{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ec056806",
   "metadata": {},
   "source": [
    "# Lesson 30 demo part 2: optuna hyperparameter optimization\n",
    "\n",
    "This notebook demonstrates how to use [**Optuna**](https://optuna.org) to automatically find the best hyperparameters for a CNN. Optuna is an awesome optimization framework that can be used to optimize just about *anything* and has a few cool features:\n",
    "\n",
    "1. Intelligent parameter search with advanced sampling algorithms\n",
    "2. Built in 'pruning' of non-promising trials (think early stopping...)\n",
    "3. A built in results logging & dashboard\n",
    "4. The ability to stop and then resume optimization experiments\n",
    "5. Built in parallelism over trials\n",
    "\n",
    "We'll optimize just 2 hyperparameters to keep things simple:\n",
    "1. **Number of convolutional blocks** (1-4)\n",
    "2. **Dropout rate** (0.2-0.5)\n",
    "\n",
    "To run this notebook install `cifar10_tools` via pip: `pip install cifar10_tools`\n",
    "\n",
    "**Note**: If you are not working in one of the course deeplearning containers, you will also need to pip install `optuna` and `optuna-dashboard` to run this notebook.\n",
    "\n",
    "```\n",
    "pip install optuna optuna-dashboard\n",
    "```\n",
    "\n",
    "The Optuna dashboard can be viewed either via the VS Code extension 'Optuna Dashboard', or via the built-in web server. Start it with:\n",
    "\n",
    "```\n",
    "optuna-dashboard sqlite:///data/simple_optimization.db --host 0.0.0.0\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "45009458",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using device: cuda:1\n"
     ]
    }
   ],
   "source": [
    "# Standard library imports\n",
    "from pathlib import Path\n",
    "\n",
    "# Third-party imports\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import optuna\n",
    "import torch\n",
    "import torch.nn as nn\n",
    "import torch.optim as optim\n",
    "import torchvision\n",
    "import torchvision.transforms as transforms\n",
    "from torch.utils.data import DataLoader\n",
    "\n",
    "# Custom package imports\n",
    "from cifar10_tools.pytorch.training import train_model\n",
    "from cifar10_tools.pytorch.evaluation import evaluate_model\n",
    "from cifar10_tools.pytorch.plotting import (\n",
    "    plot_sample_images,\n",
    "    plot_learning_curves,\n",
    "    plot_confusion_matrix\n",
    ")\n",
    "\n",
    "# Suppress Optuna info messages (show only warnings and errors)\n",
    "optuna.logging.set_verbosity(optuna.logging.WARNING)\n",
    "\n",
    "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
    "print(f'Using device: {device}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "69cd7d65",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fixed hyperparameters (not optimized)\n",
    "batch_size = 1000\n",
    "initial_filters = 32\n",
    "fc_units_1 = 512\n",
    "fc_units_2 = 128\n",
    "use_batch_norm = True\n",
    "learning_rate = 0.001\n",
    "\n",
    "# Optuna settings\n",
    "n_trials = 20            # Number of Optuna trials\n",
    "n_epochs_per_trial = 20  # Short training per trial\n",
    "n_epochs_final = 50      # Longer training for final model\n",
    "\n",
    "# Storage path for Optuna study\n",
    "storage_path = Path('../data/simple_optimization.db')\n",
    "storage_path.parent.mkdir(parents=True, exist_ok=True)\n",
    "storage_url = f'sqlite:///{storage_path.resolve()}'\n",
    "\n",
    "# CIFAR-10 class names\n",
    "class_names = [\n",
    "    'airplane', 'automobile', 'bird', 'cat', 'deer', \n",
    "    'dog', 'frog', 'horse', 'ship', 'truck'\n",
    "]\n",
    "\n",
    "num_classes = len(class_names)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae3add42",
   "metadata": {},
   "source": [
    "## 1. Load and prepare data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "06308407",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training samples: 50000\n",
      "Test samples: 10000\n"
     ]
    }
   ],
   "source": [
    "# Data directory\n",
    "data_dir = Path('../data')\n",
    "data_dir.mkdir(parents=True, exist_ok=True)\n",
    "\n",
    "# Transform: convert to tensor and normalize RGB channels\n",
    "transform = transforms.Compose([\n",
    "    transforms.ToTensor(),\n",
    "    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))\n",
    "])\n",
    "\n",
    "# Download and load CIFAR-10\n",
    "train_dataset = torchvision.datasets.CIFAR10(\n",
    "    root=data_dir,\n",
    "    train=True,\n",
    "    download=True,\n",
    "    transform=transform\n",
    ")\n",
    "\n",
    "test_dataset = torchvision.datasets.CIFAR10(\n",
    "    root=data_dir,\n",
    "    train=False,\n",
    "    download=True,\n",
    "    transform=transform\n",
    ")\n",
    "\n",
    "print(f'Training samples: {len(train_dataset)}')\n",
    "print(f'Test samples: {len(test_dataset)}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0b7eeee4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train: torch.Size([40000, 3, 32, 32])\n",
      "X_val: torch.Size([10000, 3, 32, 32])\n",
      "X_test: torch.Size([10000, 3, 32, 32])\n"
     ]
    }
   ],
   "source": [
    "# Preload data to GPU for faster training\n",
    "X_train_full = torch.stack([img for img, _ in train_dataset]).to(device)\n",
    "y_train_full = torch.tensor([label for _, label in train_dataset]).to(device)\n",
    "X_test = torch.stack([img for img, _ in test_dataset]).to(device)\n",
    "y_test = torch.tensor([label for _, label in test_dataset]).to(device)\n",
    "\n",
    "# Split training data into train and validation sets (80/20)\n",
    "n_train = int(0.8 * len(X_train_full))\n",
    "indices = torch.randperm(len(X_train_full))\n",
    "\n",
    "X_train = X_train_full[indices[:n_train]]\n",
    "y_train = y_train_full[indices[:n_train]]\n",
    "X_val = X_train_full[indices[n_train:]]\n",
    "y_val = y_train_full[indices[n_train:]]\n",
    "\n",
    "print(f'X_train: {X_train.shape}')\n",
    "print(f'X_val: {X_val.shape}')\n",
    "print(f'X_test: {X_test.shape}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dab7fae8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training batches: 40\n",
      "Validation batches: 10\n",
      "Test batches: 10\n"
     ]
    }
   ],
   "source": [
    "# Create DataLoaders\n",
    "train_tensor_dataset = torch.utils.data.TensorDataset(X_train, y_train)\n",
    "val_tensor_dataset = torch.utils.data.TensorDataset(X_val, y_val)\n",
    "test_tensor_dataset = torch.utils.data.TensorDataset(X_test, y_test)\n",
    "\n",
    "train_loader = DataLoader(train_tensor_dataset, batch_size=batch_size, shuffle=True)\n",
    "val_loader = DataLoader(val_tensor_dataset, batch_size=batch_size, shuffle=False)\n",
    "test_loader = DataLoader(test_tensor_dataset, batch_size=batch_size, shuffle=False)\n",
    "\n",
    "print(f'Training batches: {len(train_loader)}')\n",
    "print(f'Validation batches: {len(val_loader)}')\n",
    "print(f'Test batches: {len(test_loader)}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "18183370",
   "metadata": {},
   "source": [
    "## 2. Define CNN architecture\n",
    "\n",
    "This function creates a CNN with a configurable number of convolutional blocks and dropout rate."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "dc2ade26",
   "metadata": {},
   "outputs": [],
   "source": [
    "def create_cnn(n_conv_blocks: int, dropout_rate: float) -> nn.Sequential:\n",
    "    '''Create a CNN with configurable architecture.\n",
    "    \n",
    "    Args:\n",
    "        n_conv_blocks: Number of convolutional blocks (1-4)\n",
    "        dropout_rate: Dropout probability\n",
    "    \n",
    "    Returns:\n",
    "        nn.Sequential model\n",
    "    '''\n",
    "\n",
    "    layers = []\n",
    "    in_channels = 3  # RGB input\n",
    "    current_size = 32  # Input image size\n",
    "    \n",
    "    for block_idx in range(n_conv_blocks):\n",
    "        out_channels = initial_filters * (2 ** block_idx)\n",
    "        \n",
    "        # Conv -> BatchNorm -> ReLU -> Conv -> BatchNorm -> ReLU -> Pool -> Dropout\n",
    "        layers.append(nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1))\n",
    "        layers.append(nn.BatchNorm2d(out_channels))\n",
    "        layers.append(nn.ReLU())\n",
    "        \n",
    "        layers.append(nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1))\n",
    "        layers.append(nn.BatchNorm2d(out_channels))\n",
    "        layers.append(nn.ReLU())\n",
    "        \n",
    "        layers.append(nn.MaxPool2d(2, 2))\n",
    "        layers.append(nn.Dropout(dropout_rate))\n",
    "        \n",
    "        in_channels = out_channels\n",
    "        current_size //= 2\n",
    "    \n",
    "    # Calculate flattened size\n",
    "    final_channels = initial_filters * (2 ** (n_conv_blocks - 1))\n",
    "    flattened_size = final_channels * current_size * current_size\n",
    "    \n",
    "    # Classifier (3 fully connected layers)\n",
    "    layers.append(nn.Flatten())\n",
    "    layers.append(nn.Linear(flattened_size, fc_units_1))\n",
    "    layers.append(nn.ReLU())\n",
    "    layers.append(nn.Dropout(dropout_rate))\n",
    "    layers.append(nn.Linear(fc_units_1, fc_units_2))\n",
    "    layers.append(nn.ReLU())\n",
    "    layers.append(nn.Dropout(dropout_rate))\n",
    "    layers.append(nn.Linear(fc_units_2, num_classes))\n",
    "    \n",
    "    return nn.Sequential(*layers)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4080c835",
   "metadata": {},
   "source": [
    "## 3. Optuna hyperparameter optimization\n",
    "\n",
    "We define an objective function that:\n",
    "1. Samples hyperparameters from defined search spaces\n",
    "2. Creates and trains a model with those hyperparameters\n",
    "3. Returns the validation accuracy to maximize\n",
    "\n",
    "### 3.1. Define training function for trials"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "590f3eab",
   "metadata": {},
   "outputs": [],
   "source": [
    "def train_trial(\n",
    "    model: nn.Module,\n",
    "    optimizer: optim.Optimizer,\n",
    "    criterion: nn.Module,\n",
    "    train_loader: DataLoader,\n",
    "    val_loader: DataLoader,\n",
    "    n_epochs: int,\n",
    "    trial: optuna.Trial\n",
    ") -> float:\n",
    "    '''Train a model for a single Optuna trial with pruning support.'''\n",
    "    \n",
    "    best_val_accuracy = 0.0\n",
    "    \n",
    "    for epoch in range(n_epochs):\n",
    "\n",
    "        # Training phase\n",
    "        model.train()\n",
    "\n",
    "        for images, labels in train_loader:\n",
    "            optimizer.zero_grad()\n",
    "            outputs = model(images)\n",
    "            loss = criterion(outputs, labels)\n",
    "            loss.backward()\n",
    "            optimizer.step()\n",
    "        \n",
    "        # Validation phase\n",
    "        model.eval()\n",
    "        val_correct = 0\n",
    "        val_total = 0\n",
    "        \n",
    "        with torch.no_grad():\n",
    "            for images, labels in val_loader:\n",
    "\n",
    "                outputs = model(images)\n",
    "                _, predicted = torch.max(outputs.data, 1)\n",
