diff --git a/.DS_Store b/.DS_Store
index ea3fe03..8e71669 100644
Binary files a/.DS_Store and b/.DS_Store differ
diff --git a/Homework4/FashionMNIST_CNN.ipynb b/Homework4/FashionMNIST_CNN.ipynb
new file mode 100644
index 0000000..e6f7ab7
--- /dev/null
+++ b/Homework4/FashionMNIST_CNN.ipynb
@@ -0,0 +1,1127 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Homework 4 - CPTS570 Ricardo Rivero\n",
+    "## Convolutional Neural Network for classifying the Fashion MNIST dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch \n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "import torch.nn.functional as F\n",
+    "from torch.autograd import Variable\n",
+    "import torchvision\n",
+    "import torchvision.transforms as transforms\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "from sklearn.metrics import confusion_matrix\n",
+    "import numpy as np\n",
+    "import random\n",
+    "import os\n",
+    "import time\n",
+    "import copy\n",
+    "import matplotlib.pyplot as plt\n",
+    "from keras._tf_keras.keras.datasets import fashion_mnist\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "device = torch.device('mps' if torch.backends.mps.is_available() else 'cpu')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Load data\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MPS device is available and will be used.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [1/20]: 100%|██████████| 938/938 [00:09<00:00, 103.13it/s, loss=0.541]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [1/20], Average Loss: 0.8064, Accuracy: 69.91%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [2/20]: 100%|██████████| 938/938 [00:08<00:00, 109.54it/s, loss=0.366]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [2/20], Average Loss: 0.5067, Accuracy: 81.39%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [3/20]: 100%|██████████| 938/938 [00:08<00:00, 111.14it/s, loss=0.605]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [3/20], Average Loss: 0.4396, Accuracy: 83.89%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [4/20]: 100%|██████████| 938/938 [00:08<00:00, 111.99it/s, loss=0.389]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [4/20], Average Loss: 0.4030, Accuracy: 85.19%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [5/20]: 100%|██████████| 938/938 [00:07<00:00, 118.52it/s, loss=0.324]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [5/20], Average Loss: 0.3763, Accuracy: 86.18%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [6/20]: 100%|██████████| 938/938 [00:08<00:00, 116.07it/s, loss=0.53]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [6/20], Average Loss: 0.3601, Accuracy: 86.78%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [7/20]: 100%|██████████| 938/938 [00:08<00:00, 114.82it/s, loss=0.249] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [7/20], Average Loss: 0.3427, Accuracy: 87.31%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [8/20]: 100%|██████████| 938/938 [00:08<00:00, 109.75it/s, loss=0.468]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [8/20], Average Loss: 0.3296, Accuracy: 87.81%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [9/20]: 100%|██████████| 938/938 [00:08<00:00, 116.03it/s, loss=0.377] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [9/20], Average Loss: 0.3186, Accuracy: 88.26%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [10/20]: 100%|██████████| 938/938 [00:08<00:00, 116.96it/s, loss=0.384]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [10/20], Average Loss: 0.3087, Accuracy: 88.66%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [11/20]: 100%|██████████| 938/938 [00:09<00:00, 100.53it/s, loss=0.183] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [11/20], Average Loss: 0.2966, Accuracy: 89.19%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [12/20]: 100%|██████████| 938/938 [00:09<00:00, 100.12it/s, loss=0.546] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [12/20], Average Loss: 0.2913, Accuracy: 89.31%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [13/20]: 100%|██████████| 938/938 [00:08<00:00, 112.28it/s, loss=0.118] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [13/20], Average Loss: 0.2822, Accuracy: 89.61%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [14/20]: 100%|██████████| 938/938 [00:08<00:00, 113.52it/s, loss=0.171] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [14/20], Average Loss: 0.2747, Accuracy: 89.85%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [15/20]: 100%|██████████| 938/938 [00:09<00:00, 102.46it/s, loss=0.25]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [15/20], Average Loss: 0.2712, Accuracy: 89.98%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [16/20]: 100%|██████████| 938/938 [00:09<00:00, 104.05it/s, loss=0.134] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [16/20], Average Loss: 0.2647, Accuracy: 90.23%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [17/20]: 100%|██████████| 938/938 [00:08<00:00, 113.33it/s, loss=0.262] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [17/20], Average Loss: 0.2594, Accuracy: 90.48%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [18/20]: 100%|██████████| 938/938 [00:08<00:00, 106.58it/s, loss=0.0785]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [18/20], Average Loss: 0.2547, Accuracy: 90.57%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [19/20]: 100%|██████████| 938/938 [00:08<00:00, 111.05it/s, loss=0.0949]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [19/20], Average Loss: 0.2504, Accuracy: 90.73%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [20/20]: 100%|██████████| 938/938 [00:10<00:00, 92.52it/s, loss=0.172]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [20/20], Average Loss: 0.2461, Accuracy: 90.80%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Evaluating: 100%|██████████| 157/157 [00:02<00:00, 72.42it/s] "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Accuracy: 89.37%\n",
+      "fashion_mnistVanilla_cnn.pth\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Vanilla CNN from the homework\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from torchvision import datasets, transforms\n",
+    "from torch.utils.data import DataLoader\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "# Define the CNN Model\n",
+    "import torch.nn as nn\n",
+    "import torch.nn.functional as F\n",
+    "\n",
+    "class VanillaCNN(nn.Module):\n",
+    "    def __init__(self, num_classes = 10):\n",
+    "        super(VanillaCNN, self).__init__()\n",
+    "        #First convolutional layer\n",
+    "        self.conv1 = nn.Conv2d(in_channels=1, out_channels=8, kernel_size=5, padding=2, stride=2)\n",
+    "        #Second convolutional layer\n",
+    "        self.conv2 = nn.Conv2d(in_channels=8, out_channels=16, kernel_size=3, padding=1, stride=2)\n",
+    "        #Third convolutional layer\n",
+    "        self.conv3 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, padding=1, stride=2)\n",
+    "        #Fourth convolutional layer\n",
+    "        self.conv4 = nn.Conv2d(in_channels=32, out_channels=32, kernel_size=3, padding=1, stride=2)\n",
+    "        #Pooling layer\n",
+    "        self.AveragePool = nn.AdaptiveAvgPool2d(1)\n",
+    "        #Fully connected layer\n",
+    "        self.fc = nn.Linear(32, num_classes)\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = F.relu(self.conv1(x))\n",
+    "        x = F.relu(self.conv2(x))\n",
+    "        x = F.relu(self.conv3(x))\n",
+    "        x = F.relu(self.conv4(x))\n",
+    "        x = self.AveragePool(x)\n",
+    "        x = x.view(x.size(0), -1)\n",
+    "        x = self.fc(x)\n",
+    "        return x\n",
+    "    \n",
+    "# Define device\n",
+    "if torch.backends.mps.is_available():\n",
+    "    device = torch.device(\"mps\")\n",
+    "    print(\"MPS device is available and will be used.\")\n",
+    "elif torch.cuda.is_available():\n",
+    "    device = torch.device(\"cuda\")\n",
+    "    print(\"CUDA device is available and will be used.\")\n",
+    "else:\n",
+    "    device = torch.device(\"cpu\")\n",
+    "    print(\"No GPU found. Using CPU.\")\n",
+    "\n",
+    "\n",
+    "train_loader = DataLoader(\n",
+    "    train_dataset, \n",
+    "    batch_size=64, \n",
+    "    shuffle=True, \n",
+    "    num_workers=2, \n",
+    "    pin_memory=False  # Set to False for MPS\n",
+    ")\n",
+    "test_loader = DataLoader(\n",
+    "    test_dataset, \n",
+    "    batch_size=64, \n",
+    "    shuffle=False, \n",
+    "    num_workers=2, \n",
+    "    pin_memory=False\n",
+    ")\n",
+    "\n",
+    "# Instantiate the model\n",
+    "model = VanillaCNN(num_classes=10)\n",
+    "model.to(device)\n",
+    "\n",
+    "\n",
+    "# Define loss criterion and optimizer\n",
+    "criterion = nn.CrossEntropyLoss()\n",
+    "optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
+    "\n",
+    "#Store the loss and accuracy values\n",
+    "train_loss = []\n",
+    "train_accuracy = []\n",
+    "\n",
+    "# Number of epochs\n",
+    "num_epochs = 20\n",
+    "\n",
+    "# Training Loop\n",
+    "for epoch in range(num_epochs):\n",
+    "    model.train()\n",
+    "    running_loss = 0.0\n",
+    "    \n",
+    "    # Initialize counters at the start of each epoch\n",
+    "    total = 0\n",
+    "    correct = 0\n",
+    "    \n",
+    "    loop = tqdm(train_loader, desc=f\"Epoch [{epoch+1}/{num_epochs}]\")\n",
+    "    \n",
+    "    for images, labels in loop:\n",
+    "        images = images.to(device)\n",
+    "        labels = labels.to(device)\n",
+    "        \n",
+    "        optimizer.zero_grad()\n",
+    "        outputs = model(images)\n",
+    "        loss = criterion(outputs, labels)\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "        \n",
+    "        running_loss += loss.item()\n",
+    "        loop.set_postfix(loss=loss.item())\n",
+    "        \n",
+    "        # Calculate predictions\n",
+    "        _, predicted = torch.max(outputs.data, 1)\n",
+    "        \n",
+    "        # Accumulate total and correct counts\n",
+    "        total += labels.size(0)\n",
+    "        correct += (predicted == labels).sum().item()\n",
+    "    \n",
+    "    # Calculate accuracy\n",
+    "    accuracy = 100 * correct / total\n",
+    "    \n",
+    "    # Calculate average loss\n",
+    "    avg_loss = running_loss / len(train_loader)\n",
+    "    \n",
+    "    # Store loss and accuracy\n",
+    "    train_loss.append(avg_loss)\n",
+    "    train_accuracy.append(accuracy)\n",
+    "    \n",
+    "    # Print epoch summary\n",
+    "    print(f\"Epoch [{epoch+1}/{num_epochs}], Average Loss: {avg_loss:.4f}, Accuracy: {accuracy:.2f}%\")\n",
+    "\n",
+    "# Evaluation Loop\n",
+    "model.eval()\n",
+    "correct = 0\n",
+    "total = 0\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    for images, labels in tqdm(test_loader, desc=\"Evaluating\"):\n",
+    "        images = images.to(device)\n",
+    "        labels = labels.to(device)\n",
+    "        outputs = model(images)\n",
+    "        _, predicted = torch.max(outputs.data, 1)\n",
+    "        total += labels.size(0)\n",
+    "        correct += (predicted == labels).sum().item()\n",
+    "\n",
+    "accuracy = 100 * correct / total\n",
+    "print(f\"Test Accuracy: {accuracy:.2f}%\")\n",
+    "\n",
+    "# Save the model\n",
+    "torch.save(model.state_dict(), 'fashion_mnistVanilla_cnn.pth')\n",
+    "print(\"fashion_mnistVanilla_cnn.pth\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Plot the training curves\n",
+    "plt.figure(figsize=(12,5))\n",
+    "plt.subplot(1,2,1)\n",
+    "plt.plot(train_loss, label='Training Loss',  color='purple')\n",
+    "plt.title(\"Training Loss - Vanilla CNN\")\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.subplot(1,2,2)\n",
+    "plt.plot(train_accuracy, label='Training Accuracy', color='green')\n",
+    "plt.title(\"Training Accuracy - Vanilla CNN\")\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend()\n",
+    "plt.tight_layout()\n",
+    "plt.savefig('fashion_mnist_cnnVanilla_training_curves.jpeg', dpi = 600)\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "MPS device is available and will be used.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [1/20]: 100%|██████████| 1875/1875 [00:17<00:00, 104.51it/s, loss=0.454]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [1/20], Average Loss: 0.5568, Accuracy: 81.50%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [2/20]: 100%|██████████| 1875/1875 [00:20<00:00, 92.87it/s, loss=0.421]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [2/20], Average Loss: 0.3576, Accuracy: 87.15%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [3/20]: 100%|██████████| 1875/1875 [00:20<00:00, 90.65it/s, loss=0.424]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [3/20], Average Loss: 0.3212, Accuracy: 88.29%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [4/20]: 100%|██████████| 1875/1875 [00:22<00:00, 83.67it/s, loss=0.437]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [4/20], Average Loss: 0.3008, Accuracy: 89.01%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [5/20]: 100%|██████████| 1875/1875 [00:19<00:00, 95.34it/s, loss=0.191]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [5/20], Average Loss: 0.2845, Accuracy: 89.62%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [6/20]: 100%|██████████| 1875/1875 [00:19<00:00, 98.51it/s, loss=0.3]    \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [6/20], Average Loss: 0.2722, Accuracy: 90.00%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [7/20]: 100%|██████████| 1875/1875 [00:18<00:00, 98.71it/s, loss=0.171]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [7/20], Average Loss: 0.2619, Accuracy: 90.30%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [8/20]: 100%|██████████| 1875/1875 [00:19<00:00, 95.97it/s, loss=0.431]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [8/20], Average Loss: 0.2559, Accuracy: 90.57%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [9/20]: 100%|██████████| 1875/1875 [00:20<00:00, 92.82it/s, loss=0.245]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [9/20], Average Loss: 0.2491, Accuracy: 90.81%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [10/20]: 100%|██████████| 1875/1875 [00:20<00:00, 92.72it/s, loss=0.124]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [10/20], Average Loss: 0.2422, Accuracy: 91.14%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [11/20]: 100%|██████████| 1875/1875 [00:20<00:00, 91.04it/s, loss=0.21]   \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [11/20], Average Loss: 0.2360, Accuracy: 91.30%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [12/20]: 100%|██████████| 1875/1875 [00:21<00:00, 86.90it/s, loss=0.537]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [12/20], Average Loss: 0.2328, Accuracy: 91.49%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [13/20]: 100%|██████████| 1875/1875 [00:21<00:00, 89.06it/s, loss=0.291]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [13/20], Average Loss: 0.2270, Accuracy: 91.68%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [14/20]: 100%|██████████| 1875/1875 [00:19<00:00, 94.47it/s, loss=0.256]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [14/20], Average Loss: 0.2237, Accuracy: 91.76%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [15/20]: 100%|██████████| 1875/1875 [00:19<00:00, 93.93it/s, loss=0.304]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [15/20], Average Loss: 0.2168, Accuracy: 92.01%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [16/20]: 100%|██████████| 1875/1875 [00:19<00:00, 96.95it/s, loss=0.328]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [16/20], Average Loss: 0.2165, Accuracy: 92.01%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [17/20]: 100%|██████████| 1875/1875 [00:19<00:00, 94.85it/s, loss=0.198]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [17/20], Average Loss: 0.2112, Accuracy: 92.18%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [18/20]: 100%|██████████| 1875/1875 [00:19<00:00, 94.27it/s, loss=0.224]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [18/20], Average Loss: 0.2088, Accuracy: 92.24%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [19/20]: 100%|██████████| 1875/1875 [00:20<00:00, 91.63it/s, loss=0.138]  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [19/20], Average Loss: 0.2033, Accuracy: 92.58%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Epoch [20/20]: 100%|██████████| 1875/1875 [00:19<00:00, 94.24it/s, loss=0.0575] \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch [20/20], Average Loss: 0.2029, Accuracy: 92.44%\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Evaluating: 100%|██████████| 313/313 [00:02<00:00, 127.25it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test Accuracy: 90.72%\n",
+      "Model saved to fashion_mnist_cnn.pth\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from torchvision import datasets, transforms\n",
+    "from torch.utils.data import DataLoader\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "# Define the CNN Model\n",
+    "import torch.nn as nn\n",
+    "import torch.nn.functional as F\n",
+    "\n",
+    "class FashionMNISTCNN(nn.Module):\n",
+    "    def __init__(self, num_classes=10):\n",
+    "        super(FashionMNISTCNN, self).__init__()\n",
+    "        \n",
+    "        # First Convolutional Layer\n",
+    "        self.conv1 = nn.Conv2d(in_channels=1, out_channels=8, kernel_size=5, padding=2, stride=2)\n",
+    "        self.bn1 = nn.BatchNorm2d(8)  # BatchNorm after conv1\n",
+    "        \n",
+    "        # Second Convolutional Layer\n",
+    "        self.conv2 = nn.Conv2d(in_channels=8, out_channels=16, kernel_size=3, padding=1, stride=2)\n",
+    "        self.bn2 = nn.BatchNorm2d(16)  # BatchNorm after conv2\n",
