{
  "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": "markdown",
      "source": [
        "# **CNN Experiment 3**"
      ],
      "metadata": {
        "id": "Z1AQ_zY31w0e"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "This experiment improves the baseline CNN by adding data augmentation, a third convolutional layer, a lower learning rate and training callbacks."
      ],
      "metadata": {
        "id": "7qyoWo4t176W"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount(\"/content/drive\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Sw0Vl5JgvbyO",
        "outputId": "aaf9f6be-25a5-4fe8-a5be-9805812ee215"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import zipfile\n",
        "\n",
        "zip_path = \"/content/drive/MyDrive/PlantPathology_Split.zip\"\n",
        "extract_path = \"/content\"\n",
        "\n",
        "with zipfile.ZipFile(zip_path, \"r\") as zip_ref:\n",
        "    zip_ref.extractall(\"/content\")\n",
        "\n",
        "print(\"Unzip completed.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aU0-O3E6If7i",
        "outputId": "e4abfc97-1375-4f54-fc9e-cc2776da58e7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Unzip completed.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 1. Dataset Preparation"
      ],
      "metadata": {
        "id": "0MmWWLwn2IqL"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import shutil\n",
        "\n",
        "source_dir = \"/content/PlantPathology_Split\"\n",
        "target_dir = \"/content/PlantPathology_5Classes\"\n",
        "\n",
        "selected_classes = [\n",
        "    \"healthy\",\n",
        "    \"scab\",\n",
        "    \"frog_eye_leaf_spot\",\n",
        "    \"rust\",\n",
        "    \"powdery_mildew\"\n",
        "]\n",
        "\n",
        "splits = [\"train\", \"valid\", \"test\"]\n",
        "\n",
        "# Remove old version if it already exists\n",
        "if os.path.exists(target_dir):\n",
        "    shutil.rmtree(target_dir)\n",
        "\n",
        "# Copy only the five required classes\n",
        "for split in splits:\n",
        "    for class_name in selected_classes:\n",
        "\n",
        "        source_class_dir = os.path.join(\n",
        "            source_dir,\n",
        "            split,\n",
        "            class_name\n",
        "        )\n",
        "\n",
        "        target_class_dir = os.path.join(\n",
        "            target_dir,\n",
        "            split,\n",
        "            class_name\n",
        "        )\n",
        "\n",
        "        if not os.path.exists(source_class_dir):\n",
        "            print(f\"Missing folder: {source_class_dir}\")\n",
        "            continue\n",
        "\n",
        "        shutil.copytree(\n",
        "            source_class_dir,\n",
        "            target_class_dir\n",
        "        )\n",
        "\n",
        "print(\"Five-class dataset created.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7ItFYHBXIw2Q",
        "outputId": "0967f81e-075f-4344-a97a-729f19445f09"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Five-class dataset created.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 2. Dataset Distribution"
      ],
      "metadata": {
        "id": "rxnotBP62Txb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "for split in splits:\n",
        "    print(f\"\\n{split.upper()}\")\n",
        "\n",
        "    total = 0\n",
        "\n",
        "    for class_name in selected_classes:\n",
        "        class_path = os.path.join(\n",
        "            target_dir,\n",
        "            split,\n",
        "            class_name\n",
        "        )\n",
        "\n",
        "        image_count = len([\n",
        "            file_name\n",
        "            for file_name in os.listdir(class_path)\n",
        "            if os.path.isfile(\n",
        "                os.path.join(class_path, file_name)\n",
        "            )\n",
        "        ])\n",
        "\n",
        "        total += image_count\n",
        "\n",
        "        print(f\"{class_name}: {image_count}\")\n",
        "\n",
        "    print(f\"Total: {total}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Vd601LX1I72b",
        "outputId": "a582b66e-9f89-4422-9a3c-1e3916192676"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "TRAIN\n",
            "healthy: 2074\n",
            "scab: 2334\n",
            "frog_eye_leaf_spot: 1448\n",
            "rust: 864\n",
            "powdery_mildew: 587\n",
            "Total: 7307\n",
            "\n",
            "VALID\n",
            "healthy: 444\n",
            "scab: 500\n",
            "frog_eye_leaf_spot: 310\n",
            "rust: 185\n",
            "powdery_mildew: 125\n",
            "Total: 1564\n",
            "\n",
            "TEST\n",
            "healthy: 445\n",
            "scab: 500\n",
            "frog_eye_leaf_spot: 310\n",
            "rust: 186\n",
            "powdery_mildew: 126\n",
            "Total: 1567\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 3. TensorFlow Data Pipeline"
      ],
      "metadata": {
        "id": "JyB07TFb2dxg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import tensorflow as tf\n",
        "\n",
        "IMG_SIZE = (512, 512)\n",
        "BATCH_SIZE = 32\n",
        "\n",
        "train_dir = \"/content/PlantPathology_5Classes/train\"\n",
        "valid_dir = \"/content/PlantPathology_5Classes/valid\"\n",
        "test_dir = \"/content/PlantPathology_5Classes/test\"\n",
        "\n",
        "train_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "    train_dir,\n",
        "    image_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    label_mode=\"int\",\n",
        "    shuffle=True,\n",
        "    seed=42\n",
        ")\n",
        "\n",
        "valid_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "    valid_dir,\n",
        "    image_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    label_mode=\"int\",\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "test_ds = tf.keras.utils.image_dataset_from_directory(\n",
        "    test_dir,\n",
        "    image_size=IMG_SIZE,\n",
        "    batch_size=BATCH_SIZE,\n",
        "    label_mode=\"int\",\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "class_names = train_ds.class_names\n",
        "\n",
        "print(\"\\nClasses:\")\n",
        "print(class_names)\n",
        "\n",
        "print(\"\\nNumber of classes:\", len(class_names))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JVa-slm2JAtn",
        "outputId": "30d65959-6ab1-42e0-96cb-faa061fe6701"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 7307 files belonging to 5 classes.\n",
            "Found 1564 files belonging to 5 classes.\n",
            "Found 1567 files belonging to 5 classes.\n",
            "\n",
            "Classes:\n",
            "['frog_eye_leaf_spot', 'healthy', 'powdery_mildew', 'rust', 'scab']\n",
            "\n",
            "Number of classes: 5\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 4. Dataset Performance Optimisation"
      ],
      "metadata": {
        "id": "QeHYskrR2lQy"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "AUTOTUNE = tf.data.AUTOTUNE\n",
        "\n",
        "train_ds = train_ds.prefetch(\n",
        "    buffer_size=AUTOTUNE\n",
        ")\n",
        "\n",
        "valid_ds = valid_ds.prefetch(\n",
        "    buffer_size=AUTOTUNE\n",
        ")\n",
        "\n",
        "test_ds = test_ds.prefetch(\n",
        "    buffer_size=AUTOTUNE\n",
        ")"
      ],
      "metadata": {
        "id": "DAiQ_LIXJgZG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 5. Data Augmentation\n"
      ],
      "metadata": {
        "id": "1bbj7Ux-Q2l3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras import layers, models\n",
        "\n",
        "data_augmentation = models.Sequential([\n",
        "    layers.RandomFlip(\"horizontal\"),\n",
        "    layers.RandomRotation(0.1),\n",
        "    layers.RandomZoom(0.1)\n",
        "], name=\"data_augmentation\")"
      ],
      "metadata": {
        "id": "KEoPAuaESM3f"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 6. Experiment 3 CNN Architecture"
      ],
      "metadata": {
        "id": "74rwYnFFSTjN"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "num_classes = len(class_names)\n",
        "\n",
        "experiment3_model = models.Sequential([\n",
        "\n",
        "    layers.Input(shape=(512, 512, 3)),\n",
        "\n",
        "    data_augmentation,\n",
        "\n",
        "    layers.Rescaling(1./255),\n",
        "\n",
        "    layers.Conv2D(32, 3, activation=\"relu\"),\n",
        "    layers.MaxPooling2D(),\n",
        "\n",
        "    layers.Conv2D(64, 3, activation=\"relu\"),\n",
        "    layers.MaxPooling2D(),\n",
        "\n",
        "    layers.Conv2D(128, 3, activation=\"relu\"),\n",
        "    layers.MaxPooling2D(),\n",
        "\n",
        "    layers.Flatten(),\n",
        "\n",
        "    layers.Dense(128, activation=\"relu\"),\n",
        "    layers.Dropout(0.3),\n",
        "\n",
        "    layers.Dense(num_classes, activation=\"softmax\")\n",
        "\n",
        "], name=\"experiment3_cnn\")\n",
        "\n",
        "experiment3_model.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 513
        },
        "id": "P5ON57sTkftU",
        "outputId": "ff49d191-9a32-482f-88a2-06ed824c57b5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"experiment3_cnn\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"experiment3_cnn\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ data_augmentation (\u001b[38;5;33mSequential\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ rescaling (\u001b[38;5;33mRescaling\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m512\u001b[0m, \u001b[38;5;34m3\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m510\u001b[0m, \u001b[38;5;34m510\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m896\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m255\u001b[0m, \u001b[38;5;34m255\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m253\u001b[0m, \u001b[38;5;34m253\u001b[0m, \u001b[38;5;34m64\u001b[0m)   │        \u001b[38;5;34m18,496\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m64\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;34m124\u001b[0m, \u001b[38;5;34m124\u001b[0m, \u001b[38;5;34m128\u001b[0m)  │        \u001b[38;5;34m73,856\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m62\u001b[0m, \u001b[38;5;34m62\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m492032\u001b[0m)         │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │    \u001b[38;5;34m62,980,224\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m)              │           \u001b[38;5;34m645\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",
              "│ data_augmentation (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Sequential</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ rescaling (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Rescaling</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">3</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</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\">510</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">510</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</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\">255</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">255</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">253</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">253</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)   │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">126</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">126</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</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\">124</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">124</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)  │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</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\">62</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">62</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">492032</span>)         │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │    <span style=\"color: #00af00; text-decoration-color: #00af00\">62,980,224</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">645</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m63,074,117\u001b[0m (240.61 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\">63,074,117</span> (240.61 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m63,074,117\u001b[0m (240.61 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\">63,074,117</span> (240.61 MB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 7. Model Compilation\n",
        "\n"
      ],
      "metadata": {
        "id": "jvebUxgvmfZ3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.optimizers import Adam\n",
        "\n",
        "experiment3_model.compile(\n",
        "    optimizer=Adam(learning_rate=0.0003),\n",
        "    loss=\"sparse_categorical_crossentropy\",\n",
        "    metrics=[\"accuracy\"]\n",
        ")"
      ],
      "metadata": {
        "id": "W_UYNLmFmt7U"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 8. Training Callbacks"
      ],
      "metadata": {
        "id": "Dma-yagpTsAt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint\n",
        "\n",
        "early_stop = EarlyStopping(\n",
        "    monitor=\"val_loss\",\n",
        "    mode=\"min\",\n",
        "    patience=5,\n",
        "    restore_best_weights=True,\n",
        "    verbose=0\n",
        ")\n",
        "\n",
        "checkpoint = ModelCheckpoint(\n",
        "    \"/content/drive/MyDrive/experiment3_cnn_best.keras\",\n",
        "    monitor=\"val_loss\",\n",
        "    mode=\"min\",\n",
        "    save_best_only=True,\n",
        "    verbose=0\n",
        ")\n",
        "\n",
        "callbacks = [\n",
        "    early_stop,\n",
        "    checkpoint\n",
        "]"
      ],
      "metadata": {
        "id": "TDUEPMO3mzPY"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 9. Model Training\n",
        "\n"
      ],
      "metadata": {
        "id": "A01eBBYNm7KH"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "history_experiment3 = experiment3_model.fit(\n",
        "    train_ds,\n",
        "    validation_data=valid_ds,\n",
        "    epochs=30,\n",
        "    callbacks=callbacks\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sCV2uCaNnGNL",
        "outputId": "17601ac2-d2d4-4e14-ed55-78b9e90a9c46"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m94s\u001b[0m 370ms/step - accuracy: 0.3866 - loss: 1.4085 - val_accuracy: 0.4015 - val_loss: 1.3962\n",
            "Epoch 2/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m128s\u001b[0m 339ms/step - accuracy: 0.4960 - loss: 1.2032 - val_accuracy: 0.5691 - val_loss: 1.0592\n",
            "Epoch 3/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 316ms/step - accuracy: 0.5571 - loss: 1.0936 - val_accuracy: 0.5205 - val_loss: 1.0966\n",
            "Epoch 4/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m90s\u001b[0m 352ms/step - accuracy: 0.5944 - loss: 1.0155 - val_accuracy: 0.6490 - val_loss: 0.8896\n",
            "Epoch 5/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 352ms/step - accuracy: 0.6294 - loss: 0.9288 - val_accuracy: 0.6586 - val_loss: 0.8693\n",
            "Epoch 6/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 345ms/step - accuracy: 0.6409 - loss: 0.9010 - val_accuracy: 0.6886 - val_loss: 0.7936\n",
            "Epoch 7/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 315ms/step - accuracy: 0.6728 - loss: 0.8221 - val_accuracy: 0.6880 - val_loss: 0.8181\n",
            "Epoch 8/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 310ms/step - accuracy: 0.6950 - loss: 0.7856 - val_accuracy: 0.6618 - val_loss: 0.8309\n",
            "Epoch 9/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m78s\u001b[0m 343ms/step - accuracy: 0.7064 - loss: 0.7371 - val_accuracy: 0.7231 - val_loss: 0.6855\n",
            "Epoch 10/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 319ms/step - accuracy: 0.7219 - loss: 0.7144 - val_accuracy: 0.7078 - val_loss: 0.7551\n",
            "Epoch 11/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m88s\u001b[0m 347ms/step - accuracy: 0.7349 - loss: 0.6776 - val_accuracy: 0.7321 - val_loss: 0.6696\n",
            "Epoch 12/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 339ms/step - accuracy: 0.7463 - loss: 0.6361 - val_accuracy: 0.7532 - val_loss: 0.6273\n",
            "Epoch 13/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 313ms/step - accuracy: 0.7571 - loss: 0.6117 - val_accuracy: 0.7212 - val_loss: 0.6923\n",
            "Epoch 14/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 313ms/step - accuracy: 0.7647 - loss: 0.6019 - val_accuracy: 0.7455 - val_loss: 0.6410\n",