    "                val_total += labels.size(0)\n",
    "                val_correct += (predicted == labels).sum().item()\n",
    "        \n",
    "        val_accuracy = 100 * val_correct / val_total\n",
    "        best_val_accuracy = max(best_val_accuracy, val_accuracy)\n",
    "        \n",
    "        # Report for pruning\n",
    "        trial.report(val_accuracy, epoch)\n",
    "        \n",
    "        if trial.should_prune():\n",
    "            raise optuna.TrialPruned()\n",
    "    \n",
    "    return best_val_accuracy"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "497b5bb3",
   "metadata": {},
   "source": [
    "### 3.2. Define objective function\n",
    "\n",
    "This is where we specify which hyperparameters to optimize:\n",
    "- `n_conv_blocks`: 1 to 4 convolutional blocks\n",
    "- `dropout_rate`: 0.2 to 0.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "86190b9f",
   "metadata": {},
   "outputs": [],
   "source": [
    "def objective(trial: optuna.Trial) -> float:\n",
    "    '''Optuna objective function - optimize dropout rate and\n",
    "    number of covolutional blocks.'''\n",
    "    \n",
    "    # Hyperparameters to optimize\n",
    "    n_conv_blocks = trial.suggest_int('n_conv_blocks', 1, 4)\n",
    "    dropout_rate = trial.suggest_float('dropout_rate', 0.2, 0.5)\n",
    "    \n",
    "    # Create model\n",
    "    model = create_cnn(\n",
    "        n_conv_blocks=n_conv_blocks,\n",
    "        dropout_rate=dropout_rate\n",
    "    ).to(device)\n",
    "    \n",
    "    # Create optimizer\n",
    "    optimizer = optim.Adam(model.parameters(), lr=learning_rate)\n",
    "    \n",
    "    # Set loss function\n",
    "    criterion = nn.CrossEntropyLoss()\n",
    "    \n",
    "    # Train and return validation accuracy\n",
    "    try:\n",
    "        return train_trial(\n",
    "            model=model,\n",
    "            optimizer=optimizer,\n",
    "            criterion=criterion,\n",
    "            train_loader=train_loader,\n",
    "            val_loader=val_loader,\n",
    "            n_epochs=n_epochs_per_trial,\n",
    "            trial=trial\n",
    "        )\n",
    "\n",
    "    except torch.cuda.OutOfMemoryError:\n",
    "\n",
    "        torch.cuda.empty_cache()\n",
    "        raise optuna.TrialPruned('CUDA OOM')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6a959352",
   "metadata": {},
   "source": [
    "### 3.3. Run optimization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "ebcf6ba0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "61ba123d2c57406fba1f21786b9b9ce5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/20 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Winning validation accuracy: 84.20%\n",
      "\n",
      "Best hyperparameters:\n",
      " n_conv_blocks: 4\n",
      " dropout_rate: 0.2095718780178986\n",
      "CPU times: user 19min 33s, sys: 7min, total: 26min 34s\n",
      "Wall time: 26min 18s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "    \n",
    "# Create Optuna study (maximize validation accuracy)\n",
    "study = optuna.create_study(\n",
    "    direction='maximize',\n",
    "    study_name='simple_optimization',\n",
    "    storage=storage_url,\n",
    "    load_if_exists=True,\n",
    "    pruner=optuna.pruners.MedianPruner(n_warmup_steps=3)\n",
    ")\n",
    "\n",
    "# Run optimization\n",
    "study.optimize(objective, n_trials=n_trials, show_progress_bar=True)\n",
    "\n",
    "print(f'Winning validation accuracy: {study.best_trial.value:.2f}%')\n",
    "print(f'\\nBest hyperparameters:')\n",
    "\n",
    "for key, value in study.best_trial.params.items():\n",
    "    print(f' {key}: {value}')\n",
    "\n",
    "print()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "02c4e964",
   "metadata": {},
   "source": [
    "### 3.4. Visualize optimization results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "25f039d0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABKQAAAGGCAYAAABFf1lKAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjgsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvwVt1zgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAzcBJREFUeJzs3XlcVPX+P/DXGRhm2BeRTVRQRMEV10zT0nLPFsubWWDdlttmplbWTUy66bXFNsvu7WeGN9tsz25108zSzIVwBUVQUXJBBGZghoEZ5vz+4HuOM7I4A7PC6/l48Chmzpz5zIbnvOb9eX8EURRFEBERERERERERuYjC3QMgIiIiIiIiIqKOhYEUERERERERERG5FAMpIiIiIiIiIiJyKQZSRERERERERETkUgykiIiIiIiIiIjIpRhIERERERERERGRSzGQIiIiIiIiIiIil2IgRURERERERERELsVAioiIiIiIiIiIXIqBFFEH8d5770EQBJw4ccJh+3z22WchCILD9ufp99sa3jRWIiIiIiIiV2EgReQmhw4dwh133IEuXbpApVIhLi4Os2fPxqFDh9q032XLluHLL790zCDdSK/X49lnn8XPP//s7qFYEQQBDz/8cJPXSaHfnj172nQfp0+fxrPPPou9e/e2aT9ERETe7HL/rl599dXo16+fi0dF9srLy8Ozzz7r0C9FL8dRx2Tu9NZbb+G9995z9zCInIqBFJEbfP755xg8eDA2b96Mu+66C2+99Rb++te/YsuWLRg8eDC++OKLVu+7uUDqzjvvRE1NDbp3796GkVt75plnUFNT47D9WdLr9Vi6dGmTgZQz79fRWjPW06dPY+nSpQykiIiIyOvl5eVh6dKlLg2k2gMGUtQR+Lp7AEQdTVFREe6880706NEDv/zyCzp37ixf9+ijj+Kqq67CnXfeif3796NHjx4Ou18fHx/4+Pg4bH8A4OvrC19f1/8Zcdf9toYnjVWn0yEwMNDdwyAiIuoQXPnvriiKMBgM8Pf3d8n9eYL2elyj1+sREBDg7mEQuQQrpIhc7MUXX4Rer8e///1vqzAKACIjI/Gvf/0LOp0OL7zwgny51Ifo8OHDmDlzJkJCQtCpUyc8+uijMBgM8naCIECn0yE7OxuCIEAQBMyZMwdA0z2kEhISMG3aNPz8888YOnQo/P390b9/f7kq6fPPP0f//v2hVqsxZMgQ5ObmWo330v5Ic+bMke/30p9nn30WAFBXV4fMzEwMGTIEoaGhCAwMxFVXXYUtW7bI+zlx4oT83CxdurTRPprqy2QymfDcc8+hZ8+eUKlUSEhIwNNPP43a2lqr7aTHvG3bNgwfPhxqtRo9evTAunXrLvPKtU5TY/3xxx8xevRohIWFISgoCL1798bTTz8NAPj5558xbNgwAMBdd90lP3bLb8g2bNiAIUOGwN/fH5GRkbjjjjvw559/Wt3HnDlzEBQUhKKiIkyZMgXBwcGYPXs2lixZAqVSifPnzzca63333YewsDCr9xQREZG3GDt2LAYOHNjkdb1798bEiRMBNBxnCIKAl156Ca+88gq6d+8Of39/jB07FgcPHmx028OHD+OWW25BREQE1Go1hg4diq+//tpqG+k4a+vWrXjwwQcRFRWF+Ph4ALYfxwHA2rVrMW7cOERFRUGlUiE1NRWrV69uNCbpeOaHH36Qj+H+9a9/tWofrT0OtOW5ee+993DrrbcCAK655hr5uMayAv67777DVVddhcDAQAQHB2Pq1KmNWlg0d1xjD2kfJ0+exLRp0xAUFIQuXbrgzTffBAAcOHAA48aNQ2BgILp3744PPvjA6vbSa/zLL7/g/vvvR6dOnRASEoL09HRUVFQ0ur+33noLffv2lVtzPPTQQ6isrLTaRpp2mpOTgzFjxiAgIABPP/00EhIScOjQIWzdulV+zq6++moAQHl5ORYuXIj+/fsjKCgIISEhmDx5Mvbt22e1759//hmCIOCTTz7B888/j/j4eKjVaowfPx6FhYWNxrtz505MmTIF4eHhCAwMxIABA/Daa69ZbWPLZ4HIHp7xtT1RB/LNN98gISEBV111VZPXjxkzBgkJCfj2228bXTdz5kwkJCRg+fLl+P333/H666+joqJCDlP+85//4J577sHw4cNx3333AQB69uzZ4ngKCwtx++234/7778cdd9yBl156Cddffz3efvttPP3003jwwQcBAMuXL8fMmTNx5MgRKBRNZ9n3338/rr32WqvLvv/+e6xfvx5RUVEAAK1Wi//3//4fZs2ahXvvvRdVVVVYs2YNJk6ciF27dmHQoEHo3LkzVq9ejQceeAA33XQTbr75ZgDAgAEDmn0c99xzD7Kzs3HLLbdgwYIF2LlzJ5YvX478/PxGUyALCwtxyy234K9//SsyMjLw7rvvYs6cORgyZAj69u3b4vMFAAaDAWVlZY0ur66uvuxtDx06hGnTpmHAgAHIysqCSqVCYWEhtm/fDgBISUlBVlYWMjMzcd9998nvkyuvvBJAw8HQXXfdhWHDhmH58uU4d+4cXnvtNWzfvh25ubkICwuT78tkMmHixIkYPXo0XnrpJQQEBGDkyJHIysrCxx9/bNULq66uDp9++ilmzJgBtVp92cdBRETkKhqNpsl/d41Go9Xvd955J+69914cPHjQqrfU7t27UVBQgGeeecZq+3Xr1qGqqgoPPfQQDAYDXnvtNYwbNw4HDhxAdHQ0gIZ/t0eNGoUuXbpg0aJFCAwMxCeffIIbb7wRn332GW666SarfT744IPo3LkzMjMzodPprK673HEcAKxevRp9+/bF9OnT4evri2+++QYPPvggzGYzHnroIav9HTlyBLNmzcL999+Pe++9F71797Z7H205DrTluRkzZgzmzp2L119/HU8//TRSUlIAQP7vf/7zH2RkZGDixIlYsWIF9Ho9Vq9ejdGjRyM3NxcJCQnyWJs6rrFXfX09Jk+ejDFjxuCFF17A+vXr8fDDDyMwMBB///vfMXv2bNx88814++23kZ6ejpEjRyIxMdFqHw8//DDCwsLw7LPP4siRI1i9ejWKi4vlAAhoCCGXLl2Ka6+9Fg888IC83e7du7F9+3YolUp5fxcuXMDkyZNx22234Y477kB0dDSuvvpqPPLIIwgKCsLf//53AJDfk8eOHcOXX36JW2+9FYmJiTh37hz+9a9/YezYscjLy0NcXJzVeP/5z39CoVBg4cKF0Gg0eOGFFzB79mzs3LlT3ubHH3/EtGnTEBsbi0cffRQxMTHIz8/Hxo0b8eijj9r8ehPZTSQil6msrBQBiDfccEOL202fPl0EIGq1WlEURXHJkiUiAHH69OlW2z344IMiAHHfvn3yZYGBgWJGRkajfa5du1YEIB4/fly+rHv37iIA8bfffpMv++GHH0QAor+/v1hcXCxf/q9//UsEIG7ZskW+TBpXc44ePSqGhoaK1113nWgymURRFEWTySTW1tZabVdRUSFGR0eLd999t3zZ+fPnRQDikiVLGu330vvdu3evCEC85557rLZbuHChCED86aefGj3mX375Rb6stLRUVKlU4oIFC5p9LBIAl/3ZvXt3s2N95ZVXRADi+fPnm72P3bt3iwDEtWvXWl1eV1cnRkVFif369RNramrkyzdu3CgCEDMzM+XLMjIyRADiokWLGu1/5MiR4ogRI6wu+/zzzxu9vkRERO4kHbu09NO3b195+8rKSlGtVotPPvmk1X7mzp0rBgYGitXV1aIoiuLx48flY52SkhJ5u507d4oAxMcee0y+bPz48WL//v1Fg8EgX2Y2m8Urr7xS7NWrV6Oxjh49Wj7mkdhzHKfX6xs9DxMnThR79OhhdZl0PPP999832t7efbT2ONDW52bDhg1NHmNUVVWJYWFh4r333mt1+dmzZ8XQ0FCry1s6rmmK9HpYHpNJ+1i2bJl8WUVFhejv7y8KgiB+9NFH8uWHDx9udBwq7XPIkCFiXV2dfPkLL7wgAhC/+uorURQbjiv9/PzECRMmiPX19fJ2q1atEgGI7777rnzZ2LFjRQDi22+/3egx9O3bVxw7dmyjyw0Gg9V+RbHhPa1SqcSsrCz5si1btogAxJSUFKtj79dee00EIB44cEAUxYZj88TERLF79+5iRUWF1X7NZrP8/7a+3kT24JQ9IheqqqoCAAQHB7e4nXS9Vqu1uvzSb7UeeeQRAMB///vfVo8pNTUVI0eOlH8fMWIEAGDcuHHo1q1bo8uPHTtm0351Oh1uuukmhIeH48MPP5T7V/n4+MDPzw8AYDabUV5eDpPJhKFDh+KPP/5o1WOQHv/8+fOtLl+wYAEANKo2S01NtapQ69y5M3r37m3zY7vhhhvw448/Nvp5/PHHL3tbqYLpq6++gtlstun+JHv27EFpaSkefPBBqyqmqVOnok+fPk1W1T3wwAONLktPT8fOnTtRVFQkX7Z+/Xp07doVY8eOtWtMREREzvbmm282+e/upZXToaGhuOGGG/Dhhx9CFEUADRUxH3/8MW688cZG/YZuvPFGdOnSRf59+PDhGDFihHxcUV5ejp9++gkzZ85EVVUVysrKUFZWhgsXLmDixIk4evRooynz9957b7M9O205jrPsASVVho0dOxbHjh2DRqOxun1iYqI8DdGSPfto7XFga56bS/3444+orKzErFmz5NuXlZXBx8cHI0aMsGrnIGnquMZe99xzj/z/YWFh6N27NwIDAzFz5kz58t69eyMsLKzJY8P77rvPqsLpgQcegK+vr/w6btq0CXV1dZg3b57VrIJ7770XISEhjY7XVCoV7rrrLpvHr1Kp5P3W19fjwoULcguIpo6l77rrLvnYG4B8DCw9ttzcXBw/fhzz5s2zqrQHIFd8OeL1JmoKp+wRuZAUNEnBVHOaC6569epl9XvPnj2hUCjatGqJ5cEG0HAwBwBdu3Zt8vKm5sg35d5770VRURF+++03dOrUyeq67OxsvPzyyzh8+LBVuf2lJdG2Ki4uhkKhQFJSktXlMTExCAsLQ3FxsdXllz5mAAgPD7f5scXHxzeamggAJSUll73tX/7yF/y///f/cM8992DRokUYP348br75Ztxyyy3NToWUSI9DKsm31KdPH2zbts3qMl9fX7l/xaVjmDdvHtavX4/MzExoNBps3LgRjz32WKN+V0RERO42fPhwDB06tNHl4eHhjabypaen4+OPP8avv/6KMWPGYNOmTTh37hzuvPPORre/9LgKAJKTk/HJJ58AaJjOJooiFi9ejMWLFzc5ttLSUqtQq6VjGVuO47Zv344lS5Zgx44d0Ov1VttrNBr5eKyl+7JnH609DmzNc3Opo0ePAmgIv5oSEhJi9XtzxzX2UKvVjXq4hoaGIj4+vtExUGhoaJPHhpe+jkFBQYiNjZVfx+aO1/z8/NCjR49Gx6VdunSxCowux2w247XXXsNbb72F48ePo76+Xr7u0mNuoPFrHB4eDuDiayl9QWk5zfVSjni9iZrCQIrIhUJDQxEbG4v9+/e3uN3+/fvRpUuXRv8QX8oR4UFz3+I1d7n0jWNLXnvtNXz44Yd4//33MWjQIKvr3n//fcyZMwc33ngjHn/8cURFRcHHxwfLly+3qthpDVufj7Y8trby9/fHL7/8gi1btuDbb7/F999/j48//hjjxo3D//73P4euhGj5DZql8PBwTJs2TQ6kPv30U9TW1uKOO+5w2H0TERG5w8SJExEdHY33338fY8aMwfvvv4+YmJgmv0i6HKmSeeHChU1WIgFo9GWYPavcXXrcUlRUhPHjx6NPnz5YuXIlunbtCj8/P/z3v//FK6+80qiyuqn7sncfrT0ObM1zcylpH//5z38QExPT6PpLVylu7rjGHs447m0re1dGXLZsGRYvXoy7774bzz33HCIiIqBQKDBv3rwmq+8d8dgc8XoTNYWBFJGLTZs2De+88w62bduG0aNHN7r+119/xYkTJ3D//fc3uu7o0aNW34YVFhbCbDZbNXx0d4XLr7/+ioULF2LevHlNrn7y6aefokePHvj888+txrpkyRKr7ex5HN27d4fZbMbRo0flJpkAcO7cOVRWVqJ79+6teCTOo1AoMH78eIwfPx4rV67EsmXL8Pe//x1btmzBtdde2+xjlx7HkSNHGn2beOTIEbseZ3p6Om644Qbs3r0b69evR1pamk0N3YmIiDyZj48Pbr/9drz33ntYsWIFvvzyy2an0UkVOpYKCgrk46oePXoAAJRKZasCrabur6XjuG+++Qa1tbX4+uuvrapampq61hxH7MMW9jw3zR3XSAvvREVFOeT5dZWjR4/immuukX+vrq7GmTNnMGXKFADWx2vS8wQ0LCBz/Phxmx9rc8/bp59+imuuuQZr1qyxuryyshKRkZF2PRbg4utw8ODBZsfm6M8CkYQ9pIhc7PHHH4e/vz/uv/9+XLhwweq68vJy/O1vf0NAQECT/YikZWklb7zxBgBg8uTJ8mWBgYGNlpR1lTNnzmDmzJkYPXo0XnzxxSa3kQ4ILb+V2blzJ3bs2GG1nbRyii2PRToAePXVV60uX7lyJYCGHkueory8vNFlUhVZbW0tAMg9Li597EOHDkVUVBTefvtteVugYbnk/Px8ux7n5MmTERkZiRUrVmDr1q2sjiIionbjzjvvREVFBe6//35UV1c3+2/cl19+adX3ZteuXdi5c6d8XBUVFYWrr74a//rXv3DmzJlGtz9//rxd47rccVxTx0gajQZr1661+T4csQ9b2PPcNHdcM3HiRISEhGDZsmWNVky8dB+e5N///rfVeFevXg2TySS/jtdeey38/Pzw+uuvW70Oa9asgUajsfl4rbljeh8fn0bVTRs2bGh1D6fBgwcjMTERr776aqP7k+7H0Z8FIgkrpIhcrFevXsjOzsbs2bPRv39//PWvf0ViYiJOnDiBNWvWoKysDB9++KH8bYWl48ePY/r06Zg0aRJ27NiB999/H7fffjsGDhwobzNkyBBs2rQJK1euRFxcHBITE+VGlM42d+5cnD9/Hk888QQ++ugjq+sGDBiAAQMGYNq0afj8889x0003YerUqTh+/DjefvttpKamorq6Wt7e398fqamp+Pjjj5GcnIyIiAj069evyfntAwcOREZGBv7973+jsrISY8eOxa5du5CdnY0bb7zR6lssd8vKysIvv/yCqVOnonv37igtLcVbb72F+Ph4uWKuZ8+eCAsLw9tvv43g4GAEBgZixIgRSExMxIoVK3DXXXdh7NixmDVrFs6dO4fXXnsNCQkJeOyxx2weh1KpxG233YZVq1bBx8cHs2bNctZDJiIicqm0tDT069cPGzZsQEpKCgYPHtzkdklJSRg9ejQeeOAB1NbW4tVXX0WnTp3wxBNPyNu8+eabGD16NPr37497770XPXr0wLlz57Bjxw6UlJRg3759No/rcsdxEyZMgJ+fH66//no5THvnnXcQFRXVZAjQFEfsw1a2PjeDBg2Cj48PVqxYAY1GA5VKhXHjxiEqKgqrV6/GnXfeicGDB+O2225D586dcfLkSXz77bcYNWoUVq1a5dAxO0JdXR3Gjx+PmTNn4siRI3jrrbcwevRoTJ8+HUDDYjlPPfUUli5dikmTJmH69OnydsOGDbP5S8AhQ4Zg9erV+Mc//oGkpCRERUVh3LhxmDZtGrKysnDXXXfhyiuvxIEDB7B+/Xqraix7KBQKrF69Gtdffz0GDRqEu+66C7GxsTh8+DAOHTqEH374AYBjPwtEMjes7EdEoiju379fnDVrlhgbGysqlUoxJiZGnDVrlrwEqyVpueC8vDzxlltuEYODg8Xw8HDx4YcfFmtqaqy2PXz4sDhmzBjR399fBCBmZGSIonhxqdrjx4/L23bv3l2cOnVqo/sDID700ENWl0lLJL/44ouNxiWRlq5t6kdaNtdsNovLli0Tu3fvLqpUKjEtLU3cuHGjmJGRIXbv3t3qPn/77TdxyJAhop+fn9U+Lr1fURRFo9EoLl26VExMTBSVSqXYtWtX8amnnrJamralxzx27Ngml9a15bmRNLXE8KVj3bx5s3jDDTeIcXFxop+fnxgXFyfOmjVLLCgosNrXV199Jaampoq+vr4iAHHt2rXydR9//LGYlpYmqlQqMSIiQpw9e7bVstWi2LC0cWBgYIuPZdeuXSIAccKECZd93ERERK7W1L+rlsaOHSv27du3yeteeOEFEYC4bNmyRtdZHtO8/PLLYteuXUWVSiVeddVV4r59+xptX1RUJKanp4sxMTGiUqkUu3TpIk6bNk389NNPbRqrPcdxX3/9tThgwABRrVaLCQkJ4ooVK8R3333X5mM4R+zD1uNAW58bURTFd955R+zRo4fo4+MjAhC3bNkiX7dlyxZx4sSJYmhoqKhWq8WePXuKc+bMEffs2SNvY8txjaWmXo/m9tHc++jS50fa59atW8X77rtPDA8PF4OCgsTZs2eLFy5caHT7VatWiX369BGVSqUYHR0tPvDAA2JFRYVN9y2Konj27Flx6tSpYnBwsAhAPk41GAziggULxNjYWNHf318cNWqUuGPHjkbHslu2bBEBiBs2bLDar/RaWh5biqIobtu2TbzuuuvE4OBgMTAwUBwwYID4xhtvWG1j6+tNZCtBFF3QqY2I2uTZZ5/F0qVLcf78+VbNDSdqyr59+zBo0CCsW7euydWHiIiIvNVrr72Gxx57DCdOnGi0ytiJEyeQmJiIF198EQsXLnT6WHgc1z689957uOuuu7B79+4mV30kIvuxhxQRUQf1zjvvICgoCDfffLO7h0JEROQwoihizZo1GDt2bKMwioiIPAd7SBERdTDffPMN8vLy8O9//xsPP/yw3GyUiIjIm+l0Onz99dfYsmULDhw4gK+++srdQyIiohYwkCIi6mAeeeQRnDt3DlOmTMHSpUvdPRwiIiKHOH/+PG6//XaEhYXh6aeflptMExGRZ2IPKSIiIiIiIiIicin2kCIiIiIiIiIiIpdiIEVERERERERERC7V7ntImc1mnD59GsHBwRAEwd3DISIiIhuJooiqqirExcVBoeB3aB0Bj9uIiIi8U2uO29p9IHX69Gl07drV3cMgIiKiVjp16hTi4+PdPQxyAR63EREReTd7jtvafSAVHBwMoOFJCQkJcfNoiIiIyFZarRZdu3aV/y2n9o/HbURERN6pNcdtbg2k6uvr8eyzz+L999/H2bNnERcXhzlz5uCZZ56Ry7TnzJmD7Oxsq9tNnDgR33//vU33Ie0nJCSEBzZEREReiFO3Og4etxEREXk3e47b3BpIrVixAqtXr0Z2djb69u2LPXv24K677kJoaCjmzp0rbzdp0iSsXbtW/l2lUrljuERERERERERE5ABuDaR+++033HDDDZg6dSoAICEhAR9++CF27dpltZ1KpUJMTIw7hkhERERERERERA7m1iVrrrzySmzevBkFBQUAgH379mHbtm2YPHmy1XY///wzoqKi0Lt3bzzwwAO4cOFCs/usra2FVqu1+iEiIiIiIiIiIs/h1gqpRYsWQavVok+fPvDx8UF9fT2ef/55zJ49W95m0qRJuPnmm5GYmIiioiI8/fTTmDx5Mnbs2AEfH59G+1y+fDmWLl3qyodBRERERERERER2EERRFN115x999BEef/xxvPjii+jbty/27t2LefPmYeXKlcjIyGjyNseOHUPPnj2xadMmjB8/vtH1tbW1qK2tlX+XOr1rNBo2xyQiIvIiWq0WoaGh/De8A+FrTkRE5J1a82+4WyukHn/8cSxatAi33XYbAKB///4oLi7G8uXLmw2kevTogcjISBQWFjYZSKlUKjY9JyIiIiIiIiLyYG4NpPR6PRQK6zZWPj4+MJvNzd6mpKQEFy5cQGxsrLOHR0TkVcxmMwoLC6HRaBAaGoqkpKRGf2OJiIiIiIg8gVsDqeuvvx7PP/88unXrhr59+yI3NxcrV67E3XffDQCorq7G0qVLMWPGDMTExKCoqAhPPPEEkpKSMHHiRHcOnYjIo+Tm5iI7Oxv5+fkwGAxQq9VISUlBRkYG0tLS3D08IiIiIiIiK24NpN544w0sXrwYDz74IEpLSxEXF4f7778fmZmZABqqpfbv34/s7GxUVlYiLi4OEyZMwHPPPcdpeURE/yc3NxdZWVkoKytDfHw8AgMDodPpkJOTg+LiYmRmZjKUIiIiIiIij+LWpuauIDfWOn266cZaPj6AWn3xd52u+Z0pFIC/f+u21euB5p5qQQACAlq3bU0N0MIURwQGtm5bgwGor3fMtgEBDeMGgNpawGRyzLb+/g3PMwDU1QFGo2O2Vasb3hf2bms0NmzfHJUK8PW1f1uTqeG5aI6fH6BU2r9tfX3Da9ccpbJhe3u3NZsb3muO2NbXt+G5ABo+E3q9Y7a153Pv4X8jzGYzFi1ahNzcXPTu3RtQKGD8v/eOKIooOngQQwcPxvLly5uevse/EfZvy78RDVzwN0JbWYnQ8HA2uO5A2NSciIjIO7Xq33CxndNoNCIAUdNw+tb4Z8oU6xsEBDS9HSCKY8dabxsZ2fy2Q4dab9u9e/PbpqZab5ua2vy23btbbzt0aPPbRkZabzt2bPPbBgRYbztlSvPbXvq2ueWWlretrr64bUZGy9uWll7c9sEHW972+PGL2y5c2PK2Bw9e3HbJkpa33bXr4rYvvNDytlu2XNx21aqWt9248eK2a9e2vO0nn1zc9pNPWt527dqL227c2PK2q1Zd3HbLlpa3feGFi9vu2tXytkuWXNz24MGWt1248OK2x4+3vO2DD17ctrS05W0zMi5uW13d8ra33CJaaWlbL/sbcS4gQBw+fLg4e/Zs8b777hMLIyKa3y//Rlz84d+Ihh8P+xuh2b9fBCBqNBqROgb5uI2vORERkVdpzb/hbp2yR0TUknOlpdAUFDQ053b3YLxEfX09tFotysrKEBgYyKbmROSVblrxA3zVAZffkIiIWvTD4qnuHgJRszhlz8On41x2W07Za/h/Tsexf1sPmI7T1Lb79u3D+vXrcfjwYejr6uATENDQnDs9HWm9eze/3w46Ze/o0aNYsGABIiIiEBwcjAMHD+JcVRXi4uKQlJSEmvJyVJaX4+WXX0avXr0a75t/I+zfln8jGnDKHjmBdNw27ulPGEgRETkAAylyldZM2es4FVKBgdYnSC1tZ88+bRVgx0GVPdtantA6clvLE3BHbqtSXQwNHLmtn9/Fkx13batUXjyRc+S2vr4XTzwdua2Pj+3vYXu2VShavW1ubi6yXnxRbs4d1drm3ILgvM+yh/2N6DlgAHr074+cnBykhIej6v+CH6PRCFEUcfzsWQwdOhQ9Bwy4GLg0h38jHLat2WxGYWEhNBoNQkNDG6r8+Deigb1/I4iIiIioXeo4gRQReTSz2Yzs7GyUlZUhJSUFwv9VwYSEhCAlJQX5+flYt24dBg4cyGloFhQKBTIyMlBcXIz8/HzodDqIooiqqirk5+cjMjIS6enpfM5cKDc3F9nZ2cjPz4fBYIBarW6o8svI4GqHRERERET/h2coROQRCgsLkZ+fj/j4eABASUkJTp06BY1GA1EUER8fj7y8PBQWFrp1nGazGQUFBdi9ezcKCgpgbmmKm4ukpaXJ1WM6nQ5arRZVVVUYOnSo7VVl5BC5ubnIyspCTk4OIiIi0KtXL0RERCAnJwdZWVnIzc119xCJiIiIiDwCK6SIyCNoNBoYDAYEBgZCq9Xi2LFj8nUKhQIBAQHQ6XTYtWsXYmNjERwcbNN+m5w61cpqIU+ufElLS0O3bt1w7tw51NXVITIyEi+//DIro1zIssqvT58+OH/+PJRKJav8iIiIiIiawECKiDxCaGgo1Go1dDod6v6vmbOvry8UCgXq6upQXl6Ouro6fPPNN/j1118RFRWFpKQkJCUloWfPnoiOjpan+UkcGSBJlS9Sf6vA1va3cqKqqiqEhYUBAJRKZaPng5zLsspPq9XiyJEjCAsLw4ABAyAIglWVX3JysruHS0RERETkVgykiMgjJCUlISUlBTk5OfKqDOHh4ejTpw8MBgP279+PmJgY9OnTB2fPnkVpaSlKS0vx22+/AQCCgoLQs2dP9OzZE0lJSSgvL8eyZcscEiB5S38rrVYr/7/RaERdXR1Utjb9pjazrPIrKysDANRarGgXEBCA06dPQ6PRuGuIREREREQeg4EUEXkEy+bcR44cQV1dHRQKBaqqqlBSUoLExEQ5RNLr9Th27BgKCwtRWFiIEydOoLq6Gvv27cO+ffsgiiJ27twJrVaLpKQkGI1G1NfXQ61WIyEhAUeOHMEbb7yBhQsXysGN9FNbW2v137q6Opw8eRLff/891Go19u7di/r6egQEBMjhlKdUvlwadFRXVzOQciHLKj+j0QgA8n8BQK/XQ61WIzQ01F1DJCIiIiLyGAykiMhjSM25n3rqKRw6dAhlZWVQqVQYOnQo0tPT5YqmgIAA9OvXD/369QMAmEwmnDx5EkVFRSgqKsKuXbtQXl4OPz8/lJSUoKSkxOp+6urq8OOPP0Kn08lT3FpSWloqN1eXKl70ej10Oh2CgoI8pvLFskIKaAikOnXq5KbRdDyWVX7+/v4AgPr6eoiiCKChUf/QoUORlJTkzmESEREREXkEBlJE5FHS0tIwffp0hIaG4pprrsG4ceMu24jc19cXPXr0QI8ePXDddddh8ODByM/PR2RkJHQ6HTQaDfR6PQRBkBukG41GhIaGIjExEX5+flCpVPDz85N/LH8vLS3F6dOnER4ejuDgYBQVFaGmpkbudeUplS9NBVLkOpZVfnl5eTCZTPD19UVFRQXOnj2LyMhIpKens6E5EREREREYSBGRB5Iql4YPH96qKXBhYWEICQlBUFAQ4uLiAECuUhEEAVqtFuXl5Vi4cKFN+zebzdizZw9ycnLQrVs3+Pv7y4GUKIoeU/lyaYWWTqdz00g6LqnKb+HChSgoKIBer8f58+cbVfkREREREXV0DKSIyONUVVUBaGhU3hqWU6ekPk9SI/LWBEiWlS/5+fmor6+H2WxGZWUlysvLPabyRaqQ8vX1hclkYoWUm6SlpWHy5MmIjIxEXV0dHnroIYwbN87t7w8iIiIiIk/Co2Mi8jhSIBUcHNyq20sBUmRkJPLz86HVamEymaDVauWpfPYGSFLly5AhQ1BbWwutVouKigoMHTrUrhX7nEkKpGJiYgBwyp471dTUICwsDFFRUejcuTPDKCIiIiKiS7BCiog8Sn19PfR6PYDWV0gBFwOk7Oxs5Ofn4/Tp01Cr1W2aOpWWloaBAwfi/fffxxdffIFBgwZh8eLFHhM2SIFUXFwcSkpKGEi5keV0Sb4ORERERESNMZAiIo8incgLgoDAwMA27UsKkAoLC6HRaBAaGnrZBumXo1Ao0K9fP2zfvh1qtdpjwqja2lp5BUCpbxaDEPexfO75OhARERERNcZAiog8ilTlExQU5JCwR6FQtKoxekuk1fQubSLuTtJYVCoVOnXqBIBNzd3FaDTCaDTKv/N1ICIiIiJqzDO+2ici+j9SNUlbpus5m2UgJa3e525SkCetLgiwMsddLg2g+DoQERERETXGQIqIPEpbG5q7ghRImUwm1NTUuHk0DRhIeY5Ln3e+DkREREREjTGQIiKP4g0VUkqlEgEBAQA8Z9qeNI7Q0FCrQMpTKrg6Eqkpv4RT9oiIiIiIGmMgRUQexbLSx5N5Wh8py+dNagZvMpnkRufkOlKoKggCAAZSRERERERNYSBFRB7FGyqkAM8LpCwrpPz8/KBUKgEwDHEH6TmPiIgAwCl7RERERERNYSBFRB7FG3pIAZ4XSFk+b4IgsI+UG0mBVFRUlPw7p04SEREREVljIEVEHoUVUq1jWSEFgIGUG0mBVHR0NADAbDZ7TPN7IiIiIiJPwUCKiDwKK6Ra59LeWwyk3EcKpMLCwqBSqQDwdSAiIiIiuhQDKSLyKN4SSEnBjycEUqIoyoGUFJRJjc0ZhLie9JwHBgbKrwN7eRERERERWWMgRUQew2w2yyfunh5IeVKFlF6vR319PYCLzxsrpNxHeg8HBgbKrwMDKSIiIiIiawykiMhjSOGJIAhyZYmn8qRAShpDYGAgfH19ATCQcifLQIqVakRERERETWMgRUQeQzppDwgIgELh2X+epEDKYDCgtrbWrWO5tH8UwEDKnaRAKigoiK8DEREREVEzPPuMj4g6lKaCFU+lVquhVCoBuL9K6tIV9gAGUu4iiqJVDylO2SMiIiIiahoDKSLyGNKJvHQS78kEQfCYaXuskPIctbW1MJvNADhlj4iIiIioJQykiMhjeMsKexJvCKRYmeNa0vPt6+sLpVLJYJCIiIiIqBkMpIjIY3hThRTgHYFUdXU1RFF0y7g6Isv+UYIgMBgkIiIiImoGAyki8hhShZQ39JACPCeQaqqHlDRVrL6+3u1N1zsSyxX2LP/LCikiIiIiImsMpIjIY0iBFCuk7NNUhZSfnx/8/PwAMAxxJcuG5pb/ZYUUEREREZE1BlJE5DHYQ6p1mludkNU5rndphRSnThIRERERNY2BFBF5DPaQsl99fb38vFlO2QO40p47WPaQsvyvyWRCXV2d28ZFRERERORpGEgRkcdghZT9qqqqIIoiFAqFXJUjYSDlelIgFRAQAKBh6qSvry8Avg5ERERERJbcGkjV19dj8eLFSExMhL+/P3r27InnnnvOalqDKIrIzMxEbGws/P39ce211+Lo0aNuHDUROYPZbJZP5r0tkNLpdDCZTG4ZgzRdLzg4GAqF9Z90BlKud2mFFFfaIyIiIiJqmlsDqRUrVmD16tVYtWoV8vPzsWLFCrzwwgt444035G1eeOEFvP7663j77bexc+dOBAYGYuLEiTAYDG4cORE5mk6nk8Nob5myFxQUJIdAUjDkas31jwIYSLnDpU3NLf+frwMRERER0UVuDaR+++033HDDDZg6dSoSEhJwyy23YMKECdi1axeAhuqoV199Fc888wxuuOEGDBgwAOvWrcPp06fx5ZdfunPoRORg0nS9wMDARpU+nkoQBLdP25Pu99L+UQADKXfQ6/UAmg6kWCFFRERERHSRW8/6rrzySmzevBkFBQUAgH379mHbtm2YPHkyAOD48eM4e/Ysrr32Wvk2oaGhGDFiBHbs2OGWMRORc3hbQ3OJFAR5coUUgxDXaapCisEgEREREVFjvu6880WLFkGr1aJPnz7w8fFBfX09nn/+ecyePRsAcPbsWQBAdHS01e2io6Pl6y5VW1uL2tpa+Xd3nSQSkX1aClY8mbsrpDhlz7NI4R8DKSIiIiKilrm1QuqTTz7B+vXr8cEHH+CPP/5AdnY2XnrpJWRnZ7d6n8uXL0doaKj807VrVweOmIicxdsrpBhIkSiK8pQ9y/cxp+wRERERETXm1kDq8ccfx6JFi3Dbbbehf//+uPPOO/HYY49h+fLlAICYmBgAwLlz56xud+7cOfm6Sz311FPQaDTyz6lTp5z7IIjIIaQeUt6ywp7E3YFUSz2k2EzbtfR6vdyYPyAgQL6cwSARERERUWNuDaT0en2j5sU+Pj4wm80AgMTERMTExGDz5s3y9VqtFjt37sTIkSOb3KdKpUJISIjVDxF5PlZItY6tFVJSUELOI1VAqVQq+PpenBHPQIqIiIiIqDG39pC6/vrr8fzzz6Nbt27o27cvcnNzsXLlStx9990AGlawmjdvHv7xj3+gV69eSExMxOLFixEXF4cbb7zRnUMnIgdjhVTr2LLKntlshsFggL+/v0vH1tFIgdSloSqbyxMRERERNebWQOqNN97A4sWL8eCDD6K0tBRxcXG4//77kZmZKW/zxBNPQKfT4b777kNlZSVGjx6N77//Hmq12o0jJ09hNptRWFgIjUaD0NBQJCUlNaq6I+/AQMp+dXV1MBgMAJqukFIqlVCpVKitrUV1dTUDKSeTAifL6XoAe0gRERERETXFrYFUcHAwXn31Vbz66qvNbiMIArKyspCVleW6gZFXyM3NRXZ2NvLz82EwGKBWq5GSkoKMjAykpaW5e3hkJ28PpLRaLcxms0sDUWm6nlKpbDakDwoKkgOpzp07u2xsHVFzFVLs5UVERERE1JhbAymi1srNzUVWVhbKysoQHx+PwMBA6HQ65OTkoLi4GJmZmQylvIy39pAKCQmBIAgwm82orq52ad86y/5RgiA0uU1gYCAuXLjAMMQFpOdYCqAk0nu6trYWJpPJqr+UO7CylIiIiIg8AQMp8jpmsxnZ2dkoKytDSkqKfCIeEhKClJQU5OfnY926dRg4cCBPsryEFOYA3lchpVAoEBQUhKqqKmg0GpcGUi31j5Kwf5Hr6PV6AI0DKX9/fygUCvl9HhYW5obRNWBlKRERERF5Cp6tk9cpLCxEfn4+4uPjYTKZsGfPHhQVFQFomOIZHx+PvLw8FBYWunmkZCudTievAudtFVKA+/pISdMcWwrBuMKb6zRXISUIgkdM25MqS3NychAREYFevXohIiICOTk5yMrKQm5urtvGRkREREQdDwMp8joajQYGgwGBgYE4f/489Ho9SktL5esDAgJgMBjctuoZ2U86SQ8ICICPj4+bR2M/dwVS0v0xkPIMUhXapYEU4P5KtUsrS0NCQuDj4yNXlpaVlWHdunUwm81uGR8RERERdTwMpMjrhIaGQq1WQ6fToaysDABgNBrlEym9Xg+1Wt3iNCbyLN7a0FzirkDKsodUcxhIuU5zTc0B9zc2t6wsFQQBR48exaFDhyCKIitLiYiIiMgtGEiR10lKSkJKSgpOnjyJyspK+fK6ujqIooiSkhKkpqYiKSnJfYMku3hrQ3OJuyukWgpf3R2EdCQtVUhJl7mrQsqystRsNuPMmTNWze5ZWUpERERErsZAiryOQqFARkYGlEolKioqUFdXB7PZjAsXLiA/Px+RkZFIT09nQ3MvYksvJE/GCinbmM1mFBQUYPfu3SgoKGh308Oa6yEFuP91sKwsNRqN8uXSe5aVpURERETkalxlj7xSWloaRo8ejQsXLqCyshJ6vR5lZWUYOXIk0tPTuVqUl5ECKVZI2cebAqmOsLqbLT2k3PU6SJWlOTk5iI+Ply/XaDTo0qULSkpKMHToUFaWNuHqq6/GoEGD8Oqrr7p7KERERETtCgMp8komkwlarRYjR46Er68vzpw5g+uvvx5z5sxhZZQXYg8p+4miaNOUPXcHIcDF1d3KysoQHx+PwMBA6HQ65OTkoLi4GJmZmV4fStXX18NgMADwzCl7UmVpcXExjhw5grq6Ovj6+qKsrAx5eXno3LkzK0vbAVeGZwkJCZg3bx7mzZvn9PsiIiKi9smuI8/8/HwsWbIE48aNQ8+ePREbG4sBAwYgIyMDH3zwAWpra501TiIrR44cQW1tLcLCwjB+/HhERUUhKCiIJ1Neqj31kBJF0SX3WVNTA5PJBMC2CimdTueysVmyXN2tT58+qKurg9FobHeru+n1egCAIAgICAhodL0nBINpaWnIzMxEUlIS6urqoNVqodPpkJqa2i5CQXeoq6tz9xAcShRF+e8KERERkbPZdPb+xx9/4Nprr0VaWhq2bduGESNGYN68eXjuuedwxx13QBRF/P3vf0dcXBxWrFjBYIqcbu/evQCAgQMHIiIiAgBQUVHhxhFRW7SXCimTyYSamhqX3Kc0Xc/f3x9KpbLZ7aQgxGw2u2xslixXd6uqqkJeXh4KCgoAoF2t7iYFTf7+/k0G454QSAENoVR6ejquvPJKXHHFFbjyyisxe/ZshlH/R6fTIT09HUFBQYiNjcXLL79sdX1CQgKee+45pKenIyQkBPfddx8A4LPPPkPfvn2hUqmQkJDQ7O1mzZqFwMBAdOnSBW+++abVNidPnsQNN9yAoKAghISEYObMmTh37px8/Zw5c3DjjTda3WbevHm4+uqr5eu3bt2K1157DYIgQBAEnDhxosXH+/PPP0MQBHz33XcYMmQIVCoVtm3bhqKiItxwww2Ijo5GUFAQhg0bhk2bNsm3u/rqq1FcXIzHHntMvi/Jtm3bcNVVV8Hf3x9du3bF3Llz3VYZSERERJ7NpkBqxowZuPnmm3H27Fls3rwZy5cvxyOPPIJ77rkHTzzxBNatW4fjx49j48aNyM3NbXQgRuRIoihi//79ABoCqbCwMACwWnGPvIu3B1JKpRL+/v4AXDdtz5b+UQDg6+sLlUoFwD1hiOXqblIgJlUTAe1ndbeW+kdZXu4JJ+ZVVVUICwtDXFwcwsLCcOzYMXcPyWM8/vjj2Lp1K7766iv873//w88//4w//vjDapuXXnoJAwcORG5uLhYvXoycnBzMnDkTt912Gw4cOIBnn30WixcvxnvvvWd1uxdffFG+3aJFi/Doo4/ixx9/BNAQGN9www0oLy/H1q1b8eOPP+LYsWP4y1/+YvPYX3vtNYwcORL33nsvzpw5gzNnzqBr16423XbRokX45z//ifz8fAwYMADV1dWYMmUKNm/ejNzcXEyaNAnXX389Tp48CQD4/PPPER8fj6ysLPm+AKCoqAiTJk3CjBkzsH//fnz88cfYtm0bHn74YZsfBxEREXUcNvWQKigoaPEbeMnIkSMxcuRIqxV8iBytuLgYlZWVUKlU6NOnD0pKSgCwQsqbeXsgBTRUSdXU1ECj0SA2Ntbp9ycFUrasihYUFITa2lpUV1cjKirK2UOzYrm6mzS9yWg0wmw2Q6FQtJvV3S4XSFlOnXQ36b2TkpKCAwcOeH11mqNUV1djzZo1eP/99zF+/HgAQHZ2tlUTeAAYN24cFixYIP8+e/ZsjB8/HosXLwYAJCcnIy8vDy+++CLmzJkjbzdq1CgsWrRI3mb79u145ZVXcN1112Hz5s04cOAAjh8/LodI69atQ9++fbF7924MGzbssuMPDQ2Fn58fAgICEBMTY9djz8rKwnXXXSf/HhERgYEDB8q/P/fcc/jiiy/w9ddf4+GHH0ZERAR8fHwQHBxsdV/Lly/H7Nmz5b5SvXr1wuuvv46xY8di9erVUKvVje67trbWqrJeen8SERFR+2dThZQtYVRbtieyhzRdr2/fvvD19ZUrpDQajdf3oemIRFGUT9K9tYcU4PrG5tL9XK5CCnDvdDFpdbeSkhL5pFMURdTV1UEURZSUlCA1NdXrV3e73HtYCqr0er3b/05JJ/xpaWkQBAFlZWWsMEVDdU9dXR1GjBghXxYREYHevXtbbTd06FCr3/Pz8zFq1Ciry0aNGoWjR4+ivr5evmzkyJFW24wcORL5+fnyPrp27WpV0ZSamoqwsDB5G2e69DFVV1dj4cKFSElJQVhYGIKCgpCfny9XSDVn3759eO+99xAUFCT/TJw4EWazGcePH2/yNsuXL0doaKj8Y2tVFxEREXm/VneAPnPmDG655RZ07twZERERuP7661n2Ty6xb98+AMCgQYMANJyQKxQKmM1mudKGvIflCToDKdvZOmUPcG8gJa3uFhkZieLiYtTV1cFsNuPChQvIz89HZGRku1jdTXpuLzdlD3B/lZT03omKipKrf1glZbvmXmNnUygUjRYmcFRF+qWPaeHChfjiiy+wbNky/Prrr9i7dy/69+9/2Sbu1dXVuP/++7F37175Z9++fTh69Ch69uzZ5G2eeuopaDQa+efUqVMOeUxERETk+Vp9BnD33XejX79+2Lp1K3766SdER0fj9ttvd+TYiBo5f/48Tp8+DYVCgX79+gFoOEiXTso5bc/7SCfHAQEB8PW1aRaxR2Ig1TxpdbeYmBh5dbeysjIMHTq03azuJvXFai6sUCgU8up77m5sbvnekSrTGEgBPXv2hFKpxM6dO+XLKioq5Cb8zUlJScH27dutLtu+fTuSk5Ph4+MjX/b7779bbfP7778jJSVF3sepU6eswpi8vDxUVlYiNTUVANC5c2e5V5NEqhiW+Pn5WVVltdb27dsxZ84c3HTTTejfvz9iYmIaNUhv6r4GDx6MvLw8JCUlNfrx8/Nr8r5UKhVCQkKsfoiIiKhjsDmQevTRR62+1S0sLMSTTz6J1NRUDBo0CI8++iiOHDnilEESSaTqqOTkZKsTv/DwcABsbO6NpJNzb66OAtw3Zc/WHlKAeytz0tLSMGrUKHl1t3vvvRcvv/xyuwijgMtXSAHuDwaBhn49BoMBQMN7p1evXgAYSAENr89f//pXPP744/jpp59w8OBBzJkz57LVewsWLMDmzZvx3HPPoaCgANnZ2Vi1ahUWLlxotd327dvxwgsvoKCgAG+++SY2bNiARx99FABw7bXXon///pg9ezb++OMP7Nq1C+np6Rg7dqw8nW7cuHHYs2cP1q1bh6NHj2LJkiU4ePCg1X0kJCRg586dOHHiBMrKylo9PbRXr174/PPP5Qqn22+/vdG+EhIS8Msvv+DPP/9EWVkZAODJJ5/Eb7/9hocffhh79+7F0aNH8dVXX7GpORERETXJ5kAqPj4eQ4YMwddffw0A+Mtf/oIRI0Zg0aJFWLBgAaZPn47Zs2c7baBEwMVvgy2brQKQ+0ixQsr7tIeG5gArpC5HFEV5dbeoqCgEBAR4/TQ9S5dram55nTuDQenzplQqoVKp5GlUJSUl8iqIHdmLL76Iq666Ctdffz2uvfZajB49GkOGDGnxNoMHD8Ynn3yCjz76CP369UNmZiaysrKsGpoDDcHVnj17kJaWhn/84x9YuXIlJk6cCAAQBAFfffUVwsPDMWbMGFx77bXo0aMHPv74Y/n2EydOxOLFi/HEE09g2LBhqKqqQnp6utV9LFy4ED4+PkhNTUXnzp0v2/OpOStXrkR4eDiuvPJKXH/99Zg4cSIGDx5stU1WVhZOnDiBnj17onPnzgCAAQMGYOvWrSgoKMBVV10lV0fGxcW1ahxERETUvtk8P+bxxx/HLbfcggcffBDvvfce3njjDYwYMQI///wz6uvr8cILL+CWW25x5lipg6uurpa/xW8ukGKFlPdhhVTrtKZCyp2BVFVVlVWFRXsLj21pzO8JlWqWQaYgCAgLC0NkZCTKyspw7Ngx9O3b121j8wRBQUH4z3/+g//85z/yZY8//rj8/5dOW5PMmDEDM2bMaHHfISEh+OSTT5q9vlu3bvjqq69a3MfSpUuxdOnSZq9PTk7Gjh07WtyHpauvvrpRXyqgofrpp59+srrsoYcesvr9iiuukKuWLQ0bNgz/+9//bB4DERERdVx2NWxJTEzEd999h/Xr12Ps2LF49NFH8dJLL0EQBGeNj0i2f/9+iKKI+Ph4dOrUyeo6TtnzXqyQsp9lA39vqZC69HkpLy9300icQwqZpD5RTZEqpDzhdbAMMnv16oWysjIUFhZ2+ECKiIiIiFzH7vkSFy5cwOzZs7F7927k5uZi5MiR2L9/vzPGRmTl0tX1LHHKnvdqb4GUwWBAbW2tU++ruroaoihCEASbnjdPCEKksFipVFr93l7YUyHlztdBqpCyfN+wsXn79be//Q1BQUFN/vztb39z9/CIiIiog7O5Qmrz5s24/fbbcf78ecTFxWHDhg149913sWXLFsyaNQtTp07F0qVL4e/v78zxUgdlNBqRl5cHoPF0PYAVUt6svQRSarUaSqUSRqMRGo0GUVFRTrsvKVQICgqyqQ+TJ0wVkz6b3bp1Q1FREaqqqmA0GuWAytvZ09TcE6bsWVZISYHU8ePHYTKZvHq1S0/V3FQ/Z8vKymrUXF3C1eyIiIjI3WyukHrooYfwxBNPQK/XY9WqVZg3bx4A4JprrsEff/wBpVLZZOUKkSPk5+ejrq4O4eHh6Nq1a6PrLSukmuqHQZ6rvfSQEgTBZdP2mgoVWmJZmeOuz4f0nMTGxsrLv7eXikaj0Qij0QjAtqbmnlAhZRlGREdHIygoCEajsdVNsMkzRUVFISkpqckfZ4bmRERERLawOZA6c+YMpk6dCrVajUmTJuH8+fPydSqVCs8//zw+//xzpwySSFpdb9CgQU32LJMqpOrq6rhSlJdpLxVSwMWASDrpd5ampl21RApCRFGEXq932rhaIgVSYWFh8ue1vQRSUsWTQqGAWq1udjtPmLInvQ6WgZQgCJy2R0REREQuZ3MgNX36dNxyyy14+umnMWHCBEyZMqXRNmyGSs5gNpvlPmVNTdcDGvrSSCfdnLbnXdpjIOXsCil7VtgDAF9fXzkocVcYIn0uw8LCEBERAaD9BFKW0/VaWuTDE6bsNdcMn4EUEREREbmazYHUmjVrcP/990Oj0eCOO+7Aq6++6sRhEV10/PhxVFVVwd/fH8nJyc1u196qLjoCURTlk3kGUrZratrV5bi7OscyRJM+q+1lpT2p6qyl6XqW13tChdSlYWavXr0ANARSnPZMRERERK5gc+dSPz8/PPLII84cC1GTpOl6/fr1g4+PT7PbhYWFoaSkhBVSXkSv18NsNgPw/h5SgOdWSAENz29ZWZnbqnMsK6TaW3hsS0NzwLpCSlol0ZVEUWw2zOzatSuUSiV0Oh3Onj2L2NhYl46NiIiIiDoemyqkfv/9d5t3qNfrcejQoVYPiOhS+/btA4DLNs23bGxO3kE6kVer1e1iZS9WSDXNbDZbNWJvb4GUFPLZWiEliqJbet3V1tbKzdcvrUj08fFBjx49AHDaHhERERG5hk2B1J133omJEydiw4YNzX67npeXh6effho9e/ZETk6OQwdJHdfZs2dx7tw5+Pj4oF+/fi1uK53kskLKezTXz8ZbMZBqmlarlSuCgoOD210PKenfxctV+fn6+kKlUgFwz+sgvS/VarU8DkvStL2jR4+6dFxERERE1DHZVJKQl5eH1atX45lnnsHtt9+O5ORkxMXFQa1Wo6KiAocPH0Z1dTVuuukm/O9//0P//v2dPW7qIKTqqD59+rS4ehXACilvJAVS7WG6HuD5U/YA9wYhoaGhUCgU7a6HlBRIBQQEXHbboKAg1NbWorq6GlFRUc4empXLBZlsbE5ERERErmRTIKVUKjF37lzMnTsXe/bswbZt21BcXIyamhoMHDgQjz32GK655hr5W28iR5H6RzW3up4lVkh5n/a0wh5wMSCqrq6GyWRyyjREk8kkN9G2p0LKnQ21Lw3QpH8r9Ho9amtrm6zW8Sa2VkhJ21y4cMEtvbwuF0glJiZCEARcuHABFRUV8t9UIiIiIiJnsPtsaejQoRg6dKgzxkJkRavV4vjx4wBsC6RYIeV9pHCkvVRIBQUFQaFQwGw2o6qqyikn9FKo4OPjY1NFjuXYAPcEUpYNzYGGKWNqtRoGgwGVlZWIjo52+Zgcydam5pbbuGvqJNB8IKVWq9GtWzcUFxejsLAQw4YNc+XwiIiIiKiDsamHFJE77Nu3D6Ioonv37vKJbEukk3+dTic37iXP1t4qpARBcPq0PctQwZ5V2jxlyp6kPU3bs7WpOWC90p6rSa9DS5V1nLZHRERERK7CQIo8lq2r60n8/f2hVCoBcNqet2hvgRTg/D5SrWloDnhGhZRlINWeGpvbE0h5QoVUS73HGEgRERERkaswkCKPVFtbi/z8fAC2B1KCILCPlJdhIGW/1jQ0BzwjkLKsdGyPFVK29pACPHPKHnAxkPrzzz/lXmVERERERM7AQIo8Ul5eHkwmEyIjIxEbG2vz7dhHyru0tx5SgOdXSOn1epjNZoePqyXSc9FUIOXtn1VRFL1myp4t752QkBBERUVBFEUcO3bMVUMjIiIiog7I7kCKB6jkCtLqeoMGDbKrTw4rpLwLK6Ts19pASgpLRFFETU2Nw8fVkqaqutrLlL3a2lrU19cD8J4pe5d773DaHhERERG5gt2BVFJSEq655hq8//77MBgMzhgTdXBmsxkHDhwAYNvqepakCgwGUp5PFEUGUq3Q2il7Pj4+8Pf3B+DaMKS+vl5+ndtjhZRU6eTr6yv3sGuJu6bsiaJoUw8pgIEUEREREbmG3YHUH3/8gQEDBmD+/PmIiYnB/fffj127djljbNRKZrMZBQUF2L17NwoKClw+PaetCgsLodPpEBgYKJ8Y2aq9nOR2BDU1NfJ7k4GU7VpbIQW4JwzRarUQRREKhcJqamZ76SFl2T/KlmpOd03Z0+v1ciXX5T5v0t/d48ePw2QyOX1sRERERNQx2R1IDRo0CK+99hpOnz6Nd999F2fOnMHo0aPRr18/rFy5EufPn3fGOMlGubm5mD9/Ph555BEsXLgQjzzyCObPn4/c3Fx3D81m0nS9AQMGQKGw7y3KCinvIVXNqNVq+Pr6unk0juOpFVKAewIpy/FaBjZSIGUwGLy62tae/lGW2+l0Ooii6LRxXUoKMgMCAi77eYuKikJwcDBMJhOKi4tdMTwiIiIi6oBa3dTc19cXN998MzZs2IAVK1agsLAQCxcuRNeuXZGeno4zZ85cdh8JCQkQBKHRz0MPPQQAuPrqqxtd97e//a21Q273cnNzkZWVhZycHERERKBXr16IiIhATk4OsrKyvCKUEkUR+/btA2D/dD2AFVLepD02NAcuBkVardYp1YltqZByR/8iKRy+NEBTqVQICAgA4N1VUtJzaW8gZTKZUFtb67RxXcqeIFMQBE7bIyIiIiKna3UgtWfPHjz44IOIjY3FypUrsXDhQhQVFeHHH3/E6dOnccMNN1x2H7t378aZM2fknx9//BEAcOutt8rb3HvvvVbbvPDCC60dcrtmNpuRnZ2NsrIypKSkwGw2o6amBiEhIUhJSUFZWRnWrVvn8dP3Tp8+jbKyMiiVSqSmptp9e6lCSqPRePxj7ejaY/8ooOHxCIIAs9ns8OCntrYWdXV1ALxnyp4USFn2j5K0h8bm9lZI+fn5yb2mXDltTwoybf28MZAiIiIiImeze57MypUrsXbtWhw5cgRTpkzBunXrMGXKFHlqVWJiIt577z0kJCRcdl+dO3e2+v2f//wnevbsibFjx8qXBQQEICYmxt5hdjiFhYXIz89HfHw8qqursX//fgBAbGwsEhISEB8fj7y8PBQWFiI5OdnNo22eVB2VkpIClUpl9+1DQkKgUChgNpuh1WqbPAkmz9BeAykfHx8EBQWhqqoKGo2mVcFRc6QqF5VK1arPhzun7DX1WQwLC0NJSYlXV0jZG0gJgoDAwEBUVlaiuroanTp1cubwZLY2NJdYBlKiKNq12ikRERERkS3srpBavXo1br/9dhQXF+PLL7/EtGnTGvX5iYqKwpo1a+zab11dHd5//33cfffdVge+69evR2RkJPr164ennnoKer2+xf3U1tZCq9Va/XQEGo0GBoMBgYGBVid3Z86cwZ49e1BVVYWamhqn9bVxFKl/VGum6wGAQqGQT7jYR8qztddACnBeH6m2TNcD3N9D6lJShZQ3f1btDaQA9zWXB2x/73Tr1g0qlQp6vd6mKfhERERERPayu0Lq6NGjl93Gz88PGRkZdu33yy+/RGVlJebMmSNfdvvtt6N79+6Ii4vD/v378eSTT+LIkSP4/PPPm93P8uXLsXTpUrvuuz0IDQ2FWq2GTqeTp7906dIFlZWV0Ol0yM/Ph4+PD2pqatw80uZVVFSguLgYgiBgwIABrd5PWFgYKioqUFFRYVOlHrlHe+0hBTR8HktKShhIoeUpe+1hpT3LVfZs5Y6V9uxthq9QKJCYmIjDhw+jsLAQcXFxzhweEREREXVAdldIrV27Fhs2bGh0+YYNG5Cdnd3qgaxZswaTJ0+2Oui97777MHHiRPTv3x+zZ8/GunXr8MUXX6CoqKjZ/Tz11FPQaDTyz6lTp1o9Jm+SlJSElJQUFBcXyyet8fHxGDx4MHr06IGamhqo1Wp88MEH2LBhg0euaiVN1+vRo0ebpjlJJ7neXHXREbBCyn5tWWEP8LwgpD30kLK3qbnltq4MBlvzeWMfKSIiIiJyJrsDqeXLlyMyMrLR5VFRUVi2bFmrBlFcXIxNmzbhnnvuaXG7ESNGAGj54FilUiEkJMTqpyNQKBTIyMiAn58fKioq4OvrCx8fH1RVVUGr1SItLQ3Tp0+HKIrYtGkTlixZgj179rh02fHLacvqepakSgxvPsntCBhI2c+bK6SaCqTaQ4WUNI28NYGUpwSDzenVqxcA2yqjiYiIiIjsZfeUvZMnTyIxMbHR5d27d8fJkydbNYi1a9ciKioKU6dObXE7qb9QbGxsq+6nvUtLS8O4ceNw4cIF+Pj4oLCwEGq1GkOHDkV6ejrS0tJw6NAhfPTRRygtLcU777yD7du3Y9asWYiKinLr2GtqanDkyBEAwKBBg9q0LymQYoWUZ2MgZT9HVUi5KpAymUzyfbU0Za+iosJrG2e3pkLKG3pIAQ2LlCgUCpSXl6O8vFyuaCMiIiIicgS7A6moqCjs37+/UW+effv2tWq1ILPZjLVr1yIjIwO+vheHU1RUhA8++ABTpkxBp06dsH//fjz22GMYM2ZMm/oLtWeiKKKqqgojR47ETTfdhMjISISGhiIpKUluPN+3b19kZmbihx9+wHfffYe8vDwsXboUkyZNwqRJk+TlyF3t0KFDqK+vR3R0NKKjo9u0L07Z8w7tvYcU4LkVUnq9HmazudGCFI4mjdfHx6fJwEb6rNbV1aGmpgYBAQFOHY8zeENTc7PZLAfA9rx3VCoVunbtiuLiYhQVFTGQIiIiIiKHsvtsZNasWZg7dy62bNmC+vp61NfX46effsKjjz6K2267ze4BbNq0CSdPnsTdd99tdbmfnx82bdqECRMmoE+fPliwYAFmzJiBb775xu776Cj+/PNPaLVaqFQqXHfddRg2bBiSk5MbnXQqlUpMmzYNS5YsQd++fWEymbBx40Y8++yzOHjwoFvGLlW/tbU6CuCUPW8ghacAK6Ts0dZASgpNRFF0yXQxy4bmTVU/KZVKOZzxxml7oijKU/Y8ual5dXW1XIFm7+eN0/aIiIiIyFnsrpB67rnncOLECYwfP16uaDKbzUhPT29VD6kJEyY02ceoa9eu2Lp1q93768gOHToEAOjdu7dVtVlzoqKi8MgjjyA3Nxcff/wxysrK8MYbb2Dw4MGYOXOmXL3gbCaTSQ7C2to/CrCukPLWaUDtncFgQH19PYD2H0g58j3Y1il7CoUCAQEB0Ov10Ol0Tn/ubRlveHg4qqurUVFRgfj4eKeOx9H0er3875c91V2ubmouBZlBQUF2V8UlJSVh06ZNbGxORERERA5ndyDl5+eHjz/+GM899xz27dsHf39/9O/fH927d3fG+MgOUiDVt29fm28jCAIGDx6M1NRUbNy4EZs3b8Yff/yBQ4cOYdq0aRg/fjx8fHycNWQADd+819TUICQkpMn+ZPaSKqS8eRpQeydVR6lUKrdNE3UmKYAxmUwOew9aVpW1ZbGGoKAg6PV6l4QhlhVSzYmIiMCpU6e8sqJRqnBSqVQ2fQkgcfWUvbZU1vXs2RMAcPr0aej1ev49JSIiIiKHsTuQkiQnJyM5OdmRY/EqZrMZhYWF0Gg0jfo0uYPBYJC/wbYnkJKo1WrccsstGDlyJNavX4+ioiJ89tln2LFjB26//XZ52oYzSNP1BgwY4JDnUKlUIjAwEDqdDpWVlTyB8kDteboe0PAe9Pf3R01NDTQajUPeg3q93iFVZUFBQSgtLXVJGGJrhRTgnVP2pEDK3j5orp6y15ZAKiQkBNHR0Th37hyKiorQv39/Rw+PiIiIiDqoVgVSJSUl+Prrr3Hy5EnU1dVZXbdy5UqHDMyT5ebmIjs7G/n5+TAYDFCr1UhJSUFGRgbS0tLcMqYjR46gvr4ekZGRbVoxr0uXLnj88cexY8cOfPbZZzh9+jReeukljBw5EjNmzHB4gCCKIvbt2wfAMdP1JOHh4dDpdKioqEBcXJzD9kuO0Z4bmktCQ0PlQMoRK4NK4U5gYKBd1TiXcmV1jlQh1VIgJTXK9uYKKXsDR2nKXl1dHYxGo9OrBNs61TMpKQnnzp1DYWEhAykiIiIichi7z2o2b96M6dOno0ePHjh8+DD69euHEydOQBRFDB482Blj9Ci5ubnIyspCWVkZ4uPj5UqcnJwcFBcXIzMz0y2hlDRdr1+/fm3elyAIuPLKKzFw4EB88cUX2LZtG3bs2IF9+/bhpptuwlVXXeWwnjjSVB0/Pz+kpKQ4ZJ9AwxShkpISrrTnodp7hRTQcPJ/9uxZhzU2b2tDc4kr+xdJj72lKXvevAhBayuk1Go1FAoFzGYzqqurnd6vr63vnaSkJGzfvp2NzYmIiIjIoeyeH/XUU09h4cKFOHDgANRqNT777DOcOnUKY8eOxa233uqMMXoMs9mM7OxslJWVISUlRf5WPCQkBCkpKSgrK8O6detgNptdOi5RFFvVP+pyAgMDcccdd+CJJ55A165dodfrsX79evzzn//EyZMnHXIfUnVU3759HVolIJ3geeNJbkfQUQIpwHEr7bW1ykXiyulitvaQArzzsyqFelLIZytBEFz6OjgikAKA4uJiGI1Gh42LiIiIiDo2uwOp/Px8pKenAwB8fX1RU1ODoKAgZGVlYcWKFQ4foCcpLCxEfn4+4uPjUVxcjN9//x3nzp0D0HCCER8fj7y8PJevRnT+/HmUlZXBx8cHvXv3dvj+e/Togaeffhq33XYb1Go1Tpw4gWXLluGjjz5CTU1Nm/Yt9Y8aNGhQ2wdqQToBZoWUZ2IgZT9HVUi5csqePT2kKioqmlxx1ZPp9XoA9gdSlrdxxevQ1vdO586dERISApPJhOLiYkcOjYiIiIg6MLsDqcDAQLlvVGxsLIqKiuTrysrKHDcyD6TRaGAwGBAYGAilUgmz2YzS0lL5+oCAABgMBoedgNpKqo5KSkqCSqVyyn0oFApcc801yMrKwrBhwyCKIrZs2YLMzEzs2rWrVSeSZWVlKCkpgUKhcHhfElZIebaO0kMK6LiBlNFolKt/LjdlTxAEGI1Gl6065yitrZAC3BMMtva9IwiCXCXFaXtERERE5Ch2B1JXXHEFtm3bBgCYMmUKFixYgOeffx533303rrjiCocP0JOEhoZCrVZDp9MhMjISgiBAq9XCYDAAaPi2XK1Wt3lKjb0OHjwIwLHT9ZoTGhqKe+65B4899hiio6Oh1WqxZs0avPrqqzh79qxd+5Km6yUlJbXqhK4lrJDybKyQsp+jp+w5OwiRxuvr6wt/f/9mt/P19ZXfB94WIEuBW1sCKVdO2WvLe0cKpFxdAUxERERE7ZfdgdTKlSsxYsQIAMDSpUsxfvx4fPzxx0hISMCaNWscPkBPkpSUhJSUFJSUlMDPz08+uD9//jxEUURJSQlSU1PlA3dXMBqNKCgoAOCaQErSp08fZGZm4oYbboBSqcThw4eRlZWFL7/8stHKi81xxup6ElZIeTYGUvbztqbmlg3NL7cIgrd+Xlvb1By4+Do4O5AymUzyfbTlvSP9u1ZUVOR1UyuJiIiIyDPZtcpefX09SkpKMGDAAAANB9Rvv/22UwbmiRQKBTIyMlBcXIz8/HwEBgaivLwcp06dQlVVFSIjI5Geng6Fwu6cr9UKCwtRV1eH0NBQdOnSxWX3CzRUNkyZMgXDhw/HRx99hAMHDuC7777Drl27cNttt8nvk6bodDp56oej+0cBFyukdDqdS5ZVJ/swkLKft1VISdWJtow3IiICxcXFXhtIeXIPKemzplAo2lSJ2rVrV6hUKtTU1ODPP/9EfHy8o4ZIRERERB2UXcmJj48PJkyY4HUnDY6UlpaGzMxMDBkyBEDDwX5lZaVcMZSWlubS8Viurne5KgRniYyMxEMPPYQHH3wQERERuHDhAt5880289dZbuHDhQpO3OXjwIMxmM+Li4hAZGenwMfn7+8PPzw8Ap+15GlEUO1QPKYPBYHPVYEukYMFRPaT0er1TVwS1rJC6HKlCqry83GnjcQZv6CFlWVnXln8jFAoFevToAYDT9oiIiIjIMewu5enXrx+OHTvmjLF4jbS0NKxcuRJvvfUW0tPTceWVV2LixIkuD6MA60DKnQRBwMCBA/Hss89i4sSJUCgU2LdvH5YsWYLvv/8eJpMJAGA2m1FQUIAvv/wSlZWVLVZRtXU80olwRw5QPVFtba38fmjPFVJqtVquzGtrlVR9fb0cXDhiyp4UTDhzupgUBNsTSHnbZ9Ubekg5aqonwD5SRERERORYdk