+    "        \n",
+    "        # Third Convolutional Layer\n",
+    "        self.conv3 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, padding=1, stride=2)\n",
+    "        self.bn3 = nn.BatchNorm2d(32)  # BatchNorm after conv3\n",
+    "        \n",
+    "        # Fourth Convolutional Layer\n",
+    "        self.conv4 = nn.Conv2d(in_channels=32, out_channels=32, kernel_size=3, padding=1, stride=2)\n",
+    "        self.bn4 = nn.BatchNorm2d(32)  # BatchNorm after conv4\n",
+    "        \n",
+    "        # Adaptive Average Pooling Layer\n",
+    "        self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))\n",
+    "        \n",
+    "        # Fully Connected Layer\n",
+    "        self.fc = nn.Linear(32, num_classes)\n",
+    "        \n",
+    "    def forward(self, x):\n",
+    "        # First Conv Layer + BatchNorm + ReLU\n",
+    "        x = self.conv1(x)\n",
+    "        x = self.bn1(x)\n",
+    "        x = F.relu(x)\n",
+    "        \n",
+    "        # Second Conv Layer + BatchNorm + ReLU\n",
+    "        x = self.conv2(x)\n",
+    "        x = self.bn2(x)\n",
+    "        x = F.relu(x)\n",
+    "        \n",
+    "        # Third Conv Layer + BatchNorm + ReLU\n",
+    "        x = self.conv3(x)\n",
+    "        x = self.bn3(x)\n",
+    "        x = F.relu(x)\n",
+    "        \n",
+    "        # Fourth Conv Layer + BatchNorm + ReLU\n",
+    "        x = self.conv4(x)\n",
+    "        x = self.bn4(x)\n",
+    "        x = F.relu(x)\n",
+    "        \n",
+    "        # Adaptive Average Pooling\n",
+    "        x = self.avg_pool(x)  # Shape: [batch_size, 32, 1, 1]\n",
+    "        \n",
+    "        # Flatten the tensor\n",
+    "        x = x.view(x.size(0), -1)  # Shape: [batch_size, 32]\n",
+    "        \n",
+    "        # Fully Connected Layer\n",
+    "        x = self.fc(x)  # Shape: [batch_size, num_classes]\n",
+    "        \n",
+    "        return x\n",
+    "\n",
+    "# Define device\n",
+    "if torch.backends.mps.is_available():\n",
+    "    device = torch.device(\"mps\")\n",
+    "    print(\"MPS device is available and will be used.\")\n",
+    "elif torch.cuda.is_available():\n",
+    "    device = torch.device(\"cuda\")\n",
+    "    print(\"CUDA device is available and will be used.\")\n",
+    "else:\n",
+    "    device = torch.device(\"cpu\")\n",
+    "    print(\"No GPU found. Using CPU.\")\n",
+    "\n",
+    "# # Define transformations\n",
+    "# train_transform = transforms.Compose([\n",
+    "#     transforms.RandomHorizontalFlip(),\n",
+    "#     transforms.ToTensor(),\n",
+    "#     transforms.Normalize((0.5,), (0.5,))  # Normalize to [-1, 1]\n",
+    "# ])\n",
+    "\n",
+    "# test_transform = transforms.Compose([\n",
+    "#     transforms.ToTensor(),\n",
+    "#     transforms.Normalize((0.5,), (0.5,))\n",
+    "# ])\n",
+    "\n",
+    "# Download and create datasets\n",
+    "train_dataset = datasets.FashionMNIST(\n",
+    "    root='./data', \n",
+    "    train=True, \n",
+    "    download=True, \n",
+    "    transform=train_transform\n",
+    ")\n",
+    "test_dataset = datasets.FashionMNIST(\n",
+    "    root='./data', \n",
+    "    train=False, \n",
+    "    download=True, \n",
+    "    transform=test_transform\n",
+    ")\n",
+    "\n",
+    "# Create DataLoaders\n",
+    "train_loader = DataLoader(\n",
+    "    train_dataset, \n",
+    "    batch_size=32, \n",
+    "    shuffle=True, \n",
+    "    num_workers=2, \n",
+    "    pin_memory=False  # Set to False for MPS\n",
+    ")\n",
+    "test_loader = DataLoader(\n",
+    "    test_dataset, \n",
+    "    batch_size=32, \n",
+    "    shuffle=False, \n",
+    "    num_workers=2, \n",
+    "    pin_memory=False\n",
+    ")\n",
+    "\n",
+    "# Instantiate the model\n",
+    "model = FashionMNISTCNN(num_classes=10)\n",
+    "model.to(device)\n",
+    "\n",
+    "\n",
+    "# Define loss criterion and optimizer\n",
+    "criterion = nn.CrossEntropyLoss()\n",
+    "optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
+    "\n",
+    "#Store the loss and accuracy values\n",
+    "train_loss = []\n",
+    "train_accuracy = []\n",
+    "\n",
+    "# Number of epochs\n",
+    "num_epochs = 20\n",
+    "\n",
+    "# Training Loop\n",
+    "for epoch in range(num_epochs):\n",
+    "    model.train()\n",
+    "    running_loss = 0.0\n",
+    "    \n",
+    "    # Initialize counters at the start of each epoch\n",
+    "    total = 0\n",
+    "    correct = 0\n",
+    "    \n",
+    "    loop = tqdm(train_loader, desc=f\"Epoch [{epoch+1}/{num_epochs}]\")\n",
+    "    \n",
+    "    for images, labels in loop:\n",
+    "        images = images.to(device)\n",
+    "        labels = labels.to(device)\n",
+    "        \n",
+    "        optimizer.zero_grad()\n",
+    "        outputs = model(images)\n",
+    "        loss = criterion(outputs, labels)\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "        \n",
+    "        running_loss += loss.item()\n",
+    "        loop.set_postfix(loss=loss.item())\n",
+    "        \n",
+    "        # Calculate predictions\n",
+    "        _, predicted = torch.max(outputs.data, 1)\n",
+    "        \n",
+    "        # Accumulate total and correct counts\n",
+    "        total += labels.size(0)\n",
+    "        correct += (predicted == labels).sum().item()\n",
+    "    \n",
+    "    # Calculate accuracy\n",
+    "    accuracy = 100 * correct / total\n",
+    "    \n",
+    "    # Calculate average loss\n",
+    "    avg_loss = running_loss / len(train_loader)\n",
+    "    \n",
+    "    # Store loss and accuracy\n",
+    "    train_loss.append(avg_loss)\n",
+    "    train_accuracy.append(accuracy)\n",
+    "    \n",
+    "    # Print epoch summary\n",
+    "    print(f\"Epoch [{epoch+1}/{num_epochs}], Average Loss: {avg_loss:.4f}, Accuracy: {accuracy:.2f}%\")\n",
+    "\n",
+    "# Evaluation Loop\n",
+    "model.eval()\n",
+    "correct = 0\n",
+    "total = 0\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    for images, labels in tqdm(test_loader, desc=\"Evaluating\"):\n",
+    "        images = images.to(device)\n",
+    "        labels = labels.to(device)\n",
+    "        outputs = model(images)\n",
+    "        _, predicted = torch.max(outputs.data, 1)\n",
+    "        total += labels.size(0)\n",
+    "        correct += (predicted == labels).sum().item()\n",
+    "\n",
+    "accuracy = 100 * correct / total\n",
+    "print(f\"Test Accuracy: {accuracy:.2f}%\")\n",
+    "\n",
+    "# Save the model\n",
+    "torch.save(model.state_dict(), 'fashion_mnist_cnn.pth')\n",
+    "print(\"Model saved to fashion_mnist_cnn.pth\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABKUAAAHqCAYAAADVi/1VAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAACmwklEQVR4nOzdd3yN9/vH8ddJQhIjsSNWErX3JvYqpdSsVSktRdFSWqT2Kjo0RVGt2jVa1foVtWcpNaul2qotSpHEjEju3x/3N4dIEETuc5L38/G4H+fc49znuo+4c+c61+e6bYZhGIiIiIiIiIiIiCQjF6sDEBERERERERGR1EdJKRERERERERERSXZKSomIiIiIiIiISLJTUkpERERERERERJKdklIiIiIiIiIiIpLslJQSEREREREREZFkp6SUiIiIiIiIiIgkOyWlREREREREREQk2SkpJSIiIiIiIiIiyU5JKRFJcjabLVHTpk2bnuh9RowYgc1me6zXbtq0KUlieJL3/uabb5L9vUVEROTR6dom8ZYvX47NZiNr1qxERkZaGouIOD43qwMQkZRnx44dceZHjx7Nxo0b2bBhQ5zlxYoVe6L36dq1K88999xjvbZcuXLs2LHjiWMQERGRlE/XNok3c+ZMAC5dusR3331H27ZtLY1HRBybklIikuSqVKkSZz579uy4uLjEW36v69evky5dukS/T548eciTJ89jxejl5fXQeERERERA1zaJde7cOVauXEndunXZvn07M2fOdNik1KP+24jI06HheyJiidq1a1OiRAm2bNlC1apVSZcuHa+++ioAixcvpkGDBvj6+uLp6UnRokUZNGgQ165di7OPhErc/f39adKkCT/++CPlypXD09OTIkWK8OWXX8bZLqES986dO5MhQwb+/vtvGjduTIYMGcibNy/9+/ePV35++vRpWrduTcaMGcmUKRMvvfQSv/zyCzabjdmzZyfJZ/Tbb7/RrFkzMmfOjIeHB2XKlGHOnDlxtomJiWHMmDEULlwYT09PMmXKRKlSpfjkk0/s21y4cIFu3bqRN29e3N3dyZ49O9WqVWPdunVJEqeIiIjo2gZgzpw53L59m7feeouWLVuyfv16Tpw4EW+7sLAw+vfvT/78+XF3dydHjhw0btyYP/74w75NZGQko0aNomjRonh4eJA1a1bq1KnD9u3bATh+/Ph9Y7PZbIwYMSLe57p3715at25N5syZeeaZZwDYvXs37dq1w9/fH09PT/z9/Wnfvn2CcZ85c8Z+TZU2bVpy5cpF69at+ffff7l69SqZMmWie/fu8V53/PhxXF1d+eCDDxL1OYqkJqqUEhHLhIaG0rFjRwYMGMB7772Hi4uZJ//rr79o3Lgxffv2JX369Pzxxx9MmDCBXbt2xSuTT8iBAwfo378/gwYNwsfHhy+++IIuXbpQoEABatas+cDXRkVF8cILL9ClSxf69+/Pli1bGD16NN7e3gwbNgyAa9euUadOHS5dusSECRMoUKAAP/74Y5J+E3jkyBGqVq1Kjhw5mDRpElmzZmX+/Pl07tyZf//9lwEDBgDw/vvvM2LECIYMGULNmjWJiorijz/+ICwszL6voKAg9u7dy9ixYylUqBBhYWHs3buXixcvJlm8IiIiomubL7/8El9fXxo1aoSnpydfffUVs2fPZvjw4fZtrly5QvXq1Tl+/DgDBw6kcuXKXL16lS1bthAaGkqRIkW4ffs2jRo1YuvWrfTt25e6dety+/Ztfv75Z06ePEnVqlUfKa5YLVu2pF27dvTo0cOeEDx+/DiFCxemXbt2ZMmShdDQUKZNm0bFihU5dOgQ2bJlA8yEVMWKFYmKiuLdd9+lVKlSXLx4kdWrV3P58mV8fHx49dVXmTFjBu+//z7e3t729506dSpp06a1JylF5C6GiMhT1qlTJyN9+vRxltWqVcsAjPXr1z/wtTExMUZUVJSxefNmAzAOHDhgXzd8+HDj3tOYn5+f4eHhYZw4ccK+7MaNG0aWLFmM7t2725dt3LjRAIyNGzfGiRMwlixZEmefjRs3NgoXLmyf//TTTw3AWLVqVZztunfvbgDGrFmzHnhMse/99ddf33ebdu3aGe7u7sbJkyfjLG/UqJGRLl06IywszDAMw2jSpIlRpkyZB75fhgwZjL59+z5wGxEREUk8XdvEt2XLFgMwBg0aZD/OgIAAw8/Pz4iJibFvN2rUKAMw1q5de999zZ071wCMzz///L7bHDt27L6xAcbw4cPt87Gf67Bhwx56HLdv3zauXr1qpE+f3vjkk0/sy1999VUjTZo0xqFDh+772qNHjxouLi7Gxx9/bF9248YNI2vWrMYrr7zy0PcWSY00fE9ELJM5c2bq1q0bb/k///xDhw4dyJkzJ66urqRJk4ZatWoBcPjw4Yfut0yZMuTLl88+7+HhQaFChRIsw76XzWajadOmcZaVKlUqzms3b95MxowZ4zUibd++/UP3n1gbNmygXr165M2bN87yzp07c/36dXvD1UqVKnHgwAF69uzJ6tWriYiIiLevSpUqMXv2bMaMGcPPP/9MVFRUksUpIiIid6Tma5vYBuex1UA2m43OnTtz4sQJ1q9fb99u1apVFCpUiPr16993X6tWrcLDwyPJK4tatWoVb9nVq1cZOHAgBQoUwM3NDTc3NzJkyMC1a9fi/NusWrWKOnXqULRo0fvuP3/+/DRp0oSpU6diGAYAX331FRcvXqR3795JeiwiKYWSUiJiGV9f33jLrl69So0aNdi5cydjxoxh06ZN/PLLL3z77bcA3Lhx46H7zZo1a7xl7u7uiXptunTp8PDwiPfamzdv2ucvXryIj49PvNcmtOxxXbx4McHPJ1euXPb1AMHBwXz44Yf8/PPPNGrUiKxZs1KvXj12795tf83ixYvp1KkTX3zxBYGBgWTJkoWXX36Zc+fOJVm8IiIiknqvba5cucLXX39NpUqVyJ49O2FhYYSFhdGiRQtsNps9YQVmr8uHNXO/cOECuXLlsg9/TCoJ/ft06NCBKVOm0LVrV1avXs2uXbv45ZdfyJ49e5zPNzFxA/Tp04e//vqLtWvXAvDpp58SGBhIuXLlku5ARFIQ9ZQSEcvc28gTzAqhs2fPsmnTJvs3iECcHklWy5o1K7t27Yq3PCmTPFmzZiU0NDTe8rNnzwLY+xu4ubnRr18/+vXrR1hYGOvWrePdd9+lYcOGnDp1inTp0pEtWzZCQkIICQnh5MmTLF++nEGDBnH+/Hl+/PHHJItZREQktUut1zYLFy7k+vXr7Nq1i8yZM8dbv2zZMi5fvkzmzJnJnj07p0+ffuD+smfPzrZt24iJiblvYio20XZvw/YH9cy8998nPDycH374geHDhzNo0CD78sjISC5duhQvpofFDVC3bl1KlCjBlClTyJAhA3v37mX+/PkPfZ1IaqVKKRFxKLEXC+7u7nGWf/bZZ1aEk6BatWpx5coVVq1aFWf5okWLkuw96tWrZ7+IvdvcuXNJly5dgrd8zpQpE61bt6ZXr15cunSJ48ePx9smX7589O7dm2effZa9e/cmWbwiIiKSsNRwbTNz5kwyZszI+vXr2bhxY5zpgw8+IDIykgULFgDQqFEj/vzzzwc2eG/UqBE3b9584F3/fHx88PDw4Ndff42z/Pvvv09UzGD+2xiGEe/f5osvviA6OjpeTBs3buTIkSMP3e+bb77JihUrCA4OxsfHhxdffDHRMYmkNqqUEhGHUrVqVTJnzkyPHj0YPnw4adKkYcGCBRw4cMDq0Ow6derExx9/TMeOHRkzZgwFChRg1apVrF69GiDRpeY///xzgstr1arF8OHD+eGHH6hTpw7Dhg0jS5YsLFiwgBUrVsS5o0vTpk0pUaIEFSpUIHv27Jw4cYKQkBD8/PwoWLAg4eHh1KlThw4dOlCkSBEyZszIL7/8wo8//kjLli2T5gMRERGR+0rp1za//fYbu3bt4vXXX0+wn1a1atX46KOPmDlzJr1796Zv374sXryYZs2aMWjQICpVqsSNGzfYvHkzTZo0oU6dOrRv355Zs2bRo0cPjhw5Qp06dYiJiWHnzp0ULVqUdu3aYbPZ6NixI19++SXPPPMMpUuXZteuXXz11VeJPm4vLy9q1qzJBx98QLZs2fD392fz5s3MnDmTTJkyxdl21KhRrFq1ipo1a/Luu+9SsmRJwsLC+PHHH+nXrx9FihSxb9uxY0eCg4PZsmULQ4YMIW3atImOSSS1UVJKRBxK1qxZWbFiBf3796djx46kT5+eZs2asXjxYocZi58+fXo2bNhA3759GTBgADabjQYNGjB16lQaN24c7yLmfj766KMEl2/cuJHatWuzfft23n33XXr16sWNGzcoWrQos2bNonPnzvZt69Spw9KlS/niiy+IiIggZ86cPPvsswwdOpQ0adLg4eFB5cqVmTdvHsePHycqKop8+fIxcOBABgwYkASfhoiIiDxISr+2ie0X1b179wTXp0mThs6dOzN+/Hj27t1LuXLl2LZtGyNGjGDGjBmMHDmSzJkzU7FiRbp16waY7QlWrlzJuHHjWLhwISEhIWTMmJHSpUvHacYeey31/vvvc/XqVerWrcsPP/yAv79/oo/9q6++ok+fPgwYMIDbt29TrVo11q5dy/PPPx9nu9y5c7Nr1y6GDx/O+PHjuXjxItmzZ6d69epkyZIlzraenp40bdqU+fPn06NHj0THIpIa2YzY2wKIiMgTee+99xgyZAgnT55MVCNMEREREUema5vHc+vWLfz9/alevTpLliyxOhwRh6ZKKRGRxzBlyhQAihQpQlRUFBs2bGDSpEl07NhRF20iIiLidHRt8+QuXLjAkSNHmDVrFv/++2+c5ukikjAlpUREHkO6dOn4+OOPOX78OJGRkfYhcUOGDLE6NBEREZFHpmubJ7dixQpeeeUVfH19mTp1qsMMzxRxZBq+JyIiIiIiIiIiyS5xt4gSERERERERERFJQkpKiYiIiIiIiIhIslNSSkREREREREREkp0anScgJiaGs2fPkjFjRmw2m9XhiIiIiAMyDIMrV66QK1cuXFxSz/d8uk4SERGRh0nsdZKSUgk4e/YsefPmtToMERERcQKnTp1KVbdL13WSiIiIJNbDrpOUlEpAxowZAfPD8/LysjgaERERcUQRERHkzZvXft2QWug6SURERB4msddJSkolILYU3cvLSxdbIiIi8kCpbQibrpNEREQksR52nZR6GiCIiIiIiIiIiIjDUFJKRERERERERESSnZJSIiIiIiIiIiKS7NRTSkQkCUVHRxMVFWV1GCKSBNKkSYOrq6vVYTgtnQ9FJCnpnCySMikpJSKSBAzD4Ny5c4SFhVkdiogkoUyZMpEzZ85U18z8Seh8KCJPi87JIimPklIiIkkg9g+wHDlykC5dOl0siTg5wzC4fv0658+fB8DX19fiiJyHzociktR0ThZJuZSUEhF5QtHR0fY/wLJmzWp1OCKSRDw9PQE4f/48OXLk0LCRRND5UESeFp2TRVImNToXEXlCsT1T0qVLZ3EkIpLUYv9fqzdS4uh8KCJPk87JIimPklIiIklEQ1REUh79v348+txE5GnQuUUk5VFSSkREREREREREkp2SUiIikqRq165N3759E7398ePHsdls7N+//6nFJPfn7+9PSEiIfd5ms/Hdd9/Z5//44w+qVKmCh4cHZcqUSbJ/r0f9ORFxRjofyqPq3LkzzZs3t8/f+zN0/fp1WrVqhZeXFzabjbCwsHjn8ccxYsQIypQp80T7EBF5HEpKiYikUjab7YFT586dH2u/3377LaNHj0709nnz5iU0NJQSJUo81vsllrP9sbdp0yZsNhuZM2fm5s2bcdbt2rXL/u+U1EJDQ2nUqJF9fvjw4aRPn54jR46wfv36ZPv3Arh16xbvv/8+pUuXJl26dGTLlo1q1aoxa9Ysez+Rzp07Y7PZGD9+fJzXfvfdd3E+n9jPs0SJEkRHR8fZNlOmTMyePfupH484rtR2PrxbgwYNcHV15eeff06293RWsT8P935WkZGRZM2aFZvNxqZNm5L0Pe/9GZozZw5bt25l+/bthIaG4u3tzS+//EK3bt2S9H3vZ+nSpdSuXRtvb28yZMhAqVKlGDVqFJcuXQJg9uzZ2Gw2nnvuuTivCwsLi/f52Gw2PDw8OHHiRJxtmzdv/tj/50TE+SgpJSKSSoWGhtqnkJAQvLy84iz75JNP4myf2KaiWbJkIWPGjImOw9XVlZw5c+LmphvCJiRjxowsW7YszrIvv/ySfPnyPZX3y5kzJ+7u7vb5o0ePUr16dfz8/MiaNWuy/XvdunWLhg0bMn78eLp168b27dvZtWsXvXr1YvLkyfz+++/2bT08PJgwYQKXL19+6H6PHj3K3Llzn2bo4oRS6/nw5MmT7Nixg969ezNz5sxkec8HcYbm1Xnz5mXWrFlxli1btowMGTI8lfe792fo6NGjFC1alBIlSpAzZ05sNhvZs2dPlpsLDB48mLZt21KxYkVWrVrFb7/9xkcffcSBAweYN2+efTs3NzfWr1/Pxo0bH7pPm83GsGHDnmbYIuLglJQSEUmlcubMaZ+8vb2x2Wz2+Zs3b5IpUyaWLFlC7dq18fDwYP78+Vy8eJH27duTJ08e0qVLR8mSJVm4cGGc/d471MDf35/33nuPV199lYwZM5IvXz5mzJhhX39vBVNsRcv69eupUKEC6dKlo2rVqhw5ciTO+4wZM4YcOXKQMWNGunbtyqBBg55o6EFkZCRvvvkmOXLkwMPDg+rVq/PLL7/Y11++fJmXXnqJ7Nmz4+npScGCBe1/mNy6dYvevXvj6+uLh4cH/v7+jBs37rFjuVunTp348ssv7fM3btxg0aJFdOrUKd62S5cupXjx4ri7u+Pv789HH30UZ/358+dp2rQpnp6eBAQEsGDBgnj7uHv4ns1mY8+ePYwaNQqbzcaIESMSrDg7dOgQjRs3JkOGDPj4+BAUFMR///1nX3/t2jVefvllMmTIgK+vb7y4EhISEsKWLVtYv349vXr1okyZMuTPn58OHTqwc+dOChYsaN+2fv365MyZM1Gf+RtvvMHw4cPjVZ9J6pZaz4ezZs2iSZMmvP766yxevJhr167FWR8WFka3bt3w8fHBw8ODEiVK8MMPP9jX//TTT9SqVYt06dKROXNmGjZsaE8OJzSkrEyZMowYMcI+b7PZmD59Os2aNSN9+vSMGTOG6OhounTpQkBAAJ6enhQuXDheUhDM5Hzs+c7X15fevXsD8Oqrr9KkSZM4296+fZucOXPGOZc+rk6dOrFo0SJu3LgRJ5aEzskHDx6kbt26eHp6kjVrVrp168bVq1ft66Ojo+nXrx+ZMmUia9asDBgwAMMw4uzj7p+h2rVr89FHH7FlyxZsNhu1a9cG4n/W4eHhdOvWjRw5cuDl5UXdunU5cOBAnP2OHz8eHx8fMmbMSJcuXR56Tty1axfvvfceH330ER988AFVq1bF39+fZ599lqVLl8Y5/vTp0/PKK68waNCgB+4TzHPy/PnzOXjw4EO3FZGUSUmp5BYTAwcPwooV5nMRSZkMA65ds2a654L2SQwcOJA333yTw4cP07BhQ27evEn58uX54Ycf+O233+jWrRtBQUHs3Lnzgfv56KOPqFChAvv27aNnz568/vrr/PHHHw98zeDBg/noo4/YvXs3bm5uvPrqq/Z1CxYsYOzYsUyYMIE9e/aQL18+pk2b9kTHOmDAAJYuXcqcOXPYu3cvBQoUoGHDhvYhCUOHDuXQoUOsWrWKw4cPM23aNLJlywbApEmTWL58OUuWLOHIkSPMnz8ff3//J4onVlBQEFu3buXkyZOAmXjy9/enXLlycbbbs2cPbdq0oV27dhw8eJARI0YwdOjQOMPSOnfuzPHjx9mwYQPffPMNU6dO5fz58/d979DQUIoXL07//v0JDQ3l7bffTnCbWrVqUaZMGXbv3s2PP/7Iv//+S5s2bezbvPPOO2zcuJFly5axZs0aNm3axJ49ex543AsWLKB+/fqULVs23ro0adKQPn16+7yrqyvvvfcekydP5vTp0w/cb9++fbl9+zZTpkx54HaSdKw6HSbhqRBIeedDwzCYNWsWHTt2pEiRIhQqVIglS5bY18fExNCoUSO2b9/O/PnzOXToEOPHj8fV1RWA/fv3U69ePYoXL86OHTvYtm0bTZs2jTc89mGGDx9Os2bNOHjwIK+++ioxMTHkyZOHJUuWcOjQIYYNG8a7774bJ7Zp06bRq1cvunXrxsGDB1m+fDkFChQAoGvXrvz444+Ehobat1+5ciVXr16Nc156XOXLlycgIIClS5cCcOrUKbZs2UJQUFCc7a5fv85zzz1H5syZ+eWXX/j6669Zt26dPXkG5s/Cl19+ycyZM9m2bRuXLl2KVxl7t2+//ZbXXnuNwMBAQkND+fbbb+NtYxgGzz//POfOnWPlypXs2bOHcuXKUa9ePfvvsyVLljB8+HDGjh3L7t278fX1ZerUqQ887gULFpAhQwZ69uyZ4PpMmTLFmR8xYgQHDx7km2++eeB+q1atSpMmTQgODn7gdiKS9E6fhq+/htu3LQ7EkHjCw8MNwAgPD0/6nUdFGYaLi2GAYZw5k/T7F5Fkd+PGDePQoUPGjRs37iy8etX8f27FdPXqIx/DrFmzDG9vb/v8sWPHDMAICQl56GsbN25s9O/f3z5fq1Yto0+fPvZ5Pz8/o2PHjvb5mJgYI0eOHMa0adPivNe+ffsMwzCMjRs3GoCxbt06+2tWrFhhAPbPuHLlykavXr3ixFGtWjWjdOnS943z3ve529WrV400adIYCxYssC+7deuWkStXLuP99983DMMwmjZtarzyyisJ7vuNN94w6tata8TExNz3/R9V7Odw+fJlo3nz5sbIkSMNwzCMOnXqGJ988omxbNky4+5f4x06dDCeffbZOPt45513jGLFihmGYRhHjhwxAOPnn3+2rz98+LABGB9//LF9GWAsW7bMPl+6dGlj+PDh9vl7P8ehQ4caDRo0iPO+p06dMgDjyJEjxpUrV4y0adMaixYtsq+/ePGi4enpGefn5F6enp7Gm2+++cDPyDAMo1OnTkazZs0MwzCMKlWqGK+++qphGEa8z+fuz3P69OlGlixZjLCwMMMwDMPb29uYNWtWgvtP8P/3/zzV6wUH9qDjTujzsup0+BinQsMwUsf50DAMY82aNUb27NmNqKgowzAM4+OPPzaqVatmX7969WrDxcXFOHLkSIKvb9++fZzt7+Xn5xfn3GIY8c8ngNG3b98HxmkYhtGzZ0+jVatW9vlcuXIZgwcPvu/2xYoVMyZMmGCfb968udG5c+eHvs/DxJ4fQ0JCjDp16hiGYRgjR440WrRoYVy+fNkAjI0bNxqGYRgzZswwMmfObFy96wdxxYoVhouLi3Hu3DnDMAzD19fXGD9+vH19VFSUkSdPHvs5zTDi/wz16dPHqFWrVpy47v6s169fb3h5eRk3b96Ms80zzzxjfPbZZ4ZhGEZgYKDRo0ePOOsrV678wJ+ZRo0aGaVKlbrv+lh3//8ZNGiQUahQISMqKire52MYdz7P33//3XB1dTW2bNliGIZhNGvWzOjUqVOC+3/QOVlE7i8y0jB+/tkwPv7YMF580TDy5Lnz+zKBS+MkkdjrJFVKJTc3N8id23z+v2+9RUQcVYUKFeLMR0dHM3bsWEqVKkXWrFnJkCEDa9assVfx3E+pUqXsz2OHxTyoQufe1/j6+gLYX3PkyBEqVaoUZ/t75x/F0aNHiYqKolq1avZladKkoVKlShw+fBiA119/nUWLFlGmTBkGDBjA9u3b7dt27tyZ/fv3U7hwYd58803WrFlz3/faunUrGTJksE8JDaG716uvvsrs2bP5559/2LFjBy+99FK8bQ4fPhwnfoBq1arx119/ER0dzeHDh3Fzc4vzb1qkSJF4324/qj179rBx48Y4x1SkSBHA/FyPHj3KrVu3CAwMtL8mS5YsFC5c+IH7NQzjkRu5T5gwgTlz5nDo0KEHbtelSxeyZcvGhAkTHmn/zuLKlSv07dsXPz8/PD09qVq1qn0oalRUFAMHDqRkyZKkT5+eXLly8fLLL3P27FmLo3Z8Ke18OHPmTNq2bWvvX9W+fXt27txpHxq4f/9+8uTJQ6FChRJ8fWyl1JO693MFmD59OhUqVCB79uxkyJCBzz//3P65nj9/nrNnzz7wvbt27WofXn3+/HlWrFgRp7rsXnefv3r06PHQmDt27MiOHTv4559/mD17doL7Pnz4MKVLl45T1VmtWjViYmI4cuQI4eHhhIaGxjk33nuOfhx79uzh6tWr9p/J2OnYsWMcPXrUHtvd7wvEm7/X45yTBw4cyIULFx46bLJYsWK8/PLLDBw48JH2LyL3FxoK334L77wD1auDlxdUqQJvvWVWR50+Da6uUK4cXLlibazqKmsFPz84dQpOnDB/MkQk5UmXDu7qG5Hs751E7r6YBnOowccff0xISIj9j9q+ffty69atB+4nTZo0ceZtNhsxDxnCfPdrYi+E737NvRfHxhOM1Yl9bUL7jF3WqFEjTpw4wYoVK1i3bh316tWjV69efPjhh5QrV45jx46xatUq1q1bR5s2bahfv36CwxYqVKgQpx+Tj4/PQ+Nr3Lgx3bt3p0uXLjRt2pSsWbMmeAwP+kzud4xPKiYmhqZNmyaY4PH19eWvv/56rP0WKlTInhBMrJo1a9KwYUPefffdB965yc3NjTFjxtC5c+c4Q2lSiq5du/Lbb78xb948cuXKxfz586lfvz6HDh0iQ4YM7N27l6FDh1K6dGkuX75M3759eeGFF9i9e/dTiceq02FS931OSefDS5cu8d133xEVFRVnqF90dDRffvklEyZMwNPT84H7eNh6FxeXeHEk1Mj83s91yZIlvPXWW3z00UcEBgaSMWNGPvjgA/uwyIe9L8DLL7/MoEGD2LFjBzt27MDf358aNWrcd/u7z8leXl4P3X/WrFlp0qSJvRdTo0aNuHLPX3UPSuI8jTunxoqJicHX1zfBuwA+yZcQhQoVYtu2bURFRcX7Gb6fTJkyERwczMiRI+P1+brXyJEjKVSokL2noYgkXlQU/Por7NgB27ebj8ePx98ua1YIDISqVc3HihXhnlOwJVQpZYXYOyapUkok5bLZzLO8FdNTvNjdunUrzZo1o2PHjpQuXZr8+fM/dtLhSRQuXJhdu3bFWfYkf1AXKFCAtGnTsm3bNvuyqKgodu/eTdGiRe3LsmfPTufOnZk/fz4hISFxGhR7eXnRtm1bPv/8cxYvXszSpUvt/Tvu5unpSYECBexTYu7M5erqSlBQEJs2bbrvt/3FihWLEz/A9u3bKVSoEK6urhQtWpTbt2/H+ZyOHDlCWFjYQ9//QcqVK8fvv/+Ov79/nOMqUKAA6dOnp0CBAqRJkybOLdQvX77Mn3/++cD9dujQgXXr1rFv3754627fvh2vIXOs8ePH83//939xKtkS8uKLL1K8eHFGjhyZiKN0Hjdu3GDp0qW8//771KxZkwIFCjBixAgCAgKYNm0a3t7erF27ljZt2lC4cGGqVKnC5MmT2bNnz0MrfB6XVafDp3gqBJz7fLhgwQLy5MnDgQMH2L9/v30KCQlhzpw53L59m1KlSnH69On7/l8tVaoU69evv+97ZM+ePU5fp4iICI4dO/bQ49m6dStVq1alZ8+elC1blgIFCtgrfMC8I6m/v/8D3ztr1qw0b96cWbNmMWvWLF555ZUHvufd560cOXI8NEYwK1g3bdrEyy+/bO+zdbdixYqxf//+OOeqn376CRcXFwoVKoS3tze+vr5xzo23b99+aL+9hylXrhznzp3Dzc0t3jk5tg9i0aJF47wvEG/+Xh06dODq1av37T11v98lb7zxBi4uLgk2q79b3rx56d27N+++++4j9yUTSW0uXIDlyyE4GGrXBm9vqFAB3ngDFi40E1I2G5QqBd27w+zZ8Oef5uv+7//uvM4RElKgSilr+PmZj0pKiYiTKVCgAEuXLmX79u1kzpyZiRMncu7cuTiJm+Twxhtv8Nprr1GhQgWqVq3K4sWL+fXXX8mfP/9DX3vvXavA/OPh9ddf55133iFLlizky5eP999/n+vXr9OlSxcAhg0bRvny5SlevDiRkZH88MMP9uP++OOP8fX1pUyZMri4uPD111+TM2fOJx4ad7fRo0fzzjvvJFglBdC/f38qVqzI6NGjadu2LTt27GDKlCn2PyAKFy7Mc889x2uvvcaMGTNwc3Ojb9++iao6eJBevXrx+eef0759e9555x2yZcvG33//zaJFi/j888/JkCEDXbp0scfu4+PD4MGDcXF58Pdiffv2ZcWKFdSrV4/Ro0dTvXp1MmbMyO7du5kwYQIzZ85M8O5iJUuW5KWXXmLy5MkPjX38+PE0bNjwcQ/dId2+fZvo6Gg8PDziLPf09IyXtIwVHh6OzWa7789rZGQkkZGR9vmIiIgki9eZOfP5cObMmbRu3ZoSJUrEWe7n58fAgQNZsWIFzZo1o2bNmrRq1YqJEydSoEAB/vjjD2w2G8899xzBwcGULFmSnj170qNHD9KmTcvGjRt58cUXyZYtG3Xr1mX27Nk0bdqUzJkzM3To0ASTN/cqUKAAc+fOZfXq1QQEBDBv3jx++eUXAgIC7NuMGDGCHj16kCNHDnuV0k8//cQbb7xh36Zr1640adKE6OjoBO+M96See+45Lly4cN/Kqpdeeonhw4fTqVMnRowYwYULF3jjjTcICgqyV8j26dOH8ePHU7BgQYoWLcrEiROf+IuC+vXrExgYSPPmzZkwYQKFCxfm7NmzrFy5kubNm1OhQgX69OlDp06dqFChAtWrV2fBggX8/vvvD/yZqVy5MgMGDKB///6cOXOGFi1akCtXLv7++2+mT59O9erV6dOnT7zXeXh4MHLkSHr16vXQ2IODg/n88885duwYbdu2faLPQSSliI6G3367UwG1Ywf8/Xf87TJlMqufYqdKlcwhe87A8kqpqVOnEhAQgIeHB+XLl2fr1q333Tb2trj3TnffsWT27NkJbuNQt36OrZQ6ccLaOEREHtHQoUMpV64cDRs2pHbt2uTMmZPmzZsnexwvvfQSwcHBvP322/ahc507d473h3hC2rVrR9myZeNMZ8+eZfz48bRq1YqgoCDKlSvH33//zerVq8mcOTMAadOmJTg4mFKlSlGzZk1cXV1ZtGgRYPYjmTBhAhUqVKBixYocP36clStXPjTx8ijSpk1LtmzZ7jvso1y5cixZsoRFixZRokQJhg0bxqhRo+IMY5s1axZ58+alVq1atGzZ0n7L8CeRK1cufvrpJ6Kjo2nYsCElSpSgT58+eHt724//gw8+oGbNmrzwwgvUr1+f6tWrU758+Qfu193dnbVr1zJgwAA+++wzqlSpQsWKFZk0aRJvvvlmvD+m7zZ69OhEDeesW7cudevW5bblt51JOhkzZiQwMJDRo0dz9uxZoqOjmT9/Pjt37oxTtRLr5s2bDBo0iA4dOtz3j+tx48bh7e1tn/Lmzfu0D8MpOOv5cM+ePRw4cIBWrVrFW5cxY0YaNGjAzJkzAfNunxUrVqR9+/YUK1aMAQMG2KtYChUqxJo1azhw4ACVKlUiMDCQ77//3t6jKjg4mJo1a9KkSRMaN25M8+bNeeaZZx56PD169KBly5a0bduWypUrc/HixXh3fOvUqRMhISFMnTqV4sWL06RJk3hVavXr18fX15eGDRuSK1euh3+Qj8hms5EtWzbSpk2b4Pp06dKxevVqLl26RMWKFWndujX16tWLc+fP/v378/LLL9O5c2f7UMUWLVo8cVwrV66kZs2avPrqqxQqVIh27dpx/PhxezKsbdu2DBs2jIEDB1K+fHlOnDjB66+//tB9T5gwga+++oqdO3fSsGFDihcvTr9+/ShVqtQDE3+dOnVK1JdGWbJkYeDAgY71d5tIMoqJMSualiwxq5nq1zeTTWXKQM+eMG/enYRUsWLQpQvMnAmHDsHFi7ByJQwdar7OWRJSADbjSZpwPKHFixcTFBTE1KlTqVatGp999hlffPEFhw4dIl9s4uYumzZtok6dOhw5ciTOhVP27Nnt37zMnj2bPn36xPsmPGfOnImOKyIiAm9vb8LDwxM1rvyRrVwJzz8PpUvDXWPYRcQ53bx5k2PHjtkT7GKNZ599lpw5czJv3jyrQ5EU5EH/v5/69cJjOnr0KK+++ipbtmzB1dWVcuXKUahQIfbu3RunCXxUVBQvvvgiJ0+eZNOmTfc9hoQqpfLmzZvgcet86Bh0PoTr16+TK1cuvvzyS1q2bGl1OJJEdI6RlCIy0qyA2r8f9u0zHw8cSLgHY8aMZivq2CqoypXhf9+ZOrTEXidZOnxv4sSJdOnSha5duwIQEhLC6tWrmTZtGuPGjbvv63LkyPHAIRGxdzJxWLHD91QpJSLyWK5fv8706dNp2LAhrq6uLFy4kHXr1rF27VqrQxOx3DPPPMPmzZu5du0aERER+Pr60rZt2zjDn6KiomjTpg3Hjh1jw4YND7xYdHd3x93dPTlCl8eg82FcMTExnDt3jo8++ghvb29eeOEFq0MSkWQQE2Mmdtavh/BwyJPHvOl97GO2bJCEBeyP5PJlM+EUm3zatw8OH4aECrU9PMxeUGXLmnfGCww0q6ISMfrZaVmWlLp16xZ79uxh0KBBcZY3aNDgoc1Jy5Yty82bNylWrBhDhgyhTp06cdZfvXoVPz8/oqOjKVOmDKNHj6Zs2bL33V+y90qIrQILC4OICOeqrRMRcQCxwxPGjBlDZGQkhQsXZunSpdSvX9/q0EQcRvr06UmfPj2XL19m9erVvP/++8CdhNRff/3Fxo0b79unTJyDzodxnTx5koCAAPLkycPs2bPtwwlFJOU5fRrWrr0z/fff/bdNmxZy5YqfrLr70dcXEnlzyQQZhhnT3dVP+/YlfCc8gCxZzORT2bLmEL2yZaFQIUhtpy3LDve///4jOjo63q2wfXx8OHfuXIKv8fX1ZcaMGZQvX57IyEjmzZtHvXr12LRpEzVr1gSgSJEizJ49m5IlSxIREcEnn3xCtWrVOHDgAAULFkxwv+PGjUveu+9kzGjW212+bDY7f0BfDBERic/T05N169ZZHYaIQ1q9ejWGYVC4cGH+/vtv3nnnHQoXLswrr7zC7du3ad26NXv37uWHH34gOjraft2VJUuW+/bHEcel82Fc/v7+ieopJyLO59o12LwZ1qwxp8OH467PkAHq1DETTGfOmNPp03D+PNy6ZSaH7pcgAvOOdT4+909a5c5tThkymA3Ijxy5k3iKTUJdvJjwvv394yafypQx9/m07xTrDCzPwd3bsNUwjPs2cS1cuDCFCxe2zwcGBnLq1Ck+/PBDe1KqSpUqVKlSxb5NtWrVKFeuHJMnT2bSpEkJ7jc4OJh+/frZ52N7JTxV+fIpKSUiIiJJLjw8nODgYE6fPk2WLFlo1aoVY8eOJU2aNBw/fpzly5cDxLt74caNG6ldu3byBywiIpKAmBjYu9esglqzBn76CaKi7qx3cYGKFeHZZ6FBA7PvUkKVTrduQWjonSTV3Y93P4+KgnPnzGnPnvvH5e1t7vPGjfjrXF3N4XZ3J6BKl3aOHlBWsSwplS1bNlxdXeNVRZ0/fz5e9dSDVKlShfnz5993vYuLCxUrVox3R467WdIrwc/PHFiqvlIiIiKShNq0aUObNm0SXKcqEhERcWQnT95JQq1fH7/yyN/fTEA1aAB16yYu2ZM2rfnnd2xr54TExJjD/xJKXN39eOWK2bMKIH16M+F0dwKqeHGzL5QknmVJqbRp01K+fHnWrl0b59ana9eupVmzZonez759+/D19b3vesMw2L9/PyVLlnyieJNcbF+pkyetjUNEkkxMTIzVIYhIEtP/68ejz01EngadW1KeK1dg06Y7iagjR+Kuz5jRTD7FJqKeeebpDHlzcYEcOczpAe2ouXLFTE65uZmxWNU8PSWxdPhev379CAoKokKFCgQGBjJjxgxOnjxJjx49AHNY3ZkzZ5g7dy5g3p3P39+f4sWLc+vWLebPn8/SpUtZunSpfZ8jR46kSpUqFCxYkIiICCZNmsT+/fv59NNPLTnG+9Id+ERSjLRp0+Li4sLZs2fJnj07adOmve8wZBFxDoZhcOvWLS5cuICLi4t6LSWSzoci8jTonJxyREebQ+PWrDETUdu3x70LnYsLVK58Z0hepUpP1nw8qWXMCEWLWh1FymJpUqpt27ZcvHiRUaNGERoaSokSJVi5ciV+/0vYhIaGcvKuSqJbt27x9ttvc+bMGTw9PSlevDgrVqygcePG9m3CwsLo1q0b586dw9vbm7Jly7JlyxYqVaqU7Mf3QKqUEkkxXFxcCAgIIDQ0lLNnz1odjogkoXTp0pEvXz5c9FVoouh8KCJPk87Jzuv332HCBPjhB7O18t3y579TCVWnDmTKZEmIYhGbocYC8URERODt7U14eDheXl5P501+/hkCAyFvXiWmRFIIwzC4ffs20dHRVociIknA1dUVNze3+1b6JMv1ggNKzHHrfCgiSe1h52RxTAcPwujR8M03EJt58Pa+MyTv2WfNYXCS8iT2Osnyu++lWrHD92Lb/DtSTaKIPBabzUaaNGlIo//PIpLK6XwoIpK6/forjBoFd3XaoVUr6NvXvEuemzIR8j+qe7SKj495G4CYGFB5u4iIiIiIiDi5/fuhZUvzrnRLl5pNyV980UxSffMNVK+uhJTEpaSUVVxczKF7oGbnIiIiIiIi4rT27oVmzcw71y1bZiaj2rY1h+8tWQIlS1odoTgqJaWspGbnIiIiIiIi4qR274amTaF8eVi+3ExGtW8Pv/0GixZB8eJWRyiOToVzVortK6VKKREREREREXESu3bByJGwcqU57+JiJqOGDIEiRayNTZyLklJWUqWUiIiIiIiIOImffzaTUT/+aM67uMBLL5nJqEKFrI1NnJOSUlZSpZSIiIiIiIg4uO3bzWTUmjXmvKsrdOwIgwdDwYLWxibOTUkpK6lSSkREREREJEWKiYEbN+DaNbh+/fEeY59nzQrPPBN3ypPHTA49Tdu2mcmodevMeVdX6NQJ3n3XjEHkSSkpZaXYSqmTJ8EwzK5wIiIiIiIi4tBu3DAbey9dCv/+m3BC6caNpxtD2rTg728mhwoUiJuwCggAD4/H3/eWLWYyasMGc97NDTp3NpNRAQFJEb2ISUkpK+XJYz5euwaXLpnpbxEREREREXE4MTFm5dC8ebBkCUREJP61np6QLh2kT//wx3uXeXrC+fNw9Oid6dgxuHUL/vzTnO5ls0Hu3HETVXcnrjJlSjjOTZvMZNSmTeZ8mjTwyisQHGwmwESSmpJSVvL0hBw5zDPMyZNKSomIiIiIiDiYP/80E1Hz58Px43eW+/mZfZVKl35wksnT02wInpSio+HUqbiJqrunK1fg9Glz2rw5/uuzZIk/FHDhQrNCCsxkVJcuMGjQnQE+Ik+DklJW8/Mzk1InTkDZslZHIyIiIiIikupdvAiLF8PcubBz553lGTPCiy/Cyy9DjRpJn2xKLFdXs3LJ3x/q1Yu7zjDgv//iJ6r+/tt8/Pdfc6DOpUvwyy9xX5s2LXTtaiaj8uZNrqOR1ExJKavly2eeCdTsXERERERExDKRkbBypZmIWrECoqLM5a6u0LAhBAXBCy+YFVCOzGaD7NnNqUqV+OuvXoV//ombsDp+HIoUgf7973SZEUkOSkpZLbYW8sQJa+MQERERERFJZQzDrISaOxcWLYLLl++sK1vWTES1bw85c1oXY1LLkAFKlTInEaspKWW1fPnMR1VKiYiIiIiIJItjx8weUfPmwV9/3VmeK5fZJyooCEqUsC4+kdRCSSmrqVJKRERERETkqQsLg6+/NhNRW7feWZ4uHbRqZfaJqlPHHK4nIslDSSmrqVJKRERERETkqYiKgtWrzUTU99+bfaPA7LtUr56ZiGrRwhzSJiLJT0kpq8VWSv37L9y8CR4e1sYjIiIiIiLixGJiYMcOWLIEFi6ECxfurCte3ExEdeight4ijkBJKatlyWLWi16/DqdOQcGCVkckIiIiIiLiVKKj4aef4JtvYOlSOHv2zrocOcwk1MsvQ5kyZpWUiDgGJaWsZrOZQ/j++MMcwqeklIiIiIiIyEPdvm32hvrmG/j2Wzh37s46Ly944QVo1w4aNIA0aayLU0TuT0kpR+DnZyal1OxcRERERETkvm7fhk2bzIbly5bFHZqXKRM0awYvvgj164O7u1VRikhiKSnlCNTsXEREREREJEFRUbB+vVkR9d13cPHinXVZspiNylu3hrp1IW1ay8IUkcegpJQjiG12rkopERERERERIiNh3TozEfX993D58p112bJBy5ZmIqp2bQ3NE3FmSko5AlVKiYiIiIhIKnfzJqxZYyaili+H8PA763x8zETUiy9CjRrgpr9kRVIE/Vd2BKqUEhERERGRVOjGDfjxRzMR9X//B1eu3Fnn6wutWpmJqGrVwNXVujhF5OlQUsoRxFZKnToFMTHg4mJtPCIiIiIiIk+BYZjfxe/caTYq/+EHuHbtzvo8ecxhea1bQ2Cg/jQSSemUlHIEuXObZ9tbt+Dff82vBERERERERJzYlSvw229w4AD8+qs5HTwIERFxt/Pzu5OIqlRJiSiR1ERJKUeQJg3kygWnT5t9pZSUEhERERERJxETA//8cyfxFJuE+uefhLdPmxaKFYMGDcxEVIUKYLMlb8wi4hiUlHIUfn53klKVK1sdjYiIiIiISDxhYWa1090JqN9+izsE7265c0OpUnem0qWhUCHdMU9ETEpKOYp8+eCnn9TsXERERERELBcdDX/9dSf5FDvd788VDw8oUSJuAqpkSciWLXnjFhHnoqSUo4htdn7ypLVxiIiIiIhIqvTnn7B4sdl8/Ndf4ebNhLfLl+9O1VNsAqpAAXDTX5ci8oh02nAUfn7moyqlREREREQkmRw7ZiaiFi+G/fvjrkuXzqx2unvoXcmSkCmTFZGKSEqkpJSjUKWUiIiIiIgkg1OnYMkSMxH1yy93lru5Qf360KYN1KgB+fPrTngi8nQpKeUoVCklIiIiIiJPSWgofPONmYj66ac7y11coE4daNsWWraErFmti1FEUh8lpRxFbKXU5ctw5QpkzGhtPCIiIiIi4tQuXIClS81E1ObNYBjmcpvNrIRq2xZatQIfH2vjFJHUS0kpR+HlZQ7ODgszh/AVL251RCIiIiIi4mQuX4Zly8xE1Pr15l30YlWpYiaiXnwRcue2LkYRkVhKSjmSfPmUlBIRERERkUcSEQHff28motasgaioO+vKlzcTUW3a3OkYIiLiKJSUciR+fua9V9XsXEREREREHuDaNfjhB1i0CFatgsjIO+tKloR27cxEVIEC1sUoIvIwSko5kti+Ump2LiIiIiIi94iMhBUrzIqoH36A69fvrCtSxKyIatsWiha1LkYRkUehpJQjia2nVaWUiIiIiIj8z++/w8yZMHcuXLx4Z3n+/GZFVNu2ZnWUzWZdjCIij0NJKUeiSikREREREQGuXoUlS+CLL2DHjjvLc+eG9u3NRFT58kpEiYhzU1LKkcQmpVQpJSIiIiKS6hgG/PKLmYhauNBMTAG4uUHTptC1KzRsCK6u1sYpIpJUXKwOYOrUqQQEBODh4UH58uXZunXrfbfdtGkTNpst3vTHH3/E2W7p0qUUK1YMd3d3ihUrxrJly572YSSN2OF7Z87A7dvWxiIiIiIiIsni0iWYNAlKl4bKleHzz82EVMGCMGECnDoF334LjRsrISUiKYulSanFixfTt29fBg8ezL59+6hRowaNGjXi5EMqhY4cOUJoaKh9KliwoH3djh07aNu2LUFBQRw4cICgoCDatGnDzp07n/bhPLmcOSFNGoiOhrNnrY5GRERERESekpgY2LABOnSAXLmgTx84eBA8PKBjR9i8GY4cgQEDzD8TRERSIpthGIZVb165cmXKlSvHtGnT7MuKFi1K8+bNGTduXLztN23aRJ06dbh8+TKZMmVKcJ9t27YlIiKCVatW2Zc999xzZM6cmYULFyYqroiICLy9vQkPD8fLy+vRDupJPfMM/PMPbNkCNWok73uLiIhIoll6vWCh1HrcIknl7FmYPdtsXP7PP3eWly4Nr71mJqkyZ7YsPBGRJJHY6wXLKqVu3brFnj17aNCgQZzlDRo0YPv27Q98bdmyZfH19aVevXps3LgxzrodO3bE22fDhg0fuk+Hob5SIiIiIiIpyu3bsHw5vPCCebk/eLCZkPLygh49YPdu2LcPevVSQkpEUhfLGp3/999/REdH4+PjE2e5j48P586dS/A1vr6+zJgxg/LlyxMZGcm8efOoV68emzZtombNmgCcO3fukfYJEBkZSWRkpH0+IiLicQ/rycX2ldId+EREREREnNrRo/DllzBrFoSG3llevbrZtLx1a0if3rr4RESsZvnd92z33MPUMIx4y2IVLlyYwoUL2+cDAwM5deoUH374oT0p9aj7BBg3bhwjR458nPCTniqlRERERESc1s2bsGyZeQe9DRvuLM+eHTp1gi5doEgR6+ITEXEklg3fy5YtG66urvEqmM6fPx+v0ulBqlSpwl9//WWfz5kz5yPvMzg4mPDwcPt06tSpRL9/koutlFJSSkRERETEKRiGOQSvTx+zaXmHDmZCymaD556Db76B06fhgw+UkBIRuZtlSam0adNSvnx51q5dG2f52rVrqVq1aqL3s2/fPnx9fe3zgYGB8fa5Zs2aB+7T3d0dLy+vOJNlYiulNHxPRERERMSh/f47DB0KhQpBxYowaRJcvgx588KIEXD8OKxaBa1aQdq0VkcrIuJ4LB2+169fP4KCgqhQoQKBgYHMmDGDkydP0qNHD8CsYDpz5gxz584FICQkBH9/f4oXL86tW7eYP38+S5cuZenSpfZ99unTh5o1azJhwgSaNWvG999/z7p169i2bZslx/jI7h6+Zxjm1ysiIiIiIuIQjh6FxYth0SI4ePDOck9PaNoUXnkFnn0WXF2ti1FExFlYmpRq27YtFy9eZNSoUYSGhlKiRAlWrlyJ3/+GsIWGhnLyrmFst27d4u233+bMmTN4enpSvHhxVqxYQePGje3bVK1alUWLFjFkyBCGDh3KM888w+LFi6lcuXKyH99jiU1KXb1qfs2SJYu18YiIiIiIpHJnzsCSJWYiateuO8vTpDGH57VvbyakMmSwLkYREWdkMwzDsDoIRxMREYG3tzfh4eHWDOXLkQMuXDDvC1umTPK/v4iIiDyU5dcLFkmtxy2pz4ULsHSpmYjassUcxADg4gJ165qJqBYtIHNma+MUEXFEib1esKynlDxAbLNz9ZUSERGRR3TlyhX69u2Ln58fnp6eVK1alV9++cW+3jAMRowYQa5cufD09KR27dr8/vvvFkYs4jjCw2HOHLP6ydcXXn8dNm82E1LVqsGUKXD2LKxdC6++qoSUiMiTUlLKEd3dV0pERETkEXTt2pW1a9cyb948Dh48SIMGDahfvz5nzpwB4P3332fixIlMmTKFX375hZw5c/Lss89y5coViyMXscb16+bQvBYtzAELnTvD6tUQHQ3lypl3zDtxArZtg1694BFuFC4iIg9haU8puQ9VSomIiMhjuHHjBkuXLuX777+nZs2aAIwYMYLvvvuOadOmMXr0aEJCQhg8eDAtW7YEYM6cOfj4+PDVV1/RvXt3K8MXSTaRkbBmDSxcCMuXw7Vrd9YVLWoOzWvb1ryrnoiIPD1KSjkiVUqJiIjIY7h9+zbR0dF4eHjEWe7p6cm2bds4duwY586do0GDBvZ17u7u1KpVi+3btyspJSna7duwaZOZiPr2WwgLu7MuIADatTOnkiV1A2wRkeSipJQjiq2UUlJKREREHkHGjBkJDAxk9OjRFC1aFB8fHxYuXMjOnTspWLAg586dA8DnnvFHPj4+nLhPhXZkZCSRkZH2+YiIiKd3ACJPwb//wqRJ8MUXcP78neW+vmY1VLt2UKmSElEiIlZQTylHFFsppeF7IiIi8ojmzZuHYRjkzp0bd3d3Jk2aRIcOHXB1dbVvY7vnr2/DMOItizVu3Di8vb3tU968eZ9q/CJJ5Z9/oGdP8/ve994zE1JZs0L37rBxI5w6BR9/DJUrKyElImIVJaUcUWyl1Llz5oB3ERERkUR65pln2Lx5M1evXuXUqVPs2rWLqKgoAgICyJkzJ4C9YirW+fPn41VPxQoODiY8PNw+nTp16qkfg8iT2LfPrH4qWBCmTTMvpytXhqVLITQUpk+H2rXhrjytiIhYREkpR5Q1K3h6ms914SciIiKPIX369Pj6+nL58mVWr15Ns2bN7ImptWvX2re7desWmzdvpmrVqgnux93dHS8vrziTiKMxDNiwARo2NO+Yt3gxxMTAc8+ZfaR27ICWLSFNGqsjFRGRu6mnlCOy2cwhfEeOmH2lChSwOiIRERFxEqtXr8YwDAoXLszff//NO++8Q+HChXnllVew2Wz07duX9957j4IFC1KwYEHee+890qVLR4cOHawOXeSRRUfDd9/BhAnwyy/mMhcXs1JqwAAoXdrS8ERE5CGUlHJUfn5mUkp9pUREROQRhIeHExwczOnTp8mSJQutWrVi7NixpPlficiAAQO4ceMGPXv25PLly1SuXJk1a9aQMWNGiyMXSbzISJg3Dz74AP7801zm4QFdukD//ubd9ERExPEpKeWoYpud6w58IiIi8gjatGlDmzZt7rveZrMxYsQIRowYkXxBiSSRiAizJ1RIiNkfCiBzZujVC954A3LksDQ8ERF5REpKOarYZueqlBIRERGRVO7cOfjkE7NxeXi4uSx3bujXD157DVToJyLinJSUclSqlBIRERGRVO7vv+HDD2H27Ds3pS5a1OwX1aEDpE1raXgiIvKElJRyVKqUEhEREZFUas8es3n50qXmXfQAAgNh4EBo2tRsZi4iIs5PSSlHFVspdeqU+ZtYv3lFREREJAUzDNiwAcaPh3Xr7ixv3BgGDYLq1c2bVIuISMqhpJSjypPH/K0bGQkXLoCPj9URiYiIiIgkueho+PZbszJqzx5zmasrtG9vDtMrWdLa+ERE5OlRUspRpUkDuXLBmTPmED4lpUREREQkhTl6FF56CXbuNOc9PaFrV7OBub+/paGJiEgy0JgwR6Zm5yIiIiKSAhkGzJsHZcqYCSkvLxg2zPwudtIkJaRERFILVUo5Mj8/2LFDzc5FREREJMUID4fXX4eFC835GjVg/vw738eKiEjqoUopR6ZKKRERERFJQbZvN6ujFi40+0aNHg0bNyohJSKSWqlSypH5+ZmPqpQSERERESd2+zaMHQujRpk3lg4IgK++gipVrI5MRESspKSUI1OllIiIiIg4uRMnzGbmP/1kznfsCJ9+avaREhGR1E3D9xyZKqVERERExIktWgSlS5sJqYwZzd5R8+YpISUiIiYlpRxZbKXUpUtw9aq1sYiIiIiIJNKVK9C5M7RvbzY2r1IF9u83K6ZERERiKSnlyLy9zQng1ClrYxERERERSYRdu6BsWZgzB1xcYOhQ2LoV8ue3OjIREXE0Sko5uthqKQ3hExEREREHFh0N48dDtWpw9CjkzQubNpnNzd3UyVZERBKgpJSji+0rpWbnIiIiIuKgTp+G+vUhONi8016bNnDgANSoYXVkIiLiyJSUcnSqlBIRERERB/btt1CqlFkVlT49fPml2eA8c2arIxMREUenQlpHF5uUUqWUiIiIiDiQa9fgrbfg88/N+QoV4KuvoGBBa+MSERHnoUopRxc7fE+VUiIiIiLiIPbtg/LlzYSUzQYDB8JPPykhJSIij0aVUo5OlVIiIiIi4iBiYuDjj83eUVFRkCsXzJsHdetaHZmIiDgjJaUcXWyl1OnTZtdI3bpERERERCwQGgqdOsHateZ88+bwxReQNaulYYmIiBPT8D1HlzOnmYiKjjavBEREREREktkPP5jNzNeuBU9P+Owzs8G5ElIiIvIklJRydK6ukDev+Vx9pUREREQkGd24Ab17Q9Om8N9/ULo07NkD3bqZvaRERESehJJSzkB9pUREREQkma1caSahPv3UnH/rLdi5E4oWtTYuERFJOdSgyBnE9pVSUkpEREREnrKjR80E1P/9nznv6wuzZkHDhtbGJSIiKY8qpZxBbKWUhu+JiIiIyFNy/ToMHQrFi5sJKTc3ePtt+OMPJaREROTpUKWUM1CllIiIiIg8JYYBS5dCv35w6pS5rH59mDRJQ/VEROTpUlLKGahSSkRERESegkOH4I03YMMGc97PDyZOhBYt1MhcRESePg3fcwZ3J6UMw9pYRERERMTphYeblVGlS5sJKXd3GDbMTFK1bKmElIiIJA9VSjmD2KTU1asQFgaZM1sajoiIiIg4p5gYmDcPBg6Ef/81lzVrZlZH5c9vbWwiIpL6qFLKGaRLB9mymc/VV0pEREREHsPevVC9OnTubCakChWCVavgu++UkBIREWsoKeUsYpudq6+UiIiIiDyCixehRw+oUAF27ID06WHCBDh4EJ57zuroREQkNbM8KTV16lQCAgLw8PCgfPnybN26NVGv++mnn3Bzc6NMmTJxls+ePRubzRZvunnz5lOIPhnFDuFTpZSIiIiIJEJ0NEybBgULwmefma1JO3SAI0dgwABIm9bqCEVEJLWzNCm1ePFi+vbty+DBg9m3bx81atSgUaNGnHxI4iU8PJyXX36ZevXqJbjey8uL0NDQOJOHh8fTOITkE1sppaSUiIiIiDzETz+ZlVE9e8Lly1CqFGzeDAsWQO7cVkcnIiJisjQpNXHiRLp06ULXrl0pWrQoISEh5M2bl2nTpj3wdd27d6dDhw4EBgYmuN5ms5EzZ844k9O7+w58IiIiIiIJCA2FoCCzd9T+/ZApE0yeDHv2QM2aVkcnIiISl2VJqVu3brFnzx4aNGgQZ3mDBg3Yvn37fV83a9Ysjh49yvDhw++7zdWrV/Hz8yNPnjw0adKEffv2PTCWyMhIIiIi4kwOR5VSIiIiInIft27Bhx+azcvnzwebDbp2hT//hN69wU333BYREQdkWVLqv//+Izo6Gh8fnzjLfXx8OHfuXIKv+euvvxg0aBALFizA7T6/WYsUKcLs2bNZvnw5CxcuxMPDg2rVqvHXX3/dN5Zx48bh7e1tn/Lmzfv4B/a0qFJKRERERBKwdi2ULg3vvANXr0KlSrBzJ3z+OWTPbnV0IiIi92d5o3ObzRZn3jCMeMsAoqOj6dChAyNHjqRQoUL33V+VKlXo2LEjpUuXpkaNGixZsoRChQoxefLk+74mODiY8PBw+3Tq1KnHP6CnJTYpFRoKkZHWxiIiIiIiljtxAlq1ggYN4I8/zATUl1+ad9irWNHq6ERERB7OskLebNmy4erqGq8q6vz58/GqpwCuXLnC7t272bdvH7179wYgJiYGwzBwc3NjzZo11K1bN97rXFxcqFix4gMrpdzd3XF3d3/CI3rKsmcHDw+4eRNOn4ZnnrE6IhERERGxyKpV5p30wsLA1dUcojdihNlDSkRExFlYVimVNm1aypcvz9q1a+MsX7t2LVWrVo23vZeXFwcPHmT//v32qUePHhQuXJj9+/dTuXLlBN/HMAz279+Pr6/vUzmOZGOz3amWUl8pERERkVTJMOC99+D5582EVKVKsG8fhIQoISUiIs7H0paH/fr1IygoiAoVKhAYGMiMGTM4efIkPXr0AMxhdWfOnGHu3Lm4uLhQokSJOK/PkSMHHh4ecZaPHDmSKlWqULBgQSIiIpg0aRL79+/n008/TdZjeyr8/MxuleorJSIiIpLqXLkCnTvDt9+a8926waRJ4OgF/yIiIvdjaVKqbdu2XLx4kVGjRhEaGkqJEiVYuXIlfv+701xoaCgnH7EqKCwsjG7dunHu3Dm8vb0pW7YsW7ZsoVKlSk/jEJKXKqVEREREUqW//oLmzeHQIUiTBqZMMZNSIiIizsxmGIZhdRCOJiIiAm9vb8LDw/Hy8rI6nDtGj4Zhw+DVV2HmTKujERERSdUc9nrhKUutx22lFSvgpZcgPBx8fWHpUggMtDoqERGR+0vs9YLld9+TR6BKKREREZFUIybG/E6yaVMzIVWtGuzZo4SUiIikHJYO35NH9L9hjUpKiYiIiKRsERHw8svw/ffm/Ouvm83M06a1NCwREZEkpaSUM7m7UsowzDvyiYiIiEiK8scf0KKF+Zg2LUydCl26WB2ViIhI0tPwPWeSJ4+ZiLp5Ey5csDoaEREREUliy5dDpUpmQip3bti6VQkpERFJuZSUciZp05rdLQFOnLA2FhERERFJMjExMGIENGsGV65AjRpm/6iUcANpERGR+1FSytmo2bmIiIhIihIeDs2bw8iR5vwbb8D69eDjY2lYIiIiT52SUs4mttm5KqVEREREnN7hw2Y11P/9H7i7w+zZMGkSpEljdWQiIiJPnxqdOxtVSomIiIikCN99B0FBcPUq5M0L334LFSpYHZWIiEjyUaWUs1GllIiIiIhTi4mBoUPNO+xdvQq1a8Pu3UpIiYhI6qNKKWejSikRERERpxUWBi+9BCtXmvNvvQXvvw9uuioXEZFUSL/+nE1spZSSUiIiIiJO5fffzYbmf/8NHh7wxRdmgkpERCS10vA9ZxNbKfXff3DtmrWxiIiIiEiiLF0KlSubCSk/P9i+XQkpERERJaWcTaZM4OVlPj91ytJQREREROTBoqPh3XehdWvz+8R69cz+UWXLWh2ZiIiI9ZSUckax1VJqdi4iIiLisC5fhiZNYNw4c/7tt+HHHyFbNmvjEhERcRRKSjkjNTsXERERcWgHD5p30/vxR/D0hIUL4YMP1NBcRETkbkpKOaPYZueqlBIREZG73L59myFDhhAQEICnpyf58+dn1KhRxMTE2Le5evUqvXv3Jk+ePHh6elK0aFGmTZtmYdQpz6VL5jC9f/6BgADYsQPatbM6KhEREcej72qckSqlREREJAETJkxg+vTpzJkzh+LFi7N7925eeeUVvL296dOnDwBvvfUWGzduZP78+fj7+7NmzRp69uxJrly5aNasmcVHkDK8+y5cuADFisGWLZA1q9URiYiIOCZVSjkjVUqJiIhIAnbs2EGzZs14/vnn8ff3p3Xr1jRo0IDdu3fH2aZTp07Url0bf39/unXrRunSpeNsI4/vl19gxgzz+bRpSkiJiIg8iJJSzkiVUiIiIpKA6tWrs379ev78808ADhw4wLZt22jcuHGcbZYvX86ZM2cwDIONGzfy559/0rBhQ6vCTjGio+H118EwICgIata0OiIRERHHpuF7zii2Uur0afPqx9XV2nhERETEIQwcOJDw8HCKFCmCq6sr0dHRjB07lvbt29u3mTRpEq+99hp58uTBzc0NFxcXvvjiC6pXr57gPiMjI4mMjLTPR0REPPXjcFYzZsCePeDtbTY1FxERkQdTUsoZ+fqat265fRtCQyFPHqsjEhEREQewePFi5s+fz1dffUXx4sXZv38/ffv2JVeuXHTq1Akwk1I///wzy5cvx8/Pjy1bttCzZ098fX2pX79+vH2OGzeOkSNHJvehOJ3z581eUgBjx4KPj7XxiIiIOAObYRiG1UE4moiICLy9vQkPD8fLy8vqcBIWEADHj8NPP0HVqlZHIyIikuo44vVC3rx5GTRoEL169bIvGzNmDPPnz+ePP/7gxo0beHt7s2zZMp5//nn7Nl27duX06dP8+OOP8faZUKVU3rx5Heq4HUHnzjBnDpQrB7t2qZBdRERSt8ReJ6mnlLOK7SulZuciIiLyP9evX8fFJe7lnaurKzExMQBERUURFRX1wG3u5e7ujpeXV5xJ4tq2zUxI2WwwdaoSUiIiIoml4XvOKravlJqdi4iIyP80bdqUsWPHki9fPooXL86+ffuYOHEir776KgBeXl7UqlWLd955B09PT/z8/Ni8eTNz585l4sSJFkfvnG7fhp49zeddu0LlytbGIyIi4kyUlHJWqpQSERGRe0yePJmhQ4fSs2dPzp8/T65cuejevTvDhg2zb7No0SKCg4N56aWXuHTpEn5+fowdO5YePXpYGLnzmjwZDh6ErFlh3DiroxEREXEuSko5q9iklCqlRERE5H8yZsxISEgIISEh990mZ86czJo1K/mCSsHOnIHYfN/48WZiSkRERBJPPaWcVezwPVVKiYiIiFiif3+4ehWqVIH/jZAUERGRR6CklLNSpZSIiIiIZdavh8WLwcUFpk0zH0VEROTR6Nens4pNSkVEQFiYpaGIiIiIpCaRkdCrl/m8Vy8oU8bScERERJyWklLOKn36O40LVC0lIiIikmwmToQjR8DHB0aPtjoaERER56WklDOL7SulpJSIiIhIsjhx4k4i6sMPwdvb2nhEREScmZJSzix2CJ+anYuIiIgki7594cYNqFULXnrJ6mhEREScm5JSzkyVUiIiIiLJZsUK+O47cHODTz8Fm83qiERERJybklLOTJVSIiIiTs/f359Ro0ZxUl8yObQbN+CNN8znb70FxYtbG4+IiEhKoKSUM1OllIiIiNPr378/33//Pfnz5+fZZ59l0aJFREZGWh2W3GP8eDh2DPLkgWHDrI5GREQkZVBSypmpUkpERMTpvfHGG+zZs4c9e/ZQrFgx3nzzTXx9fenduzd79+61OjwB/v4bJkwwn3/8MWTIYG08IiIiKYWSUs4sNikVGgq3blkbi4iIiDyR0qVL88knn3DmzBmGDx/OF198QcWKFSldujRffvklhmFYHWKqZBjmsL3ISGjQAFq1sjoiERGRlENJKWeWIwe4u5tXS6dPWx2NiIiIPIGoqCiWLFnCCy+8QP/+/alQoQJffPEFbdq0YfDgwbykW71ZYtky+PFHSJsWpkxRc3MREZGk5GZ1APIEbDazWuqvv8y+UvnzWx2RiIiIPKK9e/cya9YsFi5ciKurK0FBQXz88ccUKVLEvk2DBg2oWbOmhVGmTlevQp8+5vOBA6FgQWvjERERSWmUlHJ2fn5mUkp9pURERJxSxYoVefbZZ5k2bRrNmzcnTZo08bYpVqwY7dq1syC61G30aLMYPSAAgoOtjkZERCTlUVLK2cX2ldId+ERERJzSP//8g1/sHXXvI3369MyaNSuZIhKAQ4dg4kTz+aRJ4OlpbTwiIiIpkXpKObvYi1glpURERJzS+fPn2blzZ7zlO3fuZPfu3RZEJIYBvXrB7dvwwgvQpInVEYmIiKRMlielpk6dSkBAAB4eHpQvX56tW7cm6nU//fQTbm5ulClTJt66pUuXUqxYMdzd3SlWrBjLli1L4qgdSGyllIbviYiIOKVevXpx6tSpeMvPnDlDr169LIhIFi6ETZvM6qhPPrE6GhERkZTL0qTU4sWL6du3L4MHD2bfvn3UqFGDRo0acfIhVT/h4eG8/PLL1KtXL966HTt20LZtW4KCgjhw4ABBQUG0adMmwW8gUwRVSomIiDi1Q4cOUa5cuXjLy5Yty6FDhyyIKHULD4f+/c3ngweDv7+l4YiIiKRolialJk6cSJcuXejatStFixYlJCSEvHnzMm3atAe+rnv37nTo0IHAwMB460JCQnj22WcJDg6mSJEiBAcHU69ePUJCQp7SUVjs7p5ShmFtLCIiIvLI3N3d+ffff+MtDw0Nxc1N7T+T27BhcO4cFCoEb79tdTQiIiIpm2VJqVu3brFnzx4aNGgQZ3mDBg3Yvn37fV83a9Ysjh49yvDhwxNcv2PHjnj7bNiw4QP36dTy5DEfb9yA//6zNhYRERF5ZLFfpoWHh9uXhYWF8e677/Lss89aGFnqs38/TJliPv/0U3B3tzQcERGRFM+yr9/+++8/oqOj8fHxibPcx8eHc+fOJfiav/76i0GDBrF169b7fnN47ty5R9onQGRkJJGRkfb5iIiIxB6G9dzdwdcXQkPNvlLZs1sdkYiIiDyCjz76iJo1a+Ln50fZsmUB2L9/Pz4+PsybN8/i6FKPmBjo2dN8bNMG6te3OiIREZGUz/JG5zabLc68YRjxlgFER0fToUMHRo4cSaFChZJkn7HGjRuHt7e3fcqbN+8jHIEDuHsIn4iIiDiV3Llz8+uvv/L+++9TrFgxypcvzyeffMLBgwed75rEic2eDTt2QIYMMHGi1dGIiIikDpZVSmXLlg1XV9d4FUznz5+PV+kEcOXKFXbv3s2+ffvo3bs3ADExMRiGgZubG2vWrKFu3brkzJkz0fuMFRwcTL9+/ezzERERznUR6OcHO3fqDnwiIiJOKn369HTr1s3qMFKtS5dg4EDz+YgRkDu3peGIiIikGpYlpdKmTUv58uVZu3YtLVq0sC9fu3YtzZo1i7e9l5cXBw8ejLNs6tSpbNiwgW+++YaAgAAAAgMDWbt2LW+99ZZ9uzVr1lC1atX7xuLu7o67MzcNUKWUiIiI0zt06BAnT57k1q1bcZa/8MILFkWUerz7rtmas3hxePNNq6MRERFJPSy9pUu/fv0ICgqiQoUKBAYGMmPGDE6ePEmPHj0As4LpzJkzzJ07FxcXF0qUKBHn9Tly5MDDwyPO8j59+lCzZk0mTJhAs2bN+P7771m3bh3btm1L1mNLVn5+5qOSUiIiIk7nn3/+oUWLFhw8eBCbzYbxv7vpxrYeiI6OtjK8FG/XLpgxw3w+bRqkSWNtPCIiIqnJY/WUOnXqFKdPn7bP79q1i759+zIj9jd6IrVt25aQkBBGjRpFmTJl2LJlCytXrsTvf0mW0NBQTj5ioqVq1aosWrSIWbNmUapUKWbPns3ixYupXLnyI+3HqcRWSmn4noiIiNPp06cPAQEB/Pvvv6RLl47ff/+dLVu2UKFCBTZt2mR1eCladDS8/joYBrz8MtSoYXVEIiIiqYvNiP067hHUqFGDbt26ERQUxLlz5yhcuDDFixfnzz//5M0332TYsGFPI9ZkExERgbe3N+Hh4Xh5eVkdzsMdOABlyph33jt/3upoREREUoWkul7Ili0bGzZsoFSpUnh7e7Nr1y4KFy7Mhg0b6N+/P/v27UvCqJ+c010nPcDUqdCrF3h7w5Ej8IAWpCIiIvIIEnu98FiVUr/99huVKlUCYMmSJZQoUYLt27fz1VdfMXv27McKWJ5AbKXUhQtw/bq1sYiIiMgjiY6OJkOGDICZoDp79iwAfn5+HDlyxMrQUrTz52HwYPP52LFKSImIiFjhsXpKRUVF2RuDr1u3zt6As0iRIoSGhiZddJI4mTJBxoxw5QqcOgWFC1sdkYiIiCRSiRIl+PXXX8mfPz+VK1fm/fffJ23atMyYMYP8+fNbHV6KNWAAhIVBuXLwv3amIiIiksweq1KqePHiTJ8+na1bt7J27Vqee+45AM6ePUvWrFmTNEBJBJtNfaVERESc1JAhQ4iJiQFgzJgxnDhxgho1arBy5UomTZpkcXQp09atMGeOeQk1dSq4ulodkYiISOr0WJVSEyZMoEWLFnzwwQd06tSJ0qVLA7B8+XL7sD5JZvnywe+/6w58IiIiTqZhw4b25/nz5+fQoUNcunSJzJkz2+/AJ0nHMOCNN8znr70GKfleOCIiIo7usZJStWvX5r///iMiIoLMmTPbl3fr1o106dIlWXDyCP53x0JVSomIiDiP27dv4+Hhwf79+ylRooR9eZYsWSyMKmW7eNG8RwyYvaRERETEOo81fO/GjRtERkbaE1InTpwgJCSEI0eOkCNHjiQNUBIpdvieKqVERESchpubG35+fkRHR1sdSqrxzz/mY+7ckC2btbGIiIikdo+VlGrWrBlz584FICwsjMqVK/PRRx/RvHlzpk2blqQBSiKpUkpERMQpDRkyhODgYC5dumR1KKlCbFJKPeRFRESs91hJqb1791KjRg0AvvnmG3x8fDhx4gRz585VQ06rqFJKRETEKU2aNImtW7eSK1cuChcuTLly5eJMkrSOHTMflZQSERGx3mP1lLp+/ToZM2YEYM2aNbRs2RIXFxeqVKnCCVXqWCO2Uur0aYiO1m1kREREnETz5s2tDiFVia2UCgiwNg4RERF5zKRUgQIF+O6772jRogWrV6/mrbfeAuD8+fN4eXklaYCSSL6+ZiIqKgrOnTMbJYiIiIjDGz58uNUhpCoaviciIuI4Hmv43rBhw3j77bfx9/enUqVKBAYGAmbVVNmyZZM0QEkkNzfIk8d8riF8IiIiIglSUkpERMRxPFalVOvWralevTqhoaGULl3avrxevXq0aNEiyYKTR5Qvn9no/MQJ+F+iUERERBybi4sLNpvtvut1Z76kExUFp06Zz5WUEhERsd5jJaUAcubMSc6cOTl9+jQ2m43cuXNTqVKlpIxNHpWfH2zdqkopERERJ7Js2bI481FRUezbt485c+YwcuRIi6JKmU6dMltvenhAzpxWRyMiIiKPlZSKiYlhzJgxfPTRR1y9ehWAjBkz0r9/fwYPHoyLy2ONCpQnFXsHPjWbFxERcRrNmjWLt6x169YUL16cxYsX06VLFwuiSpnubnL+gOI0ERERSSaPlZQaPHgwM2fOZPz48VSrVg3DMPjpp58YMWIEN2/eZOzYsUkdpyRGbFJKlVIiIiJOr3Llyrz22mtWh5GiqJ+UiIiIY3mspNScOXP44osveOGFF+zLSpcuTe7cuenZs6eSUlbx8zMfVSklIiLi1G7cuMHkyZPJE3sTE0kSx46Zj0pKiYiIOIbHSkpdunSJIkWKxFtepEgRLl269MRByWNSpZSIiIjTyZw5c5xG54ZhcOXKFdKlS8f8+fMtjCzluXv4noiIiFjvsZJSpUuXZsqUKUyaNCnO8ilTplCqVKkkCUweQ2xSKjzcnLy9rY1HREREHurjjz+Ok5RycXEhe/bsVK5cmcyZM1sYWcqj4XsiIiKO5bGSUu+//z7PP/8869atIzAwEJvNxvbt2zl16hQrV65M6hglsTJkgCxZ4NIls1qqZEmrIxIREZGH6Ny5s9UhpBpKSomIiDiWx7pNXq1atfjzzz9p0aIFYWFhXLp0iZYtW/L7778za9aspI5RHkVsXykN4RMREXEKs2bN4uuvv463/Ouvv2bOnDkWRJQyhYeb39uBhu+JiIg4isdKSgHkypWLsWPHsnTpUr799lvGjBnD5cuXdfFktdghfGp2LiIi4hTGjx9PtmzZ4i3PkSMH7733ngURpUyxTc6zZzeLy0VERMR6j52UEgelSikRERGncuLECQISKN3x8/PjpH6fJxkN3RMREXE8SkqlNKqUEhERcSo5cuTg119/jbf8wIEDZM2a1YKIUiYlpURERByPklIpTWxSSt+sioiIOIV27drx5ptvsnHjRqKjo4mOjmbDhg306dOHdu3aWR1eihE7fE9JKREREcfxSHffa9my5QPXh4WFPUkskhRih++pUkpERMQpjBkzhhMnTlCvXj3c3MxLs5iYGF5++WX1lEpCsZVSanIuIiLiOB4pKeXt7f3Q9S+//PITBSRPKLZS6uxZiIqCNGmsjUdEREQeKG3atCxevJgxY8awf/9+PD09KVmyJH6xXzRJktDwPREREcfzSEmpWbNmPa04JKnkyAHu7hAZCadP6+tAERERJ1GwYEEKFixodRgpUkwMHD9uPldSSkRExHGop1RK4+ICefOaz9VXSkRExOG1bt2a8ePHx1v+wQcf8OKLL1oQUcpz9izcugVubpAnj9XRiIiISCwlpVKi2HJ/JaVEREQc3ubNm3n++efjLX/uuefYsmWLBRGlPLFD9/z8wNXV2lhERETkDiWlUqLYvlJqdi4iIuLwrl69Stq0aeMtT5MmDRERERZElPKon5SIiIhjUlIqJVKllIiIiNMoUaIEixcvjrd80aJFFCtWzIKIUp5jx8xHJaVEREQcyyM1OhcnoUopERERpzF06FBatWrF0aNHqVu3LgDr16/nq6++4ptvvnmkfd2+fZsRI0awYMECzp07h6+vL507d2bIkCG4uNz5LvLw4cMMHDiQzZs3ExMTQ/HixVmyZAn5Yq8hUhhVSomIiDgmJaVSIlVKiYiIOI0XXniB7777jvfee49vvvkGT09PSpcuzYYNG/Dy8nqkfU2YMIHp06czZ84cihcvzu7du3nllVfw9vamT58+ABw9epTq1avTpUsXRo4cibe3N4cPH8bDw+NpHJ5DiE1K6abEIiIijsVmGIZhdRCOJiIiAm9vb8LDwx/5YtAh/P03FCwInp5w7RrYbFZHJCIikuI8reuFsLAwFixYwMyZMzlw4ADR0dGJfm2TJk3w8fFh5syZ9mWtWrUiXbp0zJs3D4B27dqRJk0a+/yjcsbrJF9fOHcOdu+G8uWtjkZERCTlS+z1gnpKpUSx9zq+cQMuXrQ2FhEREUmUDRs20LFjR3LlysWUKVNo3Lgxu3fvfqR9VK9enfXr1/Pnn38CcODAAbZt20bjxo0BiImJYcWKFRQqVIiGDRuSI0cOKleuzHfffXfffUZGRhIRERFncibXr5sJKdDwPREREUejpFRK5OFxJzH1iL0oREREJPmcPn2aMWPGkD9/ftq3b0/mzJmJiopi6dKljBkzhrJlyz7S/gYOHEj79u0pUqQIadKkoWzZsvTt25f27dsDcP78ea5evcr48eN57rnnWLNmDS1atKBly5Zs3rw5wX2OGzcOb29v+5Q3b94nPu7kdPy4+ejtDZkzWxqKiIiI3ENJqZSqf3/z8e237zRSEBEREYfRuHFjihUrxqFDh5g8eTJnz55l8uTJT7TPxYsXM3/+fL766iv27t3LnDlz+PDDD5kzZw5gVkoBNGvWjLfeeosyZcowaNAgmjRpwvTp0xPcZ3BwMOHh4fbp1KlTTxRjclOTcxEREcelRucp1ZtvwnffwebN8MorsHEjuCgHKSIi4ijWrFnDm2++yeuvv07BggWTZJ/vvPMOgwYNol27dgCULFmSEydOMG7cODp16kS2bNlwc3OjWLFicV5XtGhRtm3bluA+3d3dcXd3T5L4rKCklIiIiONSliKlcnGBWbMgQwbYsgVCQqyOSERERO6ydetWrly5QoUKFahcuTJTpkzhwoULT7TP69ev43LPl1Curq72Cqm0adNSsWJFjhw5EmebP//8E7/Yu/emMMeOmY9KSomIiDgeJaVSsoAAmDjRfP7uu3D4sLXxiIiIiF1gYCCff/45oaGhdO/enUWLFpE7d25iYmJYu3YtV65ceeR9Nm3alLFjx7JixQqOHz/OsmXLmDhxIi1atLBv884777B48WI+//xz/v77b6ZMmcL//d//0bNnz6Q8PIcRWykVEGBtHCIiIhKfzTAMw+ogHI0z3ur4vgwDnn8eVq2CChVg+3ZIk8bqqERERJze07heOHLkCDNnzmTevHmEhYXx7LPPsnz58kS//sqVKwwdOpRly5Zx/vx5cuXKRfv27Rk2bBhp06a1b/fll18ybtw4Tp8+TeHChRk5ciTNmjVL1Hs423VSyZLw22/w44/QsKHV0YiIiKQOib1eUFIqAc52sfVQZ89CiRJw+TKMGgVDh1odkYiIiNN7mtcL0dHR/N///R9ffvnlIyWlkoMzXScZhtnJ4Pp1+PNPSKLWXSIiIvIQib1esHz43tSpUwkICMDDw4Py5cuzdevW+267bds2qlWrRtasWfH09KRIkSJ8/PHHcbaZPXs2Npst3nTz5s2nfSiOK1cumDLFfD5qFOzda208IiIi8kCurq40b97c4RJSzubCBTMhZbNBCm2ZJSIi4tQsvfve4sWL6du3L1OnTqVatWp89tlnNGrUiEOHDpEvX75426dPn57evXtTqlQp0qdPz7Zt2+jevTvp06enW7du9u28vLziNfD08PB46sfj0Nq3h2XL4Jtv4OWXYc8ecOI76YiIiIg8TGw/qTx54K7RiyIiIuIgLK2UmjhxIl26dKFr164ULVqUkJAQ8ubNy7Rp0xLcvmzZsrRv357ixYvj7+9Px44dadiwYbzqKpvNRs6cOeNMqZ7NBlOnQo4c8PvvMGyY1RGJiIiIPFWxSSndeU9ERMQxWZaUunXrFnv27KFBgwZxljdo0IDt27cnah/79u1j+/bt1KpVK87yq1ev4ufnR548eWjSpAn79u1LsridWvbs8Pnn5vMPPoCffrI2HhEREZGnSEkpERERx2ZZUuq///4jOjoaHx+fOMt9fHw4d+7cA1+bJ08e3N3dqVChAr169aJr1672dUWKFGH27NksX76chQsX4uHhQbVq1fjrr7/uu7/IyEgiIiLiTCnWCy9Ap05m589OneDaNasjEhEREXkqjh0zH5WUEhERcUyWNzq32Wxx5g3DiLfsXlu3bmX37t1Mnz6dkJAQFi5caF9XpUoVOnbsSOnSpalRowZLliyhUKFCTJ48+b77GzduHN7e3vYpb968T3ZQju6TTyBvXjh6FAYMsDoaERERkacitlIqIMDaOERERCRhliWlsmXLhqura7yqqPPnz8ernrpXQEAAJUuW5LXXXuOtt95ixIgR993WxcWFihUrPrBSKjg4mPDwcPt06tSpRzoWp+PtDV9+aT6fOhXWrrU2HhEREZGnQMP3REREHJtlSam0adNSvnx51t6TEFm7di1Vq1ZN9H4MwyAyMvKB6/fv34+vr+99t3F3d8fLyyvOlOLVrw+9epnPX30VwsIsDUdEREQkKd26BadPm8+VlBIREXFMbla+eb9+/QgKCqJChQoEBgYyY8YMTp48SY8ePQCzgunMmTPMnTsXgE8//ZR8+fJRpEgRALZt28aHH37IG2+8Yd/nyJEjqVKlCgULFiQiIoJJkyaxf/9+Pv300+Q/QEc3YQKsXg1//w19+8Ls2VZHJCIiIpIkTp6EmBhIl868+bCIiIg4HkuTUm3btuXixYuMGjWK0NBQSpQowcqVK/Hz8wMgNDSUkydP2rePiYkhODiYY8eO4ebmxjPPPMP48ePp3r27fZuwsDC6devGuXPn8Pb2pmzZsmzZsoVKlSol+/E5vPTpYc4cqFHDfGzRApo1szoqERERkSd2dz+ph7QrFREREYvYDMMwrA7C0URERODt7U14eHjqGMo3aJBZNZUjB/z2G2TPbnVEIiIiDi/VXS/8j7Mc9/Tp8Prr0LQpLF9udTQiIiKpS2KvFyy/+544gJEjoUQJOH8eevQA5SlFRETEyR07Zj6qn5SIiIjjUlJKwN0d5s4FNzf49lv46iurIxIRERF5IrrznoiIiONTUkpMZcvCsGHm89694cwZa+MREREReQJ395QSERERx6SklNwRHAwVK0JYGHTtqmF8IiIi4rRUKSUiIuL4lJSSO9zczLvwubvDjz/C559bHZGIiIjII7t82fyODVQpJSIi4siUlJK4ihaFcePM5/363fmaUURERMRJxDY5z5kT0qWzNhYRERG5PyWlJL4+faBmTbh2DTp3huhoqyMSERERSTT1kxIREXEOSkpJfC4uMHs2pE8PW7fCJ59YHZGIiIhIoqmflIiIiHNQUkoSFhAAEyeaz999Fw4dsjYeERERkUSKHb6npJSIiIhjU1JK7u+11+C55yAyEjp1gqgoqyMSEREReSgN3xMREXEOSkrJ/dls8MUXkCkT7N59pwG6iIiIiAPT8D0RERHnoKSUPFju3PDpp+bz0aNh715r4xERERF5gOhoOHHCfK6klIiIiGNTUkoern17aNUKbt+Gl1+GmzetjkhEREQkQWfOmB0H0qaFXLmsjkZEREQeREkpeTibDaZNgxw54PffYdgwqyMSERERSVDs0D0/P3B1tTYWEREReTAlpSRxsmeHzz83n3/4Ifz0k7XxiIiIiCRA/aRERESch5JSkngvvGDehc8wzMerV62OSERERCQOJaVERESch5JS8mg++QTy5oWjR2HgQKujEREREYnj2DHzUUkpERERx6eklDwab2/48kvz+dSpsHattfGIiIiI3CW2UiogwNo4RERE5OGUlJJHV78+9OplPn/lFfM2NyIiIiIOQMP3REREnIeSUvJ4JkyAAgXMhFSVKnDwoNURiYiISCp39SqcP28+V1JKRETE8SkpJY8nfXpYswaKFIHTp6FaNQ3lExEREUsdP24+ZslidhwQERERx6aklDy+gADYvh1q1YIrV6Bx4zv9pkRERESSmfpJiYiIOBclpeTJZM4Mq1fDSy/B7dvQpQsMGQKGYXVkIiIiksqon5SIiIhzUVJKnpy7O8ybZyajAMaOhaAgiIy0Ni4RERFJVY4dMx+VlBIREXEOSkpJ0rDZYPRomDkT3NxgwQJo2BAuX7Y6MhEREUklVCklIiLiXJSUkqT16quwYgVkzAibN0PVqne+thQRERF5itRTSkRExLkoKSVJr0ED+OknyJMH/vgDqlSBXbusjkpERERSMMPQ8D0RERFno6SUPB0lS8LOnVCmDJw/D7Vrw3ffWRyUiIiIpFT//gs3boCLC+TLZ3U0IiIikhhKSsnTkysXbNkCjRqZV4ktW8Inn1gdlYiIiKRAsUP38uWDNGmsjUVEREQSR0kpeboyZoTly6F7d7Ouvm9fc4qOtjoyERERSUHUT0pERMT5KCklT5+bG0ybBhMmmPOffAKtW8P169bGJSIiIimG7rwnIiLifJSUkuRhs8GAAbBoEbi7m/2latc2G0CIiIiIPCE1ORcREXE+SkpJ8mrbFtatgyxZ4JdfIDDQvEOfiIiIyBNQpZSIiIjzUVJKkl/16vDzz/DMM+bXmoGBsHmz1VGJiIiIE1NPKREREeejpJRYo2BB2LHDTEiFhcGzz8KCBVZHJSIiIk4oMhLOnDGfq1JKRETEeSgpJdbJnh3WrzebnkdFQceOMHaseZc+ERERkUQ6ccK8fMiQAbJlszoaERERSSwlpcRanp6weDG8/bY5P2QIdO1qJqlEREREEuHuflI2m7WxiIiISOIpKSXWc3GBDz6ATz81n3/5JTz/PISHWx2ZiIiIOAH1kxIREXFOSkqJ4+jZE77/HtKlg7VroUYNOHXK6qhERETEwenOeyIiIs5JSSlxLE2awJYtkDMnHDwIVarA/v1WRyUiIiIO7Ngx81FJKREREeeipJQ4nvLl4eefoXhxOHsWqlWD4GA4d87qyERERMQBafieiIiIc1JSShyTnx9s2wb168P16zB+PPj7w+uvw9GjVkcnIiIiDsIwNHxPRETEWSkpJY4rUyZYvdrsM1WlCkRGwvTpUKgQdOgABw5YHaGIiIhY7NIliIgwn/v7WxqKiIiIPCLLk1JTp04lICAADw8Pypcvz9atW++77bZt26hWrRpZs2bF09OTIkWK8PHHH8fbbunSpRQrVgx3d3eKFSvGsmXLnuYhyNPk4gIvvADbt8OmTfDccxATAwsXQpky0Lix2YPKMKyOVERERCwQ208qVy7w9LQ2FhEREXk0lialFi9eTN++fRk8eDD79u2jRo0aNGrUiJMnTya4ffr06enduzdbtmzh8OHDDBkyhCFDhjBjxgz7Njt27KBt27YEBQVx4MABgoKCaNOmDTt37kyuw5KnwWaDWrVg1SrYtw/atTMTVqtWmcurVYPly82ElYiIiKQa6iclIiLivGyGYV2JSeXKlSlXrhzTpk2zLytatCjNmzdn3LhxidpHy5YtSZ8+PfPmzQOgbdu2REREsGrVKvs2zz33HJkzZ2bhwoWJ2mdERATe3t6Eh4fj5eX1CEckyeroUfjwQ5g1yxzaB2Zz9IEDzaRVmjTWxiciIilaar1ecLTjHj/evB9KUBDMnWt1NCIiIgKJv16wrFLq1q1b7NmzhwYNGsRZ3qBBA7Zv356ofezbt4/t27dTq1Yt+7IdO3bE22fDhg0fuM/IyEgiIiLiTOIEnnkGpk0z6/YHDoSMGeH33+Hll6FAAZg82WySLiIiIilW7PA9NTkXERFxPpYlpf777z+io6Px8fGJs9zHx4dz58498LV58uTB3d2dChUq0KtXL7p27Wpfd+7cuUfe57hx4/D29rZPefPmfYwjEsv4+ppfk548CePGQY4c5vM33zTv4jd6NFy+bHWUIiIiT93t27cZMmQIAQEBeHp6kj9/fkaNGkXMfYa3d+/eHZvNRkhISPIGmoR05z0RERHnZXmjc5vNFmfeMIx4y+61detWdu/ezfTp0wkJCYk3LO9R9xkcHEx4eLh9OnXq1CMehTiETJlg0CA4fhymTjWbS/z3HwwbBvnywdtvw5kzVkcpIiLy1EyYMIHp06czZcoUDh8+zPvvv88HH3zA5MmT42373XffsXPnTnLlymVBpElHPaVEREScl2VJqWzZsuHq6hqvgun8+fPxKp3uFRAQQMmSJXnttdd46623GDFihH1dzpw5H3mf7u7ueHl5xZnEiXl6wuuvw59/wldfQalScPUqfPSRecXatSscOWJ1lCIiIklux44dNGvWjOeffx5/f39at25NgwYN2L17d5ztzpw5Q+/evVmwYAFpnLgH4+3bcOKE+VyVUiIiIs7HsqRU2rRpKV++PGvXro2zfO3atVStWjXR+zEMg8jYJtdAYGBgvH2uWbPmkfYpKYSbG7RvD/v3w8qVUKMGREXBzJlQtCi0bg33XKSLiIg4s+rVq7N+/Xr+/PNPAA4cOMC2bdto3LixfZuYmBiCgoJ45513KF68+EP36ci9N0+fhuhocHc3R/OLiIiIc3Gz8s379etHUFAQFSpUIDAwkBkzZnDy5El69OgBmMPqzpw5w9z/3Url008/JV++fBQpUgSAbdu28eGHH/LGG2/Y99mnTx9q1qzJhAkTaNasGd9//z3r1q1j27ZtyX+A4hhsNmjUyJx++gkmTID/+z9YutSc6tUzh/3Vq2duKyIi4qQGDhxIeHg4RYoUwdXVlejoaMaOHUv79u3t20yYMAE3NzfefPPNRO1z3LhxjBw58mmF/ETuHrrnYnlTChEREXlUlial2rZty8WLFxk1ahShoaGUKFGClStX4ufnB0BoaCgnT560bx8TE0NwcDDHjh3Dzc2NZ555hvHjx9O9e3f7NlWrVmXRokUMGTKEoUOH8swzz7B48WIqV66c7McnDqhaNVi+HH77Dd5/3xzet369OdWubS6rWNHqKEVERB7L4sWLmT9/Pl999RXFixdn//799O3bl1y5ctGpUyf27NnDJ598wt69ex/awzNWcHAw/fr1s89HREQ4zE1h1E9KRETEudkMwzCsDsLRRERE4O3tTXh4uPpLpXTHj5u9pmbMgFu3zGVt2sB778Ezz1gamoiIODZHvF7ImzcvgwYNolevXvZlY8aMYf78+fzxxx+EhITQr18/XO4qK4qOjsbFxYW8efNy/Pjxh76HIx33u++aN97t1QumTLE0FBEREblLYq8XVOgsqZu/P0yebDZFDwoyh+8tWQJFisAbb8D581ZHKCIikmjXr1+Pk3ACcHV1JSYmBoCgoCB+/fVX9u/fb59y5crFO++8w+rVq60I+YkcO2Y+qsm5iIiIc1JSSgTAzw/mzoV9+6BhQ/N2PlOmQIECMGYMXLtmdYQiIiIP1bRpU8aOHcuKFSs4fvw4y5YtY+LEibRo0QKArFmzUqJEiThTmjRpyJkzJ4ULF7Y4+kcXO3xPSSkRERHnpKSUyN1Kl4Yff4R166BcObhyBYYOhYIFzSF+t29bHaGIiMh9TZ48mdatW9OzZ0+KFi3K22+/Tffu3Rk9erTVoT0V6iklIiLi3NRTKgGO1CtBLBQTA4sXw+DBd8YHFCliNq9o1kx36hMRSeVS6/WCoxz3lSsQ+/bh4Xeei4iIiPXUU0rkSbm4QPv2cPgwhIRA1qzwxx/QogVUrw7bt1sdoYiISKoV+31RtmxKSImIiDgrJaVEHsbdHfr0gaNHzdv8eHqaCalq1cwE1R9/WB2hiIhIqqN+UiIiIs5PSSmRxPL2hrFj4a+/oGtXs5Lqu++gRAno3h1CQ62OUEREJNVQPykRERHnp6SUyKPKnRs+/xwOHoQXXoDoaLMJeoECZlP0iAirIxQREUnxVCklIiLi/JSUEnlcxYrB99/D1q1QpQpcvw5jxpjJqcmT4dYtqyMUERFJsWJ7SikpJSIi4ryUlBJ5UrFNz5cuhUKF4MIFePNNM2m1eDHoBpciIiJJTpVSIiIizk9JKZGkYLNBy5bw228wbRr4+JiN0du1g0qVYONGqyMUERFJMWJi7lRKqaeUiIiI81JSSiQppUkDPXrA33/DyJGQIQPs3g1160LjxrBpkyqnREREnlBoKERGgqsr5M1rdTQiIiLyuJSUEnkaMmSAYcPMaqlevcDNDVatgjp1oHhxmDIFwsOtjlJERMQpxVZJ+fmZv2JFRETEOSkpJfI05chhJqAOHYJu3SB9ejh8GN54w7yLX/fusH+/1VGKiIg4FfWTEhERSRmUlBJJDgULwmefwZkzZpKqWDG4dg1mzICyZaFqVZg/H27etDpSERERhxeblFI/KREREeempJRIcvL2Nofz/fab2V+qbVtz3MGOHRAUBHnywMCBd662RUREJJ7Y4XuqlBIREXFuSkqJWMFmg1q1YNEiOHUKRo82O7VevAjvvw8FCsDzz8MPP0B0tNXRioiIOBQN3xMREUkZlJQSsVrOnDBkiHmF/d130KCBeYe+lSuhaVN45hkYPx7On7c6UhEREYeg4XsiIiIpg5JSIo7CzQ2aNYPVq+HPP6F/f8iSBU6cgOBgc2jfSy/Btm1m0kpERCQVunEDzp41n6tSSkRExLkpKSXiiAoWhA8/hNOnYfZsqFQJoqLgq6+gRg0oXRqmT4crV6yOVEREJFmdOGE+enmZ392IiIiI81JSSsSReXpCp06wcyfs3g1dupjLDh6E11+H3LnvNE4XERFJBe7uJ2WzWRuLiIiIPBklpUScRfny8MUXcOYMhIRAoUJmpdTUqVCyJNSsCQsXwvXrVkcqIiLy1KiflIiISMqhpJSIs8mcGfr0gT/+gHXroFUrcHWFrVuhQwfInh1atzaH+oWHWx2tiIhIktKd90RERFIOJaVEnJXNBvXqwTffmA02hg8HPz+zUmrpUrMpevbs0LixWWF14YLVEYuIiDyxY8fMRyWlREREnJ+SUiIpQe7cMGKEeaW+Zw8MHgxFi5rN0Vetgtdeg5w5oU4dmDwZTp2yOmIREZHHokopERGRlENJKZGUxGaDcuVgzBg4dMicxo41l8XEwKZN8OabkC8fVK4MEybAX39ZHbWIiEiiGIZ6SomIiKQkSkqJpGRFi8K775rVU8eOwcSJUL26mbzatQsGDTIbppcsaQ7/O3DAvOIXERFxQP/9B1evmr/G/PysjkZERESelJJSIqmFvz+89ZbZEP3sWZg+HRo0ADc3+O03GDUKypSBAgXgnXdgxw6zukpERMRBxPaTyp0bPDysjUVERESenJJSIqlRzpzQvTusXg3nz8PcudC8uXmF/88/8OGHULUq5M0LvXvDhg1w+7bVUYuISCqnflIiIiIpi5JSIqld5swQFATLlpnjIr75Bjp0gIwZzYqqTz817/Ln4wOvvgo//AA3b1odtYiIpELqJyUiIpKyKCklInekTw+tWsGCBXDhAqxYAV26QLZscOkSzJoFTZtCjhzw0ktmIuvGDaujFhGRVEKVUiIiIimLklIikjB3d2jcGL74AkJDYeNGeOMNs5HHlSvw1VfQsiVkzw5t28LXX8O1a1ZHLSIiKVhsTyklpURERFIGJaVE5OHc3KB2bZg0CU6eNJug9+9v3vro2jVYsgTatDETVK1bw6JFZuJKREQkCalSSkREJGVRUkpEHo2LC1SpYjZDP3YMfvkFBgww/0K4cQOWLoX27c0EVfPmMH8+hIdbHbWIiDi5qCjzexFQTykREZGUQkkpEXl8NhtUqAATJsDff8PevfDuu1CwIERGwvffm03Us2eHJk1g9myzN5WIiMgjOnkSYmLMG8XmzGl1NCIiIpIUlJQSkaRhs0HZsjB2LBw5Ar/+CsOGQbFi5tfbK1bAK6+Yd/F77jmzV9V//1kdtYiIOIm7+0nZbNbGIiIiIklDSSkRSXo2G5QsCSNHwu+/m9OoUVCqFNy+DatXw2uvmV91168P06fDv/9aHbWIiDgw9ZMSERFJeZSUEpGnr1gxGDoUDhwwq6jeew/KlYPoaFi/Hl5/HXLlMpupT5kCZ89aHbGIiDiY2KSU+kmJiIikHEpKiUjyKlQIgoNhzx44ehTefx8qVTIbhWzeDG+8AXnyQGAgjBtnVlkZhtVRi4iIxVQpJSIikvIoKSUi1smfH955B3buhOPHYeJEqFrVTEL9/LPZNL1ECShQAN56CzZsMPtTiYhIqnN3TykRERFJGZSUEhHH4OdnJp5++gnOnIHPPoPnnwd3d/Pr8ZAQqFfPvJNfhw6waBGEhVkdtYiIJBNVSomIiKQ8SkqJiOPJlQu6dYMffoCLF2HZMvPOfdmzQ3g4LFwI7dub8/Xrw6RJd75CFxGRFCc8HC5dMp/7+1saioiIiCQhy5NSU6dOJSAgAA8PD/6/vTuPjrJK8zj+q+yLJCyBLA2EgEAgICMBSVhEQCIom203Ae0Y1G6aHnRg6JkRGhFkjgecae1p7RZ0BkW76cihWZoRbIzKJluzJICKwMgSlMQIShKIhCx3/ni7EopUNkiqkqrv55x7UvXWfd/c59zk8PDkvvdNTEzUzp07a+y7bt06jR49Wu3bt1dYWJiSk5O1ZcsWhz4rV66UzWar1q5evdrUoQBoCqGh0qRJ0htvSLm51kqqp5+WevWynuT34YfSrFnWn87vuEOaP9+6HbCiwt0jBwA0EvvfHTp0kG67zb1jAQAAjcetRanVq1dr9uzZmj9/vrKysjRs2DCNHTtWOTk5Tvvv2LFDo0eP1ubNm3Xw4EGNGDFC48ePV1ZWlkO/sLAw5ebmOrSgoCBXhASgKfn6WntOLV0qffaZdPKktQ/VPfdYnx09aj3ZLynJWm31s59J//u/UnGxu0cOALgF3LoHAIBnshnjvsdaDRo0SP3799eyZcsqj/Xq1UuTJk3SkiVL6nWNhIQEpaam6tlnn5VkrZSaPXu2Lt3CXjOFhYUKDw9XQUGBwsLCbvo6AFzo22+l996TNm60vhYVVX0WHCyNHi1NmCCNGydFRrpvnAA8hrfmC+6I+9e/tp6L8fDD0qpVLvmWAADgFtQ3X3DbSqlr167p4MGDSklJcTiekpKi3bt31+saFRUVKioqUtu2bR2OX758WbGxserYsaPGjRtXbSUVAA/Utq30yCPS6tXShQvS++9LTz4pde4sff+9Vaz66U+l6GgpOdlaUbVvn3TtmrtHDgCog32lVFyce8cBAAAal9uKUhcuXFB5ebkib1ixEBkZqby8vHpd48UXX9SVK1c0efLkymPx8fFauXKlNm7cqIyMDAUFBWnIkCE6efJkjdcpKSlRYWGhQwPQggUEWCujXnlFOnNGys6WFi+WBgyQjJH27rX2nkpKksLDpeHDpXnzrI3V7TvpAgCaDfueUty+BwCAZ/Fz9wBsNpvDe2NMtWPOZGRkaNGiRfrLX/6iDh06VB5PSkpSUlJS5fshQ4aof//+euWVV/Tyyy87vdaSJUv03HPP3WQEAJo1m03q189qCxZI589bxad337U2Tf/2W2nHDqvZ9eolDRli7V81ZIjUvbt1HQCAW7CnFAAAnsltRamIiAj5+vpWWxWVn59fbfXUjVavXq0nnnhCa9as0b333ltrXx8fHw0cOLDWlVLz5s3TnDlzKt8XFhaqU6dO9YgCQIsTEyNNn261igrpxAmrOLVrl7R7t3T8uHTsmNX+53+scyIiqgpUQ4ZIiYkSD08AAJcoL7cWvUrcvgcAgKdxW1EqICBAiYmJyszM1IMPPlh5PDMzUxMnTqzxvIyMDD3++OPKyMjQAw88UOf3McYoOztbffv2rbFPYGCgAgMDGxYAgJbPx0eKj7faE09Yxy5csIpT9kLVgQPWsY0brSZZtwcOGFBVqBo82HpOOQCg0Z0/b23/5+cndezo7tEAAIDG5Nbb9+bMmaO0tDQNGDBAycnJev3115WTk6MZM2ZIslYwffXVV3r77bclWQWpRx99VL/97W+VlJRUucoqODhY4eHhkqTnnntOSUlJ6t69uwoLC/Xyyy8rOztbv//9790TJICWJSLCekrfhAnW+5IS6dChqpVUu3ZJ+fnW6927rUdCSdLtt1etpBoyxCp0+bht2z4A8Bj2/aS6dJF8fd06FAAA0MjcWpRKTU3VxYsXtXjxYuXm5qpPnz7avHmzYmNjJUm5ubnKycmp7P/aa6+prKxMM2fO1MyZMyuPp6ena+XKlZKkS5cuafr06crLy1N4eLjuvPNO7dixQ3fddZdLYwPgIQIDraf1JSdb742RvvjCsUj16afS//2f1d56y+rXpo11TmKi1Lev1KePtTeVn9u38gOAFoX9pAAA8Fw2Y4xx9yCam8LCQoWHh6ugoEBhYWHuHg6A5u6776Q9e6qKVPv2Sd9/X71fQIC1ibq9SGX/2qkTG6kDLZC35guujvvZZ6V//3fp5z+Xli9v8m8HAAAaQX3zBf5kDwC3qk0b6f77rSZJpaVSdrZVqDpyRDp61FpNdeWKdPiw1a4XFuZYpOrb12pt27o8FABoblgpBQCA56IoBQCNzd9fGjjQanYVFdbjoz75xCpS2b8ePy4VFlbtUXW96OiqQpW9WNW7txQS4tJwAMCd7HtKUZQCAMDzUJQCAFfw8bH+R9W1a9Um6pL1SKnjx6sXq86ckXJzrfb++1X9bTapWzfHFVX9+lkbrbOxOgAPxEopAAA8F0UpAHCngICq4tLUqVXHi4qsW/5uLFZ9803VpuobNlT1DwuT7rzT2ljd3rp3p1AFoEUrLpb+/rBlxcW5dywAAKDxUZQCgOaoVSspKclq18vPdyxSHT1q7VtVWCht3241u9tuq16o6tGDZ6oDaDHst+61bm1t3wcAADwLRSkAaEk6dJBGjbKaXVmZdOyYdPBgVcvOli5flnbutJpdaGhVoap/f+trfDyFKgDNEvtJAQDg2ShKAUBL5+dXdQvgtGnWsbIy6fPPqxeqrlyRPv7YanYhIdI//IPjiqr4eOu6AOBG7CcFAIBn438cAOCJ/PyqntqXnm4dKy+3NlW/vlCVlWUVqm58+l9wsLWBur1IlZBgbegSEWFttg4ALmAvSrGfFAAAnomiFAB4C19fqXdvq6WlWcfKy6UTJ6oXqi5flvbutdr1brvN+t9h167W1xtfh4S4Pi4AlcrKyrRo0SKtWrVKeXl5io6O1rRp0/