            "Epoch 15/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m70s\u001b[0m 307ms/step - accuracy: 0.7630 - loss: 0.5934 - val_accuracy: 0.7430 - val_loss: 0.6670\n",
            "Epoch 16/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 314ms/step - accuracy: 0.7767 - loss: 0.5773 - val_accuracy: 0.7398 - val_loss: 0.6481\n",
            "Epoch 17/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 348ms/step - accuracy: 0.7847 - loss: 0.5593 - val_accuracy: 0.7628 - val_loss: 0.5929\n",
            "Epoch 18/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m74s\u001b[0m 321ms/step - accuracy: 0.7935 - loss: 0.5392 - val_accuracy: 0.7212 - val_loss: 0.6840\n",
            "Epoch 19/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m87s\u001b[0m 345ms/step - accuracy: 0.7950 - loss: 0.5273 - val_accuracy: 0.7666 - val_loss: 0.5685\n",
            "Epoch 20/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m77s\u001b[0m 322ms/step - accuracy: 0.8003 - loss: 0.5070 - val_accuracy: 0.7781 - val_loss: 0.5747\n",
            "Epoch 21/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 311ms/step - accuracy: 0.8116 - loss: 0.4920 - val_accuracy: 0.7730 - val_loss: 0.5826\n",
            "Epoch 22/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m72s\u001b[0m 313ms/step - accuracy: 0.8184 - loss: 0.4790 - val_accuracy: 0.7743 - val_loss: 0.6010\n",
            "Epoch 23/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m78s\u001b[0m 339ms/step - accuracy: 0.8232 - loss: 0.4622 - val_accuracy: 0.7852 - val_loss: 0.5310\n",
            "Epoch 24/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 349ms/step - accuracy: 0.8226 - loss: 0.4663 - val_accuracy: 0.7935 - val_loss: 0.5210\n",
            "Epoch 25/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m79s\u001b[0m 343ms/step - accuracy: 0.8386 - loss: 0.4224 - val_accuracy: 0.8024 - val_loss: 0.5421\n",
            "Epoch 26/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m77s\u001b[0m 320ms/step - accuracy: 0.8367 - loss: 0.4181 - val_accuracy: 0.7973 - val_loss: 0.5732\n",
            "Epoch 27/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m71s\u001b[0m 308ms/step - accuracy: 0.8521 - loss: 0.3934 - val_accuracy: 0.8056 - val_loss: 0.5490\n",
            "Epoch 28/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m78s\u001b[0m 341ms/step - accuracy: 0.8577 - loss: 0.3915 - val_accuracy: 0.8261 - val_loss: 0.4959\n",
            "Epoch 29/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 319ms/step - accuracy: 0.8638 - loss: 0.3657 - val_accuracy: 0.8223 - val_loss: 0.5049\n",
            "Epoch 30/30\n",
            "\u001b[1m229/229\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m73s\u001b[0m 316ms/step - accuracy: 0.8642 - loss: 0.3749 - val_accuracy: 0.8210 - val_loss: 0.5173\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 10. Training Results"
      ],
      "metadata": {
        "id": "5L_2yO0EfEsf"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from IPython.display import display\n",
        "\n",
        "max_epochs = 30\n",
        "epochs_completed = len(history_experiment3.history[\"loss\"])\n",
        "\n",
        "# Best epoch based on the lowest validation loss\n",
        "best_epoch = int(np.argmin(history_experiment3.history[\"val_loss\"]) + 1)\n",
        "\n",
        "best_val_loss = history_experiment3.history[\"val_loss\"][best_epoch - 1]\n",
        "best_val_accuracy = history_experiment3.history[\"val_accuracy\"][best_epoch - 1]\n",
        "\n",
        "train_loss_at_best_epoch = history_experiment3.history[\"loss\"][best_epoch - 1]\n",
        "train_accuracy_at_best_epoch = history_experiment3.history[\"accuracy\"][best_epoch - 1]\n",
        "\n",
        "# Highest validation accuracy\n",
        "highest_val_accuracy = max(history_experiment3.history[\"val_accuracy\"])\n",
        "highest_val_accuracy_epoch = int(\n",
        "    np.argmax(history_experiment3.history[\"val_accuracy\"]) + 1\n",
        ")\n",
        "\n",
        "# Check EarlyStopping and checkpoint\n",
        "early_stopping_activated = epochs_completed < max_epochs\n",
        "\n",
        "checkpoint_path = \"/content/drive/MyDrive/experiment3_cnn_best.keras\"\n",
        "checkpoint_saved = os.path.exists(checkpoint_path)\n",
        "\n",
        "summary_table = pd.DataFrame({\n",
        "    \"Metric\": [\n",
        "        \"Maximum Epochs\",\n",
        "        \"Epochs Completed\",\n",
        "        \"Early Stopping Activated\",\n",
        "        \"Best Checkpoint Epoch\",\n",
        "        \"Training Accuracy at Best Epoch\",\n",
        "        \"Validation Accuracy at Best Epoch\",\n",
        "        \"Training Loss at Best Epoch\",\n",
        "        \"Best Validation Loss\",\n",
        "        \"Highest Validation Accuracy\",\n",
        "        \"Highest Validation Accuracy Epoch\",\n",
        "        \"Best Checkpoint Saved\"\n",
        "    ],\n",
        "    \"Result\": [\n",
        "        max_epochs,\n",
        "        epochs_completed,\n",
        "        \"Yes\" if early_stopping_activated else \"No\",\n",
        "        best_epoch,\n",
        "        f\"{train_accuracy_at_best_epoch * 100:.2f}%\",\n",
        "        f\"{best_val_accuracy * 100:.2f}%\",\n",
        "        f\"{train_loss_at_best_epoch:.4f}\",\n",
        "        f\"{best_val_loss:.4f}\",\n",
        "        f\"{highest_val_accuracy * 100:.2f}%\",\n",
        "        highest_val_accuracy_epoch,\n",
        "        \"Yes\" if checkpoint_saved else \"No\"\n",
        "    ]\n",
        "})\n",
        "\n",
        "display(\n",
        "    summary_table.style\n",
        "    .set_caption(\"Experiment 3 CNN Training Results\")\n",
        "    .hide(axis=\"index\")\n",
        "    .set_properties(**{\n",
        "        \"text-align\": \"center\",\n",
        "        \"font-size\": \"16px\"\n",
        "    })\n",
        "    .set_table_styles([\n",
        "        {\n",
        "            \"selector\": \"caption\",\n",
        "            \"props\": [\n",
        "                (\"font-size\", \"19px\"),\n",
        "                (\"font-weight\", \"bold\"),\n",
        "                (\"text-align\", \"left\"),\n",
        "                (\"padding-bottom\", \"10px\")\n",
        "            ]\n",
        "        },\n",
        "        {\n",
        "            \"selector\": \"th\",\n",
        "            \"props\": [\n",
        "                (\"border\", \"1px solid black\"),\n",
        "                (\"font-weight\", \"bold\"),\n",
        "                (\"text-align\", \"center\"),\n",
        "                (\"padding\", \"9px\")\n",
        "            ]\n",
        "        },\n",
        "        {\n",
        "            \"selector\": \"td\",\n",
        "            \"props\": [\n",
        "                (\"border\", \"1px solid black\"),\n",
        "                (\"padding\", \"9px\")\n",
        "            ]\n",
        "        }\n",
        "    ])\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 514
        },
        "id": "1czy2PEbNj6F",
        "outputId": "89aa544c-7715-4af9-e3b8-4a57a99fb599"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<pandas.io.formats.style.Styler at 0x7c802bfc1e80>"
            ],
            "text/html": [
              "<style type=\"text/css\">\n",
              "#T_07ce7 caption {\n",
              "  font-size: 19px;\n",
              "  font-weight: bold;\n",
              "  text-align: left;\n",
              "  padding-bottom: 10px;\n",
              "}\n",
              "#T_07ce7 th {\n",
              "  border: 1px solid black;\n",
              "  font-weight: bold;\n",
              "  text-align: center;\n",
              "  padding: 9px;\n",
              "}\n",
              "#T_07ce7 td {\n",
              "  border: 1px solid black;\n",
              "  padding: 9px;\n",
              "}\n",
              "#T_07ce7_row0_col0, #T_07ce7_row0_col1, #T_07ce7_row1_col0, #T_07ce7_row1_col1, #T_07ce7_row2_col0, #T_07ce7_row2_col1, #T_07ce7_row3_col0, #T_07ce7_row3_col1, #T_07ce7_row4_col0, #T_07ce7_row4_col1, #T_07ce7_row5_col0, #T_07ce7_row5_col1, #T_07ce7_row6_col0, #T_07ce7_row6_col1, #T_07ce7_row7_col0, #T_07ce7_row7_col1, #T_07ce7_row8_col0, #T_07ce7_row8_col1, #T_07ce7_row9_col0, #T_07ce7_row9_col1, #T_07ce7_row10_col0, #T_07ce7_row10_col1 {\n",
              "  text-align: center;\n",
              "  font-size: 16px;\n",
              "}\n",
              "</style>\n",
              "<table id=\"T_07ce7\" class=\"dataframe\">\n",
              "  <caption>Experiment 3 CNN Training Results</caption>\n",
              "  <thead>\n",
              "    <tr>\n",
              "      <th id=\"T_07ce7_level0_col0\" class=\"col_heading level0 col0\" >Metric</th>\n",
              "      <th id=\"T_07ce7_level0_col1\" class=\"col_heading level0 col1\" >Result</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row0_col0\" class=\"data row0 col0\" >Maximum Epochs</td>\n",
              "      <td id=\"T_07ce7_row0_col1\" class=\"data row0 col1\" >30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row1_col0\" class=\"data row1 col0\" >Epochs Completed</td>\n",
              "      <td id=\"T_07ce7_row1_col1\" class=\"data row1 col1\" >30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row2_col0\" class=\"data row2 col0\" >Early Stopping Activated</td>\n",
              "      <td id=\"T_07ce7_row2_col1\" class=\"data row2 col1\" >No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row3_col0\" class=\"data row3 col0\" >Best Checkpoint Epoch</td>\n",
              "      <td id=\"T_07ce7_row3_col1\" class=\"data row3 col1\" >28</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row4_col0\" class=\"data row4 col0\" >Training Accuracy at Best Epoch</td>\n",
              "      <td id=\"T_07ce7_row4_col1\" class=\"data row4 col1\" >85.77%</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row5_col0\" class=\"data row5 col0\" >Validation Accuracy at Best Epoch</td>\n",
              "      <td id=\"T_07ce7_row5_col1\" class=\"data row5 col1\" >82.61%</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row6_col0\" class=\"data row6 col0\" >Training Loss at Best Epoch</td>\n",
              "      <td id=\"T_07ce7_row6_col1\" class=\"data row6 col1\" >0.3915</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row7_col0\" class=\"data row7 col0\" >Best Validation Loss</td>\n",
              "      <td id=\"T_07ce7_row7_col1\" class=\"data row7 col1\" >0.4959</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row8_col0\" class=\"data row8 col0\" >Highest Validation Accuracy</td>\n",
              "      <td id=\"T_07ce7_row8_col1\" class=\"data row8 col1\" >82.61%</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row9_col0\" class=\"data row9 col0\" >Highest Validation Accuracy Epoch</td>\n",
              "      <td id=\"T_07ce7_row9_col1\" class=\"data row9 col1\" >28</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td id=\"T_07ce7_row10_col0\" class=\"data row10 col0\" >Best Checkpoint Saved</td>\n",
              "      <td id=\"T_07ce7_row10_col1\" class=\"data row10 col1\" >Yes</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 11. Training and Validation Curves"
      ],
      "metadata": {
        "id": "jaVXmrCwgw9v"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "\n",
        "epochs = range(\n",
        "    1,\n",
        "    len(history_experiment3.history[\"accuracy\"]) + 1\n",
        ")\n",
        "\n",
        "best_epoch = int(\n",
        "    np.argmin(history_experiment3.history[\"val_loss\"]) + 1\n",
        ")\n",
        "\n",
        "plt.figure(figsize=(12, 5))\n",
        "\n",
        "# Accuracy graph\n",
        "plt.subplot(1, 2, 1)\n",
        "\n",
        "plt.plot(\n",
        "    epochs,\n",
        "    history_experiment3.history[\"accuracy\"],\n",
        "    label=\"Training Accuracy\",\n",
        "    color=\"#F4B400\",\n",
        "    linewidth=2.5\n",
        ")\n",
        "\n",
        "plt.plot(\n",
        "    epochs,\n",
        "    history_experiment3.history[\"val_accuracy\"],\n",
        "    label=\"Validation Accuracy\",\n",
        "    color=\"#00AEEF\",\n",
        "    linewidth=2.5\n",
        ")\n",
        "\n",
        "plt.axvline(\n",
        "    best_epoch,\n",
        "    linestyle=\"--\",\n",
        "    color=\"black\",\n",
        "    label=f\"Best Epoch ({best_epoch})\"\n",
        ")\n",
        "\n",
        "plt.title(\"Experiment 3 CNN Accuracy\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Accuracy\")\n",
        "plt.xticks(epochs)\n",
        "plt.legend()\n",
        "\n",
        "\n",
        "# Loss graph\n",
        "plt.subplot(1, 2, 2)\n",
        "\n",
        "plt.plot(\n",
        "    epochs,\n",
        "    history_experiment3.history[\"loss\"],\n",
        "    label=\"Training Loss\",\n",
        "    color=\"#F4B400\",\n",
        "    linewidth=2.5\n",
        ")\n",
        "\n",
        "plt.plot(\n",
        "    epochs,\n",
        "    history_experiment3.history[\"val_loss\"],\n",
        "    label=\"Validation Loss\",\n",
        "    color=\"#00AEEF\",\n",
        "    linewidth=2.5\n",
        ")\n",
        "\n",
        "plt.axvline(\n",
        "    best_epoch,\n",
        "    linestyle=\"--\",\n",
        "    color=\"black\",\n",
        "    label=f\"Best Epoch ({best_epoch})\"\n",
        ")\n",
        "\n",
        "plt.title(\"Experiment 3 CNN Loss\")\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Loss\")\n",
        "plt.xticks(epochs)\n",
        "plt.legend()\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 507
        },
        "id": "XAX2KmjuNoNE",
        "outputId": "0e83f50b-9987-4ddb-88d6-daa5e7290261"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x500 with 2 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABKUAAAHqCAYAAADVi/1VAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs3Xd4FFX3wPHvbE82PZSEGiD03gWkyw9BEVEs+CLdjooVURRQARVFeLHwqggWEAVRwYaIIghIDx1poQcIISQk2Wyb+f0R2M2SCiRZSM7nefKQmbkze3ZJNnfP3HuuommahhBCCCGEEEIIIYQQJUjn7wCEEEIIIYQQQgghRNkjSSkhhBBCCCGEEEIIUeIkKSWEEEIIIYQQQgghSpwkpYQQQgghhBBCCCFEiZOklBBCCCGEEEIIIYQocZKUEkIIIYQQQgghhBAlTpJSQgghhBBCCCGEEKLESVJKCCGEEEIIIYQQQpQ4SUoJIYQQQgghhBBCiBInSSkhyrDx48ejKIq/wxBCCCGEKLOkPyaEKMskKSXEVZgzZw6KouT59c8///g7xFJh0qRJfP/994Vqa7PZGD58OI0aNSI0NJSgoCCaNm3K9OnTcTqdhX7MU6dO8eyzz1KvXj0CAwOxWq20bNmS119/nXPnznnadenSBUVR6NOnT45rHDp0CEVRePvttz37VqxY4fn52LRpU45zhgwZQlBQUKHjBHj++edRFIV77rnnss4TQgghSgPpj5UM6Y/ldDGheObMmUI/JyGEL4O/AxCiNHj11VepUaNGjv2xsbF+iKbwxo4dywsvvODvMAo0adIk+vfvz+23315gW5vNxs6dO+nduzcxMTHodDrWrFnDU089xbp165g3b16B19iwYQO9e/cmLS2NgQMH0rJlSwA2btzIG2+8wcqVK/ntt998zvnxxx/ZtGmTp21hjB8/niVLlhS6fW40TeOrr74iJiaGJUuWcP78eYKDg6/qmkIIIcT1SPpjxUv6Y0KI4iBJKSGKQK9evWjVqpW/wyi09PR0rFYrBoMBg6F0vQ1ERETkuCP68MMPExoaynvvvcfUqVOJiorK8/xz587Rr18/9Ho9W7ZsoV69ej7HJ06cyMcff+yzr1q1apw/f54JEyawePHiQsXZrFkzfvzxRzZv3kyLFi0K+exyWrFiBceOHeOPP/6gZ8+eLFq0iMGDB1/x9YpTRkYGgYGB/g5DCCFEKSX9sWtHWeuPCSGunEzfE6IEjBs3Dp1Ox/Lly332P/jgg5hMJrZu3Qp4hxJ//fXXvPjii0RFRWG1Wrnttts4evRojuuuW7eOm2++mdDQUAIDA+ncuTOrV6/2aXNxWPGuXbu47777CA8P58Ybb/Q5lp2iKIwcOZIFCxbQoEEDAgICaNeuHdu3bwfgf//7H7GxsVgsFrp06cKhQ4euKq79+/czZMgQwsLCCA0NZejQoWRkZPjEk56ezmeffeYZZj1kyJDCvfDZxMTEAPgM9c7N//73P44fP87UqVNzdIAAKlasyNixY332BQcH89RTT7FkyRI2b95cqHgef/xxwsPDGT9+fKHa52Xu3Lk0aNCArl27ctNNNzF37txc2x0/fpzhw4dTqVIlzGYzNWrU4JFHHsHhcHjanDt3jqeeeoqYmBjMZjNVqlRh0KBBniHpF6dHXPp/fvHndsWKFZ59Xbp0oVGjRmzatIlOnToRGBjIiy++CMAPP/zALbfc4omlVq1avPbaa7jd7hxxr1u3jt69exMeHo7VaqVJkyZMnz4dgNmzZ6MoClu2bMlx3qRJk9Dr9Rw/fvyyXk8hhBCll/THpD92qaLqjxXkjz/+oGPHjlitVsLCwujbty+7d+/2aXP+/HlGjRrl6YdVqFCBHj16+DyXffv2ceeddxIVFYXFYqFKlSrce++9pKSkFGv8QhSn0pWSF8JPUlJScswlVxSFyMhIIGtY9pIlSxg+fDjbt28nODiYpUuX8vHHH/Paa6/RtGlTn3MnTpyIoiiMHj2a06dPM23aNG666Sbi4uIICAgAsv649erVi5YtW3o6WbNnz6Zbt26sWrWKNm3a+Fzzrrvuonbt2kyaNAlN0/J9PqtWrWLx4sU89thjAEyePJlbb72V559/ng8++IBHH32U5ORk3nrrLYYNG8Yff/zhOfdy47r77rupUaMGkydPZvPmzXzyySdUqFCBN998E4AvvviCESNG0KZNGx588EEAatWqVeD/icPhIDU1FZvNxsaNG3n77bepXr16gUP4Fy9eTEBAAP379y/wMbJ78skneffddxk/fnyh7s6FhITw1FNP8corr1zx3Tm73c63337LM888A8CAAQMYOnQoJ0+e9Ln7eOLECdq0acO5c+d48MEHqVevHsePH2fhwoVkZGRgMplIS0ujY8eO7N69m2HDhtGiRQvOnDnD4sWLOXbsGOXKlbvs+JKSkujVqxf33nsvAwcOpGLFikBWcisoKIinn36aoKAg/vjjD1555RVSU1OZMmWK5/xly5Zx6623Eh0dzZNPPklUVBS7d+/mxx9/5Mknn6R///489thjzJ07l+bNm/s89ty5c+nSpQuVK1e+7LiFEEJcn6Q/Jv0xf/THCvL777/Tq1cvatasyfjx47HZbMyYMYMOHTqwefNmT6Lu4YcfZuHChYwcOZIGDRqQlJTE33//ze7du2nRogUOh4OePXtit9t5/PHHiYqK4vjx4/z444+cO3eO0NDQIo9diBKhCSGu2OzZszUg1y+z2ezTdvv27ZrJZNJGjBihJScna5UrV9ZatWqlOZ1OT5s///xTA7TKlStrqampnv3ffPONBmjTp0/XNE3TVFXVateurfXs2VNTVdXTLiMjQ6tRo4bWo0cPz75x48ZpgDZgwIAc8V88lt3F2OPj4z37/ve//2mAFhUV5RPXmDFjNMDT9kriGjZsmM/j9+vXT4uMjPTZZ7VatcGDB+eIPz9fffWVz/9Hq1attG3bthV4Xnh4uNa0adNCP07nzp21hg0bapqmaRMmTNAAbdOmTZqmaVp8fLwGaFOmTPG0v/h/vGDBAu3cuXNaeHi4dtttt3mODx48WLNarYV67IULF2qAtm/fPk3TNC01NVWzWCzau+++69Nu0KBBmk6n0zZs2