3ZA4B//OMfWLhwIZ577jkMGTKk0YG4Iw56vYFCoUBycjJmzpyJf/3rX8jJycGMGTNcWqVUUVGB06dPQxAEpKSkuOx+W6JSqXDzzTdj5MiR+OCDD1BQUIAvvvgCO3bswKBBg7B161YcOnQIeXl58hSShIQEp4R54eHhKC0tZYWUh5Eqffz8/OQqtvZIEASEhoairKwMGo0GnTt3bvW+qqqqIIoiFApFm6vKFAoFAgICoNPpUF1d7bRQ0J4phhEREQC8K5Cqr6+XF7Tw5Cl7zgqkRFF0W1UuEREREbUPdldITZkyBfv27cP06dMRHx+P8PBwhIeHIywsTP6WuyPp378/1Go1ysvLXf6tcV5eHgAgMTHR4avUtVVsbCzmz5+Pu+66C8HBwTh48CDmz5+P//73vwAaqgOCgoJQUFCArKws5ObmOnwMrJDyTB2hf5TEUX2kpFAhODjYISGAK8KQ1lRIedOUPb1eD6AheAwICLD79u6YstdWiYmJUCgUqKio8KrXioiIiIg8k90VUlu2bHHGOLyWUqnE4MGD8dtvv2HXrl3o1auXy+774MGDAIDU1FSX3ac9BEHAFVdcgX79+uHWW2+FwWCASqVCSUkJFAoF4uLi0LNnT+Tn52PdunUYOHCgQxvCSyfCrJDyLAyk7OfIUAFoCENKS0udGobYUyElBVKVlZVeU3kjPXf+/v6t+rvlqil7jmqGDzRUwHbr1g0nTpxAYWEhOnXq1OZ9EhEREVHHZXcgNXbsWGeMw6sNHz4cv/32G3JycvCXv/wFvr52P612M5vNOHz4MAD394+6nNOnT8NsNmPYsGE4e/asHEh06tQJgiAgPj4eeXl5KCwsRHJyssPu1/IklzxHR2hoLnFUIOXIUAFwTXWOPavshYWFQRAE1NfXo6qqyiumfrelf5Tl7WpqalBfXw8fHx+Hjc2SZXWdIyQlJcmB1IgRIxyyTyIiIiLqmOxOTn755ZcWrx8zZkyrB+OtevfujZCQEGi1WuTl5TmtUbel48ePQ6/XIyAgAAkJCU6/v7bQaDQwGAzo2rUrYmJiUFpaCpPJJFcwBQQE4PTp020+ab8Up+x5JlZI2c8ZFVKA8wKpuro61NTUALBtyp5CoUBoaCgqKytRXl7eIQKpgIAACIIAURSh0+mc9pil946jwsxevXph06ZNbGxORERERG1mdyB19dVXN7rMcnpFfX19mwbkjRQKBYYNG4bNmzdj165dLgmkpNX1UlNTHTrNzRlCQ0OhVqvlk67o6Gir6/V6PdRqtcNOmCSskPJMDKTs520VUtJ4/fz8oFarbbpNREQEKisrUVFR4fEhO9D2QMqyubwrAilH7b9nz54AGipfdTqdx/UvJCIiIiLvYXeSUVFRYfVTWlqK77//HsOGDcP//vc/Z4zRKwwfPhwAsG/fPtTW1jr9/qRAytOn6wENUzxSUlJQUlICURStrhNFESUlJUhNTZVXcHIUqTJDo9HAbDY7dN/Uegyk7OdtFVKWDc1t7QflbY3NpUCqLVNPXdFcXnrvOeq9ExwcLH+pUFRU5JB9EhEREVHHZHcgFRoaavUTGRmJ6667DitWrMATTzzhjDF6he7duyMqKgp1dXXYu3evU++ruroaxcXFADy3obklhUKBjIwMREZGIj8/H1qtFiaTCVqtFvn5+YiMjER6errDK71CQkKgUChgNpvlE3pyP/aQsp+zAilnNdRuTUWXFEh5yxTbtlZIAc4PBo1GIwwGAwDHvXcAyIt3cNoeEREREbWFwxKA6OhoHDlyxFG78zqCIMhVUrt27XLqfeXn50MURcTHx9vUn8UTpKWlITMzE0OGDEF5eTkKCwtRXl6OoUOHIjMzE2lpaQ6/T6kvDcBpe56kI1ZIVVdXw2QytXo/ju4D5KoKqfYcSEnPnSMCKWcFg9L7xtfXF/7+/g7br1TNykCKiIiIiNrC7h5S+/fvt/pdFEWcOXMG//znPzFo0CBHjcsrDR8+HBs3bkReXh6qqqqcdsJ98OBBAN5RHWUpLS0NAwcORGFhITQaDUJDQ5GUlOTUHljh4eHy9FJv6EvTEXSkQCooKEiu0quqqpJDF3s5etqVq3pI2ROYR0REAPCeQMoRFVLOnrJn+b6xdeqkLaRA6sSJEzAajVAqlQ7bNxERERF1HHYHUoMGDZJXBrJ0xRVX4N1333XYwLxRdHQ0unfvjuLiYuTk5DTZAL6tRFFEXl4eAO/oH3UphUKB5ORkl92fdELMCinPIIpihwqkBEFASEgIKisrodFoWhVI1dXVOXzalasCqdZUSHWkHlLOrpCSPmuObpgeGRmJ0NBQaDQanDhxQp7CR0RERERkD7sDqePHj1v9rlAo0LlzZ5tXUmrvhg8fjuLiYuzatcspgVRJSQm0Wi1UKpXDm4C3R942Dai9q62tlaeudYQeUkBDKCMFUq0hTbtSKpUO+zsrVebU1NSgvr4ePj4+DtmvxLKpua2kz6q0CIGnrx4qhUgBAQGt3oerKqQcvYKpIAhISkpCTk4OCgsLGUiRU3zx5ESnrT5JREREnsHuI/7u3btb/XTt2pVhlIWhQ4dCEAQUFRWhrKzM4fuXVtfr3bs3fH3tzhM7HFZIeRbpxFupVEKlUrl5NK7R1sbmlg3NHTXtKiAgQN6XM6pzWhNIWS5C0NYm8K7gyAopZwVSjm6Gb0n6QuTo0aMO3zcRERERdQx2B1Jz587F66+/3ujyVatWYd68eY4Yk1cLCwtD7969AQC7d+92+P6lQMobp+u5g3RCzAopz9CRputJ2hpIOaPKRaFQyJU9zghDWjNmhULhVZ9Xb2pq7oxASqqKKioqgtlsdvj+iYiIiKj9szuQ+uyzzzBq1KhGl1955ZX49NNPHTIob2e52t6lvbbawmAwyKsaMZCyjTQNiBVSnoGBlP2cFSo4qzrHYDDIPa/sDdG8ZYqt0WiE0WgE4NlNzZ0ZSHXp0gVqtRoGgwGnT592+P6JiIiIqP2zO5C6cOFCkycZISEhTpmi5o3S0tLg6+uL06dP488//3TYfo8cOQKz2YyoqCh07tzZYfttzywrLhwZDlLrMJCyn7cFUtLjVKlUdk/n9paV9qSKJoVC0aYp665qLu+MQEqhUKBHjx4AOG2PiIiIiFrH7kAqKSkJ33//faPLv/vuO/ngtKMLCAhA//79ATRUSTnKwYMHAbA6yh5SIGU0GlFTU+PewZB84t1RGpoDnjllD3DedDFpvPb0j5J4y0p7ltP12tLXS3oN9Hq9U6a9SWGmo987EmnanlS5S0RERERkD7u7Ys+fPx8PP/wwzp8/j3HjxgEANm/ejJdffhmvvvqqo8fntYYPH47c3Fzs2rULN910U5ubEYuiKPePSk1NdcQQOwSlUonAwEDodDpUVFS0aUUsajtWSNnPWyukWhOCeEuFlF6vB9C26XrAxRX6RFFETU1Nm/dnSRRFp07ZAy42Ni8sLIQoig5ruk9EREREHYPdgdTdd9+N2tpaPP/883juuecAAAkJCVi9ejXS09MdPkBv1b9/f6jValRUVDhkWezS0lJcuHABvr6+ctN0sk14eDh0Oh0qKyvRpUsXdw+nQ+vIgZRWq4XZbIZCYV9hqrOqXJwVSLVmhT2JdBtvqpBqC19fX7kPU3V1tUMDqdraWtTV1QFwXiCVkJAAHx8fVFZW4sKFC4iMjHTK/RARERFR+2T3lD0AeOCBB1BSUoJz585Bq9Xi2LFjDKMuoVQqMXjwYACOmbYnVUclJSVBpVK1eX8diTet3NXedcRAKiQkBIIgwGw2tyr88bYKqbYEUlKFlKcvQiBNc3REgOSsqZPS+0alUjnt3ww/Pz90794dAKftEREREZH97A6kjh8/Ljcw7dy5s3wwffToUZw4ccKhg/N20mp7OTk5MJlMbdqXFEixf5T9uNKe5+iIPaR8fHzkx2vvtD1RFJ3WmNoTp+xJn1WNRoP6+nqHjsuRpPDIEe9jZ6205+zpehLLaXtERERERPawO5CaM2cOfvvtt0aX79y5E3PmzHHEmNqN3r17IyQkBDqdDnl5ea3ej9FoxJEjRwAwkGoNVkh5jo5YIQW0vo9UTU2NHGY7OlhwVhAiBb+tCaSCg4Ph6+sLURQ9OkCWAilH9KRzVjDoykBKFEXs3LkTu3fvRkFBgVMatBMRERFR+2N3IJWbm4tRo0Y1uvyKK67A3r17HTGmdkOhUGDYsGEA2jZtr7CwEEajEWFhYYiLi3PU8DoMVkh5BlEUO3wgJYUEtpK29/f3h1KpdOiYnF0h1Zope4IgeEWA7MgKKWdP2XN2IFVdXY0dO3bgyy+/xGOPPYZHHnkE8+fPR25urlPvl4iIiIi8n92BlCAI8kmlJU+fYuEu0rS9vXv3ora2tlX7OHjwIICG6iiuYmQ/6QSXgZR71dXVwWg0Aui4gZS9FVLODBWcEUhZTjFsbRN2b1hpz1FNzS334UlTJ22Vm5uLl156CRqNBn5+fujcuTMiIiKQk5ODrKwshlJERERE1CK7A6kxY8Zg+fLlVuFTfX09li9fjtGjRzt0cO1B9+7dERUVBaPR2OoKMvaPahupQsqTT3A7AinIViqV8PPzc/NoXKu1gZQzQwUpkDIYDG3ucSepra2Vg/fWjtkbPq/e1NTcWeGv2WxGdnY2ysrK0LNnT/j5+UGn0yEkJAQpKSkoKyvDunXrOH2PiIiIiJrla+8NVqxYgTFjxqB379646qqrAAC//vortFotfvrpJ4cP0NsJgoDhw4dj48aN2LVrF0aMGGHX7SsqKnDmzBkIgoCUlBQnjbJ9kyqkdDodjEajw6c+kW0sG5p3tEo/T6yQCggIgCAIEEUROp3OIaGXVIXo7+/f6pXdpECqvLy8zeNxFkcGUs5uau6sCqnCwkLk5+cjPj4eNTU1OHv2rPz+FgQB8fHxyMvLQ2FhIZKTk50yBiIiIiLybnZXSKWmpmL//v2YOXMmSktLUVVVhfT0dBw+fBj9+vVzxhi9njRtLy8vr8npji2RqqMSExMd0kC3I/L395crcjy56qK966j9owDPrJASBEEOQxxVnSMFUq3pHyXpqBVS3tbUXKPRwGAwIDAwEKGhoejUqRM6d+4sXx8QEACDwWD3e56IiIiIOg67AykAiIuLw7Jly/Dtt9/i008/RWZmJhQKBVatWmXXfhISEiAIQqOfhx56CEDDVJKHHnoInTp1QlBQEGbMmIFz5861ZshuFR0dje7du8NsNiMnJ8eu23K6XtsJgsDG5h6AgZT9gZT0nDkrVHB0GOKIAM3Te0hJFWWAZzc1l14LZ713QkNDoVarodPpoFar0bdvX3Tp0kW+Xq/XQ61WO7WHFRERERF5t1YFUpY2b96M22+/HbGxsViyZIldt929ezfOnDkj//z4448AgFtvvRUA8Nhjj+Gbb77Bhg0bsHXrVpw+fRo333xzW4fsFlKVlD2r7dXX1yMvLw8AWH3WRt6wcld7x0CqISQQRdHm2zk7VHB0ICUFvm0JITx9yl5tba3cQ9FTp+xZrmjprPdOUlISUlJSUFJS0ug9LYoiSkpKkJqaiqSkJKfcPxERERF5v1YFUqdOnUJWVhYSExMxYcIEAMAXX3yBs2fP2rWfzp07IyYmRv7ZuHEjevbsibFjx0Kj0WDNmjVYuXIlxo0bhyFDhmDt2rX47bff8Pvvv7dm2G41dOhQCIKAoqIilJWV2XSb48ePy1MiunXr5uQRtm+skHI/yx5SHY0U0BiNRtTU1Nh8O2f3AXJWhZQjpuxVVVU5rNm6I0mVTL6+vg7pR2f5GtgTVrakpqZGfu6cFUgpFApkZGQgMjIS+fn50Gq1MJlM0Gq1yM/PR2RkJNLT06FQtPl7LyIiIiJqp2w+UjQajdiwYQMmTpyI3r17Y+/evXjxxRehUCjwzDPPYNKkSW06OK+rq8P777+Pu+++G4IgICcnB0ajEddee628TZ8+fdCtWzfs2LGj1ffjLmFhYejduzeAhsowW0jT9VJTU3lQ30askHK/jlwhpVQq4e/vD8C+aXvOrpBydHWOI6bsBQYGyv+WeGKAbDldzxHN+aXXwGw2yysUtpX0Ovj7+zt1EYe0tDRkZmZiyJAhKC8vR2FhIcrLyzF06FBkZmYiLS3NafdNRERERN7P5lX2unTpgj59+uCOO+7ARx99JH+LPWvWLIcM5Msvv0RlZSXmzJkDADh79iz8/PwafdMeHR3dYiWW5bLjwMUKA08wfPhwHD58GDt37sSkSZMuezLD/lGOI72PPPEEt6PoyIEU0BDS1NTUQKPRIDY29rLbm81mr+sh5Yim5lLPt9LSUpSXlyMyMtIhY3MURzY0BwA/Pz8olUoYjUZUV1dDrVa3eZ/Oft9YSktLw8CBA1FYWAiNRoPQ0FAkJSXxSxQiIiIiuiybjxhNJpPcdNzHx8fhA1mzZg0mT56MuLi4Nu1n+fLlCA0NlX+6du3qoBG2XVpaGnx9fXHmzBn8+eefLW5bVVWF4uJiAA0VUtQ2nLLnfgyk7GtsLk3hEgTBac+ZJwZSgGc3NpeeK0cFUoBnNpe3h0KhQHJyMoYNG4bk5GSGUURERERkE5uPGk+fPo377rsPH374IWJiYjBjxgx88cUXDpmyUFxcjE2bNuGee+6RL4uJiUFdXV2jAOHcuXOIiYlpdl9PPfUUNBqN/HPq1Kk2j89RAgIC0L9/fwCXb24uNTOPj4/nKkUOwCl77teRe0gB9gdSUnVnUFCQ007wHRmEiKLosCDEkxubO7pCCnD8SnvSe8cVFVJERERERK1l81mOWq3G7Nmz8dNPP+HAgQNISUnB3LlzYTKZ8Pzzz+PHH3+UVx6y19q1axEVFYWpU6fKlw0ZMgRKpRKbN2+WLzty5AhOnjyJkSNHNrsvlUqFkJAQqx9PYrnaXksNbKVAitP1HEM6wdVqtTCbzW4eTeuYzWYUFBRg9+7dKCgo8LrHwQop+wIpV1S5ODKQqqmpgdFoBOC4QMoTA2RnBFKO7uXFQIqIiIiIvIHNPaQs9ezZE//4xz+QlZWFH374AWvWrMG0adMQHBxs8wpyErPZjLVr1yIjIwO+vheHExoair/+9a+YP38+IiIiEBISgkceeQQjR47EFVdc0Zphe4T+/ftDrVajoqIChYWF6NWrV6NtRFGU+0f169fP1UNsl4KDg6FQKGA2m6HVats8pcjVcnNzkZ2djfz8fBgMBqjVaqSkpCAjI8MrGgfX1tairq4OAAMpeyuknBkqODKQkh5XQEBAmxtpd7RAytFT9hhIEREREZE3aNM8EIVCgcmTJ+PTTz9FSUkJnn76abv3sWnTJpw8eRJ33313o+teeeUVTJs2DTNmzMCYMWMQExODzz//vC1DdjulUonBgwcDaH7a3qlTp1BVVQWVSoUePXq4cnjtlkKhkAMBb+sjlZubi6ysLOTk5CAiIgK9evVCREQEcnJykJWVhdzcXHcP8bKkE21fX1+oVCo3j8Y9PDmQcsRUMUf1jwI8u4eU5Sp7juLoKXuu7iFFRERERNQaDmtM0rlzZ8yfP9/u202YMAGiKCI5ObnRdWq1Gm+++SbKy8uh0+nw+eeft9g/yltI0/ZycnJgMpkaXS9VR/Xp08eqaozaxpOrLppjNpuRnZ2NsrIypKSkICQkBD4+PggJCUFKSgrKysqwbt06j5++ZzldzxF957xRawMpV0zZMxgMTf4tsocjQxBP7iHljKbm0r7YQ4qIiIiIOhIuheMGvXv3RkhICHQ6ndwrypIUSLF/lGNJlRveVCFVWFiI/Px8xMfHw2QyYc+ePTh27BgAQBAExMfHIy8vD4WFhW4eacs6ekNzoPU9pJwZKvj7+8sN09s6XcyRFVJSIKXT6eSpnp5Cr9cDYA8pIiIiIqK2YiDlBgqFAsOGDQPQeNpeTU0NioqKADCQcjRvrJDSaDQwGAwIDAxEWVkZ9Ho9zp49KzfEDwgIgMFgsDnkcJeO3tAcuBhIGQwGm0IWV1RICYLgsDBECqQcMV5/f395aqenfV6dUSHl6NUOpc8bAykiIiIi8mQMpNxEmra3d+9e1NbWypcfPnwYZrMZUVFRiIyMdNfw2iVvrJAKDQ2FWq2GTqeTQyeTyQSDwQCgoVpDrVZ7fK8YBlINU5ClZt+2BIhSIOXs58xRYYj0mBxRISUIgscGyM5sau6IKXvV1dXyFN6O/HkjIiIiIs/HQMpNunfvjqioKBiNRuzdu1e+XJrCx+oox/PUE9yWJCUlISUlBadOnbIat06ngyiKKCkpQWpqKpKSktw4ystjINUQstgzbc9VjakdFYY4erye+HkVRVGesueMpuaOqJCSgsygoCD4+Pi0eX9ERERERM5id8fs+vp6vPfee9i8eTNKS0sbNVP+6aefHDa49kwQBAwfPhwbN27Erl27MGLECIiiKPeP6tevn5tH2P54Y4WUQqFARkYGDh8+jMLCQgQGBsLX1xelpaUoLS1FZGQk0tPT5T5Anoo9pBqEhoairKzssoGUyWSSgw9nT7tyVBjiyB5SgGeutKfX662myzqKI3tIsX8UtRc3rfgBvmrHfc6IiIiowQ+Lp7p7CDK7A6lHH30U7733HqZOnYp+/fp12BWzHEEKpPLy8lBVVQWdTocLFy7A19cXvXr1cvfw2h3LigtRFL3mvZuWloabbroJf/75JyorK6HX66FQKDBp0iSkp6cjLS3N3UO8LFZINbC1QkoKFXx8fBwafDTFEYGUKIpOq5DypJX2pCoylUrl0BVQpdfAaDSirq4Ofn5+rd4XAykiIiIi8hZ2H1F/9NFH+OSTTzBlyhRnjKdDiY6ORvfu3VFcXIycnBzU19cDAHr16iU39CXHkU6UjUYj9Hq9Q3vAOFt9fT1GjhyJmJgYHDhwAJGRkXj55Zc9vjJKwkCqgb2BVEhIiNODU0cEUnq9HiaTCYDjAilPrJCSAilHV/qpVCr4+Pigvr4eOp2uTYGUq6Z6EhERERG1ld1ns35+fh7fr8abDB8+HKIo4ttvv8V///tfVFZWIiUlxd3DapeUSqV8IulN0/bMZjMKCgogCAJuv/12REVFQaFQOKQBsqswkGpgayDlylDBEdPFpM9TUFCQwyqHPLlCytFVa45c7ZAVUkRERETkLew+c1iwYAFee+01rFq1ymumPHkyPz8/7NixA5WVlaivr4ePjw9CQkIQFRXlFVOxvE1YWBiqq6tRUVGBLl26uHs4Njl16hRqamqgVquRnJyMqKgolJaWoqSkxGvCS/aQatCaCilnc0RTcymQcmSA5olNzZ1VISXtU6vVtjloZiBFRERERN7C7kBq27Zt2LJlC7777jv07dtXXsZc8vnnnztscO1dbm4uXnnlFXmKhq+vLxQKBfLz85GVlYXMzEyGUg4WHh6OkpISr6qQOnz4MAAgOTkZCoUC8fHxKC0txalTp7wikDIajaitrQXACil7AylXVEg5Ysqe9Hgc1dAcuBhI1dTUwGAwQK1WO2zfrSU9R86Y7uuo5vIMpIiIiIjIW9g9ZS8sLAw33XQTxo4di8jISISGhlr9kG3MZjOys7NRVlaG/v37w8/PDwqFAjExMUhNTUVZWRnWrVvXaBVDahvphNmTqi4u58iRIwCAPn36AAC6du0KACgpKXHbmOwhTdfz8fHxiFDBnTy5QsoRgZQj/w1Qq9Xw9/cH4DmfV2nlQ2cEUo6assceUkRERETkLeyukFq7dq0zxtHhFBYWIj8/H/Hx8QgICEBhYSHMZjMiIiIgCALi4+ORl5eHwsJCJCcnu3u47YZUdeEtFVImkwlHjx4FAPTu3RvAxUDq1KlTbhuXPSz7R3X0ab5SSFBdXQ2TydRsvyUpVPCWQEr6PDmyQgpo+LzW1NSgoqICsbGxDt13a7iiQqqtU/bYr42IiIiIvEWrl+g6f/48tm3bhm3btuH8+fOOHFOHoNFoYDAYEBgYCF9fX/Ts2RPR0dHyylIBAQEwGAyXraQg+3hbhdSJEydQV1eHoKAgueeVFEidPXsWRqPRncOzCU+QLwoKCpJXRpSel6a4skJKCldqa2tb/X5yVlWOp620J4VFnjplr76+Xr49K6SIiIiIyNPZHUjpdDrcfffdiI2NxZgxYzBmzBjExcXhr3/9qzydgS4vNDQUarVaPsGJjY1F79695ZNVvV4PtVrNkwoHkwIpb6mQkvpH9e7dW64uCg0NRVBQEMxmM06fPu3O4dmEDc0vEgRBDplaCptdOe3K399f/rvT2uocZ1ZIAZ6z0p4zm5pLIVdbKqSqqqogiiIUCoVTQjMiIiIiIkeyO5CaP38+tm7dim+++QaVlZWorKzEV199ha1bt2LBggXOGGO7lJSUhJSUFJSUlEAURavrRFFESUkJUlNTkZSU5KYRtk/eNmXv0v5RQEOo4U3T9lghZe1yfaREUXRphZQgCG2uznHGKnuA562058wKKUf0kJI+a5aVeEREREREnsruI9bPPvsMa9asweTJkxESEoKQkBBMmTIF77zzDj799FNnjLFdUigUyMjIQGRkJPLz86HVamEymaDVapGfn4/IyEikp6fzpMLBpAoOnU7n8dPd6urqcOzYMQAX+0dJGEh5r8sFUrW1tairqwPgupXS2hJIWQZozqqQ8pRAytNX2WNDcyIiIiLyJnanHXq9HtHR0Y0uj4qK4pQ9O6WlpSEzMxNDhgxBeXk5CgsLUV5ejqFDhyIzMxNpaWnuHmK74+/vD5VKBcBzTnKbU1RUBJPJhLCwMERFRVldx0DKe10ukJLCHZVKJb9Xna0tYUh1dTXq6+sBOD5A64g9pNoyZc+VlXVERERERG1l9yp7I0eOxJIlS7Bu3Tp5CfeamhosXboUI0eOdPgA27u0tDQMHDgQhYWF0Gg0CA0NRVJSEiujnEQQBISFheHcuXOorKxsFPR4EsvpepeuTicFUtKUT09evY49pKxdLpByR5VLW6aLSeMNDg6Gj4+PQ8dl2UPK3e/z+vp6GAwGAJ47ZY+BFBERERF5E7sDqddeew0TJ05EfHw8Bg4cCADYt28f1Go1fvjhB4cPsCNQKBRITk529zA6jPDwcJw7d85jqi6aY9nQ/FLR0dFQKpWora3F+fPnPTpYY4WUtcsFUtLz5cpQoS0VUs5qaA5cDKRqa2tRU1ODgIAAh9+HraQKYEEQnDIO6TUwGAwwmUzw9bX7n2cGUkRERETkVew+4u3Xrx+OHj2K9evXyyfMs2bNwuzZs+Hv7+/wARI5mjestFdTU4MTJ04AaDqQUigU6NKlC06cOIFTp04xkPIitlZIeUsg5cyKLj8/PwQGBkKn06GiosKtgZT03FiuSuhIAQEBEAQBoihCr9e36vVnDykiIiIi8ib2fwWLhgPne++919FjIXIJT2uU3JSjR49CFEV07twZnTp1anKbrl27yoHUkCFDXDxC2zGQsmZrDylXhgqOqJBy1njDw8PlQKpLly5OuQ9bOLN/FHCx8kqn06G6urpVgRQrpIiIiIjIm9gUSH399deYPHkylEolvv766xa3nT59ukMGRuQs3lAhZdk/qjnx8fEAPLuxudFoRG1tLQD2kJJIwY1Wq22yL5K3VUg5c8oe0NDYvKSkxO0BsrMDKaDhdZACqdZgIEVERERE3sSmQOrGG2/E2bNnERUVhRtvvLHZ7QRBkFdbIvJU0omzu09wW9JS/yiJZWNzTyWdWPv4+HBK7/8JCQmBIAgwm82orq5uVDnmjlChLSu8SQGaswIpy8bm7uSqQOrcuXOtXmmPgRQREREReRObGmGYzWa5R43ZbG72h2EUeQPpBNdTK6Sqq6vlkKmlQKpLly4QBAGVlZXytDhPI40rKCjIo1cCdCUfHx85AGpq2p47AylP6yEFeM4UWykkcmalX1tW2jMajXLjdQZSREREROQN7O7Mum7dOnkKjqW6ujqsW7fOIYMiciapkkOj0cBsNrt3ME0oKCgAAMTFxbV4YqlWq9G5c2cAnlslxf5RTWupj5Q7GlN7+pQ9wHMCKWdXSAGtex2kz5qPj49bm78TEREREdnK7kDqrrvuavIkqqqqCnfddZdDBkXkTMHBwVAoFBBFUa5G8SS2TNeTSNP2PLWPFAOppjUXSFm+J91RIVVXV4e6ujqbb2c2m53ehN1TpuxJIZErAqnWTNmzfN+wGpGIiIiIvIHdgVRTTXiBhgoNLjVN3kChUMjvVXdXXTRFCqRaamgu8fRASjqJZ0Nza80FUjqdTq7ac2WIp1Kp4OPjI4/BVtXV1TCbzRAEwWkBmuWUPVEUnXIftnBFhVRbpuy5oxk+EREREVFb2NTUHADS0tIgCAIEQcD48ePh63vxpvX19Th+/DgmTZrklEESOVp4eDgqKio8ro9UZWUlzp07B0EQkJycfNntPT2QYoVU05oLpKQql8DAQKu/sc4mCAICAwOh1WpRXV0th0CXI31+pKpDZ5DGIvVIcmYg1BJX9JByRIUUvxgiIiIiIm9h8xmPtLre3r17MXHiRKuDcj8/PyQkJGDGjBkOHyCRM3jqSntHjhwBAHTr1s2mPjBSIHX27FkYjUYolUqnjs9eDKSadrlAyh2hQlBQkBxI2crZK+wBgK+vL4KDg1FVVYXy8nK3B1LO7M/UlgoprrBHRERERN7G5kBqyZIlAICEhAT85S9/gVqtdtqgiJzNU1fas6d/FNBw8imdrP/5559ISEhw4ujsx0Cqac0FUu6cdtWahtrObmguiYiIQFVVFSoqKuQQ1tVcWSHFQIqIiIiIOgK751hkZGQwjCKv54kVUqIo2tU/CmiYauXJ0/bYQ6ppnlohBdgXhrhqRUDp8+rOxube1NSciIiIiMgb2B1I1dfX46WXXsLw4cMRExODiIgIqx8ib+CJFVIXLlxAeXk5FAoFkpKSbL6dFEiVlJQ4a2itxgqpplkGUpaNut0ZKnh6hZTl/bma0WiE0WgE4Jqm5nq9Xm5ubytXhYNERERERI5idyC1dOlSrFy5En/5y1+g0Wgwf/583HzzzVAoFHj22WedMEQix5NOoD0pkJKqoxITE6FSqWy+nSdXSDGQapoUGhiNRtTU1MiXe8KUPXuqc1wVgkgBsrsqpKTnRKFQOLVCWAqkRFGEXq+367ZSmMnPGhERERF5C7sDqfXr1+Odd97BggUL4Ovri1mzZuH//b//h8zMTPz+++/OGCORw3nKUvKWpEAqJSXFrtvFx8cDaKiQsreqwplMJhMMBgMAniRfSqlUwt/fH4D1tD1vrZBydiAlVUi5a4qt5XQ9QRCcdj8+Pj7y+8LeaXtcZY+IiIiIvI3dgdTZs2fRv39/AA0nMNLJ1LRp0/Dtt986dnRETmJZoWJvJYIziKIor7Bna0NzSXR0NJRKJWpra3H+/HlnDK9VpOoohUIhn2TTRU31kXLntKu29JBy9pQ9d1dISX8jXLHCX2tW2qutrUVtbS0A9pAiIiIiIu9hdyAVHx+PM2fOAAB69uyJ//3vfwCA3bt32zXNiMidlEqlfALuCY3Nz549C61WC6VSiR49eth1W4VCgS5dugDwrGl7lg3NnVlV4q2aCqS8qULKbDbL43VVIFVZWemWikZXNDSXtCYYlF4HpVLJf4eJiIiIyGvYHUjddNNN2Lx5MwDgkUceweLFi9GrVy+kp6fj7rvvdvgAiZzFkxqbS9P1kpKS4Ovra/ftPbGxOftHtUwKnaRAqr6+Xg4hvCGQ0mq1EEURCoXC6asohoWFQRAEmEwm+X3lStL0OVcGUvZM2bOcrsfwl4iIiIi8hd1nvv/85z/l///LX/6Cbt26YceOHejVqxeuv/56hw6OyJnCwsJw6tQpj6iQau10PYknNjZnINWySyukLKc4OjvgaYq9U8UsG7ArFHZ/t2EXHx8fhISEQKPRoKKiwuWBnRQOueJ1ac2UPXdW1hERERERtZb9pRiXGDlyJEaOHOmIsRC5lKdUSJnNZjmQ6tOnT6v2wUDK+1waSFmGCu6ocpHCFqPRiLq6Ovj5+bW4vfS5cfZ0PUl4eLgcSHXv3t0l9ymRAqmAgACn31dbenkxkCIiIiIib2JTIPX111/bvMPp06e3ejBEriSdSLu7QqqkpAR6vR5qtbrVJ9pdunSBIAjQaDTQarUecWJq2UOKGmspkHIHlUoFX19fmEwmVFdXyyvbNcfVDdgjIiJw4sQJt3xeXVkh1Zope1L46wmfeyIiIiIiW9kUSN14441WvwuC0KixrPSNfn19vV0D+PPPP/Hkk0/iu+++g16vR1JSEtauXYuhQ4cCAObMmYPs7Gyr20ycOBHff/+9XfdDdClPqZCS+kclJye3euqTSqVCVFQUzp07h5KSEqSmpjpyiK3CCqmWXRpIubvKRRAEBAUFobKy0iMDKXeutOfKpubSfdgTSLlzdUYiIiIiotay6ezXbDbLP//73/8waNAgfPfdd6isrERlZSW+++47DB482O6QqKKiAqNGjYJSqcR3332HvLw8vPzyy/KJh2TSpEk4c+aM/PPhhx/adT9ETZEqpNwdSLW1f5TE06btMZBqWXMVUu4MFezpX+SOKXuAeyoa3dHUnD2kiIiIiKi9s7uH1Lx58/D2229j9OjR8mUTJ05EQEAA7rvvPuTn59u8rxUrVqBr165Yu3atfFliYmKj7VQqFWJiYuwdKlGLPGHKXn19PY4ePQqg9f2jJF27dsWePXsYSHkJKXgyGAyoq6tze4UUYN90MQZSzsGm5kRERETUUdg9P6ioqKjJE5DQ0FCcOHHCrn19/fXXGDp0KG699VZERUUhLS0N77zzTqPtfv75Z0RFRaF379544IEHcOHCBXuHTdSIdIKr1+tRV1fnljGcOHECtbW1CAwMRJcuXdq0L6lCqqSkxBFDazP2kGqZv78/lEolAMi9vwDPCKRsCUPc0UMKaP+BVGt6SHnCe4eIiIiIyF52B1LDhg3D/Pnzce7cOfmyc+fO4fHHH8fw4cPt2texY8ewevVq9OrVCz/88AMeeOABzJ0716pn1KRJk7Bu3Tps3rwZK1aswNatWzF58uRme1XV1tZCq9Va/RA1Ra1WQ6VSAXDftD3L6XptXVlNCqTOnj3rtoDNEiukWiYIgtW0PU8IFewJpNxZIWU2m11ynwAgiqJbmppXV1c36tXYFFEUPaK6joiIiIjIXnZP2Xv33Xdx0003oVu3blY9a3r16oUvv/zSrn2ZzWYMHToUy5YtAwCkpaXh4MGDePvtt5GRkQEAuO222+Tt+/fvjwEDBqBnz574+eefMX78+Eb7XL58OZYuXWrvw6IOSBAEhIWF4dy5c6isrERUVJTLxyA1NG/rdD2g4WQ0JCQEWq0Wp0+fRkJCQpv32Vomkwk1NTUAGEi1JDQ0FGVlZdBoNB7RmNrWQKq+vl4OHF013tDQUCgUCpjNZmi1WpcFYbW1tfIXIK6csmc2m2EwGODv79/i9gaDASaTCQADKSIiIiLyLnZXSCUlJWH//v345ptvMHfuXMydOxcbN27EgQMHkJSUZNe+YmNjG60GlpKSgpMnTzZ7mx49eiAyMhKFhYVNXv/UU0/JJ3cajcZj+umQZ3JnXxqj0YiioiIAjgmkAM9pbC4FGgqFAgEBAW4diyeTwhzLak53hgq29i+SxqpQKFw2JVOhUMjPlys/r1J1lK+vrzzF0pmUSiX8/Pys7rsl0muhVqvl2xEREREReQO7K6SAhsqSCRMmYMKECW2681GjRslTliQFBQXo3r17s7cpKSnBhQsXEBsb2+T1KpVKnoZFdDnuXGmvqKgIJpMJYWFhDqvOio+Px6FDh1oMdV1Bqp4JCgpq81TE9kwKWM6fPw+DwWB1mTvYWiFlWc3lytc3PDwcFRUVqKioaHIBDGewnK7nqscaFBSE8vJyVFdXIzIyssVtOV2PiIiIiLyVTYHU66+/jvvuuw9qtRqvv/56i9vOnTvX5jt/7LHHcOWVV2LZsmWYOXMmdu3ahX//+9/497//DaDhpGjp0qWYMWMGYmJiUFRUhCeeeAJJSUmYOHGizfdD1Bx3Vkg5sn+UxFMam7OhuW2k8EmqaFMqlW4N1G0NpFzdP0oSERGBY8eOuaVCypWVfoGBgXIgdTlShZQ7g0wiIiIiotawKZB65ZVXMHv2bKjVarzyyivNbicIgl2B1LBhw/DFF1/gqaeeQlZWFhITE/Hqq69i9uzZAAAfHx/s378f2dnZqKysRFxcHCZMmIDnnnuOVVDkEO6skHJk/yiJZSBlNpuhUNg9K9ch2NDcNpcGUq6uOLqUpwdSUoBcXl7usvt0ZUNziT0r7XnCVE8iIiIiotawKZA6fvx4k//vCNOmTcO0adOavM7f3x8//PCDQ++PyJK7KqQMBgNOnDgBoKFCylGioqKgVCpRV1eH8+fPIzo62mH7tgcDKdtIgZTUAN7docKlK7w1F465qwG7Oz6vUjjniobmEntWO2QgRURERETeyj3lE0Qewl0VUoWFhTCbzYiMjESnTp0ctl+FQoH4+HgA7m1szkDKNpcGOu6ediUFISaTCXV1dc1u584pe4B7mpq7MpCytbk8wECKiIiIiLyXTRVS8+fPt3mHK1eubPVgiFxNqrjQaDQuneKWn58PwLHT9SRdu3bF8ePHcerUKQwdOtTh+7cFe0jZ5tIAyt0Bnp+fH3x9fWEymVBdXd3s1Gh3V0i5Y8qep1ZIueu1ICIiIiJqK5sCqdzcXJt2xtW0yNsEBwdDoVDAbDZDo9HIJ7zOJjU0d1YgBbBCyhsEBQXJ7z/A/aGCIAgICgpCZWUlqqurm63ec3cg5coAmT2kiIiIiIicw6ZAasuWLc4eB5FbCIKAsLAwlJeXo7Ky0iWBlE6nk8MiR/aPkjCQ8h6CICAkJESeAucJoYJlINUcd03ZCwkJgY+PD+rr610WILujh5R0XwykiIiIiKg9Yw8p6vCkk2pX9aWRqqNiY2OdchLZpUsXCIIArVYrn6y6GgMp21lWGbm7Qgq4/HQxaTof4PpASgqQAddN29Pr9QA8c8qeKIoMpIiIiIjIa9lUIXWpPXv24JNPPsHJkycbNb79/PPPHTIwIleRqixc1djcmdP1gIY+QNHR0Th79ixOnTqFvn37OuV+WsIeUrYLDg5GZWUl6urqUFZW5tJeZk25XBgiTdfz9fVFQECAy8YliYiIwIULF1wWILuzQupygZROp5OnezL8JSIiIiJvY/dZz0cffYQrr7wS+fn5+OKLL2A0GnHo0CH89NNPHvHtPpG9XF0hdfjwYQDOma4nkabtlZSUOO0+mlNfXy9XlfAkuWW5ubn49ttv8dtvv+H333/H888/j/nz59vct88ZLte/yLJ/lDv6Brq6sbk7m5rrdDqIotjsdlJ1VGBgIHx9W/X9EhERERGR29gdSC1btgyvvPIKvvnmG/j5+eG1117D4cOHMXPmTHTr1s0ZYyRyKldWSFVWVuLs2bMQBAHJyclOux939pGSqjoEQXDpSby3yc3NRVZWFk6ePAk/Pz+EhISgc+fOyMnJQVZWlttCqctVSEmfE3d9ASF9Xl0RIIuiKIer7mhqbjQaG1UhW+J0PSIiIiLyZnYHUkVFRZg6dSqAhqlBOp0OgiDgsccew7///W+HD5DI2VxZISVN1+vatatTw5r4+HgA7gmkpP5RQUFBXHmzGWazGdnZ2SgrK0PPnj3h5+cHPz8/hIWFISUlBWVlZVi3bp08HcuVbJ2y5+r+URJXBlJ6vV6uUHLl9EQ/Pz+54qmlxubuWu2QiIiIiMgR7A6kwsPD5RPOLl264ODBgwAavjWXvkkm8ibSibUrKqSc3T9KIlVInTt3DrW1tU69r0uxofnlFRYWIj8/H/Hx8VCpVAAaQgigobIsPj4eeXl5KCwsdPnYbA2k3BWCREREAHBNICWFQSqVyqVT4iyrC1sKpPhZIwBISEjAq6++2uI2giDgyy+/dNh9Onp/RERE1DHZHUiNGTMGP/74IwDg1ltvxaOPPop7770Xs2bNwvjx4x0+QCJns5yy11K/FkdwRf8ooGEKT0hICERRxOnTp516X5diQ/PL02g0MBgMCAwMRFhYGDp16iSHiEBDNY7BYJDDH1e6XBAiBbfurpByRQ8p6Tlwx3vZlpX23B0OEhERERG1hc1f+R48eBD9+vXDqlWrYDAYAAB///vfoVQq8dtvv2HGjBl45plnnDZQImeRTqyNRiP0er3TptKVlZXhwoULUCgUSEpKcsp9WOratSsOHTqEU6dOITEx0en3J2HVxuWFhoZCrVZDp9MhJCSk0UqIer0earXaLUGDrT2k3B1IVVVVwWQyObVySQqk3LGaoC0r7bGHFBERERF5M5srpAYMGIARI0bgs88+k080FQoFFi1ahK+//hovv/yyfKJA5E18fX3l97QzpwFJ0/USExOhVquddj8SdzU2ZyB1eUlJSUhJSUFJSUmjqjxRFFFSUoLU1FSXBJeXsgykmqoYdHdVTlBQEHx9fSGKotOn2XpChVRLU/YYSNnu6quvxty5c/HEE08gIiICMTExePbZZ226bWVlJe6//35ER0dDrVajX79+2Lhxo3z9Z599hr59+0KlUiEhIQEvv/yy1e0TEhKwbNky3H333QgODka3bt2sem5eeeWVePLJJ61uc/78eSiVSvzyyy82jbGqqgqzZs1CYGAgunTpgjfffLPF7Q8cOIBx48bB398fnTp1wn333dco/Hz33XflxxUbG4uHH3642f0tWbIEsbGx2L9/PwDgrbfeQq9evaBWqxEdHY1bbrnFpsdBREREHYvNgdTWrVvRt29fLFiwALGxscjIyMCvv/7qzLERuYwr+ki5arqehIGU51IoFMjIyEBkZCTy8/Oh1WphMpmg1WqRn5+PyMhIpKenQ6Gwe1Z1m0lBiMlkarL/mLtX2RMEwWWNzaUTdHesFmnLlD0GUvbJzs5GYGAgdu7ciRdeeAFZWVlyC4LmmM1mTJ48Gdu3b8f777+PvLw8/POf/4SPjw8AICcnBzNnzsRtt92GAwcO4Nlnn8XixYvx3nvvWe3n5ZdfxtChQ5Gbm4sHH3wQDzzwgPwlxezZs/HRRx9ZBcAff/wx4uLicNVVV9n02F588UUMHDgQubm5WLRoER599NFmH5tOp8PEiRMRHh6O3bt3Y8OGDdi0aZNV4LR69Wo89NBDuO+++3DgwAF8/fXXTQbkoijikUcewbp16/Drr79iwIAB2LNnD+bOnYusrCwcOXIE33//PcaMGdPs2Gtra6HVaq1+iIiIqGOwea7DVVddhauuugpvvPEGPvnkE7z33nsYO3YskpKS8Ne//hUZGRmIiYlx5liJnCY8PBynTp1y2gmuKIpyIOXshuYSKZAqKSmB2Wx2WbjBHlK2SUtLQ2ZmJrKzs5Gfn4/Tp09DrVZj6NChSE9PR1pamlvG5efnB6VSCaPRiOrqaqtqPmlaK+C+KXtAw+f1/PnzTg+kpMfqjkDKlil77q5W8zYDBgzAkiVLAAC9evXCqlWrsHnzZlx33XXN3mbTpk3YtWsX8vPzkZycDADo0aOHfP3KlSsxfvx4LF68GACQnJyMvLw8vPjii5gzZ4683ZQpU/Dggw8CAJ588km88sor2LJlC3r37o2ZM2di3rx52LZtmxxAffDBB5g1a5bNK5WOGjUKixYtksewfft2vPLKK00+tg8++AAGgwHr1q2T32erVq3C9ddfjxUrViA6Ohr/+Mc/sGDBAjz66KPy7YYNG2a1H5PJhDvuuAO5ubnYtm0bunTpAgA4efIkAgMDMW3aNAQHB6N79+4t/j1bvnw5li5datPjJCIiovbF7jPUwMBA3HXXXdi6dSsKCgpw66234s0330S3bt0wffp0Z4yRyOmcXSF19uxZaLVa+Pr6Wp3MOFPnzp3h5+cHo9GI0tJSl9wnwAope6SlpWHlypV444038NJLL+GNN97Ayy+/7LYwStLcdDEpAFEqlfD393f5uCSuWmnPEyqkmpuyZzab5fGxQso2AwYMsPo9Njb2sn8b9+7di/j4eDmMulR+fj5GjRplddmoUaNw9OhR1NfXN3nfgiAgJiZGvu/OnTtjwoQJWL9+PQDg+PHj2LFjB2bPnm3zYxs5cmSj3/Pz85sd88CBA63e16NGjYLZbMaRI0dQWlqK06dPX3ahmsceeww7d+7EL7/8IodRAHDdddehe/fu6NGjB+68806sX7++xVWYn3rqKWg0GvnH1VW9RERE5D5tKplISkrC008/jWeeeQbBwcH49ttvHTUuIpdy9hQgaWpGUlISlEqlU+7jUgqFAvHx8QBcO22PgZR9FAoFkpOTMWzYMCQnJ7tlmt6lmpsuZlmRY2vlhjO4aqU9KQzyxCl7Uo8vQRBYjWijS//2CoIAs9nc4m0cFbxe7r5nz56NTz/9FEajER988AH69++P/v37O+S+7WXrY77uuuvw559/4ocffrC6PDg4GH/88Qc+/PBDxMbGIjMzEwMHDmz2Cx+VSiWvDCv9EBERUcfQ6jOfX375BXPmzEFMTAwef/xx3Hzzzdi+fbsjx0bkMs6ukHJ1/yiJO/pIMZDyfs2FIe5eYU/iqgopdzY1l0Kw5iqkpHAwODjYI0LM9mrAgAEoKSlBQUFBk9enpKQ0OvbZvn07kpOT5T5TtrjhhhtgMBjw/fff44MPPrCrOgoAfv/990a/p6SkNDvmffv2Wb23tm/fDoVCgd69eyM4OBgJCQnYvHlzi/c5ffp0fPDBB7jnnnvw/9u787CmzvRv4N8EQkJYAopsAopGNLggClJ0lC4qrpXW1rbjCHY61XasnY5tZ+o7FRVt6zja6c+uU20F207V1mptp+6KrYq1IrYuEQ3FBREQUbYYtjzvH07OiCtrEsL3c125lJOTkztPcuCcO/dzn9WrV9e7z9nZGcOHD8fixYvxyy+/4PTp09i5c2ejXhMRERE5vkZdLzs/Px+pqalITU2FwWDA4MGDsWzZMkyaNMkm3yATtRTLCXZrnOAKIaQKKWv1j7K4vo+UNdTV1UlTM1i10XbZe0LK8vzWqpBSq9Wt+jy3crceUmxobh1xcXEYNmwYJk6ciDfffBNarRYnTpyATCbDqFGj8OKLLyI6OhoLFizAY489hoyMDLzzzjt47733GvU8bm5uSEhIwJw5c6DX6/HEE0806vF79+7F4sWLkZCQgG3btuGLL764bdX65MmTMXfuXCQlJWHevHm4ePEiZs6ciSlTpsDPzw8AMG/ePDzzzDPw9fXF6NGjUV5ejr1792LmzJn1tvXQQw/hk08+wZQpU+Ds7IxHHnkE3377LX799VcMGzYM3t7e+O6772A2m63+hQwRERHZvwYnpEaPHo3t27dLV3/6/e9/z4MLchiWKUCtUSGVl5cHo9EIpVKJLl26tPj278TaFVKWE3iZTMYkdRvWkCl7tmSpkGrNq2ICtq2QutuUPSakrGfdunV46aWX8MQTT6CyshJarRaLFi0CAAwYMABr165FcnIyFixYgICAAKSkpNRraN5QkydPxpgxYzBs2DCEhIQ06rEvvvgiDh48iPnz58PT0xNvvvkm4uPjb7muWq3Gli1b8Kc//QnR0dFQq9VSws0iKSkJJpMJ//znP/HSSy/Bx8cHjzzyyC2398gjj8BsNmPKlCmQy+Xw9fXFV199hXnz5sFkMqFHjx74/PPP0bt370a9JiIiInJ8DU5IKRQKfPnllxg3blyjytCJ2gJLxYXRaER1dTVcXFxabNuW6Xo9evSw+r4TGBgImUwmXUq7tU9eLdP13NzcOI2oDbtddY69JKQsCeTy8nLU1NS0Wl82e2hqXlVVhdraWjg71/9zzYRU46Snp9+0bMOGDQ16bIcOHfDxxx/f9v6JEydi4sSJt73/9OnTNy07fPjwTctGjx4NIUSDYrrb9m9043b79u171yl006dPx/Tp0xu0vUmTJmHSpEnSz7cabyIiIqIbNfiMcePGjZgwYQKTUeSQVCoVlEolgJarujCbzTh58iS2bNmCK1eu3PYqTa3JxcUF/v7+AKxTJcX+UY7B3qfsqdVqKWncWn2k6urqYDKZANgmIeXq6io1jr9VHykmpIiIiIiorWMJAxGuTTFryT5SWVlZmDVrFp577jl8/vnn2LdvH9auXYusrKxmb7uxrHmlPSakHIO9T9mTyWStfmVMSy80mUxmkx5S118971bT9uzlvWjrPvvsM7i7u9/yZg9TzH744Yfbxsc+fURERNTWNaqpOZEj8/b2RmFhYbMrpLKyspCSkoLi4mJ4eXlJJw3Z2dlISUlBcnIyIiMjWyDihgkODsZPP/1klYSU5cSZJ0ptm71XSAH/219bKyFlee2urq42m37q5uaG8vJyVki1ogcffBAxMTG3vK+1poI2RlRU1C2n9xERERE5AiakiP6rJSqkzGYz0tLSUFxcDJ1Oh3PnzkEul8PHxwc6nQ56vR6rVq1CRESE1U5yrdnYnBVSjuFWCamqqipcvXoVgH0kpCyNzVvrSnuWJJAtm/Pf6Up7TEi1DA8PD7v+feXq6gqtVmvrMIiIiIhaBafsEf1XS1xpz2AwQK/XIygoCEajERcvXgRw7QReJpMhKCgIx48fh8FgaImQG8QyZa+oqAhVVVWt+lxMSDkGS0KqsrJSal5smSKmVCqlfmu21NpT9uwhIXWnKXtMSBERERFRW8eEFNF/tUSF1KVLl1BUVASDwYDMzExUVlZCLpdL1RxqtRomk0k6ubcGT09PaDQaCCFw/vz5Vn0uJqQcgyUJU1dXJyUxr+9ZZGm2bUvtKSF145S92tpaaRl7SBERERFRW8Upe0T/1ZwKqeLiYnz