TMM8/Ix8dHpaWleuaZZ7R582adOnVK4eHhuvfee7V06VLFxMS4e/jVsFIKAADPRlEKALyZr6/Uq5fVfvIT61hFhXTypGOh6uRJ6fx5q1hl32DdmchIx0LV9QWrjh25JRBoYi+88IKWL1+ut956SwkJCTpw4IAee+wxhYeHa9asWSouLtahQ4e0YMEC9evXT999951mz56tCRMm6MCBA+4efjXsKQUAgGezGWOMuwfR3BQWFio8PFwFBQUKCwtz93AAoHm4elU6c8b6X+Lp09YSBvvXU6esJwDWxs9P6tzZ+Sqrrl2ldu24NRAtSnPMF8aNG6fIyEitWLGi8thDDz2kkJAQ/eEPf3B6zv79+3XXXXfp7Nmz6ty5c53fw1VxG2Mtziwuturit9/eZN8KAAA0svrmC/zJGgBQP0FB1gbo8fHVPzNG+u475wWr06etYlZpaVUBy5nQUKlLF+ctNpb9rIB6GDp0qJYvX64TJ06oR48eOnz4sD7++GP913/9V43nFBQUyGazqXXr1i4bZ33k51sFKZvNqmcDAADPQ1EKAHDrbDapbVurJSZW/7y83Lr9z1nB6tQpKTfX2nD900+t5kxIiPNilf11+/YUreD1nn76aRUUFCg+Pl6+vr4qLy/X888/r6lTpzrtf/XqVc2dO1cPP/xwjX/FLCkpUUlJSeX7wrpWRTYS+617nTpJAQEu+ZYAAMDFKEoBAJqer6/1P8tOnaS7767++fffSzk51oqqM2eks2erXp85YxWtioulzz6zmjPBwTUXrLp0kTp0oGgFj7d69Wr98Y9/1J/+9CclJCQoOztbs2fPVkxMjNLtT+L8u9LSUk2ZMkUVFRV69dVXa7zmkiVL9NxzzzX10Kthk3MAADwfRSkAgPsFB0s9e1rNmatXpXPnHAtV1xeuzp+3ClvHjlnNmaAgqU8fafRoKSVFGjyY5RfwOP/6r/+quXPnasqUKZKkvn376uzZs1qyZIlDUaq0tFSTJ0/W6dOn9dFHH9W618O8efM0Z86cyveFhYXq1KlT0wXxdxSlAADwfBSlAADNX1CQ1L271Zy5dq32otVXX1mFrQMHrLZkibWH1YgRVoEqJUXq0YOVVGjxiouL5ePj43DM19dXFRUVle/tBamTJ09q69atateuXa3XDAwMVGBgYJOMtzb2olRcnMu/NQAAcBGKUgCAli8gQOrWzWrOlJZatwfu3i29/77V8vOld9+1mmTd7mcvUI0aJbVp47rxA41k/Pjxev7559W5c2clJCQoKytLL730kh5//HFJUllZmX70ox/p0KFDevfdd1VeXq68vDxJUtu2bRXQjFYP2veUYqUUAACey2aMMe4eRHPTHB/xDABoRBUV0tGj0pYtVoFq505rtZWdj480cGBVkWrQIMnf333jRbPUHPOFoqIiLViwQOvXr1d+fr5iYmI0depUPfvsswoICNCZM2cUV8PSo61bt+qee+6p83u4Ku7YWKuWvGePlJTUZN8GAAA0gfrmCxSlnGiOSSYAoAkVF0s7dlgFqi1bqm+mHhYmjRxZVaSqaUUWvIq35guuiPvaNeuuXWOkr7+2nlMAAABajvrmC9y+BwBASIg0ZozVJOnLL6XMTKtIlZkpXbwobdhgNckqStkLVCNGSOHh7ho54JHOnrUKUiEhUvv27h4NAABoKj51dwEAwMt07Cg99piUkWEt09i/X3r+eWn4cMnPT/riC2nZMunBB6V27aShQ6XFi6V9+6TycnePHmjxrt9PiucPAADguVgpBQBAbXx9pQEDrParX0lFRdK2bVUbpp84Ie3aZbWFC63+7dpZ9xu1b281++sbv7Zvb22o7sPfiIDr2Z+8xybnAAB4NopSAAA0RKtW0vjxVpOkM2eqClQffihdumQ92S8/v37X8/WVIiJqL2Jd/7p1a4pY8Hj2olQNe7IDAAAPQVEKAIBb0aWLNH261crLqwpS33xjNftrZ8cuXbLO+fprq9WHn5+1uuq226TQUMevNb2u61hIiFUcA5oJVkoBAOAdKEoBANBYfH2l6Gir1ce1a9KFC86LV86KWAUFUllZ1fHGFBzsWKyKiJD69pXuuMNqCQnWZ4ALXL+nFAAA8FwUpQAAcJeAACkmxmr1UVJiFbG+/Va6csVqly9Xfa3P6xuPVVRY1/7+e6tdX+zatq3qtc0mde9eVaS64w6pXz8pNpadqNHoWCkFAIB3oCgFAEBLERgo/eAHVmsMxkhXrzovWn35pXT0qHTkiHT4sLVa68QJq/35z1XXCAurWlHVr5/1tU8fa+8t4CZ89511Z6tk3R0LAAA8F0UpAAC8lc1m3bYXHGxtol6br7+2ClT2dviw9NlnUmFh1dMHr9e1a1WRyt66dmWTdtTJvkoqKsra7gwAAHguilIAAKBukZHS6NFWsystlY4frypS2QtW589blYVTp6T166v6h4Y67lN1xx3W+9atXR4Omi/2kwIAwHtQlAIAADfH39+6Va9PH+nhh6uOX7jguKrqyBHpk0+sWwP37rXa9Tp3dixW9e0r9ehhXR9eh/2kAADwHhSlAABA44qIkEaOtJpdWZl08mT1WwDPnZNycqy2aVNV/4AAqXfv6sWqqCg2Vvdw9qJUXJx7xwEAAJoeRSkAAND0/PykXr2slppadfzSJWtDdfum6keOWK8vX5ays612vYiIqgKV/WtCApsPeRBWSgEA4D0oSgEAAPdp3VoaNsxqdhUV0tmzVQUqe7Hq5Enr1sCPPrKanc0mde9efVVVXBwbq7dA7CkFAID3oCgFAACaFx8fq6AUFydNnFh1/PvvrSf+3Vis+uYb6cQJq61dW9XfvrH6vHnShAmujwMNVl4unTljvaYoBQCA56MoBQAAWobgYCkx0WrX+/prx1v/jhyRPv20amP10lL3jBcN9uWX1vZjAQFSTIy7RwMAAJoaRSkAANCyRUZKo0dbze76jdWHDnXf2NAgkZHSjh1Sfj53XgIA4A0oSgEAAM9z/cbqaDGCghy3FwMAAJ6Nv0EBAAAAAADA5ShKAQAAAAAAwOUoSgEAAAAAAMDlKEoBAAAAAADA5ShKAQAAAAAAwOUoSgEAAAAAAMDl3F6UevXVVxUXF6egoCAlJiZq586dNfZdt26dRo8erfbt2yssLEzJycnasmVLtX5r165V7969FRgYqN69e2v9+vVNGQIAAAAAAAAayK1FqdWrV2v27NmaP3++srKyNGzYMI0dO1Y5OTlO++/YsUOjR4/W5s2bdfDgQY0YMULjx49XVlZWZZ89e/YoNTVVaWlpOnz4sNLS0jR58mTt27fPVWEBAAAAAACgDjZjjHHXNx80aJD69++vZcuWVR7r1auXJk2apCVLltTrGgkJCUpNTdWzzz4rSUpNTVVhYaHee++9yj5jxoxRmzZtlJGRUa9rFhYWKjw8XAUFBQoLC2tARAAAwFt4a77grXEDAID6q2++4LaVUteuXdPBgweVkpLicDwlJUW7d++u1zUqKipUVFSktm3bVh7bs2dPtWved999tV6zpKREhYWFDg0AAAAAAABNx21FqQsXLqi8vFyRkZEOxyMjI5WXl1eva7z44ou6cuWKJk+eXHksLy+vwddcsmSJwsPDK1unTp0aEAkAAAAAAAAayu0bndtsNof3xphqx5zJyMjQokWLtHr1anXo0OGWrjlv3jwVFBRUtnPnzjUgAgAAAAAAADSUn7u+cUREhHx9fautYMrPz6+20ulGq1ev1hNPPKE1a9bo3nvvdfgsKiqqwdcMDAxUYGBgAyMAAAAAAADAzXLbSqmAgAAlJiYqMzPT4XhmZqYGDx5c43kZGRmaNm2a/vSnP+mBBx6o9nlycnK1a77//vu1XhMAAAAAAACu5baVUpI0Z84cpaWlacCAAUpOTtbrr7+unJwczZgxQ5J1W91XX32lt99+W5JVkHr00Uf129/+VklJSZUrooKDgxUeHi5JmjVrlu6++2698MILmjhxov7yl7/ogw8+0Mcff+yeIAEAAAAAAFCNW4tSqampunjxohYvXqzc3Fz16dNHmzdvVmxsrCQpNzdXOTk5lf1fe+01lZWVaebMmZo5c2bl8fT0dK1cuVKSNHjwYL3zzjt65plntGDBAnXr1k2rV6/WoEGD6j0uY4wk8RQ+AABQI3ueYM8bvAV5EgAAqEt98ySb8bZMqh6+/PJLnsAHAADq5dy5c+rYsaO7h+Ey5EkAAKC+6sqTKEo5UVFRofPnz6tVq1b1ehJgQxUWFqpTp046d+6cwsLCGv36zZm3xu6tcUvE7o2xe2vcErF7W+zGGBUVFSkmJkY+Pm5/oLHLkCc1HW+N3VvjlojdG2P31rglYve22OubJ7n19r3mysfHxyV/8QwLC/OaH8gbeWvs3hq3ROzeGLu3xi0RuzfFbt/T0puQJzU9b43dW+OWiN0bY/fWuCVi96bY65Mnec+f9QAAAAAAANBsUJQCAAAAAACAy1GUcoPAwEAtXLhQgYGB7h6Ky3lr7N4at0Ts3hi7t8YtEbu3xo7G5c0/S94au7fGLRG7N8burXFLxO6tsdeFjc4BAAAAAADgcqyUAgAAAAAAgMtRlAIAAAAAAIDLUZQCAAAAAACAy1GUaiKvvvqq4uLiFBQUpMTERO3cubPW/tu3b1diYqKCgoLUtWtXLV++3EUjbTxLlizRwIED1apVK3Xo0EGTJk3S8ePHaz1n27Ztstls1drnn3/uolHfukWLFlUbf1RUVK3neMJ8S1KXLl2czt/MmTOd9m/J871jxw6NHz9eMTExstls2rBhg8PnxhgtWrRIMTExCg4O1j333KNPP/20zuuuXbtWvXv3VmBgoHr37q3169c3UQQ3p7a4S0tL9fTTT6tv374KDQ1VTEyMHn30UZ0/f77Wa65cudLpz8HVq1ebOJqGqWvOp02bVi2GpKSkOq/b3Odcqjt2Z/Nns9n0n//5nzVes6XMO1yDPIk8qTaeMN8SedL1yJPIk8iTyJNqQlGqCaxevVqzZ8/W/PnzlZWVpWHDhmns2LHKyclx2v/06dO6//77NWzYMGVlZelXv/qV/umf/klr16518chvzfbt2zVz5kzt3btXmZmZKisrU0pKiq5cuVLnucePH1dubm5l6969uwtG3HgSEhIcxn/06NEa+3rKfEvS/v37HeLOzMyUJP34xz+u9byWON9XrlxRv3799Lvf/c7p5//xH/+hl156Sb/73e+0f/9+RUVFafTo0SoqKqrxmnv27FFqaqrS0tJ0+PBhpaWlafLkydq3b19ThdFgtcVdXFysQ4cOacGCBTp06JDWrVunEydOaMKECXVeNywszOFnIDc3V0FBQU0Rwk2ra84lacyYMQ4xbN68udZrtoQ5l+qO/ca5e+ONN2Sz2fTQQw/Vet2WMO9oeuRJ5EnkSeRJ5Em1awn/XpInkSc1GoNGd9ddd5kZM2Y4HIuPjzdz58512v/f/u3fTHx8vMOxn//85yYpKanJxugK+fn5RpLZvn17jX22bt1qJJnvvvvOdQNrZAsXLjT9+vWrd39PnW9jjJk1a5bp1q2bqaiocPq5J8y3McZIMuvXr698X1FRYaKioszSpUsrj129etWEh4eb5cuX13idyZMnmzFjxjgcu++++8yUKVMafcyN4ca4nfnb3/5mJJmzZ8/W2OfNN9804eHhjTu4JuYs9vT0dDNx4sQGXaelzbkx9Zv3iRMnmpEjR9bapyXOO5oGeZKFPMk5T51vY8iTyJPIk+rS0ubcGPKkxsBKqUZ27do1HTx4UCkpKQ7HU1JStHv3bqfn7Nmzp1r/++67TwcOHFBpaWmTjbWpFRQUSJLatm1bZ98777xT0dHRGjVqlLZu3drUQ2t0J0+eVExMjOLi4jRlyhSdOnWqxr6eOt/Xrl3TH//4Rz3++OOy2Wy19m3p832j06dPKy8vz2FeAwMDNXz48Bp/76WafxZqO6e5KygokM1mU+vWrWvtd/nyZcXGxqpjx44aN26csrKyXDPARrZt2zZ16NBBPXr00M9+9jPl5+fX2t8T5/zrr7/Wpk2b9MQTT9TZ11PmHTePPKkKeZJznjrf5EnkSRJ5EnlS7Txl3huKolQju3DhgsrLyxUZGelwPDIyUnl5eU7PycvLc9q/rKxMFy5caLKxNiVjjObMmaOhQ4eqT58+NfaLjo7W66+/rrVr12rdunXq2bOnRo0apR07drhwtLdm0KBBevvtt7Vlyxb993//t/Ly8jR48GBdvHjRaX9PnG9J2rBhgy5duqRp06bV2McT5tsZ++92Q37v7ec19Jzm7OrVq5o7d64efvhhhYWF1dgvPj5eK1eu1MaNG5WRkaGgoCANGTJEJ0+edOFob93YsWO1atUqffTRR3rxxRe1f/9+jRw5UiUlJTWe42lzLklvvfWWWrVqpR/+8Ie19vOUecetIU+ykCeRJznjCfPtDHmShTyJPKk2njLvN8PP3QPwVDf+BcQYU+tfRZz1d3a8pXjyySd15MgRffzxx7X269mzp3r27Fn5Pjk5WefOndOvf/1r3X333U09zEYxduzYytd9+/ZVcnKyunXrprfeektz5sxxeo6nzbckrVixQmPHjlVMTEyNfTxhvmvT0N/7mz2nOSotLdWUKVNUUVGhV199tda+SUlJDhtdDhkyRP3799crr7yil19+uamH2mhSU1MrX/fp00cDBgxQbGysNm3aVGvi4SlzbvfGG2/okUceqXPPA0+ZdzQO8iTyJPKk6jxhvmtDnkSeRJ5UM0+Z95vBSqlGFhERIV9f32rV3Pz8/GpVX7uoqCin/f38/NSuXbsmG2tTeeqpp7Rx40Zt3bpVHTt2bPD5SUlJLboiHBoaqr59+9YYg6fNtySdPXtWH3zwgX760582+NyWPt+SKp8i1JDfe/t5DT2nOSotLdXkyZN1+vRpZWZm1vrXP2d8fHw0cODAFv9zEB0drdjY2Frj8JQ5t9u5c6eOHz9+U7/7njLvaBjyJPIk8qSGaenzLZEnkSdZyJMaxlPmvT4oSjWygIAAJSYmVj5dwy4zM1ODBw92ek5ycnK1/u+//74GDBggf3//JhtrYzPG6Mknn9S6dev00UcfKS4u7qauk5WVpejo6EYeneuUlJTo2LFjNcbgKfN9vTfffFMdOnTQAw880OBzW/p8S1JcXJyioqIc5vXatWvavn17jb/3Us0/C7Wd09zYE62TJ0/qgw8+uKn/MBhjlJ2d3eJ/Di5evKhz587VGocnzPn1VqxYocTERPXr16/B53rKvKNhyJPIk8iTGqalz7dEnkSeZCFPahhPmfd6ce2+6t7hnXfeMf7+/mbFihXms88+M7NnzzahoaHmzJkzxhhj5s6da9LS0ir7nzp1yoSEhJh//ud/Np999plZsWKF8ff3N3/+85/dFcJN+cUvfmHCw8PNtm3bTG5ubmUrLi6u7HNj7L/5zW/M+vXrzYkTJ8wnn3xi5s6daySZtWvXuiOEm/LLX/7SbNu2zZw6dcrs3bvXjBs3zrRq1crj59uuvLzcdO7c2Tz99NPVPvOk+S4qKjJZWVkmKyvLSDIvvfSSycrKqnx6ytKlS014eLhZt26dOXr0qJk6daqJjo42hYWFlddIS0tzeLrUrl27jK+vr1m6dKk5duyYWbp0qfHz8zN79+51eXw1qS3u0tJSM2HCBNOxY0eTnZ3t8HtfUlJSeY0b4160aJH561//ar744guTlZVlHnvsMePn52f27dvnjhBrVFvsRUVF5pe//KXZvXu3OX36tNm6datJTk42P/jBD1r8nBtT98+7McYUFBSYkJAQs2zZMqfXaKnzjqZHnkSeRJ5k8aT5Jk8iTyJPIk+6WRSlmsjvf/97ExsbawICAkz//v0dHvebnp5uhg8f7tB/27Zt5s477zQBAQGmS5cuNf7wNmeSnLY333yzss+Nsb/wwgumW7duJigoyLRp08YMHTrUbNq0yfWDvwWpqakmOjra+Pv7m5iYGPPDH/7QfPrpp5Wfe+p8223ZssVIMsePH6/2mSfNt/0xzTe29PR0Y4z1uOOFCxeaqKgoExgYaO6++25z9OhRh2sMHz68sr/dmjVrTM+ePY2/v7+Jj49vdolnbXGfPn26xt/7rVu3Vl7jxrhnz55tOnfubAICAkz79u1NSkqK2b17t+uDq0NtsRcXF5uUlBTTvn174+/vbzp37mzS09NNTk6OwzVa4pwbU/fPuzHGvPbaayY4ONhcunTJ6TVa6rzDNciTyJPsPHW+7ciT0o0x5EnkSeRJN2qp894UbMb8fedAAAAAAAAAwEXYUwoAAAAAAAAuR1EKAAAAAAAALkdRCgAAAAAAAC5HUQoAAAAAAAAuR1EKAAAAAAAALkdRCgAAAAAAAC5HUQoAAAAAAAAuR1EKAAAAAAAALkdRCgCakM1m04YNG9w9DAAAgGaHPAkARSkAHmvatGmy2WzV2pgxY9w9NAAAALciTwLQHPi5ewAA0JTGjBmjN9980+FYYGCgm0YDAADQfJAnAXA3VkoB8GiBgYGKiopyaG3atJFkLRlftmyZxo4dq+DgYMXFxWnNmjUO5x89elQjR45UcHCw2rVrp+nTp+vy5csOfd544w0lJCQoMDBQ0dHRevLJJx0+v3Dhgh588EGFhISoe/fu2rhxY9MGDQAAUA/kSQDcjaIUAK+2YMECPfTQQzp8+LB+8pOfaOrUqTp27Jgkqbi4WGPGjFGbNm20f/9+rVmzRh988IFDMrVs2TLNnDlT06dP19GjR7Vx40bdfvvtDt/jueee0+TJk3XkyBHdf//9euSRR/Ttt9+6NE4AAICGIk8C0OQMAHio9PR04+vra0JDQx3a4sWLjTHGSDIzZsxwOGfQoEHmF7/4hTHGmNdff920adPGXL58ufLzTZs2GR8fH5OXl2eMMSYmJsbMnz+/xjFIMs8880zl+8uXLxubzWbee++9RosTAACgociTADQH7CkFwKONGDFCy5YtczjWtm3bytfJyckOnyUnJys7O1uSdOzYMfXr10+hoaGVnw8ZMkQVFRU6fvy4bDabzp8/r1GjRtU6hjvuuKPydWhoqFq1aqX8/PybDQkAAKBRkCcBcDeKUgA8WmhoaLVl4nWx2WySJGNM5WtnfYKDg+t1PX9//2rnVlRUNGhMAAAAjY08CYC7sacUAK+2d+/eau/j4+MlSb1791Z2drauXLlS+fmuXbvk4+OjHj16qFWrVurSpYs+/PBDl44ZAADAFciTADQ1VkoB8GglJSXKy8tzOObn56eIiAhJ0po1azRgwAANHTpUq1at0t/+9jetWLFCkvTII49o4cKFSk9P16JFi/TNN9/oqaeeUlpamiIjIyVJixYt0owZM9ShQweNHTtWRUVF2rVrl5566inXBgoAANBA5EkA3I2iFACP9te//lXR0dEOx3r27KnPP/9ckvXEl3feeUf/+I//qKioKK1atUq9e/eWJIWEhGjLli2aNWuWBg4cqJCQED300EN66aWXKq+Vnp6uq1ev6je/+Y3+5V/+RREREfrRj37kugABAABuEnkSAHezGWOMuwcBAO5gs9m0fv16TZo0yd1DAQAAaFbIkwC4AntKAQAAAAAAwOUoSgEAAAAAAMDluH0PAAAAAAAALsdKKQAAAAAAALgcRSkAAAAAAAC4HEUpAAAAAAAAuBxFKQAAAAAAALgcRSkAAAAAAAC4HEUpAAAAAAAAuBxFKQAAAAAAALgcRSkAAAAAAAC4HEUpAAAAAAAAuNz/A+sxAZJhS0UCAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 1200x500 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#Plot the training curves\n",
+    "plt.figure(figsize=(12,5))\n",
+    "plt.subplot(1,2,1)\n",
+    "plt.plot(train_loss, label='Training Loss - Modified CNN',  color='red')\n",
+    "plt.title(\"Training Loss\")\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.legend()\n",
+    "\n",
+    "plt.subplot(1,2,2)\n",
+    "plt.plot(train_accuracy, label='Training Accuracy - Modified CNN', color='blue')\n",
+    "plt.title(\"Training Accuracy\")\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.legend()\n",
+    "plt.tight_layout()\n",
+    "plt.savefig('fashion_mnist_cnn_training_curves.jpeg', dpi = 600)\n",
+    "plt.show()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Homework4/Homework4_CPTS570.pdf b/Homework4/Homework4_CPTS570.pdf
new file mode 100644
index 0000000..ae3e206
Binary files /dev/null and b/Homework4/Homework4_CPTS570.pdf differ
diff --git a/Homework4/RL.ipynb b/Homework4/RL.ipynb
new file mode 100644
index 0000000..dfcbc57
--- /dev/null
+++ b/Homework4/RL.ipynb
@@ -0,0 +1,304 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Training with epsilon-greedy policy, epsilon = 0.1...\n",
+      "Converged after 1795 episodes with epsilon-greedy policy.\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x800 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Training with epsilon-greedy policy, epsilon = 0.2...\n",
+      "Converged after 1922 episodes with epsilon-greedy policy.\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAocAAAKECAYAAAB1gJBMAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAACSN0lEQVR4nOzdeVwV9f7H8dewHXYUkE0RcU0zwz01M80lc2lPq9ti2Wb9yuyW0qZ1LcpuZZtWtz2zut02LcvMykwrl9RMy9QSEFlEFGQ7CMzvD+LkEVBBGDiH9/PxmMfDM+d7Zr4fZg5++HznO2OYpmkiIiIiIgJ4NHYHRERERKTpUHIoIiIiIg5KDkVERETEQcmhiIiIiDgoORQRERERByWHIiIiIuKg5FBEREREHJQcioiIiIiDV2N3QERERORYiouLKSkpsXy/Pj4++Pr6Wr7fxqTkUERERJq04uJiYvwC2U+Z5fuOiorizz//bFYJopJDERERadJKSkrYTxmvecbjb+EVcYWUc3XGn5SUlCg5FBEREWlqArw98Tc8LdufYZbRCMXKRqcJKSIiIiLioMqhiIiIuATDy8DDMKzbn2ndvpoSVQ5FRERExEHJoYiIiIg4aFhZREREXILh7YFhWFfXMkzTsn01JaocioiIiIiDKociIiLiEjw8DTw8rJsk4lGuCSkiIiIi0swpORQRERERBw0ri4iIiEswvA0MC4eVDQ0ri4iIiEhzp8qhiIiIuAQPL01IsYIqhyIiIiLioMqhiIiIuARdc2gNVQ5FRERExEHJoYiIiIg4aFhZREREXIKHp4GHp4UTUso0rCwiIiIizZwqhyIiIuISDE8Dw8LKoYEqhyIiIiLSzCk5FBEREREHDSuLiIiIS7B8QoqGlUVERESkuVPlUERERFyC4WHxE1JMVQ5FREREpJlT5VBERERcguHpgeFpXV3LwLRsX02JKociIiIi4qDkUEREREQcNKwsIiIiLkG3srGGKociIiIi4qDKoYiIiLgEw7D4VjblqhyKiIiISDOn5FBEREREHDSsLCIiIi7B8MTSCSlG87zNoSqHIiIiIvI3VQ5FRETEJRieBoallUNNSBERERGRZk7JYT344YcfuPjii4mOjsbHx4fo6GguueQS1q5d22h92rVrF4Zh8Nprr1m+79deew3DMFi3bl21748dO5Z27do1aB9Wr17NrFmzOHDgQIPuxx2deeaZnHnmmU7rDMNg1qxZjdIfV9KY37uGVvm93rVrl2Pd1Vdf3eDfZat8+eWXDBgwAH9/f8LDw7n66qvJyso65ufS09O59957GTBgAOHh4QQHB9O7d29efPFFysrKLOh582J4eFi+NEfNM+p69MwzzzBo0CB2797NnDlz+PLLL3nsscdITU3ltNNO48UXX2zsLjZLq1ev5oEHHlByWAfz5s1j3rx5jd0NaWLGjBnD999/T3R0dGN3pd6tWLGC0aNHExkZyccff8xTTz3Fl19+yVlnnYXdbj/qZ9evX88bb7zBWWedxRtvvMH777/PkCFDuOmmm7juuussikCkfumawxOwatUqpk6dyjnnnMOHH36Il9ffP86JEydy/vnnM2XKFHr27Enfvn0bsacix69bt26N3YV6U1ZWRmlpKTabrbG74vJatWpFq1atGrsbDeLOO++kc+fO/O9//3P8Ho+Pj2fQoEG88sor3HTTTTV+dtCgQezcuRNvb2/HuhEjRlBSUsJzzz3HAw88QGxsbIPHIFKfVDk8AUlJSRiGwfz5850SQwAvLy9H9SUpKemo29m0aROGYfDyyy9Xee+zzz7DMAwWLVoEwI4dO5g0aRKdOnXC39+f1q1bM27cODZv3nzM/tY0BDRr1iwMw/miW9M0mTdvHgkJCfj5+dGyZUsuuugi/vjjj2Pupy6Od3/Lli3j3HPPpU2bNvj6+tKxY0duuOEGsrOzneK58847gYpf8IZhYBgG33zzDQDt2rVj7NixfPLJJ/Ts2RM/Pz+6du3KJ598AlQMn3Xt2pWAgAD69etXZXh83bp1TJw4kXbt2uHn50e7du249NJLSU5OdmpXOQy3bNkyJk2aRGhoKAEBAYwbN+64f47bt2/nsssuIyIiApvNRteuXXnuueec2nzzzTcYhsGCBQuYNm0aUVFR+Pn5MWTIEDZs2ODU9o8//mDixInExMRgs9mIjIzkrLPOYuPGjY421Q0rV+eXX37h3HPPpWXLlvj6+pKQkMDrr79ebd/efvtt7rnnHmJiYggODmb48OFs27btuH4GAP/5z3/o3LkzNpuNbt26sXDhwirnc+WQ7pw5c5g9ezbx8fHYbDa+/vproOK4jR8/ntDQUHx9fenZsyf//e9/q+wrIyODG264gTZt2uDj40N8fDwPPPAApaWlTu327NnDJZdcQlBQECEhIUyYMIGMjAynNm+++SaGYfD9999X2c+DDz6It7c3e/bsOe6fQ6WSkhJmz57NSSedhM1mo1WrVkyaNIm9e/c6tas81z/88EN69OiBr68v7du35+mnn3ZqV15ezuzZs+nSpQt+fn60aNGCHj168NRTTznaVDesXJ3i4mISExOJj4/Hx8eH1q1bc/PNN1ep4lf27fPPP6dXr174+flx0kkn8corr9T653Ei0tLSWLt2LVdccYXT7/GBAwfSuXNnPvzww6N+vmXLlk6JYaV+/foBsHv37vrtcDNneBiWL82RKod1VFZWxtdff02fPn1o06ZNtW1iY2Pp3bs3X375JeXl5XjUcO3CqaeeSs+ePXn11Ve59tprnd577bXXiIiI4JxzzgEq/kMKCwvjkUceoVWrVuTk5PD666/Tv39/NmzYQJcuXeolvhtuuIHXXnuNW2+9lUcffZScnBwefPBBBg4cyKZNm4iMjDzmNiqrNkcyzao3jjre/e3cuZMBAwYwefJkQkJC2LVrF0888QSnn346mzdvxtvbm8mTJ5OTk8MzzzzDBx984BgGO7witmnTJhITE7nnnnsICQnhgQce4IILLiAxMZHly5fz8MMPYxgG06dPZ+zYsfz555/4+fkBFUlIly5dmDhxIqGhoaSnpzN//nz69u3L1q1bCQ8Pd4rt2muvZcSIESxcuJDU1FTuvfdezjzzTH7++WdatGhR489v69atDBw4kLZt2/L4448TFRXF0qVLufXWW8nOzmbmzJlO7e+++2569erFSy+9RG5uLrNmzeLMM89kw4YNtG/fHoBzzjmHsrIy5syZQ9u2bcnOzmb16tW1Hn7ftm0bAwcOJCIigqeffpqwsDAWLFjA1VdfTWZmJnfddVeVvg0aNIiXXnqJvLw8pk+fzrhx4/j111/x9PQ86r5efPFFbrjhBi688EKefPJJcnNzeeCBB2oc7nv66afp3Lkz//73vwkODqZTp058/fXXnH322fTv35/nn3+ekJAQ3nnnHSZMmEBhYSFXX301UJEY9uvXDw8PD+6//346dOjA999/z+zZs9m1axevvvoqAEVFRQwfPpw9e/aQlJRE586d+fTTT5kwYYJTXyZMmMBdd93Fc889x4ABAxzrS0tLeeGFFzj//POJiYmp1c++vLycc889l5UrV3LXXXcxcOBAkpOTmTlzJmeeeSbr1q1znKsAGzduZOrUqcyaNYuoqCjeeustbrvtNkpKSvjnP/8JwJw5c5g1axb33nsvZ5xxBocOHeK3336r9XlhmibnnXcey5cvJzExkcGDB/Pzzz8zc+ZMvv/+e77//nunKu6mTZu44447mDFjBpGRkbz00ktce+21dOzYkTPOOOOo+yorK6v2d8mRPDw8avzdCxV/5AD06NGjyns9evRg1apVx9xHdb766iu8vLzo3LlznT4v0qhMqZOMjAwTMCdOnHjUdhMmTDABc+/evUdt9/TTT5uAuW3bNse6nJwc02azmXfccUeNnystLTVLSkrMTp06mbfffrtj/Z9//mkC5quvvupYd9VVV5lxcXFVtjFz5kzz8FPh+++/NwHz8ccfd2qXmppq+vn5mXfddddRY3n11VdN4KjL4f2o6/7Ky8vNQ4cOmcnJySZgfvzxx473HnvsMRMw//zzzyqfi4uLM/38/Mzdu3c71m3cuNEEzOjoaLOgoMCx/qOPPjIBc9GiRTXGW1paaubn55sBAQHmU089VeXncP755zu1X7VqlQmYs2fPrnGbpmmao0aNMtu0aWPm5uY6rb/llltMX19fMycnxzRN0/z6669NwOzVq5dZXl7uaLdr1y7T29vbnDx5smmappmdnW0C5ty5c4+63yFDhphDhgxxWgeYM2fOdLyeOHGiabPZzJSUFKd2o0ePNv39/c0DBw449e2cc85xavff//7XBMzvv//+qH0pKyszo6KizP79+zutT05ONr29vZ3Oo8pzvkOHDmZJSYlT+5NOOsns2bOneejQIaf1Y8eONaOjo82ysjLTNE3zhhtuMAMDA83k5GSndv/+979NwNyyZYtpmqY5f/78KuecaZrmddddV+V7N3PmTNPHx8fMzMx0rHv33XdNwFyxYsVR46/O22+/bQLm+++/77R+7dq1JmDOmzfPsS4uLs40DMPcuHGjU9sRI0aYwcHBjnN97NixZkJCwlH3W3k+H/6dOvJ3yueff24C5pw5c5w+Wxnviy++6NQ3X19fp591UVGRGRoaat5www1H/yH89flj/Z458rytzltvvVXjuXj99debPj4+x+zLkZYuXWp6eHg4/U6WE5Obm2sC5sqhp5kbRpxu2bJy6GkmUOX3sLvTsHIDM//6y7Zy2La8vJzS0lLHUjmb7fLLL8dmsznNcnz77bex2+1MmjTJsa60tJSHH36Ybt264ePjg5eXFz4+Pmzfvp1ff/21Xvr8ySefYBgG//jHP5z6GhUVxamnnuoYnj2WN954g7Vr11ZZTj/99DrvLysrixtvvJHY2Fi8vLzw9vYmLi4OoFbxJyQk0Lp1a8frrl27AhVDqv7+/lXWHz5knJ+fz/Tp0+nYsSNeXl54eXkRGBhIQUFBtX24/PLLnV4PHDiQuLg4x3BndYqLi1m+fDnnn38+/v7+Tj+Xc845h+LiYn744Qenz1x22WVOlwfExcUxcOBAx35CQ0Pp0KEDjz32GE888QQbNmygvLz8mD+r6nz11VecddZZVa6luvrqqyksLKwyjDp+/Hin15VVmsqfq2maTjFWVpy3bdtGRkYGl1xyidPn27Zty6BBg6rt2/jx452G+Xbs2MFvv/3mOA5H/izT09MdQ9yffPIJQ4cOJSYmxqnd6NGjgYqJCwBff/01QUFBVeK67LLLqvSn8nq1//znP451zz77LKeccsoxq2PV+eSTT2jRogXjxo1z6mNCQgJRUVFVvp8nn3wyp556apV+5uXl8dNPPwEVQ6CbNm1iypQpLF26lLy8vFr3CyrOC8BRia108cUXExAQwPLly53WJyQk0LZtW8drX19fOnfuXOUSjeosXry42t8vRy7XX3/9cfX9yEtrjrW+Jj/99BOXXHIJp5122jEvKRJpqjSsXEfh4eH4+/vz559/HrXdrl278PPzIywsDIBrrrnG6bqsIUOG8M033xAaGsr48eN54403+Ne//oWnpyevvfYa/fr14+STT3a0nzZtGs899xzTp09nyJAhtGzZEg8PDyZPnkxRUVG9xJaZmYlpmjUOHVcOUR5L165d6dOnT5X1ISEhpKam1np/5eXljBw5kj179nDfffdxyimnEBAQQHl5Oaeddlqt4g8NDXV67ePjc9T1xcXFjnWXXXYZy5cv57777qNv374EBwdjGAbnnHNOtX2Iioqqdt2+fftq7N++ffsoLS3lmWee4Zlnnqm2zeHXWR5tP5s2bQIq/pNbvnw5Dz74IHPmzOGOO+4gNDSUyy+/nIceeoigoKAa+1Nd/6qbtVo5RHpkbJXnf6XKocXKn9frr7/u9EcQVCSMldup7tyIjIys9vt3ZL8yMzMB+Oc//+kYRj1S5c8yMzOTxYsXV3sN2eHt9u3bV22fqjsGkZGRTJgwgRdeeIEZM2awZcsWVq5cyQsvvFDtPo4lMzOTAwcOOM7Nmvp4tD5Vrqv8+SYmJhIQEMCCBQt4/vnn8fT05IwzzuDRRx+t9jtck3379uHl5VVl4ophGNWe80eeF1BxbhzPd7lbt27HPax8NJV9qO77mJOTU+V3wtFs2LCBESNG0KlTJ5YsWaKJUOKylBzWkaenJ8OGDeOzzz5j9+7d1V53uHv3btavX8/ZZ5/tWDdr1ixuueUWx+vD/0OeNGkS7733HsuWLaNt27asXbuW+fPnO21zwYIFXHnllTz88MNO67Ozs496/RpU/FVe3XVaR/5nEh4ejmEYrFy5stpfbvX9C+949/fLL7+wadMmXnvtNa666irH+zt27KjX/hxNbm4un3zyCTNnzmTGjBmO9Xa7nZycnGo/c+Qkhcp1HTt2rHE/LVu2xNPTkyuuuIKbb7652jbx8fHHtZ/D/wOOi4tzTHz6/fff+e9//8usWbMoKSnh+eefr7E/RwoLCyM9Pb3K+srJFUded3ks48aNq/a+oJV9r0zwDlddvFC10lPZl8TERC644IJqP1N5rW54eDg9evTgoYceqrZdZfIbFhbGmjVrjrtPt912G2+++SYff/wxn3/+OS1atKhSUT5e4eHhhIWF8fnnn1f7/pFJfk3nBfz98/Xy8mLatGlMmzaNAwcO8OWXX3L33