4Z9//oGLS84bNygoCKVLl8aBAwfQsWNHLFu2DE2bNpVUuBwcHPDvv//iyJEjuT8oCaZS5crwmeUHa2sbxMbGYNXKFejTozv2HDgMHR1docPLU6f+Oob798KwfsuuL5ZVrFwFmlpaWLF0IQZ7jYAYYqz0X4Ts7GzExsYIEG3+y0hPx4aApfBo0ATa/73Wr/+7JiFo/Wr0HzoaJcwssG/HZkwY2g+B2w9CT9/gW5v8ZVSoVBlTZsyGlVXOfr1uzUoM7vsHtu4+hLi4WKipqUFPTzphMDI2wdu4WIEi/jnmBppoXcUcu669xJarz1G2hC6G1y2DzGwxToRFw1gnJ4l4l5Ihdb+3KRkopqMGALgWmQAvDxt0rVESu6+/gqaaMga5WwOA5P6/uqiXL3Bw70506t4Df/Tuj3thd7F0gR/U1NTQtEVrWFnboISZOVYvX4qxk6ZBU0sbu4I2I/rNG8Qp8Pv7w35uaWWN2NgYrF8TgMF9e2Dr7oPQ0dHB0oVzUalKNdTxrCd0qAXq7JnTSExMRKs2bb+/soISiURYMM8XVapVh529AwAgLjYm57Pts9FWxsbGiItVrM+2vKRcePPqfPHDSZVYnHMuzsPDI9+CUXSPHj1CRkYGateuLWkrVqwYHB1zrj8JDw+Hqqqq1HJjY2M4OjoiPDwcAHD//n20bSv9YVarVq1vJlXp6elIT5cetpKtrA4NDQ25+0Rf5+b+8b3g4FgWFStVQbNGdXHyxHG0bd9RwMjy1pvXUVg83w/+K9fmuk8ZGRXD7LmLMd/PB7t3bIWysjIaNm4Gx7LlFeZ6KllkZWXCb9o4iCGG15jJknaRKKdC0aVHX7h55kzcMmqSD/5o1xj/O3sKzRRkmJSz68ehvXYOjqhQqTLaNm+AM6dOFKrPFGUl4N6bJKy5+AwAEBGdjDImOmhdxQwnwqJ/aBtP41Iw+0QEvDxtMMDdGiKRGHtvvEJccgZEYvH3N/ALEIlEKFu+Agb+OQIA4FC2HB4/isDBvbvQtEVrqKqqYfb8JZgzcxqa1XOFiooKfqvlBCcXd0jX6BSLs6u75P8P+3m75g1x9tQJGBoZ4VrwFWzcvucbWyicDuzbC1e3/7d333FNXX0YwJ+wNwKCoLIURFAQ1Kq4V51VFG2t2ooL6x64ah0IKrj3VlTcW9u6LSpa98KJKC4cqIiTDSHvH9S8vcWFIbmSPN/3w+dtzr1JnstNMCe/c8+pCxubEp/euYiaPCkUt+NvIWLV+k/vTFQABbqmSp1LwUVZeHg4QkJCBG2/jRmH0ePGixNIQ5mZmcHB0QkPEhLEjlKobsRew8sXyeja+f+dAqlUipgL57Bt83pEn4pBdd9a2PrHfrx6+RLaOtowNTVDy2/roGSp5iImL3w5OdkIHzsCz54kInzuUnmVCgAs/xki5OD0/2uodPX0YGtXCklPE1WetbCYmprBwcEJDx/cR7XqNZGdnY23b98IqlUvk58Xudn/klOzcD85TdB2/0Ua6rlaybcDgIWRHpJTs+X7WBrp4VZSqvz2XzeS8NeNJFgY6SIjWwqZDPihSik8fv31X08FAFbFreH4n+v+HJ3LIPrQX/Lbbu4VsHL9NqSkvEV2djYsLCzRK6AjyntUUHVcpTE1NYO9gyMePkjA7Vs38ejhAzSt5yvYZ/TwwajkUwULlq0SJ6SSPX78CKdPncCM2fPEjqI0U8JC8ffRI1i2ci1K2NrK262KW+f9bXvzRlCtSk5OhlXxovW3jcRToE5VuXLlPtmxevHihUKBirKyZctCV1cXp0+fhoODA4C8iSlu3ryJevXqwd3dHTk5OTh9+rR8+F9ycjLi4uLg4eEBAHBzc8PZs2cFj/vf2/81atQoBAUJZyuTahWNoSfqJC0tFQ8fPEDxVuo1/r5qNV+s3fy7oG3S+NFwdHLGT117CmY8LPbPdZXnzpzCyxcvUKee+gydedehevwwAZPnLoOZeTHBdlc3d+jq6eHhg3uoUMlHfp9nTx7DxtZOhMSFIy0tFQ8fJqBZy1Yo714BOjo6OHfmFBo0ylvs/f69u3jyJBGeXt7iBi2gK4/ewN7CUNBmb2GIJ2/zqv6JrzORnJKFKg7FEP9PJ8pITxvudqbYeSl/J/llWl7Hq0XFEsiS5gquxfqaeVbywYP79wRtD+7fh61d/tesiUne9YMPEu4jLvYaevbpr4qIKpGWlopHDx+gWcvWaPRtU7RqK6ws//xDGwwcOhK169YXJ6AK/L5jOywtrVBHDY9RJpNhavgEHD70F5ZGrEap0qUF2909KkBHRxdnTp9Eo2+bAgDu3b2DJ4mP4VXE/rYVJq5TVTAF6lSFhITA3LxoXBcgBhMTE/To0QPDhw+HlZUVbGxsMHr0aPkQKFdXV/j5+SEwMBBLliyBqakpfv31V5QqVQp+fnkz5g0YMAB169bFzJkz0apVKxw6dAh79+79aGdWX18/37CctGzlDctIS0sVVGMePXqIuBuxMDM3h51dSbx+/QpPEhPx7FneEJp7d+8CAKyKF1ermfJmTpuCuvUbwK5kSSQ9e4ZFC+ZBW1sLzVp8J3a0QmVsbIyyLq6CNgNDQ5iZF5O37/p9O5ycy6KYhQWuXo7BrOnh+LFzFzg6FZ2lF9LT0vD40f9f108TH+H2rRswNTWHZfHiCBszHPE3YzF+ylxIc3Pl1xCZmplDV1cXRsYmaOHXHmsjFsHapgRsbEti6/pIAEDtBk1EOaYvMXfWVNSu2wB2diWRlPQMyxfPh7aWNr5t1hImpqZo1aYd5s6YAjMzcxgbm2DG1Emo6OVdpGb+A4DN5x9jUUcv/FytNA7dfA53W1O08rLFtAP/n1hk84VHCKhhj4ev0pH4OgM9azkiOSULx+KT5fv4e9vh6uM3SM+WoqqjBfrWdcLiY/eQkil939N+dX7o9DP6dP8Zq1csRcNvmyH22hX8uWMrho/+//pEh//aj2LFLFDC1g63429h7ozJqFOvIarVqCVicsXMmzUNtevWh61dSTxPeoblixf88zpvAQsLy/dOTlHC1k4wM6I6yc3NxR87t6OVXxvo6BR4Yuiv3uRJodi3dxdmzlkAI2Nj+fW+JiamMDAwgKmpKfzatsPM6VNgZm4OExMTTA2fCK9K3ho78x8VXIHeOT/++CNsbGw+vaMGmzZtGlJSUtCqVSuYmppi6NCheP36tXz7ypUrMWjQIHz33XfIyspC3bp1sWfPHujq5l34XKtWLSxevBghISEYM2YMmjZtiiFDhmD+/PkfekqVu371KgK7B8hvz5g6GQDQyq8NQidNRvThQwge85t8+6/D86pov/Tph9798q9rVVQ9ffoEo0YE4dWrV7CwtISPTxWsXrc53/S0miDh/j0smj8Lb16/hl3JUuja4xf82Dng03f8ity6cQ2/DgyU3142bwYAoHHzVujcvTdO/X0EANC/WwfB/SbPXQavyt8AAHr0GwJtbR1MnzAGmZmZcPOoiPA5S/Nd/Pw1S3r6FMGjhuH161coZmGJSt6VsSxyAyws8l7Xg4b+ColEC6OGD0J2Vjaq+9bC8FFFbz26G09TMPqPWPSq7YQAXwckvs7AvMN3cPDG/ydfWH/2EQx1tTH8WxeY6OvgyqM3GLb9KrKk///Syt3WFN1rOsBQVxsJL9Ix/WA89scWnQkc3Ct4YtL02Vg6fw4ily+GXclSGDB0JJo0//+XQ8nPkzB/1lS8SE6GVXFrNGvZGgE9e4uYWnHPnj5F8Kjh8te5l3dlLI1cL3+da5pTJ08gMfEx2rRtJ3YUpdi6OW+tqV7duwjagyeEobWfPwBg6IhR0NLSwoigQcjKyoJvrdr4dfQ4lWf9mrBQVTASmezzrqbV1tZGYmIiO1UiCAwMxI0bN3Ds2LHPvo8yK1VfMwk08y9AelbR+Fa8sP13ZjZNYWGkmcN7/RafFDuCKLb1qv7pndSQtoZOPWakp36Vos8hzdXMzy0m+l/v63zCX+IsCTK2sYsoz6uoAs/+R8o3ffp0fPvttzA2NsbevXsRGRmJhQsXih2LiIiIiDSEhn6v8cU+u1P1brpgUr4zZ85g6tSpePv2LcqUKYO5c+eiZ8+eYsciIiIiIqL30Mwa81du8+b8C6wSEREREdHXiZ0qIiIiIiIS0NTr1L+UltgBiIiIiIiIijJWqoiIiIiISIATVRQMK1VEREREREQKYKeKiIiIiIiKvMmTJ0MikWDw4MHytoyMDPTr1w9WVlYwMTFBu3bt8PTpU8H9EhIS0LJlSxgZGcHGxgbDhw9HTk5OgZ6bnSoiIiIiIhLQkojz86XOnj2LJUuWwMvLS9A+ZMgQ/Pnnn9iyZQuio6Px+PFj+Pv7y7dLpVK0bNkSWVlZOHHiBCIjI7Fq1SqMGzeuYL+vL49OREREREQkrpSUFHTu3BnLli2DhYWFvP3169eIiIjAzJkz0bBhQ1SpUgUrV67EiRMncOrUKQDAgQMHcP36daxduxbe3t5o3rw5JkyYgAULFiArK+uzM7BTRUREREREAhKJRJSfzMxMvHnzRvCTmZn50az9+vVDy5Yt0bhxY0H7+fPnkZ2dLWgvX748HBwccPLkSQDAyZMn4enpiRIlSsj3adq0Kd68eYNr16599u+LnSoiIiIiIvoqhIeHw9zcXPATHh7+wf03btyICxcuvHefJ0+eQE9PD8WKFRO0lyhRAk+ePJHv8+8O1bvt77Z9Lk6pTkREREREAmJNqT5q1CgEBQUJ2vT19d+774MHDzBo0CAcPHgQBgYGqoj3QaxUERERERHRV0FfXx9mZmaCnw91qs6fP49nz56hcuXK0NHRgY6ODqKjozF37lzo6OigRIkSyMrKwqtXrwT3e/r0KWxtbQEAtra2+WYDfHf73T6fg50qIiIiIiIqcho1aoQrV64gJiZG/lO1alV07txZ/t+6urqIioqS3ycuLg4JCQnw9fUFAPj6+uLKlSt49uyZfJ+DBw/CzMwMHh4en52Fw/+IiIiIiEhAItLwv4IwNTVFxYoVBW3GxsawsrKSt/fo0QNBQUGwtLSEmZkZBgwYAF9fX9SoUQMA0KRJE3h4eODnn3/G1KlT8eTJE4wZMwb9+vX7YIXsfdipIiIiIiIitTRr1ixoaWmhXbt2yMzMRNOmTbFw4UL5dm1tbezatQt9+vSBr68vjI2NERAQgNDQ0AI9j0Qmk8kKOzyJLy1bM0+rBEXgaxUlSM+Sih1BFC/TPn/9CHViYaQndgRR+C0+KXYEUWzrVV3sCKLQFusqeZEZ6Wnm993SXM383GKi//W+zmcfuyvK8w6u4yzK8yqK11QREREREREpgJ0qIiIiIiIiBWhmjZmIiIiIiD5IQ0fgfjFWqoiIiIiIiBTAShUREREREQkUhSnVvyasVBERERERESmAlSoiIiIiIhLQ0tBlar4UK1VEREREREQKYKVKTWnqIriaOv5XT0czvx+xMzcQO4I4NPR1fnBQbbEjiMLim/5iRxDFy7PzxY5AKqSjraF/2EhtsFNFREREREQCmvpF9ZfSzK+3iYiIiIiICgkrVUREREREJMDFfwuGlSoiIiIiIiIFsFNFRERERESkAA7/IyIiIiIiAS3OVFEgrFQREREREREpgJUqIiIiIiISYKGqYFipIiIiIiIiUgArVUREREREJMBrqgqGlSoiIiIiIiIFsFNFRERERESkAA7/IyIiIiIiAY7+KxhWqoiIiIiIiBTAShUREREREQmw8lIw/H0REREREREpgJ0qIiIiIiIiBXD4HxERERERCUg4U0WBsFJFRERERESkAFaqiIiIiIhIgHWqgmGlioiIiIiISAGsVBERERERkYAWr6kqEFaqiIiIiIiIFMBOVSGRyWTo1asXLC0tIZFIEBMTI3YkIiIiIiJSAQ7/KyT79u3DqlWrcOTIEZQpUwbFixcXO5JKNW/SEImPH+Vr/+HHTvhtTLAIiZRv88b12LxpAx4/yjvusi6u+KVPX9SuU0/kZIVrxfIlOBx1EPfu3oG+vgG8vH0wcPBQODmXke+zfesm7NuzCzdiryM1NRVH/j4DUzMzEVMXjvPnzmL1qghcv34Nz5OSMHP2fDRo1BgAkJ2djYXz5uDvY9F4+OghTExMUL1GTQwcHAQbmxIiJy9cqakpWDhvLg5F/YWXL5LhVt4dI34djQqenmJHU6rz585i1YoIxF6/iqSkJMyauwAN/zn/RZWJkT6C+36H1g0rwdrCBJfiHmLY1K04fz0h375zR/+IwPa1MXzaVsxffwQA4GBniVG9mqH+N+VQwsoMiUmvsWHPWUxZvh/ZOVIVH03hiVi2BFEHD+Du3TvQNzCAt7cPBgcNE/ydU1fq+Dr/FE0+3wXBwX8Fw0pVIbl9+zbs7OxQs2ZN2NraQkdH2F/NysoSKZlqrNu4FX8d+Vv+s3jZSgDAt02aiZxMeWxK2GLQkGHYsGU71m/ehmrVa2BQ/36Ij78ldrRCdeHcWXz/YyesWrsJC5euQE5ODvr17on0tDT5PhnpGfCtVQfdev4iYtLCl56ejnLlymPU6HH5tmVkZCA29joCf+mLDZu2Ycasebh/7y4GD+grQlLlCh03FqdOnsDE8CnYvOMP+Nashd6B3fDs6VOxoylVenoa3NzcMEqNvhhaNK4TGtYoj+5jIlH1hzD8dfIGdi8egJLW5oL9WjfwQjVPJzx+9krQ7uZcAloSLfSfuBGV20/CiBnb0bN9bYQOaK3Coyh8586eQYeOnbFmw2YsWbYSOTk56B3YA2n/+junrtTxdf4pmny+SXkkMplMJnaIoq5r166IjIyU33Z0dISTkxMqVqwIHR0drF27Fp6enjh8+DCio6MxfPhwXLp0CZaWlggICMDEiRPlnbC3b9+id+/e2LlzJ8zMzDBixAj8/vvv8Pb2xuzZsz87U3p2YR9lwUydPAnHoo/gjz0HVLp4nNjXVNbxrYYhw4bDv933Kn3eHKnq3sYvX7xA4/o1sWzFGlSu+o1g27mzp/FLjwCVVaq0VHi+fTzLCypV73Pt6hX81PF77DlwCHZ2JZUXRoXHnZGRgdrVq2DW3AWoU6++vL3TD/6oVbsu+g0crLIsYl40XamCm2jf4Ft8079QHsdAXxdJf0/H90OWYt/f1+Ttx9eNwIHj1xGycBcAoKS1OY6uGYZWfRdgx7w+mL/usLxS9T5DujRC4Pd14NFqfKHkfOfl2fmF+ngF8eLFCzSo44sVkWtR5T9/59SZmK9zMYl5vg2+4jFj6y88FOV5O1UuLcrzKoqVqkIwZ84chIaGonTp0khMTMTZs2cBAJGRkdDT08Px48exePFiPHr0CC1atMA333yDS5cuYdGiRYiIiMDEiRPljxUUFITjx4/jjz/+wMGDB3Hs2DFcuHBBrEP7ItnZWdiz6w/4tW2nMatxS6VS7N2zG+npaahUyUfsOEqVkvIWAGBmbv6JPTXP27dvIZFIYGpa9Ic+viOV5kAqlUJPX1/Qrq9vgIsXzouUir6EjrYWdHS0kZEl/NYtIzMbNX3KAgAkEgkiJnbBrMgoxN558lmPa2ZiiBdv1Osb/pS3/DunSXi+qTB8xf3josPc3BympqbQ1taGra2tvN3V1RVTp06V3x49ejTs7e0xf/58SCQSlC9fHo8fP8bIkSMxbtw4pKamIjIyEuvXr0ejRo0AACtXrkTJkkr8xlsJDkX9hbdv36J1m7ZiR1G6Wzfj8HOnH5GVlQkjIyPMmrsAZV1cxI6lNLm5uZg+NQyVfCrDxbWc2HG+KpmZmZg7azqaNW8JExMTseMUGmNjE3hV8sayxQvhXKYMrKyKY9+e3bh8KQb2Dg5ix6MCSEnLxKlLdzAqsDni7j7F0+Q3+KFZVVT3csbtB0kAgKHdvkWONBcLNhz5rMcsY18cfX6sh1GzdigxuWrl5uZi6pQwePtUhiv/zqk9nm8qLOxUKVGVKlUEt2NjY+Hr6yuo3tSqVQspKSl4+PAhXr58iezsbFSrVk2+3dzcHG5ubh99nszMTGRmZgracrX0of+fb5ZVZef2bahVu67aXaz/Pk5Ozti8bSdSUt7i4IH9GPvbSESsWqu2HavJk0JxO/4WIlatFzvKVyU7Oxsjhg2GDMBvY8eLHafQTQyfivHjfkPThvWgra2N8u4eaNa8JWKvX/v0nemr0n3MaiwZ3xl3DkxCTo4UMTceYPO+c/Bxd4CPuz36dayPmp2mfNZjlbQ2xx/z+2H7XxexcscJJSdXnbCJIbh96xZWreHfOU3A8/1hmjLaqLBw+J8SGRsbq+R5wsPDYW5uLviZNiVcJc/9X48fP8LpUyfQtl17UZ5f1XT19ODg6AiPChUxaMhQlHMrj3VrV4sdSymmhIXi76NHsGT5apT4V0VW02VnZ2PksCFIfPwYi5ZGqFWV6h17BwdErFqLE2cuYO9fh7F24xbk5OSgVGl7saNRAd19+BxNes6BlW8QXJuPRZ2fp0NXRxt3Hz1HLZ+ysLE0wc09oXh7dg7enp0Dx5JWmBzkjxu7QwSPY2dtjn3LBuHU5TvoN2GDSEdT+MImhuJo9BEsWxnJv3MagOebChMrVSrk7u6Obdu2QSaTyXv/x48fh6mpKUqXLg0LCwvo6uri7NmzcPhnWM3r169x8+ZN1K1b94OPO2rUKAQFBQnacrXEqVL9vmM7LC2tUKdufVGeX2y5ubnIVrOZHmUyGaaGT8DhQ39hacRqlCpdNC8gVYZ3HaqEhPtYGhGJYsUsxI6kVIZGRjA0MsKb169x4sTfGBw0TOxI9IXSMrKQlpGFYqaGaFzTHaNn/46dUTE4dDpOsN+fC/th/e4zWP37KXlbyX86VBdjE9AreC3UYb4rmUyG8EkTcCjqICJWrUFpfmGg1ni+Pw8rLwXDTpUK9e3bF7Nnz8aAAQPQv39/xMXFITg4GEFBQdDS0oKpqSkCAgIwfPhwWFpawsbGBsHBwdDS0vpoCVZfP/9QPzFm/8vNzcUfO7ejlV+bfFPKq6M5s2agdp26sLWzQ1pqKvbs3oVzZ89g0dIIsaMVqsmTQrFv7y7MnLMARsbGeP4879oLExNTGBgYAACeP09C8vPneJCQt9ZN/K2bMDI2hq2dHczNi4kVXWFpaanyYwKAR48eIu5GLMzMzVG8uDWGBw3CjdjrmLNgMXJzpfLfjbm5OXR19cSKXehOHD8GmSxvuOuDhPuYNWManJ3LoHUbf7GjKVVaaioS/n3+Hz7EjdhYmJubw66IXev6TmNfd0gkwM17z1DW3hphQ9rg5t2nWP3HSeTk5OLF61TB/tk5Ujx9/ga37j8DkNeh2r98EBISX2DUzB2wtvh/ZfZp8luVHkthCpsQgr17dmH2vIUwNjLG86R//s6Z/v/vnLpSx9f5p2jy+SblUf9Pvl+RUqVKYc+ePRg+fDgqVaoES0tL9OjRA2PGjJHvM3PmTPTu3RvfffedfEr1Bw8eFIk3+amTJ5CY+Bht2rYTO4pKvHiRjDGjRiIp6RlMTE1RrpwbFi2NgG/NWmJHK1RbN+cN7enVvYugPXhCGFr75X2o3rZ5I5YuXiDf1rPbT/n2KYquX7uKwO4B8tszpk0GALRq3Qa9+/ZH9JFDAIAf27cR3G/ZikhU/aa6ynIqW8rbFMybPRNPnz6BuXkxNPr2W/QbOAS6urpiR1Oqa9euome3/7/up0/NG1bd2q8tJoRNFiuWQsxNDBA6oDVKlSiGF6/T8HtUDIIX/ImcnNzPun/DGuXh4mADFwcb3D4wSbDN0Kdwpn4Xw+ZNeX/nenT9WdAeOjEcfm2L7t+wz6GOr/NP0eTzXRC8pqpguE7VVy41NRWlSpXCjBkz0KNHj8++n9jrVIlFU9//qlyn6muiynWqvioaetxirlMlpsJap6qoEXOdKiJV+ZrXqdoc81iU5/3Bu2hWSL/iU6mZLl68iBs3bqBatWp4/fo1QkNDAQB+fn4iJyMiIiIiovdhp+orNH36dMTFxUFPTw9VqlTBsWPHULx4cbFjEREREZGG0MyxAV+OnaqvjI+PD86fPy92DCIiIiIi+kzsVBERERERkQAnqigYTkFPRERERESkAHaqiIiIiIiIFMDhf0REREREJMDKS8Hw90VERERERKQAVqqIiIiIiEiAE1UUDCtVRERERERECmCnioiIiIiISAEc/kdERERERAIc/FcwrFQREREREREpgJUqIiIiIiIS4DwVBcNKFRERERERkQJYqSIiIiIiIgEtXlVVIKxUERERERERKYCdKiIiIiIiIgVw+B8REREREQlwooqCYaWKiIiIiIhIAaxUERERERGRgIQTVRQIK1VEREREREQKYKeKiIiIiIhIARz+R0REREREApyoomBYqSIiIiIiIlIAK1VqSiaTiR1BJJr5tYqmnu9cDT3f2Tm5YkcQhb6uZn4PmHRqntgRRGHx/XKxI4ji5ZaeYkcQRZaG/l0z0Pl6/65paei/sV/q6z2TRERERERERQArVUREREREJMBrqgqGlSoiIiIiIiIFsFNFRERERESkAA7/IyIiIiIiAQ7/KxhWqoiIiIiIiBTAShUREREREQlIOKV6gbBSRUREREREpAB2qoiIiIiIiBTA4X9ERERERCSgxdF/BcJKFRERERERkQJYqSIiIiIiIgFOVFEwrFQREREREREpgJUqIiIiIiIS4OK/BcNKFRERERERkQLYqSIiIiIiIlIAh/8REREREZEAJ6ooGFaqiIiIiIiIFMBKFRERERERCXDx34JhpYqIiIiIiEgB7FQREREREREpgMP/iIiIiIhIgBNVFAwrVURERERERApgp+oj6tevj8GDB4sdg4iIiIhIpSQScX6KKnaq6IucP3cWg/r3xrcN68DHszwOR/31wX0nhgbDx7M81q2JVGFC1VuxfCm8K7ph6uRJYkcpVCsjlqJLp+9R17cKvq1fC0MH98e9e3fz7Xf50kX07tkVtatXRr2aVRHY7SdkZGSIkLhwXDh3FoP790bTRnVQxas8Dh8SvsaTk58jeMyvaNqoDmpW80b/3j2RcP+eOGGVaPWKZajh44FZ08IF7VcuxaBfr26o71sFDWt/g97dfy7S5/u/pFIpFsybg5ZNG6FGlUpo1exbLF28EDKZTOxohWrF8iX4uWN71KlRGY3r1UTQoH64d/eOYJ/MzExMnhSKhnWqo3b1yhg+ZACSk5+LlPjLaGlJMK5jFcQu7oAXG7vi2qIf8Ov33vLtOtoSTPz5G5yd7Y/nGwJwJ6Ijlg+sBzsLI8HjeJexwq7g5khc+zMerv4J8/vUhrFB0b2SYvPG9WjfthVqVquMmtUq4+dOHfD3sWixYxW6rZs3oGN7P9SvWRX1a1ZF959/xPG/j8q3b9+6Gb/06IL6Navim0ruePvmjYhpqahip0qFsrKyxI5QaNLT01GuXHmMGj3uo/sdijqIK5cvwdrGRkXJxHH1ymVs3bIR5cq5iR2l0F04dxbfd+iElWs2YsGSCOTkZKN/7x5IT0uT73P50kUM6NsLNXxrIXLdJkSu34IffuwMLa2i+ycmPT0d5dzKY+Rv+V/jMpkMQwf1w6OHDzFzzkKs37QddiVLok+v7oLfS1F3/doV7Ni2GS6uwtf1lUsxGNy/F6rXqIkVazdi5drNaP9jpyJ9vv9rVcQybN20Ab/+Nhbb/9iNgUFDEbliOTasWyN2tEJ14dxZfP9jJ6xauwkLl65ATk4O+vXuKXgdz5gajqPRhzF5+hwsW7kaSUnPMHzIABFTF9zQtl4IbOaOIctOwHvAVoxZfQZBbb3Qt2UFAICRvg68yxTH5M0X4Tt0J36c8hfKlTLHlt++lT+GnYURdo9vjttP3qDuiD/gF7oPHvYWWDagnliHpTCbErYYNGQYNmzZjvWbt6Fa9RoY1L8f4uNviR2tUNnY2KL/oCCs3rAVkeu3oGq1Ghg2qD9u/3OcGRnp8K1ZB117/CJy0q+LRKSfokp9/gVUktzcXIwYMQKWlpawtbXF+PHj5dsSEhLg5+cHExMTmJmZ4YcffsDTp0/l28ePHw9vb28sX74czs7OMDAwAABs3boVnp6eMDQ0hJWVFRo3bozU1FT5/ZYvXw53d3cYGBigfPnyWLhwocqO93PVrlMX/QYORsNG335wn2dPn2JK2ESETZ4GHZ2i+03ep6SlpeK3X4dj3PiJMDUzFztOoZu3aBla+bVFWRdXlHMrj/Gh4XiSmIjY2GvyfWZOm4wfO/6Erj0CUdbFFU5Ozvi2aXPo6emJmFwxterURd8B73+NJ9y/hyuXL2HUmGBUqOgJJ+cyGDVmPDIzMrBv724R0ha+tLRUBP82AqPGhsDUzEywbfaMyfjhx5/QpXsgypR1haOTMxo3Kdrn+78uxVxEvQaNUKdefZQsVRrfNmmGGjVr4dqVK2JHK1TzFy9Haz9/+fs7ZEI4niQ+Ruz1vPf327dv8fuObQgaNhLVqteAu0dFBE8Ix6WYi7hyKUbc8AVQo3wJ7DpzH/vOP0BCUgp2nLyHqJhHqOpqDQB4k5aN70L2YtuJu7j1+DXO3EzCkGUnUMXFGvbFjQEAzavaI1sqw+Clx3Hr8Wucj3+OAYv/Rtuazihja/axp/9q1W/QEHXq1oOjoxOcnJwxYNAQGBkZ4XIROrefo279BqhVpx4cHJ3g6OSMvgMGw8jICFcvXwIAdPopAF17BMLTq5LISakoY6fqEyIjI2FsbIzTp09j6tSpCA0NxcGDB5Gbmws/Pz+8ePEC0dHROHjwIO7cuYMOHToI7h8fH49t27Zh+/btiImJQWJiIjp27Iju3bsjNjYWR44cgb+/v3xIybp16zBu3DhMmjQJsbGxCAsLw9ixYxEZWbSGzuXm5mLMbyMQ0K0Hyrq4ih1HqcImhqJO3Xqo4VtT7CgqkZLyFgBg9k8H8kVyMq5euQwLSyt079IRTRrURq/uPyPmwnkxYyrVu6qznr6+vE1LSwt6enqIuagexz09fCJq1amHajWEr+sXL5Jx7cplWFhaIjCgE5o3qoM+PbqozXG/U8nbB2dOn8T9f4a6xt24gZgLF1CrTl2RkymX/P1tnvf+jr1+DTk52aj+r9eBs3MZ2NqVxOXLMWJE/CKnbjxFA6+ScCmZ1/nxdLKEr7stDlx48MH7mBnpITdXhlepee93fV1tZOdI8e8RoOlZUgBATfcSyguvIlKpFHv37EZ6ehoqVfIRO47SSKVSHNibd5yelbzFjkNqRH3LB4XEy8sLwcHBAABXV1fMnz8fUVFRAIArV67g7t27sLe3BwCsXr0aFSpUwNmzZ/HNN98AyPvwtXr1alhb530bduHCBeTk5MDf3x+Ojo4AAE9PT/nzBQcHY8aMGfD39wcAODs74/r161iyZAkCAgJUc9CFYOWKZdDW1kbHzj+LHUWp9u3ZjRux17Fu41axo6hEbm4uZkwNRyXvynBxLQcAePQo70PJssXzMShoBMq5lcfuXb+jT69u2LTtDzg4OomYWDmc/vlQOX/OTIweFwJDQ0OsWxOJp0+f4PnzJLHjKezgvj2Iu3EdK9Zuzrft8cOHAIDlSxZg4JDhcHUrj727/sCAX7pj3Zbf1eZ8d+vZCympqWjbqgW0tbUhlUrRb+BgtPiuldjRlCY3NxfTp4ahks//39/Jz5Ogq6ubr1ppZWWF5OdF57qq6dsvwcxID5fmfQ9prgzaWhIErzuHjUdvv3d/fV1tTOxSDZuP3cbb9GwAwJErjzGlWw0MaeOJ+buuwVhfBxN/zvu33vY/114VJbduxuHnTj8iKysTRkZGmDV3Acq6uIgdq9DF37qJ7j93RFZWJgyNjDBt1jyUKat+x1mYtIryrBEiYKfqE7y8vAS37ezs8OzZM8TGxsLe3l7eoQIADw8PFCtWDLGxsfJOlaOjo7xDBQCVKlVCo0aN4OnpiaZNm6JJkyZo3749LCwskJqaitu3b6NHjx4IDAyU3ycnJwfm5h8eVpaZmYnMzExBm1SiB/1/fYuuStevXcWGtWuwfvM2SNT4DfkkMRFTJ0/C4mUrRPtdq9qUsFDcvn0Ly1etk7fl5uZ9bevfvgNat8n7MqC8uwfOnj6FP3ZuR/9BQaJkVSZdXV1MnzUXocFj0KB2dWhra6NadV/Uql23yE9k8PRJImZOC8fcRcvf+7rOzc0FALRt9wO+88s7327lPXD2zCns+n07+g5Uj/N9YN9e7N31J8KmTEdZFxfE3biB6VPCYG1jg9Z+bcWOpxSTJ4XidvwtRKxaL3aUQte+Vhn8WLcsus46jOsJL+HlbIVpPWog8WUa1h0WXj+koy3B2mENIQEwcMlxeXvsg1cInBuNyd2qI/SnbyDNlWHh7mt48jKtSL/vnZycsXnbTqSkvMXBA/sx9reRiFi1Vu06Vo5OTli3eTtSUlIQdXA/xo8dhSURq9mxokLDTtUn6OrqCm5LJBL5h4rPYWxsLLitra2NgwcP4sSJEzhw4ADmzZuH0aNH4/Tp0zAyyvuma9myZahevXq++31IeHg4QkJCBG2/jRmH0WPHf3bOwnTxwnm8eJGMFk0aytukUilmTp+CdWsjsWf/IVFyFbbr16/hxYtkdPzBX94mlUpx4fxZbNqwDmcuXPnoeStqpoRNwN9Ho7F0xRqUKGErby9ePO9LA+cyZQX7OzuXwZMniSrNqEruHhWxYctOvH37FjnZ2bCwtESXTj/Ao0JFsaMp5EbsNbx8kYyundrL26RSKWIunMPWTeuxaUfeNWNO/znfTmp2vmfPmIZuPQPRrEVLAIBrOTckJj7GyuVL1bJTNSUsFH8fPYJlK9eihO3/399Wxa2RnZ2Nt2/eCKpVycnJsCpeXIyoXyQsoBqmb7+ELX/nzWx4LeElHKxNMNy/kqBTpaMtwbphjeBgbYLmwXvkVap3Nh27jU3HbsPG3BCpmdmQyYCBrSri7tO3Kj2ewqSrpweHf0bOeFSoiGtXr2Dd2tUYNz5U5GSFS1dXD/YOecfp7lEB169dwcZ1a/DbuJBP3FNzqe/X4srBTtUXcnd3x4MHD/DgwQN5ter69et49eoVPDw8PnpfiUSCWrVqoVatWhg3bhwcHR2xY8cOBAUFoWTJkrhz5w46d+782VlGjRqFoCDht8NSiXgXjLds1RrVa/gK2vr27omW3/nBr436fBipXqMGtu74U9A2bswoODuXQbcegWrToZLJZJgaPhFHDv2FJRGRKFW6tGB7yVKlYG1tI7/25J379++jVu06qowqClNTUwB5k1fEXr+KPv0HipxIMVWr+WLdlt8FbRODR8PR2Rk/d+2JUqXtYW1tg4R79wT7PLh/D7611Od8Z2SkQyIRXnaspaVVoC/VioK89/cEHD70F5ZGrM73/nb3qAAdHV2cOX0Sjb5tCgC4d/cOniQ+hpeXtwiJv4yhvg7+e+qkuTJoaf3/Y+O7DlXZkmZoNnYPXrzNxIc8e50OAOjSqBwysqWIinmklNxiyM3NRbYazVb8IbJcGbKy1f84SXXYqfpCjRs3hqenJzp37ozZs2cjJycHffv2Rb169VC1atUP3u/06dOIiopCkyZNYGNjg9OnTyMpKQnu7u4AgJCQEAwcOBDm5uZo1qwZMjMzce7cObx8+TJfx+kdfX39fMN00rKUOxQhLS0VDxIS5LcfPXqIuBuxMDM3h51dSRQrZiHYX0dHB8WLF4eTcxml5lIlY2MT+XUH7xgaGsG8WLF87UXZlLBQ7Nu7GzNmz4eRsbH8miETE1MYGBhAIpHg567dsWTRfLi6lYebW3ns+mMn7t+7g6kzZosbXgH/fY0//s9r/OCBfbCwsICtXUnE37qJ6VMmoX6DRvCtWVvE1IozNjbON7mMgaEhzM2Lyds7B3THssXz4VrODa5u5bHnz99x/95dhE2bLUJi5ahbvwEili2GnZ0dyrq44EZsLNauXoU2bduJHa1QTZ4Uin17d2HmnAXvfX+bmprCr207zJw+BWbm5jAxMcHU8InwquRdpC7y33M2ASPbe+PB8xRcT3gJ7zJWGNi6IlZH3QSQ16FaP6IxfMpYwX/SAWhrSVCimCEA4EVKJrJz8npkvZt74FTcU6RkZKNRpVIIC6iOsWvO4nVa0fxwPmfWDNSuUxe2dnZIS03Fnt27cO7sGSxaGiF2tEI1f85M1KxdB7a2JZGWlop9e3bh/LkzmLdoGQDg+fMkJD9/jgcP7gMA4uNvwsjIGLZ2djA3LyZicipK2Kn6QhKJBL///jsGDBiAunXrQktLC82aNcO8efM+ej8zMzMcPXoUs2fPxps3b+Do6IgZM2agefPmAICePXvCyMgI06ZNw/Dhw2FsbAxPT08MHjxYBUf1+a5fu4rA7v+fOGPGtMkAgFat2yB00mSxYpESbN28EQDwSw/hRCnBoWFo9c8wqE4/BSArMwuzpk3G69evUc7NDQsWR6C0vYPK8xaW69euCo555j+v8e9at0HIxMl4nvQMs6ZNRnJyMopbW6NlKz8E/tJHrLgq9WPnLsjKzMTsGVPw5vVruJZzw5xFy4v0+f6vkb+NwcJ5cxE2MRQvXyTD2toG7b/vgF59+oodrVBt3bwBANCrexdBe/CEMLT+55q5oSNGQUtLCyOCBiErKwu+tWrj10+sUfi1CVp2EsGdqmBOr5qwNjdE4ss0RBy4gbDNFwEAJS2N0apa3tCwM7P8BfdtMmY3jl3LG9pa1dUaYzpWhomBLuIevkL/RX9jQ3S8ag+mEL14kYwxo0YiKekZTExNUa6cGxYtjYBvzVpiRytUL18kY/yYX/E8KQkmJqZwKVcO8xYtQ3XfvOPcvmUTli1eIN+/V7e8SbbG/evfOY3E8X8FIpEV5asr6YOUXan6WqnzxBgfkyNVryFJn0tTz3e2hp5vfV3NXAVEzUYcfjbrH9WrWvK5Xm7pKXYEUWTlaOYL3czg6/27dur2K1Get0bZYqI8r6JYqSIiIiIiIgEJS1UF8vV2j4mIiIiIiIoAVqqIiIiIiEhAQ0fYfzFWqoiIiIiIiBTAThUREREREZECOPyPiIiIiIgEOPqvYFipIiIiIiIiUgArVUREREREJMRSVYGwUkVERERERKQAdqqIiIiIiIgUwOF/REREREQkIOH4vwJhpYqIiIiIiEgBrFQREREREZGAhIWqAmGlioiIiIiISAHsVBERERERkYBEpJ+CCA8PxzfffANTU1PY2NigTZs2iIuLE+yTkZGBfv36wcrKCiYmJmjXrh2ePn0q2CchIQEtW7aEkZERbGxsMHz4cOTk5BQoCztVRERERERU5ERHR6Nfv344deoUDh48iOzsbDRp0gSpqanyfYYMGYI///wTW7ZsQXR0NB4/fgx/f3/5dqlUipYtWyIrKwsnTpxAZGQkVq1ahXHjxhUoi0Qmk8kK7cjoq5GWpZmnVaKhA4BzpLliRxCFpp7vbA093/q6mvk9YK5mnm5Y/xghdgRRvNzSU+wIosjK0cwXupnB1/t37cK9N6I8b2Unsy++b1JSEmxsbBAdHY26devi9evXsLa2xvr169G+fXsAwI0bN+Du7o6TJ0+iRo0a2Lt3L7777js8fvwYJUqUAAAsXrwYI0eORFJSEvT09D7rub/eM0lEREREROIoCuP//uP169cAAEtLSwDA+fPnkZ2djcaNG8v3KV++PBwcHHDy5EkAwMmTJ+Hp6SnvUAFA06ZN8ebNG1y7du2zn5uz/xERERER0VchMzMTmZmZgjZ9fX3o6+t/9H65ubkYPHgwatWqhYoVKwIAnjx5Aj09PRQrVkywb4kSJfDkyRP5Pv/uUL3b/m7b52KlioiIiIiIBCQi/S88PBzm5uaCn/Dw8E/m7devH65evYqNGzeq4LeTHytVRERERET0VRg1ahSCgoIEbZ+qUvXv3x+7du3C0aNHUbp0aXm7ra0tsrKy8OrVK0G16unTp7C1tZXvc+bMGcHjvZsd8N0+n4OVKiIiIiIi+iro6+vDzMxM8POhTpVMJkP//v2xY8cOHDp0CM7OzoLtVapUga6uLqKiouRtcXFxSEhIgK+vLwDA19cXV65cwbNnz+T7HDx4EGZmZvDw8Pjs3KxUERERERGRQFGYYLdfv35Yv349fv/9d5iamsqvgTI3N4ehoSHMzc3Ro0cPBAUFwdLSEmZmZhgwYAB8fX1Ro0YNAECTJk3g4eGBn3/+GVOnTsWTJ08wZswY9OvX75MVsn9jp4qIiIiIiIqcRYsWAQDq168vaF+5ciW6du0KAJg1axa0tLTQrl07ZGZmomnTpli4cKF8X21tbezatQt9+vSBr68vjI2NERAQgNDQ0AJl4TpVaorrVGkWrlOlWbhOlWbhOlWahetUaZaveZ2qSwlvRXneSg6mojyvor7eM0lERERERFQEcPifmsrS0G+ytTW0cqGjrZnfj2jo6YaOtrbYEUiFJJr59tbYio3FtxPEjiCKJ3tGix2BSCHsVBERERERkZCGfnH5pTT0+y8iIiIiIqLCwUoVEREREREJSFiqKhBWqoiIiIiIiBTAShUREREREQlo6mRQX4qVKiIiIiIiIgWwU0VERERERKQADv8jIiIiIiIBjv4rGFaqiIiIiIiIFMBKFRERERERCbFUVSCsVBERERERESmAnSoiIiIiIiIFcPgfEREREREJSDj+r0BYqSIiIiIiIlIAK1VERERERCQgYaGqQFipIiIiIiIiUgArVUREREREJMBCVcGwUkVERERERKQAdqqIiIiIiIgUwOF/REREREQkxPF/BcJKFRERERERkQJYqSIiIiIiIgEu/lswrFQREREREREpgJ0qJeratSvatGnz0X2cnJwwe/ZsleQhIiIiIqLCx+F/Ijt79iyMjY3FjlEg2zZvxPYtG/H48SMAQJmyLujRqw9q1q6Lx48eoW3Lb997v7CpM9GoSTNVRi1UKyOW4nDUQdy7ewf6+gbw8vbBgMFD4eTkDAB4/OgRWrdo/N77Tp42C42L8LH/26IF87Bk0XxBm5OzM3b+uU+kRKoRsWwJog4ewN27d6BvYABvbx8MDhoGJ+cyYkdTKk097nc2rl+HyJUReP48CeXcyuPX38bC08tL7FhKo6nv73fU7XxraUkwJqAeOn5bESUsTZD4/C3W7L+MyWuOyfcxNtDFxF6N0Kq2GyzNDHEv8RUWbj+D5X9eAAA4lDBH3MaB7338zuO3Ynt0rEqORRFbN2/A9i0bkfjP5xbnsi7o2asvatauCwDo3aMLLpw/K7hP2/YdMGrMeFVH/apIOPqvQNipEpm1tbXYEQrMpkQJ9B04BPYOjgCA3X/sxPDB/bFm4zY4OpfBnr+iBfvv2LYF6yJXwLd2HTHiFpoL587i+w6d4FGhIqRSKRbMm4X+vXtgy/ZdMDQyQglbW+yLOiq4z46tm7EmcgVqFvFj/6+yLq5Ysnyl/La2traIaVTj3Nkz6NCxMyp4ekKaI8W8OTPRO7AHtv+xG0ZGRmLHUxpNPW4A2Ld3D6ZPDceY4BB4elbCujWR6PNLD/y+ax+srKzEjqc0mvj+BtTzfA/tWBOBflUQOPl3XL+bhCpuJbFkZCu8Sc3Awu15nYgp/Zqgvo8Tuk3aiftPXqHxN2UwZ3ALJCanYPeJm3iY9AZO/jMFj9u9VWUM6eCL/afjxTisAitRwhb9BgbB3sERMsiw+4/fMeyfzy1lXVwBAG38v0evvgPk9zEwMBQrLhVRHP5XCLZu3QpPT08YGhrCysoKjRs3Rmpqqnz79OnTYWdnBysrK/Tr1w/Z2dnybf8d/ieRSLBo0SI0b94choaGKFOmDLZu3arKw/mkOvUaoFadenBwdIKDoxP6DBgMIyMjXL1yGdra2rAqbi34iT70Fxo1aQYjo6JVkfuveYuWoZVfW5R1cUU5t/IYHxqOJ4mJiI29BiDvg0fx4taCn8OHotBYDY79v/57rBYWlmJHUrpFSyPg19YfLi6ucCtfHqGTJiMx8TFir18TO5pSaepxA8CayJXwb/8D2rRth7IuLhgTHAIDAwPs3L5N7GhKpYnvb0A9z3eNCqWx63gc9p2KR8LT19hxNBZR5+6gavlSgn3W7r+MY5fuI+Hpa6zYdRGXbz9F1fIlAQC5uTI8fZkq+Glduzy2HbmO1IzsDz31V+Xfn1scHZ3RV/655ZJ8HwMDA8Hr3sTERMTEXweJSD9FFTtVCkpMTETHjh3RvXt3xMbG4siRI/D394dMJgMAHD58GLdv38bhw4cRGRmJVatWYdWqVR99zLFjx6Jdu3a4dOkSOnfujB9//BGxsV9neV0qleLAvj1IT09HRa9K+bbHXr+Gm3E30LpNOxHSKVdKylsAgJmZ+Xu35x17LPzatldlLJVISLiPbxvURstmjTBq5FAkJj4WO5LKpbz95/ybv//8qytNOe7srCzEXr+GGr415W1aWlqoUaMmLl+6KGIy5dPE97e6nu9T1x6iQWVnuJTO6xh7li0B34r2OHAmXrDPdzXLoWRxUwBAXW9HuJa2xF/n7rz3MX3K2cLb1RaRe2KUnl8Z8j637EZ6eho8vbzl7fv27sK39X3xY7tWWDB3JjLS08ULSUUSh/8pKDExETk5OfD394ejY95wOE9PT/l2CwsLzJ8/H9ra2ihfvjxatmyJqKgoBAYGfvAxv//+e/Ts2RMAMGHCBBw8eBDz5s3DwoULlXswBRB/6yZ6dumIrKwsGBoaYcrMuShT1iXffn/u2AanMmXg5e0jQkrlyc3NxYyp4ajkXRkuruXeu8/vO7bCuUxZVFKzY/f08kLoxHA4OTnj+fMkLF64AN27dMbWnX/C2FgzvtnLzc3F1Clh8PapDNcPnH91pEnH/fLVS0il0nzDvqysrHD37vs/bKoDTX1/q+v5nr7+OMyM9HEpsi+kubnQ1tJCcMRhbPzrqnyfoLn7sGBoS9zeMhjZOVLk5srQd8ZuHL+c8N7HDGjhg9h7STh17aGqDqNQxN+6iR5dOiIrKxOGhkaYOnOe/HNL0+bfwbZkSVhb2yD+Zhzmz5mB+/fuYurMeSKnFllRLhuJgJ0qBVWqVAmNGjWCp6cnmjZtiiZNmqB9+/awsLAAAFSoUEEwHt3Ozg5Xrlz56GP6+vrmux0TE/PB/TMzM5GZmSlsy9WBvr5+AY/m8zk6OWHNpu1ISUnBob/2I3Tcb1i0PFLQscrIyMD+vbvRvVdvpeUQy5SwUNy+fQvLV6177/aMjAzs27sbPQP7qDiZ8tWuU0/+3+XcyqOiZyW0aNIAB/btRdt234uYTHXCJobg9q1bWLVmvdhRVEpTj1uT8P2tXtrXr4AfG1dE14k7cP1eErxcSmBavyZITH6LdfsvAwD6tv0G1dxLo91vG5Hw9DVqezlg9qBmSHz+Focv3BU8noGeDjo0qojJq4+97+m+ao5OTlj7r88tIeNGYfHy1ShT1gVt2/8g38/FtRysrK3Rr1c3PHyQgNL2DiKmpqKEw/8UpK2tjYMHD2Lv3r3w8PDAvHnz4Obmhrt38/4Q6erqCvaXSCTIzc0t1Azh4eEwNzcX/MyaNrlQn+O/dHX1YO/gCHePCug3MAiu5dywaf0awT6H/jqAjIx0tPjOT6lZVG1K2AT8fTQai5dFokQJ2/fuE3VwPzLSM9CylXod+/uYmZnBwdEJDxLe/62mugmbGIqj0UewbGUkSti+//yrI007botiFtDW1kZycrKgPTk5GcWLFxcpleppyvtbXc93WO9GmL7hBLYcvoZrd59hw8ErmLf1NIZ3qgUgr5MU0rMhRi46gD0nb+HqnWdYvPMcth6+jsEdauR7vLb13GGkr4t1By6r+lAU9jmfW96p6Jk34+ODB+r9uqfCxU5VIZBIJKhVqxZCQkJw8eJF6OnpYceOHV/8eKdOncp3293d/YP7jxo1Cq9fvxb8DBn+6xc//5fIzZUhO0t4weqfO7ahTv2GsLBUj4ucZTIZpoRNwJFDf2HRspUoVbr0B/f9fec21K3fQG2O/WPS0lLx8MEDFC+CM1kWhEwmQ9jEUByKOohlKyJRurS92JFUQlOPW1dPD+4eFXD61El5W25uLk6fPgmvSuo1pPdjNOX9ra7n21BfF7m5MkGbNFcGrX/mytbV0YKervZ79smV7/NvXVt4Y/eJm3j+Ok15oVUkN1eGrKys9267eeMGAKB4cfV+3X+KRKT/FVUc/qeg06dPIyoqCk2aNIGNjQ1Onz6NpKQkuLu74/LlL/smZ8uWLahatSpq166NdevW4cyZM4iIiPjg/vr6+vmG+uWmS7/ouT/HgrkzUbNWXZSwtUNaWir2792FC+fOYM7CZfJ9HiTcx8UL5zBr/mKl5VC1KWGh2Ld3N2bMng8jY2M8f54EADAxMYWBgYF8vwcJ93Hx/DnMWbBErKhKNXPaFNSt3wB2JUsi6dkzLFowD9raWmjW4juxoylV2IQQ7N2zC7PnLYSxkTGeJ/1z/k2F51/daOpxA8DPAd0w9reRqFChIip6emHtmkikp6ejTVt/saMpjaa+vwH1PN97Tt7CyJ9q48Gz17h+NwnerrYY+H11rN6bN+vd27QsHI25h7DejZGemYOEp69Rp5IDOjfxwsiFBwWPVaakBWp7OaLNrxvEOBSFLJg7E7616sDWtqTgc8vchcvw8EEC9u/dhZq168HcvBjib8Vh1vTJ8KlSFa7l3MSOTkUIO1UKMjMzw9GjRzF79my8efMGjo6OmDFjBpo3b45NmzZ90WOGhIRg48aN6Nu3L+zs7LBhwwZ4eHgUcvIv9/LFC4SM+RXPnyfBxMQULuXKYc7CZaj+r1mT/ty5HTYlSqC6by0RkxaurZs3AgB+6REgaA8ODUMrv7by23/s3A6bEraooUbH/m9Pnz7BqBFBePXqFSwsLeHjUwWr122GpZpX5TZvyvsg0aPrz4L20Inh8CvCH7o+RVOPGwCaNW+Bly9eYOH8uXj+PAlu5d2xcMlyWBXh4WCfoqnvb0A9z3fQ3H0I7l4fcwY1h7WFMRKfv0XEnxcQtvr/ayp2Cd2O0MCGWDW6DSzMDJHw9DXGRxzGsj/OCx4roIU3HiW9wV/nbqv6MBT24kVyvs8tcxcuQ3XfWnj6JBFnTp/EhnWrkZGejhIlbNGg0bforobXRBcUF/8tGIns3dzf9FWQSCTYsWMH2rRpo9DjvFJipeprpq2hfwF0tDVzJK+Gnm7SMJr6r7Smvr8tvp0gdgRRPNkzWuwIojA3/Hr//Y5/Js608i42RXPh5a/3TBIRERERERUBHP5HREREREQCGlos/mLsVH1lOBqTiIiIiKhoYaeKiIiIiIiEWKoqEF5TRUREREREpABWqoiIiIiISKAoL8QrBlaqiIiIiIiIFMBOFRERERERkQI4/I+IiIiIiAQ0dQHuL8VKFRERERERkQJYqSIiIiIiIgEWqgqGlSoiIiIiIiIFsFNFRERERESkAA7/IyIiIiIiIY7/KxBWqoiIiIiIiBTAShUREREREQlIWKoqEFaqiIiIiIiIFMBKFRERERERCXDx34JhpYqIiIiIiEgB7FQREREREREpgMP/iIiIiIhIgKP/CoaVKiIiIiIiIgWwUkVERERERAKcqKJgWKkiIiIiIiJSADtVRERERERECuDwPyIiIiIi+g+O/ysIiUwmk4kdggpfWpZmntb0bKnYEURhrM/vR4iI1EGuhn4ss6rzq9gRRJF+aorYET7o4cssUZ63tIWeKM+rKH4SIyIiIiIiAU5UUTC8poqIiIiIiEgBrFQREREREZEAC1UFw0oVERERERGRAtipIiIiIiIiUgCH/xERERERkQAnqigYVqqIiIiIiIgUwEoVEREREREJSDhVRYGwUkVERERERKQAdqqIiIiIiIgUwOF/REREREQkxNF/BcJKFRERERERkQJYqSIiIiIiIgEWqgqGlSoiIiIiIiIFsFNFRERERESkAA7/IyIiIiIiAQnH/xUIK1VEREREREQKYKWKiIiIiIgEJJyqokBYqSIiIiIiIlIAK1VERERERCTEQlWBsFJFRERERESkAHaqiIiIiIiIFMDhf0REREREJMDRfwXDStVX5t69e5BIJIiJiRE7ChERERERfQZWqj5T/fr14e3tjdmzZ4sd5atw/txZrF4VgevXr+F5UhJmzp6PBo0aAwCys7OxcN4c/H0sGg8fPYSJiQmq16iJgYODYGNTQuTkX2754gVYsXShoM3ByRkbt+8CAPQL7IqL588Ktrdp9wNGjA5WWUZV2LxxPTZv2oDHjx4BAMq6uOKXPn1Ru049kZMpV8SyJYg6eAB3796BvoEBvL19MDhoGJycy4gdTenOnzuLVSsiEHv9KpKSkjBr7gI0/Of9ru42rl+HyJUReP48CeXcyuPX38bC08tL7FhKpannWxOPWyqVYvHC+diz6w8kP38Oa2sbtGrTFoG/9IGkCK/8amKkh+BeTdG6XgVYW5jg0s3HGDbrD5yPfQgA8KtfAT3b1oBP+VKwMjdG9Z9n4/KtRPn9HewsELfj1/c+duff1mL7oSsqOQ6xFeGXgCjYqSokMpkMUqkUOjqa8StNT09HuXLl4de2HYYOHiDYlpGRgdjY6wj8pS/KubnhzZs3mDYlDIMH9MX6TdtESlw4nMu6YO6i5fLb2trC8926bXsE9ukvv21gYKiybKpiU8IWg4YMg4OjI2QyGf78fScG9e+HTdt2wMXFVex4SnPu7Bl06NgZFTw9Ic2RYt6cmegd2APb/9gNIyMjseMpVXp6Gtzc3NDGvx2CBvX/9B3UxL69ezB9ajjGBIfA07MS1q2JRJ9feuD3XftgZWUldjyl0dTzrYnHvSpiGbZu2oDQSZNR1sUF165dxfgxv8HExASdfuoidrwvtui39vAoY4vuIZuQ+PwNOjbzwe55gajccQYeJ72BkYEeTly6h21Rl7Hot/b57v/w6Ss4tZggaOvepjqGdK6H/SfjVHUYVMRoRg9AQV27dkV0dDSio6MxZ84cAMDKlSvRrVs37NmzB2PGjMGVK1dw4MABrFq1Cq9evcLOnTvl9x88eDBiYmJw5MgRAEBubi6mT5+OpUuX4sGDByhRogR++eUXjB49Ot9zS6VSBAYG4sSJEzhw4AAcHBxUccifVLtOXdSuU/e920xNTbF42QpB26+/jcVPHb9HYuJj2NmVVEVEpdDR1oZVcesPbjcwMPjodnVQv0FDwe0Bg4Zg88YNuHwpRq07VYuWRghuh06ajAZ1fBF7/RqqVP1GpFSqUbtOPbWvRL7PmsiV8G//A9q0bQcAGBMcgqNHj2Dn9m3oEdhL5HTKo6nnWxOP+1LMRdRr0Ah16tUHAJQsVRr79uzGtStFtxJjoK+DNvUr4vsRq3E85i4AYNLyv9CitjsC/WsgZMkBbNh3EUBeRep9cnNlePoiRdDWul4FbIu6jNT0LOUeABVZvKbqM8yZMwe+vr4IDAxEYmIiEhMTYW9vDwD49ddfMXnyZMTGxsLrM4eEjBo1CpMnT8bYsWNx/fp1rF+/HiVK5B8Wl5mZie+//x4xMTE4duzYV9Oh+hJv376FRCKBqamZ2FEU8iAhAa2b1Ef7Vk0xfvQIPEl8LNh+YO9uNG9YC52/98OiebOQkZ4uUlLVkEql2LtnN9LT01Cpko/YcVQq5e1bAICZubnISUgZsrOyEHv9Gmr41pS3aWlpoUaNmrh86aKIyYgKTyVvH5w5fRL37+V1PuJu3EDMhQuo9YEvTYsCHW0t6OhoIyMrW9CekZmNmpWcvugxfdxKwdutFCL/PPvpndWIRKT/FVWsVH0Gc3Nz6OnpwcjICLa2tgCAGzduAABCQ0Px7bfffvZjvX37FnPmzMH8+fMREBAAAChbtixq164t2C8lJQUtW7ZEZmYmDh8+DPOPfHDLzMxEZmamoE0q0YO+vv5n51KmzMxMzJ01Hc2at4SJiYnYcb5YBU8vjAmZBAdHJzx/noQVSxehT48uWLvldxgbG+PbZi1ga1cS1tY2iL91EwvnzkTCvXsInzFH7OiF7tbNOPzc6UdkZWXCyMgIs+YuQFkXF7FjqUxubi6mTgmDt09luLqWEzsOKcHLVy8hlUrzDfOzsrLC3bt3REpFVLi69eyFlNRUtG3VAtra2pBKpeg3cDBafNdK7GhfLCUtC6cu38eo7o0Qd+8Znr5IwQ9NvFG9oiNuP0z+oscMaP0NYu8+xakr9ws5LakTdqoUVLVq1QLtHxsbi8zMTDRq1Oij+3Xs2BGlS5fGoUOHYGj48etywsPDERISImj7bcw4jB47vkDZlCE7Oxsjhg2GDMBvX0EeRfjWqiP/b5dybqjg6QX/lt/i0MF9aNWmHdq0+0G+vaxrOVgVL46BvXvg4YMElLYvulXG93FycsbmbTuRkvIWBw/sx9jfRiJi1VqN6ViFTQzB7Vu3sGrNerGjEBF9sQP79mLvrj8RNmU6yrq4IO7GDUyfEgZrGxu09msrdrwv1j1kI5aM/h53do1BTo4UMXGPsflgDHzKly7wYxno66BDE29MXhmlhKRfN05UUTDsVCnI2NhYcFtLSwsymUzQlp39/xL0pzpI77Ro0QJr167FyZMn0bBhw4/uO2rUKAQFBQnapBK9z3oeZcrOzsbIYUOQ+PgxlkasKtJVqvcxNTWDvYMjHj5IeO/2Cp55w0HVsVOlq6cHB0dHAIBHhYq4dvUK1q1djXHjQ0VOpnxhE0NxNPoIVkSuRYl/KtekfiyKWUBbWxvJycJvtpOTk1G8eHGRUhEVrtkzpqFbz0A0a9ESAOBazg2JiY+xcvnSIt2puvvoBZr0XQIjA12YGRvgSfJbrJnYCXcfFbxS1baBJ4wMdLFuzwUlJCV1wmuqPpOenh6kUukn97O2tkZiYqKg7d9rTrm6usLQ0BBRUR//xqNPnz6YPHkyWrdujejo6I/uq6+vDzMzM8GP2EP/3nWoEhLuY/GylShW7P0XgxZlaWmpePTwwQcnprgVlzdEtLiaT1wB5A2Hy85S74t3ZTIZwiaG4lDUQSxbEYnSpe3FjkRKpKunB3ePCjh96qS8LTc3F6dPn4SXhl0/SOorIyMdEonwo6CWlhZyc3NFSlS40jKy8ST5LYqZGqJx9XLYdfR6gR+ja+tvsPtYLJ6/SlVCQlInrFR9JicnJ5w+fRr37t2DiYnJB//gNGzYENOmTcPq1avh6+uLtWvX4urVq/DxyftH2MDAACNHjsSIESOgp6eHWrVqISkpCdeuXUOPHj0EjzVgwABIpVJ899132Lt3b77rrsSUlpaKBwn/r9A8evQQcTdiYWZujuLFrTE8aBBuxF7HnAWLkZsrxfPnSQDyrk/T1RW/ivYl5s2ahtp168PWriSeJz3D8sULoK2ljW+btcDDBwk4uG83fGvVhXmxYoi/FYc5M6bCu3JVuJRzEzt6oZozawZq16kLWzs7pKWmYs/uXTh39ky+2fHUTdiEEOzdswuz5y2EsZExniflvaZNTE1hYGAgcjrlSktNRcK/3+8PH+JGbCzMzc1hV7Lozub5KT8HdMPY30aiQoWKqOjphbVrIpGeno42bf3FjqZUmnq+NfG469ZvgIhli2FnZ4eyLi64ERuLtatXyWe8LKoaVy8HiQS4eT8JZe2LI6x/C9y8n4TVu84BACzMDGFfohjsiudNnlXOMe/Lz6fJbwWz/pUpbYXa3s5oE7RS9QdBRY5E9t+xavReN2/eREBAAC5duoT09HT5lOovX75EsWLFBPsGBwdjyZIlyMjIQPfu3ZGdnY0rV64IplQPDw/HsmXL8PjxY9jZ2aF3794YNWoU7t27B2dnZ1y8eBHe3t4AgJkzZ2L8+PHYt28fatasic+RlqXc03ru7GkEdg/I196qdRv07tsfLZu9f8HEZSsiUfWb6krLlZ796Wrilxr76zBcunAOr1+/QjELS3h5V8Yv/QaitL0Dnj5JRMiYX3Hn9i1kpKfDpoQt6jVohK49e8NYBcMejfVV9/1I8NjfcObUKSQlPYOJqSnKlXNDtx6B8K1ZS2UZxFCpwvs7x6ETw+Gn5h+yz545jZ7d8q9Z09qvLSaETRYhkepsWLdWvvivW3l3jPxtDLy8KokdS6k09Xx/Lcedq8KPZampKVg4by4ORf2Fly+SYW1tg2YtWqJXn74q/wLUqs77F9v9Eu0aeSG0TzOUsjHHizdp+P3wVQQv3o83qRkAgJ9aVsGysT/ku9/E5Qcxaflf8tshvZuiY7PKcGs7Od+lHYUl/dQUpTxuYXiZprzPVB9jYaQtyvMqip0qNaXsTtXXSpmdqq+ZKjtVRESkPKrsVH1NCrNTVZR8zZ2qV+nifKYqZlg0O1W8poqIiIiIiEgB/HqbiIiIiIgEivJCvGJgpYqIiIiIiEgB7FQREREREREpgMP/iIiIiIhIQMLRfwXCShUREREREZECWKkiIiIiIiIBFqoKhpUqIiIiIiIiBbBSRUREREREQixVFQgrVURERERERApgp4qIiIiIiEgBHP5HREREREQCEo7/KxBWqoiIiIiIiBTAShUREREREQlw8d+CYaWKiIiIiIhIAexUERERERERKYDD/4iIiIiISICj/wqGlSoiIiIiIiIFsFJFRERERERCLFUVCCtVRERERERECmClioiIiIiIBLj4b8GwUkVEREREREXWggUL4OTkBAMDA1SvXh1nzpxReQZ2qoiIiIiIqEjatGkTgoKCEBwcjAsXLqBSpUpo2rQpnj17ptIc7FQREREREZGARCLOT0HNnDkTgYGB6NatGzw8PLB48WIYGRlhxYoVhf9L+Qh2qoiIiIiI6KuQmZmJN2/eCH4yMzPfu29WVhbOnz+Pxo0by9u0tLTQuHFjnDx5UlWR88iIClFGRoYsODhYlpGRIXYUleJx87g1AY+bx60JeNw8bhJXcHCwDIDgJzg4+L37Pnr0SAZAduLECUH78OHDZdWqVVNB2v+TyGQymWq7caTO3rx5A3Nzc7x+/RpmZmZix1EZHjePWxPwuHncmoDHzeMmcWVmZuarTOnr60NfXz/fvo8fP0apUqVw4sQJ+Pr6yttHjBiB6OhonD59Wul53+GU6kRERERE9FX4UAfqfYoXLw5tbW08ffpU0P706VPY2toqI94H8ZoqIiIiIiIqcvT09FClShVERUXJ23JzcxEVFSWoXKkCK1VERERERFQkBQUFISAgAFWrVkW1atUwe/ZspKamolu3birNwU4VFSp9fX0EBwd/dtlWXfC4edyagMfN49YEPG4eNxUtHTp0QFJSEsaNG4cnT57A29sb+/btQ4kSJVSagxNVEBERERERKYDXVBERERERESmAnSoiIiIiIiIFsFNFRERERESkAHaqiIiIiIiIFMBOFRERERERkQLYqaJCk5WVhbi4OOTk5IgdhajQrV69GpmZmfnas7KysHr1ahESKV92dja6d++Ou3fvih2FiKhQPHz48IPbTp06pcIkpG44pTopLC0tDQMGDEBkZCQA4ObNmyhTpgwGDBiAUqVK4ddffxU5ofIcO3YMS5Yswe3bt7F161aUKlUKa9asgbOzM2rXri12PCpE2traSExMhI2NjaA9OTkZNjY2kEqlIiVTLnNzc8TExMDZ2VnsKCplYWEBiUSSr10ikcDAwAAuLi7o2rWryheXVKagoKD3tv/7mP38/GBpaaniZKQscXFxmDdvHmJjYwEA7u7uGDBgANzc3EROpjweHh74+++/872Ojx8/jpYtW+LVq1fiBKMij5UqUtioUaNw6dIlHDlyBAYGBvL2xo0bY9OmTSImU65t27ahadOmMDQ0xMWLF+VVjNevXyMsLEzkdIXLx8cHlStX/qwfdSWTyd77Ifvhw4cwNzcXIZFqtGnTBjt37hQ7hsqNGzcOWlpaaNmyJUJCQhASEoKWLVtCS0sL/fr1Q7ly5dCnTx8sW7ZM7KiF5uLFi4iIiMDSpUsRHR2N6OhoLFu2DBEREYiKikJQUBBcXFxw/fp1saMqxZo1a1CrVi2ULFkS9+/fBwDMnj0bv//+u8jJlGPbtm2oWLEizp8/j0qVKqFSpUq4cOECKlasiG3btokdT2lq1KiBJk2a4O3bt/K2o0ePokWLFggODhYxGRV1OmIHoKJv586d2LRpE2rUqCH40FmhQgXcvn1bxGTKNXHiRCxevBhdunTBxo0b5e21atXCxIkTRUxW+Nq0aSP/74yMDCxcuBAeHh7w9fUFkDdk4tq1a+jbt69ICZXHx8cHEokEEokEjRo1go7O//9sSqVS3L17F82aNRMxoXK5uroiNDQUx48fR5UqVWBsbCzYPnDgQJGSKdfff/+NiRMnonfv3oL2JUuW4MCBA9i2bRu8vLwwd+5cBAYGipSycL2rQq1cuRJmZmYA8r4k6tmzJ2rXro3AwEB06tQJQ4YMwf79+0VOW7gWLVqEcePGYfDgwZg0aZK88lysWDHMnj0bfn5+IicsfCNGjMCoUaMQGhoqaA8ODsaIESPQrl07kZIp1/Lly9G+fXu0atUK+/fvx4kTJ9C6dWtMnDgRgwYNEjseFWEc/kcKMzIywtWrV1GmTBmYmpri0qVLKFOmDC5duoS6devi9evXYkdUCiMjI1y/fh1OTk6C475z5w48PDyQkZEhdkSl6NmzJ+zs7DBhwgRBe3BwMB48eIAVK1aIlEw5QkJC5P8/dOhQmJiYyLfp6enByckJ7dq1g56enlgRlepjw/4kEgnu3LmjwjSqY2JigpiYGLi4uAja4+Pj4e3tjZSUFNy+fRteXl5ITU0VKWXhKlWqFA4ePAgPDw9B+7Vr19CkSRM8evQIFy5cQJMmTfD8+XORUiqHh4cHwsLC0KZNG8Hf86tXr6J+/fpqd7xA3r9hly9fzvcav3XrFipVqoS0tDSRkilfVlYWWrZsibS0NFy+fBnh4eHo37+/2LGoiGOlihRWtWpV7N69GwMGDAAAebVq+fLl8kqGOrK1tUV8fDycnJwE7X///TfKlCkjTigV2LJlC86dO5ev/aeffkLVqlXVrlP1bjiIk5MTOnToIBjiqgk0dZIKS0tL/PnnnxgyZIig/c8//5Rfi5GamgpTU1Mx4inF69ev8ezZs3ydqqSkJLx58wZAXuUmKytLjHhKdffuXfj4+ORr19fXV5tO83/Vr18fx44dy9ep+vvvv1GnTh2RUinH5cuX87WNHz8eHTt2xE8//YS6devK9/Hy8lJ1PFIT7FSRwsLCwtC8eXNcv34dOTk5mDNnDq5fv44TJ04gOjpa7HhKExgYiEGDBmHFihWQSCR4/PgxTp48iWHDhmHs2LFix1MaQ0NDHD9+HK6uroL248ePq3WHIyAgQOwIosrKysLdu3dRtmxZwRBIdTV27Fj06dMHhw8fRrVq1QAAZ8+exZ49e7B48WIAwMGDB1GvXj0xYxYqPz8/dO/eHTNmzMA333wDIO+Yhw0bJh8CfObMGZQrV07ElMrh7OyMmJgYODo6Ctr37dsHd3d3kVIpV+vWrTFy5EicP38eNWrUAJA3lHvLli0ICQnBH3/8Idi3KPP29oZEIsG/B2e9u71kyRIsXbpUft2suk46RMrH4X9UKG7fvo3Jkyfj0qVLSElJQeXKlTFy5Eh4enqKHU1pZDIZwsLCEB4eLh8moa+vj2HDhuUbGqdOJk+ejJCQEAQGBso/bJ4+fRorVqzA2LFj1Xa2R6lUilmzZmHz5s1ISEjI9239ixcvREqmXJo8u+fx48cxf/58xMXFAQDc3NwwYMAA1KxZU+RkypGSkoIhQ4Zg9erV8qUxdHR0EBAQgFmzZsHY2BgxMTEA8j6kqpPly5dj/PjxmDFjBnr06IHly5fj9u3bCA8Px/Lly/Hjjz+KHbHQaWl93lxl6tDReDfxyOf4b8ea6HOxU0WkoKysLMTHxyMlJQUeHh6Ca27U1ebNmzFnzhzBNLyDBg3CDz/8IHIy5Rk3bhyWL1+OoUOHYsyYMRg9ejTu3buHnTt3Yty4cWo7YcOgQYNw/PhxzJ49G82aNcPly5dRpkwZ/P777xg/fjwuXrwodkQqZCkpKfJr5cqUKaMRf9MAYN26dRg/frx8gqWSJUsiJCQEPXr0EDkZERUF7FRRocjNzUV8fDyePXuG3Nxcwba6deuKlIoKW05ODsLCwtC9e3eULl1a7DgqVbZsWcydOxctW7aEqakpYmJi5G2nTp3C+vXrxY6oFI6OjvLZPf99AX98fDwqV64sv9ZGHUmlUuzcuVP+5UGFChXQunVraGtri5xM+d4tkKpp73MgrzqbkpKSb006Ug/h4eEoUaIEunfvLmhfsWIFkpKSMHLkSJGSUVHHThUp7NSpU+jUqRPu37+P/76c1GHYwL/5+/t/9r7bt29XYhLxmJiY4OrVq/km6FB3xsbGiI2NhYODA+zs7LB7925UrlwZd+7cgY+Pj1rPcqmJs3vGx8ejRYsWePTokXwh1Li4ONjb22P37t0oW7asyAkLX25uLiZOnIgZM2YgJSUFAGBqaoqhQ4di9OjRnz1crChKT0+HTCaDkZERgLzhYjt27ICHhweaNGkicrrCM3fuXPTq1QsGBgaYO3fuR/dV1+q7k5MT1q9fn28Y7+nTp/Hjjz9q7OQ8pDj1v9qYlK53797yGQDt7Ozeu0CqulDnRV4/V6NGjRAdHa1xnarSpUsjMTERDg4OKFu2LA4cOIDKlSvj7Nmz0NfXFzue0mjq7J4DBw5E2bJlcerUKflsf8nJyfjpp58wcOBA7N69W+SEhW/06NGIiIjA5MmTUatWLQB5M8GNHz8eGRkZmDRpksgJlcfPzw/+/v7o3bs3Xr16hWrVqkFPTw/Pnz/HzJkz0adPH7EjFopZs2ahc+fOMDAwwKxZsz64n0QiUdtO1ZMnT2BnZ5ev3draGomJiSIkInXBThUp7NatW9i6dWu+aVnV0cqVK8WOILrmzZvj119/xZUrV967GGxRnyXqQ9q2bYuoqChUr14dAwYMwE8//YSIiAgkJCTkm3ZbnWjq7J7R0dGCDhUAWFlZCToc6iYyMhLLly8XvIe9vLxQqlQp9O3bV607VRcuXJB3MrZu3QpbW1tcvHgR27Ztw7hx49SmU/XvKoymVmTs7e1x/PjxfGvwHT9+HCVLlhQpFakDdqpIYdWrV0d8fLxGdKoI6Nu3LwBg5syZ+bap23DPf5s8ebL8vzt06ABHR0ecOHECrq6uaNWqlYjJlKt27dqIiYnB5MmT4enpKa/QnTx5Uq1n99TX18fbt2/ztaekpKjtQs8vXrxA+fLl87WXL19ebWe3fCctLU2+5tiBAwfg7+8PLS0t1KhRo0Azx9HXLzAwEIMHD0Z2djYaNmwIAIiKisKIESMwdOhQkdNRUcZrqkhhO3bswJgxYzB8+HB4enpCV1dXsF2dFtKrXLkyoqKiYGFhAR8fn48Odbxw4YIKk5Gy8eJmzdKlSxdcuHABERERgqUDAgMDUaVKFaxatUrcgEpQvXp1VK9ePd+1NgMGDMDZs2dx6tQpkZIpn5eXF3r27Im2bduiYsWK2LdvH3x9fXH+/Hm0bNkST548ETtioZNKpVi1ahWioqLeO8nUoUOHREqmXDKZDL/++ivmzp0rXxrDwMAAI0eOxLhx40ROR0UZO1WksPddvPxuUT11q1yEhIRg+PDhMDIyQkhIyEf3DQ4OVlEqUgVNvrj59u3bWLlyJe7cuYPZs2fDxsYGe/fuhYODAypUqCB2PKV49eoVAgIC8Oeff8q/KMrOzoafnx9WrlyJYsWKiRtQCaKjo9GyZUs4ODjIr5c7efIkHjx4gD179qBOnToiJ1SerVu3olOnTpBKpWjUqBEOHDgAIO/LlKNHj2Lv3r0iJyx8/fv3x6pVq9CyZcv3Xg/9sWuu1EFKSgpiY2NhaGgIV1dXtb42llSDnSpS2KeGRnAhvaKPM0blfZMZGxubbxz+nTt34OHhgYyMDJGSKVd0dDSaN2+OWrVq4ejRo4iNjUWZMmUwefJknDt3Dlu3bhU7olLFx8cL1mNT92HOjx8/xoIFC3Djxg0Aecfct29fjbjW5MmTJ0hMTESlSpXkXxaeOXMGZmZm7x0WWdQVL14cq1evRosWLcSOQqQW2KkiUtC5c+fkH7o8PDxQpUoVkRMVPmdnZ5w7dw5WVlb5OhX/JpFI5IuGqhtXV1cEBwfjp59+ErSvWbMGwcHBanvcvr6++P777xEUFCSYUv3MmTPw9/eXr2ekDoKCgj573/ddU1iUZWdno1mzZli8eDFcXV3FjqNS2dnZMDQ0RExMDCpWrCh2HJUpWbIkjhw5gnLlyokdRaUaNGjw0aH76jrskZSPE1VQobl+/ToSEhLkY5TfUdfZ4B4+fIiOHTvi+PHj8qFAr169Qs2aNbFx40a1WjTzQzNGvftORp2n0X9HUy9uvnLlynsXNraxscHz589FSKQ8Fy9eFNy+cOECcnJy5OtU3bx5E9ra2mr5xYmuri4uX74sdgxR6OrqwsHBQa2Gqn+OoUOHYs6cOZg/f75G/A1/x9vbW3A7OzsbMTExuHr1KgICAsQJRWqBnSpS2J07d9C2bVtcuXJFfi0V8P8P2ur6D1XPnj2RnZ2N2NhYweKg3bp1Q8+ePbFv3z6REypPREQEZs2ahVu3bgHIq+IMHjwYPXv2FDmZ8gwfPhzJycno27dvvoubR40aJXI65SlWrBgSExPzVSgvXryIUqVKiZRKOQ4fPiz/75kzZ8LU1BSRkZGwsLAAALx8+RLdunVT22uL3i0T8O+ZLjXF6NGj8dtvv2HNmjWCafTVzX8XsD906BD27t2LChUq5JtkSl0XsP/QtWLjx4+XL3pN9CU4/I8U1qpVK2hra2P58uVwdnbGmTNnkJycjKFDh2L69Olq+wHE0NAQJ06cgI+Pj6D9/PnzqFOnDtLS0kRKplzjxo3DzJkzMWDAAMHF7PPnz8eQIUMQGhoqckLl0rSLm4cNG4bTp09jy5YtKFeuHC5cuICnT5+iS5cu6NKli9pOyFKqVCkcOHAg30QcV69eRZMmTfD48WORkinPgAEDsHr1ari6ur53DTp1G/L4bz4+PoiPj0d2djYcHR3zHbu6zObarVu3z95X09ZljI+PR7Vq1dR++QBSHlaqSGEnT57EoUOHULx4cWhpaUFLSwu1a9dGeHg4Bg4cmG9Ijbqwt7dHdnZ2vnapVKrWF3UvWrQIy5YtQ8eOHeVtrVu3hpeXFwYMGKD2nSoTExN88803YsdQmbCwMPTr1w/29vaQSqXw8PBATk4OOnfujDFjxogdT2nevHmDpKSkfO1JSUnvXb+qqLp8+TIqVqwILS0tXL16FZUrVwaQN9Tx39R9eFibNm3EjqAS/+4opaenIzc3V96BvHfvHnbu3Al3d3c0bdpUrIiiOXnyJAwMDMSOQUUYO1WkMKlUKl80sXjx4nj8+DHc3Nzg6OiIuLg4kdMpz7Rp0zBgwAAsWLAAVatWBZA3acWgQYMwffp0kdMpT3Z2tvx4/61KlSrIyckRIREpk56eHpYtW4Zx48bhypUrSElJgY+Pj9pPZtC2bVt069YNM2bMEKxTNXz48HxDqIoyHx8fJCYmwsbGBvfv38fZs2dhZWUldiyVU9eK68f4+fnB398fvXv3xqtXr1CjRg3o6uri+fPnmDlzJvr06SN2RKX47/tXJpMhMTER586dw9ixY0VKReqAw/9IYXXq1MHQoUPRpk0bdOrUCS9fvsSYMWOwdOlSnD9/HlevXhU7YqGxsLAQfGObmpqKnJwc6OjkfT/x7r+NjY3VdgjBgAEDoKurm28o0LBhw5Ceno4FCxaIlIwKiybPgvdOWloahg0bhhUrVsgr0jo6OujRowemTZuWb3hYUWVlZYU9e/agevXq0NLSwtOnT2FtbS12LNGcP39ePptrhQoV8g3vVifFixdHdHQ0KlSogOXLl2PevHm4ePEitm3bhnHjxsl/D+rmv0MgtbS0YG1tjYYNG6JJkyYipSJ1wEoVKWzMmDFITU0FAISGhuK7775DnTp1YGVlhU2bNomcrnDNnj1b7Aii+PeHbIlEguXLl+PAgQOoUaMGgLxv8BMSEtClSxexIlIh0uRZ8N4xMjLCwoULMW3aNNy+fRsAULZsWbXpTL3Trl071KtXT774a9WqVaGtrf3efdV12QAAePbsGX788UccOXJEMJtrgwYNsHHjRrXsaKalpclHmRw4cAD+/v7Q0tJCjRo1Prn+ZFEllUrRrVs3eHp6yiegISosrFSRUrx48SJfVYeKrgYNGnzWfhKJhGt8qJmZM2fiyJEjH5wFT52nk9cU+/btQ3x8PAYOHIjQ0FD5B+3/GjRokIqTqU6HDh1w584drF69Gu7u7gDylgkJCAiAi4sLNmzYIHLCwufl5YWePXuibdu2qFixIvbt2wdfX1+cP38eLVu2xJMnT8SOqBQfWsidSFHsVBEpQCqVYufOnYLhIq1bt/7gN71ERY0mzoKnqbp164a5c+d+sFOlzszNzfHXX3/lm4TmzJkzaNKkCV69eiVOMCXaunUrOnXqBKlUikaNGuHAgQMAgPDwcBw9ehR79+4VOaFyVK1aFVOmTEGjRo3EjkJqhsP/6IsU5EJtdV3rIj4+Hi1atMCjR4/kw6LCw8Nhb2+P3bt3o2zZsiInJFKcpsyCR5o3hfa/5ebm5lunCchbGDg3N1eERMrXvn171K5dG4mJiahUqZK8vVGjRmjbtq2IyZRr4sSJGDZsGCZMmPDepQPMzMxESkZFHStV9EW41gXQokULyGQyrFu3Tr5YZHJyMn766SdoaWlh9+7dIickUlyXLl1w7Nix986CV6dOHURGRoqckEhxfn5+ePXqFTZs2CBfEuPRo0fo3LkzLCwssGPHDpETUmHR0tKS//e/L1GQyWSQSCSQSqVixCI1wE4V0RcyNjbGqVOn4OnpKWi/dOkSatWqxZXZSS1oyix4pNkePHiA1q1b49q1a7C3twcAJCQkwNPTE3/88QdKly4tckIqLJGRkbC3t883TD83NxcJCQkICAgQKRkVdexUUaF59uyZfF0qNzc32NjYiJxIuSwtLbFr1y7UrFlT0H78+HG0atVKbadUJ82Umpqq1rPgEclkMkRFRcmvkXV3d0fjxo1FTkWFTVtbW742278lJyfDxsaGlSr6YuxUkcLevHmDfv36YePGjfI/Rtra2ujQoQMWLFgAc3NzkRMqR5cuXXDhwgVEREQIhkUFBgaiSpUqWLVqlbgBiYjos0VFRSEqKgrPnj3Ldx3VihUrREpFhe1D67Hdv38fHh4e8iViiAqKE1WQwgIDA3Hx4kXs2rULvr6+AICTJ09i0KBB+OWXX7Bx40aREyrH3LlzERAQAF9fX/kFzjk5OWjdujXmzJkjcjoiIvpcISEhCA0NRdWqVeVrdpF6ebfeokQiwdixY2FkZCTfJpVKcfr0aXh7e4uUjtQBK1WkMGNjY+zfvx+1a9cWtB87dgzNmjVT+299bt26hRs3bgDIGy7i4uIiciIiIioIOzs7TJ06FT///LPYUUhJ3q23GB0dDV9fX+jp6cm36enpwcnJCcOGDYOrq6tYEamIY6WKFGZlZfXeIX7m5uYasWK5q6sr/wgTERVhWVlZ+a6PJfVy+PBhAHmzF8+ZM4dTp1OhY6WKFLZ06VJs2bIFa9asga2tLQDgyZMnCAgIgL+/P3755ReREyqHTCbD1q1bcfjw4feOwVfX9bmIiNTNyJEjYWJigrFjx4odhYiKKHaqSGE+Pj6Ij49HZmYmHBwcAORNRauvr5+vgnPhwgUxIirFoEGDsGTJEjRo0AAlSpTINwZfXdfnIiJSB++usQHyptOOjIyEl5cXvLy88i0EPHPmTFXHI6IihsP/SGFt2rQRO4Io1qxZg+3bt6NFixZiRyEiogK6ePGi4Pa7SQquXr0qaOekFUT0OdipIoVIpVI0aNAAXl5eKFasmNhxVMrc3BxlypQROwYREX2Bd9fYEBEVBi2xA1DRpq2tjSZNmuDly5diR1G58ePHIyQkBOnp6WJHISIiIiIRsVJFCqtYsSLu3LkDZ2dnsaOo1A8//IANGzbAxsYGTk5O+cbgq9P1Y0RERET0YexUkcImTpyIYcOGYcKECahSpQqMjY0F29V12tKAgACcP38eP/3003snqiAiIiIizcDZ/0hhWlr/H0X6746FTCaDRCKBVCoVI5bSfWjRYyIiIiLSLKxUkcI09WJfe3t7ta3CEREREdHnY6WK6Avt3r0b8+bNw+LFi+Hk5CR2HCIiIiISCTtV9EUuX76MihUrQktLC5cvX/7ovl5eXipKpVoWFhZIS0tDTk4OjIyM8k1U8eLFC5GSEREREZEqsVNFX0RLSwtPnjyBjY0NtLS0IJFI8L6XkjpfUxUZGfnR7QEBASpKQkRERERiYqeKvsj9+/fh4OAAiUSC+/fvf3RfR0dHFaUiIiIiIlI9dqqo0Fy/fh0JCQnIysqSt0kkErRq1UrEVMollUqxc+dOxMbGAgAqVKiA1q1bQ1tbW+RkRERERKQq7FSRwu7cuYO2bdviypUrgmGA76ZXV9fhf/Hx8WjRogUePXoENzc3AEBcXBzs7e2xe/dulC1bVuSERERERKQKWp/ehejjBg0aBGdnZzx79gxGRka4evUqjh49iqpVq+LIkSNix1OagQMHomzZsnjw4AEuXLiACxcuICEhAc7Ozhg4cKDY8YiIiIhIRVipIoUVL14chw4dgpeXF8zNzXHmzBm4ubnh0KFDGDp0KC5evCh2RKUwNjbGqVOn4OnpKWi/dOkSatWqhZSUFJGSEREREZEqsVJFCpNKpTA1NQWQ18F6/PgxgLwJKuLi4sSMplT6+vp4+/ZtvvaUlBTo6emJkIiIiIiIxMBOFSmsYsWKuHTpEgCgevXqmDp1Ko4fP47Q0FCUKVNG5HTK891336FXr144ffo0ZDIZZDIZTp06hd69e6N169ZixyMiIiIiFeHwP1LY/v37kZqaCn9/f8THx+O7777DzZs3YWVlhU2bNqFhw4ZiR1SKV69eISAgAH/++ad84d+cnBy0bt0aK1euRLFixcQNSEREREQqwU4VKcWLFy9gYWEhnwFQncXHx8unVHd3d4eLi4vIiYiIiIhIldipIvpCoaGhGDZsGIyMjATt6enpmDZtGsaNGydSMiIiIiJSJXaqiL6QtrY2EhMTYWNjI2hPTk6GjY2N2q7PRURERERCnKiC6AvJZLL3Dm+8dOkSLC0tRUhERERERGLQETsAUVHz7loxiUSCcuXKCTpWUqkUKSkp6N27t4gJiYiIiEiVOPyPqIAiIyMhk8nQvXt3zJ49G+bm5vJtenp6cHJygq+vr4gJiYiIiEiV2Kki+kLR0dGoWbOmfDp1IiIiItJM7FQRfaGEhISPbndwcFBREiIiIiISEztVRF9IS0vro+twcfY/IiIiIs3AiSqIvtDFixcFt7Ozs3Hx4kXMnDkTkyZNEikVEREREakaK1VEhWz37t2YNm0ajhw5InYUIiIiIlIBrlNFVMjc3Nxw9uxZsWMQERERkYpw+B/RF3rz5o3gtkwmQ2JiIsaPHw9XV1eRUhERERGRqrFTRfSFihUrlm+iCplMBnt7e2zcuFGkVERERESkarymiugLRUdHC25raWnB2toaLi4u0NHh9xVEREREmoKdKiIFXb9+HQkJCcjKyhK0t27dWqRERERERKRK/Dqd6AvduXMH/v7+uHz5MiQSCd59P/FuSCDXqSIiIiLSDJz9j+gLDRo0CE5OTnj27BmMjIxw9epVHD16FFWrVuV06kREREQahMP/iL5Q8eLFcejQIXh5ecHc3BxnzpyBm5sbDh06hKFDh+ZbHJiIiIiI1BMrVURfSCqVwtTUFEBeB+vx48cAAEdHR8TFxYkZjYiIiIhUiNdUEX2hihUr4tKlS3B2dkb16tUxdepU6OnpYenSpShTpozY8YiIiIhIRTj8j+gL7d+/H6mpqfD390d8fDy+++473Lx5E1ZWVti0aRMaNmwodkQiIiIiUgF2qogK0YsXL2BhYZFvUWAiIiIiUl/sVBERERERESmAE1UQEREREREpgJ0qIiIiIiIiBbBTRUREREREpAB2qoiISCFdu3ZFmzZt5Lfr16+PwYMHqzzHkSNHIJFI8OrVK6U9x3+P9UuoIicREakWO1VERGqoa9eukEgkkEgk0NPTg4uLC0JDQ5GTk6P0596+fTsmTJjwWfuquoPh5OSE2bNnq+S5iIhIc3DxXyIiNdWsWTOsXLkSmZmZ2LNnD/r16wddXV2MGjUq375ZWVnQ09MrlOe1tLQslMchIiIqKlipIiJSU/r6+rC1tYWjoyP69OmDxo0b448//gDw/2FskyZNQsmSJeHm5gYAePDgAX744QcUK1YMlpaW8PPzw7179+SPKZVKERQUhGLFisHKygojRozAf1fm+O/wv8zMTIwcORL29vbQ19eHi4sLIiIicO/ePTRo0AAA5Ou7de3aFQCQm5uL8PBwODs7w9DQEJUqVcLWrVsFz7Nnzx6UK1cOhoaGaNCggSDnl5BKpejRo4f8Od3c3DBnzpz37hsSEgJra2uYmZmhd+/eyMrKkm/7nOxERKReWKkiItIQhoaGSE5Olt+OioqCmZkZDh48CADIzs5G06ZN4evri2PHjkFHRwcTJ05Es2bNcPnyZejp6WHGjBlYtWoVVqxYAXd3d8yYMQM7duxAw4YNP/i8Xbp0wcmTJzF37lxUqlQJd+/exfPnz2Fvb49t27ahXbt2iIuLg5mZGQwNDQEA4eHhWLt2LRYvXgxXV1ccPXoUP/30E6ytrVGvXj08ePAA/v7+6NevH3r16oVz585h6NChCv1+cnNzUbp0aWzZsgVWVlY4ceIEevXqBTs7O/zwww+C35uBgQGOHDmCe/fuoVu3brCyssKkSZM+KzsREakhGRERqZ2AgACZn5+fTCaTyXJzc2UHDx6U6evry4YNGybfXqJECVlmZqb8PmvWrJG5ubnJcnNz5W2ZmZkyQ0ND2f79+2UymUxmZ2cnmzp1qnx7dna2rHTp0vLnkslksnr16skGDRokk8lksri4OBkA2cGDB9+b8/DhwzIAspcvX8rbMjIyZEZGRrITJ04I9u3Ro4esY8eOMplMJhs1apTMw8NDsH3kyJH5Huu/HB0dZbNmzfrg9v/q16+frF27dvLbAQEBMktLS1lqaqq8bdGiRTITExOZVCr9rOzvO2YiIiraWKkiIlJTu3btgomJCbKzs5Gbm4tOnTph/Pjx8u2enp6C66guXbqE+Ph4mJqaCh4nIyMDt2/fxuvXr5GYmIjq1avLt+no6KBq1ar5hgC+ExMTA21t7QJVaOLj45GWloZvv/1W0J6VlQUfHx8AQGxsrCAHAPj6+n72c3zIggULsGLFCiQkJCA9PR1ZWVnw9vYW7FOpUiUYGRkJnjclJQUPHjxASkrKJ7MTEZH6YaeKiEhNNWjQAIsWLYKenh5KliwJHR3hn3xjY2PB7ZSUFFSpUgXr1q3L91jW1tZflOHdcL6CSElJAQDs3r0bpUqVEmzT19f/ohyfY+PGjRg2bBhmzJgBX19fmJqaYtq0aTh9+vRnP4ZY2YmISFzsVBERqSljY2O4uLh89v6VK1fGpk2bYGNjAzMzs/fuY2dnh9OnT6Nu3boAgJycHJw/fx6VK1d+7/6enp7Izc1FdHQ0GjdunG/7u0qZVCqVt3l4eEBfXx8JCQkfrHC5u7vLJ91459SpU58+yI84fvw4atasib59+8rbbt++nW+/S5cuIT09Xd5hPHXqFExMTGBvbw9LS8tPZiciIvXD2f+IiAgA0LlzZxQvXhx+fn44duwY7t69iyNHjmDgwIF4+PAhAGDQoEGYPHkydu7ciRs3bqBv374fXWPKyckJAQEB6N69O3bu3Cl/zM2bNwMAHB0dIZFIsGvXLiQlJSElJQWmpqYYNmwYhgwZgsjISNy+fRsXLlzAvHnzEBkZCQDo3bs3bt26heHDhyMuLg7r16/HqlWrPus4Hz16hJiYGMHPy5cv4erqinPnzmH//v24efMmxo4di7Nnz+a7f1ZWFnr06IHr169jz549CA4ORv/+/aGlpfVZ2YmISP2wU0VERAAAIyMjHD16FA4ODvD394e7uzt69OiBjIwMeeVq6NCh+PnnnxEQECAfIte2bduPPu6iRYvQvn179O3bF+XLl0dgYCBSU1MBAKVKlUJISAh+/fVXlChRAv379wcATJgwAWPHjkV4eDjc3d3RrFkz7N69G87OzgAABwcHbNu2DTt37kSlSpWwePFihIWFfdZxTp8+HT4+PoKf3bt345dffoG/vz86dOiA6tWrIzk5WVC1eqdRo0ZwdXVF3bp10aFDB7Ru3VpwrdqnshMRkfqRyD50dTERERERERF9EitVRERERERECmCnioiIiIiISAHsVBERERERESmAnSoiIiIiIiIFsFNFRERERESkAHaqiIiIiIiIFMBOFRERERERkQLYqSIiIiIiIlIAO1VEREREREQKYKeKiIiIiIhIAexUERERERERKYCdKiIiIiIiIgX8D5+P1oqs2p9IAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "ZhLHrkH_VHbq"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "qgd8jTQOVHet"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "OXUoFIuOVHhl"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "bSIH4BcGVHq-"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "hC71akEHVHt0"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}