//ff49ttvUVxcDBcXFyiVSvj4+CAoKAgqlQrAtUbJKpXK6ieRwcHBKC0txblz59CtW7dWex72kHIMLi4ucHFxQXV1NSoqKqBSqeyuibYlydvaCSlbfpZvN2XPkviVy+U2abhORERERNQSmJAi+i9LhVRDE1JmsxlHjx7F7t27cezYMQgh4OzsDD8/P1y9ehXR0dH1pjYJIZCXl4eoqCir9wQJDg7G0aNHW72PFCukHIe7uztKSkpQUVEBHx8fu2poDlxLjF25cgVlZWU4efIktFpti/Zls6cKqRsTUtdP17OHajUiIiIioqZgQorovywnuBcvXsSJEycQFhZ2yxPc8vJy7NmzBz/88AMuXbokLQ8PD0dcXBzq6uqwcOFC5OTkICgoCGq1GkajEXl5efDx8UFiYqLVr9pl6SPFhBQ11PUJKQB2VSGVlZWFjz76CPv27UNtbS1mzJiB3r17IykpqcWuYGl53faQkLpxyp49vRdERERERE3FhBQRrp3gpqWlSSe4f/zjH9GvXz/pBFcIAYPBgN27d+PQoUOoq6sDcK0n1JAhQzBs2DD4+vpK20tOTkZaWhr0ej3y8/OhUqkQFRWFxMTEFjthboyQkBAAwPnz52E2m1slIWY2m2E0GgFwyp4juHG6mL1USGVlZSElJQXFxcXSdDU3NzdkZmbizJkzSE5ObpF9zB4qpCzPfWNCiolfIiIiInIETEhRu3f9Ca6Hhwfq6uqkE9xff/0VDz74IM6fP4/8/HzpMaGhoYiLi0NUVBQUCsVN24yMjERERAQMBgNKS0uh0WhafEpRY3Tq1AlKpRJVVVUoLCxEQEBAiz9HRUUFhBCQyWRMSDmAG6eL2UNCymw2Iy0tDcXFxdDpdDAajTAajXBxcYFOp4Ner8eqVasQERHR7H3NHhJSt5uyxwopIiIiInIETEhRu3bjCe7PP/+MsrIy1NbWQqFQ4ODBgzh9+jTuueceuLi4ICYmBnFxcVLF0Z3I5XKEhYVZ4VXcnUwmQ1BQEHJycpCXl9dqCSngWtWYrRJv1HJuTIbYQxLEYDBAr9cjKCgIMpkMKpUKRqMR1dXV0mf8+PHjMBgMzd737CEhdbum5tf3kCIiIiIiaquYkKJ27cYTXEsT8tOnTwMAXF1dUVlZiSFDhuDRRx9t01e0Cg4ORk5ODs6dO4fo6OgW3z6nETkWe0xIlZaWwmQySYkaV1dXAEBJSQn8/PygVquRn58vxdoc9nCVPctzX716td5UWyakiIiIiMgRsIyB2rUbT3At/8pkMnTq1AmRkZHo3LkzwsPD23QyCmj9xuZMSDmW6xNSJpMJJpMJgG0TUhqNBiqVSkoW+fv7AwCKi4tx9epVGI1GqFSqFonRHpqaW55bCFGvjxQTUkRERETkCJiQonbtxhPczp07o3fv3hg0aBB0Oh0UCgVcXV0doldLcHAwgGsJKSFEi2+fCSnHcv0V3iwVRyqVCiqVymYxabVa6HQ65OXlQQgBNzc3dOzYEUIInDt3Dnl5eQgPD4dWq23W89TU1KCmpgaAbRNScrlcSoRfn5Cyh2o1IiIiIqLmYkKK2rUbT3CdnJzQsWNHKJVKCCFa7ATXHnTu3BkymQzl5eVShUVLslSUsKG5Y7i+QspeEiByuRxJSUnw8fGBXq9HWVkZAgICUF1djRMnTsDLywuJiYkt1tBcLpfbNAEH1E8MWrBCioiIiIgcARNS1K7d6gS3trYWZWVl0Ov18PHxaZETXHugUCikKU4tPW3PbDbj5MmTKCoqQllZGcxmc4tun6zv+oSUPVxhzyIyMhLJyckYOHAgSkpKUFhYCCcnJ3Tq1An33XcfIiMjm/0c10/Xk8lkzd5ec9zY2Ly6ulqaPsmEFBERERG1ZWxqTu2e5QQ3LS0Ner0e+fn5UKlUiIqKQmJiYouc4NqL4OBgXLhwAefOnUOfPn1aZJtZWVlIS0vD1q1bcfnyZeTl5SE7OxtJSUkONXbtjb0mpIBr+2xERAQMBgNKS0tx/vx5fPfddzh37hxMJlOzq5qMRiMA207Xs7gxIWWpjlIoFDav3iIiIiIiag4mpIhw8wmuRqOBVqt1iMqo6wUHB+PAgQMtViGVlZWFlJQUFBcXw8XFBZ6enujQoQMyMzNx5swZJCcnMynVRlkSIWazGQUFBQBsP2XvenK5HGFhYQCAgQMH4tChQygsLMSePXswfPjwZm3bHhqaW9x4tcPrp+vZunqLiIiIiKg5bH62ff78efzud79Dx44d4erqir59++LgwYPS/UIIJCcnIyAgAK6urhg+fDhOnTplw4jJUVlOcKOjoxEWFuZwySigfmPz5jKbzUhLS0NxcTF0Oh2cnJwgl8vh5eUFnU6H4uJirFq1itP32iiFQgGlUgng2u9pwL4SUteTy+UYMWIEAGD79u2oq6tr1vYs/ZrsKSFliYn9o4iIiIjIUdj0jPvy5csYMmQIFAoFNm3ahOPHj2Pp0qXw9vaW1lm8eDGWLVuGDz74AD/++CPc3NwQHx8v9dAgooYLCgoCAFy8eLHZ+5DBYIBer0dAQAAMBoM0zUmpVEImkyEoKAjHjx+HwWBodtxkG5ZkiCUhZS9T9m7lnnvugaenJy5fvoyffvqpWduyJH/soUH/7absMSFFRERERG2dTRNSf//73xEcHIyVK1di0KBBCA0NxciRI9G9e3cA16qj3nrrLbz66quYMGEC+vXrh1WrViE/Px8bNmywZehEbZKHhwe8vLwghJCSDE1VWlqKkpISnDhxAhcuXAAAhISEwNXVFQCgVqthMpmkK7RR22NJyNTU1ACw3wop4FpF1/333w8A2LJlC4QQTd6WJSGlVqtbJLbmuHHKnmV/YkKKiIiIiNo6myakNm7ciKioKDz66KPw9fVFZGQkli9fLt2fm5uLgoKCev1ANBoNYmJikJGRccttVlVVoaysrN6NiP6nJabtmUwmpKeno6CgAJWVlVCpVIiIiEDXrl2ldYxGI1QqlV0nMejObqwQsucKKQCIi4uDUqlEfn4+jh071uTt2FOF1O2m7HG/IiIiIqK2zqYJqV9//RXvv/8+evTogS1btuDZZ5/F888/j7S0NACQGun6+fnVe5yfn590343eeOMNaDQa6WY5+Saiayz7RF5eXpMer9frMX/+fJw6dQpeXl5QKBQYMGBAvRNkIQTy8vIQHh4OrVbbInGT9d3YQ8nekyBqtRpDhw4FcK1Kqqnsqam5JQb2kCIiIiIiR2PThJTZbMaAAQPw+uuvIzIyEtOmTcPTTz+NDz74oMnbnD17NkpLS6VbS11NjMhRNLVCymQy4bPPPsNbb72FkpIS+Pj4YMGCBdDpdDh58iTKyspQW1uLsrIy6PV6+Pj4IDEx0SGbw7cX11cIubq6wsXFxYbRNMzw4cMhl8tx8uRJnD59uknbsMem5uwhRURERESOxtmWTx4QEIDw8PB6y3Q6HdatWwcA8Pf3BwAUFhYiICBAWqewsBD9+/e/5TaVSqV0ZSgiupmlsfn58+dhNpsblDA6ceIEVq1ahUuXLgEA7r33Xjz88MNQKpXo0qUL0tLSoNfrkZ+fD5VKhaioKCQmJiIyMrJVXwu1rusTUvY+Xc/C29tbmta9ZcsWTJ8+vdHbsKeE1PUVUkIIJqSIiIiIyGHYNCE1ZMgQZGdn11t28uRJdOnSBQAQGhoKf39/7NixQ0pAlZWV4ccff8Szzz5r7XCJHEKnTp2gVCpRVVV1U7L3RlVVVfjqq6+Qnp4OAOjYsSMSExPRq1cvaZ3IyEhERETAYDCgtLQUGo0GWq2WlVEO4PqElL1P17veyJEjkZGRgaysLBQVFcHX17dRj7enhJTlPTCbzbh69arU1LwtvR9ERERERLdi04TUn//8ZwwePBivv/46Jk2ahAMHDuDDDz/Ehx9+CACQyWR44YUXsHDhQvTo0QOhoaGYM2cOAgMDkZCQYMvQidosmUyGoKAg5OTk4Ny5c7dNSJ08eRJpaWkoLi4GAAwbNgwTJ06ESqW6aV25XI6wsLBWjZusT61W48qVK6iurkbXrl0bXFFna4GBgejbty+OHDmCbdu2YfLkyQ1+rBDCrpqaOzs7SwnkS5cuSVc89PDwsHFkRERERETNY9OEVHR0NNavX4/Zs2cjJSUFoaGheOutt+qdPPzlL39BZWUlpk2bhitXruA3v/kNNm/efMuTYiJqmODgYCkhNWjQoHr3VVVVYf369di1axcAoEOHDkhMTIROp7NFqGQjWVlZeOedd7Bv3z7U1tYiNzcXhYWFSEpKahNTMePj43HkyBHs27cP48ePb/AUt6qqKtTV1QGwjwop4FpirKqqCvn5+QA4NZ2IiIiIHINNE1IAMG7cOIwbN+6298tkMqSkpCAlJcWKURE5ts6dO+PKlSvYu3cv+vbtK02xO3XqFFJTU6WqqKFDh+KRRx5hAridycrKQkpKCs6fPw8XFxeo1Wp06NABmZmZOHPmDJKTk+0+KaXVahEaGorc3Fzs2rULEyZMaNDjLNVRzs7OUCgUrRlig7m5ueHSpUtSQorT9YiIiIjIEdg8IUVE1pWVlYXU1FTs27cPQggcPXoUPXv2ROfOnZGbmwvgWmPoxMTEmy46QI7PbDZLUzV1Oh0OHDgA4FpTcx8fH+j1eqxatQoRERF2PX1PJpMhPj4eH3zwAdLT0zFq1KgGVRVdP11PJpO1dpgNYpk6aElIsaE5ERERETkCJqSI2hFL5cvFixehVCrh5OQEmUyGr7/+Gk5OThgwYAASEhLwyCOPwNXV1dbhkg0YDAbo9XoEBQXBxcVFWq5UKqX+Y8ePH4fBYLD7vmERERHw9fVFUVER9uzZgwceeOCuj7EkpNRqdWuH12CWqYNMSBERERGRI7Hfr7eJqEVdX/kSHh4OLy8vyOVynD17Fmq1GjU1NXBzc8PkyZOZjGrHSktLYTKZ4ObmBrlcLiWiLNM21Wo1TCaTdLU3eyaXyzFy5EgAwLZt26TeUHdiTw3NLSyxXLp0CQATUkRERETkGJiQImonrq98kclk9U64AwICEBsbi8LCQhgMBhtGSbam0WigUqmkxEzv3r3Rp08fqVrKaDRCpVK1mT5G99xzDzw8PHD58mUcPHjwrutXVFQAsJ+G5sD/ElJCCADsIUVEREREjoEJKaJ24vrKFwAIDAyEj48P+vTpg7CwMHh6eraZyhdqPVqtFjqdDnl5eRBCwN3dHd7e3gCuJUTy8vIQHh4OrVZr40gbRqFQSFP1tmzZIiV1bseSiLOnhNSNsXh4eNgoEiIiIiKilsOEFFE7cWPli4eHB8LDw9GhQwcAba/yhVqHXC5HUlKS1MC8rKwMtbW1KCsrg16vh4+PDxITE+26ofmN4uLioFQqcf78eRw/fvyO69pjQurG6YPcR4mIiIjIEbCpOa59619bW9ug/iLUvjk5OcHZ2dlurr7VGJbKl8zMTOh0unqvwVL5EhUV1WYqX6j1REZGIjk5GWlpadDr9cjPz4dKpUJUVBQSExMRGRlp6xAbRa1WY+jQodi+fTu2bNmC3r1733Zde+4hZcEeUkRERETkCNp9Qqq6uhoXLlyA0Wi0dSjURqjVagQEBNS7AllbYKl8OXPmjNRLSq1Ww2g0Ii8vr01WvlDriYyMREREBAwGA0pLS6HRaKDVatvs52P48OHYuXMnsrOzcfr0aXTt2vWW69ljD6kbY2FCioiIiIgcQbtOSJnNZuTm5sLJyQmBgYFwcXFpk5UvZB1CCFRXV+PixYvIzc1Fjx492tzJuaNVvlDrksvlCAsLs3UYLcLb2xuDBg3C/v37sXXrVkybNu2W61m+nLCnhBQrpIiIiIjIEbXrhFR1dTXMZjOCg4OhVqttHQ61Aa6urlAoFDhz5gyqq6uhUqlsHVKjOVrlC1FDjRw5Evv378ehQ4dQVFQEX1/fm9ax9woptVoNZ+d2/aebiIiIiBwEz0ABnohTozjC58VS+RIdHY2wsDCHeE1Ed9O5c2f06dMHQghs27btluvYY1NzZ2dnVFRUoKioCDU1NTCbzbYOiYiIiIio2XgWSkRE7UZ8fDwAYN++fSgrK6t3nxBCmrJnL03Ns7Ky8OKLL2Lfvn3Yv38/tm3bhlmzZiErK8vWoRERERERNQsTUkRE1G706NEDXbt2RW1tLXbt2lXvPqPRCCEEANjFNO6srCykpKQgMzMTHh4e8PT0hEajQWZmJlJSUpiUIiIiIqI2jQmpNmjq1KmQyWTSrWPHjhg1ahR++eWXFnuOefPmoX///k16bEFBAaZMmQJ/f3+4ublhwIABWLdu3S3XraqqQv/+/SGTyXD48OHbbrOkpAQzZ85Ez5494erqipCQEDz//PMoLS2tt97Zs2cxduxYqNVq+Pr64uWXX0Ztba10f1ZWFiIjI+Hu7o7x48ejpKREuq+2thYDBw7EgQMHmvS6icj+yWQyqUoqPT0dVVVV0n2W6XpKpdLmfZrMZjPS0tJQXFwMnU4HNzc3yOVyeHp6QqfTobi4GKtWreL0PSIiIiJqs5iQaqNGjRqFCxcu4MKFC9ixYwecnZ0xbtw4W4cFAEhMTER2djY2btyII0eO4OGHH8akSZNu+W3+X/7yFwQGBt51m/n5+cjPz8eSJUtw9OhRpKamYvPmzXjqqaekderq6jB27FhUV1dj3759SEtLQ2pqKpKTk6V1/vCHP+D+++/HoUOHUFpaitdff126b+nSpRgyZAgGDRrUzBEgInvWv39/+Pr6wmg0Ys+ePdJye+ofZTAYoNfrERQUBJlMBoVCAQDS1WCDgoJw/PhxGAwGG0dKRERERNQ0TEi1UUqlEv7+/vD390f//v3xyiuv4Ny5c7h48aK0zrlz5zBp0iR4eXmhQ4cOmDBhAk6fPi3dn56ejkGDBsHNzQ1eXl4YMmQIzpw5g9TUVMyfPx8///yzVIWVmpra4Nj27duHmTNnYtCgQejWrRteffVVeHl5ITMzs956mzZtwtatW7FkyZK7brNPnz5Yt24dxo8fj+7du+P+++/Ha6+9hm+++UaqgNq6dSuOHz+OTz/9FP3798fo0aOxYMECvPvuu6iurgYA6PV6PP300wgLC8MTTzwBvV4PAPj111/x0Ucf4bXXXmvw6ySitkkul2PEiBEAgO3bt6Ourg6AfSWkSktLYTKZpFgCAwPRsWNHdOrUCcC1KYUmk+mmKlEiIiIioraCCalbqay8/c1kavi6V682bN1mqqiowKeffgqtVouOHTsCAGpqahAfHw8PDw/88MMP2Lt3L9zd3TFq1ChUV1ejtrYWCQkJiIuLwy+//IKMjAxMmzYNMpkMjz32GF588UX07t1bqsJ67LHHAFybLnjvvffeMZ7BgwdjzZo1KCkpgdlsxurVq2Eymeo9rrCwEE8//TQ++eSTJvdqKS0thaenpzS1JiMjA3379oWfn5+0Tnx8PMrKynDs2DEAQEREBLZt24ba2lrs2LED/fr1AwA888wzWLx4MTw8PJoUCxG1LbGxsfDw8EBJSQkOHjwI4H8JKXtoaK7RaKBSqaSYNBoNevfuDZVKBeBavyuVSgWNRmPLMImIiIiImowJqVtxd7/9beLE+uv6+t5+3dGj66/bteut12uCb7/9Fu7u7nB3d4eHhwc2btyINWvWQC6/9pauWbMGZrMZK1asQN++faHT6bBy5UqcPXsW6enpKCsrQ2lpKcaNG4fu3btDp9MhKSkJISEhcHV1hbu7O5ydnaUqLFdXVwBAQEAAQkJC7hjb2rVrUVNTg44dO0KpVGL69OlYv349tFotgGtXspo6dSqeeeYZREVFNen1FxcXY8GCBZg2bZq0rKCgoF4yCoD0c0FBAQBgxYoV+PLLL9G9e3e4uLhg9uzZUlIsOjoa8fHx0Gq1ePXVV5sUFxG1DQqFAg888ACAa9WVQghUVFQAsI8KKa1WC51Oh7y8PKnRuoUQAnl5eQgPD5d+rxIRERERtTW27dpKTXbffffh/fffBwBcvnwZ7733HkaPHo0DBw6gS5cu+Pnnn2EwGG6q+DGZTMjJycHIkSMxdepUxMfHY8SIERg+fDgmTZqEgICAOz7vG2+8cdfY5syZgytXrmD79u3w8fHBhg0bMGnSJPzwww/o27cv3n77bZSXl2P27NlNeu1lZWUYO3YswsPDMW/evEY9tnfv3ti9e7f086VLlzB37lx8//33mDlzJgYPHoyvvvoK0dHRiImJwfjx45sUIxHZv7i4OGzatAl5eXk4fvw4jEYjAPtISMnlciQlJeHMmTNSLym1Wg2j0Yi8vDz4+PggMTFR+hKCiIiIiKit4ZHsrVRU3P5249Xiiopuv+6mTfXXPX361us1gZubG7RaLbRaLaKjo7FixQpUVlZi+fLl/30JFRg4cCAOHz5c73by5En89re/BQCsXLkSGRkZ0hS7sLAw7N+/v0nxWOTk5OCdd97Bxx9/jAceeAARERGYO3cuoqKi8O677wIAdu7ciYyMDOlKVpZv+KOiopCUlHTH7ZeXl2PUqFHw8PDA+vXrpUa/AODv74/CwsJ661t+9vf3v+X2Zs2ahRdeeAFBQUFIT0/Ho48+Cjc3N4wdOxbp6elNHQYiagPUajWGDh0K4FqVlD1VSAFAZGQkkpOTMXDgQJSUlMBgMKCkpARRUVFITk5GZGSkrUMkIiIiImoyVkjdSmNORlpr3UaSyWSQy+W4+t++VQMGDMCaNWvg6+sLT0/P2z4uMjISkZGRmD17NmJjY/Hvf/8b99xzD1xcXKRGv41hqTC48Vt7Jycn6fLky5Ytw8KFC6X78vPzER8fjzVr1iAmJua22y4rK0N8fDyUSiU2btwo9VKxiI2NxWuvvYaioiL4+voCALZt2wZPT0+Eh4fftL0dO3ZAr9dj5cqVAK5dpa+mpgYApH+JyLE98MAD2LlzJ/R6PXJyclBUVITLly/DbDbbRfVRZGQkIiIiYDAYUFpaCo1GA61WaxexERERERE1B49o26iqqioUFBSgoKAAer0eM2fOREVFhTTFbPLkyfDx8cGECRPwww8/IDc3F+np6Xj++eeRl5eH3NxczJ49GxkZGThz5gy2bt2KU6dOQafTAQC6du2K3NxcHD58GMXFxaiqqgIAzJ49G4mJibeNq1evXtBqtZg+fToOHDiAnJwcLF26FNu2bUNCQgIAICQkBH369JFuYWFhAIDu3bsjKCgIAHD+/Hn06tULBw4cAHAtGTVy5EhUVlbio48+QllZmfT6LYmzkSNHIjw8HFOmTMHPP/+MLVu24NVXX8WMGTOgVCrrxWkymfDcc8/hww8/lE7shgwZgnfffRc///wz1q1bhyFDhrTEW0VEdqxDhw7w8/NDRkYGvv76a+zfvx/vv/8+Zs2ahaysLFuHB+Bagj8sLAzR0dEICwtjMoqIiIiIHAKPatuozZs3IyAgAAEBAYiJicFPP/2EL774QrqSnVqtxvfff4+QkBA8/PDD0Ol0eOqpp2AymeDp6Qm1Wo0TJ05g4sSJCAsLw7Rp0zBjxgxMnz4dADBx4kSMGjUK9913Hzp16oTPP/8cAHDhwgWcPXv2tnEpFAp899136NSpE8aPH49+/fph1apVSEtLw5gxYxr8+mpqapCdnS1VXB06dAg//vgjjhw5Aq1WK732gIAAnDt3DsC1Kqxvv/0WTk5OiI2Nxe9+9zskJiYiJSXlpu3Pnz8fY8eORf/+/aVly5Ytw+HDhzFs2DCMHz8eE29sYE9EDicrKwv79+/HxYsX4eLiAk9PT3h7eyMzMxMpKSl2k5QiIiIiInI0MnHj5XscTFlZGTQaDUpLS2+aumYymZCbm4vQ0NCbpn8R3Q4/N0SOwWw2Y9asWcjMzERdXR0uX74MAOjfvz88PDyg1+sRFRWFpUuXsirJRu70N5wck+U9v///rYWzSm3rcIiIiBzOljljW2W7TTlu4xE2ERG1SwaDQbqCXUhIiLRcoVBAJpMhKCgIx48fh8FgsGGURERERESOiU3NiYioXSotLYXJZIKbmxvkcjkCAgJQXV0tVT6q1Wrk5+ejtLTUxpEStT/r/xrPqjgiIiIHx4QUERG1SxqNBiqVCpWVlfD09ESPHj3q3W80GqFSqaDRaGwUIRERERGR4+KUPSIiape0Wi10Oh3y8vJwYztFIQTy8vIQHh4OrVZrowiJiIiIiBwXE1JERNQuyeVyJCUlwcfHB3q9HmVlZaitrUVZWRn0ej18fHyQmJjIhuZERERERK2AR9nATd+ME90JPy9EjiMyMhLJyckYOHAgSkpKYDAYUFJSgqioKCQnJyMyMtLWIRIREREROaR23UNKoVAAuNYnxNXV1cbRUFthNBoB/O/zQ0RtW2RkJCIiImAwGFBaWgqNRgOtVsvKKCIiIiKiVtSuE1JOTk7w8vJCUVERgGtXVJLJZDaOiuyVEAJGoxFFRUXw8vKCk5OTrUMiohYil8sRFhZm6zCIiIiIiNqNdp2QAgB/f38AkJJSRHfj5eUlfW6IiIiIiIiIqPHafUJKJpMhICAAvr6+qKmpsXU4ZOcUCgUro4iIiIiIiIiaqd0npCycnJyYaCAiIiIiIiIisgJ2bCUiIiIiIiIiIqtiQoqIiIiIiIiIiKyKCSkiIiIiIiIiIrIqh+8hJYQAAJSVldk4EiIiImoMy99uy99ycnw8biMiImqbmnLc5vAJqfLycgBAcHCwjSMhIiKipigvL4dGo7F1GGQFly5dAsDjNiIioraqMcdtMuHgXzuazWbk5+fDw8MDMpmsRbddVlaG4OBgnDt3Dp6eni26bWo4vg/2ge+DfeD7YD/4XjSfEALl5eUIDAyEXM4uA+3BlStX4O3tjbNnzzIJ2UT83dMyOI7NxzFsGRzH5uMYtoy7jWNTjtscvkJKLpcjKCioVZ/D09OTH2w7wPfBPvB9sA98H+wH34vmYVKifbEcwGo0Gu43zcTfPS2D49h8HMOWwXFsPo5hy7jTODb2uI1fNxIRERERERERkVUxIUVERERERERERFbFhFQzKJVKzJ07F0ql0tahtGt8H+wD3wf7wPfBfvC9IGo87jfNxzFsGRzH5uMYtgyOY/NxDFtGa4yjwzc1JyIiIiIiIiIi+8IKKSIiIiIiIiIisiompIiIiIiIiIiIyKqYkCIiIiIiIiIiIqtiQqqJ3n33XXTt2hUqlQoxMTE4cOCArUNqd+bNmweZTFbv1qtXL1uH5fC+//57jB8/HoGBgZDJZNiwYUO9+4UQSE5ORkBAAFxdXTF8+HCcOnXKNsE6sLu9D1OnTr1p/xg1apRtgnVgb7zxBqKjo+Hh4QFfX18kJCQgOzu73jomkwkzZsxAx44d4e7ujokTJ6KwsNBGERPZXmOPob744gv06tULKpUKffv2xXfffWelSO1XY8bw2LFjmDhxIrp27QqZTIa33nrLeoHaucaM4/LlyzF06FB4e3vD29sbw4cP5/E/GjeGX331FaKiouDl5QU3Nzf0798fn3zyiRWjtV9NPbdcvXo1ZDIZEhISWjfANqAxY5iamnrTcbJKpbJitParsZ/FK1euYMaMGQgICIBSqURYWFij/k4zIdUEa9aswaxZszB37lwcOnQIERERiI+PR1FRka1Da3d69+6NCxcuSLc9e/bYOiSHV1lZiYiICLz77ru3vH/x4sVYtmwZPvjgA/z4449wc3NDfHw8TCaTlSN1bHd7HwBg1KhR9faPzz//3IoRtg+7d+/GjBkzsH//fmzbtg01NTUYOXIkKisrpXX+/Oc/45tvvsEXX3yB3bt3Iz8/Hw8//LANoyayncYeQ+3btw9PPPEEnnrqKWRlZSEhIQEJCQk4evSolSO3H40dQ6PRiG7dumHRokXw9/e3crT2q7HjmJ6ejieeeAK7du1CRkYGgoODMXLkSJw/f97KkduPxo5hhw4d8Le//Q0ZGRn45Zdf8OSTT+LJJ5/Eli1brBy5fWnqueXp06fx0ksvYejQoVaK1H41ZQw9PT3rHSefOXPGihHbp8aOY3V1NUaMGIHTp0/jyy+/RHZ2NpYvX47OnTs3/EkFNdqgQYPEjBkzpJ/r6upEYGCgeOONN2wYVfszd+5cERERYesw2jUAYv369dLPZrNZ+Pv7i3/84x/SsitXrgilUik+//xzG0TYPtz4PgghRFJSkpgwYYJN4mnPioqKBACxe/duIcS1z79CoRBffPGFtI5erxcAREZGhq3CJLKZxh5DTZo0SYwdO7bespiYGDF9+vRWjdOeNec4tEuXLuKf//xnK0bXdjT3eL62tlZ4eHiItLS01grR7rXEOVFkZKR49dVXWyO8NqMp41hbWysGDx4sVqxYwWM+0fgxXLlypdBoNFaKru1o7Di+//77olu3bqK6urrJz8kKqUaqrq5GZmYmhg8fLi2Ty+UYPnw4MjIybBhZ+3Tq1CkEBgaiW7dumDx5Ms6ePWvrkNq13NxcFBQU1Ns/NBoNYmJiuH/YQHp6Onx9fdGzZ088++yzuHTpkq1DcnilpaUArn0LDACZmZmoqampt0/06tULISEh3Ceo3WnKMVRGRka99QEgPj6+3e4/PA5tGS0xjkajETU1NdLv+/amuWMohMCOHTuQnZ2NYcOGtWaodq2p45iSkgJfX1889dRT1gjTrjV1DCsqKtClSxcEBwdjwoQJOHbsmDXCtVtNGceNGzciNjYWM2bMgJ+fH/r06YPXX38ddXV1DX5eJqQaqbi4GHV1dfDz86u33M/PDwUFBTaKqn2KiYlBamoqNm/ejPfffx+5ubkYOnQoysvLbR1au2XZB7h/2N6oUaOwatUq7NixA3//+9+xe/dujB49ulF/IKhxzGYzXnjhBQwZMgR9+vQBcG2fcHFxgZeXV711uU9Qe9SUY6iCggL+TbkOj0NbRkuM41//+lcEBgbelDBtL5o6hqWlpXB3d4eLiwvGjh2Lt99+GyNGjGjtcO1WU8Zxz549+Oijj7B8+XJrhGj3mjKGPXv2xMcff4yvv/4an376KcxmMwYPHoy8vDxrhGyXmjKOv/76K7788kvU1dXhu+++w5w5c7B06VIsXLiwwc/r3KyoiWxo9OjR0v/79euHmJgYdOnSBWvXruW3BdTuPf7449L/+/bti379+qF79+5IT0/HAw88YMPIHNeMGTNw9OhR9rIjInJwixYtwurVq5Gens5GyI3k4eGBw4cPo6KiAjt27MCsWbPQrVs33HvvvbYOrU0oLy/HlClTsHz5cvj4+Ng6nDYrNjYWsbGx0s+DBw+GTqfDv/71LyxYsMCGkbUtZrMZvr6++PDDD+Hk5ISBAwfi/Pnz+Mc//oG5c+c2aBtMSDWSj48PnJycbrpCUmFhIRtF2piXlxfCwsJgMBhsHUq7ZdkHCgsLERAQIC0vLCxE//79bRQVAUC3bt3g4+MDg8HAhFQreO655/Dtt9/i+++/R1BQkLTc398f1dXVuHLlSr0qKf7NoPaoKcdQ/v7+POa6Do9DW0ZzxnHJkiVYtGgRtm/fjn79+rVmmHatqWMol8uh1WoBAP3794der8cbb7zRbhNSjR3HnJwcnD59GuPHj5eWmc1mAICzszOys7PRvXv31g3azrTE70WFQoHIyMh2fR7ZlHEMCAiAQqGAk5OTtEyn06GgoADV1dVwcXG56/Nyyl4jubi4YODAgdixY4e0zGw2Y8eOHfWyrGR9FRUVyMnJqZcIIesKDQ2Fv79/vf2jrKwMP/74I/cPG8vLy8OlS5e4f7QwIQSee+45rF+/Hjt37kRoaGi9+wcOHAiFQlFvn8jOzsbZs2e5T1C705RjqNjY2HrrA8C2bdva7f7D49CW0dRxXLx4MRYsWIDNmzcjKirKGqHarZb6LJrNZlRVVbVGiG1CY8exV69eOHLkCA4fPizdHnzwQdx33304fPgwgoODrRm+XWiJz2JdXR2OHDnSro+TmzKOQ4YMgcFgkJKiAHDy5EkEBAQ0KBkFgFfZa4rVq1cLpVIpUlNTxfHjx8W0adOEl5eXKCgosHVo7cqLL74o0tPTRW5urti7d68YPny48PHxEUVFRbYOzaGVl5eLrKwskZWVJQCIN998U2RlZYkzZ84IIYRYtGiR8PLyEl9//bX45ZdfxIQJE0RoaKi4evWqjSN3LHd6H8rLy8VLL70kMjIyRG5urti+fbsYMGCA6NGjhzCZTLYO3aE8++yzQqPRiPT0dHHhwgXpZjQapXWeeeYZERISInbu3CkOHjwoYmNjRWxsrA2jJrKdux1DTZkyRbzyyivS+nv37hXOzs5iyZIlQq/Xi7lz5wqFQiGOHDliq5dgc40dw6qqKunvRUBAgHjppZdEVlaWOHXqlK1egl1o7DguWrRIuLi4iC+//LLe7/vy8nJbvQSba+wYvv7662Lr1q0iJydHHD9+XCxZskQ4OzuL5cuX2+ol2IXGjuONeJW9xo/h/PnzxZYtW0ROTo7IzMwUjz/+uFCpVOLYsWO2egl2obHjePbsWeHh4SGee+45kZ2dLb799lvh6+srFi5c2ODnZEKqid5++20REhIiXFxcxKBBg8T+/fttHVK789hjj4mAgADh4uIiOnfuLB577DFhMBhsHZbD27VrlwBw0y0pKUkIIYTZbBZz5swRfn5+QqlUigceeEBkZ2fbNmgHdKf3wWg0ipEjR4pOnToJhUIhunTpIp5++mkmzVvBrd4DAGLlypXSOlevXhV//OMfhbe3t1Cr1eKhhx4SFy5csF3QRDZ2p2OouLg46e+Jxdq1a0VYWJhwcXERvXv3Fv/5z3+sHLH9acwY5ubm3vL3VFxcnPUDtzONGccuXbrcchznzp1r/cDtSGPG8G9/+5vQarVCpVIJb29vERsbK1avXm2DqO1PY38vXo8JqWsaM4YvvPCCtK6fn58YM2aMOHTokA2itj+N/Szu27dPxMTECKVSKbp16yZee+01UVtb2+DnkwkhRMNqqYiIiIiIiIiIiJqPPaSIiIiIiIiIiMiqmJAiIiIiIiIiIiKrYkKKiIiIiIiIiIisigkpIiIiIiIiIiKyKiakiIiIiIiIiIjIqpiQIiIiIiIiIiIiq2JCioiIiIiIiIiIrIoJKSIiIiIiIiIisiompIiozZo3bx769+/fqMfIZDJs2LChVeIhIiIiIiKihmFCiojsgkwmu+Nt3rx5Nz3mpZdewo4dO6wfLBEREZEdmzp1KhISEmwdxi2dPn0aMpkMhw8ftnUoRGRjzrYOgIgIAC5cuCD9f82aNUhOTkZ2dra0zN3dXfq/EAJ1dXVwd3evt5yIiIiI7Fd1dbWtQyAiO8IKKSKyC/7+/tJNo9FAJpNJP584cQIeHh7YtGkTBg4cCKVSiT179tw0Ze+nn37CiBEj4OPjA41Gg7i4OBw6dMh2L4qIiIjIxu69917MnDkTL7zwAry9veHn54fly5ejsrISTz75JDw8PKDVarFp0ybpMenp6ZDJZPjPf/6Dfv36QaVS4Z577sHRo0frbXvdunXo3bs3lEolunbtiqVLl9a7v2vXrliwYAESExPh6emJadOmITQ0FAAQGRkJmUyGe++9F0DDjuNkMhlWrFiBhx56CGq1Gj169MDGjRvrrXPs2DGMGzcOnp6e8PDwwNChQ5GTkyPdv2LFCuh0OqhUKvTq1Qvvvfdes8eYiJqGCSkiajNeeeUVLFq0CHq9Hv369bvp/vLyciQlJWHPnj3Yv38/evTogTFjxqC8vNwG0RIRERHZh7S0NPj4+ODAgQOYOXMmnn32WTz66KMYPHgwDh06hJEjR2LKlCkwGo31Hvfyyy9j6dKl+Omnn9CpUyeMHz8eNTU1AIDMzExMmjQJjz/+OI4cOYJ58+Zhzpw5SE1NrbeNJUuWICIiAllZWZgzZw4OHDgAANi+fTsuXLiAr776CkDDj+Pmz5+PSZMm4ZdffsGYMWMwefJklJSUAADOnz+PYcOGQalUYufOncjMzMTvf/971NbWAgA+++wzJCcn47XXXoNer8frr7+OOXPmIC0trcXHnIgaQBAR2ZmVK1cKjUYj/bxr1y4BQGzYsKHeenPnzhURERG33U5dXZ3w8PAQ33zzjbQMgFi/fn0LR0xERERkP5KSksSECROEEELExcWJ3/zmN9J9tbW1ws3NTUyZMkVaduHCBQFAZGRkCCH+d+y1evVqaZ1Lly4JV1dXsWbNGiGEEL/97W/FiBEj6j3vyy+/LMLDw6Wfu3TpIhISEuqtk5ubKwCIrKysO76G2x3Hvfrqq9LPFRUVAoDYtGmTEEKI2bNni9DQUFFdXX3LbXbv3l38+9//rrdswYIFIjY29o6xEFHrYIUUEbUZUVFRd7y/sLAQTz/9NHr06AGNRgNPT09UVFTg7NmzVoqQiIiIyP5cX1nu5OSEjh07om/fvtIyPz8/AEBRUVG9x8XGxkr/79ChA3r27Am9Xg8A0Ov1GDJkSL31hwwZglOnTqGurk5adrfjN4uGHsdd/1rc3Nzg6ekpxX348GEMHToUCoXipu1XVlYiJycHTz31lNSH1N3dHQsXLqw3pY+IrIdNzYmozXBzc7vj/UlJSbh06RL+7//+D126dIFSqURsbCwbaBIREVG7dmOCRiaT1Vsmk8kAAGazucWf+27HbxYNPY671WuxxO3q6nrb7VdUVAAAli9fjpiYmHr3OTk5NShGImpZTEgRkcPYu3cv3nvvPYwZMwYAcO7cORQXF9s4KiIiIqK2af/+/QgJCQEAXL58GSdPnoROpwMA6HQ67N27t976e/fuRVhY2B0TPC4uLgBQr4rK8tjmHsf169cPaWlpqKmpuSlx5efnh8DAQPz666+YPHlyo7ZLRK2DCSkichg9evTAJ598gqioKJSVleHll1++4zdlRERERHR7KSkp6NixI/z8/PC3v/0NPj4+SEhIAAC8+OKLiI6OxoIFC/DYY48hIyMD77zzzl2vWufr6wtXV1ds3rwZQUFBUKlU0Gg0LXIc99xzz+Htt9/G448/jtmzZ0Oj0WD//v0YNGgQevbsifnz5+P555+HRqPBqFGjUFVVhYMHD+Ly5cuYNWtWU4eJiJqIPaSIyGF89NFHuHz5MgYMGIApU6bg+eefh6+vr63DIiIiImqTFi1ahD/96U8YOHAgCgoK8M0330gVTgMGDMDatWuxevVq9OnTB8nJyUhJScHUqVPvuE1nZ2csW7YM//rXvxAYGIgJEyYAaJnjuI4dO2Lnzp2oqKhAXFwcBg4ciOXLl0vVUn/4wx+wYsUKrFy5En379kVcXBxSU1MRGhra+MEhomaTCSGErYMgIiIiIiIi+5Ceno777rsPly9fhpeXl63DISIHxQopIiIiIiIiIiKyKiakiIiIiIiIiIjIqjhlj4iIiIiIiIiIrIoVUkREREREREREZFVMSBERERERERERkVUxIUVERERERERERFbFhBQREREREREREVkVE1JERERERERERGRVTEgREREREREREZFVMSFFRERERERERERWxYQUERERERERERFZFRNSRERERERERERkVf8ff/8f367Cqo0AAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(1, 2, figsize=(12, 4))\n",
    "\n",
    "# Optimization history\n",
    "axes[0].set_title('Optimization History')\n",
    "\n",
    "trial_numbers = [t.number for t in study.trials if t.value is not None]\n",
    "trial_values = [t.value for t in study.trials if t.value is not None]\n",
    "\n",
    "axes[0].plot(trial_numbers, trial_values, 'ko-', alpha=0.6)\n",
    "axes[0].axhline(y=study.best_value, color='r', linestyle='--', label=f'Best: {study.best_value:.2f}%')\n",
    "axes[0].set_xlabel('Trial')\n",
    "axes[0].set_ylabel('Validation Accuracy (%)')\n",
    "axes[0].legend()\n",
    "\n",
    "# Hyperparameter importance\n",
    "axes[1].set_title('Hyperparameter Importance')\n",
    "completed_trials = [t for t in study.trials if t.state == optuna.trial.TrialState.COMPLETE]\n",
    "\n",
    "if len(completed_trials) >= 5:\n",
    "    importance = optuna.importance.get_param_importances(study)\n",
    "    params = list(importance.keys())\n",
    "    values = list(importance.values())\n",
    "    axes[1].barh(params, values, color='steelblue')\n",
    "    axes[1].set_xlabel('Importance')\n",
    "\n",
    "else:\n",
    "    axes[1].text(0.5, 0.5, 'Not enough trials\\nfor importance analysis', \n",
    "                 ha='center', va='center', transform=axes[1].transAxes)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0568375d",
   "metadata": {},
   "source": [
    "## 4. Train final model with best hyperparameters\n",
    "\n",
    "Now we train the winning model configuration for more epochs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "5633d796",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best hyperparameters:\n",
      " - n_conv_blocks: 4\n",
      " - dropout_rate: 0.210\n"
     ]
    }
   ],
   "source": [
    "# Get best hyperparameters\n",
    "best_params = study.best_trial.params\n",
    "\n",
    "print('Best hyperparameters:')\n",
    "print(f' - n_conv_blocks: {best_params[\"n_conv_blocks\"]}')\n",
    "print(f' - dropout_rate: {best_params[\"dropout_rate\"]:.3f}')\n",
    "\n",
    "# Create model with best hyperparameters\n",
    "best_model = create_cnn(\n",
    "    n_conv_blocks=best_params['n_conv_blocks'],\n",
    "    dropout_rate=best_params['dropout_rate']\n",
    ").to(device)\n",
    "\n",
    "# Create optimizer\n",
    "best_optimizer = optim.Adam(best_model.parameters(), lr=learning_rate)\n",
    "\n",
    "# Set loss function\n",
    "criterion = nn.CrossEntropyLoss()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "d45b409e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/50 - loss: 1.7795 - accuracy: 31.25% - val_loss: 1.9832 - val_accuracy: 27.61%\n",
      "Epoch 5/50 - loss: 0.8929 - accuracy: 68.03% - val_loss: 1.1476 - val_accuracy: 61.66%\n",
      "Epoch 10/50 - loss: 0.5746 - accuracy: 80.08% - val_loss: 0.6262 - val_accuracy: 79.00%\n",
      "Epoch 15/50 - loss: 0.4158 - accuracy: 85.70% - val_loss: 0.5503 - val_accuracy: 81.97%\n",
      "Epoch 20/50 - loss: 0.3147 - accuracy: 89.00% - val_loss: 0.4839 - val_accuracy: 84.02%\n",
      "Epoch 25/50 - loss: 0.2419 - accuracy: 91.45% - val_loss: 0.5741 - val_accuracy: 82.96%\n",
      "Epoch 30/50 - loss: 0.1839 - accuracy: 93.47% - val_loss: 0.5307 - val_accuracy: 84.98%\n",
      "Epoch 35/50 - loss: 0.1508 - accuracy: 94.72% - val_loss: 0.5506 - val_accuracy: 85.31%\n",
      "Epoch 40/50 - loss: 0.1223 - accuracy: 95.66% - val_loss: 0.5861 - val_accuracy: 85.65%\n",
      "Epoch 45/50 - loss: 0.0956 - accuracy: 96.74% - val_loss: 0.5863 - val_accuracy: 85.54%\n",
      "Epoch 50/50 - loss: 0.0831 - accuracy: 97.09% - val_loss: 0.6322 - val_accuracy: 85.27%\n",
      "\n",
      "Training complete.\n",
      "CPU times: user 7min 27s, sys: 1.37 s, total: 7min 28s\n",
      "Wall time: 7min 23s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "# Train for more epochs\n",
    "history = train_model(\n",
    "    model=best_model,\n",
    "    train_loader=train_loader,\n",
    "    val_loader=val_loader,\n",
    "    criterion=criterion,\n",
    "    optimizer=best_optimizer,\n",
    "    epochs=n_epochs_final,\n",
    "    print_every=10\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "57e97c64",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot learning curves\n",
    "fig, axes = plot_learning_curves(history)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "893772dd",
   "metadata": {},
   "source": [
    "## 5. Evaluate on test set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7cab2506",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test accuracy: 84.76%\n"
     ]
    }
   ],
   "source": [
    "test_accuracy, predictions, true_labels = evaluate_model(best_model, test_loader)\n",
    "print(f'Test accuracy: {test_accuracy:.2f}%')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4c1f8d03",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x800 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "ename": "",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
     ]
    }
   ],
   "source": [
    "# Confusion matrix\n",
    "fig, ax = plot_confusion_matrix(true_labels, predictions, class_names)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}