JDjGhf/n1555RUN0BYtWpRnm4s/79l/NrI/pz///NPndQG0mTNn5rheRkZGjn0PPfSQFhgYqGVmZmqapmkul0urUaOGVr16dS05OTnXeDRN0wYMGKBVqlRJc7vdnn2bN2/WAG327Nk5HkcIIUTpI/0x6Y/5qz928fVLTEzMs02zZs20ChUqaElJSZ59W7du1XQ6nTZo0CDPvtDQUO2xxx7L8zpbtmzxxCxEaSLT94QoAu+//z7Lli3z+frll1982jRq1IgJEybwySef0LNnT86cOcNnn32Waw2BQYMG+RSr7t+/P9HR0fz8888AxMXFsW/fPu677z6SkpI4c+YMZ86cIT09ne7du7Ny5UpUVfW55sMPP1zo59O9e3fPXRuAtm3bAnDnnXf6xHVx/8GDB4ssro4dO5KUlERqamqh481N165dWbZsGQsWLODhhx/GaDSSnp5e4HmpqalXXCj8ySefJDw8nAkTJhSqfWhoKKNGjWLx4sW5TkEryNy5c2nVqpXnbmNwcDC33HKLzxQ+VVX5/vvv6dOnT651Ni5OF/j2229p2rQp/fr1y7PN5TKbzQwdOjTH/ot3lyFrqPqZM2fo2LEjGRkZ7NmzB4AtW7YQHx/PqFGjCAsLyzOeQYMGceLECf7880/Pvrlz5xIQEMCdd955RXELIYS4Pkl/TPpjUPL9sfwkJCQQFxfHkCFDiIiI8Oxv0qQJPXr08PwsAYSFhbFu3TpOnDiRZ5wAS5cu9ZlaKcT1TqbvCVEE2rRpU6jCms899xzz589n/fr1TJo0iQYNGuTarnbt2j7biqIQGxvrqRewb98+gHwLWqekpBAeHu7Zzm01mrxUq1bNZ/viH8GqVavmuj85OfmK47r0sS4eS05OJiQkpNAxX6pixYqe6WL9+/dn0qRJ9OjRg3379uVbWDMkJITz589f0WNe7NSMGzeOLVu2+DzPvGQfZv7DDz8U+rHOnTvHzz//zMiRI9m/f79nf4cOHfj222/Zu3cvderUITExkdTUVBo1apTv9Q4cOFDkSZzKlStjMply7N+5cydjx47ljz/+yNHZvVgT4cCBAwAFxt2jRw+io6OZO3cu3bt3R1VVvvrqK/r27SurEAohRBkj/THpj0HJ9scKcvjwYQDq1q2b41j9+vVZunSpp+D9W2+9xeDBg6latSotW7akd+/eDBo0iJo1awJZPztPP/00U6dOZe7cuXTs2JHbbruNgQMHytQ9cV2TpJQQJejgwYOejsLFQpVX4uLdrSlTptCsWbNc2wQFBflsZx+dUhC9Xn9Z+7ULNRGuJK6CrllU+vfvz0svvcQPP/zAQw89lGe7evXqERcXh8PhyDWhUpCLnZoJEyYwbdq0Attf7DiNHz/+su7OLViwALvdzjvvvMM777yT4/jcuXMLfYewsPIaMZVbgXLI/Wfu3LlzdO7cmZCQEF599VVq1aqFxWJh8+bNjB49Osed24Lo9Xruu+8+Pv74Yz744ANWr17NiRMnGDhw4GVdRwghRNkh/THpj13qSvtjRenuu++mY8eOfPfdd/z2229MmTKFN998k0WLFtGrVy8A3nnnHYYMGcIPP/zAb7/9xhNPPMHkyZP5559/qFKlil/iFuJqSVJKiBKiqipDhgwhJCSEUaNGMWnSJPr3788dd9yRo+3FjtJFmqaxf/9+mjRpAngLS4aEhHDTTTcVf/CFVFxxXen0sexsNhtAgauT9OnTh7Vr1/Ltt98yYMCAy36c7J2a/O5QZjdq1CimTZvGhAkTckxVy8vcuXNp1KgR48aNy3Hsf//7H/PmzWPChAmUL1+ekJAQduzYke/1atWqVWCbi3caL10x5+JdwMJYsWIFSUlJLFq0iE6dOnn2x8fH54gHYMeOHQX+LA0aNIh33nmHJUuW8Msvv1C+fHl69uxZ6JiEEEKUHdIfu3LSH7t81atXB+Dff//NcWzPnj2UK1cOq9Xq2RcdHc2jjz7Ko48+yunTp2nRogUTJ070JKUAGjduTOPGjRk7dixr1qyhQ4cOzJw5k9dff71IYhaipElNKSFKyNSpU1mzZg0fffQRr732Gu3bt+eRRx7JsUoMwOeff+4zZHnhwoUkJCR4/iC1bNmSWrVq8fbbb5OWlpbj/MTExOJ7IvkorrisVmuBSwdfdObMmVzv6n3yyScABQ7rf/jhh4mOjuaZZ55h7969OY6fPn26wD/6F+sgvfrqq4WK+WLH6YcffiAuLq7A9kePHmXlypXcfffd9O/fP8fX0KFD2b9/P+vWrUOn03H77bezZMkSNm7cmONaF1+rO++8k61bt/Ldd9/l2eZiJ3flypWeY263m48++qhQzxO8d2Kz/x85HA4++OADn3YtWrSgRo0aTJs2Lcf//aX/v02aNKFJkyZ88sknfPvtt9x777251gYRQgghpD8m/bG8XG5/rDCio6Np1qwZn332mc9rt2PHDn777Td69+4NZPWnLk3UVahQgUqVKmG324GsOlsul8unTePGjdHpdJ42QlyPpNcuRBH45ZdfPAWas2vfvj01a9Zk9+7dvPzyywwZMoQ+ffoAMGfOHJo1a8ajjz7KN99843NeREQEN954I0OHDuXUqVNMmzaN2NhYHnjgAQB0Oh2ffPIJvXr1omHDhgwdOpTKlStz/Phx/vzzT0JCQliyZEnxP/FLFFdcLVu25Pfff2fq1KlUqlSJGjVqeIp6XurLL79k5syZ3H777dSsWZPz58+zdOlSli1bRp8+fejWrVu+jxUeHs53331H7969adasGQMHDqRly5YAbN68ma+++op27drle43Q0FCefPLJy5o+d3GY+datW33umOVm3rx5aJrGbbfdluvx3r17YzAYmDt3Lm3btmXSpEn89ttvdO7cmQcffJD69euTkJDAggUL+PvvvwkLC+O5555j4cKF3HXXXQwbNoyWLVty9uxZFi9ezMyZM2natCkNGzbkhhtuYMyYMZw9e5aIiAjmz5+fo4OUn/bt2xMeHs7gwYN54oknUBSFL774IkfHVafT8eGHH9KnTx+aNWvG0KFDiY6OZs+ePezcuZOlS5f6tB80aBDPPvssgEzdE0KIMkr6YxRrXNIfy9vUqVMJDAz02afT6XjxxReZMmUKvXr1ol27dgwfPhybzcaMGTMIDQ1l/PjxQNbCL1WqVKF///40bdqUoKAgfv/9dzZs2OAp0/DHH38wcuRI7rrrLurUqYPL5eKLL75Ar9fL4i7i+uaPJf+EKC3yW4KYC0vSu1wurXXr1lqVKlW0c+fO+Zw/ffp0DdC+/vprTdO8y9N+9dVX2pgxY7QKFSpoAQEB2i233KIdPnw4x+Nv2bJFu+OOO7TIyEjNbDZr1atX1+6++25t+fLlnjb5LVWb1xLEly5Hm9tSutnjvXRp2quJ6+Jrmn0J5D179midOnXSAgICNCDf5Yg3bNig3XXXXVq1atU0s9msWa1WrUWLFtrUqVN9lnsuyIkTJ7SnnnpKq1OnjmaxWLTAwECtZcuW2sSJE7WUlBRPu+xLEGeXnJyshYaG5rsE8aUuviYFLUHcuHFjrVq1avm26dKli1ahQgXPcz58+LA2aNAgrXz58prZbNZq1qypPfbYY5rdbveck5SUpI0cOVKrXLmyZjKZtCpVqmiDBw/Wzpw542lz4MAB7aabbtLMZrNWsWJF7cUXX9SWLVumAdqff/5Z4OuiaZq2evVq7YYbbtACAgK0SpUqac8//7y2dOnSHNfQNE37+++/tR49emjBwcGa1WrVmjRpos2YMSPHNRMSEjS9Xq/VqVMn39dFCCFE6SP9MemP+aM/lr1tbl96vd7T7vfff9c6dOigBQQEaCEhIVqfPn20Xbt2eY7b7Xbtueee05o2berp8zRt2lT74IMPPG0OHjyoDRs2TKtVq5ZmsVi0iIgIrWvXrtrvv/9e8AspxDVM0bQirl4nhLhiK1asoGvXrixYsID+/fv7OxwhrhtnzpwhOjqaV155hZdfftnf4QghhLiOSX9MCCFKjtSUEkIIcd2bM2cObreb+++/39+hCCGEEEIIIQpJakoJIYS4bv3xxx/s2rWLiRMncvvttxMTE+PvkIQQQgghhBCFJEkpIYQQ161XX33VsxzyjBkz/B2OEEIIIYQQ4jJITSkhhBBCCCGEEEIIUeKkppQQQgghhBBCCCGEKHGSlBJCCCGEEEIIIYQQJa7M1ZRSVZUTJ04QHByMoij+DkcIIYQQ1zhN0zh//jyVKlVCpyu79/OkDyWEEEKIwips/6nMJaVOnDhB1apV/R2GEEIIIa4zR48epUqVKv4Ow2+kDyWEEEKIy1VQ/6nMJaWCg4OBrBcmJCTEz9EIIYQQ16/09HQqVaoEZCUsrFarnyMqHqmpqVStWtXThyirpA8lhBBCXD3pP/kqc0mpi8PNQ0JCpEMlhBBCXAW9Xu/5PiQkpNR2qi4q61PWpA8lhBBCXD3pP/kqu4URhBBCCCGEEEIIIYTfSFJKCCGEEEIIIYQQQpQ4SUoJIYQQQgghhBBCiBJX5mpKFZbb7cbpdPo7DCGKnNFo9JnHLIQQQgghhBBC+IMkpS6haRonT57k3Llz/g5FiGITFhZGVFRUmS/aK4S4OkajkXHjxnm+F0IIIYQQ+ZP+ky9F0zTN30GUpNTUVEJDQ0lJScl15ZiEhATOnTtHhQoVCAwMlA/tolTRNI2MjAxOnz5NWFgY0dHR/g5JCCGueQX1HcoKeR2EEEIIUViF7TfISKls3G63JyEVGRnp73CEKBYBAQEAnD59mgoVKshUPiGEEEIIIYQQfiFJqWwu1pAKDAz0cyRCFK+LP+NOp1OSUkKIK6aqKrt37wagfv366HSyfooQQgghRH6k/+RLklK5kCl7orSTn3EhRFGw2Ww0atQIgLS0NKxWq58jEkIIIYS4tkn/yVfZTskJIYQQQgghhBBCCL+QpJTIU0xMDNOmTSt0+xUrVqAoiqxcKIQQQgghhBBCiAJJUqoUUBQl36/x48df0XU3bNjAgw8+WOj27du3JyEhgdDQ0Ct6vCtRr149zGYzJ0+eLLHHFEIIIYQQQgghxNWTpFQpkJCQ4PmaNm0aISEhPvueffZZT1tN03C5XIW6bvny5S+r6LvJZCIqKqrE6hX9/fff2Gw2+vfvz2effVYij5mfi4XyhRBCCCGEEEIIUTBJSpUCUVFRnq/Q0FAURfFs79mzh+DgYH755RdatmyJ2Wzm77//5sCBA/Tt25eKFSsSFBRE69at+f33332ue+n0PUVR+OSTT+jXrx+BgYHUrl2bxYsXe45fOn1vzpw5hIWFsXTpUurXr09QUBA333wzCQkJnnNcLhdPPPEEYWFhREZGMnr0aAYPHsztt99e4POeNWsW9913H/fffz+ffvppjuPHjh1jwIABREREYLVaadWqFevWrfMcX7JkCa1bt8ZisVCuXDn69evn81y///57n+uFhYUxZ84cAA4dOoSiKHz99dd07twZi8XC3LlzSUpKYsCAAVSuXJnAwEAaN27MV1995XMdVVV56623iI2NxWw2U61aNSZOnAhAt27dGDlypE/7xMRETCYTy5cvL/A1EUKIskbTNDTVgeZKR1MLd9NFXJs0VzrupBVoqtzkEUIIIcoKWX2vAJozBfX8dr89vi64MYrx6qfDvfDCC7z99tvUrFmT8PBwjh49Su/evZk4cSJms5nPP/+cPn368O+//1KtWrU8rzNhwgTeeustpkyZwowZM/jPf/7D4cOHiYiIyLV9RkYGb7/9Nl988QU6nY6BAwfy7LPPMnfuXADefPNN5s6dy+zZs6lfvz7Tp0/n+++/p2vXrvk+n/Pnz7NgwQLWrVtHvXr1SElJYdWqVXTs2BHIWsWgc+fOVK5cmcWLFxMVFcXmzZtRVRWAn376iX79+vHSSy/x+eef43A4+Pnnn6/odX3nnXdo3rw5FouFzMxMWrZsyejRowkJCeGnn37i/vvvp1atWrRp0waAMWPG8PHHH/Puu+9y4403kpCQwJ49ewAYMWIEI0eO5J133sFsNgPw5ZdfUrlyZbp163bZ8QkhxLVKc6bgPvM77jO/odkOZyUiNCdk+1fTXD77crTRXKC5Pdc0t1qCoeKtfnxWJWflypVMmTKFTZs2kZCQwHfffVeoGzoAq1evpnPnzjRq1Ii4uLhijbMw3Oc24NjxCGpqHGhuLDduRB/a0t9hCSGEEKIESFKqAOr57WSu7ei3x7e0W4U+4sarvs6rr75Kjx49PNsRERE0bdrUs/3aa6/x3XffsXjx4hwjdbIbMmQIAwYMAGDSpEn897//Zf369dx88825tnc6ncycOZNatWoBMHLkSF599VXP8RkzZjBmzBjPKKX33nuvUMmh+fPnU7t2bRo2bAjAvffey6xZszxJqXnz5pGYmMiGDRs8CbPY2FjP+RMnTuTee+9lwoQJnn3ZX4/CGjVqFHfccYfPvuzTJR9//HGWLl3KN998Q5s2bTh//jzTp0/nvffeY/DgwQDUqlWLG2/M+j++4447GDlyJD/88AN33303kDXibMiQISU2LVIIIQrLaDR63vOMRmO+bTVNQ0vbiev0z7hP/4yavDorqVSUtLIzwiY9PZ2mTZsybNiwHH+H8nPu3DkGDRpE9+7dOXXqVDFGWHiKMQI1ZZNnWz27RpJSQgghSq3L6T+VBZKUKiNatWrls52Wlsb48eP56aefSEhIwOVyYbPZOHLkSL7XadKkied7q9VKSEgIp0+fzrN9YGCgJyEFEB0d7WmfkpLCqVOnPCOIAPR6PS1btvSMaMrLp59+ysCBAz3bAwcOpHPnzsyYMYPg4GDi4uJo3rx5niO44uLieOCBB/J9jMK49HV1u91MmjSJb775huPHj+NwOLDb7Z7aXLt378Zut9O9e/dcr2exWDzTEe+++242b97Mjh07fKZJCiHEtcJkMjFlypQ8j2uu87jPLMed+Avu0z+jZR4r3oCKOsl1DevVqxe9evW67PMefvhh7rvvPvR6fY5p6v6iBNZEMVdEs2clydzJqzHWeNzPUQkhhBDFo6D+U1kjSakywmq1+mw/++yzLFu2jLfffpvY2FgCAgLo378/Docj3+tcmslVFCXfBFJu7TVNu8zofe3atYt//vmH9evXM3r0aM9+t9vN/PnzeeCBBwgICMj3GgUdzy3O3AqZX/q6TpkyhenTpzNt2jQaN26M1Wpl1KhRnte1oMeFrCl8zZo149ixY8yePZtu3bpRvXr1As8TQgh/yxoNtRt34i+4Tv+MenZVwaOXdGZ0IS1AH4CiM4JiAMUIOiMoxgv7jJfsu6TNhe91wZc/4rUsmT17NgcPHuTLL7/k9ddf93c4HoqioAtrj/vUdwCoyWv8HJEQQgghSookpQqgC26Mpd0qvz5+cVi9ejVDhgzxTJtLS0vj0KFDxfJYeQkNDaVixYps2LCBTp06AVmJpc2bN9OsWbM8z5s1axadOnXi/fff99k/e/ZsZs2axQMPPECTJk345JNPOHv2bK6jpZo0acLy5csZOnRoro9Rvnx5n4Ls+/btIyMjo8DntHr1avr27esZxaWqKnv37qVBgwYA1K5dm4CAAJYvX86IESNyvUbjxo1p1aoVH3/8MfPmzeO9994r8HGFEMIfVFXl8ME9uJPXUNm0CS3pFzTb4QLPUwJqoK/QO+srsguKvvArvYors2/fPl544QVWrVqFwVC47p/dbsdut3u2U1NTiyW24zaVdzOfZL+zLwepyXT1aTrbjqILqFosjyeEEEL4k6qqnhlK1apVQ6cr2+vPSVKqAIoxtEhqOl1rateuzaJFi+jTpw+KovDyyy8XOGWuODz++ONMnjyZ2NhY6tWrx4wZM0hOTs6zfpLT6eSLL77g1VdfpVGjRj7HRowYwdSpU9m5cycDBgxg0qRJ3H777UyePJno6Gi2bNlCpUqVaNeuHePGjaN79+7UqlWLe++9F5fLxc8//+wZedWtWzfee+892rVrh9vtZvTo0YWa71u7dm0WLlzImjVrCA8PZ+rUqZw6dcqTlLJYLIwePZrnn38ek8lEhw4dSExMZOfOnQwfPtznuYwcORKr1eqzKqAQQvibprpQUzbiPrOc1GO/UbPbSgBOLQSrJY+TdCZ0EZ0xVOiNvnwvFGsdqZNXgtxuN/fddx8TJkygTp06hT5v8uTJPrUXi0umW+OdxKZA1ki3vVptOiavQRdwT7E/thBCCFHSbDYbNWrUALIGh1w6+6asKdspuTJs6tSphIeH0759e/r06UPPnj1p0aJFiccxevRoBgwYwKBBg2jXrh1BQUH07NkTiyX3TzaLFy8mKSkp10RN/fr1qV+/PrNmzcJkMvHbb79RoUIFevfuTePGjXnjjTfQ6/UAdOnShQULFrB48WKaNWtGt27dWL9+veda77zzDlWrVqVjx47cd999PPvss566UPkZO3YsLVq0oGfPnnTp0oWoqKgcqyG9/PLLPPPMM7zyyivUr1+fe+65J0ddrgEDBmAwGBgwYECer4UQQpQETdNQz+/AGT+dzA23kbEsksw17XDuHYt6dmWe5ykB1TBUexhzq8UE9kgioO1vGGuMQhdUVxJSJez8+fNs3LiRkSNHYjAYMBgMvPrqq2zduhWDwcAff/yR63ljxowhJSXF83X06NFiia96oA5Dth+Jg1oN3DKFTwghhCgTFO1qC/xcZ1JTUwkNDSUlJYWQkBCfY5mZmcTHx1OjRg1JBPiJqqrUr1+fu+++m9dee83f4fjNoUOHqFWrFhs2bCiWZKH8rAsh8qNmHMoqUJ60HDXpD08B6kulZ0LF/lnfn/rWQHClThjK90JfoTdKUP1Sk3zKr+9wLVAUhe+++y7HTZCLVFVl165dPvs++OAD/vjjDxYuXEiNGjUKdZe2OF+H2N9SOZCeNWK7v+5bPo/8kIAbNxbpYwghhBDXgvT0dIKCgoDSPVKqsP0Gmb4n/Orw4cP89ttvdO7cGbvdznvvvUd8fDz33Xefv0PzC6fTSVJSEmPHjuWGG27wy+g1IUTZo9kTcSf94UlEaRkHC3WeElgLOABAYPejBIRGFWOUIru0tDT279/v2Y6PjycuLo6IiAiqVavGmDFjOH78OJ9//jk6nS7HlPcKFSpgsVhy7PeXWKvOk5SK12JQU+PQXOkohtLZURdCCCFEFklKCb/S6XTMmTOHZ599Fk3TaNSoEb///jv169f3d2h+sXr1arp27UqdOnVYuHChv8MRQpRimus8zgNTcJ/6AfX8tkKdo5ij0ZXrjj6yO/py3UGNALLu9CmG4GKMVlxq48aNdO3a1bP99NNPAzB48GDmzJlDQkKCp4jq9aCW1VtR4qBWEzQ3asoG9JFd/BeUEEIIIYqdJKWEX1WtWpXVq1f7O4xrRpcuXShjM2qFEH7gTl6HPe6+gkdEGcLQR3ZBfyERpQTV852Sl55evIGKPBX092LOnDn5nj9+/HjGjx9ftEFdhdggb1IqmXDOamFUPLtaklJCCCFEKSdJKSGEEKKM0DQ3zv1v4Nw3DjR3zgY6C7qIGz0joXShLVAUfckHKsqcWlbfn7N4rQblpdi5EEIIUepJUkoIIYQoA1TbEexx9+dYMU+xVMVQZRD6yO7owtuh6Au/+IHBYODRRx/1fC/ElYq1+i4IfVCrQctzf6JpKooii0ULIYQoPaT/5EteASGEEKKUc534Bvv2h8B1zme/vtIAzI0+QDGGXdF1zWYz77///tUHKMq8mlYdCnBxQuJBaoBzEVraHpTgBv4MTQghhChS0n/yJbeehBBCiFJKc53HvnUo9i33+CakDMGYmn6OudncK05ICVGULHqFygHeemXxWg0A3DKFTwghhCjVJCklhBBClELuc+uxrWqO69gcn/26sBsI6BiHscr9vkXLr4CmaSQmJpKYmCiLNIirFputrtQBrSYAqiSlhBBClDLSf/IlSSkhhBCiFNE0N479k8hc0wEt40C2IzqMsS9jabcSXWDNInmsjIwMKlSoQIUKFcjIyCiSa4qyq1a2ulIHPSOlZIVeIYQQpYv0n3xJUkp4dOnShVGjRnm2Y2JimDZtWr7nKIrC999/f9WPXVTXEUKIsky1HSXzn+44/30JNJdnvxJQDUu7FZjqvoqiM/oxQiHylr3Y+SmiSNcC0dL3ojnO+DEqIYQQQhQnSUqVAn369OHmm2/O9diqVatQFIVt27Zd9nU3bNjAgw8+eLXh+Rg/fjzNmjXLsT8hIYFevXoV6WPlxWazERERQbly5bDb7SXymEIIUdxcCQuxrWyCevYvn/36SvcS0HEr+oiOfopMiMKpFeTbLfXWlVrrj3CEEEIIUQIkKVUKDB8+nGXLlnHs2LEcx2bPnk2rVq1o0qTJZV+3fPnyBAYGFkWIBYqKisJsNpfIY3377bc0bNiQevXq+X10lqZpuFyughsKIUodNfM4rtO/4D63AdV2BM2deUXX0Vxp2LcOx775Lt9i5vogTE0/w9xsnhQzF9eF7COlAA4SA4AqU/iEEEKIUkuSUqXArbfeSvny5ZkzZ47P/rS0NBYsWMDw4cNJSkpiwIABVK5cmcDAQBo3bsxXX32V73Uvnb63b98+OnXqhMVioUGDBixbtizHOaNHj6ZOnToEBgZSs2ZNXn75ZZxOJwBz5sxhwoQJbN26FUVRUBTFE/Ol0/e2b99Ot27dCAgIIDIykgcffJC0tDTP8SFDhnD77bfz9ttvEx0dTWRkJI899pjnsfIza9YsBg4cyMCBA5k1a1aO4zt37uTWW28lJCSE4OBgOnbsyIED3rosn376KQ0bNsRsNhMdHc3IkSMBOHToEIqiEBcX52l77tw5FEVhxYoVAKxYsQJFUfjll19o2bIlZrOZv//+mwMHDtC3b18qVqxIUFAQrVu35vfff/eJy263M3r0aKpWrYrZbCY2NpZZs2ahaRqxsbG8/fbbPu3j4uJQFIX9+/cX+JoIIUqOpjqw7xyFbXkV7Bt6k7m6DbY/qpPxawDpS0PJWFEH25qOZG7qj33HYzj2vYrz8P9wnfwe99k1qOkH0FxZ74fucxux/d0C17FPfR5DF9b2QjHzQVddzFyIklIrW6FzgIMXip3LCnxCCCFE6WXwdwDXuhSnxvYUt98ev3GonlBj/h8oDAYDgwYNYs6cObz00kueDyALFizA7XYzYMAA0tLSaNmyJaNHjyYkJISffvqJ+++/n1q1atGmTZsC41BVlTvuuIOKFSuybt06UlJSfOpPXRQcHMycOXOoVKkS27dv54EHHiA4OJjnn3+ee+65hx07dvDrr796Ei6hoaE5rpGenk7Pnj1p164dGzZs4PTp04wYMYKRI0f6JN7+/PNPoqOj+fPPP9m/fz/33HMPzZo144EHHsjzeRw4cIC1a9eyaNEiNE3jqaee4vDhw1SvXh2A48eP06lTJ7p06cIff/xBSEgIq1ev9oxm+vDDD3n66ad544036NWrFykpKaxeffl3cF944QXefvttatasSXh4OEePHqV3795MnDgRs9nM559/Tp8+ffj333+pVq0aAIMGDWLt2rX897//pWnTpsTHx3PmzBkURWHYsGHMnj2bZ5991vMYs2fPplOnTsTGxl52fEKI4qFmxGPffA9qyobcG7hS0VypaOn7Cr6YPhBUO2jZ/0YpGGNfxFh7nNSOEtedEKNCeZNCoiNrJaKLxc7VcxvQVAeKzuTP8IQQQghRDCQpVYDtKW46rkoruGExWdUxiBvLFfzfNGzYMKZMmcJff/1Fly5dgKykxJ133kloaCihoaE+CYvHH3+cpUuX8s033xQqKfX777+zZ88eli5dSqVKlQCYNGlSjjpQY8eO9XwfExPDs88+y/z583n++ecJCAggKCgIg8FAVFRUno81b948MjMz+fzzz7FarQC899579OnThzfffJOKFSsCEB4eznvvvYder6devXrccsstLF++PN+k1KeffkqvXr0IDw8HoGfPnsyePZvx48cD8P777xMaGsr8+fMxGrM+0NWpU8dz/uuvv84zzzzDk08+6dnXunXrAl+/S7366qv06NHDsx0REUHTpk0926+99hrfffcdixcvZuTIkezdu5dvvvmGZcuWcdNNNwFQs6Z39awhQ4bwyiuvsH79etq0aYPT6WTevHk5Rk8JIfzHlbAI+7Zh4Eopmgu6fVdrUSxVMTf7En1kp6K5vhB+UMuqI9GRlWi9mJRCzURN2YI+vK0fIxNCCCFEcZCkVClRr1492rdvz6effkqXLl3Yv38/q1at4tVXXwXA7XYzadIkvvnmG44fP47D4cButxe6ZtTu3bupWrWqJyEF0K5duxztvv76a/773/9y4MAB0tLScLlchISEXNZz2b17N02bNvUkpAA6dOiAqqr8+++/nqRUw4YN0eu9Q/2jo6PZvn17ntd1u9189tlnTJ8+3bNv4MCBPPvss7zyyivodDri4uLo2LGjJyGV3enTpzlx4gTdu3e/rOeTm1atWvlsp6WlMX78eH766ScSEhJwuVzYbDaOHDkCZE3F0+v1dO7cOdfrVapUiVtuuYVPP/2UNm3asGTJEux2O3fddddVxyqEuDqa245j97O4Dr/ne8AYibnRe2AMR7Of8n45sv7F830ioOb7GProuzE3noliDC++J5ILg8HA4MGDPd8LcbVig3T8k5yVlLpY6BxATV4jSSkhhBClgvSffMkrUIoMHz6cxx9/nPfff5/Zs2dTq1YtTxJjypQpTJ8+nWnTptG4cWOsViujRo3C4XAU2eOvXbuW//znP0yYMIGePXt6Rhy98847RfYY2V2aOFIUBVXN+4Pb0qVLOX78OPfcc4/PfrfbzfLly+nRowcBAQF5np/fMQCdLqtEm6Zpnn151bjKnnADePbZZ1m2bBlvv/02sbGxBAQE0L9/f8//T0GPDTBixAjuv/9+3n33XWbPns0999xTYoXqhRC5U9MPYN98N2rqZp/9uvAbMTf/Cl1AlQKvoWlucCT5JKw0++ms79029OV6oK9wi19qR5nN5hz1DIW4GrFWPZD1t/MoVXBoRkyKE3fyGow85d/ghBBCiCIg/SdfkpQqQONQPas6Bvn18Qvr7rvv5sknn2TevHl8/vnnPPLII54PKatXr6Zv374MHDgQyKoRtXfvXho0aFCoa9evX5+jR4+SkJBAdHQ0AP/8849PmzVr1lC9enVeeuklz77Dhw/7tDGZTLjd+dfoql+/PnPmzCE9Pd2TvFm9ejU6nY66desWKt7czJo1i3vvvdcnPoCJEycya9YsevToQZMmTfjss89wOp05kl7BwcHExMSwfPlyunbtmuP65cuXByAhIYHmzZsD+BQ9z8/q1asZMmQI/fr1A7JGTh06dMhzvHHjxqiqyl9//eWZvnep3r17Y7Va+fDDD/n1119ZuXJloR5bCFE8XAkLsG8bAa5Un/3GWmMw1nkVRVe4P8GKogdzBRRzBaBxMUQqxLWjVrYV+FT0HKYatTmAmrwaTdOkcL8QQghRykhSqgChRqVQNZ2uBUFBQdxzzz2MGTOG1NRUhgwZ4jlWu3ZtFi5cyJo1awgPD2fq1KmcOnWq0Empm266iTp16jB48GCmTJlCampqjuRO7dq1OXLkCPPnz6d169b89NNPfPfddz5tYmJiiI+PJy4ujipVqhAcHIzZbPZp85///Idx48YxePBgxo8fT2JiIo8//jj333+/Z+re5UpMTGTJkiUsXryYRo0a+RwbNGgQ/fr14+zZs4wcOZIZM2Zw7733MmbMGEJDQ/nnn39o06YNdevWZfz48Tz88MNUqFCBXr16cf78eVavXs3jjz9OQEAAN9xwA2+88QY1atTg9OnTPjW28lO7dm0WLVpEnz59UBSFl19+2WfUV0xMDIMHD2bYsGGeQueHDx/m9OnT3H333QDo9XqGDBnCmDFjqF27dq7TK4UQxU9zZ+LY9TSuIx/6HjCVx9zsCwzle/onsGKgaRoZGVm1rQIDAyVhIK5abJDvwtAHtZrUVg6g2RPQbIdRAmP8E5gQQghRRKT/5EtXcBNxPRk+fDjJycn07NnTp/7T2LFjadGiBT179qRLly5ERUVx++23F/q6Op2O7777DpvNRps2bRgxYgQTJ070aXPbbbfx1FNPMXLkSJo1a8aaNWt4+eWXfdrceeed3HzzzXTt2pXy5cvz1Vdf5XiswMBAli5dytmzZ2ndujX9+/ene/fuvPfeeznaFtbFoum51YPq3r07AQEBfPnll0RGRvLHH3+QlpZG586dadmyJR9//LFn1NTgwYOZNm0aH3zwAQ0bNuTWW29l3z7vKlmffvopLpeLli1bMmrUKF5//fVCxTd16lTCw8Np3749ffr0oWfPnrRo0cKnzYcffkj//v159NFHqVevHg888ADp6ek+bYYPH47D4WDo0KGX+xIJIYqAmr6PzDXtciSkdBGdCegYV6oSUgAZGRkEBQURFBTk6VwJcTWyj5QCOKjFeL5Xky9/tVshhBDiWiP9J1+Klr0AThmQmppKaGgoKSkpOQpwZ2ZmEh8fT40aNbBYLH6KUIgrt2rVKrp3787Ro0fzHVUmP+tCFD3X8a+wb38Q3NlXbFUwxr6Esfa4Qk/Xu56kp6cTFJQ1xT0tLS1HvbzSIr++Q1lSEq+DpmmE/ZhCqitr+xH9J0zRPweAofqjmBu9XyyPK4QQQpQU6T/5kpFSQpQCdrudY8eOMX78eO66664rnuYohLh8mtuGfftD2OPu801ImSpgafsbprqvlcqEFMCaMy7P9wuOO9iV6sallql7XaKIKYpCLau3nuZBQzPP92ryGj9EJIQQQojiVDp7yUKUMV999RXDhw+nWbNmfP755/4OR4gyQ037N2t1vfPbfPbrIrtibjYXnSXaT5EVv/nHHPxnrTcJN3RTBlgUzDqoH6ynSYiOJqH6rK8QPRUtch9MFE5skI4tKVmLosRrNTz71dRtaK7zKIZgf4UmhBBCiCImSSkhSoEhQ4b4FLYXQuRNtR1DPbcOzXEaFBPoTCg6M+hMoDOjXPjXs62YQG8GxbedO2Eh9h0Pgzt7bTcFY+1XMNZ+OWvVvFLq00N2RmyxkVsBALsKcSlu4lLccNTp2V/epHgSVE1CsxJWDYL1WPRlu7inyCl7Xal4Zzhugw69ogIq6rl16MvlvgqtEEIIIa4/kpQSQghRammqAzVlC+q5tbiT16Imr0XLPFosj6WYK2JuNg99uW7Fcv1rxXsH7Dy+zXbZ5yU6NJYnulie6J3ypwPqBOmoE6Qj3KQQalQINWT9G2a8sH3xe4N3WxJZpVtstqSUU9NxnMpUI+v31p28RpJSQgghRCkiSSkhhBClhpqZgJq81puEStkIqr3YH1cX2R1zsy/RWaKK/bH86c29mbywMzPXY2s6BbHfHcC2FDfbUt1sS3Fz0p5/fSkV2JOmsidNvaw4zDo8Cawwkzdh9VhNE13LGy/rWuLak2MFPnMnqjnmAqCelRX4hBBCiNJEklJCCCGuS5rqRE3dipq8Fve5C6OgbIdKOAodxjrjMca+WKqn62maxiu7M3n9X98E3/N1AznYvz8AzSPNtLOYfI6ftqtsT3GzPdXNthSVbaludqa6yby8HFQOdhVO2zVO2zXINnvyjkqSkCoNYoN8f5cOWTrDhaSU+9w/aJq7VP++CSGEKN30ej39L/Sf9Hr5eyZJKSGEENcNNW0vrpOLcCf+inpuPaiFn0ammKPQhbVDF94OfXh7dEH1QHOhqY6s0VSqA+3Cv6h20Bxo7qx/Ue0+7VDtoOjQl+uJLrh+MT5j/9M0jWe2Z/LuAd+E1MQGFl6sa4EFC/I8t4JZR/cKOrpX8CaL3JrG/jTVM5pqW4qb45kaKc6sr3NODecVLuAXapRpfaVBpQsF8+0XkpcH9U28B12paOd3oYQ09k9wQgghxFWyWCwsyKf/VNZIUkoIIcQ1S9M01NQ43CcX4Tr5HVrazsKdqOjRhTRDF94e/YVElBJQHUXJmbSQNEbeVE3jkTgbHx1y+Oyf3iSAJ2qZr+iaekWhbrCeusF67qqc87imaWSqeBJU2ZNVKU6NFJeW+zGXRkWz/G+WBjpFoZZVx67zWVmpeK26z3F38mp0kpQSQgghSgVJSgkhhLimaJqKmrw2a0TUyUWFm5JnqoA+/MIoqLB26MJaoegDiz3W0sylagzdnMGX2VbQU4CPmwcwPObKElKFoSgKAXoI0CtEWYrtYcQ1LjZbUupAZiAYI8B5FgA1eQ1Uf9if4QkhhBCiiEhSSpRaMTExjBo1ilGjRl3WeUlJSdSvX5/169cTExNTZPG88MILpKenM2PGjCK7phClhaY6cCetwH1yEe5T36PZT+XbXgmshb58T+8oqMCauY6CElfG7tYYsCGD7xK8CSm9Al+0DGRAVW/dqPT0dIKCggBIS0vDarWWeKyidKpl1QNZKzUeSFfRRbVDTfwJyFqBTwghhLheSf/Jl67gJuJ6MGTIEBRF8XxFRkZy8803s23btiJ7jPHjx9OsWbNCtcsey8WvevXqFVksxWnixIn07dvXk5DaunUrAwYMoGrVqgQEBFC/fn2mT5+e47y5c+fStGlTAgMDiY6OZtiwYSQlJXmOP/vss3z22WccPHiwpJ6KENc0zZ2B6+R32OMGkbGsIvb1PXEd+V+eCSldcBOMtccT0HErAV32YW70PoYqA9FZa0lCqgjZ3Bq3r0v3SUiZdPBtG6tPQkqI4hQb5O2iprshMfgmz7aWcaDAxLUQQgghrg8yUqoUufnmm5k9ezYAJ0+eZOzYsdx6660cOXKkxGNp2LAhv//+u88+g+Ha/3HLyMhg1qxZLF261LNv06ZNVKhQgS+//JKqVauyZs0aHnzwQfR6PSNHjgRg9erVDBo0iHfffZc+ffpw/PhxHn74YR544AEWLVoEQLly5ejZsycffvghU6ZM8cvzE8LfNM2NO+FbXAlf4z79S4GFynVh7dBH9cMQ1Q+dNbaEoiy7zjs1bvsnnRVnXJ59AXr4rq2VnhVlZTtRcmpZfe+bHjJ3IDLbtjt5DYaofiUblBBCCCGKnIyUKkXMZjNRUVFERUXRrFkzXnjhBY4ePUpiYqKnzdGjR7n