XczatQoUlNTnarpRxMWFkZpaSl79+51ShBN0yQjI6Ne79rQoUOH46owzpw586j36OzevTsAmzdvdlzbXWnz5s2O949lw4YNDB8+nLi4OL744gtCQkKO63NSO1ZPEtGEFKm1GTNmsGTJEqZMmcKHH37odGF9WVkZN910E2VlZdx2222O9e3atavxprEjR46kdevWvPrqq7Rt2xZfX18uvfRSpzaGYVRJoD799FPS0tKOmmxU7jsrK4vMzExH1aOkpISlS5c6tRs7diyPPPIIaWlpVYbzGsLx7q/yP/0j46+uAnNkZaq+GIaBaZpV+vDSSy/VeMPbt956iwsvvNDxevXq1SQnJzN58uQa9+Pv78/QoUPZsGEDPXr0qLFKdLi3336badOmOX5OycnJrF69miuvvLLa9p07d+bee+/l/fffdwwvHq+zzjqLDz/8kD179jhNqHjjjTfw9/fntNNOq9X2wsLCqq0idenShaioKP773/8ybdo0x/qUlBRWr159XJM5unTpQqdOndi0aVOVP6qONHbsWJYsWUKHDh1o2bJlje2GDh3Kf//7XxYtWuQ0tLxw4cJq2/fu3ZuBAwfy6KOP8ssvv3D99dcTEBBwzL7X1Md33nmHsrIy+vfvf8z2W7ZsYdOmTU5DywsXLiQoKIhevXpVad+iRQsuuugi0tLSmDp1Krt27Tru2xudddZZzJkzhwULFnD77bc71r///vsUFBRw1llnHdd2jsfixYuPeQ9C4JjnSOvWrenXrx8LFizgn//8p+P3+A8//MC2bduYOnXqMfexceNGhg8fTps2bVi2bNlRzx0RV6Dk8AQMGjSIuXPnctttt3H66adzyy230LZtW1JSUnjuuef4/vvvmTVrFiNGjDiu7Xl6enLllVfyxBNPEBwczAUXXFDlr8+xY8fy2muvcdJJJ9GjRw/Wr1/PY489VuOM6cNNmDCB+++/n4kTJ3LnnXdSXFzM008/XSWpGTRoENdffz2TJk1i3bp1nHHGGQQEBJCens53333HKaecctT7ftXW8e7vpJNOokOHDsyYMQPTNAkNDWXx4sUsW7asyjZPOeUUAJ566imuuuoqvL296dKlS62GTqsTHBzMGWecwWOPPUZ4eDjt2rVjxYoVvPzyyzVWbtetW8fkyZO5+OKLSU1N5Z577qF169ZMmTLlqPt66qmnOP300xk8eDA33XQT7dq14+DBg+zYsYPFixc7ru+qlJWVxfnnn891111Hbm4uM2fOxNfXl8TERAB+/vlnbrnlFi6++GI6deqEj48PX331FT///LNTFfR4zJw503F93v33309oaChvvfUWn376KXPmzKm3qomHhwcPPPAAN9xwAxdddBHXXHMNBw4c4IEHHiA6OvqYQ4aVXnjhBUaPHs2oUaO4+uqrad26NTk5Ofz666/89NNPvPfee0DF7WWWLVvGwIEDufXWW+nSpQvFxcXs2rWLJUuW8Pzzz9OmTRuuvPJKnnzySa688koeeughxzDikX9oHe62225jwoQJGIZR7bH/5ptvGDp06DErXRMnTuStt97inHPO4bbbbqNfv354e3uze/duvv76a84991zOP/98R/uYmBjGjx/PrFmziI6OZsGCBSxbtoxHH33UUREcN24c3bt3p0+fPrRq1Yrk5GTmzp1LXFwcnTp1Oq6fMVTc32/UqFFMnz6dvLw8Bg0a5Jit3LNnT6644orj3taxVH7H68Ojjz7KiBEjuPjii5kyZQpZWVnMmDGD7t27O13ukJycTIcOHbjqqqscFfht27YxfPhwAB566CG2b9/O9u3bHZ/p0KGD294fsjEYhrVPLTGM5jk1Q8nhCfq///s/+vTpw+OPP84dd9zB3r17KS8vx9fXl08//bTKMMWxTJo0iaSkJPbu3VvlGiyoSBi8vb1JSkoiPz+fXr168cEHH3Dvvfcec9vx8fF8/PHH3H333Vx00UVER0czbdo09u7dywMPPODU9oUXXuC0007jhRdeYN68eZSXlxMTE8OgQYMc9++qT8ezP29vbxYvXsxtt93GDTfcgJeXF8OHD+fLL790uqgdKiaWJCYm8vrrr/Of//yH8vJyvv766+O6f9+xLFy4kNtuu4277rqL0tJSBg0axLJlyxgzZky17V9++WXefPNNJk6ciN1uZ+jQoTz11FPHvJapW7du/PTTT/zrX//i3nvvJSsrixYtWtCpU6dqz6uHH36YtWvXMmnSJPLy8ujXrx/vvPMOHTp0ACquM+vQoQPz5s0jNTUVwzBo3749jz/+OP/3f/9Xq59Bly5dWL16NXfffTc333wzRUVFdO3alVdffbXKZIQTdf311zvuX3j++efTrl07ZsyYwccff0xKSspxbWPo0KGsWbOGhx56iKlTp7J//37CwsLo1q2bU7U6OjqadevW8a9//YvHHnuM3bt3ExQURHx8PGeffbajIuTv789XX33FbbfdxowZMzAMg5EjR/LOO+8wcODAavtw3nnnYbPZGDp0aLUJV35+vqMPR+Pp6cmiRYt46qmnePPNN0lKSsLLy4s2bdowZMiQKklTQkICkyZNYubMmWzfvp2YmBieeOIJp8re0KFDef/99x23GoqKimLEiBHcd999NV5/WR3DMPjoo4+YNWsWr776Kg899BDh4eFcccUVPPzww032GrwzzzyTJUuWcP/99zNu3Dj8/f0ZO3Ysjz32mFOfTdOkrKzM6Q/q77//3nG94rhx46psuyG+EyINzTCP54peqZU33niDq666irvuuotHH320sbsjjeS1115j0qRJrF27tlYX9ddWZcXpvffe46KLLmqw/TQlBw4coHPnzpx33nku84jKxYsXM378+Br/aLzrrrt4++232b59O76+vvWyz3bt2tG9e3fHDd5FXFVeXh4hISGsHnk6gd7W1bXyD5Uy8IvvyM3NJTg42LL9NjZVDhvAlVdeSXp6OjNmzCAgIID777+/sbsk4rIyMjJ46KGHGDp0KGFhYSQnJ/Pkk09y8OBBp+t5m6qtW7eSnJzMHXfcQUJCguO2OEf6+uuvue++++otMRQRqSslhw1k+vTpTJ8+vbG7IeLybDYbu3btYsqUKeTk5DgmvDz//PNOt3lqqqZMmcKqVavo1asXr7/+eo33zatutraISGPQsLKIiIg0aZXDyj+MHmz5sPJpn61sdsPKzXMajoiIiIhUS8PKIiIi4hJ0E2xrWJ4clpeXs2fPHoKCgmr9zEoRERFpHKZpcvDgQWJiYo77HqPimixPDvfs2UNsbKzVuxUREZF6kJqaelwPXhDXZXlyWPmEit5nvYen1/E9r1NEREQaV1lpIeuXX3zCT5o6EYaHxU9IaaYVUsuTw8qhZE8vf7y86/ZsUREREWkcuiTM/WlCioiIiLgETUixRvOsl4qIiIhItVQ5FBEREZegyqE1VDkUEREREQclhyIiIiLioGFlERERcQkaVraGKociIiIi4qDKoYiIiLiEisqhlTfBVuVQRERERJo5JYciIiIi4qBhZREREXEJhoeBh6eFE1LKNKwsIiIiIs2cKociIiLiEnQrG2uocigiIiIiDkoORURERMRBw8oiIiLiEgwPD4vvc9g8a2jNM2oRERERqZYqhyIiIuISNCHFGrVODg8ePMh9993Hhx9+SFZWFj179uSpp56ib9++DdE/J0X5u9mxKYlDJbl4eQXSMWEG/kHtqrTLTPmUtB0LMTFpEd6L9t2nYnhUhJqTuZrkrfMxzTL8gzvSKWEGnl7+Dd53d4pBcTStONwhBneJwx1iUBxNKw53iEFcT62HlSdPnsyyZct488032bx5MyNHjmT48OGkpaU1RP+c7Nz8OJFtx9Jr6AJiOkxkx6Y5VdoUF6aTsu0Vug96hl5D36LEnkNm6hIAykoL2bnpMbr0nU2vYQvxsYWye/uCBu+3u8UAiqMpxeEOMYB7xOEOMYDiaEpxuEMM9amycmjl0hzVKjksKiri/fffZ86cOZxxxhl07NiRWbNmER8fz/z58xuqjwCU2PdTkPs7rVqPACAsegj2onSKC9Od2u1LX0FY1GB8bKEYhkFU2/Fkpy0HYH/WGgJadME/MA6AqHbnkb1neYP2291iUBxNKw53iMFd4nCHGBRH04rDHWIQ11Sr5LC0tJSysjJ8fX2d1vv5+fHdd99V+xm73U5eXp7TUhclRVn4+IY7yuSGYWDzjcRelOW8v6JMbH6Rjtc2/yjsxVk1vldSnI1pltepT7XlDjGA4mhKcbhDDOAecbhDDKA4mlIc7hCDuKZaJYdBQUEMGDCAf/3rX+zZs4eysjIWLFjAjz/+SHp6erWfSUpKIiQkxLHExsaeQHedy7smZg3NDKdWzlto7BKxO8QAiuPwLTR2HO4QA7hHHO4QAyiOw7fQ2HG4Qwz1p/JWNlYuzVGto37zzTcxTZPWrVtjs9l4+umnueyyy/D09Ky2fWJiIrm5uY4lNTW1Th318YugpHgvZnkpAKZpUlKchc0vwqmdzS8Se2GG47W9MBObb4TjveKiw9/LqPirzLDm4LtDDKA4mlIc7hADuEcc7hADKI6mFIc7xCCuqdZnR4cOHVixYgX5+fmkpqayZs0aDh06RHx8fLXtbTYbwcHBTktd+NhaEhDckb1py4CKayxsflH4+kc7tQuLOoN9GSspsedgmiYZKYsIbz0MgJYR/cg/8BuF+ckAZOz6iPCYYXXqT3ONQXE0rTjcIQZ3icMdYlAcTSsOd4ihvmlCijUM0zRrqFEfn/379xMfH8+cOXO4/vrrj9k+Ly+PkJAQ+o36FC/vgFrtqyg/he0bH6H0UB6eXv50SkjEPyieHZvmEBo5iNCoQQBkJn9C2s6KKf0hYT1pf8o0PCqn9GesIvnX5yum9Ae1p2NCYq37cSLcIQbF0bTicIcY3CUOd4hBcTStOJpSDKWHClizdAy5ubl1LvTUVWXusOXacQT5eFu234Mlhzj55cWNEnNjqnVyuHTpUkzTpEuXLuzYsYM777wTm83Gd999h7f3sQ/YiSSHIiIi0jiUHDaf5LDWN8HOzc0lMTGR3bt3ExoayoUXXshDDz10XImhiIiISF3p2crWqHVyeMkll3DJJZc0RF9EREREpJHp2coiIiLiGgzjiNv2WLC/Zqh51ktFREREpFpKDkVERMQlGIbFt7KpY+Vw3rx5xMfH4+vrS+/evVm5cuVR27/11luceuqp+Pv7Ex0dzaRJk9i3b1+d9l0flByKiIiI1JN3332XqVOncs8997BhwwYGDx7M6NGjSUlJqbb9d999x5VXXsm1117Lli1beO+991i7di2TJ0+2uOd/U3IoIiIiUk+eeOIJrr32WiZPnkzXrl2ZO3cusbGxzJ8/v9r2P/zwA+3atePWW28lPj6e008/nRtuuIF169ZZ3PO/KTkUERERl9BYz1bOy8tzWux2e7X9KykpYf369YwcOdJp/ciRI1m9enW1nxk4cCC7d+9myZIlmKZJZmYm//vf/xgzZkz9/vBqQcmhiIiIyFHExsYSEhLiWJKSkqptl52dTVlZGZGRkU7rIyMjycjIqPYzAwcO5K233mLChAn4+PgQFRVFixYteOaZZ+o9juOlW9mIiIiIS7D6eceV+0pNTXV6QorNZjv6546YyGKaZo2TW7Zu3cqtt97K/fffz6hRo0hPT+fOO+/kxhtv5OWXXz7BCOpGyaGIiIjIUQQHBx/X4/PCw8Px9PSsUiXMysqqUk2slJSUxKBBg7jzzjsB6NGjBwEBAQwePJjZs2cTHR194gHUkoaVRUREROqBj48PvXv3ZtmyZU7rly1bxsCBA6v9TGFhIR5HPKbP09MTqKg4NgZVDkVERMQluMKzladNm8YVV1xBnz59GDBgAC+++CIpKSnceOONACQmJpKWlsYbb7wBwLhx47juuuuYP3++Y1h56tSp9OvXj5iYmHqN53gpORQRERGpJxMmTGDfvn08+OCDpKen0717d5YsWUJcXBwA6enpTvc8vPrqqzl48CDPPvssd9xxBy1atGDYsGE8+uijjRUChmlxzTIvL4+QkBD6jfoUL+8AK3ctIiIidVR6qIA1S8eQm5t7XNff1afK3GH7bZcQZPOxbL8H7SV0euq/jRJzY9I1hyIiIiLioGFlERERcQmNdSub5kaVQxERERFxUHIoIiIiIg4aVhYRERHX4OFRsVi5v2aoeUYtIiIiItVS5VBERERcgmEYNT6juKH21xypcigiIiIiDkoORURERMRBw8oiIiLiElzh2cruoHlGLSIiIiLVUuVQREREXIKekGINVQ5FRERExEGVQxEREXENhsU3wTaaZw2teUYtIiIiItVScigiIiIiDhpWFhEREddg8YQUNCFFRERERJo7VQ5FRETEJRiGB4aFk0Ss3FdT0jyjFhEREZFqKTkUEREREQcNK4uIiIhr8DCsnSSiCSkiIiIi0typcigiIiIuwfDwwLDwCSlW7qspaZ5Ri4iIiEi1XKpyWJS/mx2bkjhUkouXVyAdE2bgH9SuSrvMlE9J27EQE5MW4b1o330qhkdFqDmZq0neOh/TLMM/uCOdEmbg6eWvGBSHy8bhDjG4SxzuEIPiaFpxuEMM9cmw+CbYlt5wuwmpVeWwtLSUe++9l/j4ePz8/Gjfvj0PPvgg5eXlDdU/Jzs3P05k27H0GrqAmA4T2bFpTpU2xYXppGx7he6DnqHX0LcoseeQmboEgLLSQnZueowufWfTa9hCfGyh7N6+wJK+u1MMoDiaUhzuEAO4RxzuEAMojqYUhzvEIK6nVsnho48+yvPPP8+zzz7Lr7/+ypw5c3jsscd45plnGqp/DiX2/RTk/k6r1iMACIsegr0oneLCdKd2+9JXEBY1GB9bKIZhENV2PNlpywHYn7WGgBZd8A+MAyCq3Xlk71ne4H13pxgUR9OKwx1icJc43CEGxdG04nCHGMQ11So5/P777zn33HMZM2YM7dq146KLLmLkyJGsW7euofrnUFKUhY9vuKNMbhgGNt9I7EVZTu3sRZnY/CIdr23+UdiLs2p8r6Q4G9O0pvLpDjGA4mhKcbhDDOAecbhDDKA4mlIc7hBDvTMMMDwsXDSsfEynn346y5cv5/fffwdg06ZNfPfdd5xzzjk1fsZut5OXl+e01J3zQTIxa2hmOLVy3kJjH2h3iAEUx+FbaOw43CEGcI843CEGUByHb6Gx43CHGMTV1Co5nD59OpdeeiknnXQS3t7e9OzZk6lTp3LppZfW+JmkpCRCQkIcS2xsbJ066uMXQUnxXszyUgBM06SkOAubX4RTO5tfJPbCDMdre2EmNt8Ix3vFRYe/l1HxV5lFz050hxhAcTSlONwhBnCPONwhBlAcTSkOd4ihvlVOSLFyaY5qdXa8++67LFiwgIULF/LTTz/x+uuv8+9//5vXX3+9xs8kJiaSm5vrWFJTU+vUUR9bSwKCO7I3bRlQcY2FzS8KX/9op3ZhUWewL2MlJfYcTNMkI2UR4a2HAdAyoh/5B36jMD8ZgIxdHxEeM6xO/WmuMSiOphWHO8TgLnG4QwyKo2nF4Q4xiGsyTNOsoUZdVWxsLDNmzODmm292rJs9ezYLFizgt99+O65t5OXlERISQr9Rn+LlHVCrzhblp7B94yOUHsrD08ufTgmJ+AfFs2PTHEIjBxEaNQiAzORPSNtZMaU/JKwn7U+ZhkfllP6MVST/+nzFlP6g9nRMSKx1P06EO8SgOJpWHO4Qg7vE4Q4xKI6mFUdTiqH0UAFrlo4hNzeX4ODgeo3zWCpzh9SHbiTY12bdfovtxN7zfKPE3JhqlRyGhYUxe/ZsbrrpJse6pKQkXn31Vcd1iMdyIsmhiIiINI4mkRwmTbE+OUyc1+ySw1rdBHvcuHE89NBDtG3blpNPPpkNGzbwxBNPcM011zRU/0RERETEQrVKDp955hnuu+8+pkyZQlZWFjExMdxwww3cf//9DdU/EREREaDidj6GhbeXsXJfTUmtksOgoCDmzp3L3LlzG6g7IiIiItKYXOrZyiIiItKMGR7gYeFteFz0lj8nqnlGLSIiIiLVUnIoIiIiIg4aVhYRERGXYPVTS/SEFBERERFp9lQ5FBEREddgeFg7SUQTUkRERESkuVNyKCIiIiIOGlYWERER1+BhVCxW7q8ZUuVQRERERBxUORQRERGXYBgeGBZOErFyX01J84xaRERERKql5FBEREREHDSsLCIiIq5BE1IsocqhiIiIiDiocigiIiIuwfDwwPCwcEKKhftqSppn1CIiIiJSLVUOT8CqxUMauwsiTc6gcSsauwv1Qt9vqW/u8t1oVIZRsVi5v2ZIlUMRERERcVByKCIiIiIOGlYWERER1+BhgJWTRHQrGxERERFp7lQ5FBEREdegCSmWUOVQRERERByUHIqIiIiIg4aVRURExCXoCSnWaJ5Ri4iIiEi1VDkUERER12B4VCxW7q8Zap5Ri4iIiEi1VDkUERER12AY1t6YWreyEREREZHmTsmhiIiIiDhoWFlERERcgmF4YFg4ScTKfTUlzTNqEREREamWKociIiLiGjwsnpBi5b6aEFUORURERMRByaGIiIiIOGhYWURERFyDnpBiiVolh+3atSM5ObnK+ilTpvDcc8/VW6dqUpS/mx2bkjhUkouXVyAdE2bgH9SuSrvMlE9J27EQE5MW4b1o330qhkdFqDmZq0neOh/TLMM/uCOdEmbg6eXf4H0XkaPT91ukKn0vpDHUKiVeu3Yt6enpjmXZsmUAXHzxxQ3SuSPt3Pw4kW3H0mvoAmI6TGTHpjlV2hQXppOy7RW6D3qGXkPfosSeQ2bqEgDKSgvZuekxuvSdTa9hC/GxhbJ7+wJL+i4iR6fvt0hV+l4cwTCsX5qhWiWHrVq1IioqyrF88skndOjQgSFDhjRU/xxK7PspyP2dVq1HABAWPQR7UTrFhelO7falryAsajA+tlAMwyCq7Xiy05YDsD9rDQEtuuAfGAdAVLvzyN6zvMH7LiJHp++3SFX6XkhjqfNgeklJCQsWLOCaa67BsCCzLinKwsc33FEmNwwDm28k9qIsp3b2okxsfpGO1zb/KOzFWTW+V1KcjWmWN3j/RaRm+n6LVKXvRTU8PKxfmqE6T0j56KOPOHDgAFdfffVR29ntdux2u+N1Xl5eXXcJOCehJmYNzQynVs5baJ4lYpGmT99vkar0vRDr1Tklfvnllxk9ejQxMTFHbZeUlERISIhjiY2NrdP+fPwiKCnei1leCoBpmpQUZ2Hzi3BqZ/OLxF6Y4XhtL8zE5hvheK+46PD3Mir+Kmums5FEmgp9v0Wq0vdCGkudzo7k5GS+/PJLJk+efMy2iYmJ5ObmOpbU1NS67BIfW0sCgjuyN61iEsy+9BXY/KLw9Y92ahcWdQb7MlZSYs/BNE0yUhYR3noYAC0j+pF/4DcK8ytmXGfs+ojwmGF16o+I1B99v0Wq0veiGpW3srFyaYbqNKz86quvEhERwZgxY47Z1mazYbPZ6rKbKjr0uIPtGx9h94638PTyp1NCIgA7Ns0hNHIQoVGD8A2IoW3nSfyy6hZMTELCehIRW9FPTy9/Ova4k21r762Y0h/Uno5/bUNEGpe+3yJV6XshjcEwTbOGCxiqV15eTnx8PJdeeimPPPJIrXeYl5dHSEgI/UZ9ipd3QK0/35SsWtzws7RFXM2gcSsauwv1Qt9vqW+u/t0oPVTAmqVjyM3NJTg42NJ9V+YOmW89SrC/r3X7LSwm8vLpjRJzY6p1vfTLL78kJSWFa665piH6IyIiIiKNqNbDyiNHjqSWxUYRERERcRF6trKIiIi4BsOw+NnKzfM2QM1zGo6IiIiIVEuVQxEREXENVj/vWJVDEREREWnuVDkUERER12D1846b6bOVm2fUIiIiIlItJYciIiIi4qBhZREREXENmpBiCVUORURERMRBlUMRERFxDYaHxTfBbp41tOYZtYiIiIhUS8mhiIiIiDhoWFlERERcg2HxfQ41rCwiIiIizZ0qhyIiIuIadCsbS6hyKCIiIiIOqhyKiIiIa9CtbCzRPKMWERERkWqpcngCBo1b0dhdEDezavGQxu7CCfO2+TR2F+rFhbftbOwu1Iu2nSIbuwsnbMsPvzd2F0SaFSWHIiIi4ho0IcUSGlYWEREREQdVDkVERMQ1eFh8E2wr99WENM+oRURERKRaSg5FRERExEHDyiIiIuISTMPAtHCSiJX7akpUORQRERERB1UORURExDUYhsVPSFHlUERERESaOVUORURExDXo2cqWaJ5Ri4iIiEi1lByKiIiIiIOGlUVERMQl6FY21lDlUERERKQezZs3j/j4eHx9fenduzcrV648anu73c4999xDXFwcNpuNDh068Morr1jU26pUORQRERHX4AITUt59912mTp3KvHnzGDRoEC+88AKjR49m69attG3bttrPXHLJJWRmZvLyyy/TsWNHsrKyKC0tPdHe15mSQxEREZF68sQTT3DttdcyefJkAObOncvSpUuZP38+SUlJVdp//vnnrFixgj/++IPQ0FAA2rVrZ2WXq9CwsoiIiMhR5OXlOS12u73adiUlJaxfv56RI0c6rR85ciSrV6+u9jOLFi2iT58+zJkzh9atW9O5c2f++c9/UlRUVO9xHC9VDkVERMQ1GIa1Ty35a1+xsbFOq2fOnMmsWbOqNM/OzqasrIzIyEin9ZGRkWRkZFS7iz/++IPvvvsOX19fPvzwQ7Kzs5kyZQo5OTmNdt2hkkMRERGRo0hNTSU4ONjx2mazHbW9cUQCa5pmlXWVysvLMQyDt956i5CQEKBiaPqiiy7iueeew8/P7wR7X3tKDkVERMQ1eHhULFbuDwgODnZKDmsSHh6Op6dnlSphVlZWlWpipejoaFq3bu1IDAG6du2KaZrs3r2bTp06nUAAdVPr5DAtLY3p06fz2WefUVRUROfOnXn55Zfp3bt3Q/TPSVH+bnZsSuJQSS5eXoF0TJiBf1C7Ku0yUz4lbcdCTExahPeiffepGB4VoeZkriZ563xMswz/4I50SpiBp5d/g/fdnWJQHE0vDndQeDCVbev+VXEsvAPp0udeAoLjq7RL/3MxqdvexKSclq360KnnPzE8vMjP3cmOjf+mpHg/Hh5eBId2p2PCNDw8fSyLIf/ALtZ9cSclxfvxtgXTe/ijBIdV/cW+a8t/2bbuBTDLaRU7kIShD+Dx1/n0+08vkbL1fQwPLzw8fTj1zJmERvawLAaA/Vk7+GLBDRTl78Pm14KR/3iesOiTnNrk7kvmiwU3snf3z7Ro1YHL7vrW6f28nFS+fm8aB7J2AAannnE9CUNutDAKKMhLYcv3MzlkP4CXTxAnD5hFYEj7Ku3SdnzEn1tfA7Oc0Kh+nNR3huN4QEXV56flN3HwwO+cedFXFkag31GuxsfHh969e7Ns2TLOP/98x/ply5Zx7rnnVvuZQYMG8d5775Gfn09gYCAAv//+Ox4eHrRp08aSfh+pVun3/v37GTRoEN7e3nz22Wds3bqVxx9/nBYtWjRQ95zt3Pw4kW3H0mvoAmI6TGTHpjlV2hQXppOy7RW6D3qGXkPfosSeQ2bqEgDKSgvZuekxuvSdTa9hC/GxhbJ7+wJL+u5OMYDiaGpxuIPtGx4lOv5c+o16l9jOl7Nt/cNV2hQV7GHX1v+QcObz9Bv1HiX2HNJ3fQKAh4cPHRPuoN+od+g9/HVKSwtI3f62pTFs+Ope4rtPZOSVX9K513X8tDyxSpuC3FS2/jCXIRe/y8irvqK4cC+7trwHwIG9v7Jz0xucecn/OOuyxXQ49Qo2fTPL0hgAlr9zG90HTuLq+zfSZ/hUli2cUqWNzTeIgWPvY/RVL1d5zzRNPnnpMrr2u4yr7tvAlfeup1PP86u0a2i/rnmINh3PZ9D4D2nX7Uq2/vBglTZF+Wns+Hk+fUe8zKDxH2Mv2seenR87tUn9/V18A2Os6rYT/Y5yPdOmTeOll17ilVde4ddff+X2228nJSWFG2+s+OMoMTGRK6+80tH+sssuIywsjEmTJrF161a+/fZb7rzzTq655ppGGVKGWiaHjz76KLGxsbz66qv069ePdu3acdZZZ9GhQ4eG6p9DiX0/Bbm/06r1CADCoodgL0qnuDDdqd2+9BWERQ3GxxaKYRhEtR1PdtpyAPZnrSGgRRf8A+MAiGp3Htl7ljd4390pBsXR9OJwByXFORw88DuRbUcBEN56KMUF6RQXOB+L7N1fEx5zBj6+FcciOv48slKXAeAfFEtgSEcADMOToJZdKS7YY1kMxYX7OJC1hdiTKqoDMR3PpiBvNwV5u53ape34nJj2I/D1D8cwDNqfchm7f1/seN8sL6W0tGKW4iF7Hn6BUZbFAFB4cC9ZuzfRte9EADomnEvevmRy9yU7tfMNCKV1h4F42QKqbCN12zd4efvS+a+E0DAMAoKrH1JrKCXFORzM+Y2o+HMAiIg9i6L8PRTlO58TmSnLiWgzFJtfGIZh0KbThWTsWup4vyAvhYxdX9Cu29VWdh/Q76jqVD4hxcqltiZMmMDcuXN58MEHSUhI4Ntvv2XJkiXExVUcg/T0dFJSUhztAwMDWbZsGQcOHKBPnz5cfvnljBs3jqeffrrefm61Vath5UWLFjFq1CguvvhiVqxYQevWrZkyZQrXXXddjZ+x2+1OU77z8vLq1NGSoix8fMMdZXLDMLD5RmIvysLXP/rv/RVlYvP7+5eQzT8Ke3FWje+VFGdjmuUYFtxU0x1iUBxNLw53YC/KwnbEsfD1j6S4MAPfgL+PRXFRJjb/v5Ml34Bo7IWZVbZXVlpE+p+LaH9K1YpXQynKT8c3IMIxHGkYBv5BMRQd3ENA8N9DQ4UH9+Af3Nrx2j+oNYUHK/6zb9GqKx17XsPS187E2xaCp6cPZ1xkbfXz4P7dBIZE4eH5dxxBLWM5uD+VkLC449rGvozf8AsMZ8mrV7M/azvBoW054/yHCQmveplAQykuyMTm18rpePgGRFFckIHfYVXA4oIM/A47x/wCYygurLhezDTL+fXH2XTtO91pmNkq+h3luqZMmcKUKdX//nnttdeqrDvppJNYtmxZA/fq+NXqzPjjjz+YP38+nTp1YunSpdx4443ceuutvPHGGzV+JikpiZCQEMdy5HTw2jli9g9mDc0Mp1bOW2js5yS6QwygOA7fQlOIwx0c+XOs/lg4/7yrtikvL2Xrj/cRGtmP8Jgz6q97x6OaGYo1NDy8leNfhXlppP+xnJFXfcU5166iY89JrF06rf77eUzHdyxqUl52iJRt39D/7OlcPn0V7bqNYMmrk+qve8fryKpPTcfj8HaHtUne+iYtInoSFNqlATp3vPQ7yknlE1KsXJqhWkVdXl5Or169ePjhh+nZsyc33HAD1113HfPnz6/xM4mJieTm5jqW1NTUOnXUxy+CkuK9mOUVj5MxTZOS4ixsfhFO7Wx+kdgL/54lZC/MxOYb4XivuOjw9zIq/iqz6OC7QwygOJpaHO7A5heBvSjL6VgUF2bh6+88pOrrF+k0pFZckIHN/++qSEVieC8+vmF0OPV2azr/F7/AaIryMyg/LIai/HT8gpyvVfMPiqHwsKHmwoN78A+qqALt3vEZwWGd8AuoOL/iul1EdtpazPIyi6KAoJZtyD+wh/Kyv+M4uH83QS2P/w/74NC2RLTpQVh0VwBO6juRrNQNlFsYh29AJPbCTKfjUVyYiW/AEedUQJTTUHNRQbrjvNuf9RPpfyxm5UdjWfvFtRwqOcjKj8ZyyF63EbDa0u8oaSy1Ojuio6Pp1q2b07quXbs6jZ0fyWazOaaAH+9U8Or42FoSENyRvWkVZdd96Suw+UU5ldYBwqLOYF/GSkrsOZimSUbKIsJbDwOgZUQ/8g/8RmF+xbUzGbs+IjxmWJ3601xjUBxNLw534OMbSmCLzmSmVFzrlZ32Nb4B0U5DygDhrc8ke8+3lBRXHIv0Pz8iInY4UHGt3q8/3o+3TzCde82o8Z5iDcXXP4wWrbqR+lvFZIY9Oz7HP6i105AyQOuOo9jzxzKKC7MxTZM/Ni+kTeexAAQEx7Jvz3pKSwoASP/zK4JCO2B4eFoWh39QK1q16cGva98BYMfGjwkOa3vcQ8oA7bqNID83nfwDFUlX8tZlhEV3w8PCOHx8QwlqeRIZf1ZMzMhKXY5fQLTTkDJAROwwsnZ/jb1oX8WtQ7a/T2RcxdMteg59isHnL2HweZ/Qd+TLePsEMfi8T/C21e3/sVrHoN9RVZiGh+VLc2SYNY97VHHZZZeRmprKypUrHetuv/12fvzxxxofC3OkvLw8QkJC6DfqU7y8q17IfDRF+Sls3/gIpYfy8PTyp1NCIv5B8ezYNIfQyEGERg0CIDP5E9J2VkzpDwnrSftTpjmuF8nJWEXyr89XTOkPak/HhMRa9+NEuEMMiqPh4li1eEi9xdZYzrzo+zp9rvBgMr+tm01pSR6eXgGc1PdeAoLbs219EmHRpxMeMxiA9D8/JmXbAjBNWkT0plPPO/Hw8CIzZSm/rX2AgJCOVA7FhYSdQqee/6xTf8JaRxy70REO7v+D9cvuoqT4AF4+gfQZMYfgsM6s/zKR6PZnEdO+IpH985d3+H39i5imSas2p9Fz6IN4eHpjmiZbVv+bPX8sw9PTBy/vAE4dcj8tIk6uUwwAbTvVfiJITubvfLHgRooLcvDxDWbUFS8QFt2VZQtvpv0p59DhlDGUHrLz2oM9KCu1Yy/Kwz+oFSf1ncjp4x8AYNevX/Ldx/eDaWLzD2HYJU86Kom1teWH3+v0uYK8XWz5fhaH7Ll4egfQfcADBLbowJYfHqRVmyFEtKn4vu3e8QG7trwOmLSM7EPXfol4eHg7basofw8/fv6PE7qVTUHuwVp/pin9jio9VMCapWPIzc2tc6Gnripzh7Qv3yY4wLrb8OQVFNJ6+KWNEnNjqlVyuHbtWgYOHMgDDzzAJZdcwpo1a7juuut48cUXufzyy49rGyeSHIq4u+acHDY1dUkOm6K6JIdNTV2Tw6amLslhU6LksPkkh7Wql/bt25cPP/yQt99+m+7du/Ovf/2LuXPnHndiKCIiIlJnlc9WtnJphmo9N3/s2LGMHTu2IfoiIiIiIo1Mz1YWERERl2Bi7SQRs3YDrG6jeUYtIiIiItVScigiIiIiDhpWFhEREddg9SSRZjohRZVDEREREXFQ5VBERERcg2FY+7xjVQ5FREREpLlT5VBERERcgmkYmBZW86zcV1OiyqGIiIiIOCg5FBEREREHDSuLiIiIazA8LJ6Q0jxraM0zahERERGpliqHIiIi4hJMDEwsnJBi4b6aElUORURERMRByaGIiIiIOGhYWURERFyCaXhgWjhJxMp9NSXNM2oRERERqZYqhyIiIuIadCsbSyg5FJF6dche0thdqBcZf+xu7C7Ui3HntW/sLpywjNRWjd2FemEvLGrsLpwgpQzNhY60iIiIuAQ9W9kazbNeKiIiIiLVUnIoIiIiIg4aVhYRERGXoFvZWKN5Ri0iIiIi1VLlUERERFyDYVQsVu6vGVLlUERERMTF7dixg6VLl1JUVHHLJNM067wtJYciIiIiLmrfvn0MHz6czp07c84555Ceng7A5MmTueOOO+q0TSWHIiIi4hr+mpBi1eIKT0i5/fbb8fLyIiUlBX9/f8f6CRMm8Pnnn9dpm7rmUERERMRFffHFFyxdupQ2bdo4re/UqRPJycl12qaSQxEREXEJJgYmFj4hxcJ91VVBQYFTxbBSdnY2NputTtts+vVSEREREanWGWecwRtvvOF4bRgG5eXlPPbYYwwdOrRO21TlUERERFyCboJd1WOPPcaZZ57JunXrKCkp4a677mLLli3k5OSwatWqOm2z6UctIiIiItXq1q0bP//8M/369WPEiBEUFBRwwQUXsGHDBjp06FCnbapyKCIiIuLCoqKieOCBB+pte0oORURExDUYWPyEFOt2VVfffvvtUd8/44wzar1NJYciIiIiLurMM8+sss44LIEuKyur9TZ1zaGIiIi4BBMPy5embv/+/U5LVlYWn3/+OX379uWLL76o0zZVORQRERFxUSEhIVXWjRgxApvNxu2338769etrvU2XSg6L8nezY1MSh0py8fIKpGPCDPyD2lVpl5nyKWk7FmJi0iK8F+27T8XwqAg1J3M1yVvnY5pl+Ad3pFPCDDy9qt48UjEoDleKwx24w7FwhxgAMnZv56VHriY/Lxv/gBZcO/1VWrfr5tRm609f8f5Ld1NcdBDD8KDnoPFccM1sx3DWZ+88xqov3sA0y4lq04Vrp7+Cf2ALS+M4mPMnPyyZRklRDt62YPqf8zgh4Z2rtNv58zv8+sM8TMqJbDuIPiMfwuOv4/Hrj8+za8v/MM1ygkI70H/0v/HxrfqfcUMpyk9l2/qHOGQ/gJdPEJ173U1AcHyVdum7PiH19wVAOS1a9abTqXdgeHhRVlrI1h/v5eCBbQAMHPOpZX2XxtWqVSu2bdtWp8/Wql46a9YsDMNwWqKiouq047rYuflxItuOpdfQBcR0mMiOTXOqtCkuTCdl2yt0H/QMvYa+RYk9h8zUJQCUlRayc9NjdOk7m17DFuJjC2X39gWW9d9dYgDF0dTicAfucCzcIQaA15+4kTPHXscjb2xj9MQ7efXfk6u0CQhqyQ33LuShV7cw8/m1bNv0LT989TYAW9YtY9WyN7nn2dU89OoWYjueyvsv32N1GKz9IpEOp17GmOtW0LX/jaz5/K4qbfIPpLB55b8Zfvn7jL1uJcUFe/nj53cAyNj1Lbu2vM/wyz/inGu/omVEN35e+ZilMfy+4TGi2o2n78h3aNPpMn7/6ZEqbYoK9pD8639IOGMefUe8S0lxDunJnwBgGF606XQZPQbNtbTfDcU0DMuXpu7nn392WjZt2sTnn3/OTTfdxKmnnlqnbdZ6MP3kk08mPT3dsWzevLlOO66tEvt+CnJ/p1XrEQCERQ/BXpROcWG6U7t96SsIixqMjy20InltO57stOUA7M9aQ0CLLvgHxgEQ1e48svcst6T/7hKD4mh6cbgDdzgW7hADQN7+LJK3/8SAEf8AoM8ZF7I3/U+yM3Y5tYvr1JOImPYAePv4EtvhVPbu+QOAlJ2b6HzK6fj5BwGQMGAsq5dZm+QWF2SzP/MX2p18PgBtOp9DQW4q+bmpTu1Sty2hTeez8Q1ohWEYdEz4B8m/LgLgQNavtGrTD29bIAAxHc5i15YPLIuhxL6f/NzfiYwdCUB4zJkUF6ZTXOB8TmWnfUNY9Bn4+FacUzHx57F395cAeHj60DKiD17egZb1W6yVkJBAz549SUhIcPz7nHPOoaSkhJdffrlO26z1sLKXl5el1cJKJUVZ+PiGO4ZeDMPA5huJvSgLX/9oRzt7USY2v0jHa5t/FPbirBrfKynOxjTLMSy4C7o7xKA4ml4c7sAdjoU7xACQszeVluExeHr+HUdYRFv2ZaYQHtWu2s/k5mSw7tv3uT2pYsgyvksfvvnkRXJzMgluGcH3yxZQXHiQ/LwcAoNDLYmj8OAe/AIjHMPDhmHgHxRDYd4eAkNindoFBLd2vA4IaUNhXhoALaN6sGPjWxQX7MXmH86uLR9SWpKPvegANr8WDR6DvTAT2xHnlK9/JMVFmfgGOJ9Tvv5//79s84/CXpjZ4P1rDHpCSlV//vmn02sPDw9atWqFr69vnbdZ6+Rw+/btxMTEYLPZ6N+/Pw8//DDt27evsb3dbsdutzte5+Xl1a2nwJE3HDIxa2hmOLVy3kJjl4jdIQZQHIdvoSnE4Q7c4Vi4Qwxw3HEARQV5zL1nPOdMvJN2nXsBcFLCmZx98TTm3j0WD08veg+uqN55enk3XJerdeTPsqY4qj8ekW0HcFLf61jxv6vx8PCiTeezARwJZ2MwzdrFIO4vLi6u3rdZqzO8f//+vPHGG3Tu3JnMzExmz57NwIED2bJlC2FhYdV+JikpqV7