77rsJCwsjIiKCvn37cujQIc/xFStW0KZNG6xWK2FhYXTo0IHDhw8zZ84cJkyYwNatWz0jn+bMmZNnLAaDwRPLxa9y5cp5jsfExPDaa68xYMAArFYrlStX5v333/e5xpEjR+jbty9BQUGEhIRw9913c+qU753RJUuW0Lp1aywWC+XKlaNfP98OakZGBsOGDSM4OJhq1arx0Ucf5fsa/vzzz5jNZm644QbPvmHDhjF9+nQ6d+5MzZo1GThwIEOHDvUkmwDWrl1LTEwMTzzxBDVq1ODGG2/koYceYv369T7X79OnD/Pnz883BiFKI03TcCV8i21lY+xb7sF9clHuCSlFjy6yO6aG7xPQ/RgBHdZgqvWcJKRKQLJD5f9Wp/kkpIIM8Gv7IElIiRIXe0lS6qBSDxTvzS1VpvAJIYQQpYIkpQopPT09z6/MzMxCt7XZbIVqe7XS0tL48ssviY2NJTIy696i0+mkZ8+eBAcHs2rVKlavXk1QUBA333wzDocDl8vF7bffTufOndm2bRtr167lwQcfRFEU7rnnHp555hkaNmxIQkICCQkJ3HPPPVcV45QpU2jatClbtmzhhRde4Mknn2TZsmUAqKpK3759OXv2LH/99RfLli3j4MGDPo/5008/0a9fP3r37s2WLVtYvnw5bdq08XmMd955h1atWrFlyxYeffRRHnnkEf799988Y1q1ahUtW7YsMPaUlBQiIiI82+3atePo0aP8/PPPaJrGqVOnWLhwIb179/Y5r02bNhw7dswnEShEaaZpGq7EpWSubo19c3+0tN05G+nM6CvehqnpHAJvOkXADb9jjHkUnSWXpdlEsUi0q3T7O51/kt2efWFGheUdguhU7tof5SpKn2qBOvTZZuUesBnQhTT3bLvPrvZDVEIIIYQoatLTLKSLhchy07t3b3766SfPdoUKFcjIyMi1befOnVmxYoVnOyYmhjNnzuRop2naZcf4448/euJMT08nOjqaH3/8EZ0uK/f49ddfo6oqn3zyiaf+yuzZswkLC2PFihW0atWKlJQUbr31VmrVqgVA/fr1PdcPCgryjIAqyPbt23O8ZgMHDmTmzJme7Q4dOvDCCy8AUKdOHVavXs27775Ljx49WL58Odu3byc+Pp6qVasC8Pnnn9OwYUM2bNhA69atmThxIvfeey8TJkzwXLNp06Y+j9m7d28effRRAEaPHs27777Ln3/+Sd26dXON+/Dhw1SqVCnf57ZmzRq+/vprn//zDh06MHfuXO655x4yMzNxuVz06dMnx+ivi9c+fPhwkRZRF+Ja5D67Gse/L6KeXZnzoN6KvuJtGKL6oS/fC8WQ93usKF4nbCo3rU5j94WVzgDKmxSW3RhE01C9HyMTZZlRpxATqONA+oUV+NJVdOHtUVM2AKCmbkJzZ6LoZYlGIYQQ4nomI6VKka5duxIXF0dcXBzr16+nZ8+e9OrVi8OHDwNZBbv3799PcHAwQUFBBAUFERERQWZmJgcOHCAiIoIhQ4bQs2dP+vTpw/Tp00lISLiiWOrWreuJ5eLXq6++6tOmXbt2ObZ3784aRbF7926qVq3qSUgBNGjQgLCwME+buLg4unfvnm8cTZo08XyvKApRUVGcPn06z/Y2mw2LJe8O7o4dO+jbty/jxo3j//7v/zz7d+3axZNPPskrr7zCpk2b+PXXXzl06BAPP+y7ZHVAQABAnklLIUoDd8oWMtffQubaG3MmpHRmDDWeJrBrPJbm8zBE3yUJKT86lO6m4yrfhFQli8LKTpKQEv6Xva7U/nQVfXh770HVgZqyyQ9RCSGEEKIoyUipQkpLS8vzmF7v23HPL+lxcdTSRUU5jctqtRIb66278sknnxAaGsrHH3/M66+/TlpaGi1btmTu3Lk5zi1fvjyQNXLqiSee4Ndff+Xrr79m7NixLFu2zKfGUmGYTCafWIrDxQRPfoxG3zooiqKgqmoerbOKkScnJ+d6bNeuXXTv3p0HH3yQsWPH+hybPHkyHTp04LnnngOykmFWq5WOHTvy+uuvEx0dDcDZs2cB7+stRGmipu3Fsfdl3Anf5Dyo6DFUHY4x9mV0AVVKPjjhI9mhMu+Yk8n/ZnI80zsyNyZQx/IbrdS0Fi4hpdfrPdOUL/1bKMTVirXq+O3C9wfSskZKZedOXoM+okPJByaEEEJcBek/+ZKkVCFZrVa/t71ciqKg0+k8daxatGjB119/TYUKFQgJCcnzvObNm9O8eXPGjBlDu3btmDdvHjfccAMmkwm3253neZfrn3/+ybF9cbpg/fr1OXr0KEePHvWMltq1axfnzp2jQYMGQFbiZ/ny5QwdOrTIYmrevDlffvlljv07d+6kW7duDB48mIkTJ+Y4npGRkWN1wYtvMNmnYu7YsQOj0UjDhg2LLGYh/E21HcG571Vcx+aAdul7hIK+0gBMdSZIsXI/UzWNv864+OSQg0UnnGRekp+vE6Rj+Y1BVAko/CBqi8XiM5VZiKKUfaTUWadGir4S5oBqaLasVYWl2LkQQojrkfSffPl9+t77779PTEwMFouFtm3b5lit7FLTpk2jbt26BAQEULVqVZ566qkchcbLKrvdzsmTJzl58iS7d+/m8ccfJy0tjT59+gDwn//8h3LlytG3b19WrVpFfHw8K1as4IknnuDYsWPEx8czZswY1q5dy+HDh/ntt9/Yt2+fJ1EUExNDfHw8cXFxnDlzBrvdnmcsLpfLE8vFr0tXzlu9ejVvvfUWe/fu5f3332fBggU8+eSTANx00000btyY//znP2zevJn169czaNAgOnfuTKtWrQAYN24cX331FePGjWP37t1s376dN99886pew549e7Jz506f0VI7duyga9eu/N///R9PP/205/lkX9WwT58+LFq0iA8//JCDBw+yevVqnnjiCdq0aeNTo2rVqlV07NixUKO8hLjWafbT2HeOwraiNq6js3IkpPQVbyOgYxyW5nMlIXUJh6rx80knXxxxsCvVfUV1BAvruE1l4r+Z1F52nm5/pzPvWM6EVOMQHSs7Xl5CSojiFhvke/f4Yl2pi9zJq4v1d0cIIYQQxc+vI6W+/vprnn76aWbOnEnbtm2ZNm0aPXv25N9//6VChQo52s+bN48XXniBTz/9lPbt27N3716GDBmCoihMnTrVD8/g2vLrr796pokFBwdTr149FixYQJcuXQAIDAxk5cqVjB49mjvuuIPz589TuXJlunfvTkhICDabjT179vDZZ5+RlJREdHQ0jz32GA899BAAd955J4sWLaJr166cO3eO2bNnM2TIkFxj2blzpyeWi8xms08C8ZlnnmHjxo1MmDCBkJAQpk6dSs+ePYGsUV4//PADjz/+OJ06dUKn03HzzTczY8YMz/ldunRhwYIFvPbaa7zxxhuEhITQqVOnq3oNGzduTIsWLfjmm288z3vhwoUkJiby5Zdf+oyiql69umf65ZAhQzh//jzvvfcezzzzDGFhYXTr1i1Hkmz+/PmMHz/+qmIUwt805zmcB9/GGT8N3DlXC9VFdsVUdxL68Mub9lsWHLOpfBRv56NDDk7ZvR+mI00KN0bq6RhpoFM5A81D9Rh0Sj5Xyp9T1fjxpJNZhxz8cspFXpOWK5oVhlY38UIdC6HGK388IYpDrNU3Sbo/XaVpeAfcJ+Zn7XAkomUcQJGktxBCCHHdUjQ/3mJq27YtrVu35r333gNAVVWqVq3K448/7lmVLbuRI0eye/duli9f7tn3zDPPsG7dOv7+++9CPWZqaiqhoaGkpKTkmMKWmZlJfHw8NWrUyLfYtbh6MTExjBo1ilGjRvk7lBx++uknnnvuOXbs2JGjBtjV+OWXX3jmmWfYtm1bjql+JU1+1sXlUm3HUM/+hTtpBa6T34IzZ+01XVibrGRUufwXIChrNE3jzzMu3j/o4IcEJ+5C/NW16qFdhIGO5Qx0jNTTNtxAoKHgpNG/593MOuzgsyMOTttzfyC9Ar0rGhhe3UzvKAPGq0h+paene24inT59ulinpPtTfn2HsqSkXwebWyNwcYpn+/UGFl6I2kXm3y09+0xNP8NYZVCxxyKEEEIUFek/+fLbJ2OHw8GmTZsYM2aMZ59Op+Omm25i7dq1uZ7Tvn17vvzyS9avX0+bNm04ePAgP//8M/fff3+ej2O3232mmaWmphbdkxCl0i233MK+ffs4fvy4z+p/Vys9PZ3Zs2f7PSElRGGotqOoSX/hPrsCd9IKtIwDebZVghpiqjsRfcXbUBQZbXNRqlPj8yMOPoi3+6xuVxjpbvg90cXviS4AjAq0DNNfSFIZuDFST7gpK2me7tJYcNzBJ4ccrD6bd92/WKuO4dVNDKpmolIRTtOT1URFcQnQK1QJUDhmy0qw7k9T0QU3Ab3VM0pTTV4NkpQSQghxnZH+k5ffPh2fOXMGt9tNxYoVffZXrFiRPXv25HrOfffdx5kzZ7jxxhvRNA2Xy8XDDz/Miy++mOfjTJ48mQkTJhRp7KL0K44RXP379y/yawpRVFTbEdxJf6EmrcB9dgVaxsECz1ECa2Kq8yr6SveiKLJyyEU7U928f9DOF0cdpLlyb1M/WMejNcx0iNTzz1k3q5JcrEpyeT58X8qpwT/Jbv5JdjNlX9aNlsYhOuoG6Vl62sn5PB7HooO7KhsZHmOmU6RekobiulPLquOYLSvZeiDdjaIzoAtri5r0B5C1Ap8QQgghrl/X1ZCNFStWMGnSJD744APatm3L/v37efLJJ3nttdd4+eWXcz1nzJgxPP30057t1NTUIh39Iq7MxVpMQgj/UDMO4z67Ims0VNIKNFt84U7UB6IPvxF9dH8MVYag6IzFG+h1wqlqfJ/g5P2Ddv46k/toJb0Ct0cbebSmia7lDJ4EUfMwA4/UNKNpGoczVFYlXUhSnXGxJy3vEVbbU1W2p+Z+vGWYnuHVTQyoYiTMJMXLxfUr1qr3/E7tT8/6edeHt/ckpbTzO9Gc51CMYf4KUQghhBBXwW9JqXLlyqHX63OsyHbq1CmioqJyPefll1/m/vvvZ8SIEUBWUer09HQefPBBXnrppVzr/5jNZsxmc9E/ASGEuIZomgbuNDTHWTTnWXBm/euz7TiL5kxCTd2KZjtUuAvrregjbkQX0QV9ZBd0oS0lEZVNQqbKR/EOPjpk50Rm7qOcKpoVHowx8WANc76r2ymKQoxVT4xVz/3VTAAk2lX+TnKx6kxWompLijvPmlThRoWBVbNGRTUNlZFronSola3YeUKmRrpLwxzeIVsLDXfyPxgq3FzywQkhhBDiqvktKWUymWjZsiXLly/n9ttvB7IKnS9fvpyRI0fmek5GRkaOxJNen9XxliWBhRClmaZpqGdX4T79I5r9VFbC6ZKkE1oec7guhz4oKwkV2QV9RBd0oS0kCXUJVdNYccbF/+IdLDrhxJXHn58bI/U8VtPMHZWMmK6wmHh5s45+lUz0q5S1fd6p8U9y1iiqlUkuDqSr1AvSM6y6iX6VjFj0Mj1PlC6xQb79voPpKo0uWdlTTV4DkpQSQgghrkt+nb739NNPM3jwYFq1akWbNm2YNm0a6enpDB06FIBBgwZRuXJlJk+eDECfPn2YOnUqzZs390zfe/nll+nTp48nOVUUVPXyCtIKcb2Rn/Hrh+Y8h+vYFziPzERL21X0D6APQh/R8UISqrMkofJx3KYy54iDTw87OJie++9QoB4GVjXxaM3iGa0UbFToUcFIjwryfyTKhuwjpQD2p7tpHBqGEtQQLW0nIHWlhBBCiOuZX5NS99xzD4mJibzyyiucPHmSZs2a8euvv3qKnx85csRnZNTYsWNRFIWxY8dy/PhxypcvT58+fZg4cWKRxGMymdDpdJw4cYLy5ctjMpmkKKwoVTRNw+FwkJiYiE6nw2Qy+TskkQd3yiZchz/EdeIrcBfB6hyGUBRjBIopAsVcCV3EjVnT8UJaoOiuq/KCJcqpaixJcDLrsINfT7nIK51bJyircPngamWrhpNOp6Nz586e74UoarWsvsndAxfrSkV0wHUhKaWe+wdNdcl7mRBCiOuC9J98KVoZm/eWmppKaGgoKSkphISE5DjucDhISEiQJRpFqRYYGEh0dLQkpa4xmjsD14n5uA7PRE3ZkEcrHUpgTRRTJIoxAi4mmozeL7JvmyLAECYf1i7TnvNuZh1y8PlRB6ftuf+Z1Ctwa5SBx2qa6V7egE5uYpRaBfUdygp/vQ7lf0rhjCPr9/ChGBMzmwfiPPYZjq1DPG0sN25GH9q8xGISQgghRP4K22+QTymXMJlMVKtWDZfLhdud+wpKQlzP9Ho9BoNBRgFeQ9Tzu3EemYnr2GfgSsm1jWKOwlD1AQzVRqALqFbCEZYNaS6NBccdfHLIwZqzeb//x1p1DK9uYnB1E9EWubslRHGLteo448j6nTyQbQW+7NTkNZKUEkIIIa5DkpTKhaIoGI1GjEap2SGEKB6a6sB98juch2einl2RZztdZHeM1R9BX/E2qfVUDDRNY11y1qio+ccdpOVRKz5AD/0rGRkRY6ZjpF6SukKUoNggHf8kZyWl9l9ISimBsWAqD45EANzJqzHGPOa3GIUQQghxZSQpJYQQJUjNOITryMe4js1Cs5/KvZExHEOVoRirPYQuqE7JBlhGnLGrfHHUwaxDDnaez7vwf6swPcNjTAyoYiLUKImoS6WnpxMTEwPAoUOHsFqt/g1IlErZi50fyVBxqBomnYI+vD3uUz8AF1bgE0IIIa4D0n/yJUkpIYQoZprbjvv0j7iOfoo78Rcg9xpFurAbMFR/BEP0XSj6gJINsow4many5l47M+PtZOaRiwo3KgysamR4TPGsoFfanDlzxt8hiFIuNluxcxU4lK5SJ1iPLltSSrMdRs08js5S2U9RCiGEEIUn/ScvSUoJIUQx0DQNNXULrqOzcZ2YB86zuTfUWzFUHoih2sPoQ5uVaIxlSaJd5a29dt6Pt2PLo1xU9/IGhlc30a+SEYteRkUJca3IPlIKsupK1QnWow/vgDPbfjV5Dbrou0o2OCGEEEJcFUlKCSFEEdLsp3Ed/xLnsTlo57fn2U4JboSx2iMYKg9EMZbd1byKW5Jd5e39dmYcsJOeSzKqskVhaHUTQ6ubqGmVUVFCXItig3yTUhfrSulCW4JiBC0rNeVOXoNBklJCCCHEdUWSUkIIcZU01YH79M+4js3Gffpn0PKolq0PxBB1J4ZqD6ELby/FsovRWYfK1P12ph+w51q8vFGIjnH1LPSrZEQv/w9CXNPKmRSCDXD+wu/ygQsZZkVvQRfaEvXcPwCoZ1f7K0QhhBBCXCFJSgkhxBVyp269MD1vLjjynheuC78RQ9WhWbWiDMElGGHZc86hMu2AnXf320nNJRlVP1jH+HoW+lc2opNklBDXBUVRiLXq2ZJyYQW+NG9BOF14B29SKnULmjsDRR/olziFEEIIcfkkKSWEEJdBc5zBdXwurmNzUFPj8mynWKpiqDIYQ5XB6KyxJRdgMXJrGl8ecbI80YnVoNAx0kDHSANVA3UFn1zMUp0a0w/YmbrfzjlnzkLydYKyRkbdU0VGRglxPapl1XmSUgfSvUkpfXh7XPHvZG1oLtRzG9FHdvJHiEIIIYS4ApKUEkKIQnCfW49z/xu4T//oqV+Sg86CPuoOjFWHoovsiqKUjhpFmqaxOMHFi7ts7Drv/TA4M94BQEygjo6R+qwkVTkDdYN0JTY1Mc2lMeOAnbf32TmbSzKqljUrGTWgihGDTpJRRU2n09GqVSvP90IUl+x1pQ5mqLg1Db2ioAtv79POnbxaklJCCCGuadJ/8iVJKSGEyIfmOo/j35dwHXoPyJn0ANCFtcNQdQiG6HtQjKElG2Ax+/uMi9E7baw5m8eSdcChDJVDGSpfHM1K1pU3KdwYaaBjuaxEVbNQfZEnhNJdGh8ctPPWPjtnHDn/X2ICdbxSz8zAqiaMkowqNgEBAWzYsMHfYYgyIPsKfA4Vjtk0qgcq6CxRKIE10TIOAlkr8AkhhBDXMuk/+ZKklBBC5MF16iccOx5Byzya45hiroShyqCs6XlB9fwQXfHakermxZ02lpzMWZjJqge3BplqLicCiQ6N7xKcfJeQlaQKMkD7CINnJFWbcD0Bem+iyKlqpDgvfLk0zjmzbTvxbmc7ti3FTWIuyahqAQpj61oYXN2ESZJRQpQasVbfO8kH0t1UvzB1WBfeHveFpJQ7eQ2apslCEkIIIcR1QpJSQghxCc1+GvuuJ3GfmJ/jmL7i7RiqPYS+fI9SMz0vuyMZKuN2Z/LZEUeOcWFGBR6raebFumZCjQqbkt2sSnKx8oyL1WfdudZyAkhzwW+nXfx2OivBZdJljWQ678pKMGXkPQir0CpbFF6qa2FYdRNmvXwYFaK0iQ3yfb/dn6bSrXzW9/rwDriPf5m14TyLlv4vSim8WSCEEEKURjKBUQghLtA0DefROWT8VT9HQkoJqI65za9YWn2HocLNpS4hlWRXeXa7jTrLUplzSUJKAe6vamRvj2DebRJAebMOk06hXaSB5+tY+LF9EEm3hLC1WzDvNQ3gnspGKlnyTgw5VNibppKQefUJqWiLwn+bBLD//0J4pKZZElIlLCMjg5iYGGJiYsjIyPB3OGXKypUr6dOnD5UqVUJRFL7//vt82y9atIgePXpQvnx5QkJCaNeuHUuXLi2ZYItAJYuCOVuv9dJi59m5ZQqfEEKIa5j0n3zJSCkhhADU9APYtz+EmrT8kiM6DDWexFTnVRRDkF9iK04ZrqxV697Ym0lqzpl69K5oYHLDAJqE5p+E0ykKTUL1NAnV81hNM5qmEZ+hsuqMdzTVvvQ85vsVQAeEGRVCL3yFGRXCjQrdyhsYHmPymQooSpamaRw+fNjzvSg56enpNG3alGHDhnHHHXcU2H7lypX06NGDSZMmERYWxuzZs+nTpw/r1q2jefPmJRDx1dEpCrWsOs9iC/uzvZ8owQ3BEAKuVOBCXamqw/wSpxBCCFEQ6T/5kqSUEKJM01QXzvipOPeOB9Xmc0wX0hRT44/Rh7X2T3DFyKVqfHrYwfg9mSRk5vxj2CZcz5sNLXQpb7yi6yuKQk2rnppWPYOrmwA4manyd5KLv5NcnHFohBp8E02hRsWzL3sSyqpH6sMIcYlevXrRq1evQrefNm2az/akSZP44YcfWLJkyXWRlAJ8klIH0r3DLBVFjz7sBtxnfgPAnbRC6koJIYQQ1wlJSgkhyix3ymYc20agpm7xPaCzYKw9DmPNZ1B0V5aUuVZpmsaiE05e3JXJ3rScI5fqBumY1MBCv0rGIv9AF2XR0b+yif6VTUV6XSHE5VNVlfPnzxMREZFnG7vdjt1u92ynpqaWRGh5irXqgawhnfvTVJ/Eky6ikycppWUcQE36E325bv4KVQghhBCFJDWlhBBljubOwLH7OTL/bp0jIaWL7EpAp22YYl8odQmpcw6VTqvS6L8+I0dCqpJF4aNmAezoHswdlU0ywkCIUu7tt98mLS2Nu+++O882kydPJjQ01PNVtWrVEowwp1pB3m5ruhtO272jPA1VBkO2Wn/OQzNKNDYhhBBCXBkZKSWEuOap6ftwJ60AxYBiKo9irpD1r6k86K2XlUBxJy7Dvv0hNFu87wFDGKYG72CoMrTUJmSe3Gbj7yTfyuKhRnihtoUnapkJNJTO5y2E8DVv3jwmTJjADz/8QIUKFfJsN2bMGJ5++mnPdmpqql8TU7FW33up+9NVKlqy9ukCqqCv2A/3yYUAuE8tRs04jC6weonHKYQQQojCk6SUEOKapNlP4TrxNa4Tc1HPrc+7oc7ik6RSTOXBVAHFXD7bvgoohmCcB97EdfzzHJfQR9+FqcF/0VmiivEZ+dehdDdzjzk922YdPF7TzJi6ZiJMMmhWiLJi/vz5jBgxggULFnDTTTfl29ZsNmM2m0sosoLVuiQpdSBdpUOkd9sY87gnKQUqrsMfYKr/ZskFKIQQQojLJkkpIcQ1Q3Ol4z71Pa7jX+I+sww0d8EnqZlotiNotiOX/XiKpQqmRh9gqNjnCqK9PPHpbh6Os3HKrvJh00DaRZbs2+/b++24s9UzX3yDlf+rWLqmJ4qSpygKDRo08Hwvrm1fffUVw4YNY/78+dxyyy3+DueyVQ/UoVfwvJftT/P9G6GL6IgupClq6lYAnEc/wVhnHIo+sKRDFUIIIfIk/SdfkpQSQviVprpwn1mG6/hc3Ke+A3dGCTyqgqH6o5jqTkIxhhT7o52wqXT/O534jKw6TneuT+fA/4UQoC+ZP0KnMlVmHXJ4tluF6elRQd7+xdULDAxk586d/g6jTEpLS2P//v2e7fj4eOLi4oiIiKBatWqMGTOG48eP8/nnWaND582bx+DBg5k+fTpt27bl5MmTAAQEBBAaGuqX53C5jDqF6oE6DqZfXIHPtzaeoigYqj+OY/uIrB3Os7iOz8NYbURJhyqEEELkSfpPvuRTiRCixGmahpqyAdfxL3Gd+Bocp/Nsq5groa80AEPl+1DMFdHsiWiO0+BIRHMkotlPZ/17yTaulNyvF9QAc+OP0Ue0L66n5+OsQ6XnmjRPQgogIVNjZrydp2ItJRLD9AN2MrN9dhtTxyx3ZYS4zm3cuJGuXbt6ti/Wfho8eDBz5swhISGBI0e8I0g/+ugjXC4Xjz32GI899phn/8X214tYqzcptT895wqihsr34djzPDjPAuA6NAND1eHynieEEEJcoyQpJYQoMWr6flzH5+I6MRctfV/eDQ3BGKL6Y6j8H3SRXVCyraiEpXKhHktz29GcZ9DsiRcSWKdRTBXQRXZG0Zmu8pkUTppLo/eadHak5vzgNPlfOw/EmAkq5uLiKU6N9w96l3SvF6Tj9koybU+I612XLl3QNC3P45cmmlasWFG8AZWQWKuO3y58vz8t53urog/AWHUEzoNvAaCe34Z6dhX6yE4lGKUQQgghCkuSUkKIYqW5M3Edm4Pr2BzUc+vybqgY0FfojaHSf9BX7IOiD7iqx1X0ZhR95UInsYqa3a3R75901iV7a56YdOC48Bkq0aEx44CdMXWLd7TUzHg7qS7v9ug6ZnQyYkAUkYyMDFq3bg3Ahg0bCAyU2j2ieGUvdn7WqZHsUAm/ZLEGQ/VHcR58G8h6w3UemiFJKSGEENcM6T/5kqSUEKJYaG47rqOf4DwwGS3zeJ7tdOEdMFQeiCH6LhRTZJ7tricuVeO+jRn8nujNBpU3Kfx+YxC3rE3jmC1rdMNb++w8UsNEWDGtfmdza7y73ztKqmqAwn1VS2aUmCgbNE1j165dnu+FKG6xQXqf7QPpKq0ueQ/VBVZHX7FvVp1CwH3qO1TbUXQBVUssTiGEECIv0n/yJeuACyGKlOa24zz8IbYVsTh2jsw1IaVY62Gs8zoBXQ8S0P5vjNUfLjUJKU3TeCjOxqITTs++EAMs7WClSaiel7ONjDrn1Hj3gD23yxSJOYcdnLJ7/9A9E2vBpJNRUkKI61f2kVKQs9j5RcaYx70bmhvX4Q+LMywhhBBCXCFJSgkh8nU4Q2Xyv5n8dcaVbztNdeA8/D9sK2rj2PEoWuYx3wbGSAw1nsJy4yYCOu/CVPsldIE1ijHykqdpGs/uyOTTw96V7iw6+LFdEM3DsgamDq1uoma2D1Xv7rdzxp77h6qr4VI1puzzJrwiTQojYmSUlBDi+lbzkqRUbsXOgax6hMGNPNvOox+juTOLNTYhhBBCXD5JSgkh8rQx2UWzP87z4q5Muq1K45eTzhxtNNWJ88gn2FbUwbHjYbTMo74NjJEY671BYLdDmBtMRR/aotSugjRpr52p2abLGRRY2NZKx3LemdJGncK4et7RUudd+CSPisrXx50+K/49WcuMtZiLqgshRHEL0CtUtnjfyw7kUuwcQFEUjNVHenc4zuA6Mb+4wxNCCCHEZZKklBAiV+vOurhpdRrnnFnTv1RgxJYMzl2o1K2pTpxHP8W2oi6O7Q+g2Q77XsAYgbHuJAK7xWOqNRrFEFTCz6BkfXDQzthd3rvwCvB5y0Buicq50t1/qhqpF+R9+51x0M7JzKIbLaVqGm/s9cYSZICRNWWUlBCidIjN9v65P92dZztD5YFgCPNsuw79V2p3CCGEENcYSUoJIXJYk+Six+o0Ui4ZGHUiU+OpbRk4j87B9lc9HNuGo9nifRsZwjDWeY3ArvGYYsegGIJLLnA/mXfUwcitNp997zcNYEAeRcX1isKE+t7RUjY3TN5bdNNKfjrpYkeqN8n1cIw5x+pUQghxvapl9RY7z6umFIBisGKoOtyzraZuQU1eU6yxCSGEEOLyyKcUIYSPv8+46LkmjfPZSkhln/Q156iLxXFfoWUc9D3REIqxzgQCux3CVHssijGkROL1t59OOhm8KYPs994nNrDwSE1zvuf1r2ykSYj3LXhmvIOjGVc/WkrTNJ8El0kHT8XmH4sQV0pRFKpXr0716tVL7bRcce2JzVZX6kSmRoYr79FPxphHyf5XzHloRnGGJoQQQhRI+k++JCklhPD464yLm9ekkZYtIfV/FfT8WvcfFLwJk5GuaSRroVkbhhCMtcddSEa9gmIMLeGo/WflGRf916WT/fPQs7FmxtQpOAmkUxReaxDg2Xao8Pq/Vz9aalWSm7VnvdNZhlQzUSlA3upF8QgMDOTQoUMcOnSIwMBAf4cjyohLV+A7mE9CXxdYE32FWz3b7pPfomaeKLbYhBBCiIJI/8mXfFIRQgDwR6KTXmvSyF6eo2dYEl85O9EhvheP69737D9JNM+r72CMHZuVjKozHsUYVmyxbTnn4pG4DJ7aZmPa/kwWHXewKdlFol31W32Qzedc9FmbRvZSUMOrm3irkaXQdzz6RBloHe6dhvLpYQcH0vKuj1IY2UdJ6YDnassoKSFE6ZK9phTA/gLeN401nvBuaC5ch2cWR1hCCCGEuAKGgpsIIUq7Zaed3LY23SfBcrNpHXPTb8OsOAB4WT+JX9Se7KMOAF+57+TeECu3GXMW8i5KG5NddF6VRkYenzkC9FAtQEf1QJ3338CL2wpVAnQYdUU7LPbf825uXp1OarYRZXdWMvK/5gGXNQRXURRer2+h55p0AFwavLonk89aWa8ori3nXPx6yhvUXZWNxAbp8zlDCCGuP9lrSkH+daUAdJHdUYLqo6XtBsB55H8YY19C0UvSXgghhPA3SUoJUcb9esrJ7f+kY8/Wp79V+YnPtGGehBRAgEHPrMrr6HKoNuqF+hwPbcmgQ0QwkebiGXQZn+7mlrXpeSakIKtI+L9pKv/mtSw4UMmiUD1QR0ygjjpBeuoE6agTpKN2kJ4Q4+UlrI5kqPRYnUaiwztCq0cFA3NbBaK/gjnhPSoY6BipZ1VS1pP88qiTF+q4qR9y+cmkN/bafbZfKMQ0QiGuhs1mo1OnTgCsXLmSgICAAs4Q4uqFGhXKmRTOXHgf3l9AUkpRFIzVR+LY+VjWDsdpXAnfYKxyf3GHKoQQQuQg/SdfkpQSogz7+aSTfuvScWTrz9+mLGaOYQQm5cLSezoThuqPYqo1ho7mCjxrtPHWvqzkx0m7xhPbbMxtfWUje/KTZFfptSad03Zv8sekwyfWwtCA45kaxzPdrDnrBnyXFIy2KBeSVHrPv3WDdNSw6jBdMsLqtD0rIXXU5o3phnA9i9paMeuvbDSWoii83iCAzqvSAFCB8Xsy+brN5b2m+9LcLDzufW69KhpoFiZv8aJ4qarKxo0bPd8LUVJirTrOOLKS+fvzuCmRnaHKIBz/jgFXKgCuQzMkKSWEEMIvpP/kSz6xCFFGLUlwcue6NJyaN5nST/cdn+ofxKi4AB2GKoMw1h6PLrC6p82E+haWnHSy+3zWG+i8Y076V3bQr5KpyGKzuTVu+yfdZ/RTqzA9KzoG4dLgcIbKkQyVw7YL/2aoHLFl/ZuQqXE5VaYSMjUSMt38dcZ3OJZegRqBWSOq6gbpqROs46N4B3uzxdQ4RMfP7a0EGa5uemCncgZ6VDCw7HTW1Ltvjjt5McVN09DCj5Z6a6+d7H/SxtSxXFVMQghxLasVpOOf5Kz37YKm7wEohiAMVYfhip8GgJqyAXfyOvThbYszTCGEEEIUQJJSQpRBi44kce8mcOJNevTXfcsn+ocwKG70Ffthqvs6uuAGOc616BXmtAik3V9pniTIw3E2OkYaKFcE0/jcmsbAjRkXRjVlqWnV8WM7K9YLyZ8moXqa5JGwcagaxzzJKs2TrDqcoXIwQ+VQukph7ke4tawpIfvTVX7OVqcpe0xLOwQRbiqaqYuv1bew7HSaZ/uVXTZ+aBdUqHOP21Q+O+KdatkhQk/HcvL2LoQovWKzrcB3OEPFoWo5Rrdeylj9MVzx0+HCrQvnoRmSlBJCCCH8TD61CFGGaK40vo5bwv1Hb8KFt0D5vbqvmal/DFO5TpjqTi6wk94mwsDoOmYmX6hhdNquMXKrjfmXOeUsR3yaxtPbbSw64Z2GFmlS+KWdlYqWwiV/TDqFmlY9Na25J63sbo0D6Sp709zsTVMvfLn5N031mSqYn2iLwu8drEQXMqbCaBthoE+UgSUnsxJgi0+6WH/WRZuIgt+m391vx5kt9BdklJQQopTLXuxcJSsxVbuAhR101lj05XvhTvwZAHfCN6j130ZniSrOUIUQQgiRD0lKCVEGaKoD15GPmLdrI8Ptb+PO9qs/UDeXDyM+I6DeL+jK3VTo1ePG1bOwOMHJzgvT+L4+7qT/cQf9K1/5NL5399v57wHviB+LDpbcYKVOcNGtIGfWKzQI0dMgl0Li5xwq+9KzJarOe79PvzBwK8qs8FuHIGrkkfS6Gq/Wt7DkpHe01NjdmfzWIf/RUmcdKjPjvQXOG4fouCVK3tqFEKVb9pFSkFVXqqCkFIAh5nFPUgrNievI/zDVGVccIQohhBCiEOSTixClmKapuI/Pw7H3Zb5Oa8UI90zUbFP2hpi+53/NK2KMXlfoZNRFZr3CZy0DaftXGu4Lo3QeibPRqZyBClcwje+bYw6e2ZHp2VaAea0DaRdZcm9TYSYdrU06Wof77tc0jYRMjeOZKnWvYMW+wmoWZuCuykYWXChYvuy0i7/OuOicz1S89w46PAkzyBoldbn/l0IIcb2pFeT7d6YwdaUA9OX/D8VaBy19LwCuIzMxxo5B0RVdXUQhhBBCFF7xrOMuhPA7d+pWMtd2xL71fuamtc2RkHqg3AE+ufk/mCr1v+IkRstwA2PqmD3bZxwaj8XZLvs6K8+4uH9Ths++/zYJKNLi6VdDURQqBehoHW4otoTURRPqWXzemF/eZUPTcp9WmO7S+O8B7yipmlYdd1c25tpWiOJSrlw5ypUr5+8wRBlT3qQQnC1fvz/dnXfjbBRFh7H6SM+2Zj+JO+Hbog5PCCGEyJf0n7wkKSVEKaM5U7HveorMv1uiJq/hC/d9POT+wCch9WiMjv/d2AK9/uoTGC/Xs9A4xPtWsvCEk2+OOfI5w9euVDd9/0nHke0m93O1zYysZc77pFKsfoie/1T1/r+sSnJ7VuW71MeH7CQ5vAmr52qbMRRQ6FeIomS1WklMTCQxMRGr9epqyglxORRF8akrVdiRUgCGKoNB750a7Tw0o0hjE0IIIfIj/SdfkpQSopTQNA3XifnY/qqXteS15uYbd38edc9Ay/ar/mQtE+81Cy6yKV4mncKcloEYsl3u0a02TmUW/AHhhE2l15o0zmWr0n1vFSNvNCzbhbrH1bOgz/Z6jt2dmWO0lEPVeGe/d5RUlFlhSLVrY2SZEEKUhOx1pfanFT4ppRhDMFQZ4tlWz63FfW5jUYYmhBBCiEKSpJQQpYCatofMdTdh3zIAzZ4AwF/qjTzkft8nIfV0rJl3GwcUec2hFmEGXqrrHdmU5NB4JC7vaWcA550at6xN54jN26ZzOT1zWgSiK+M1kWoF6RlW3Ztg2pDs9qzKd9GXRxwcy/baPRVrxqIv26+bEKJsqZUtKXUwQ8Wdz9+cSxljRvpsu2S0lBBCCOEXkpQS4jqmudJx7HkR28omqEl/ePbvUBswwDUPJ97ExjOxZt5uVHxFsF+sa6FpqPct5bsEJ/OPOXNt61Q1+q9PJy7FWwOkYbCO79taMUtiBYCxdS2Ysr1Dv7zLhnrhA5db03hrn3eUVKgRHq5RNqc7Cv+y2Wx06dKFLl26YLNdfj05Ia5GbLZi5w4VjtsKn5TSBdVFX76nZ9uVMB/NfrpI4xNCCCFyI/0nX5KUEuI6pGkarpPfY1vZAOeByaB5kz/Hler051dSCfbsu7+qkSnFmJCCrGl8n7W0+kzje2yrjYRLpvFpmsaDW2z8lq1OUiWLws/tgwgzyVvSRdUCdTwU400qbktVWXhhVb7vTzj5N9tUlcdqmIu9ALsQuVFVlb/++ou//voLVS389CkhikL26XsABwpZ7PwiQ/XHvRuqA+eRj4siLCGEECJf0n/yJZ8AhbjOqBkHsW/sg31TPzTbEZ9jaZG309+4kWMub0Kqe3kDn7QILNaE1EVNQ/W8XM9bDyrZqfHwlgyfaXzj92Qy54i3EHqwAX5uH0S1QHk7utSYuhYCvHV8eWV3Ji5VY/Je7ygpiw6ejJVRUkKIsid7oXO4vLpSAPoKvVACa3m2XUc+RFNzH+ErhBBCiOIhnwKFuE5o7kwc+17F9ldD3Kd/8jmmWCqjNFvIf1yfsz3Nu0Z24xAd37a1YirBFdnG1DHTPNT7QWHxSRdzj2Z18mcdsvPqHm9CxaDAt22tNA3V57iOgGiLjpE1vQmnf9NUhm/OYNM572iAETEmKpjlrVwIUfZUDlDI/va3/zJW4ANQFB3G6o95trXM47hPfldU4QkhhBCiEOSTjBDFaGOyix9OOMl0F77ORW5cp3/FtrIxzr3jQM30HlAMGGs+h6XTbh5KuJnlid5kRZWArClxoSU8rcuoU/isZSDZH/bxbTY+PWTnoTjfOdOzWgTSo4KxROO73jxf20yQN8/I50e9d/ENCjxbu2yvVCiEKLt0ikLNbFP4DlxmUgrAUHUo6L3LcTul4LkQQghRoiQpJUQx+eWkk9Yr0rh9XTot/zzPtpTLq3UBoGYeJ3NTf+wbeqFl7Pc5povoREDHOEz13+LlvQa+zJasCDXCL+2DqBLgn1/xxqF6xtX3JkvOOTWGb7GRPTf3egMLg6qZcjlbZFfOrOOpWrlPz7uvipHqMu1RCFGGZa8rtf8ya0oBKMYwDJUHebadZ9fgTokritCEEEIIUQjyaUaIYjIl2+pou86rtF5xnun77T71lfLjSliEbWVj3Ce/9dmvmCtibvoFlhtWoAtuyMx4O5Oy1RgyKvBdWyuNQvw7JW50bTMtw3KP4cEYEy/WkTpIhfV0rJmwXEa8ja4jo6SEEGVb9rpSB9LVQv+Nzc4YMxK7ZmK0ayKVnYfovubqRzgLIYQQonAkKSVEMThhU1lxxuWzz6HCqO02eq9N51Rm3lMMNHcG9m0PYt98JziTsx3RYag+koDOezBUGYiiKCxJcPLYJVPi5rQMpGt5/0+JM1yYxnfpgnq3VDTwftOAEim8XlqEmXQ8V9s3idc32kADPycehQAIDAwkMDDQ32GIMio2yPtHJs0Fp+2Xn0w6ZaxHb1byvvooaQTzV2ZtPj14tijDFEIIIXxI/8lLklJCFINvjjvIq1v86ykXjZef5+eTOVf4caduxbaqJa6jvstS60JbYblxA+ZGM1CMYQCsP+ving3pZE9vvdHQwn1Vr50pcQ1D9Exs4B3N0ypMz9dtrBhKsPB6afFELTPVArJeN6MCr9STUVLC/6xWK+np6aSnp2O1Wgs+QYgiVsvq25W93LpSa5JctPzzPOucdX32rzi866pjE0IIIXIj/SdfkpQSohjMO+ZNOFUJUPigaQAB2Qa1JDo0blmbzhNbM8h0a2iahjN+Opmr26Cl78l2JQVjrRextF+DPrSFZ++BNDe3rk3Hlq18xqM1TDxf+9qbEvdsbQvft7XyYbMA/uoYhNUgCakrEWRQWNkpmCmNLPzVMYgWYYaCTxJCiFIu9pKk1OWswPdRvJ0uq9JIyMx5G+mf82GoqduvOj4hhBBC5E8+1QhRxPanudmQ7M0WDahi4pGaZrqUMzBgYzpbU7wd5hkHHfx5OpM5gS9Q75zv6CjFUhlz0y/Ql+vqsz/RrnLzmnQSHd5OdN9oA/+9hqfE9a3k/+mEpUH1QJ2stieEENlUD9ShV/AspHGgEMXO7W6Nx7fZ+PiQw2d/gM6NTc26g3SUqhzYNpTYDouu2b+tQgghRGkgI6WEKGJfHfOdljegSlZCpn6InnWdg3OspLYjTUeH068y0/0AF+uz6iv2JaDj1hwJqQyXxm1r033uBLcN1zOvlRW9dJqFECUsMzOTW265hVtuuYXMzEx/hyPKIKNO8VmFdH9a/iOlTthUuqxKy5GQGlDFyA/tQnz2/ZOs4T4+t+iCFUIIIZD+06VkpJQQRUjTNL465u3o1g3S0SzUO2/PrFeY2iSA/yuvMWTDWU65gwCwY+FZ91v8rvXgk4ZpVKo1JMedWbemcd/GdP7JNgor1qpjSTsrgTIlTgjhB263m59//tnzvRD+EGvVcfDCzZr8akqtSXJx57p0TmYrhq4DpjSy8FSsGbsKRkXDqWX9TV2ntuHOPc+hr3gbijEkj6sKIYQQl0f6T75kpJQQRWhbqsru894O8X1VTTmSS2rav3TefyNrdc25WVnqc+xXtQct997Bb6d9V+7TNI0nttr4IcG7v5xJ4Zf2Vsqb5ddYCCFE2ZW92HluNaU0TeN/F+pHZU9IRZoUfutg5enaFhRFwaJXaJmtXt96rTWa/SSOfeOLNX4hhBCiLJNPs0IUoXlHc04HuEjTNJxHZmH7uwVq6hYqKGdYYLiXd/TPYVa8U/5O2TVuXpPOU9ts2C8UyZiyz84H8d5rB+jhx3ZWYoOyVU8XQgghyqDsxc6THBrnHN7ElN2t8eAWGw/H2XBmq2feLFTPxi5BdK/gW/OwfaQ3KRWnNcWmWXAd+q8UPRdCCCGKiSSlhCgiqqYxP9vUvZZhempfSBppznPYt9yLY/sIcGd42ijmcjzRti8bu0XQKMT313HaATttVpznzb2ZjN7pnWusA+a3ttI2QmbfCiGEELWsvjdoLk7hO25T6bwqjU8O57xhtLpTEDHWnDd22kV49zkxsUVrBpob+86RaFrOVfqEEEIIcXUkKSVEEVl71s0Rm7fDet+FUVLus39jW9UUd8I3Pu115W4ioOM2DBVvpVGIng1dgnmilsmnzbZUlRd2+ha/e69pALdFy2p2QgghBEBskG93dn+6yuokF63+PM+6bHUYdcA7jSzMbRWYZy3G9pfc8FmntQFAPbsS94mvijZwIYQQQkhSSoiikn3qngLcHa3h2DuOzLWd0WxHvA0VA8Z6b2FpsxSdJdqz26JXmN4kkJ/aWSlvyr2z/EIdM4/UNOd6TAghhCiLalp9u7PTDxRcPyovlQJ0VA/0Hl+n3eD53rH7GTRnahFGLoQQQghJSglRBJyqxoLj3rpQnYITiVhXF+e+VwFvbQvFWhtL+7WYaj2HouT+69c7ysi27sHcXNH3bu1/qhqZ2MBSLPELIYQQ16sAvUJlizeRtPasG1ch6kflJftoqXVKZy7O2ssqej6hSGIWQgghRBZJSglRBJYnukh0eHvAd2ZMRMs86tPGUGUoATduRh/WqsDrRVl0/NTOyofNAugUqeelumY+bRGILp+7u0IIUdKsViuapqFpGlar1d/hiDKsljX3Lu19+dSPykv2pFSiO5B4cyfPtuvQdNTzO648UCGEEGWe9J98XRNJqffff5+YmBgsFgtt27Zl/fr1ebbt0qULiqLk+LrllltKMGIhfM07cMzzvQEnfXWLvQdN5TE3/wpz009RDEGFvqZOUXi4hpm/OgXzeoMATDpJSAkhhBC5uXQ12ov1o77Mp35UXtpH+l5rU9Rb3g3NjX2HFD0XQgghiorfk1Jff/01Tz/9NOPGjWPz5s00bdqUnj17cvr06VzbL1q0iISEBM/Xjh070Ov13HXXXSUcuRCgnt9B8vo7+f6UtwPbQ1lOpJIM+iCMdSYQ2PUAhkr3+jFKIYQQonS7Nco7uinSpLDsxoLrR+WlSYiewGx5qXXuxugr3OrZVs/+hfvE/KuKVwghhBBZ/J6Umjp1Kg888ABDhw6lQYMGzJw5k8DAQD799NNc20dERBAVFeX5WrZsGYGBgZKUEiVKtR3BvnUotpVN+OmUi/OEeI7dpf8eQ8wTBHY9gKn2KyiGYD9GKoQQxSczM5O77rqLu+66i8zMzIJPEKKY3B5t5KvWgUxsYGFrt2C6lb/yVWoNOoU24d4k15okF6aG00HnXWhEip4LIYS4UtJ/8uXXpJTD4WDTpk3cdNNNnn06nY6bbrqJtWvXFuoas2bN4t57781zLqbdbic1NdXnS4grpTmSsO96FtuKOriOzQE0Frjv9BwPUBzc2Xky5obTUcwV/BanEEKUBLfbzcKFC1m4cCFut9vf4YgyTFEU7q1i4sW6FioHXH33tn2Ed6jU9lSVNGMNjLVGe/Zp9gQc+1696scRQghR9kj/yZdfk1JnzpzB7XZTsWJFn/0VK1bk5MmTBZ6/fv16duzYwYgRI/JsM3nyZEJDQz1fVatWveq4RdmjudJx7J9Exp81ccW/A6odgBQthKXa/3na9a1sJSSkhr/CFEIIIUQRaB/pHSmlAeuSXRhrvYASEOPZn1X0fGfJByeEEEKUIn6fvnc1Zs2aRePGjWnTpk2ebcaMGUNKSorn6+jRo3m2FeJSmurEefh/2FbUxvnvS+DyHWn3o+Vx7Fg82wOqmEo6RCGEEEIUsRvCfYudr0lyo+gDsqbxXaS5pOi5EEIIcZX8mpQqV64cer2eU6dO+ew/deoUUVFR+Z6bnp7O/PnzGT58eL7tzGYzISEhPl9CFIb7zJ/YVjbEseNhNHuCzzHFWhdzi2/5NuAFz75wo8LNFQ2XXkYIIYQQ15lIs456Qd5u8pqzLgD0FfqgL9/bs189uwJ3wtclHp8QQghRWvg1KWUymWjZsiXLly/37FNVleXLl9OuXbt8z12wYAF2u52BAwcWd5iiDHIlLiVzw81o6ft89ivmSpgaf0RApx0khd/O76ddnmN3VjJi0l3+Kj9CCCGEuPZkn8L3z1kXqqahKAqmhv/1LXq+6xk013l/hCiEEEJc9/w+fe/pp5/m448/5rPPPmP37t088sgjpKenM3ToUAAGDRrEmDFjcpw3a9Ysbr/9diIjI0s6ZFHKuc/8iX3j7aA6vDsNoRjrvUFA130Yqz2AojOw4LgTNdt5A6pe+Uo/QgghhLi2ZC92nuqCXeez/urrrLUw1nzec0yzn8ApRc+FEEKIK+L3uUb33HMPiYmJvPLKK5w8eZJmzZrx66+/eoqfHzlyBJ3ON3f277//8vfff/Pbb7/5I2RRirnPriZz462gepfm1EffjbnRhyimCJ+28455k1bRFoXO5fz+6ySEEEKIItIuwvfv+pokF41CshJVxtgXcB3/HM12GABn/DQMVYaiC25Q4nEKIYQQ1zNFK2PVGVNTUwkNDSUlJUXqSwkf7nPryVx3E2Qbgq+P6o+5+VcoOt+O6aF0NzV+87YbVcvMu00CSixWIYS4FmiaRkZGBgCBgYEoSumcwix9hyxl7XVQNY3In1I558zqKg+uZmROS6vnuOvkD9g33e7Z1kV2xdJ2ean9PRBCCFE0pP/kS4Z2iGvSouMO3thnJ8OlYdErmHVg0StYdGDWKVj0YNEpmC/8a9GT1eaSfdEWHT0qGNAX8IvuTokjc11P34RUhT6Ym8/NkZACmH/M6bM9oIpM3RNClD2KomC1WgtuKMR1SKcotIvQ88uprPqRa5LcPsf1FW9DX74X7sRfAFCT/sSd8A2GSveUeKxCCCGuH9J/8iVJKXHN2Zjs4p4NGbiKaAzfnZWMfNMmEF0eiSn1/E4y1/cA1znPPn25/8Pc4hsUnSnXc7JP3atl1dH6kqWjhRBCCHH9ax9h8CSl9qWrJNpVypuzykpcLHpuW9nQU4fSsetp9BV6oxiC/RazEEIIcT3xe6FzIbJLc2ncV4QJKYBvTzgZtzsz12Nq2l4y13UHxxnPPl1EF8ytvkPRW3I9Z0eqm+2p3hLnA6oYS+2QSyGEyI/dbmfIkCEMGTIEu93u73CEKHLtI31vOq096ztaSmeNzaXo+WslEpsQQojrk/SffElNKXFNGbE5g1mHvaOQmofqiQnUkalq2FXIdGtkqmC/+K+qkekm67gbnPn8NH/TJpC7KntHPqkZ8WSu7YSWecyzTxfeHkubpSiGoDyv89JOG5P2et88dnUPpn6IjJQSQpQ96enpBAVlvV+mpaWV2qHo0nfIUhZfhzSXRuiSFM9quy/UMTO5oW8NSc2dge2vBp6i5ygGAjpuQxdcv2SDFUIIcV2Q/pMvmb4nrhnfHnf4JKSqBigsv9FKuKnwA/rcWlZyyq5qLE5wMWRzhufY4E0ZxFp1NA8zoNqOkvlPN9+EVGgrLK1/zjchpWka849760k1DdVJQkoIIYQopYIMCk1D9WxJyRohtSbJlaONog/E1OBd7JvuyNqhubDveoKAtstKMlQhhBDiuiTT98Q14ZhN5YEtNs+2AnzZ6vISUgB6RSHQoBBu0jG4uokxdcyeYzY39P0nnZMpCVkJKdshzzFdSNOsEVLG0Hyvvz7ZzcH07FP3cq85JYQQQojSIfsUvvXJbpxqzmHZ+oq3oy9/s2dbPfM7rsTfSiQ+IYQQ4nomSSnhd6qmMWhjBsnZ5t6NqWOmU7mrH8j3egMLt0Z5r3PUpnHnyn+xpx/27FOCGmBpswzFFFHg9bIXOAe4V5JSQggh/GDlypX06dOHSpUqoSgK33//fYHnrFixghYtWmA2m4mNjWXOnDnFHmdp0C7C24/IVCEuxZ2jjaIomBpMA8WbwHLuGY2mqTnaCiGEEMJLklLC797eZ+fPM97h8K3D9Yyvn3uR8culUxTmtrJSP9j7o77G1Yyn3W+haaAExmJp+zuKuXyB13JrGl8f807d6xChp3qg/AoJIYQoeenp6TRt2pT333+/UO3j4+O55ZZb6Nq1K3FxcYwaNYoRI0awdOnSYo70+tc+wnea/pqknEkpAF1QXQxVh3u21dQ43CfmF2tsQgghxPVOakoJv9qU7GLsLu/KeFY9zGsViFFXdKvZhRgVfmil0nZFKslaVoG1OeoQmpgSePKGkegs0YW6zp+JLk7ZvaO5BlSVUVJCCCH8o1evXvTq1avQ7WfOnEmNGjV45513AKhfvz5///037777Lj179iyuMEuFmEAdUWaFkxf6AGvOungSc65tjbXH4Tr2BahZJQkc/76EPupOFH3u7YUQQoiyToZ5CL9Jd2nctzHDZ8W8GU0DiA0q2sLhmiuNKrtu4TP9YHR4724+Z3+Bv9KiCn2dr7KNktIrcFdlY5HGKYQQQhSXtWvXctNNN/ns69mzJ2vXrvVTRNcPRVFoH+m9j7vmbM5i5xfpLJUw1nzas63ZDuE6MrNY4xNCCCGuZ5KUEn7z9HYbe9O8tRb6VzIypFrRjj7S3BlkbuiDmryGbroVTNaP9Rxzawp3rc8gPj33YfjZ2d0a357w1pO6qbyBCmb59RFClG2BgYGcPn2a06dPExgY6O9wRD5OnjxJxYoVffZVrFiR1NRUbDZbrufY7XZSU1N9vsqq7FP4jtk0jmbkXSvKWPM5MEZ6th37XkNzphRrfEIIIa4f0n/yJZ+qhV98d8LBR4e8SZ4qAQofNQ9AUYpu2p7mzsS+sR/q2RWefY9aFjIkOsOzneTQuO2fdM47c66kk90vp5ykeAdKcZ9M3RNCCBRFoXz58pQvX75I37/FtWHy5MmEhoZ6vqpWrervkPymfYRvxYu1+YyWUoyhmGp7b4LhTMJ58O3iCk0IIcR1RvpPviQpJUrcCZvKiM3eu7IK8EXLQMJNRffjqKlO7Jvvxn0m23LMxnACbvidma2jaZftjueOVJVBmzJQtbwTU9mn7ll0cHu0TN0TQghx/YiKiuLUqVM++06dOkVISAgBAQG5njNmzBhSUlI8X0ePHi2JUK9JLcL0ZO+m5DeFD8BQ7RGUgBjPtjN+KmpmQjFFJ4QQQly/JCklSpSqaQzalMHZbCOTRtcx06V80SZ5nHtfxn16iXeHIQRLm6XoQ5pi1issamulssWblf4+wcmEPZm5XAnOOzUWJ3iTUrdEGQkxSkZbCCHsdjuPPfYYjz32GHa73d/hiHy0a9eO5cuX++xbtmwZ7dq1y/Mcs9lMSEiIz1dZZdYrtAzz3tBaczb/qf+K3oyp7uveHe4MnPsmFFd4QgghriPSf/IlSSlRot7db2d5ovfuYqswPRPqW4r0MdzJ/+A8MMW7Q2/F0vpn9GGtPbuiLDq+v8GKJdtvwKt77Hx73MGlfkhwkpmtdMR9VWSUlBBCALhcLj744AM++OADXK78R46IopWWlkZcXBxxcXEAxMfHExcXx5EjR4CsUU6DBg3ytH/44Yc5ePAgzz//PHv27OGDDz7gm2++4amnnvJH+Nel7FP4tpxzk+HKf+q/vtIAdCFNPduuo5+gpv1bbPEJIYS4Pkj/yZckpUSJ2XLOxZid3tFIgXqY2yoQk64o60jZsG8dAnizSOZmX6CP6JCjbatwA7Na+BaWG7Qpg60pvnc/vzrmTVSFGKB3lCSlhBBC+NfGjRtp3rw5zZs3B+Dpp5+mefPmvPLKKwAkJCR4ElQANWrU4KeffmLZsmU0bdqUd955h08++YSePXv6Jf7rUfZi5y4NNp4rYLSUosNY703vDs2N49+Xiis8IYQQ4rpkKLiJEFcvw6Vx34YMstcT/2+TAOoE6/M+6Qo4/n0ZLd17F1JfeSCGqH55tr+vqoltKW7e3Jc1bDLDDX3/SWNDl2DKm3Wcsav8dtqbve5XyYhFL1P3hBBC+FeXLl3Q8qmFOGfOnFzP2bJlSzFGVbq1i/TtNq9JctGpXP5daX25/0MX2R01KWvqpPvkt7iT/0EffkOxxSmEEEJcT2SklCgRz+ywsSfNO3rpjkpGhlUv2hXs3GdX44qf6tlWzNGYG0wv8LyJDS3cUtHbqTycodF/XToOVWPhCSfZR+ffV0VW3RNCCCHKomiLjhqB3q5zfivwXaQoCqZ6b/jsc+x5Pt+EohBCCFGWSFJKFLsfTjiZGe+dAlfZovBx84AiXf5Sc2dcmLbn7eSZGn+EYooo8Fy9ojC3tZV6Qd5fh5VJbp7cZmPeUW/cFcwK3crL4EIhhBCirGof6VvsvDDJJX1YK/TR93i21bOrcJ/+uVjiE0IIIa43kpQS/8/efYdHUXZtAL9nZnsaIZBCCIQOCT10RERBUETEhhVUxAYKIorYQFR4Fbv4yWsB9FUECyoKioIgVWnSe0kB0gikb52Z74/AljQSsiWB+3dducjMzsyeXQJ59sxzzuNT6RYFY/4tdm4LAP7XzYT6Ou/+6NkOPAe1+IhzW9P4Pmiibqjy+WFaAUt7B6Ge26p6c4/bsC7H1S/i9lgtNF7sf0VERER1i3uz89M2FUeKlEqOdtG1eRUQXOfaDj4LVa28JxUREdHlgEkp8hlFVTF6WzFybK67iE+30mNAQ+82Cpdz/oIj2VWmJxhioUt4p9rXaRUsYXF3U4X/KO5k6R4REdFlrXd9z16YG3OqllgSg1pC0+QR57ZasAeOE//zamxERER1UbWTUvHx8ZgxY4bHii5E5XnvqBV/uDUJ71pPwisJBq8+h+oohHXn/R77dB0/g6Ctd1HXuzZKizc7lI2xqUkoMxAlIrrcGY1GHD9+HMePH4fRaAx0OEQ+1yFUQpDbcGBjFfpKnadr9SIgBTu37YdehCqbvRkeERHVARw/eap2UmrixIlYsmQJmjdvjkGDBmHRokWwWq2+iI3qsB25Djy71+LcNknAwm4m6Lxc/mY7MAWq+bhzWxM3FpqGNVveemILPUY38ZzNdWdjnVd7YBERXQpEUUR8fDzi4+Mhipx8TZc+jSigp1sJX3WSUoI+Etrmk53bquUEHMkfejU+IiKq/Th+8nRRSakdO3Zg8+bNaNeuHR5//HHExMRg/Pjx2L59uy9ipDrmSKGMu7YWw+bWZuHdDka0CfHuTCP59Co4Uv7PuS0Ym0DX7s0aX1cQBMztbMKgyJJBZ4xBwOPN9TW+LhEREdV9fdxmTu/NV5Bnr/pKetrmkwBdpHPbdnQmVPtZr8ZHRERUl1x0Wq5r1654//33cerUKUybNg2ffvopunfvjs6dO2PevHlc6vYyo6oq1p12YMTfRWj9RwH2F7gyUiNitHgw3rv9mFR7Pqy7HvDYp+/4GQRtqFeub5AErOgThG0DgrHvmhA0MjKDTURUms1mw9NPP42nn34aNpvtwicQXQLcm52rAP6pzmwpTQh0raa5dtjPwn7kP16MjoiIajuOnzwJ6kVmj+x2O3744QfMnz8ff/zxB3r16oUxY8bgxIkT+PDDD3H11Vdj4cKF3o63xvLz8xEWFoa8vDyEhnongXE5cygqvjtlx9tHrNhytmyzz0YGAbuuDkGE3rtJHevuh+FI/di5rWnyKPQd/q+SM4iIyNuKiooQHFzSI6ewsBBBQUEBjsg3OHYowfehxFmbgvrL8p3b09rqMb1d1XuCqIod5r8SXKsGi3oYrzoM0Rjn7VCJiKgW4vjJk6bCRyqwfft2zJ8/H19//TVEUcSoUaPwzjvvoG3bts5jRowYge7du19c5FQn5NlVfJpsxftHrUg1l5/X7BkuYV5Xk9cTUo7s3z0SUoIxHrp2b3j1OYiIiIjKE64TkRAiYt+5WeEbz1RtBb7zBFELXZvXYP13ZMkOxQr7oenQd/rM26ESERHVetVOSnXv3h2DBg3CRx99hJtuuglarbbMMc2aNcMdd9zhlQCpdkkpVvDeESs+TbGioJzZ6gKAEY20eKqlHn0iqv3jdUGqPQ+2XWM89uk7zYegCa7gDCIiIiLv6lNfg30FJSUXf59xQFZVSNVYEEWKuRXisW5Q8rYCABwnFkDbfBLEkESfxEtERFRbVTtrcOzYMTRt2rTSY4KCgjB//vyLDopqn81nHHjriBXfn7JDLmdiVJAEjInX4YnmerQI9m5Dc3e2fZOgWk44tzXxj0OKuMpnz0dERERUWu/6Ej5NKfm+wFHS8LxjWNXHP4IgQtf2DVj+ufrcHgW2A1Nh6L7U+8ESERHVYtVOSmVlZSEjIwM9e/b02P/PP/9AkiR069bNa8FRYMmqiqXpJf2i1ueUPzU91iDgiRZ6jI3XIVzn22bgjqzlcJyY59wWTC2gazPLp89JREREVFrp2eAbzziqlZQCAKnBAEgNh0DO/g0AIGf9DPnMOkj1+3ktTiIiotqu2lmEcePGIS0trcz+kydPYty4cV4JigLLKquYc9SKNn8U4OZ/istNSHUOk/C/JBOODQ7FM60NPk9IqfazsO0a67ZHOFe2d2k2hSMiIqLaq3WwiPpaV7neppyqr8DnTtv2PyhpflDCtn8KV7AmIqLLSrUzCfv27UPXrl3L7O/SpQv27dvnlaAosEb8U4THd5lxtEgp89gN0Rr8eUUQtg8Ixj1NdNCJVe+fUBO2vROhWk85tzXNJvJOIhEREQWEKAjoXd81M6q6zc7Pk0I7QYq927mt5G6CnPlTjeMjIiKqK6qdlNLr9cjMzCyzPz09HRqN9xtbk39lWBT8mul5t88gAg/H67B/YAh+7h2MAQ21EKrRzLOmHJlL4Tj5hXNbCGoNXZtX/fb8RERUPqPRiD179mDPnj0wGo2BDofIr9xL+I4UKciylr2ZVxW61q8Aos65bTswFapycTOviIio9uP4yVO1k1LXXnstpk6diry8POe+3NxcPPfccxg0aJBXgyP/25vveadvQgsdUoeEYm4XE9qG+K6BeUVUWw5sux922yNC32kBBMnk91iIiMiTKIpITExEYmIiRNG3ZdxEtU2f+p7jok0V9N+8ENEUD01TVwsMtegAHCe4YBAR0aWK4ydP1X4H3nzzTaSlpaFp06YYMGAABgwYgGbNmiEjIwNvvfWWL2IkP9pb4HmXb0prAxrqA/cPxbr3CajWDOe2tvlTkMJ7ByweIiIiIgDoHq6B5DZxfOOZi5/dpGv5HKAJdW7bD02DUnSkJuERERHVCdXONsTGxmLXrl144403kJCQgKSkJLz33nvYvXs34uLifBEj+dE+t5lS4VoB0Xr/lemV5khfAvnUQue2ENQW2tYzAhYPERF5stlsmD59OqZPnw6bzRbocIj8KkgjoFOYe1+pi09KCboG0LZ41rmtWtNhXpsI28EXoDqKahQnERHVLhw/eRLUy2yJj/z8fISFhSEvLw+hoaEXPuEy029tgXO1vSsiJKy7MiQgcajWbBSvTQRs2ef2iDD03QSpXo+AxENERGUVFRUhODgYAFBYWIigoEtzRVSOHUrwfSjr8Z3FmHOs5AOFXgTyh4Vd9CIwqlwM81+JUM3JHvsFQxx0Ce9Air7Zrz09iYjINzh+8nTRncn37duH1NTUMpm9G2+88WIvSQGmqir25rvK9xIC0EMKAOS8f2HbO94tIQVoW0xhQoqIiIhqlT71Nc6klFUBduTK6FH/4obXgmSCodefsO4aAyVntXO/akmDdfutEBsMhD7hfYgh7bwSOxERUW1Q7d+ax44dw4gRI7B7924IgoDzE63O37mR5Ytr8kiBl2lVcdbumjiXGOrfpJRSfAy2gy9APvW1x34hOBHaVtP8GgsRERHRhbivwAeUlPBdbFIKAERTMxh6roKc/i1s+ydBtZx0PqacXgnzuo7QNnsS2lYvQtAEZjY7ERGRN1W7p9SECRPQrFkzZGVlwWQyYe/evVi7di26deuGNWvW+CBE8pfSK+8lhvinwblqzYR1z+Mwr2lbJiEFKQj6zl9AkPR+iYWIiMiX0tLScOLECef25s2bMXHiRHz88ccBjIouVhOjgEYGV0ndxjM1vzkrCAI0jW6Hsf8BaFtMBQSt60HVAfux2TCvaQPHyYW4zLpwEBHRJajaWYdNmzZhxowZaNCgAURRhCiKuOKKKzBr1iw88cQTvoiR/KT0ynu+nimlOgpgOzQNxatbwJEyB1DtHo9LUTfC2HcLpLCuPo2DiIjIX+666y6sXl1SmpWRkYFBgwZh8+bNeP755zFjBhfzqGsEQUAft5lRG3IcXksUCZpg6NrOhPHKPZAaDvZ4TLWmw7rjblj+vgpK/i6vPB8REVEgVDspJcsyQkJKpgs3aNAAp06dAgA0bdoUBw8e9G505FelV96L8tHKe6pshf34+yhe3QL2wzMA2XNVGTH8Chh6r4eh20/sm0BERJeUPXv2oEePkh6J33zzDdq3b4+NGzfiq6++woIFCwIbHF2UPhGum3inLCrSzN6dvSQGt4a++6/QJ/0IwRjv8ZhyZi3M67vCuncCVHuuV5+XiIjIH6qdlGrfvj127twJAOjZsyfeeOMNbNiwATNmzEDz5s29HiD5z94CV1IqMVT0+govqqrAcfIrmP9qC9u+CR6NzIGS3lH6bkth6L0WUv2+Xn1uIiKi2sBut0OvLylJX7lypXOBmLZt2yI9PT2QodFF6lO/bF8pbxMEAZro4TD231fSZ1N0a2ugynAkv4/iNa1hT5sPVVUqvhAREVEtU+2k1AsvvABFKfllN2PGDBw/fhz9+vXD8uXL8f7773s9QPKP0ivvJXpx5T1VVeHI+hWW9V1h3XFP2aWOjU2g67QAxit3QhM1jMsdExHVEQaDAZs3b8bmzZthMBgCHU6dkJiYiLlz52LdunX4448/MGTIEADAqVOnEBEREeDo6GJ0qSdB7zai3pjj/aTUeYJkhK71dBj774MUNdzzQVs2bLsegGVjX8h523wWAxER1QzHT56qvTzI4MGumvaWLVviwIEDOHPmDMLDw5lMqMNKr7yX4KV+UvLZf2A78CyUM2vKPqitD13L56Fp+hgEif8YiYjqGkmS0L1790CHUae8/vrrGDFiBGbPno3Ro0ejU6dOAIClS5c6y/qobtGJArrVk7DhXJPzTV5odn4hoqk5DN1+hCPrV9j2PgG1+IjzMSX3b1jWd4eu/YfQNn3U57EQEVH1cPzkqVpJKbvdDqPRiB07dqB9+/bO/fXr1/d6YORf3l55Tyk8CNvB5yBnLCn7oGiEtvkkaJs/DUEbVqPnISIiqkuuuuoqnD59Gvn5+QgPD3fuf+ihh2AymQIYGdVEnwiNMyn1b56MIoeKII3vb9ZqIq+DFLEH9uNvw37kVUAuPveICtu+iZAaDIQY1MrncRAREV2samUetFotmjRpAln2/R0g8i9vrrwnn1kP87ouZRNSggRNk0dgHHAUujavMiFFRFTH2Ww2zJ49G7Nnz4bNZgt0OHWC2WyG1Wp1JqRSUlLw7rvv4uDBg4iMjAxwdHSx+tR3jZtkFdia67+xsiDpoWs5Fcb+ByBF3+p6QLHBtneC11YDJCIi7+D4yVO1p8M8//zzeO6553DmzBlfxEMBstdLK++pshXWXWMAxeyxX4q5DcYr90Hf4SOIhpgaxUpERLWD3W7HM888g2eeeQZ2uz3Q4dQJw4cPxxdffAEAyM3NRc+ePfHWW2/hpptuwkcffRTg6Ohi9S7d7NyHfaUqIhrjoO/6DcSIq5375OxfIWf94vdYiIioYhw/eap2UmrOnDlYu3YtGjVqhDZt2qBr164eX1Q37fPSynv2Y29ALTrk3BbD+8DQdwsMXb+BGNy6xnESERHVZdu3b0e/fv0AAN999x2ioqKQkpKCL774ggvG1GFRBhEtglzD6oUnbNiU4/D7LCVBEKBPfB8QXDO3bPsmQpUtfo2DiIioqqrd6Pymm27yQRgUSN5aeU8pOgr7kddcO3QNYej+CwRteMUnERERXUaKi4sREhICAPj9999x8803QxRF9OrVCykpKQGOjmqiT30JR4tKxlN78hX0WVuI7uESJrTQ47ZYLXSifxYEEkMSoYl/Ao7j7wAA1OJjsB97E7pWL/jl+YmIiKqj2kmpadOm+SIOCqAML6y8p6oqbHsfBxSrc5+u3ZtMSBEREblp2bIlfvzxR4wYMQIrVqzAk08+CQDIyspCaGhogKOjmrgnTocv0+xwnxu15ayMe7YW4+k9Ah5tpsfDzXSI1NdsMZmq0LWaBvnUQqjWTACA/chMaGLvhWhq6vPnJiIiqg7f/1akWm+fF1bekzN+gJz9q3NbrN8fmth7axwbERHRpeSll17C5MmTER8fjx49eqB3794ASmZNdenSJcDRUU1cG6XF2n7BGBatQek5UekWFS/ttyDut3zcv60YO3J923NK0IZB2/YN1w7FDNv+p3z6nERERBej2tkHURQhSVKFX1T31HTlPdVRCNu+Ca4dggb69v930X2piIiILlW33norUlNTsXXrVqxYscK5/5prrsE777wTwMjIG65ooMHS3sE4NCgEE1roEFKqJsGmAAtSbeiyuhD91xZgyUkbHIpv+k5pYu+BGN7HuS1nfA85+w+fPBcREdHFqnb53g8//OCxbbfb8e+//+Lzzz/Hyy+/7LXAyH/cV96rfxEr79kOTYdqOeHc1jZ/CmJIgtfiIyIiupRER0cjOjoaJ06U/O5s3LgxevToEeCoyJtaBkt4t6MJM9oZsSDVhvePWp39ps5bmyNjbU4xmpoEjG+ux5imOoTrvFfEIAgidIlzYFmfBJwrKrTufQLGK3dCEHVeex4iIqKaqHZSavjw4WX23XrrrUhMTMTixYsxZswYrwRG/uO+8l5CNVfeU/J3w5H8rnNbMDaBtuWL3gyPiIhqKYPBgNWrVzu/pwtTFAWvvvoq3nrrLRQWFgIAQkJC8NRTT+H555+HKLKzwqUkVCvgiRZ6jG+uw/IMB947asXKbM/SvZRiFU/vsWDafgtGN9HhiRZ6tL3IRWdKk8K6QNPkYThS5wIA1KIDcBx/H9oWk71yfSIiqj6OnzwJqpfWqj127Bg6duzoHGDVVvn5+QgLC0NeXh4biqKkQXnEsnxno/OH43WY28VUxXMVWDZdCeXsBuc+fdKP0ESXTVwSERHVVd4cO0ydOhWfffYZXn75ZfTt2xcAsH79ekyfPh1jx47Fa6+9doErBA7HUN6xN1/G+0et+F+aDWa5/GPuidPiky4mGKSat0JQbTkoXtMasJ8p2SEFw3jVIYiGmBpfm4iIqCJVHTd45Xac2WzG+++/j9jYWG9cjvyo9Mp71ekn5TjxuUdCSoocxoQUERFRJT7//HN8+umnePTRR9GxY0d07NgRjz32GD755BMsWLAg0OGRHySGSvhvFxPSBofiP4kGxBnLJp6+TLNjxgGLV55P0EVA12ama4dcCNuBZ7xybSIiopqqdvleeHi4R3mXqqooKCiAyWTCl19+6dXgyPdKr7yXUMWV91RbDmz7n3btEI3QJb7vzdCIiKiWs9vt+PjjjwEADz30ELRabYAjqv3OnDmDtm3bltnftm1bnDlzJgARUaBE6EVMaW3AUy31+CHdjveOWLHhjGtcNvuwFXfH6aq9AE15NE0ehCP1Yyj52wEA8skvITd5CFL9fjW+NhERVQ/HT56qXb63YMECj6SUKIpo2LAhevbsifDwcK8H6G2ceu7p/aNWTNhldm6nXxeKaMOFE1PWXQ/BkfaJc1vbZiZ0Laf6JEYiIqqdioqKEBwcDAAoLCxEUFBQgCPyDW+OHXr27ImePXvi/fc9b+Q8/vjj2Lx5M/75558aXd+XOIbyva/SbLhna7Fzu1+EhL/6BXtlRWP57CZYNrpW4xNDOsJwxTYIYrXvURMRUQ1w/OSp2r+F7rvvvprERbXMxay8J5/d5JGQEoLbQdv8KZ/ER0REdCl54403MHToUKxcuRK9e/cGAGzatAlpaWlYvnx5gKOjQLursRZfp2mwLLOkGfq6HBmfp9pwX1N9ja8thfeGpvF9cJxYAABQCnbBkfpfaOPH1fjaREREF6vaPaXmz5+Pb7/9tsz+b7/9Fp9//rlXgiL/qe7Ke6rigG3Pox779O3/j0sLExERVUH//v1x6NAhjBgxArm5ucjNzcXNN9+MvXv34n//+1+gw6MAEwQBH3QywuhWsTd5jwWnrYpXrq9r+x9A47pbbTv4AlRrtleuTUREdDGqnZSaNWsWGjRoUGZ/ZGQkZs6cWc4ZVFupqoq9+a5BTmIVlh92pMyBkr/TuS3F3gMp4ipfhEdERHRJatSoEV577TV8//33+P777/Hqq6/i7Nmz+OyzzwIdGtUCzYIkvNTGtUR4jk3FlL1eanquj4Ku9cuuHY5c2A4+75VrExERXYxqJ6VSU1PRrFmzMvubNm2K1NRUrwRF/lHdlfcUy0nYDr7o2qEJg77dm74Kj4iIiOiy9FQrPRLdFp+Zl2LDutMOr1xb03QchOBE57Yj7VPIuVu8cm0iIqLqqnZSKjIyErt27Sqzf+fOnYiIiPBKUOQfe6u58p5t3yRALnRu69rMhKCP8klsRERERJcrrSjgo84mj32P7CiGTanW+kTlEkQt9IkfuO1RYds7HqrqnRJBIiKi6qh2UurOO+/EE088gdWrV0OWZciyjD///BMTJkzAHXfc4YsYyUf2FXgOPiqbKeXI/h1y+jfObTGsGzRNH/ZZbERERESXs34NNHigqatn574CBW8ftnrl2lKDAZBiRjq3ldzNzgboRERE/lTt1fdeeeUVJCcn45prroFGU3K6oigYNWoUe0rVMVVdeU+VLbDtcV+ZRYCuw1wIwoV7UBER0aVLr9fjl19+cX5PFbv55psrfTw3N9c/gVCd8nqiAT+l25FjK5khNeOgBSMba9EsqOZjMF27N2HO+hmQiwEAtgPPQhM9AoI2vMbXJiKiinH85KnaM6V0Oh0WL16MgwcP4quvvsKSJUtw9OhRzJs3Dzpd9Vdg+/DDDxEfHw+DwYCePXti8+bNlR6fm5uLcePGISYmBnq9Hq1bt+YSyhfJPSmVWMnKe/ajr0MtPuLc1jR9DFJYks/jIyKi2k2j0WDo0KEYOnSo80YVlS8sLKzSr6ZNm2LUqFGBDpNqmQZ6EW+2dzU9N8vA+J1mqGrNy/hEY2NoW7r1CrVlw3ZoWo2vS0REleP4ydNFvwOtWrVCq1atavTkixcvxqRJkzB37lz07NkT7777LgYPHoyDBw8iMjKyzPE2mw2DBg1CZGQkvvvuO8TGxiIlJQX16tWrURyXI1VVPcr3EipYeU8pOgL70VnObUEfBV2bV30eHxER0aVk/vz5gQ6B6qjRTXSYn2LD2pySm4nLMx1YcsqOW2KrfzO4NG2zJ+E4MQ9q0WEAgCP5Q2jjHoQY2rHG1yYiIqqKas+UuuWWW/D666+X2f/GG2/gtttuq9a13n77bYwdOxb3338/EhISMHfuXJhMJsybN6/c4+fNm4czZ87gxx9/RN++fREfH4/+/fujU6dO1X0Zl72qrLynqiWNL6G4+hfo2r0FQVvPHyESEVEtZ7fbsWDBAixYsAB2uz3Q4RBdkgShpOm5xm1C+xO7zCiwe6HpuaSHLuE9tz0KrHsfr9FMLLOs4s9sO5Zn2CF7YUYXEdGlhuMnT9VOSq1duxbXX399mf3XXXcd1q5dW+Xr2Gw2bNu2DQMHDnQFI4oYOHAgNm3aVO45S5cuRe/evTFu3DhERUWhffv2mDlzJmRZLvd4ALBarcjPz/f4orIr7yWGlv1RkDO+g5y9wrktRlwNqdFdPo+NiIjqBpvNhvvvvx/3338/bDZboMMhumQlhEp4upWr78gpi4qX9lu8cm1N5HWQom50bitn1kI+tajK56uqij35Mt4+bMGQDYWo/0serllfhKGbivDwv2avxEhEdCnh+MlTtZNShYWF5faO0mq11Ur4nD59GrIsIyoqymN/VFQUMjIyyj3n2LFj+O677yDLMpYvX44XX3wRb731Fl59teJyslmzZnn0bIiLi6tyjJey0ivvlS7fUx0FsO2d6NohaKFv/2GFfaeIiIiIyHdeaGNAM5Nr6P7+USu25zq8cm1dwjuA6Ep62fZPhuooqPD4bKuChWk23LetCLG/5aPDqgI8tceCFVkOWNyGmF+k2pBrUyq8DhERUbWTUh06dMDixYvL7F+0aBESEhK8ElRFFEVBZGQkPv74YyQlJWHkyJF4/vnnMXfu3ArPmTp1KvLy8pxfaWlpPo2xrrjQynu2Q9OgWk85t7XNn4YY3NZv8RERERGRi0kjYE4no3NbAfDIDrNXSuREU3NoW0xxbqvWU7Afdt30tcoqVmfbMXWvGUmrCxC5PB93by3G56l2pFsqfn67CvyS4Z3EGRERXZqq3ej8xRdfxM0334yjR4/i6quvBgCsWrUKCxcuxHfffVfl6zRo0ACSJCEzM9Njf2ZmJqKjo8s9JyYmBlqtFpLkmtXTrl07ZGRkwGazlTuDS6/Xc5nFclS28p6cvxOO5Ped24IxHtpWz/s1PiIiIiLydH20Frc20uK7UyU9SLaclfHf4zY81rzmY11tiylwnPgcqjkFqgrsOfoz/jKPwCpLe6w57UBRxd0ynOKMAgZHarH4pA0F53JR35+y454mNW/KTkREl6Zqz5QaNmwYfvzxRxw5cgSPPfYYnnrqKZw8eRJ//vknWrZsWeXr6HQ6JCUlYdWqVc59iqJg1apV6N27d7nn9O3bF0eOHIGiuKYBHzp0CDExMeUmpKh8la28p6oqbHseA1TXyEOX+AEEyeTXGImIiIiorHc7GhHidlt56l4zMiw1L5ETJBPsrd/Fm/KTSLDvQpJ9IyaltMWyzIoTUiYJGBqlwXsdjdg/MAQpg0PxSVcThkVrncf8lmlHkYMNz4mIqHzVTkoBwNChQ7FhwwYUFRXh2LFjuP322zF58uRqr4I3adIkfPLJJ/j888+xf/9+PProoygqKsL9998PABg1ahSmTp3qPP7RRx/FmTNnMGHCBBw6dAjLli3DzJkzMW7cuIt5GZetylbek08thHJ2o3NbiroJmqgb/BofEREREZUv1iji1QRXGV++A3hyd80ailtlFe8ftaL1rgGYLr+ENFTcg7VrPQnPttbjzyuCcGZoGH7pE4wnWujRNkRyzry/uZErKWVRShJTRERE5al2+d55a9euxWeffYbvv/8ejRo1ws0334wPP/ywWtcYOXIksrOz8dJLLyEjIwOdO3fGb7/95mx+npqaClF05c3i4uKwYsUKPPnkk+jYsSNiY2MxYcIETJkypaKnoHJUtPKe6iiC7YDbeykaoEt414+REREREdGFPNZMh89TbdieWzKmW3TCjvub2HFtlPYCZ3pyKCq+SLXh5QMWpJrLn80UjXRcI67GQN12DOkyBtHR5Vc0uBsSpYVRAsznhpzfn7LjllhWNRARUVnVSkplZGRgwYIF+Oyzz5Cfn4/bb78dVqsVP/7440U3OR8/fjzGjx9f7mNr1qwps6937974+++/L+q5qERFK+/Zj74O1XLSuV/bYgpEU1O/xkZERHWHXq/HN9984/yeiPxDIwqY29mInmsKcT6V9NhOM3Zfo4FRuvBKyYqq4ruTdry434JDhWVL/2INAsZHHcXVmY8gQd4CQUBJZ/Xtn8Pe7k1o4p+odEXmII2AIZFa/JBeMkPqlww7rLIKfRViIyK61HH85KnK5XvDhg1DmzZtsGvXLrz77rs4deoUPvjgA1/GRj5S3sp7SnEK7MdmO/cLhsbQtngmEOEREVEdodFocNttt+G2226DRnPRk6/pIn344YeIj4+HwWBAz549sXnz5kqPf/fdd9GmTRsYjUbExcXhySefhMVi8VO05G3dwzV4rLlr9tHRIgWzDlb+96mqKpZn2JG0uhAjtxSXSUhF6AS81d6Aw9eG4tmuXdHtyoUQQzu4XcAB276JsO64C6qjsNLnci/hK3AAK7O5Ch8REcDxU2lVTkr9+uuvGDNmDF5++WUMHTrUYwU8qlvKW3nPduAZQHENZHRtX2dzcyIiolpq8eLFmDRpEqZNm4bt27ejU6dOGDx4MLKysso9fuHChXj22Wcxbdo07N+/H5999hkWL16M5557zs+Rkze9lmBEtN41++g/h6w4UFB+V/K/TjtwxdpCDN1UhB15nseEaoCX2xlw7NpQTGplcM62EoNawtj3b0ix93gcL59aBPOGnlAKD1YY2w3RGmjdJkYtOcW+UkREVFaVk1Lr169HQUEBkpKS0LNnT8yZMwenT5/2ZWzkA6qqYq9b+V5iqAT5zDrI6d8494nhfSA1ujMQ4RERUR3icDjw7bff4ttvv4XDwVkQ/vT2229j7NixuP/++5GQkIC5c+fCZDJh3rx55R6/ceNG9O3bF3fddRfi4+Nx7bXX4s4777zg7Cqq3cK0At7t6Gp6bleBx3aYoaqu/lBbzzoweEMhrlpXiI1nPJNRBhF4ppUex64NxUttDQjVli2vEyQT9J2+gC7xQ0BwzX5SC/fBvKE7HOlLyo2tnk7ENZGuGQA/pdvhULgKHxERx0+eqpyU6tWrFz755BOkp6fj4YcfxqJFi9CoUSMoioI//vgDBQUFvoyTvCTDqiLXbeW9dsECbHsneByjS3i30j4BREREAGC1WnH77bc7e0ySf9hsNmzbtg0DBw507hNFEQMHDsSmTZvKPadPnz7Ytm2bMwl17NgxLF++HNdff32Fz2O1WpGfn+/xRbXP7bFaXOuW/Fl92oGv0uzYly/jln+K0H1NIX7P8vzQoxFKmqUfvTYUr7c3IkJf+UcCQRCgjX8Mht5rIRhiXQ84CmDdfgts+6dAVcp+sLo5xpXEyrGpWJvDD19ERBw/eapyUuq8oKAgPPDAA1i/fj12796Np556Cv/5z38QGRmJG2+80RcxkheVXnmvreUPKPn/Orc1je+DVK+7v8MiIiKiKjp9+jRkWXauVnxeVFQUMjIyyj3nrrvuwowZM3DFFVdAq9WiRYsWuOqqqyot35s1axbCwsKcX3FxcV59HeQdgiDgw05GuOeVHt5RjA6rCsqUzAkARsVpcXBQCD7sbEIjY/U+CkjhvWC8YjvEiAEe++3H3oBl87VQrZke+4c30np82GAJHxERlVbtpJS7Nm3a4I033sCJEyfw9ddfeysm8qG9+Z4NLVuefNa1IQVD22amnyMiIiIiX1uzZg1mzpyJ//u//8P27duxZMkSLFu2DK+88kqF50ydOhV5eXnOr7S0ND9GTNXRMljC820Mzu1iuWSxPHc3N9Ji9zUh+LxbEJoHXXxvWEEfCUOP36FtMcVjv5KzGub1SZDPumbrRepF9Gvgeq4lp+xQVJbwERGRS42SUudJkoSbbroJS5cu9cblyIf2uTW/rC8WI9K+37mtbfkcRENMIMIiIiKiKmrQoAEkSUJmpueslMzMTERHR5d7zosvvoh7770XDz74IDp06IARI0Zg5syZmDVrFhSldPqihF6vR2hoqMcX1V7PtNKjTXDZof3gSA22XBWM73sGITHUOwsVCaIGurb/gT5pCaAJce5XLSdh2dQf9uQ5zr5WNzdyrRCYblHxz5nyG7ETEdHlyStJKao73Mv32qo7cb51lGBsBm2zJwMUFREREVWVTqdDUlISVq1a5dynKApWrVqF3r17l3tOcXExRNFz2Hd+JWWVM1cuCXpJwPyuJpjO5Z361pewpl8wfusbjG7hvllyXBM9Asa+WyEEJ7p2qnbY9j4O6457oTqKMMKtrxTAEj4iIvLEpNRlpPTKe+0E1ywpXbs3IUiG8k4jIiKiWmbSpEn45JNP8Pnnn2P//v149NFHUVRUhPvvvx8AMGrUKEydOtV5/LBhw/DRRx9h0aJFOH78OP744w+8+OKLGDZsmDM5RXVf7wgN0oaE4uDAEKy7Mhj9G/gmGeVODG4NY99/yqzcLJ/6CpbNQ9BYZ0aPcNfP2Pen7EyEEhGRk+9/U1GtUXrlvbbCAQCAGDEAUvSIQIVFRERE1TRy5EhkZ2fjpZdeQkZGBjp37ozffvvN2fw8NTXVY2bUCy+8AEEQ8MILL+DkyZNo2LAhhg0bhtdeey1QL4F8pL5ORH3dhY/zJkETBH3nr+Co1xu2/ZMAtWSVPeXseli23oibo3/E5rMlxx4vVrAzT0bnevwYQkREgKBeZrcq8vPzERYWhry8vMuuN8LKLDsGbShybv+iuRFXiRtg7PcvxNCOAYyMiIjqIrvdjq+++goAcPfdd0Or1V7gjLrpch47uOP7QFUhn9kAy9bhgD3Hue94+P3okPm2c/uFNnq8kmAMRHhERAHH8ZMnJqUuI+8dsWLibrNz+6i2NWKb3gx9h7kBjIqIiKh2u5zHDu74PlBVyXnbYfn7asCR59zXS92FPfY4AEBCiIi9A/kzRER0KavquIE9pS4je/OKnd/XRw4iNTboWle8FDQRERERUXVJYV1h6PEbIAU7992ofOn8fl+BggMFXIWPiIiYlLqs7MlKdX7fVjgIfetpEPQNAxgRERHVZQ6HA8uWLcOyZcvgcDgCHQ4R1SJSeC8Yui8DxJIyvRuFXzwe5yp8RHS54vjJEzsMXibk/H3YbwlzbidoM6CJHxfAiIiIqK6zWq244YYbAACFhYXQaDisICIXKeJKGLr9BMvWYUhU96EljuAIWgIoSUo914YrPxPR5YfjJ0+cKVXLrMqy49oNhXhxn9lry+WqqorUPS8jF/Wc+9o37gxB9PPSLERERER0WZEaDoK+63cQRA1uFF2zpbblyjheyBI+IqLLHZNStYhDUXHP1mL8keXAqwet+DTZ5pXrylnLsDcn02Nfh0YdvHJtIiIiIqLKaKJugL7LItwoLfPY/93OnwIUERER1RZMStUiqWYFGVbX7Ki3jlih1HC2lKrYYNs/CfvUth77E0OkGl2XiIiIiKiqNDG3oE/nJxGLk859P2QbYTv8agCjIiKiQGNSqhY5XqR4bB8sVPBbZs0anzmS50AtOoz9bkmpCJ2ASL1Qo+sSEREREVWHtvFdGBFpdm7/rfbEiYMfwH7sLa8+j6yqeOeIBU/tNiPbqlz4BCIiChgmpWqR48Vlf2m+e9R60ddTrVmwHX4ZAHDQLSmVECJCEJiUIiIiIiL/uq1NZ+f3KkT8rAyFbf9k2JP/z2vP8fRuCybttuDtI1Zcu6EIspf6tBIRkfcxKVWLJJeTlPojy4E9+RfXBNJ26EXAkQ9VhcdMqcRQlu4RERERkf/1jZDQUOe6OfqTMgwAYNs7Dva0eTW+/rrTDo+bujvyZPwv1Tt9WomIyPsu77UHa5nS5XvnvXvEik+7mqp1LTlvBxypnwAAMhDtsfIe+0kREZE36HQ6zJkzx/k9EdGFSIKAmxpp8cm5BX3Wqv1wRq2H+kIubLsehCAaoIm966KuXeRQcf/2YpSeF/XCPgtGNtbBKLFSgIgCj+MnT0xK1SLlle8BwJdpNsxMNCBSX7WJbaqqwrZvInDuV/IBtY3H4wmhnCBHREQ1p9VqMW7cuECHQUR1zC1uSSkZGvyqDMHd0iIAKqw7RwGiHpqYW6p93al7zThazk3ekxYV7x2x4tk2hpqGTkRUYxw/eWJ2ohZxnynV1OS6k2NVgLnHqz7tWM5YAuXMX87tA8G3ezzOmVJEREREFCgDGmoQpnVtLzVMdG2oMqz/3glH5rJqXXNNth0fHHONlxsbBUS7Lewz65CFTc+JiGohJqVqCbOsIsPqmmw8Nl6PFkGuv57/O2aFVb5wk0ZVtsC2f7Jrh6jDwaCbnZtceY+IiLxFlmWsWbMGa9asgSxfXP9DIrr86EQBw6JdWamV5jYwN37CdYBqh3X7LZBPr6zS9QodKu7fbvbY91kXE2a0c82MyncArx601CxwIiIv4PjJE5NStURKqdK9FkEiJrTQO7czrSq+PnHh2VKO1I+hmpOd29pmT2K/Oci5nciV94iIyEssFgsGDBiAAQMGwGLhhz0iqrpbGrmSUlYFWFn/DWgaj3YdoFhh2TwE1h2joRQeqPRaz+wxeywY9FC8DtdGaXF/Ux3ahbjf5LXhSCE/ABJRYHH85IlJqVqidJPzZiYR9zfVeUxtfueIFeoFlrR1nPzCtaGLhKbFc9hb4Lp2AlfeIyIiIqIAuzZSC5PbsPSHdAd0HT+DFDPStVOV4Tj5Bcx/JcCyfSSU/F1lrrMyy46P3NpcNDUJeLO9EQCgEQW8nmh0PuZQgef38QMgEVFtwqRULVG6yXmzIBHBGgFjm7pmS+3KV7D6tKPCayiFh6DkbXNua+PuR4YjGLl2VyKL/aSIiIiIKNBMGgHXR7nuvi7LsMOqiNB3/h+kRneUOlqFnP4NzOs6wbJ1OOTczQCAfLuKMduLPY78rIsJIVpXVcAN0RpcGeEa/35z0o5/zlQ8niYiIv9iUqqWcJ9ybJKAhrqSX6aPt9DDffXad45YK7yG49TXHttSozuxr8BzinIiV94jIiIiolrgZrcSviIZ+D3LAUHUQt95IQw9V0Ksf1WZc+TMpbBs6AnLP4Px1LbjSDW7br4+1kyHayK1HscLgoDZ7Y0e+57ZY75g9QEREfkHMxS1hHv5XrzJ1fepiUn0qLn/JcOBQwVla+FVVYXj1ELnthCcADGkI/bme87ASuBMKSIiIiKqBYZGa6Fz+zSy5FRJGZ4gCJAaXANj79Uw9F4HqeGQMueuyHLg0/T6zu1mJgGvl0o+ndejvgYjY13j6bU5Mn7J4GwpIqLagEmpWsK9fK+ZyfOv5cmWeo/t946WnS2l5G+HWnTIua1pdBcEQcBetwQWV94jIiIiotoiVCtgUEONc3tpugN2xXMGk1T/Chh6/ApD3y2Qom4CAOSqoXjM8b7HcXN1k2HIWVbhDKjXEgxwq+rDlL1mOBTOliIiCjQmpWoJ95lSzYI8/1p61degV7hrhtOCVBvO2jxnQDlOepbuac7V4u/LdyWluPIeEREREdUm7iV8Z+0q1lTQP1Wq1w2Gbj/A2G8XntN/jVOIdT72qDgXfYs/hXXrMFjWd4Ej/TuoaqmVrYMlPNZc59zeX6BgfsqFV7YmIiLfYlKqFsi3qzjj1ow83lT2r8V9tlSxDHyS7PolqqoyZLd+UmK9nhCDWkBVVa68R0REPqPVavHGG2/gjTfegFarvfAJRESl3Bij9eifuuSUvdLjfy1uiy8K+zi3WwjHMF16xbmt5O+EdfttMK9tD8eJL6Gqrhu0L7QxINQ1MQsv7begyMHZUkTkXxw/eWJSqhZILr3yXjlJqZsbadHE6PqN/cExq3N6s3JmHVTrKedjmkZ3AQDSLSpX3iMiIp/R6XR4+umn8fTTT0On0134BCKiUhroRfRv4MoU/XDKDrmCEryzNgVj/3WtticAmNe9AcKajgJEz/+D1ML9sO68F5Z/BkG1Zjufa2prg/OYDKuKtytZRIiIyBc4fvLEpFQt4F66B5Qt3wMAjSjg8Rau2VInzCq+P3cnyXPVPRFSzO0A4NFPCuDKe0RERERU+7iX8GVaVWzKKbuoDwBM2GVGusWVsHqypR5XxjaBvsNHMA44Bk2ziYDo2excyVkN8/okyLlbSq7RUo/Gbjd63zhsQabFcyxORET+wyxFLXC82PMXb3kzpQDgwaY6BLlNdnrniBWKbIUj/VvnPrHB1RAN0QCAfVx5j4iIfEiWZWzZsgVbtmyBLJf/IZKI6EJGxHiWr3xfTgnfT6fs+F+aa3/rYBGvJrhmPYmGWOgT3oHp6mRoWzwLSEHOx1RLGiybroA99TMYJQGvtHOdV+gAZhywePPlEBFViuMnT0xK1QLu5XthWqCervy/lno6EQ80dU3v23xWxvpjmwD7Wee+86V7ALjyHhER+ZTFYkGPHj3Qo0cPWCz8UEdEF6eRUUTv+q6bp0tO2TxW0cuxKnh4h6tsTwTweZIJRqns2FbQR0LXdhaMV2yDENzO9YBig233g7Dufhj3xKro4FZB8N9kGw4W8IMhEfkHx0+emJSqBTxW3jNVPpvpiRZ6uP/6ffeY22woUQ9N9M3Ozb1ceY+IiIiI6gD3Er5Us4rtua5x7OO7zMi0upJUk1vp0au+BpURg9vA2PcfSNG3eux3pH4M+z/98Z9Whc59sgo8t48fDImIAoFJqVrgeLF7Uqryv5KWwRKGRbt+Cf9U3AkpahwAQGp4PQRtGABAVVXsc1t5L5Er7xERERFRLeWelAJcJXzfn7Th6xOusr12ISJediu/q4ygCYG+6zfQtn0D7h97lNzNuPJAZ1xdr8C5b8kpOzbmOGrwCoiI6GIwKRVgqqp6JqXKaXJe2pMtXQ3PFUiYKz8EANDEukr3Sq+8x35SRERERFRbNQ+S0DnMNV79/pQd2VYFj+4wO/dJQknZnqGcsr2KCIIAXYunYej5O6CNcO23Z2NG0XCPY5/eY/YoGyQiIt9jUirAcmwqCt1uysRfYKYUAPRvoPH4pf25MgoFUjSkyKHOfVx5j4iIiIjqklvcZksdKlRw46YiZNtcSaIprfToHl552V5FpAbXwHjFNohhSc59nYV/MVL8xrm98YyMH8ppsh4omRYFHxy1YutZzuAioksXMxUB5t7kHLhw+R5QcsdnYrzrF2Y+QvGV8TUIkmsJ3NIr77F8j4iIiIhqs9IlfH+fdd1kbR8q4qW2VSvbq4hoagpD7/XQNH7Aue8l6VXoYHVuP7vXArsS+NlSp60Kuq8pwBO7zOixphCLTtgCHRIRkU8wKRVgx0snpapQvgcAtwrfIwoZzu0Pi66H7DbduPTKew11bHJORERERLVXuxARbYLLjoXPl+3pq1G2VxFBMkDX8VPoOvwXELRoKqThEfFj5+OHixR8khzYBJCqqnjw32KkmUvG9iqAUVuL8UdW7ZnFRUTkLUxKBZj7yntA1cr3AEDM+BIPSZ+6rmM14Od01y8qrrxHRES+ptVqMW3aNEybNg1arfbCJxARVUIQBI8SvvOeb6NH13oXV7ZX0fNomzwEQ++1EAyxmCy9jXrIdT4+fU8O8m1yxRfwsbnHbfgp3bNkz64CI/4uwhaW8lWbqqqYl2zFrIMWnLUpFz6ByMc4fvLEpFSAuc+UaqgTEKS5cPJIMadBObMOY8T5MMDV/PGdIyVTj7nyHhER+YNOp8P06dMxffp06HS6QIdDRJeA0iV8ncJEPN+mZmV7FZHCe8F4xTY0iOiEp6W3nPuzZRP+s/ZzqPazPnneyuzNlzFpt7ncx4pk4PqNRThYELiEWV00+7AVY/4147l9Fty3rTjQ4RBx/FQKk1IBllzNlfcAQD61GICKBsIZ3CEudu5fmyNje66DK+8RERERUZ3UtZ6EAQ1KZkWFaYEvkoKgE30341/QR8HQ8w+Ma25AE6Q6979XMBjH1g6Bkr/LZ89dmkVWceeWIljcJvPMbm/A0CjXLLHTNhXXbijESTNn/FTFWZuCmYcszu2lGQ4cYlKPqFZhUirA3Mv3qtLkHAAcpxY6vx9v+tnjsXeOWLnyHhER+YWiKNi7dy/27t0LReEHJCKqOUEQ8FvfIPzeNwh7rglFxzDf31wVRC3C2s/GK81dM6OKEYRXC++EeWNvODJ/8XkMAPDMHjN2uy1WdF2UBk+11OObHkHoU9/1PqSaVQzeUIgzLEW7oLeOWJFXqhXXxwHuGUbE8ZMnZisCSFHVas+UUgoPQMn/17ndIa4HBke67p4sOmHHyizPWnOW7xERkS+YzWa0b98e7du3h9lcfrkJEVF16UQBgyK1aGz070eVezpeiS4hroTFF8q92O+Ig3XrcNhTP/Hpcy/LsOODY67njtILWJBkgiAIMGkE/Nw7CIkhrvdjb4GCYZuKUOwI/EqBtVW2VcG7R6xl9s9PscEi832jwOH4yROTUgGUYVFhdUuMVqXJuePU1x7bmkZ34cmWetfjKvDuUdd/vlx5j4iIiIjowkRBwOyO4c5tBRKmOaYBUGDb/RBsB1+Cqno/mZFuUcr0OlqQZEKk3vXZoL5OxIq+wWhidI3rN56RcfvmItgVJljK88YhK4rKqdQ7Y1fx3UmuZEhUWzApFUDus6SAC5fvqaoKx0lX6Z4Q0h5iaAdcG6lBgtudE/eZvFx5j4iIiIioaq6J1GKIWw+n5ep1eEd+AqoK2I+8AtuuB6Aq3ktoKKqK0duKcdrmSiw92UKPIVFlV+SKNYr4vW8wGrjdcF6W6cCD24uh+CBZBgAbchyYtMuMT45bUWCvO8mvdIuCOcdcN+pbB4sIcVvA8b/JZWdQEVFgMCkVQMdLJ6UuUL6n5G2DWnzEua1pdBeAktr7iS305Z7D0j0iIiIioqp7PdEI91u6L8ovY6r8KhRVgOPEAli3DoPqKPDKc71zxIo/3FpvdA6TMCux4tUG24RIWN4nCEFuQ/wv0uyYssdS4TkX40ihjFv+KcIVawvxzlErHtphRsyveXj432Jsz3Vc+AIBNvOgxaNh/KsJBtwb51rlbH2OjD35bHhOVBswKRVA7k3OBQBNLlA3797gHAA0je5wfn9PEx0iyinTY1KKiIiIiKjqOoZJeC3BMzE0RxmHB+X/wqZqIWevgGXTVVAsGTV6nu25Dkzd60omGSXg6+4m6KXKqxy6h2vwQ68gaN0Oe/OIFbMP1TwxlWNVMHFXMRJWFmDJKc8ZYUVySZPwpNWF6LGmAJ8lW1FUC3tapRYrHs3MO4WJuKWRFg8387yJ/9/jnC1FVBswKRVA7jOlGhmESn8BqaoM+dQi57ZYrzdEUzPntlES8EgzXZnz3Mv6iIiIiIjowqa2MWBOJ88ZU98ot+E2x9coUIOh5G+HZWNvKIUHL+r6RQ4Vd24phntF3HsdjGgbUrUbyoMitfiim8kjvmf2WrAg5eISLVZZxVuHLWj5RwHeO2rDhSr1tpyV8eC/ZjT6NQ/jdxZjd17tmXX06kGLRzuTGe2MEAUBHcMkj1UMv0i11cqkGtHlhhmLAKrOyntKzlqo1nTntib2rjLHjGuu97hjAnCmFBERERHRxRjXXI/FPUzQuQ3TV6nXYKjjJ2SpDaCak2He2AfymQ3VvvaEXWYcKnR9FrilkRYPxpe9wVyZOxrr8F5Ho8e+B/814+f0qve8UlUV35ywod3KAkzeY0FuqWzUVQ00+Lt/MBZ1N+GqBpoy5+c7gA+P2dDxzwL0/asA/0u1wRzAle2OFsqYn+KaJdU9XMKwaFfc7rOl8h3A4hM2EFFgMSkVQO7lexdqcu5ZuidCE3NbmWNiDCLuaOxqihhrEDxW7SAiIvImrVaLyZMnY/LkydBqyzblJSKq626L1eG3PkEeTbK3q10xyP4bktUmgP0MLP8MhCPjhypf89uTNnzmljhpbBTwcRfjRS1O9HgLPV5o40q0yCpw++YirD994b5Pm3Ic6Lu2ECO3FJfpddsmWMTSXkH484og9KyvwcjGOqzuF4z9A0PwZAs9wkvfCUfJaoCjthUj9td8TNplxoEC/8+emnHAAvfJT6+0M3i8r7fFaj1in5vMpBT5H8dPngTVF+ua1mL5+fkICwtDXl4eQkNDAxaHQ1FhWJqH8zcSXmqrx8vtjOUeq8pWFK+MBhy5AACpwbUw9FxR7rHpFgVDNhQixazgo04m3BlXvTsuRERE5Km2jB0Cje8DXc7+zXXguo1FyLS6PjpFIQM/aG5DR3EPAAG6xPehjR9f6XVSixV0+rPAOSNJALC6XzD6lzMLqapUVcUjO8wefZTqaQWs7ReMDmFlqyaOFcl4dq8F354sO6OqgU7Ay+0MGBuvg1asOElmllV8d9KO/x63YsOZipNPVzXQ4OFmOoyI0V6wV1ZNHSiQkbiyAOfTa1dESFjbL7hMsm/SLjPeOeoqc9x6VTCSwi/+/Sei8lV13MBpNAFywqzAfWZrfCUzpeTs35wJKQCQyindOy/GIGLnNaE4MzSMCSkiIiIiIi/oUk+Djf2D0dKt5UYmojHEsQxrlb4AVNj2Pg7b/ilQVaXca8iqinu2FnmUyD3fRl+jhBRQshL3/3U24uZGrhkXuXYVQzYWIrnIlTA6a1Pw1G4z2v5RUCYhpReBZ1vrceTaUDzWXF9pQgoo6Wd7bxMd1vcPwe5rQjC+uQ6h5byMNacduHNLMZquyMeKzKqXFV6M6fstcH/nS8+SOu/hUn14/8vZUkQBxaRUgCSXmiJbWfme49TXrg1RD03UiAteX7yI6b9ERETVoSgKkpOTkZycDEUp/0MYEdGlonmQhA39g5FUzzX7KB+huMnxPX5QbgQA2I+9AeuOUVCVsomOmQetWJfjShL1CpfwUltDmeMuhiQI+KqbZ9+nUxYVgzcW4aRZwXtHrGj5ewHePmIt08T87jgtDg4KxaxEI8LKKcu7kPahEj7oZMKp68LwWRcjuoeXnZ2VaVVx099F2HL2wmWFF2NXnozFbom2axpqcFXD8sui2oRIGOD2Pi1MsyH/Qp3dibyI4ydPTEoFSOm67WZB5TckVx0FkDOXOrelyBsgaDllnoiIAs9sNqNZs2Zo1qwZzGZzoMMhIvK5SL2I1VcEY2BDV1LDBj1GOebjY3kMAEA+9RUsm6+Das9zHrMxx4GXD1ic2yEa4KvupgvOSKoOgyTgp15B6OxWsneoUEH8inxM3G3GmVKJl34REjZfFYwvuwWh6QX621ZFkEbAA/F6bL4qBNsHBOPheB2C3WZPWRTgxk1FSC32/ofwafstHtuvtKs82ec+W6pIBr5K42wp8h+OnzwxKRUg7k3ONUJJU/LyyBk/AYrrB1XTqOLSPSIiIiIi8q0QrYBlfYI8FhhSIWKS/CZecUyFqgJKzp+wbLoSiuUk8uwq7t5a7NG6Y25nE5pXcFO6JkK1An7rE4QWbmWGjlKTgFoFifihpwl/9QtGdx/1UupST4O5XUw4NSQMw2Ncz5FhVTFsUyEKvDgzaetZB350W3Hw+igNekdU/rpGNNKioc71+euj41ZcZq2WiWoNJqUCxH2mVJxRhKaCuyQepXuaUEiR1/s6NCIiIiIiqoROLCmXm9DCsz/R68ozeFx+Bw5VglKwC+b1vfDI5hSP1h33xmlxlw97v0YZRPzeNwhRes/PFxE6Ae93NGLPwBDc1Eh3Uav9VVeIVsBX3YLQ1a3kcVe+gru2FkH2UhLopVKzpGZcYJYUUPL3Nybe9XewO1/B35U0bCci32FSKkDcfzE1Cyr/r0G1ZkM+7VplTxN9MwTJO3XnRERERER08URBwDsdjPhPouf4fIFyH+5xfA6zasDC4r5YlFXP+VjzIBFzOpl8HlvzIAm/9w1Gh1ARDXQCJrfU48igEDzeQg+dF0sGqyJII2BpryA0cqsM+SXDgad3Wyo5q2o25jjwa6arT9WIGG2VV9IbG6+D+zsx97i1wmOJyHeYlAoQ9/K9ipqcOzK+A1RXxp6le0REREREtYcgCJjS2oD5XY2Q3DIcv6hDMdTxEybJs537NLBjfvArCLbs90tsHcMk7Lw6BNlDwzC7gxH1dIH76BdrFPFz7yCY3CoW3zlqxX9rmAh60W2WlADg5SrMkjqveZCEayNdCaxvTtpxxsam00T+xqRUAFhlFacsrumqFc2Uci/dE/RRECMG+Dw2IiIiIiKqnvua6vFTryAY3ZIum9UeKESIc/sFaRaSzr4J89oOsO4YDaX4mM/j8keJXlV1rafBwm5BHrOTxu00448se4XnVGZ1th1/ZrtmSY1srEWHsOr16XrEreG5RQG+SGXDcyJ/Y1IqAFKKFbhXUMeXM1NKMadCObPOuS3F3A5B9E0jQiIiIiIiqpmh0Vqs6huM+tqyiaB+wjo8Kb53bkuB4+QXMK9pA+vux6BYTvk30AAa3kiLN9q7ZjPJKnDb5iLsz69ePydVVfHiPtcsKRHA9LbVb3NyQ7TWo6xw7nEbG54T+RmTUgGQXGoZ1PLK9xynFnlss3SPiIhqG41Gg8ceewyPPfYYNBreOCEi6h2hwforgxFndCU66msF/K9XY+gaDvQ8WHXAkfoRzKtbwLb/aai2036ONjCeaqnHg01dM5Ty7MDQTUXItla9dG5FlgMb3BqTj2qiQ5uQ6q9mqBEFjHVreH6wUMFfpx2VnEFUcxw/eaoVSakPP/wQ8fHxMBgM6NmzJzZv3lzhsQsWLIAgCB5fBkPdav59vHRSqpzyPdm9dM/YDGK9nj6Pi4iIqDr0ej0+/PBDfPjhh9Dr9YEOh4ioVmgXKmFj/xDc3EiLPvUl/NI7CE2ju8DQcwUMvdZADO/reYJigf3Ymyhe3Ry2Q9Og2vMCE7ifCIKA/+tsxNUNXR/GjxcrGPF3EazyhWcplZ4lpRGAl9pe/O+gB+P1Hh+K/5vMEj7yLY6fPAU8KbV48WJMmjQJ06ZNw/bt29GpUycMHjwYWVlZFZ4TGhqK9PR051dKSoofI6459ybnBhGILrVcq1KwD0r+Due2ptGdtaoenIiIiIiIKtbYKOL7nkHY0D8EvSNcyRcpoj8MvddB330ZxNAunic5CmA/PKMkOXX0DahysZ+j9h+tKOC7Hia0DnZ9HN1wRsaD/xZfsHxuaboDW3Nds6TGNNWhWVD1Z0md19go4oZo19/R9yftyKrGrC0iqpmAJ6XefvttjB07Fvfffz8SEhIwd+5cmEwmzJs3r8JzBEFAdHS08ysqKsqPEdec+0yppiaxTMLJvcE5AGhiWbpHRES1j6qqyM7ORnZ2NntwEBFVkSAI0EReD8MVW6Hv+g2EoLaeB9jPwH5gCsyrW8Ce/CFUuWYr1NVW4ToRy3oHefTg+jLNjlcPVvx6FVXFi/vNzm2dCDzfpuZVM480c81WsavA/BTOliLf4fjJU0CTUjabDdu2bcPAga76alEUMXDgQGzatKnC8woLC9G0aVPExcVh+PDh2Lt3b4XHWq1W5Ofne3wFmntPqdKle6qqeiSlxJCOEEMS/RYbERFRVRUXFyMyMhKRkZEoLr507+gTEfmCIIjQxNwG45W7oes4H4KxqcfjqjUDtr3jUfx7PZg39oV135NwnFwIpejIJfNBtmWwhB96BcG9N/xL+y1YfKL8pNB3J+3Yne/6LPVIMx3iyunPW13XRmk8Fp/6ONkG5RJ5j6n24fjJU0CTUqdPn4Ysy2VmOkVFRSEjI6Pcc9q0aYN58+bhp59+wpdffglFUdCnTx+cOHGi3ONnzZqFsLAw51dcXJzXX0d1uZfvlW5yruRtgVp81LktNbrTb3ERERFR3VGdnpwAkJubi3HjxiEmJgZ6vR6tW7fG8uXL/RQtEVVEEDXQxt0HY/+D0CXOgaCP9jxAsUA5uxGO4+/CuuNumNe0QvEfEbD8Mxi2gy/CkbkUiqX8z051wZUNNPiki8lj3+htxfj7jGfDcVlVMW2/q5eUUQKmtvZOb2FJ8Gx4fqxIwcosNjwn8oeAl+9VV+/evTFq1Ch07twZ/fv3x5IlS9CwYUP897//Lff4qVOnIi8vz/mVlpbm54g9FTpUZNtcWffSSSnHyYUe25pGd/glLiIiIqo7qtuT02azYdCgQUhOTsZ3332HgwcP4pNPPkFsbKyfIyeiigiSHtr4cTAOOApt2zcAbf2KD7afhXz6d9iPvArr1uEwr4pB8aomsGy7Bbajr0M+vRqqPfAVIlU1uqkOU1u7SuisCjD87yIkF7l6Ry1Ms+NAoevm/vjmekQbvPdx9oGmOmjcZmzNPc4SPiJ/COj6gw0aNIAkScjMzPTYn5mZiejo6ArO8qTVatGlSxccOXKk3Mf1en2t6mifXGrlvXi38j1VVSCnL3Zui+F9IZri/RUaERER1RHuPTkBYO7cuVi2bBnmzZuHZ599tszx8+bNw5kzZ7Bx40ZotVoAQHx8vD9DJqIqEiQTdC2ehrbJw5Azl0LO2wwldzOU/H8BpeJEiWpJg5yRBjljCewlV4IQ3BZSWDeIoZ0hhnaCGNIRgr6hv15KtbyaYMDhQgXfnSqJPsuqYtjfRdhwZQiMEjD9gGuWVLAGeKaVdz/jRRtEjGikxbcnS55/aYYdJ80KYo11bh5HuVRVxd4CBVZZRVJ4QNMARB4C+i9Mp9MhKSkJq1atcu5TFAWrVq1C7969q3QNWZaxe/duxMTE+CpMr0ou8kxKuc+UUouPQrW6pt5qYm73W1xERERUN1xMT86lS5eid+/eGDduHKKiotC+fXvMnDkTsiyXezwRBZ6gDYWm8T3QJ74PY9+/YRpcAMMVW6Fr/3/QNL4fQnAigMpW6FahFu6H4+T/YNv/FCz/DETxykgUr2wEy+brYDvwbEmPqoK9UJXAl6qJgoDPk0zoHu5aSW9PvoKRW4rwWYoNx9w+R01soUcDvfc/yj7SzFXCJ6vAZ5dAw/Mcq4J3j1