u2u3jF0FJ8V7M8lIMDy9M06SkOAubX4RTO5tfJPbCDMfrir+8Ihzv5e7bcNh7GRV/6Vv0l4E7xACKo6nF4Q7c4Vi4QwwAoa1i2Z+9m7KyUjw9K+LIyUolLLJtlbZFhQd5fPpoeg4cx6iLpzm9N3T8jQwdfyMAO7f+QMtWbRzDzFbwD4qh6GAG5eWlePx1PAoPpuMfHFOlXUHebsfrgtw0/A+rJHbseQUde14BQPaen/ALinYMMzc0m38k9iLnc8pelIXvYdVlqDhvDr98wV6Yic0/8sjNuQUTA9PCP6Cs3FdtPP3008fd9tZbb6319mv1G2f06NFceOGFnHLKKQwfPpxPP60YQnj99ddr/ExiYiK5ubmOJTU1tca2R+Nja0lAcEf2pi0DKq7bsflFOQ3XAIRFncG+jJWU2HMwTZOMlEWEtx4GQMuIfuQf+I3C/GQAMnZ9RHjMsDr1p7nGoDiaXhzuwB2OhTvEABDcMoK2HXvy/V/XCK779n3Co9pVGVIuLsrniemj6d53JOOvuK/Kdg7sq0hW7MWFfPjqTM6ZcGeD9/1wvgHhtIg8mV1bPgRg9+9LCAhu4zSkDBDbZTS7f/+c4oK9mKbJjo0LiDtpnOP9ovyK4dnSQ0Vs/u5xuva70bIYfGwtCWzRiczUinvVZe/5Bl//KKchZYDw1kPYl/4tJcUV59SePz+iVZvhlvVTrPfkk08e1zJ37tw6bd8wa65RH5cRI0bQsWNH5s+ff1zt8/LyCAkJod+oT/HyDqjVvoryU9i+8RFKD+Xh6eVPp4RE/IPi2bFpDqGRgwiNGgRAZvInpO2suE1ESFhP2p8yzTEMkJOxiuRfn6+4TURQezomJNa6HyfCHWJQHA0Xx6rFQ+ottsYyaNyKOn2uqR0Ld4nhumm1f3RWeso2Xp4zify8ffj5BzN5+mu0jj+ZV/49mZ4DxtNz0HgWL3iIj19/gJh2Jzs+13fIRYz7R8Ws5Huv7YFZXk5paQkDR/yD8Vfc5/TUhtpY+vnuYzeqRt6+nfz42R2UFO3HyyeQ08Y8QUh4F9Z8dhetOw6ndaeKiR47Ny3k1x/nY5qH3crGs2II/LNXRmCa5ZSXHaLdyRdw8sDb6hzHnu0ptf5M4cEUtq1/iNKSXDy9A+jS+x4Cgtvz+0+PEBZ9OmHRpwOQ/uciUre/BWbFrWw6JvzTcU799NU1lBTvo8S+Hx/fMFq06sVJfaom9MdSeqiA1Z+MIjc3l+Dg4Fp//kRU5g7b1q4kKNC6yTUH8/Pp0ndwo8TcmE4oObTb7XTo0IHrr7+e+++//7g+cyLJoYi7a87JoTSMuiSHTU1dk8Ompi7JYVPSFJLD39atsjw5PKnPoGaXHNbqmsN//vOfjBs3jrZt25KVlcXs2bPJy8vjqquuaqj+iYiIiMhR7N69m0WLFpGSkkJJSYnTe0888UStt1er5HD37t1ceumlZGdn06pVK0477TR++OGHBpkpIyIiInI4q29M7Qo3wV6+fDnjx48nPj6ebdu20b17d3bt2oVpmvTq1atO26xVcvjOO+/UaSciIiIiUv8SExO54447ePDBBwkKCuL9998nIiKCyy+/nLPPPrtO29T9NkRERERc1K+//uq4vM/Ly4uioiICAwN58MEHefTRR+u0TSWHIiIi4hIq73No5dLUBQQEOB42EhMTw86dOx3vZWdn12mbjXebdxERERE5IaeddhqrVq2iW7dujBkzhjvuuIPNmzfzwQcfcNppp9Vpm0oORURExCXo2cpVPfHEE+Tn5wMwa9Ys8vPzeffdd+nYsSNPPvlknbap5FBERETERbVv397xb39/f+bNm3fC22z6KbGIiIgIuuawOpMmTWL58uWc4APvnCg5FBEREXFR+/btY8yYMbRp04Y77riDjRs3nvA2lRyKiIiIuKhFixaRkZHBzJkzWb9+Pb1796Zbt248/PDD7Nq1q07bVHIoIiIiLsHEwzEpxZLFRdKkFi1acP311/PNN9+QnJzMpEmTePPNN+nYsWOdtucaUYuIiIjIUR06dIh169bx448/smvXLiIjI+u0HSWHIiIi4hI0IaV6X3/9Nddddx2RkZFcddVVBAUFsXjxYlJTU+u0Pd3KRkRERMRFtWnThn379jFq1CheeOEFxo0bh6+v7wltU8mhiIiIiIu6//77ufjii2nZsmW9bVPDyiIiIuISTMOwdkKK0fSHla+//npHYjhmzBjS09NPeJtKDkVERETcwLfffktRUdEJb0fDyiIiIuISrJ4k4ioTUuqbKociIiIibiAuLg5vb+8T3o4qhyIiIiJu4JdffqmX7Sg5FBFxY6e33dXYXThh/9ma0thdEKD0UGljd+GvCSkWDiu7wIQUgJ9//pnff/8dHx8fOnfuzEknnXRC21NyKCIiIuKC1qxZw7XXXsvWrVsxTRMAwzDo27cvr732miNJzMnJITQ09Li3q2sORURExCWYpmH50lRt3bqVs846Cz8/PxYsWMBPP/3E+vXrefPNNykrK2PgwIHs2bOHefPmMW/evFptW5VDERERERczc+ZMRowYwfvvv49x2PB3z549ufTSS7ngggsYOnQoqampfPbZZ7XatpJDERERcREemJYOejbdAdZvvvmGzz77zCkxrGQYBnfffTf9+/fns88+Y8iQIbXadtONWkRERESqdfDgQSIjI2t8PyoqCm9vb0aNGlXrbSs5FBEREXEx7dq1Y82aNTW+/+OPPxIXF1enbSs5FBEREZdQ+YQUK5emasKECUybNq3aextu3ryZf/7zn0ycOLFO29Y1hyIiIiIuJjExkS+//JKEhARGjBhB165dgYpZzF9++SX9+vUjMTGxTttWcigiIiIuQc9W/puvry9ff/01Tz75JG+//TYrVqwAoFOnTsyePZvbb78dm81Wp20rORQRERFxQT4+PkyfPp3p06fX63Z1zaGIiIiIOKhyKCIiIi5Bw8rWUOVQRERERBxUORQRERGXoMqhNVQ5FBEREXFRRUVFNb6Xnp5ep20qORQRERGXYJqG5UtT17NnT3766acq6//3v//Ro0ePOm1TyaGIiIiIixoxYgQDBw7kkUcewTRN8vPzufrqq7nqqqu4//7767RNXXMoIiIi4qKeeeYZxowZw6RJk/j000/Zs2cPwcHBrF27lm7dutVpm0oORURExCVoQkr1Ro4cyQUXXMD8+fPx8vJi8eLFdU4M4QSTw6SkJO6++25uu+025s6deyKbOi5F+bvZsSmJQyW5eHkF0jFhBv5B7aq0y0z5lLQdCzExaRHei/bdp2J4VISak7ma5K3zMc0y/IM70ilhBp5e/g3ed3eKQXE0vTjcgTscC3eIAWDXrj+568472b8/h+DgYB559DE6depUbVu73c6548fh5+fLhx8tAmDVqu945JEkR5ucffsID2/Fx4sWW9L/Su5wPNwhBmlYO3fu5LLLLiMjI4OlS5eyYsUKzj33XG699VYeeughvL29a73NOl9zuHbtWl588cU6X+xYFzs3P05k27H0GrqAmA4T2bFpTpU2xYXppGx7he6DnqHX0LcoseeQmboEgLLSQnZueowufWfTa9hCfGyh7N6+wLL+u0sMoDiaWhzuwB2OhTvEAHDfvfcyYeJEln35FZOvu567E2fU2PaJx/9Nz549ndYNGnQ6ixd/6li6nXwy48ef29DdrsIdjoc7xFCfKiuHVi5NXUJCAvHx8WzatIkRI0Ywe/ZsvvrqKz744AP69etXp23WKTnMz8/n8ssv5z//+Q8tW7as045rq8S+n4Lc32nVegQAYdFDsBelU1zoPE17X/oKwqIG42MLxTAMotqOJzttOQD7s9YQ0KIL/oFxAES1O4/sPcst6b+7xKA4ml4c7sAdjoU7xACwb182W7b8wrnnngfA2WePZvfuVHbv3l2l7dq1a9i1axfnnXd+jdvLzMzkh++/57zzz2ugHlfPHY6HO8QgDW/evHm88847tGjRwrFu4MCBbNiwgV69etVpm3VKDm+++WbGjBnD8OHDj9nWbreTl5fntNRFSVEWPr7hjjK5YRjYfCOxF2U5768oE5tfpOO1zT8Ke3FWje+VFGdjmuV16lNtuUMMoDiaWhzuwB2OhTvEABX3RYuIiMTL6+84YmJi2LNnj1O7wsJCHpo9mwce/NdRt/fhB+9zxpAhhIWFN1ifq+MOx8MdYpCGd8UVV1S7PigoiJdffrlO26z1NYfvvPMOP/30E2vXrj2u9klJSTzwwAO17lj1nMu7JmYNzQynVs5baOwSsTvEAIrj8C00hTjcgTscC3eIoSIJOZxpVo3j0UeSuPwf/yAqKorkXbtq3Nb77/+Pe+69r767eJzc4Xi4Qwz1RxNSarZ161ZSUlIoKSlxrDMMg3HjxtV6W7VKDlNTU7ntttv44osv8PX1Pa7PJCYmMm3aNMfrvLw8YmNja9dLwMcvgpLivZjlpRgeXpimSUlxFja/CKd2Nr9I7IUZjtf2wkxsvhGO93L3bTjsvYyKv8oMa2736A4xgOJoanG4A3c4Fu4QA0B0dDQZGemUlpbi5VURR3p6OjExMU7t1q9fx4oV3/Dcs89gt9vJzc1j9Nmj+OzzpY42a9asoaiomMGDz7Cs/5Xc4Xi4QwzS8P744w/OP/98Nm/ejGEYjj/mKv/IKysrq/U2a3V2rF+/nqysLHr37o2XlxdeXl6sWLGCp59+Gi8vr2o7YLPZCA4OdlrqwsfWkoDgjuxNWwZUXGNh84vC1z/aqV1Y1Bnsy1hJiT0H0zTJSFlEeOthALSM6Ef+gd8ozE8GIGPXR4THDKtTf5prDIqj6cXhDtzhWLhDDABhYeF063YyH3/8EQCff/4ZrVu3oU2bNk7tPvn0M75ZsZJvVqxk7tyn6dKls1NiCPC//73HBRdeiKenp1Xdd3CH4+EOMdQ3E4ufkOIClcPbbruN+Ph4MjMz8ff3Z8uWLXz77bf06dOHb775pk7bNMzqxgtqcPDgQZKTk53WTZo0iZNOOonp06fTvXv3Y24jLy+PkJAQ+o36FC/vgFp1tig/he0bH6H0UB6eXv50SkjEPyieHZvmEBo5iNCoQQBkJn9C2s6KKf0hYT1pf8o0PCqn9GesIvnX5yum9Ae1p2NCYq37cSLcIQbF0XBxrFo8pN5iayyDxq2o0+ea2rFwlxhen9u21p/5448/mH7XnRw4sJ/AwEDmzPk3nTp35u7EGZx11nDOOuJ68x9/+IFHHnnYcSsbqJi4ePqgASxa/Clt29a+D4e7ampKnT7XFI+HK8dQeqiANUvHkJubW+dCT11V5g6rftpBYGCQZfvNzz/IoF4dGyXm4xUeHs5XX31Fjx49CAkJYc2aNXTp0oWvvvqKO+64gw0bNhx7I0eoVXJYnTPPPJOEhITjvs/hiSSHIu6uOSeH0jDqkhw2NXVNDqV+NYXkcOVPOy1PDgf36tCkk8OWLVuyfv162rdvT4cOHXjppZcYOnQoO3fu5JRTTqGwsLDW29QTUkRERERcVPfu3fn5559p3749/fv3Z86cOfj4+PDiiy/Svn37Om3zhJPDuo5ni4iIiMiJuffeeykoKABg9uzZjB07lsGDBxMWFsa7775bp22qcigiIiIuQbeyqWrUqFGOf7dv356tW7eSk5NDy5Ytq9yW6ngpORQRERFxI6GhoSf0eSWHIiIi4hIqbzFj5f6aqmuuuea42r3yyiu13raSQxEREREX89prrxEXF0fPnj2rfYrRiVByKCIiIuJibrzxRt555x3++OMPrrnmGv7xj3+c8HByJT0/R0RERFyCyd+TUqxZmq558+aRnp7O9OnTWbx4MbGxsVxyySUsXbr0hCuJSg5FREREXJDNZuPSSy9l2bJlbN26lZNPPpkpU6YQFxdHfn5+nberYWURERFxCZqQUjPDMDAMA9M0KS8vP6FtqXIoIiIi4oLsdjtvv/02I0aMoEuXLmzevJlnn32WlJQUAgMD67xdVQ5FRETEJegm2H+bMmUK77zzDm3btmXSpEm88847hIWF1cu2lRyKiIiIuJjnn3+etm3bEh8fz4oVK1ixYkW17T744INab1vJoYiIiIiLufLKK+v8eLxjUXIoIiIiLkETUv722muvNdi2NSFFREREpB7NmzeP+Ph4fH196d27NytXrjyuz61atQovLy8SEhIatoPHoORQREREXIIJlFu41OVW0u+++y5Tp07lnnvuYcOGDQwePJjRo0eTkpJy1M/l5uZy5ZVXctZZZ9Vhr/VLyaGIiIhIPXniiSe49tprmTx5Ml27dmXu3LnExsYyf/78o37uhhtu4LLLLmPAgAEW9bRmSg5FREREjiIvL89psdvt1bYrKSlh/fr1jBw50mn9yJEjWb16dY3bf/XVV9m5cyczZ86s137XlZJDERERcQmVE1KsXABiY2MJCQlxLElJSdX2Lzs7m7KyMiIjI53WR0ZGkpGRUe1ntm/fzowZM3jrrbfw8moa84SbRi9ExG0kfnZ9Y3ehXvS8OaGxu1AvQtf3aewu1IN+jd0BaeZSU1MJDg52vLbZbEdtf+QtZkzTrPa2M2VlZVx22WU88MADdO7cuX46Ww+UHIqIiIhLaKwnpAQHBzslhzUJDw/H09OzSpUwKyurSjUR4ODBg6xbt44NGzZwyy23AFBeXo5pmnh5efHFF18wbNiweoikdjSsLCIiIlIPfHx86N27N8uWLXNav2zZMgYOHFilfXBwMJs3b2bjxo2O5cYbb6RLly5s3LiR/v37W9V1J6ocioiIiEtwhZtgT5s2jSuuuII+ffowYMAAXnzxRVJSUrjxxhsBSExMJC0tjTfeeAMPDw+6d+/u9PmIiAh8fX2rrLeSkkMRERGRejJhwgT27dvHgw8+SHp6Ot27d2fJkiXExcUBkJ6efsx7HjY2JYciIiIi9WjKlClMmTKl2veO9di7WbNmMWvWrPrvVC0oORQRERGX0FgTUpobTUgREREREQdVDkVERMQllJsVi5X7a45UORQRERERByWHIiIiIuKgYWURERFxCZqQYg1VDkVERETEQZVDERERcQmu8IQUd6DKoYiIiIg4qHIoIiIiLsE0KxYr99ccqXIoIiIiIg5KDkVERETEQcPKIiIi4hLKMSi38PYyVu6rKVHlUEREREQcXKpyWJS/mx2bkjhUkouXVyAdE2bgH9SuSrvMlE9J27EQE5MW4b1o330qhkdFqDmZq0neOh/TLMM/uCOdEmbg6eWvGBSHS8fhDvaYJTxZnkEeZQTgwVSPKNoaNqc25abJq2Y2P5kFlGHSzfDjJiMSb8Mg0zzE9eV/Esffn0n0iCba8LEshj8OHOT2L9aQU2wn2ObDk8P70jksxKmNaZrMXvUzX+9Kx8MwaOnrw5yz+hDfIoiCkkNcv2Q1P2ftB2Dz9edZ1vfD7Ujfy3Xz/su+gwWE+Pvx4pRL6Nomskq7X1LSuePVj8k6kE+5Wc4Dl47mvP6nADB38QoWfLMOT08PfL29eXzSufTpGGtpHO7w/XaHGOqTbmVjjVpVDufPn0+PHj0IDg4mODiYAQMG8NlnnzVU36rYuflxItuOpdfQBcR0mMiOTXOqtCkuTCdl2yt0H/QMvYa+RYk9h8zUJQCUlRayc9NjdOk7m17DFuJjC2X39gWW9d9dYgDF0dTicAfPlWcyygjhBc94LvQI5enyzCptlpm57DLtzPWIY75HOwAWm/sd7wfgwdOecY7FysQQYMZX67m8e3tWXnkON/Xqwj+Xr6vS5os/9vBj2l6WXjqSLy8fxemxkTy6ejMAXh4e3NT7JN45f4il/T7S//3nA645qz8/z72LaeOHcNPz71VpU2gvYcK/X2fmhFFsePKfrH/8DgZ1jQfg5117mP/5Kr556BZ+nHM7N549kNtf+cjiKNzj++0OMYjrqVVy2KZNGx555BHWrVvHunXrGDZsGOeeey5btmxpqP45lNj3U5D7O61ajwAgLHoI9qJ0igvTndrtS19BWNRgfGyhGIZBVNvxZKctB2B/1hoCWnTBPzAOgKh255G9Z3mD992dYlAcTS8Od3DALGUndoYawQAMJJBMDpFpHnJq9yd2Egx/vA0DwzDobQTwtZnXGF2uIruwmF+y9nPBSRXnwpiObUjNKyA1r6BK25KycuxlZZimycGSQ0QHVlRxbF6enB4bSbDN2qT2cFm5+Wz8M41LB/cE4Lz+p7ArK4fkrByndu9+t4H+neIYeFJFQujl6Umr4EDH+4fKyigoLgHgQEERrUOdK6gNzR2+3+4Qg7imWg0rjxs3zun1Qw89xPz58/nhhx84+eST67VjRyopysLHN9xRJjcMA5tvJPaiLHz9ox3t7EWZ2Pz+Hv6w+UdhL86q8b2S4mxMsxzDaPjLL90hBsXR9OJwB9mUEooXnkbFEI5hGLTCi70cIhJvR7tO+LLUzGW02QJvDFaWHySTUsf7RZRze1ky5cBpRiCXGKGObTa0PfmFRAb44eXh4YghJsiftIOFxAYHONqNaB/D92lZ9HxpEYE+3kQF+PG/C8+0pI/HY/e+A0S3DMbL0xOoiCM2vCWp2QeIiwh1tPstLQubtxcXPPoKaftyOaVtNElXjqVVcCA92sVw65gz6PZ/j9Ay0B+btydfzLrJ0jjc4fvtDjHUN93n0Bp1PjPKysp45513KCgoYMCAATW2s9vt5OXlOS115/xL3qSGo+b0n4FzG6PRZx65QwygOA7fQlOIw/1UdySGGcH0NAJILE/lnvJU2ho+jr9wQ/HkVY/2POkZx2yPNmw1i/josCFnK1TJQ6v5n2Vz1n527D/IumvHsf7acQyKjeDeFRus6eBxMo4IxKwmjkOlZXz58+88c92F/PDoVFqHt+D2lz8CIGXvfj5dt5Vfnp7Ojvn3cMs5g7nmmbet6PoR3OH77Q4xiKupdXK4efNmAgMDsdls3HjjjXz44Yd069atxvZJSUmEhIQ4ltjYul2Q7OMXQUnxXszyiiqBaZqUFGdh84twamfzi8RemOF4bS/MxOYb4XivuOjw9zIq/iqz6K8nd4gBFEdTi8MdhOPFPkop+ysJMU2TbEppdVjVECqSlks9wnjKM445nm1pgw+xf01A8TY8aGFUpIpBhifDjWC2mEWWxRAT6E96fhGl5eWOGPbkF9E6yPnC///+uouBbSIIsfngYRhc3LUdq3dnWdbPY2kT1oK0fbmUlpUBFXHs3neA2PAWTu3atmrJkG4daB0agmEYTDy9J+t2pgLwwQ8/0y02iuiWFZcJXHlmX7779U/K/vrZWMEdvt/uEEN9MzEsX5qjWp8dXbp0YePGjfzwww/cdNNNXHXVVWzdurXG9omJieTm5jqW1NTUOnXUx9aSgOCO7E1bBlRcY2Hzi3IqrQOERZ3BvoyVlNhzME2TjJRFhLceBkDLiH7kH/iNwvxkADJ2fUR4zLA69ae5xqA4ml4c7qCF4UV7bI7rB1eTTyTeRBrOyWGJWU6+WZG05Jpl/M/cz4UeLYGK6xZL/0ouD5nlfG/m0/6I2c4NKdzfl5NbteCD3yrOhU937KZNkL/TkDJAXHAAq1IzOVRWkSgt+3MPXcKsvR7vaCJCAjk1Poa3V1ZUMz/6cTNxrUKdhpQBLhzQg/U7d5NXWAzAso3bOCWu4rvTLiKU77f9SX6xHYAl67dyUusIPD0s/OPPDb7f7hCDuCbDrG68oBaGDx9Ohw4deOGFF46rfV5eHiEhIfQb9Sle3gHH/sBhivJT2L7xEUoP5eHp5U+nhET8g+LZsWkOoZGDCI0aBEBm8iek7ayY0h8S1pP2p0zDo3JKf8Yqkn99vmJKf1B7OiYk1rofJ8IdYlAcDRfHqsWNO0u1Pnzi1aVOn9ttljC3PIODlOH/161s4gwbT5dn0N8IpL8RyH6zlMTyVDwwKMfkXKMloz1aALDaPMhb5fvwAMqAUw1/rjHC8a5jhaTnzQm1/szO/Xncvmwt+4vtBPl48+SIfnQJC+GfX65lZPsYRrZvjb20jHtX/MSaPdl4e3gQGeDLI8P6OJLIs9/+gqyCYrKL7ET4+zKwTQRPj+pfpxgAQgf1qfVnft+TxfXz/ktOfiFBfjb+M2UC3WKjuOn59xjTpxtj+1RcY/7WivU8segbvDw8iA4N5tnrL6RNWAtM02Tm25+zaO0v2Ly8CPSz8fikc0mIb12nGIa/2a9On2tq329Xj6H0UAFrlo4hNzeX4ODgeo3zWCpzhw++20tAoHX7LsjP44LTWzVKzI3phJPDs846i9jYWF577bXjan8iyaGIu2vOyWFTU5fksCmqS3LY1NQ1OZT61RSSw/+ttD45vGhw80sOazVb+e6772b06NHExsZy8OBB3nnnHb755hs+//zzhuqfiIiIiFioVslhZmYmV1xxBenp6YSEhNCjRw8+//xzRowY0VD9ExEREalg8RNSaKZPSKlVcvjyyy83VD9EREREpAlwqWcri4iISPOlm2BbwzVvdCQiIiIiDULJoYiIiIg4aFhZREREXEI5BuUWPrXEyn01JaocioiIiIiDKociIiLiEjQhxRqqHIqIiIiIg5JDEREREXHQsLKIiIi4BNPiJ6RY+jSWJkSVQxERERFxUOVQREREXEK5WbFYub/mSJVDEREREXFQ5VBERERcgm5lYw1VDkVERETEQcmhiIiIiDhoWFlERERcgomBaeHzjq3cV1OiyqGIiIiIOKhyKCIiIi6hHItvZWPdrpoUJYciUq+SRr/Y2F2oH380dgfqx32TBjR2F06YX/Dmxu5CvSjKy2/sLogcFw0ri4iIiIiDKociIiLiEnSfQ2uocigiIiIiDqocioiIiEtQ5dAaqhyKiIiIiIMqhyIiIuISyk2DctO6G1Nbua+mRJVDEREREXFQcigiIiIiDhpWFhEREZegCSnWUOVQRERERBxUORQRERGXoMqhNVQ5FBEREREHJYciIiIi4qBhZREREXEJpgnlGlZucKocioiIiIiDKociIiLiEkzTwLTwqSVW7qspUeVQRERERBxUORQRERGXoFvZWEOVQxERERFxqFXlMCkpiQ8++IDffvsNPz8/Bg4cyKOPPkqXLl0aqn9OivJ3s2NTEodKcvHyCqRjwgz8g9pVaZeZ8ilpOxZiYtIivBftu0/F8KgINSdzNclb52OaZfgHd6RTwgw8vfwt6b+7xKA4ml4c7sAdjoU7xACQlrydx++fTN6BbAKCWjDtgZeI69DVqc2vm37g2Yf/D4DS0kOc3HMgN971JD4+NgCy0lN47pHbSEvejmEYjL3kRs699GZL4yjMS2HrD7MosR/A2zuQrgNmERjSvkq7PTs/YteW14FyWkb2o0vf6Xh4eFGUn8bmldMxzXJMs4yA4Hac1P8evH2CLYvBXc4pcS21qhyuWLGCm2++mR9++IFly5ZRWlrKyJEjKSgoaKj+Odm5+XEi246l19AFxHSYyI5Nc6q0KS5MJ2XbK3Qf9Ay9hr5FiT2HzNQlAJSVFrJz02N06TubXsMW4mMLZff2BZb03Z1iAMXR1OJwB+5wLNwhBoBnHrqF0Rdey0sfb+Giq+5g7gM3VGkT37kHTy1YzXPvrmX+ez+Ruz+bz/73HwBM0+Rfd1zC8LH/4KWPfuHFD35m8IgLrQ6D39Y+TEzH8xk47gPadruSX3/4V5U2Rflp7Pz5eXqPeIkB4z6ipDibPTs/BsDm14reI16i/zkLOW3Mu9j8I/hz80uWxuAu51R9KTetX5qjWiWHn3/+OVdffTUnn3wyp556Kq+++iopKSmsX7++ofrnUGLfT0Hu77RqPQKAsOgh2IvSKS5Md2q3L30FYVGD8bGFYhgGUW3Hk522HID9WWsIaNEF/8A4AKLanUf2nuUN3nd3ikFxNL043IE7HAt3iAHgQE4WO37dwLBzLgPg9OHnk7lnF5l7djm18/Xzx8vbG4DSQyWUFBdheFT8l7Lxx6/wsfk5EkLDMAgNj7IuCKCkOIeDOb8R1W40ABGxZ1FcsIei/D1O7bJSltOqzVBsfmEYhkHrjheSmbwUAA9PHzy9fAEwy8soKy3EMKy7GstdzilxPSd0lufm5gIQGhpaL505mpKiLHx8wx1lcsMwsPlGYi/KcmpnL8rE5hfpeG3zj8JenFXjeyXF2ZhmeYP3H9wjBlAcTS0Od+AOx8IdYgDYm7Gb0FbReHr9HUerqFiy0lOrtM3cs4ubJ/RlwtAY/AODGX3hZABS/viVkJbhJE3/BzdP7MeD0y4mffcflsUAUFyYiY9fKzwOOx6+/pEUF2Yc0S4Dv4C/E1ffwBiKCzIdr8vLDvHjksv49v3hFB5MJf6UydYEgPucU/WpckKKlUtzVOfk0DRNpk2bxumnn0737t1rbGe328nLy3Na6s75fkMmNRw1w3Bq5byFxr5nkTvEAIrj8C00hTjcgTscC3eIoSIJOZxZw/+QkTHteO7dtSz8MoVDJXZWLf8IqLgGceOPX3HZ9Xfz3Dtr6DNoFI/MuKKhu11FlThqbnlYI+dWHp7e9D9nIYMv+AL/4DjStr9fr308Nvc4p8S11Dk5vOWWW/j55595++23j9ouKSmJkJAQxxIbG1un/fn4RVBSvBezvBSo+GVVUpyFzS/CqZ3NLxL7YX8Z2gszsflGON4rLjr8vYyKv8osGiZwhxhAcTS1ONyBOxwLd4gBoFVUG7Kz0igr/TuO7MzdRETX/Lvbzz+QM0ZdwtefVfx/EBEdR4cuCcR16AbAsHMuY8evP1FWVtbwAfylokqYSflhx8NemImvf9QR7aIoKvh7mLa4IB3fgEiO5OHpTUz78aT/uaRhO34YdzmnxPXU6ez4v//7PxYtWsTXX39NmzZtjto2MTGR3Nxcx5KaWnVo4nj42FoSENyRvWnLgIprLGx+Ufj6Rzu1C4s6g30ZKymx52CaJhkpiwhvPQyAlhH9yD/wG4X5yQBk7PqI8JhhdepPc41BcTS9ONyBOxwLd4gBoEVoBB26JPDVkoUAfPflh0TExBEZ086p3Z7UnZQeOgTAoUMlrP7qI+I7nQJA39NHkb03jeysNADWr/6CuA4n4+npaVkcPr6hBLXsQsauzwDISl2Ob0A0foExTu0i2g5j7+6vsRftwzRN0na8T2TcSACKCzIoKy0CwDTLyUxeRmCLTtbF4CbnVH3SsLI1DLOm8YJqmKbJ//3f//Hhhx/yzTff0KlT7b8keXl5hISE0G/Up3h5B9Tqs0X5KWzf+Ailh/Lw9PKnU0Ii/kHx7Ng0h9DIQYRGDQIgM/kT0nZWTOkPCetJ+1OmOa47yclYRfKvz1dM6Q9qT8eExFr340S4QwyKo+HiWLV4SL3F1lgGjVtRp881tWPhLjHc968Btf7M7l3bePz+6ziYuw//gGDu+NfLxHXoxtwHbuS0IWM47cxxLP3wVT5862k8PDwpKyvl1L5nMvn2R/CxVUzgWL/6C1556h5M0yQgqAW33P20o5JYW/9+bHOdPleQt4ut3z9QcRsY7wC6nTaLwBYd+PXHfxHe+gxatan4vqXt+JDkra9jmiahUX3o0jcRDw8vstO+Y+emZ4GK5DCo5Ul07j0Nb1uLOvWnKC+/9p9pQudU6aEC1iwdQ25uLsHB1t3OB/7OHZ5dlItfgIW3EirI45bxIY0Sc2OqVXI4ZcoUFi5cyMcff+x0b8OQkBD8/PyOaxsnkhyKuLvmnBxKw6hLctjU1DU5bGrqkhw2JU0hOXz6Y+uTw1vPbX7JYa2GlefPn09ubi5nnnkm0dHRjuXdd99tqP6JiIiIiIVq9YSUWhQZRUREROqVnq1sDU1XEhEREREHJYciIiIi4lCrYWURERGRxlJeXrFYub/mSJVDEREREXFQ5VBERERcgiakWEOVQxERERFxUHIoIiIiIg4aVhYRERGXoGFla6hyKCIiIiIOqhyKiIiISygHyi2s5jXTO9mocigiIiIif1PlUERERFyCaZqYFl4IaOW+mhJVDkVERETEQcmhiIiIiDhoWFlERERcgm5lYw1VDkVERETEQZVDERERcQlmOZRbeH8Zs5ney0aVQxERERFxUHIoIiIiIg4aVhZpQgaNW9HYXZC/BIW1aOwu1IuPvyho7C6csOKDrh+D1A9NSLGGKociIiIi4qDKoYiIiLiEctPiZyurcigiIiIizZ2SQxERERFx0LCyiIiIuARNSLGGKociIiIi4qDKoYiIiLgEs9zEtHCWiJX7akpUORQRERERB1UORURExCXoVjbWUOVQRERERByUHIqIiIiIg4aVRURExCXoVjbWUOVQRERERBxUORQRERGXUF5uUm7hLBEr99WUqHIoIiIiIg5KDkVERETEQcPKIiIi4hI0IcUaqhyKiIiIiIMqhyIiIuISVDm0Rq2Tw2+//ZbHHnuM9evXk56ezocffsh5553XAF2rqih/Nzs2JXGoJBcvr0A6JszAP6hdlXaZKZ+StmMhJiYtwnvRvvtUDI+KUHMyV5O8dT6mWYZ/cEc6JczA08vfkv67SwyKo2nF4Q4xuEscBXnJ/PLdfZTYD+DlHcQppz9IYIsOVdrt3v4hf25+BdM0CYvuR9fT7sbD4+9fx6Zpsu6LGzi4/3eGTfzGsv5XOpC9k6/fnUJxYQ4+viEMveRZQiNPcmqTl5PC1+/dzL60nwkJ78CFt35VZTumafLJf85nX/ovXD1zh1XddyjK3832jQ9XnFPegXRKSKzxnNq94y0wTULCe9HhlNsxPLwoKy3kt3X3k3/gdwD6n73I4gjc43shrqfWw8oFBQWceuqpPPvssw3Rn6PauflxItuOpdfQBcR0mMiOTXOqtCkuTCdl2yt0H/QMvYa+RYk9h8zUJQCUlRayc9NjdOk7m17DFuJjC2X39gWKoQ4UR9OJwx1iAPeIY+v3s2nT+UIGn7+I+O5X88vqB6q0KTyYxo4N8+g3+jUGX7AYe9E+0rZ/5NQm5bd38AuMsajXVX37wTS69r+KS+9cS8KQ/2PF/26t0sbHN4h+I+/hrEv/U+N2fln9H4JaxjZkV49q58//JjJuHL2HvUXrDpeyY9OjVdoUF6aT/NvLnDLoWXoNW1hxTqVUnFOG4UXrDpdy8oDHre66gzt8L+pTuWlavjRHtU4OR48ezezZs7ngggsaoj81KrHvpyD3d1q1HgFAWPQQ7EXpFBemO7Xbl76CsKjB+NhCMQyDqLbjyU5bDsD+rDUEtOiCf2AcAFHtziN7z3LFoDhcNg53iMFd4rAX5ZC371ei248BIDJuOEUH0yjKT3Nql5m8jIi2Q7H5hWEYBrFdLiL9z88c7xfkJZPx5+fEnzLJsr4frih/L9lpm+jc8xIA2p8ynrycFPJyUpza+fq3JDr+NLx8qq9AHcjeyY5NH5AwdGpDd7laJfb95OduJ+Kwc6q4MKPKOZW95xvCog87p+LOZe9f542Hpw8tWvXGyzvQ8v6De3wvxDU1+IQUu91OXl6e01IXJUVZ+PiGO8rkhmFg843EXpTlvL+iTGx+kY7XNv8o7MVZNb5XUpyNaZbXqU+15Q4xgOJoSnG4QwzgHnEUF2Zg849wDA8bhoFvQBRF+RnO7Qoy8AuMdrz2C4yhuKCijWmWs2X1g3Q9LdFpmNlK+QfSCAiOwsPz7zgCW7Qh/8Du496GWV7OivenMvi8x/Dw8G6orh5VxTkV5nxO+UVUOadKjjhvfP2jsBdlWtrXmrjD90JcU4Mnh0lJSYSEhDiW2NgTGWIwnF6Z1FDuNQynVs5bcN6G9dwhBlAch2+hseNwhxjAfeI4XE1DUof187Bhq11bXqdlZG+CQ0+q5jNWOvLnWLuhtY3fPktM/ADCY06pvy7VyRFx1DhEWPM51fjc8XtRd2a59Utz1ODJYWJiIrm5uY4lNTW1Ttvx8YugpHgvZnkpUHGhc0lxFja/CKd2Nr9I7IV//6VuL8zE5hvheK+46PD3Mir+KjOsuaOPO8QAiqMpxeEOMYB7xOHrH4W9MIvyw2IoLsjELzDKuV1AFEX5exyviwrS8Q2oaLM/8yf27FzEiv+N5sfPJnGoJI8V/xvNIXvdRlzqIrBFawpy91Be9ncc+QfSCGzR5ri3kf7narate5sFj5zKx/NHYy86wIJHTsVeeKCBel1VdeeUvXhvlXPKxy8S+2HnTXGhc6WtMbnD96K5mjdvHvHx8fj6+tK7d29WrlxZY9sPPviAESNG0KpVK4KDgxkwYABLly61sLdVNfjZYbPZCA4OdlrqwsfWkoDgjuxNWwZUXGNh84vC1z/aqV1Y1Bnsy1hJiT0H0zTJSFlEeOthALSM6Ef+gd8ozE8GIGPXR4THDDuB6JpfDIqjacXhDjG4Sxw2v1CCQruQ/senAGQmf4lfYAx+ga2d2kXGDScr5WvsRfswTZPUbf8jOv5sAHqd9QxDLvqcIRd9Rv/Rr+LtE8yQiz7D21a335t14RfYirDWPfh9w38B+GPzIoJaxhIc2va4t3HOpHf4x92b+ceMTZx702fY/FrwjxmbsPm3aKBeV+Vja0lASCeyjnFOhUcPYV/6YedU8seWn/81cYfvRX0zMTFNC5c6VJLfffddpk6dyj333MOGDRsYPHgwo0ePJiUlpdr23377LSNGjGDJkiWsX7+eoUOHMm7cODZs2HCiP646M0yz7lNxDMOo9a1s8vLyCAkJod+oT/HyDqjV/oryU9i+8RFKD+Xh6eX/120J4tmxaQ6hkYMIjRoEQGbyJ6TtrJjSHxLWk/anTHNcv5OTsYrkX5+vmNIf1J6OCYm17seJcIcYFEfTisMdYmiKcQSFtaj1Zwpyd7F51f0csh/AyzuQUwY9SGDLjvyy+gEi2gwhou2ZAKT+/j5//vIamOWERvej22l3V7k2ryg/je8/ufyEb2UT3+34k7pKB/Zu5+v/3kxx4X58bEEMveQ5QqO68s3/bqVdt9G06zaaslI7Cx/tRVlZCSXFefgFhNO51wT6j77faVt5OSl88MywE7qVzebvNtfpc4X5KezYmMShkjw8vQLo3LPinNr+1zkV9tc5lZG8mLQdb2NS/tetbP4+pzaumEyJfR+H7Afw8Q0jJCyBzr3urVN/6vLfbVP6XpQeKmDN0jHk5ubWudBTV5W5w4wXs/H1s27fxUV5PHJ9eK1i7t+/P7169WL+/PmOdV27duW8884jKSnpuLZx8sknM2HCBO6///5jN24AtU4O8/Pz2bGj4kves2dPnnjiCYYOHUpoaCht2x77l9CJJIciIlapS3LYFNUlOWxq6pocNjUnUItpEppzcpiamuoUs81mw2azVWlfUlKCv78/7733Hueff75j/W233cbGjRtZsWLFMfdZXl5Ou3btuOuuu7jlllvqJ5BaqvWw8rp16+jZsyc9e/YEYNq0afTs2bPRslsRERFpHsxyKLdwqZyQEhsb6zS5tqYKYHZ2NmVlZURGOl+3GhkZSUZGRrWfOdLjjz9OQUEBl1xyyQn9rE5Ere+VcOaZZ7r8Xz8iIiIix6u6yuHRGMYRs8xNs8q66rz99tvMmjWLjz/+mIiIiGO2byh6trKIiIi4hMqJIlbuDzjuCbXh4eF4enpWqRJmZWVVqSYe6d133+Xaa6/lvffeY/jw4XXvdD3QXHYRERGReuDj40Pv3r1ZtmyZ0/ply5YxcODAGj/39ttvc/XVV7Nw4ULGjBnT0N08JlUORURExCWUmxWLlfurrWnTpnHFFVfQp08fBgwYwIsvvkhKSgo33ngjUHH/57S0NN544w2gIjG88soreeqppzjttNMcVUc/Pz9CQkLqLZbaUHIoIiIiUk8mTJjAvn37ePDBB0lPT6d79+4sWbKEuLiK51unp6c73fPwhRdeoLS0lJtvvpmbb77Zsf6qq67itddes7r7gJJDERERkXo1ZcoUpkyZUu17RyZ833zzTcN3qJaUHIqIiIhLMMtNTAvHla3cV1OiCSkiIiIi4qDKoYiIiLgE06xYrNxfc6TKoYiIiIg4KDkUEREREQcNK4uIiIhLKC83KbdwkoiV+2pKVDkUEREREQdVDkVERMQlNNazlZsbVQ5FRERExEGVQxEREXEJZnnFYuX+miNVDkVERETEQcmhiIiIiDhoWFlERERcQrlpUm7hJBEr99WUKDkUEanGwX0HGrsL9WLzd7mN3YUT1lxnjIo0FiWHIiIi4hJ0Kxtr6JpDEREREXFQcigiIiIiDhpWFhEREZegZytbQ5VDEREREXFQ5VBERERcgmlWLFburzlS5VBEREREHFQ5FBEREZdgmiamhdcB6lY2IiIiItLsKTkUEREREQcNK4uIiIhLMC1+trKGlUVERESk2VPlUERERFyCWW7xhBTdBFtEREREmjslhyIiIiLioGFlERERcQkaVraGKociIiIi4qDKoYiIiLiEcrNisXJ/zZEqhyIiIiLi4FKVw6L83ezYlMShkly8vALpmDAD/6B2VdplpnxK2o6FmJi0CO9F++5TMTwqQs3JXE3y1vmYZhn+wR3plDADTy9/xaA4XDYOd4jBXeJwhxgq49i+8eGKOLwD6ZSQWGMcu3e8BaZJSHgvOpxyO4aHF2Wlhfy27n7yD/wOQP+zF1na/0rucDzcIYb6pGsOrVGnyuG8efOIj4/H19eX3r17s3LlyvruV7V2bn6cyLZj6TV0ATEdJrJj05wqbYoL00nZ9grdBz1Dr6FvUWLPITN1CQBlpYXs3PQYXfrOptewhfjYQtm9fYElfXenGEBxNKU43CEGcI843CEGgJ0//5vIuHH0HvYWrTtcyo5Nj1ZpU1yYTvJvL3PKoGfpNWxhRRwpFXEYhhetO1zKyQMet7rrTtzheLhDDOJ6ap0cvvvuu0ydOpV77rmHDRs2MHjwYEaPHk1KSkpD9M+hxL6fgtzfadV6BABh0UOwF6VTXJju1G5f+grCogbjYwvFMAyi2o4nO205APuz1hDQogv+gXEARLU7j+w9yxu03+4Wg+JoWnG4QwzuEoc7xFAZR37udiIOi6O4MKNKHNl7viEs+rA44s5l71999fD0oUWr3nh5B1ra98O5w/FwhxjENdU6OXziiSe49tprmTx5Ml27dmXu3LnExsYyf/78huifQ0lRFj6+4Y4yuWEY2HwjsRdlObWzF2Vi84t0vLb5R2EvzqrxvZLibEyzvEH7XskdYgDF0ZTicIcYwD3icIcYoDKOMOc4/CKqxFFyRF99/aOwF2Va1s9jcYfj4Q4x1DfTNC1fmqNaJYclJSWsX7+ekSNHOq0fOXIkq1evrvYzdrudvLw8p6XuDKdXJjUcNMNwauW8BedtWM8dYgDFcfgWGjsOd4gB3CMOd4gBjoyDGv+DrDmOpsEdjoc7xCCuplbJYXZ2NmVlZURGRjqtj4yMJCMjo9rPJCUlERIS4lhiY2Pr1FEfvwhKivdilpcCFX89lBRnYfOLcGpn84vEXvh3X+yFmdh8IxzvFRcd/l5GxV9lhjWTtt0hBlAcTSkOd4gB3CMOd4gBqo/DXry3Shw+fpHYD+trcaFzhaqxucPxcIcY6lt5OZSXmxYujR1x46jT2WEYR/wlY5pV1lVKTEwkNzfXsaSmptZll/jYWhIQ3JG9acuAimssbH5R+PpHO7ULizqDfRkrKbHnYJomGSmLCG89DICWEf3IP/AbhfnJAGTs+ojwmGF16k9zjUFxNK043CEGd4nDHWJwxBHSiaxjxBEePYR96YfFkfyx5X09Gnc4Hu4Qg7gmw6zFgHpJSQn+/v689957nH/++Y71t912Gxs3bmTFihXH3EZeXh4hISH0G/UpXt4BtepsUX4K2zc+QumhPDy9/P+6vUI8OzbNITRyEKFRgwDITP6EtJ0VU/pDwnrS/pRpeFRO6c9YRfKvz1dM6Q9qT8eExFr340S4QwyKo2nF4Q4xuEscTTGGmv5wP5rC/BR2bEziUEkenl4BdO5ZEcf2v+II+yuOjOTFpO14G5Pyv25l83ccG1dMpsS+j0P2A/j4hhESlkDnXvfWKYa6XvfVFI+HK8dQeqiANUvHkJubS3BwcL3GeSyVucOV9/2Jj2+QZfstKT7IG/+Kb5SYG1OtkkOA/v3707t3b+bNm+dY161bN84991ySkpKO+fkTSQ5FRKR26pIcNjXNdVJAU9MUksMr7v3D8uTwzdntm11yWOubYE+bNo0rrriCPn36MGDAAF588UVSUlK48cYbG6J/IiIiImKhWieHEyZMYN++fTz44IOkp6fTvXt3lixZQlxcXEP0T0RERATQE1KsUqfH502ZMoUpU6bUd19EREREpJG55lx2EREREWkQdaocioiIiFhNw8rWUOVQRERERBxUORQRERGXUI5JuYW3Nipvko+FbHiqHIqIiIiIgyqHIiIi4hJ0zaE1VDkUEREREQclhyIiIiLioGFlERERcQmmaVr6rO3m+lxvVQ5FRERExEGVQxEREXEJZrlJuSakNDhVDkVERETEQcmhiIiIiDhoWFlERERcgu5zaA1VDkVERETEQZVDERERcQm6lY01VDkUEREREQfLK4eVWXhZaaHVuxYRaXYMw2jsLpyw5lq9aWoq/99uzONhlpdjlpdbur/myPLk8ODBgwCsX36x1bsWERGRE3Tw4EFCQkIauxvSgCxPDmNiYkhNTSUoKKhB/qLNy8sjNjaW1NRUgoOD6337VlEcTYc7xADuEYc7xACKoylxhxjAmjhM0+TgwYPExMQ0yPal6bA8OfTw8KBNmzYNvp/g4GCX/qJXUhxNhzvEAO4RhzvEAIqjKXGHGKDh42jsimG5xU9IsXJfTYkmpIiIiIiIg25lIyIiIi5Bt7KxhttVDm02GzNnzsRmszV2V06I4mg63CEGcI843CEGUBxNiTvEAO4ThzQNhtlc02IRERFxCXl5eYSEhHDezT/jbQuybL+H7Af56Lke5ObmusU1qcdLw8oiIiLiEvRsZWu43bCyiIiIiNSdKociIiLiElQ5tIYqhyIiIiLi4HbJ4bx584iPj8fX15fevXuzcuXKxu5SrXz77beMGzeOmJgYDMPgo48+auwu1VpSUhJ9+/YlKCiIiIgIzjvvPLZt29bY3aq1+fPn06NHD8dNZQcMGMBnn33W2N06IUlJSRiGwdSpUxu7K7Uya9YsDMNwWqKiohq7W3WSlpbGP/7xD8LCwvD39ychIYH169c3dreOW7t27aocC8MwuPnmmxu7a7VSWlrKvffeS3x8PH5+frRv354HH3yQchd7lu7BgweZOnUqcXFx+Pn5MfD/27v/mKjrPw7gTzqBMyQaGCeX4siKCDSF60uH0vph5xAdNKZoTjFqk4UZ3HQKrnIEUrmaJYlSiIUz+ANR8kviaQszfwFyxug2cTLIBhJOQalA7j7fPxqfvnwhv3en3tvP8Xxst3nvfW6f502R1+f1uffrYmJQV1cnOtZdY4MNNsmFDyjr38Od4lbFYXl5OTIyMrBx40Y0NjYiNjYWcXFxaG9vFx3Nbn19fXjqqadQUFAgOorTamtrkZ6ejlOnTsFkMmFwcBAGgwF9fX2iozlk8uTJeP/991FfX4/6+nq88MILSEhIQHNzs+hoTqmrq0NRURFmzJghOopTwsPD0dHRIT+amppER3LY1atXMXv2bHh6euLbb7/Fzz//jI8++ggPPvig6Gh2q6urG/b3YDKZAACLFi0SnMwxH3zwAXbs2IGCggJYLBZ8+OGH2LJlC7Zt2yY6mkNef/11mEwmlJaWoqmpCQaDAXPnzsWvv/4qOhopmFuNsomOjkZkZCQKCwvltbCwMCQmJiI/P19gMud4eHigsrISiYmJoqPclt9++w2BgYGora3Fs88+KzrObfH398eWLVvw2muviY7ikBs3biAyMhLbt29Hbm4uZs6cia1bt4qOZbdNmzZh//79MJvNoqPclg0bNuDHH39U3B2NW8nIyMDBgwfR0tICDw8P0XHstmDBAmg0GhQXF8trSUlJuP/++1FaWiowmf3++OMP+Pr64sCBA4iPj5fXZ86ciQULFiA3N1dgujtraJTNglVn4enlwlE2A9dxcGfkmBtl4zadw4GBATQ0NMBgMAxbNxgMOHHihKBUBAA9PT0A/iqslMpqtaKsrAx9fX3Q6/Wi4zgsPT0d8fHxmDt3rugoTmtpaYFWq0VISAiWLFmCixcvio7ksKqqKuh0OixatAiBgYGYNWsWPv/8c9GxnDYwMIA9e/YgNTVVUYUhAMyZMwdHjx7F+fPnAQDnzp3D8ePHMX/+fMHJ7Dc4OAir1Qq1Wj1sffz48Th+/LigVHeXZPt7U4prHqLfsRhus1u5u7sbVqsVGo1m2LpGo0FnZ6egVCRJEoxGI+bMmYOIiAjRcRzW1NQEvV6PP//8ExMmTEBlZSWefPJJ0bEcUlZWhrNnzyr6c0jR0dH46quv8Pjjj+Py5cvIzc1FTEwMmpubERAQIDqe3S5evIjCwkIYjUZkZ2fjzJkzWLNmDby9vbFixQrR8Ry2f/9+XLt2DStXrhQdxWHr169HT08PnnjiCahUKlitVuTl5WHp0qWio9nN19cXer0e7733HsLCwqDRaPD111/j9OnTeOyxx0THIwVzm+JwyP9evUqSpLgrWneyevVq/PTTT4q9ig0NDYXZbMa1a9dQUVGBlJQU1NbWKqZA/OWXX/DWW2/h8OHDI7oLShIXFyf/efr06dDr9Zg2bRq+/PJLGI1GgckcY7PZoNPpsHnzZgDArFmz0NzcjMLCQkUWh8XFxYiLi4NWqxUdxWHl5eXYs2cP9u7di/DwcJjNZmRkZECr1SIlJUV0PLuVlpYiNTUVDz/8MFQqFSIjI/HKK6/g7NmzoqPdFRxl4xpuUxxOnDgRKpVqRJewq6trRDeRXOPNN99EVVUVjh07hsmTJ4uO4xQvLy88+uijAACdToe6ujp88skn2Llzp+Bk9mloaEBXVxeioqLkNavVimPHjqGgoAD9/f1QqVQCEzrHx8cH06dPR0tLi+goDgkKChpxYREWFoaKigpBiZzX1taGI0eOYN++faKjOGXdunXYsGEDlixZAuCvi462tjbk5+crqjicNm0aamtr0dfXh97eXgQFBSE5ORkhISGio5GCuc1nDr28vBAVFSXvnBtiMpkQExMjKNXYJEkSVq9ejX379uG7775zq/+kJElCf3+/6Bh2e/HFF9HU1ASz2Sw/dDodli1bBrPZrMjCEAD6+/thsVgQFBQkOopDZs+ePWKs0/nz5zF16lRBiZxXUlKCwMDAYRshlOT333/HffcN/xWoUqkUN8pmiI+PD4KCgnD16lXU1NQgISFBdCRSMLfpHAKA0WjE8uXLodPpoNfrUVRUhPb2dqSlpYmOZrcbN27gwoUL8vPW1laYzWb4+/sjODhYYDL7paenY+/evThw4AB8fX3lbq6fnx/Gjx8vOJ39srOzERcXhylTpuD69esoKyvD999/j0OHDomOZjdfX98Rn/X08fFBQECAoj4DunbtWixcuBDBwcHo6upCbm4uent7FdXhAYDMzEzExMRg8+bNWLx4Mc6cOYOioiIUFRWJjuYQm82GkpISpKSkYNw4Zf4aWbhwIfLy8hAcHIzw8HA0Njbi448/RmpqquhoDqmpqYEkSQgNDcWFCxewbt06hIaG4tVXXxUd7a6QJAmuHLLiRgNdHKLMn+p/kJycjCtXriAnJwcdHR2IiIhAdXW1oq7K6+vr8fzzz8vPhz5PlZKSgt27dwtK5ZihUULPPffcsPWSkhJFfXD98uXLWL58OTo6OuDn54cZM2bg0KFDeOmll0RHG3MuXbqEpUuXoru7Gw899BCeeeYZnDp1SlE/2wDw9NNPo7KyEllZWcjJyUFISAi2bt2KZcuWiY7mkCNHjqC9vV1xhdR/27ZtG95++2288cYb6OrqglarxapVq/DOO++IjuaQnp4eZGVl4dKlS/D390dSUhLy8vLg6ekpOhopmFvNOSQiIiL3MzTncN7KM/D0muCy894cuIGa3f/inEMiIiIiGrvc6rYyERERuS+OsnENdg6JiIiISMbikIiIiIhkvK1MREREiiBJNkgu/MJjV57rXsLOIRERERHJ2DkkIiIiReCGFNdg55CIiIiIZCwOiYiIiEjG28pERESkDC6+rQzeViYiIiKisY6dQyIiIlIEm2SDzYXjZVx5rnsJO4dEREREJGPnkIiIiBSBo2xcg51DIiIiIpKxOCQiIiIiGW8rExERkSJIkg2Sjd+tfLexc0hEREREMnYOiYiISBG4IcU12DkkIiIiIhmLQyIiIiKS8bYyERERKYIk2Vy6SYQbUoiIiIhozGPnkIiIiBTBZgNsLtwk4sKpOfcUdg6JiIiISMbOIRERESmCZHPxEOwx2jpk55CIiIiIZCwOiYiIiEjG28pERESkCPyGFNdg55CIiIiIZOwcEhERkSJwCLZrsHNIRERERDIWh0REREQkY3FIREREijC0IcWVD2ds374dISEhUKvViIqKwg8//HDL42traxEVFQW1Wo1HHnkEO3bscOq8dwqLQyIiIqI7pLy8HBkZGdi4cSMaGxsRGxuLuLg4tLe3j3p8a2sr5s+fj9jYWDQ2NiI7Oxtr1qxBRUWFi5P/zUOSpLG5T5uIiIgUobe3F35+foie92+M8/Rx2XkHb/bhdE08enp68MADD9j1mujoaERGRqKwsFBeCwsLQ2JiIvLz80ccv379elRVVcFischraWlpOHfuHE6ePHn7b8IJ7BwSERER3QEDAwNoaGiAwWAYtm4wGHDixIlRX3Py5MkRx8+bNw/19fW4efPmXct6KxxlQ0RERIpgHewTcr7e3t5h697e3vD29h5xfHd3N6xWKzQazbB1jUaDzs7OUc/R2dk56vGDg4Po7u5GUFDQ7bwFp7A4JCIionual5cXJk2ahPqji11+7gkTJmDKlCnD1t59911s2rTpH1/j4eEx7LkkSSPW/t/xo627CotDIiIiuqep1Wq0trZiYGDA5ecerbAbrWsIABMnToRKpRrRJezq6hrRHRwyadKkUY8fN24cAgICbiO581gcEhER0T1PrVZDrVaLjnFLXl5eiIqKgslkwssvvyyvm0wmJCQkjPoavV6Pb775Ztja4cOHodPp4OnpeVfz/hNuSCEiIiK6Q4xGI7744gvs2rULFosFmZmZaG9vR1paGgAgKysLK1askI9PS0tDW1sbjEYjLBYLdu3aheLiYqxdu1bUW2DnkIiIiOhOSU5OxpUrV5CTk4OOjg5ERESguroaU6dOBQB0dHQMm3kYEhKC6upqZGZm4rPPPoNWq8Wnn36KpKQkUW+Bcw6JiIiI6G+8rUxEREREMhaHRERERCRjcUhEREREMhaHRERERCRjcUhEREREMhaHRERERCRjcUhEREREMhaHRERERCRjcUhEREREMhaHRERERCRjcUhEREREMhaHRERERCT7DxBMbHsElTmPAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 800x800 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Training with epsilon-greedy policy, epsilon = 0.3...\n",
+      "Converged after 1719 episodes with epsilon-greedy policy.\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x800 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Training with boltzmann policy...\n",
+      "Converged after 1490 episodes with boltzmann policy.\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x800 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import math\n",
+    "\n",
+    "# Define the environment\n",
+    "board_rows = 10\n",
+    "board_cols = 10\n",
+    "board = np.zeros((board_rows, board_cols))\n",
+    "win_state = [(4, 5)]\n",
+    "loss_state = [(6, 3), (2, 3), (2, 5), (2, 6), (5, 5), (5, 6), (4, 6), (3, 8), (4, 8)]\n",
+    "gray_state = [\n",
+    "    (7, 1), (7, 2), (7, 3), (7, 4),\n",
+    "    (6, 4), (5, 4), (4, 4), (3, 4), (2, 4),\n",
+    "    (7, 6), (7, 7), (7, 8)\n",
+    "]\n",
+    "start = (9, 0) \n",
+    "deterministic = True\n",
+    "\n",
+    "class State:\n",
+    "    def __init__(self, start, board, win_state, loss_state, gray_state):\n",
+    "        self.board = board\n",
+    "        self.win_state = win_state\n",
+    "        self.loss_state = loss_state\n",
+    "        self.gray_state = gray_state\n",
+    "        self.start = start\n",
+    "        self.state = start\n",
+    "        self.isEnd = False\n",
+    "        self.deterministic = deterministic\n",
+    "\n",
+    "    def giveReward(self):\n",
+    "        if self.state in self.win_state:\n",
+    "            return 1\n",
+    "        elif self.state in self.loss_state:\n",
+    "            return -1\n",
+    "        else:\n",
+    "            return 0\n",
+    "\n",
+    "    def isEndFunc(self):\n",
+    "        if (self.state in self.win_state) or (self.state in self.loss_state):\n",
+    "            self.isEnd = True\n",
+    "\n",
+    "    def nextPosition(self, action):\n",
+    "        if self.deterministic:\n",
+    "            if action == \"up\":\n",
+    "                next_state = (self.state[0] + 1, self.state[1])  \n",
+    "            elif action == \"down\":\n",
+    "                next_state = (self.state[0] - 1, self.state[1])  \n",
+    "            elif action == \"left\":\n",
+    "                next_state = (self.state[0], self.state[1] - 1)\n",
+    "            elif action == \"right\":\n",
+    "                next_state = (self.state[0], self.state[1] + 1)\n",
+    "\n",
+    "            if (0 <= next_state[0] < board_rows) and (0 <= next_state[1] < board_cols):\n",
+    "                if next_state not in self.gray_state:\n",
+    "                    return next_state\n",
+    "            return self.state\n",
+    "\n",
+    "class Agent:\n",
+    "    def __init__(self, exp_rate=0.3, temperature=1.0, temperature_decay=0.99):\n",
+    "        self.actions = [\"up\", \"down\", \"left\", \"right\"]\n",
+    "        self.State = State(start, board, win_state, loss_state, gray_state)\n",
+    "        self.learning_rate = 0.01\n",
+    "        self.discount = 0.9\n",
+    "\n",
+    "        # Exploration settings\n",
+    "        self.exp_rate = exp_rate  # For epsilon-greedy\n",
+    "        self.temperature = temperature  # For Boltzmann exploration\n",
+    "        self.temperature_decay = temperature_decay\n",
+    "\n",
+    "        # Initialize Q-values\n",
+    "        self.Q_values = {}\n",
+    "        for i in range(board_rows):\n",
+    "            for j in range(board_cols):\n",
+    "                self.Q_values[(i, j)] = {a: 0 for a in self.actions}\n",
+    "\n",
+    "    def softmax(self, q_values, temperature):\n",
+    "        max_q = max(q_values.values())\n",
+    "        exp_q = {a: math.exp((q - max_q) / temperature) for a, q in q_values.items()}\n",
+    "        total = sum(exp_q.values())\n",
+    "        return {a: exp_q[a] / total for a in q_values.keys()}\n",
+    "\n",
+    "    def chooseAction(self, exploration_policy=\"epsilon-greedy\"):\n",
+    "        if exploration_policy == \"epsilon-greedy\":\n",
+    "            if np.random.uniform(0, 1) <= self.exp_rate:\n",
+    "                return np.random.choice(self.actions)\n",
+    "            else:\n",
+    "                current_state = self.State.state\n",
+    "                q_values = self.Q_values[current_state]\n",
+    "                max_q = max(q_values.values())\n",
+    "                max_actions = [a for a, q in q_values.items() if q == max_q]\n",
+    "                return np.random.choice(max_actions)\n",
+    "        elif exploration_policy == \"boltzmann\":\n",
+    "            current_state = self.State.state\n",
+    "            q_values = self.Q_values[current_state]\n",
+    "            probabilities = self.softmax(q_values, self.temperature)\n",
+    "            actions, probs = zip(*probabilities.items())\n",
+    "            return np.random.choice(actions, p=probs)\n",
+    "\n",
+    "    def TakeAction(self, action):\n",
+    "        position = self.State.nextPosition(action)\n",
+    "        return State(position, board, win_state, loss_state, gray_state)\n",
+    "\n",
+    "    def reset(self):\n",
+    "        self.State = State(start, board, win_state, loss_state, gray_state)\n",
+    "\n",
+    "    def play(self, rounds=10000, exploration_policy=\"epsilon-greedy\", max_steps_per_episode=10000):\n",
+    "        convergence_threshold = 1e-3\n",
+    "        for episode in range(rounds):\n",
+    "            self.reset()\n",
+    "            max_change = 0\n",
+    "            steps = 0\n",
+    "            while not self.State.isEnd and steps < max_steps_per_episode:\n",
+    "                current_state = self.State.state\n",
+    "                action = self.chooseAction(exploration_policy)\n",
+    "                self.State = self.TakeAction(action)\n",
+    "                reward = self.State.giveReward()\n",
+    "                next_state = self.State.state\n",
+    "                self.State.isEndFunc()\n",
+    "\n",
+    "                # Q-learning update\n",
+    "                q_current = self.Q_values[current_state][action]\n",
+    "                if self.State.isEnd:\n",
+    "                    q_target = reward\n",
+    "                else:\n",
+    "                    q_target = reward + self.discount * max(self.Q_values[next_state].values())\n",
+    "                updated_q_value = q_current + self.learning_rate * (q_target - q_current)\n",
+    "                max_change = max(max_change, abs(updated_q_value - q_current))\n",
+    "                self.Q_values[current_state][action] = round(updated_q_value, 3)\n",
+    "\n",
+    "                # Reset if end state is reached\n",
+    "                if self.State.isEnd and self.State.state in self.State.win_state:\n",
+    "                    self.State = State(start, board, win_state, loss_state, gray_state)\n",
+    "                elif self.State.isEnd:\n",
+    "                    break  # Episode ends on losing state\n",
+    "\n",
+    "                steps += 1\n",
+    "\n",
+    "                # Decay exploration parameters if needed\n",
+    "                if exploration_policy == \"boltzmann\":\n",
+    "                    self.temperature = max(0.1, self.temperature * self.temperature_decay)\n",
+    "\n",
+    "\n",
+    "            if max_change < convergence_threshold:\n",
+    "                print(f\"Converged after {episode + 1} episodes with {exploration_policy} policy.\")\n",
+    "                break\n",
+    "\n",
+    "    def visualize_q_values(self, q_values, gray_state, board_rows=10, board_cols=10):\n",
+    "        grid = np.zeros((board_rows, board_cols))\n",
+    "        for i in range(board_rows):\n",
+    "            for j in range(board_cols):\n",
+    "                if (i, j) in gray_state:\n",
+    "                    grid[i, j] = np.nan\n",
+    "                else:\n",
+    "                    grid[i, j] = max(q_values[(i, j)].values())\n",
+    "        plt.figure(figsize=(8, 8))\n",
+    "        plt.imshow(grid, cmap=\"coolwarm\", interpolation=\"nearest\")\n",
+    "        plt.colorbar(label=\"Max Q-value\")\n",
+    "        if policy == \"epsilon-greedy\":\n",
+    "            plt.title(f\"Q-value Heatmap {policy}, epsilon = {self.exp_rate}\")\n",
+    "        elif policy == \"boltzmann\":\n",
+    "            plt.title(f\"Q-value Heatmap {policy}, temperature = 20\")\n",
+    "        plt.xticks(range(board_cols))\n",
+    "        plt.yticks(range(board_rows))\n",
+    "        plt.gca().invert_yaxis()\n",
+    "        for i in range(board_rows):\n",
+    "            for j in range(board_cols):\n",
+    "                if not np.isnan(grid[i, j]):\n",
+    "                    plt.text(j, i, f\"{grid[i, j]:.2f}\", ha=\"center\", va=\"center\", fontsize=8, color=\"black\")\n",
+    "        if policy == 'epsilon-greedy':\n",
+    "            plt.savefig(f\"q_values_{policy}_{self.exp_rate}.jpeg\", dpi = 600)\n",
+    "        elif policy == 'boltzmann':\n",
+    "            plt.savefig(f\"q_values_{policy}_T20.jpeg\", dpi = 600)\n",
+    "        plt.show()\n",
+    "\n",
+    "    def display_converged_q_values(self, q_values):\n",
+    "        for state, actions in q_values.items():\n",
+    "            print(f\"State {state}: {actions}\")\n",
+    "\n",
+    "if __name__ == \"__main__\":\n",
+    "    policies = [\"epsilon-greedy\", \"boltzmann\"]\n",
+    "    for policy in policies:\n",
+    "        if policy == \"epsilon-greedy\":\n",
+    "            for exp_rate in [0.1, 0.2, 0.3]:\n",
+    "                print(f\"\\nTraining with {policy} policy, epsilon = {exp_rate}...\")\n",
+    "                ag = Agent(exp_rate=exp_rate)\n",
+    "                ag.play(10000, exploration_policy=policy)\n",
+    "                ag.visualize_q_values(ag.Q_values, gray_state)\n",
+    "                # ag.display_converged_q_values(ag.Q_values)\n",
+    "        elif policy == \"boltzmann\":\n",
+    "            print(f\"\\nTraining with {policy} policy...\")\n",
+    "            ag = Agent(temperature=20.0, temperature_decay=0.99)\n",
+    "            ag.play(10000, exploration_policy=policy)\n",
+    "            ag.visualize_q_values(ag.Q_values, gray_state)\n",
+    "            # ag.display_converged_q_values(ag.Q_values)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}