jQYVUBOqwqQLc1hZiyx3zhE4n8JOAp0kmTJmH06NHo1q0bevTogXfffRdFRUXOO3+jRo1CbGwsZs2aBQCYMWMGevXqhZYtWyI3NxezZ89GSkoKHnzwwUC+jCo7XlxxUkrJ2+7xmFi/r19iIiIiorqjsp6cBw4cKPecY8eO4c8//8Tdd9+N5cuX48iRI3jsscdgt9sxbdq0cs+xWq2wWl2rYNWGxWKILmeCqIMUlgQpLAlo+igAQHUUQMnbDjl3M5S8LVByN0M1p1R6HdWaDjk7HXL2b66doh5icCLE0I7nZlR1ghjaCYKukhJCHzBpBPzUKwg91xQgzVzS8uS3TAd+z3QlzeppBTzV0jeVMAMaaNAqSMThcwmwT5KteK61HhqxsuRf7aOoKlZnO/Bpig1LTtlh8/wIijcOWzEwUoNBkdrABEjkJuBJqZEjRyI7OxsvvfQSMjIy0LlzZ/z222/OgVZqaipE0ZW4OXv2LMaOHYuMjAyEh4cjKSkJGzduREJCQqBeQrW4NzkP0QD1da7/4DySUoIGYnB7f4ZGRERElyhFURAZGYmPP/4YkiQhKSkJJ0+exOzZsytMSs2aNQsvv/yynyMlouoQNCGQIvpDiujv3KdasyDnbnEmqZT8fz2qMcqlWKHkb4eS73mTXDDEliSoIq6CptFIiMYmvngZHmIMIn7uHYwr1hag8Fwuyj2n8lRLPerpfFPwIwgCHm6mw+Q9JaWCJ8wqfs10YFhM3UjenDIrWJBqKzOzrDxjthdjzzWhCNXWrYQbXXoCnpQCgPHjx2P8+PHlPrZmzRqP7XfeeQfvvPOOH6LyDfeZUvEmEYLg+k9AdvslIIa0hyDVnl5YREREpWk0GowePdr5PfnHxfTkjImJgVarhSS5ymLatWuHjIwM2Gw26HS6MudMnToVkyZNcm7n5+fXilWMiahygj4SmqihQNRQ5z7VmgUlf2fJV8Gukj8L9wFq5WV7quUkZMtJyNnLYT/wDMTwPtDE3AEp5jaIhqr1AL4YncIkfN0tCMP/LvJISEXoBExo4dvPSKOb6PD8Pgus55547nFrrU5KOZSSxNmnyVYsy3RAVss/LtYgoHmQiHU5JWXbaWYVk/eY8XGplQ/J9zh+8sR3wM+OF7t6N3j0k1JVj5lSYmhXv8ZFRERUXXq9HgsWLAh0GJcd956cN910EwBXT86KbvL17dsXCxcuhKIozhnohw4dQkxMTLkJKaD2LRZDRBdP0EdCajgIUsNBzn2qYoNSuP9csmoXlIKSpBVs2RVeRzm7EbazG4F9EyFGDICm0Uhoom+GoIvwesw3xGjxVgcDntztanA+pZUeIT6e2dNAL+K2WC2+TCtpeP5rpgPJRTLig6QLnOlfx4tkfJZiw/wUG05Zys9ESQIwLFqLB+N1GBypgUUBOq4qcE6U+CTZhlsbaXFtVO1Nul2KOH7yxKSUn7mvvtfMfeU9cypgP+PcFsOS/BoXERER1R3V7cn56KOPYs6cOZgwYQIef/xxHD58GDNnzsQTTzwRyJdBRAEkiDpIoZ0ghXZy7lNVFao1w3NG1dn1JZ9VPChQclbBlrMKtj2PQWpwLaRGd0ATNRyCNtRrMU5ooYdVAd47asWABho84eNZUuc9HK93JqVUAJ+m2PBqgtEvz10Zq6zip3Q7Pkm2YWV2xbPcWgSJeLCpDqOb6hBjcH3mDBaBeV2NGLC+yLlvzL8lZXxhLOOjAGFSyo/O2hTk2V3bzUyubLuSt83jWDGMM6WIiKh2U1UVxcXFAACTyeRRkk6+Vd2enHFxcVixYgWefPJJdOzYEbGxsZgwYQKmTJkSqJdARLWQIAgQDDEQDTFA5BAA5yo6cv+B49QiyOnfQLWme56kOiBnL4ecvRw2UQ8pcig0je6AFDkUglSz0jBBEDCltQFTWhtqdJ3q6hshITFExN6CkgkFnybbMK2tAVo/Njw3yyr2F8jYm69gb76MvQUyNp2RkWMrf1aUXgRuaVQyK6p/Aw3ECn4nX9VQi/HNdZhzrGRlwRNmFU/tNuPTrizj8xeOnzwJqqpWUHV6acrPz0dYWBjy8vIQGuq9LH5VbM91IGl1oXP7x55BGN6oZKqk7eALsB957dwjIkxDCmr8nzgREZEvFRUVITg4GABQWFiIoKCgAEfkG4EcO9QmfB+ISFVlKGfWwXFqERzp3wH2nIoPloIgRQ0vSVA1HAxBLL9UuLaac9SKx3eZndvf9jDh1ljvvwaLrOJg4bnE07nk0958BUeLFFTlg3r7UBFj4/W4u7EWEfqqNYAvcqjo+GeBRzP0X/sEYQjL+PyC4ydPnCnlR8dLrYDgXr7n3k9KCG7HhBQREREREdUqgiBBirgKUsRV0CV+APn0Ksjpi+DI+AFw5HseLBdBPrUQ8qmFgDYcmkZ3QhP3AMTQrnViZsi9TXSYsteM8y2B5x631SgpZZVVHC5SsOd88ilfwd4CGUcKFVS+Tl5ZQRJwR2Mdxsbr0CNcqvb7GaQRML+rCf3XuSZMjGUZHwUIk1J+5N5PCnA1OldVFbJb+Z7E0j0iIiIiIqrFBFELTeQQaCKHQNd+LuTs30pK/DKXAorZ82D7WThS/g+OlP+DGNoJmsYPQBN7t08apHtLmFbAnY11+CylpMxtVbYDhwtltAouv+G5qqo4bVNxrEjBsaKSmU7HihQcK5ZxrEjBCbNapZlP5dEKQOtgEYmhEgZFajAyVlfjhu9XNtDgiRY6vH/UVcY3abcZn13iZXw2RcWXqTbk2lXcFadDtKFqs8vId5iU8qPjbkmpCJ3g/I9EtaYDtiznY+wnRUREREREdYUgGaCJvgma6JugOgohZ/1SkqDK/hVQbB7HKvk7Yds3AbYDT0OKugmauAcgNRgIQahdq9sBwMPNXEkpAPjwmBWPNdPjWLFSKvkk41ixgsKKe49XiUYAWgWLSAyRkBhakoRKDJHQKlj0ST+rmQlGLMtw4Oi5ip55KSWr8V0XfWmW8W3PdeC+bcXYnV/yel/cb8HjzfV4prUe9XVMTgUKk1J+5F6+F28qv3QP4Mp7RERERERUNwmaYGga3QFNozug2nPhyFgCx4kFUM6s8zxQsUFO/wZy+jcQDHHQNL4Pmrj7IJqaBybwcnSrJ6FrPQnbc0tq+N47asN7R20XOOvCRJxLPoWWNFRPDJWQGCqhdbAInR+bqbuX8Z2fxfXgv8XYe00I6l1CSRqrrOLVgxbMOmSF7DZdrVgGXj9sxUfHrXiqlQETW+gRyvJFv2NSyo/cZ0o180hKlVp5L7Szv0IiIiIiIiLyCUFbD9q4B6CNewBK4SE4TsyH48TnZVbwUy1psB95BfYjr0CMuBrauAcgRd8MQTIGKPISgiDgkXgdHtphvvDB5WhsFNDcJKJ5kITmQSJaBolICJXQJliEQaodyY9+58r4zifbTllUPLnbgvlJl0YZ37azDty3vRh78ivu3JXvAKbtt+D9o1Y821qPcc31MNaSv5/LAZNSfqKqqkdPKY8m5/luTc6DWkPQhPg1NiIiIiIiIl8Sg1tD13YWtK1fgZy9Ao4T80r6T6meNW9Kzp+w5vwJaMLONUcfAzEsKWDN0e+M0+HlAxactJTtCGWSgOZBIloEiWhuKkk8nf+KN9WexNOFnC/jO3KusmdBqg23xmoxtA6X8VllFa8ctOA/pWZHAcBtsVpcH6XBzINWHHarZsqxqXh6jwVvH7HihTYGPBiv8+vMtcsVk1J+kmVVYZZd280qKN9jPykiIqorJEnCrbfe6vyeiIjoQgRRA03UUGiihkK1ZsFx8kvY0z6DWrjP80BHHhypc+FInQshpAO0cWOhaTwagrbipeV9IVgjYNUVwVh4wgZJEM4loEoST5F6oU6sJHghJo2ABUkm9FvrKuN76N9i7LkmBOF1sIxv61kH7i9ndlRDnYAPOxtx27lVFO+J0+HzVBtePmBBmtmVuUq3qBi304w3Dlswra0B98bpoPFicorjJ0+CqqoXuwhAnZSfn4+wsDDk5eUhNNR//6H9fcaB3n+5ltxc3jsI10VroVqzULwyyrlf2/YN6Fo87be4iIiIqHKBGjvUNnwfiMhXVFWFkrsZjhPz4Dj1NeAoKP9ATQg0je+HNv5xiEEt/RvkZWDSLjPeOWp1bo9uosWCpKAARlQ9VlnFjAMWvH647Oyo22O1mNPJiIb6skk2q6zi42QbXjtoQaa1bHqkTbCIGe0MuDVWC/ESSEL6S1XHDXUv7VlHuTc5B1zle3L+vx77Jc6UIiIiIiKiy4ggCJDCe0Lf4b8wXZMOXafPIdbvX/ZARwEcye/DvKY1LFtugCP7d1xmcyx86tUEA1q5tZn5PNWOX9LtAYyo6raedSBpdQFmlirXa6gT8G0PExb3CCo3IQUAeknA4y30OHZtKF5PNKB+qWbnBwsVjNxSjK6rC/BLup0/c17GpJSfuPeTAoCm58r3yq68x6QUERERERFdngRNELSNR8HYew2MVx2GtsVUCPqoUkepkLOWwbp5MMx/JcCe8hFUR2G516OqM2kEzE8ywT0l89COYpy1VdwkPNCssorn9prR669C7C3wjHNkrBZ7B4bg1nPlehdi0gh4prUBxwaHYlpbPUJKNTvamadg2N9F6PNXIf7MrhvJurqASSk/cV95L1ovOLv5u6+8JxibQdCG+z02IiKii1FUVARBKOmnUVRUFOhwiIjoEiMGtYSu7UwYB6RA3+l/EMO6lTlGLToA257HULyqMaz7noJSfCwAkV46+kZo8GRLvXM73aJiwq6LW33Q17acdaDr6gLMKjU7KlIv4LseJiyqZHZUZcK0Aqa3M+LYtaF4upUexlJtn/4+K+Oa9UUYvqkQ5tJ1glXA8ZMnJqX8xL18z2PlPTY5JyIiIiIiqpAg6aFpfA8MfTfD0GcTpEZ3AkKpaSyOPDiOvw3z6pawbB0O+fSfLLO6SK8mGNA62PWZ9X9pdvxci8r4LLKKqXvN6LWmEPtKzY66o7EWe68JwS1VnB1VmQZ6EW+0N+LotaEY11yHUlV9WJrhwN1biiHz56xGmJTyE/eZUudX3lPtZ6Gajzv3MylFRERERERUvpLeU71g6LIQxqtToG35IqBrWOooFXLmUlj+uQbmtR1gT/0YqlwckHjrKqMkYEFXk0ey4KF/i3EmwGV8qqriz2w7klYX4D+HrHCPJlIv4PseJnzdPQgNLmJ2VGViDCLmdDLh0KAQ3N9E5/G+/JBux8RdZiZAa4BJKT+QVRWpxWVnSil5nk3OxVAmpYiIiIiIiC5ENDSCrs0MmK5Oha7TAoihXcocoxbuhW33wyhe1Ri2/U9DzlkDVbYEINq6p3eEBpPcyvgyrIEr47MrKr5Os6H7mkJcs76ozOyoO8/NjrrZC7OjKhMfJGFekgnrrgz2KOmbc8yGt45YKz6RKsWklB+cMquwuyVO4ytocs6V94iIiIiIiKpOkAzQNh4NwxXbYOi9HlLMbYBQqgmQ/Szsx96E5e8BKP49HOa/r4bt8CuQz6yHqtgCE3gdMCPBgDZuZXxfptnx0yn/lfHl21W8fdiClr/n466txdiWK3s8HqUXsKSnCQt9MDuqMn0iNPi6W5BHMuXpPRYsOsGfpYuhufAhVFPHS628d758T853JaUEQ2MI+ki/xkVERERERHQpEAQBUv2+kOr3hWJOgyPlI9hTPwbsOZ4HKhYoOauh5KyGHQAkE8TwvpAiroYUMQBiWBIEkR+TgXNlfEkm9P2r0Fkq9/COYlwREYIIHyaBTpgVvH/Uiv8etyLfUfZxEcC9TbR4q73Rp3FUZngjLd7vZMT4na7ZY6O3FSNaL+CqhtqAxFRXcaaUH7g3OQfcy/dcK++xnxQREREREVHNicY46NrOhOmaNOg6fgYxLKnig+ViKKf/gP3gVFg29kLxH/Vh2TwU9qNvQs7bBlWVKz73MtCrvgZPtXKV8WVaVdy9tRg/p9uRZfVuj6kduQ7cu7UIzVbkY/bhsgmpIAmY2EKPo9eGYEFSUMASUueNa67HFLf3xqYAN/1ThL35l/fPTHUxBewHyW4zpUQAcUYRqj0fatEh1372kyIiojpGkiRcf/31zu+JiIhqE0EyQhv3ALRxD0C1ZkHOWQM5ZzXknNVQiw6Wf5KjAHL2csjZy0u2NfUgRVwJKWIApKjhEE3N/PcCaokZ7Qz4Od2OA4Uln2tXZDmwIqskYxRvEtEzXELP+hJ6hmvQpZ4EoyRUdjkPqqpiRZYDbx22YmV2OdOiAMQYBExoocdD8TqE62rXvJqZiQakmRUsPFFS1phnB67bWIi/+4egkbH8WDl+8iSol1mb+Pz8fISFhSEvLw+hoaF+ec77thXh89SSH9ImRgEpQ8Ign1kHy6Yrncfouy2FJmqYX+IhIiKiqgvE2KE24vtARJcSxXIKSs4ayDl/liSpio9V4SwBUtQwaOMnQIwYAEGoevKlrtt8xoHebmV8FdEIQKcw6VyiSoOe4RJaBYsQS71XVlnF1ydKGoTvyS//qh1CRTzV0oA747TQibX3vbbKKq7bWITVp11JtU5hItb2C0GotvbG7WtVHTdwppQfuJfvuUr3PJucs3yPiIiIiIjIP0RDI4ixd0ETexcAQDGnQj7Xa0rOWQ3VnFrOWSrkzKWQM5dCCGkPbfwEaGLvhiAZ/Rt8APSor8GX3UyYeciCvfkKKprZ4lCBbbkytuXK+L/jJY2/62kF9AgvSVT1CNdgd76M949akWEt/yqDIjWY3FKPQZGaOpH400slDdf7rSt0Jth25im45Z8iLOsTVKsTarUBZ0r5QZPf8pBmLnmb72uiw/wkE6w7RsNx8gsAgKCPgvGa9DrxD46IiOhywxlCJar6PsiyDLvdf6sz0eVNq9Wy/IW8TlVVqObjkE+vPpeo+hOqNb38g7UR0DZ5CJqmj0E0NvZvoAGSb1exNdeBf87I+OdsyZ8VJZiqSiMAdzXWYlIrAzqF1c1/02nFCnr/VYCTFtd7MSpOiwVJplr7Wd8sq7DKKur5oCySM6VqCZui4qTZ9UN5fqaU+8p7YmjXWvtDSkREVJGioiJERpasHJuVlYWgoKAAR0SBpKoqMjIykJubG+hQ6DJTr149REdHczxNXiMIAgRTc4hNmkPbZAxUVYVydiPsye9BzlgCuDc/t+fAfnQW7MfegBR9K7TNJkCs1+uS/nkM1Qq4uqEWV59bZU5VVaSZVfxz1oHN5xJVW3NlmKvQ7ztMCzwcr8fjLfRoXEEPproiziRieZ9g9Ftb4GzS/kWaHU1MFryS4JpNF8jxk6yq2J4rY2WWAyuzHdiQ48CzrfWY3i5ws/2YlPKxtGLFo+423iRClYuhFuxz7mPpHhER1VXFxcWBDoFqifMJqcjISJhMtfeuMF06VFVFcXExsrKyAAAxMTEBjoguVYIgQKrfF1L9vlDMaXCkfAh76ieA/YzrIFWGnL4YcvpiiGHdoW02AVLMbRBEXeAC9xNBENDEJKCJSYfbYkv2ORQVe/Jl/HNWds6o2l/gKvtrYhTwZEs9xjTVI+QS6rvUMUzCkp5BGLKxCI5zL/bVg1bEGUU81My1Up+/xk+qquJIkeJMQv2Z7UCu3XNW28osB6a380s45WJSyseOF3s2bWtmEqHk7wLcUlVceY+IiIjqMlmWnQmpiIiIQIdDlxGjseTuflZWFiIjI1nKRz4nGuOga/sfaFu9BMfJr2A//h7Uwr0exyh5W2DdcQ+E/U9D0/RRaJs8DEEfGaCIA0MjCuhcT4PO9TR4+NyChfl2FdtzHdCKAnqGS9Bcor2WronUYl5XE0ZtcyWeHt1hRiODiBtitD5//kyLgj+zS5JQK7PsSDVXXlr591kZ+XY1YE3ZmZTyMfcm50BJ+Z6SySbnREREdOk430PKZDIFOBK6HJ3/ubPb7UxKkd8IkgnaJmOhiXsQSs4q2I+/DznrF8CtBbhqTYf90EuwH3kVmkZ3QRP/BKSwLoELOsBCtQKuauj7pExtcG8THU6YFTy3zwKgZErKyC1FWNMvGAlenjxX6FCx7rQrCbWrgtUMS2sVJGJgpAYDG2rgg5ZSVcaklI8lu82U0gpAI4MAu1s/KWjDIRibBiAyIiIiIu9iyR4FAn/uKJAEQYDUYCCkBgOhFB2BPXkOHCfmAY4C10GKDY4TC+A4sQBCUFtookdAir4ZYlgSf34vYc+21iPVrGDuuVUIi2Xghk1FWNWtZn/nWVYF/+aWlEauyrJj0xkZ9ir0mW+oE5xJqGsitWhqqh09vJiU8jH38r2mJhGiIEDJc2tyzv+IiIiIiC4Z8fHxmDhxIiZOnFil49esWYMBAwbg7NmzqFevnk9jIyLfEoNaQp/4LnStZ8BxYgHsye9DLT7qcYxadKCkMfrRWRCMTSBFjYAm+maI9ftCEDjT71IiCAI+6GjESbOCnzNKOp9nWVXc9HfV+kmpqork4pIE1L95svPPU5aqrXRokoD+DUqSUAMjtWgfWpKPqG2YlPIx9/K9ZkEiVNkKpWCPc5/EflJEREREfnehm4LTpk3D9OnTq33dLVu2VGslpT59+iA9PR1hYWHVfq7qYPKLyH8EbSi0zZ6AJn485KzlsCe/B+X0yjLHqeZUOJLfgyP5PUDXEJqomyBFj4AUcTUESV/Olamu0YgCvu4ehKvXF2Lz2ZLlCI8WlS2vcygqDhSeS0CdSz7tyJPLNCWvjCQAPcIlZxKqV30JujrQt4tJKR9znynVzCRCKdwDqHbnPvaTIiKiukoURfTv39/5PVFdkp6e7vx+8eLFeOmll3Dw4EHnvuDgYOf3qqpClmVoNBceOjds2LBaceh0OkRHR1frHCKqGwRBhCbqBmiiboBSeACO9O8gZyyBkv9v2YNt2XCkfQJH2ieAJhRS5A3QRN8MqeEQCJqqJ7qp9gnSCPi5dxD6/FVYkpASRCCxL8K1Ap7YZcFuq4LdeTIsVWsF5aFt8Pm+UFpc1VCDsDq4kiFHkD5kllVkWl2ZzWYm0aN0D2BSioiI6i6j0Yg1a9ZgzZo1zhWwiOqK6Oho51dYWBgEQXBuHzhwACEhIfj111+RlJQEvV6P9evX4+jRoxg+fDiioqIQHByM7t27Y+VKz9kP8fHxePfdd53bgiDg008/xYgRI2AymdCqVSssXbrU+fiaNWsgCAJyc3MBAAsWLEC9evWwYsUKtGvXDsHBwRgyZIhHEs3hcOCJJ55AvXr1EBERgSlTpmD06NG46aabLvr9OHv2LEaNGoXw8HCYTCZcd911OHz4sPPxlJQUDBs2DOHh4QgKCkJiYiKWL1/uPPfuu+9Gw4YNYTQa0apVK8yfP/+iYyG6FInBbaFr9QKM/bbDOOAYdO3ehhh+BYBykgiOfMinFsK6/VYU/9EAlq0jYD/xBVT7Wb/HTd4RqRfxa58gNNAJgN4IvPILzr70M+ZlSNhy9sIJKRFAuxARdzXWYnZ7A1b2DcLp60Oxf1AoPuhkwvBG2jqZkAI4U8qnkktNy4sPEqGcdUtKaUIgmFr4OSoiIiIi31LteVAKdgfs+cWQDhC0NS+He/bZZ/Hmm2+iefPmCA8PR1paGq6//nq89tpr0Ov1+OKLLzBs2DAcPHgQTZo0qfA6L7/8Mt544w3Mnj0bH3zwAe6++26kpKSgfv365R5fXFyMN998E//73/8giiLuueceTJ48GV999RUA4PXXX8dXX32F+fPno127dnjvvffw448/YsCAARf9Wu+77z4cPnwYS5cuRWhoKKZMmYLrr78e+/btg1arxbhx42Cz2bB27VoEBQVh3759ztlkL774Ivbt24dff/0VDRo0wJEjR2A2my86FqJLnWhqBrH5k9A2fxKKJQNy5k+QM5ZAzvkTUB2eBysWyJk/Qs78ETZBA7F+P0gNB0NqOARiSEf2J65DWgVL+Ll3EAasK6w0CaUXgQ6hErrUk9AlrOTPjqESTJpL8++aSSkfci/dA87NlEpxa3Ie2gWCwMlqREREdGlRCnbDsqlfwJ7f0HsdpPpX1Pg6M2bMwKBBg5zb9evXR6dOnZzbr7zyCn744QcsXboU48ePr/A69913H+68804AwMyZM/H+++9j8+bNGDJkSLnH2+12zJ07Fy1alNy8HD9+PGbMmOF8/IMPPsDUqVMxYsQIAMCcOXOcs5Yuxvlk1IYNG9CnTx8AwFdffYW4uDj8+OOPuO2225CamopbbrkFHTp0AAA0b97ceX5qaiq6dOmCbt26ASiZLUZEVSMaoiE2fRjapg9DtZ+FI/OXkgRV9m+AYvE8WHVAyVkNJWc17AeehaCPhtTgWkgNh0BqOAiCrkFgXgRVWa/6GnzbIwh3bi1CoQMI0wKdwyR0CdM4k1BtQ0Ro60AvKG9hUsqHSiel4o0KlPydzm0xLMnfIREREXlNUVGR88NncnJytZo7E9UF55Ms5xUWFmL69OlYtmwZ0tPT4XA4YDabkZqaWul1Onbs6Pw+KCgIoaGhyMrKqvB4k8nkTEgBQExMjPP4vLw8ZGZmokePHs7HJUlCUlISFOUiGpIA2L9/PzQaDXr27OncFxERgTZt2mD//v0AgCeeeAKPPvoofv/9dwwcOBC33HKL83U9+uijuOWWW7B9+3Zce+21uOmmm5zJLSKqOkEbDm3je6FtfC9URxHk7BVwZCyBnPUz4Mgvc7xqzYDj5BdwnPwCgAAxLOlcgmowxHq9IIj8uF8bDQi1Qf9AK+gApBw/7tHD8HLEaTo+5L7ynkkCGtgOAIrVuY8r7xERUV13+vRpnD59OtBhEPlE6UTr5MmT8cMPP2DmzJlYt24dduzYgQ4dOsBms1V6Ha1W67EtCEKlCaTyjlfVqq/A5AsPPvggjh07hnvvvRe7d+9Gt27d8MEHHwAArrvuOqSkpODJJ5/EqVOncM0112Dy5MkBjZeorhM0QdDE3AxDly9hGpQNffdfoWnyKARjswrOUKHkbYX9yKuwbOqH4j8iYNl2C+ypH0MpTvFr7HRhOadP48zp0yy/BGdK+VSy20ypeJMIJZ9NzomIiOjSJ4Z0gKH3uoA+vy9s2LAB9913n7NsrrCwEMnJyT55roqEhYUhKioKW7ZswZVXXgkAkGUZ27dvR+fOnS/qmu3atYPD4cA///zjnOGUk5ODgwcPIiEhwXlcXFwcHnnkETzyyCOYOnUqPvnkEzz++OMASlYdHD16NEaPHo1+/frh6aefxptvvlmzF0tEAABB1EETOQSayCFQVRVq8RHI2StKvnL+BOTisic58kvKADOWlFwjqG1JL6rI6yBFXA1B1JY9hygAmJTyIffyvWalk1KiEUJwmwBERURERORbgjbMKz2daptWrVphyZIlGDZsGARBwIsvvnjRJXM18fjjj2PWrFlo2bIl2rZtiw8++ABnz56t0h333bt3IyQkxLktCAI6deqE4cOHY+zYsfjvf/+LkJAQPPvss4iNjcXw4cMBABMnTsR1112H1q1b4+zZs1i9ejXatWsHAHjppZeQlJSExMREWK1W/PLLL87HiMi7BEGAENQKYlAraOPHQ5WtUM5ugJz9G+TsFVAKdpV7nlp0AI6iA3AkvwfoGkATcwc0sfdArNeDs3UooJiU8iH38r1mQSKUPPcm550hCFIgwiIiIiKii/D222/jgQceQJ8+fdCgQQNMmTIF+fll+7z42pQpU5CRkYFRo0ZBkiQ89NBDGDx4MCTpwmPL87OrzpMkCQ6HA/Pnz8eECRNwww03wGaz4corr8Ty5cudpYSyLGPcuHE4ceIEQkNDMWTIELzzzjsAAJ1Oh6lTpyI5ORlGoxH9+vXDokWLvP/CiagMQdJDanA1pAZXA+3egGI5BTn7d8inV0DO/gOw55Q9yXYajpQ5cKTMgWBqCU3sPdDE3g0xqKX/XwBd9gQ10AXqfpafn4+wsDDk5eUhNDTUZ8+TZ1dR75c85/ab7fV45GhDQC4CAGiajoO+/RyfPT8REZGvFRUVOZtzFhYWXrKNzv01dqjtKnsfLBYLjh8/jmbNmsFgMAQowsuXoiho164dbr/9drzyyiuBDsfv+PNHVD5VlaHkbXOW+ilnNwGoeHanWK9XSYKq0Uiu5OdDHD954kwpH0kutfJeUzHDmZACuPIeEREREV2clJQU/P777+jfvz+sVivmzJmD48eP46677gp0aERUiwiCBKleD0j1egCtXoRqOwNHxndwnPwSypmyff+U3L9hy/0btn0TITW8DprYeyBFDYMgGQMQPV0umJTykeNFssd2U3mPxzabnBMRUV0niiK6devm/J6I/EMURSxYsACTJ0+Gqqpo3749Vq5cyT5ORFQpQVcf2iYPQdvkISjFyXCcWgjHif9BLTrgeaDqgJz1M+SsnwFNCDTRt5b0n4roX2kLGlWxQ7VlQbVmlny5f2/NhGor+VPQhELXbjak8N4+fsW1E8dPnpiU8pHjpWZKNbFucm2IOojBCSAiIqrLjEYjtmzZEugwiC47cXFx2LBhQ6DDIKI6TDTFQ9fyOWhbTIWS/y8cJ7+EfGohVGum54GOAjhOzIfjxHwIhlhIMXdA0IY7E0zuySfYz1TpuVUAlr+vgT5pCTSRQ7z/4mo5jp88MSnlI+5NzutpBYQWbnJW74ohHbkEJxEREREREQWUIAiQwrpCCusKte0bkHP+hHzySzgylni0nwEA1XISjuNveeeJFTOsW28EunwFTcxt3rkm1UmcK+Yj7j2l4k0ClHy3lfdYukdERERERES1iCBqoGl4LfSdv4BpYCb0nb+C1HAIapw20IRBCGoNsX4/z97Kqh3W7XfAnvpZza5PdRpnSvmIe/levN4MmF3LBYuhTEoREVHdV1xcjISEknL0ffv2wWQyBTgiIiIi8gZBEwRN7F3QxN4F1ZoJx6lFJQ3S87aWHKCNgKCPcn3poiDoI8/96b4/EoLkWhVTVRyw7R4Lx4kF5/YosO1+EHDkQdt8kt9fZyBw/OSJSSkfUFXVo3wvXsrweJwr7xER0aVAVVWkpKQ4vyciIqJLj6CPgrbZBGibTYAqFwOC9qLb0QiiBrqOnwGaUDiS33fut+1/Cqo9F9rWL0MQBG+FXitx/OSJ5Xs+cNqmwn3xvabKQdeGoIEY0t7/QRERERERERHVgCCZatwfWRBE6BLehbbVNI/99iOvwLZvIlRVqeBMuhQxKeUDyaVW3ouzu/WTCkn0mL5IREREREREdDkRBAG61tOha/e2x35H8vuw7XoAquIIUGTkb0xK+YB76R4ANDH/5fye/aSIiIiILh1XXXUVJk6c6NyOj4/Hu+++W+k5giDgxx9/rPFze+s6RESBom3+JHQdPoV7asJx4nNYt98OVbYGLjDyGyalfOB4qZlSTR27nN9z5T0iIiKiwBs2bBiGDBlS7mPr1q2DIAjYtWtXuY9XZsuWLXjooYdqGp6H6dOno3PnzmX2p6en47rrrvPqc5W2YMEC1KtXz6fPQUSXN22TMdB3XQQIrrJAOfMHWLYOg+ooCmBk5A9MSvmA+0ypSK0NQUKxc5tNzomIiIgCb8yYMfjjjz9w4sSJMo/Nnz8f3bp1Q8eOHat93YYNG/ptJaXo6Gjo9Xq/PBcRkS9pYm6DvttSQDQ69ymn/4Dln0FQ7WcDGBn5GpNSPuDeU6qplOP2iAgxpPqDGyIiotpIEAQkJCQgISHhkl8phy49N9xwAxo2bIgFCxZ47C8sLMS3336LMWPGICcnB3feeSdiY2NhMpnQoUMHfP3115Vet3T53uHDh3HllVfCYDAgISEBf/zxR5lzpkyZgtatW8NkMqF58+Z48cUXYbfbAZTMVHr55Zexc+dOCIIAQRCcMZcu39u9ezeuvvpqGI1GRERE4KGHHkJhYaHz8fvuuw833XQT3nzzTcTExCAiIgLjxo1zPtfFSE1NxfDhwxEcHIzQ0FDcfvvtyMzMdD6+c+dODBgwACEhIQgNDUVSUhK2bi1ZUj4lJQXDhg1DeHg4goKCkJiYiOXLl190LERUt2kih8DQ83dAE+rcp+RuguXvAVCtmZWcWbdw/ORJE+gALkXu5XtNhWTn90JwWwiaoABERERE5H0mkwl79+4NdBhUC+XZVezOky98oI90CJMQpq18oK/RaDBq1CgsWLAAzz//vPODwbfffgtZlnHnnXeisLAQSUlJmDJlCkJDQ7Fs2TLce++9aNGiBXr06HHBOBRFwc0334yoqCj8888/yMvL8+g/dV5ISAgWLFiARo0aYffu3Rg7dixCQkLwzDPPYOTIkdizZw9+++03rFy5EgAQFhZW5hpFRUUYPHgwevfujS1btiArKwsPPvggxo8f75F4W716NWJiYrB69WocOXIEI0eOROfOnTF27NgLvp7yXt/5hNRff/0Fh8OBcePGYeTIkVizZg0A4O6770aXLl3w0UcfQZIk7NixA1ptSYnOuHHjYLPZsHbtWgQFBWHfvn0IDg6udhxEdOmQ6l8BQ6/VsGweDNhOAwCU/J0wb+oHQ8+VEI1NAhxhzXH85IlJKS9TVNVzppS82/k9+0kRERHR5WB3nox+6wovfKCPrOsXjCsaXHiY+8ADD2D27Nn466+/cNVVVwEoKd275ZZbEBYWhrCwMEyePNl5/OOPP44VK1bgm2++qVJSauXKlThw4ABWrFiBRo0aAQBmzpxZpg/UCy+84Pw+Pj4ekydPxqJFi/DMM8/AaDQiODgYGo0G0dHRFT7XwoULYbFY8MUXXyAoqOQm6Jw5czBs2DC8/vrriIqKAgCEh4djzpw5kCQJbdu2xdChQ7Fq1aqLSkqtWrUKu3fvxvHjxxEXFwcA+OKLL5CYmIgtW7age/fuSE1NxdNPP422bdsCAFq1auU8PzU1Fbfccgs6dOgAAGjevHm1YyCiS48U1hXG3utKSvcsJSXWatFhWDZeAUPPPyAGtwlwhORNLN/zsnSLCptbn/Om8j7n9xJX3iMiIiKqNdq2bYs+ffpg3rx5AIAjR45g3bp1GDNmDABAlmW88sor6NChA+rXr4/g4GCsWLECqampVbr+/v37ERcX50xIAUDv3r3LHLd48WL07dsX0dHRCA4OxgsvvFDl53B/rk6dOjkTUgDQt29fKIqCgwcPOvclJiZCkiTndkxMDLKysqr1XO7PGRcX50xIAUBCQgLq1auH/fv3AwAmTZqEBx98EAMHDsR//vMfHD161HnsE088gVdffRV9+/bFtGnTLqqxPBFdmsTgtjD0Xg/B1NK5T7WkwbypH+S8HYELjLyOSSkvSy698p7gGlBwphQREV1KiouLkZiYiMTERBQXF1/4BKJaaMyYMfj+++9RUFCA+fPno0WLFujfvz8AYPbs2XjvvfcwZcoUrF69Gjt27MDgwYNhs9m89vybNm3C3Xffjeuvvx6//PIL/v33Xzz//PNefQ5350vnzhMEAYqiVHB0zU2fPh179+7F0KFD8eeffyIhIQE//PADAODBBx/EsWPHcO+992L37t3o1q0bPvjgA5/FQkR1i2hqCkPvdRBCOrh22rJh+fsq2E/8D/LZf6AUJ0OVzYEL8iJw/OSJ5Xte5r7yHgA0FVKc34uhXfwdDhERkc+oqop9+/Y5vyc6r0OYhHX9AtcbqEOYdOGDzrn99tsxYcIELFy4EF988QUeffRRZ3+pDRs2YPjw4bjnnnsAlPRQOnToEBISEqp07Xbt2iEtLQ3p6emIiYkBAPz9998ex2zcuBFNmzbF888/79yXkpLicYxOp4MsV96jq127dliwYAGKioqcs6U2bNgAURTRpo1vSl3Ov760tDTnbKl9+/YhNzfX4z1q3bo1WrdujSeffBJ33nkn5s+fjxEjRgAA4uLi8Mgjj+CRRx7B1KlT8cknn+Dxxx/3SbxEVPeIhmgYe62BZctQKLnn/v905MG2c5TngZowCPpoCPqoc3+6f7nt0zWEIGrLPpEfcfzkiUkpL3Nvci5AQRxKamCFoFYQtKEVnUZERER0yQjTClXq6VQbBAcHY+TIkZg6dSry8/Nx3333OR9r1aoVvvvuO2zcuBHh4eF4++23kZmZWeWk1MCBA9G6dWuMHvPhoPAAADUCSURBVD0as2fPRn5+vkfy6fxzpKamYtGiRejevTuWLVvmnEl0Xnx8PI4fP44dO3agcePGCAkJgV6v9zjm7rvvxrRp0zB69GhMnz4d2dnZePzxx3Hvvfc6+0ldLFmWsWPHDo99er0eAwcORIcOHXD33Xfj3XffhcPhwGOPPYb+/fujW7duMJvNePrpp3HrrbeiWbNmOHHiBLZs2YJbbrkFADBx4kRcd911aN26Nc6ePYvVq1ejXbt2NYqViC49gq4+DD3/gGXrTVByVpV/kCMPqiMPatHB8h93XQ3QRUAMagNt/BOQYm6FILCALJD47nuZ+0ypRkIW9ELJ1GuR/aSIiIiIaqUxY8bg7NmzGDx4sEf/pxdeeAFdu3bF4MGDcdVVVyE6Oho33XRTla8riiJ++OEHmM1m9OjRAw8++CBee+01j2NuvPFGPPnkkxg/fjw6d+6MjRs34sUXX/Q45pZbbsGQIUMwYMAANGzYEF9//XWZ5zKZTFixYgXOnDmD7t2749Zbb8U111yDOXPmVO/NKEdhYSG6dOni8TVs2DAIgoCffvoJ4eHhuPLKKzFw4EA0b94cixcvBgBIkoScnByMGjUKrVu3xu23347rrrsOL7/8MoCSZNe4cePQrl07DBkyBK1bt8b//d//1TheIrr0CJpgGLr/Ak3j+1GzNIYK2E5DObsB1n9HwrK+GxxZv3LGUgAJ6mX27ufn5yMsLAx5eXkIDfX+zKWr1xVi9WkHAKC3sAl/aK8HAGjbvg5di2e8/nxERESBUlRU5Fy+vbCw0KPB8qXE12OHuqKy98FiseD48eNo1qwZDAZDgCKkyxV//oguL6rtDFTLCSjWDKjWTKjWDLcv1zbsOVW+pli/H3RtZkGq39eHkZfg+MlT3ZhXXYe4l+/Fu/WTktjknIiIiIiIiKhGBF19CLr6ENGx0uNUxQbVmgXVlgnV4pa4Mh+H4+RXgGJxHqucWQfLpisgRQ6Fts1rkEI7+fpl0Dks3/Mih6IizexKSjUFm5wTERGRb3z44YeIj4+HwWBAz549sXnz5iqdt2jRIgiCUK0yNCIiorpGEHUQjY0hhSVBEzUU2iZjoGv1PPQdP4VxwFFomjwCCJ7zdOSsZbCs6wLLv3dBKToSoMgvL0xKeVGaWYHsVgx5fqaUYIyHoIsIUFRERES+IQgCmjZtiqZNmzpXKyP/WLx4MSZNmoRp06Zh+/bt6NSpEwYPHoysrKxKz0tOTsbkyZPRr18/P0VKRERU+4iGRtB3+AjG/gcgNbobgPs4RoV86muY/2oH6+5HoFhOevW5OX7yVCuSUpfKnb5kt9I9AGgipAIARJbuERHRJchkMiE5ORnJyckwmUyBDuey8vbbb2Ps2LG4//77kZCQgLlz58JkMmHevHkVniPLMu6++268/PLLaN68uR+jJSIiqp3EoBYwdPkSxn47IEUO83xQdcCR+l+YV7eEbf8zUG1V71FVGY6fPAU8KXUp3elzX3kPAOLPJ6W48h4RERF5ic1mw7Zt2zBw4EDnPlEUMXDgQGzatKnC82bMmIHIyEiMGTOmSs9jtVqRn5/v8UVERHQpEkM7wtB9KQy9N0Cs39/zQcUC+7HZKF7dHLbDr0J1FAYmyEtUwJNSl9KdPvcm5xrYEYuSaX6cKUVERETecvr0aciyjKioKI/9UVFRyMjIKPec9evX47PPPsMnn3xS5eeZNWsWwsLCnF9xcXE1ipuIiKi2k+r3gaHXauh7/FZ2cokjH/ZDL6J4dXPYj78HpTgFqjUbqlwMVVXKvyBdUEBX3zt/p2/q1KnOfdW907du3bpKn8NqtcJqtTq3fXmXzz0pFYcTkISSba68R0RElyKz2Ywrr7wSALB27VoYjcYAR0TlKSgowL333otPPvkEDRo0qPJ5U6dOxaRJk5zb+fn5TEwREdElTxAEaBoOhtRgEOSM72E7+ALUokOuA2zZsO2bCOyb6HmiaAQkEwRNECCaIEgmQBNU8qfo+t5s12Hg6O8BUYe16zfDFBLpz5dX6wQ0KVXZnb4DBw6Ue875O307duyo0nPMmjULL7/8ck1DrZI7YnVoahRx5OR61DdvBwAI+kYQ9FEXOJOIiKjuURQFW7dudX5P/tGgQQNIkoTMzEyP/ZmZmYiOji5z/NGjR5GcnIxhw1y9Ms7/fWk0Ghw8eBAtWrQoc55er4der/dy9ERERHWDIIjQxNwGKWoEHCc+h/3wdKiWExWfoJgBxQzVXtJ7Sq3gMJsF2Lan5PvC1e2h7TQDmrgHIYgBTc8ETMDL96rjYu70TZ06FXl5ec6vtLQ0n8V3Q4wWryUaMV/3BN7UPAsAEMOSfPZ8REREdPnR6XRISkrCqlWrnPsURcGqVavQu3fvMse3bdsWu3fvxo4dO5xfN954IwYMGIAdO3Zw9hMREVElBFEDbZMxMF51GLp2bwO6qs86viB7Nmx7HoV5bQc4MpdCVStKZV26ApqK88edPn/f5VMdhVCLDjq32U+KiIiIvG3SpEkYPXo0unXrhh49euDdd99FUVER7r//fgDAqFGjEBsbi1mzZsFgMKB9+/Ye59erVw8Ayuwnio+Px8SJEzFx4sRqnZeTk4N27dph8+bNiI+P91o8zz77LIqKivDBBx947ZpERBdDkAzQNn8SmiZjIZ9ZB9jPQJWLAbkYqlx07s9iQC5y7nf/XnUUAUrJPsBzJT+16ACsW4dDrH8ldO3ehFSve2BeZAAEdKbUpXinT8nfAfeJekxKERERkbeNHDkSb775Jl566SV07twZO3bswG+//eZsiZCamor09PQAR1n73XfffRAEwfkVERGBIUOGYNeuXV57junTp6Nz585VOs49lvNfbdu29VosvvTaa69h+PDhzoTUzp07ceeddyIuLg5GoxHt2rXDe++9V+a8r776Cp06dYLJZEJMTAweeOAB5OS4PqxNnjwZn3/+OY4dO+avl0JEVClBEwxN5HXQxN4NbZOx0DabAF3L56Br8yr0CW9D3+G/MHT+HwxJ38PQ4zcYe6+F8YqtMF21H6arUxB0TYrrYppQj2srZ9bCsqEHLP/eCaX4uJ9fWWAEvGjxUrvTp+Rt99gu07GfiIiIyAvGjx+P8ePHl/vYmjVrKj13wYIF3g+ojhoyZAjmz58PAMjIyMALL7yAG264AampqX6PJTExEStXrvTYp9EEfLh+QcXFxfjss8+wYsUK575t27YhMjISX375JeLi4rBx40Y89NBDkCTJ+XO7YcMGjBo1Cu+88w6GDRuGkydP4pFHHsHYsWOxZMkSACWVFYMHD8ZHH32E2bNnB+T1ERH5iunK3dCkvwNH8oeAanful08tgjljCTRNx0PX8nkIuvoBjNK3At5T6lK706fkuyWldA0hGGIDFwwRERERVUqv1yM6OhrR0dHo3Lkznn32WaSlpSE7O9t5TFpaGm6//XbUq1cP9evXx/Dhw5GcnOx8fM2aNejRoweCgoJQr1499O3bFykpKViwYAFefvll7Ny50znzqbKEoEajccZy/su9j2p8fDxeeeUV3HnnnQgKCkJsbCw+/PBDj2ukpqZi+PDhCA4ORmhoKG6//fYyrTJ+/vlndO/eHQaDAQ0aNMCIESM8Hi8uLsYDDzyAkJAQNGnSBB9//HGl7+Hy5cuh1+vRq1cv574HHngA7733Hvr374/mzZvjnnvuwf333+9MNgHApk2bEB8fjyeeeALNmjXDFVdcgYcffhibN2/2uP6wYcOwaNGiSmMgIqqLBF0E9AnvwNh/P6SY2z0fVGxwHH8bxWtawn7sLaiytcbPp6oylMIDcJxcCOu+yTD/fTVsh1+r8XVrIuBJKaDkTl9KSgqsViv++ecf9OzZ0/nYmjVrKv3lvWDBAvz444++D7KKZLeZUlJYVwiCEMBoiIiIfKtBgwZVXnyELj9FRUUVflksliofazabq3RsTRUWFuLLL79Ey5YtERERAQCw2+0YPHgwQkJCsG7dOmzYsAHBwcEYMmQIbDYbHA4HbrrpJvTv3x+7du3Cpk2b8NBDD0EQBIwcORJPPfUUEhMTkZ6ejvT0dIwcObJGMc6ePRudOnXCv//+i2ef/f/27jysqnLtH/h3bWTcugEHFERwSjRTjjgdtNTEADUcT9Yblb71Zo7pW5l60qPVqdQGO2+WZRmn0qNmR5Mi8aiplceJBNFCRCUzJ8yBeeb+/cGPfdywh7VYWwb9fq6L65K913Pve8HT4tuz115rHmbNmoXt27cDqLwMxujRo3H16lXs2bMH27dvx+nTpy1eMyEhAWPHjsWIESOQnJyMnTt3ol+/fhav8eabb6JPnz5ITk7GtGnTMHXqVKSnp8OW77//Hr17O765T3Z2Npo3/8+7/eHh4Th79iy++eYbiAguXbqEL774AiNGjLAY169fP/z2228WC4FERI1Z9fxkMHaCR9gGeAzYD4Pv3ZYbl15DSdpzKNzTFWXn1kFE3R2PpaIMFTlHUfrbJyj+aRYK/30PCrZ5o3BPNxSnxKIs801UXNmF8qt7nLlrmjX884EbESkvhOT9bP7eYOKd94iI6NZlNBotziYhqq5p06Y2nxsxYgQSEhLM3/v5+aGgoMDqtoMHD7b4SGL79u3x+++/19iuNnct+vrrr8195ufnw9/fH19//TUMhsr3bjds2ICKigp89NFH5jcb4+Li4OPjg927d6NPnz7Izs7G/fffb77hTrdu3cz1mzZtaj4DypGjR4/W+Jk98sgjeP/9983fDxw4EPPmVd7luUuXLti7dy+WL1+O++67Dzt37sTRo0eRmZlpvtbqp59+iu7du+PQoUPo27cvXnnlFTz00EN48cUXzTVDQ0MtXnPEiBGYNm0aAGDu3LlYvnw5du3ahZCQEKt9nzlzBgEBAXb37d///jc2bNhg8TsfOHAg1q5diwcffBBFRUUoKytDTExMjbO/qmqfOXPGqRdRJyKqD/byk4tvf3iEf4fyS1tQcvx5SH6G+Tkp/AXFKQ/DkLm88mLoLQb957nyYlTkHUNF9uHKr5zDqMhJBSqKrL2MhYrswxCRejuhhotSTlSRexSQcvP3vMg5ERERUcN27733YuXKlQCAa9eu4b333sPw4cNx8OBBBAcH48iRIzh58iSaNWtmMa6oqAinTp1CZGQkJk2ahKioKNx3330YNmwYJkyYAH9/f829hISEID4+3uIxk8nyIrjVbwYUHh6Ot99+GwCQlpaGdu3aWdz8584774SPjw/S0tLQt29fpKSk4Mknn7TbR8+ePc3/VhQFbdq0QVZWls3tCwsL4eHhYfP5Y8eOYfTo0Vi0aBEiIyPNj//888+YNWsW/vKXvyAqKgoXLlzAnDlzMGXKFKxevdq8naenJwDYXLQkIrqVKIqCJm3GwMVvJMp+XYWSjMVAyX/eiKnIPoSi/YPh4nc/FPfWlYtQuccsrkmlisENhmY9YPDuXbl45eLp3B1RiYtSTlSR/aPF91yUIiIiottZXl6ezedcXFwsvre36FF11lIVZ36My2g0onPnzubvP/roI3h7e+PDDz/EX//6V+Tl5aF3795Yu3ZtjbGtWrUCUHnm1NNPP43ExERs2LABCxYswPbt2y2usaSGm5ubRS83Q9UCjz2urq4W3yuKgooK2x8XadmyJa5du2b1uZ9//hkRERGYPHkyFixYYPHca6+9hoEDB2LOnDkAKhfDjEYj7rnnHvz1r381L+xdvXoVwH9+3kREtwPF4ArX9tPRpO2jKD21FKWZb1mc+VSe9bX6YgZPGEx/gME7rPLLFAZDszuhGNxuQufacFHKiSzuvNfEB4pn+3rrhYiI6GYrLCzE8OHDAQBbt25V9T+7dHsxGo31vq1WiqLAYDCYr2MVFhaGDRs2wM/Pr8ZZSzfq1asXevXqhfnz5yM8PBz/+Mc/8Mc//hFubm4oLy+3OU6r/fv31/i+6uOC3bp1w9mzZ3H27Fnz2VI///wzrl+/jjvvvBNA5cLPzp07zXe6doZevXphzZo1NR7/6aefMHToUEycOBGvvFLzQroFBQU17i5YtVh540cxjx07BldXV3Tv3t1pPRMR1Ret+UlxNcGt6ytoEjwVpScWouy3TwDY+bh6k2YwmHrB4N0bLqbKRSilaQgUxcX2mHrERSlnkjLA4AlUFFb+4nmRcyIiuoVVVFRgz5495n8TNUbFxcW4ePEigMqP761YsQJ5eXmIiYkBAMTGxuL111/H6NGj8dJLLyEwMBBnzpzBpk2b8Pzzz6O0tBSrVq3CqFGjEBAQgPT0dGRkZOCxxx4DUHn9q8zMTKSkpCAwMBDNmjWDu7u71V7KysrMvVRRFMV8V2oA2Lt3L5YtW4YxY8Zg+/bt2Lhxo/k6TcOGDUOPHj0QGxuLt99+G2VlZZg2bRoGDx6MPn36AAAWLVqEiIgIdOrUCQ899BDKysrwzTffYO7cubX+GUZFRWH+/Pm4du0afH19AVQuJA0dOhRRUVF45plnzPvl4uJiPuMpJiYGTz75JFauXGn++N7s2bPRr18/i2tUff/997jnnnu48E1Et4Ta5ieDZyDcQ+PQpMNslB6fj/Ir3wIuXhaLTwbvMChenaAoDeKedqpwUcqJ3EPj4NbjQ0h+OkTFBcWIiIiIqH4lJiaaPybWrFkzdO3aFRs3bsSQIUMAAF5eXvjuu+8wd+5cjBs3Drm5uWjbti0iIiJgMplQWFiI48eP45NPPsGVK1fg7++P6dOn46mnngIAjB8/Hps2bcK9996L69evIy4uDpMmTbLay08//VTjWlTu7u4Wdyp89tlnkZSUhBdffBEmkwlvvfUWoqKiAFQuYG3ZsgUzZ87EoEGDYDAYEB0djXfeecc8fsiQIdi4cSNefvllLFmyBCaTCYMGDYIePXr0QFhYGD7//HPzfn/xxRe4fPky1qxZY3EWVXBwsPnjl5MmTUJubi5WrFiBZ599Fj4+Phg6dCiWLl1qUX/9+vVYvHixrh6JiG4VLqZQuPT7BiLlAAyN/mQYRWpzm5JGLCcnB97e3sjOzrZ7CjYRERHZl5+fb75TWF5e3k39SFV9YnaoZO/nUFRUhMzMTHTo0MHuBa9Jn/bt22P27NmYPXt2fbdSQ0JCAubMmYNjx47VuAaYHlu3bsWzzz6L1NTUGh/1q8L5R0SNCfOTJZ4pRUREREREuowcORIZGRk4d+6cxd3/9MrPz0dcXJzNBSkiImrceHQnIiIiIiLdbsYZXH/605+cXpOIiBoOLkoRERERETUCVddiIiIiulVwUYqIiIhqzcvLq75bICIiImpUmJ/+g4tSREREVCtGoxH5+fn13QYRERFRo8H8ZMl5t8YgIiIiotvabXZTZ2ogOO+IiBovLkoRERERkS6urq4AgIKCgnruhG5HVfOuah4SEVHjwY/vERERUa0UFRVh/PjxAIB//vOf8PDwqOeOqL64uLjAx8cHWVlZACqvlaEoSj13Rbc6EUFBQQGysrLg4+MDFxeX+m6JiMgh5idLXJQiIiKiWikvL8c333xj/jfd3tq0aQMA5oUporri4+Njnn9ERA0d85MlLkoRERERkW6KosDf3x9+fn4oLS2t73boNuHq6sozpIiIGjEuShERERGR07i4uHCRgIiIiFThhc6JiIiIiIiIiKjOcVGKiIiIiIiIiIjqHBeliIiIiIiIiIiozt1215QSEQBATk5OPXdCRETUuOXn55v/nZOTc8veQaYqM1RliNsVMxQREZF+zE+WbrtFqdzcXABAu3bt6rkTIiKiW0dAQEB9t3DT5ebmwtvbu77bqDfMUERERM7F/AQocpu97VdRUYHz58+jWbNmUBTF6fVzcnLQrl07nD17FiaTqV5qsAf2wB7YA3tgD+zBeUQEubm5CAgIgMFw+175oKFnqIYwl9gDe2AP7IE9sIfbqQd71Oan2+5MKYPBgMDAwJv+OiaTSfcvVm8N9sAe2AN7YA/sgT04x+18hlSVxpKhGsJcYg/sgT2wB/bAHm6nHmxRk59u37f7iIiIiIiIiIio3nBRioiIiIiIiIiI6hwXpZzM3d0dixYtgru7e73VYA/sgT2wB/bAHtgDNTa3wlxiD+yBPbAH9sAebqcenOG2u9A5ERERERERERHVP54pRUREREREREREdY6LUkREREREREREVOe4KEVERERERERERHWOi1JO8t133yEmJgYBAQFQFAVffvmlpvGvvfYa+vbti2bNmsHPzw9jxoxBenq6phorV65Ez549YTKZYDKZEB4ejq1bt2qqcaMlS5ZAURTMnj1b9ZjFixdDURSLr65du2p63XPnzuGRRx5BixYt4OnpiR49eiApKUn1+Pbt29foQVEUTJ8+XdX48vJyLFy4EB06dICnpyc6deqEl19+GVovv5abm4vZs2cjODgYnp6eGDBgAA4dOmR1W0fzR0Twl7/8Bf7+/vD09MSwYcOQkZGhqcamTZsQGRmJFi1aQFEUpKSkqB5fWlqKuXPnokePHjAajQgICMBjjz2G8+fPa+ph8eLF6Nq1K4xGI3x9fTFs2DAcOHBA9fgbTZkyBYqi4O2339bUw6RJk2rMjejoaE09pKWlYdSoUfD29obRaETfvn3x66+/qq5hbX4qioLXX39d1fi8vDzMmDEDgYGB8PT0xJ133on3339f08/h0qVLmDRpEgICAuDl5YXo6GiLOaXmmFRUVITp06ejRYsWaNq0KcaPH49Lly6pHr9q1SoMGTIEJpMJiqLg+vXrFs87qnH16lXMnDkTISEh8PT0RFBQEJ5++mlkZ2er7uGpp55Cp06d4OnpiVatWmH06NE4fvy4pp9DFRHB8OHDLX7easYPGTKkxlyYMmWK5h727duHoUOHwmg0wmQyYdCgQSgsLHQ4/pdffrE5Jzdu3Ki6h4sXL+LRRx9FmzZtYDQaERYWhn/+85+qx586dQpjx45Fq1atYDKZMGHCBPN8Ahz/jbM3H6lhq+8MdavkJ0BfhtKbnwDnZCgt+QnQn6H05idHNdRkKL35SU2NG1nLUHrzk9oe7GUovflJTQ1HGaq+85PaGvYylN78pLYHexlKb35SW8NehtKbn9TUcJSh9OYntfthL0M1hvzERSknyc/PR2hoKN59991ajd+zZw+mT5+O/fv3Y/v27SgtLUVkZCTy8/NV1wgMDMSSJUvw448/IikpCUOHDsXo0aPx008/ae7n0KFD+OCDD9CzZ0/NY7t3744LFy6Yv3744QfVY69du4aBAwfC1dUVW7duxc8//4w333wTvr6+mnq/8fW3b98OAHjggQdUjV+6dClWrlyJFStWIC0tDUuXLsWyZcvwzjvvqO4BAP7nf/4H27dvx2effYajR48iMjISw4YNw7lz52ps62j+LFu2DP/3f/+H999/HwcOHIDRaERUVBSKiopU18jPz8fdd9+NpUuX2nze1viCggIcPnwYCxcuxOHDh7Fp0yakp6dj1KhRmvajS5cuWLFiBY4ePYoffvgB7du3R2RkJC5fvqxqfJXNmzdj//79CAgI0LQfVaKjoy3myLp161SPP3XqFO6++2507doVu3fvRmpqKhYuXAgPDw/VNW587QsXLuDjjz+GoigYP368qvHPPPMMEhMTsWbNGqSlpWH27NmYMWMG4uPjVfUgIhgzZgxOnz6NLVu2IDk5GcHBwRg2bJj5mKPmmPS///u/+Oqrr7Bx40bs2bMH58+fx7hx41SPLygoQHR0NP785z9b3U9HNc6fP4/z58/jjTfewLFjx/D3v/8diYmJeOKJJ1T30Lt3b8TFxSEtLQ3btm2DiCAyMhLl5eWqa1R5++23oSiKpn2o8uSTT1rMiWXLlmmqsW/fPkRHRyMyMhIHDx7EoUOHMGPGDBgMBofj27VrV2NOvvjii2jatCmGDx+uuofHHnsM6enpiI+Px9GjRzFu3DhMmDABycnJDsfn5+cjMjISiqLg22+/xd69e1FSUoKYmBhUVFQAcPw3zt58pIatvjPUrZCfAP0ZSm9+ApyTobTkJ0B/htKbnxzVUJOh9OYnNTWq2MpQevOTmhqOMpTe/KSmhqMMVd/5SW0NexlKb35S24O9DKU3P6ntAbCdofTmJzU1HGUovflJTQ+OMlSjyE9CTgdANm/erKtGVlaWAJA9e/boquPr6ysfffSRpjG5ublyxx13yPbt22Xw4MEya9Ys1WMXLVokoaGh2pq8wdy5c+Xuu++u9XhrZs2aJZ06dZKKigpV248cOVIef/xxi8fGjRsnsbGxql+zoKBAXFxc5Ouvv7Z4PCwsTF544QW7Y6vPn4qKCmnTpo28/vrr5seuX78u7u7usm7dOlU1bpSZmSkAJDk5WXUP1hw8eFAAyJkzZ2pdIzs7WwDIjh07VI//7bffpG3btnLs2DEJDg6W5cuX26xvrcbEiRNl9OjRdvuyN/7BBx+URx55RNV4WzWqGz16tAwdOlT1+O7du8tLL71k8Zi9uVW9Rnp6ugCQY8eOmR8rLy+XVq1ayYcffmi1RvVj0vXr18XV1VU2btxo3iYtLU0AyL59+xyOv9GuXbsEgFy7ds3qa6upUeXzzz8XNzc3KS0trdX4I0eOCAA5efKkph6Sk5Olbdu2cuHCBbu/c2vjtR5nrdXo37+/LFiwoNbjq/vDH/5Q4zjoqIbRaJRPP/3UYrvmzZtbnVPVx2/btk0MBoNkZ2ebt7l+/booiiLbt2+32UfV3zit85EaroaSoRpbfhJxfobSmp9E9GcoPflJRH+G0pufHNWoYi9D6c1P9mqozVB685OtGloylN78ZKuGlgzVEPKTtRo3UpOh9OYntTXsZSi9+clWDS3HWr35yd5+3MhehtKbn6zVqE2Gamj5iWdKNVBVp082b968VuPLy8uxfv165OfnIzw8XNPY6dOnY+TIkRg2bFitXjsjIwMBAQHo2LEjYmNjLT7W5Eh8fDz69OmDBx54AH5+fujVqxc+/PDDWvUBACUlJVizZg0ef/xxqyvw1gwYMAA7d+7EiRMnAABHjhzBDz/8YD5jQI2ysjKUl5dbnD0DAJ6enprf+czMzMTFixctfh/e3t7o378/9u3bp6mWM2VnZ0NRFPj4+NRqfElJCVatWgVvb2+EhoaqGlNRUYFHH30Uc+bMQffu3Wv1ugCwe/du+Pn5ISQkBFOnTsWVK1dUv35CQgK6dOmCqKgo+Pn5oX///po/anKjS5cuISEhweLdKUcGDBiA+Ph4nDt3DiKCXbt24cSJE4iMjFQ1vri4GAAs5qfBYIC7u7vN+Vn9mPTjjz+itLTUYl527doVQUFBVuel3mOa2hrZ2dkwmUxo0qSJ5vH5+fmIi4tDhw4d0K5dO9U9FBQU4OGHH8a7776LNm3a1Gof1q5di5YtW+Kuu+7C/PnzUVBQoLpGVlYWDhw4AD8/PwwYMACtW7fG4MGDVf8uq/vxxx+RkpJid05aqzFgwABs2LABV69eRUVFBdavX4+ioiIMGTLE4fji4mIoigJ3d3fzNh4eHjAYDFb3o/rfOK3zkW5teo43jTU/Ac7NULXJT4D+DOXM/ATcmhmqNvkJcE6Gqm1+qnp9Z2ao2uQnQF+Gqo/8ZK2GVnrzk5oajjKU3vxkrwe1GUpvfrLXQxVHGUpvfrJWQ0uGarD5qc6Wv24j0PkuX3l5uYwcOVIGDhyoeWxqaqoYjUZxcXERb29vSUhI0DR+3bp1ctddd0lhYaGIaH8H/5tvvpHPP/9cjhw5IomJiRIeHi5BQUGSk5Ojary7u7u4u7vL/Pnz5fDhw/LBBx+Ih4eH/P3vf9e0H1U2bNggLi4ucu7cOdVjysvLZe7cuaIoijRp0kQURZFXX31V82uHh4fL4MGD5dy5c1JWViafffaZGAwG6dKli91x1efP3r17BYCcP3/eYrsHHnhAJkyYoKrGjZxxplRhYaGEhYXJww8/rLnGV199JUajURRFkYCAADl48KDq8a+++qrcd9995ndta3Om1Lp162TLli2Smpoqmzdvlm7duknfvn2lrKzM4fiqd3G8vLzkrbfekuTkZHnttddEURTZvXu3pp9DlaVLl4qvr6/5vzk144uKiuSxxx4TANKkSRNxc3OTTz75xOZrVK9RUlIiQUFB8sADD8jVq1eluLhYlixZIgAkMjKyxnhrx6S1a9eKm5tbjW379u0rzz//vMPxN1LzLp+a4+Lly5clKChI/vznP2sa/+6774rRaBQAEhISYvMsKVs1Jk+eLE888YT5e1u/c1vjP/jgA0lMTJTU1FRZs2aNtG3bVsaOHau6h3379gkAad68uXz88cdy+PBhmT17tri5ucmJEydU/xyqTJ06Vbp162bzeVs1rl27JpGRkeZ5aTKZZNu2barGZ2VliclkklmzZkl+fr7k5eXJjBkzBIBMnjzZvJ2tv3Fa5iM1bPWVoRp7fhJxboaqTX4ScU6Gqm1+EtGfofTmJ0c1RBxnKL35yVYNLRlKb36yVkNrhtKbn2zV0JKh6js/2apxI0cZSm9+clRDTYbSm5/s1VCbofTmJ0c/hyr2MpTe/GSrhpoM1dDzExelbgK9gWrKlCkSHBwsZ8+e1Ty2uLhYMjIyJCkpSebNmyctW7aUn376SdXYX3/9Vfz8/OTIkSPmx7SGququXbsmJpNJ9Snwrq6uEh4ebvHYzJkz5Y9//GOtXj8yMlLuv/9+TWPWrVsngYGBsm7dOklNTZVPP/1UmjdvrjnUnTx5UgYNGiQAxMXFRfr27SuxsbHStWtXu+Ma+qJUSUmJxMTESK9evSxOE1VbIy8vTzIyMmTfvn3y+OOPS/v27eXSpUsOxyclJUnr1q0tAnJtFqWqO3XqlOqPEJ47d04AyH/9139ZbBcTEyMPPfRQrXoICQmRGTNmaNqH119/Xbp06SLx8fFy5MgReeedd6Rp06Y2T9G1ViMpKUlCQ0PN8zMqKkqGDx8u0dHRNcZbOyZp+SPm6JimZlHKUY3s7Gzp16+fREdHS0lJiabx169flxMnTsiePXskJiZGwsLCrIZcazW2bNkinTt3ltzcXPNjtn7nao/tO3futHn6u7UaVceI+fPnW2zbo0cPmTdvnqYeCgoKxNvbW9544w2b/dmqMWPGDOnXr5/s2LFDUlJSZPHixeLt7S2pqamqxm/btk06duwoiqKIi4uLPPLIIxIWFiZTpkwxb2Prb1xDCVWkX31lqMaen0Scm6Fqk59EnJOhapufRBr+opSaDKU3P1mroTVD6c1P1mpozVB685OtGloyVH3nJ1s1buQoQ+nNT45qqMlQevOTmv2oYitD6c1PanpwlKH05id7NRxlqIaen7godRPoCVTTp0+XwMBAOX36tFN6iYiIsHiX2Z7NmzebD7BVXwDMk9vWOyGO9OnTx+p/2NYEBQVZrJiLiLz33nsSEBCg+XV/+eUXMRgM8uWXX2oaFxgYKCtWrLB47OWXX5aQkBDNPYhUhoiqMDRhwgQZMWKE3e2rz5+qP/rVQ9CgQYPk6aefVlXjRnoWpUpKSmTMmDHSs2dP+f333zXthy2dO3e2+i5q9fHLly83z8Ub56fBYJDg4GBdPbRs2VLef/99h+OLi4ulSZMm8vLLL1ts9/zzz8uAAQM09/Ddd98JAElJSbHZW/XxBQUF4urqWuN6G0888YRERUVp7uH69euSlZUlIiL9+vWTadOmWTxv65hU9Ue/eggKCgqSt956y+H4GzkKVI5q5OTkSHh4uERERFhdTNJyXC0uLhYvLy/5xz/+oarGrFmzbM7LwYMH16qHvLw8ASCJiYmqejh9+rQAkM8++8zi8QkTJli8E6+mh08//VRcXV3Nc6I6WzVOnjxZ4zobIpV/g5566ilNPVy+fNk8F1q3bi3Lli2zuW3V3zi185EavoaSoRpbfhJxXoaqbX4ScW6G0pqfRPRnqJu5KKU2Q+nNT9ZqaM1QevOTtRpaM5Te/GSthtYMVZ/5yV6NG9nLUHrzk9oeqljLUHrzk9YerGUovflJbQ/2MpTe/KS2B7UZqqHlJ15TqoEQEcyYMQObN2/Gt99+iw4dOjilbkVFhfnzz45ERETg6NGjSElJMX/16dMHsbGxSElJgYuLi+bXz8vLw6lTp+Dv769q+4EDB9a4xeWJEycQHBys+bXj4uLg5+eHkSNHahpXUFBgvuNCFRcXF/MdoLQyGo3w9/fHtWvXsG3bNowePVrT+A4dOqBNmzbYuXOn+bGcnBwcOHBA8/Uu9CgtLcWECROQkZGBHTt2oEWLFk6pq3aOPvroo0hNTbWYnwEBAZgzZw62bdtW69f/7bffcOXKFVVz1M3NDX379nXaHF29ejV69+6t6ZoQpaWlKC0tddoc9fb2RqtWrZCRkYGkpCTz/HR0TOrduzdcXV0t5mV6ejp+/fVXhIeHO+WYpqZGTk4OIiMj4ebmhvj4eIvrPNSmB6l8s8Y8Jx3VmDdvXo15CQDLly9HXFxcrXqoqlE1Jx3VaN++PQICAmzOSy09rF69GqNGjUKrVq1q/Fzs1ai6foOteamlh5YtW8LHxwfffvstsrKyatzl80ZVxw9H85FubTcjQzW2/AQ4L0PVNj8Bzs1QevMTcGtnKC1z9GZkKC35CXBuhqpNfgKcm6FuVn5SU8MRvfmptj3cmKH05qfa9nBjhtKbn7T2YC1D6c1PWntQm6EaXH6qq9WvW11ubq4kJydLcnKyADB/VtrWncmqmzp1qnh7e8vu3bvlwoUL5q+CggLVPcybN0/27NkjmZmZkpqaKvPmzRNFUeRf//pXbXdL8+nnzz77rOzevVsyMzNl7969MmzYMGnZsqXNd92rO3jwoDRp0kReeeUVycjIkLVr14qXl5esWbNGU9/l5eUSFBQkc+fO1TROpPLuIm3btpWvv/5aMjMzZdOmTdKyZUvNpzAmJibK1q1b5fTp0/Kvf/1LQkNDpX///lZPjXU0f5YsWSI+Pj7mz/KPHj1aOnToYPGuhqMaV65ckeTkZElISBAAsn79eklOTpYLFy44HF9SUiKjRo2SwMBASUlJsZijxcXFqnrIy8uT+fPny759++SXX36RpKQk+e///m9xd3c3vzug9b8ja6ee26uRm5srzz33nOzbt08yMzNlx44dEhYWJnfccYcUFRWp6mHTpk3i6uoqq1atkoyMDHnnnXfExcVFvv/+e9W/C5HK06W9vLxk5cqVmufD4MGDpXv37rJr1y45ffq0xMXFiYeHh7z33nuqa3z++eeya9cuOXXqlHz55ZcSHBws48aNM49Xc0yaMmWKBAUFybfffitJSUkSHh5u/uiImvEXLlyQ5ORk+fDDDwWAfPfdd5KcnCxXrlxRVSM7O1v69+8vPXr0kJMnT1psU1ZW5nD8qVOn5NVXX5WkpCQ5c+aM7N27V2JiYqR58+bmj0TU5tiMG95ZdTT+5MmT8tJLL0lSUpJkZmbKli1bpGPHjjJo0CBNv4vly5eLyWSSjRs3SkZGhixYsEA8PDzk5MmTqvchIyNDFEWRrVu31tgnRzVKSkqkc+fOcs8998iBAwfk5MmT8sYbb4iiKJKQkKCqh48//lj27dsnJ0+elM8++0yaN28uzzzzjPl5R3/j7M1HatjqO0PdCvlJxDkZSk9+EnFOhtKSn0T0Zyi9+clRDTUZSm9+UrMf1VXPUHrzk5oeHGUovflJTQ1HGaq+85PaGvYylN78pKYHRxlKb35S04OjDKU3P6mtIWI7Q+nNT2p7sJehGkN+4qKUk1SdOln9a+LEiarGWxsLQOLi4lT38Pjjj0twcLC4ublJq1atJCIiQlegEtEeqh588EHx9/cXNzc3adu2rTz44IM2Lxpsy1dffSV33XWXuLu7S9euXWXVqlUau678XC0ASU9P1zw2JydHZs2aJUFBQeLh4SEdO3aUF154wWLxRY0NGzZIx44dxc3NTdq0aSPTp0+X69evW93W0fypqKiQhQsXSuvWrcXd3V0iIiJq7JujGnFxcVafX7RokcPxVaesW/vatWuXqh4KCwtl7NixEhAQIG5ubuLv7y+jRo2yuFCn1v+OrC1K2atRUFAgkZGR0qpVK3F1dZXg4GB58skn5eLFi5p6WL16tXTu3Fk8PDwkNDS0xkcc1NT44IMPxNPT0+qccDT+woULMmnSJAkICBAPDw8JCQmRN9980+K23Y5q/O1vf5PAwEBxdXWVoKAgWbBggcUcV3NMKiwslGnTpomvr694eXnJ2LFjzSFdzfhFixbZ3cZRDVv7CMDunK0af+7cORk+fLj4+fmJq6urBAYGysMPPyzHjx/X9HOo7sZQ5Wj8r7/+KoMGDZLmzZuLu7u7dO7cWebMmWNxrRG1Pbz22msSGBgoXl5eEh4ebg75asfPnz9f2rVrJ+Xl5Vb3yVGNEydOyLhx48TPz0+8vLykZ8+e5lscqxk/d+5cad26tbi6usodd9xRY047+htnbz5Sw1bfGepWyU8i+jOUnvwk4pwMpSU/iejPUHrzk6MaajKU3vykZj+qq56h9OYntT3Yy1B685OaGo4yVH3nJ7U17GUoR+Md5Sc1PTjKULU5LgOWi1KOajjKUGp7sJWftNSwlaHUjLeXn9TWsJehGkN+Uv7/jhIREREREREREdUZXlOKiIiIiIiIiIjqHBeliIiIiIiIiIioznFRioiIiIiIiIiI6hwXpYiIiIiIiIiIqM5xUYqIiIiIiIiIiOocF6WIiIiIiIiIiKjOcVGKiIiIiIiIiIjqHBeliIiIiIiIiIioznFRiohIJ0VR8OWXX9Z3G0RERESNBvMTEQFclCKiRm7SpElQFKXGV3R0dH23RkRERNQgMT8RUUPRpL4bICLSKzo6GnFxcRaPubu711M3RERERA0f8xMRNQQ8U4qIGj13d3e0adPG4svX1xdA5anhK1euxPDhw+Hp6YmOHTviiy++sBh/9OhRDB06FJ6enmjRogUmT56MvLw8i20+/vhjdO/eHe7u7vD398eMGTMsnv/9998xduxYeHl54Y477kB8fPzN3WkiIiIiHZifiKgh4KIUEd3yFi5ciPHjx+PIkSOIjY3FQw89hLS0NABAfn4+oqKi4Ovri0OHDmHjxo3YsWOHRWhauXIlpk+fjsmTJ+Po0aOIj49H586dLV7jxRdfxIQJE5CamooRI0YgNjYWV69erdP9JCIiInIW5iciqhNCRNSITZw4UVxcXMRoNFp8vfLKKyIiAkCmTJliMaZ///4ydepUERFZtWqV+Pr6Sl5envn5hIQEMRgMcvHiRRERCQgIkBdeeMFmDwBkwYIF5u/z8vIEgGzdutVp+0lERETkLMxPRNRQ8JpSRNTo3XvvvVi5cqXFY82bNzf/Ozw83OK58PBwpKSkAADS0tIQGhoKo9Fofn7gwIGoqKhAeno6FEXB+fPnERERYbeHnj17mv9tNBphMpmQlZVV210iIiIiuqmYn4ioIeCiFBE1ekajscbp4M7i6empajtXV1eL7xVFQUVFxc1oiYiIiEg35iciagh4TSkiuuXt37+/xvfdunUDAHTr1g1HjhxBfn6++fm9e/fCYDAgJCQEzZo1Q/v27bFz58467ZmIiIioPjE/EVFd4JlSRNToFRcX4+LFixaPNWnSBC1btgQAbNy4EX369MHdd9+NtWvX4uDBg1i9ejUAIDY2FosWLcLEiROxePFiXL58GTNnzsSjjz6K1q1bAwAWL16MKVOmwM/PD8OHD0dubi727t2LmTNn1u2OEhERETkJ8xMRNQRclCKiRi8xMRH+/v4Wj4WEhOD48eMAKu/ssn79ekybNg3+/v5Yt24d7rzzTgCAl5cXtm3bhlmzZqFv377w8vLC+PHj8dZbb5lrTZw4EUVFRVi+fDmee+45tGzZEn/605/qbgeJiIiInIz5iYgaAkVEpL6bICK6WRRFwebNmzFmzJj6boWIiIioUWB+IqK6wmtKERERERERERFRneOiFBERERERERER1Tl+fI+IiIiIiIiIiOocz5QiIiIiIiIiIqI6x0UpIiIiIiIiIiKqc1yUIiIiIiIiIiKiOsdFKSIiIiIiIiIiqnNclCIiIiIiIiIiojrHRSkiIiIiIiIiIqpzXJQiIiIiIiIiIqI6x0UpIiIiIiIiIiKqc1yUIiIiIiIiIiKiOvf/ANwq9nzUeoMQAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}