{"cells":[{"cell_type":"markdown","metadata":{},"source":"# Custom ResNet50 for Object Recognition in Images with AdamW on CIFAR-10\n\n**Dataset's link:** [CIFAR-10 Competition on Kaggle](https://www.kaggle.com/competitions/cifar-10/overview/description)\n\n---\n\n## Description\n\nCIFAR-10 is an established computer-vision dataset used for object recognition. It is a subset of the 80 million tiny images dataset and consists of **60,000 32x32 color images** containing one of **10 object classes**, with **6,000 images per class**. \n\nIt was collected by **Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton**.\n\n\n\n---\n\n## Data Description\n\nThe CIFAR-10 data consists of **60,000 32x32 color images** in 10 classes, with **6,000 images per class**:\n\n- **50,000 training images**\n- **10,000 test images**\n\nThe official train/test split is preserved. Provided files include:\n\n- `train.7z` — a folder containing training images in PNG format  \n- `test.7z` — a folder containing test images in PNG format  \n- `trainLabels.csv` — the training labels  \n\n>Note:\n>To discourage cheating (e.g., hand labeling), the test set contains:\n>- **290,000 junk images** (ignored in scoring)\n>- Trivial modifications to official 10,000 test images to prevent hash lookup\n\nYou must predict labels for **all 300,000 images**.\n\n---\n\n## Label Classes\n\nThe dataset has 10 classes:\n\n- airplane  \n- automobile  \n- bird  \n- cat  \n- deer  \n- dog  \n- frog  \n- horse  \n- ship  \n- truck  \n\n> Note:  \n> - “Automobile” includes sedans, SUVs, etc.  \n> - “Truck” includes only large trucks (not pickup trucks)  \n> - Classes are completely distinct (no overlap)\n"},{"cell_type":"markdown","metadata":{},"source":""},{"cell_type":"markdown","metadata":{},"source":"# Resnet50 architecture\n"},{"cell_type":"code","execution_count":1,"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.execute_input":"2025-05-11T08:08:59.595064Z","iopub.status.busy":"2025-05-11T08:08:59.594812Z","iopub.status.idle":"2025-05-11T08:09:08.080505Z","shell.execute_reply":"2025-05-11T08:09:08.079873Z","shell.execute_reply.started":"2025-05-11T08:08:59.595017Z"},"trusted":true},"outputs":[],"source":"import numpy as np\nimport pandas as pd\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torchvision\nfrom torchvision.transforms import v2\nimport matplotlib.pyplot as plt\nfrom PIL import Image\n"},{"cell_type":"code","execution_count":2,"metadata":{"execution":{"iopub.execute_input":"2025-05-11T08:09:08.081489Z","iopub.status.busy":"2025-05-11T08:09:08.081178Z","iopub.status.idle":"2025-05-11T08:09:08.143929Z","shell.execute_reply":"2025-05-11T08:09:08.143082Z","shell.execute_reply.started":"2025-05-11T08:09:08.081473Z"},"trusted":true},"outputs":[{"name":"stdout","output_type":"stream","text":["cuda\n"]}],"source":"device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\nprint(device)"},{"cell_type":"markdown","metadata":{},"source":"# Data preprocessing"},{"cell_type":"code","execution_count":3,"metadata":{"execution":{"iopub.execute_input":"2025-05-11T08:09:08.146731Z","iopub.status.busy":"2025-05-11T08:09:08.146454Z","iopub.status.idle":"2025-05-11T08:09:15.562786Z","shell.execute_reply":"2025-05-11T08:09:15.562021Z","shell.execute_reply.started":"2025-05-11T08:09:08.146710Z"},"trusted":true},"outputs":[{"name":"stdout","output_type":"stream","text":["Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar-10-python.tar.gz\n"]},{"name":"stderr","output_type":"stream","text":["100%|██████████| 170M/170M [00:03<00:00, 50.2MB/s] \n"]},{"name":"stdout","output_type":"stream","text":["Extracting ./data/cifar-10-python.tar.gz to ./data\n","Files already downloaded and verified\n","Files already downloaded and verified\n"]}],"source":"#Data augmentation\nmean=[0.485, 0.456, 0.406]\nstd=[0.229, 0.224, 0.225]\ntrain_transform = v2.Compose([\n    v2.ToImage(), \n    v2.ToDtype(torch.float32, scale=True),  \n    v2.RandomHorizontalFlip(),\n    v2.RandomRotation(20),\n    v2.RandomCrop(32, padding=4),  \n    v2.Normalize(mean=mean,\n                 std=std)  \n])\n\ndev_transform = v2.Compose([\n    v2.ToImage(),\n    v2.ToDtype(torch.float32, scale=True),\n    v2.RandomHorizontalFlip(),\n    v2.RandomRotation(20),\n    v2.RandomCrop(32, padding=4),\n    v2.Normalize(mean=mean,\n                 std=std)  \n])\n\ntest_transform = v2.Compose([\n    v2.ToImage(), \n    v2.ToDtype(torch.float32, scale=True),    \n    v2.Normalize(mean=mean,\n                 std=std)  \n])\n\ntrain_datasets = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=train_transform)\ndev_datasets = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=dev_transform)\ntest_datasets = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=test_transform)\ntrain_loader = torch.utils.data.DataLoader(train_datasets, batch_size=256, shuffle=True)\ndev_loader = torch.utils.data.DataLoader(dev_datasets, batch_size=256, shuffle=True)\ntest_loader = torch.utils.data.DataLoader(test_datasets, batch_size=256, shuffle=True)"},{"cell_type":"code","execution_count":4,"metadata":{"execution":{"iopub.execute_input":"2025-05-11T08:09:15.563819Z","iopub.status.busy":"2025-05-11T08:09:15.563636Z","iopub.status.idle":"2025-05-11T08:09:16.315463Z","shell.execute_reply":"2025-05-11T08:09:16.314693Z","shell.execute_reply.started":"2025-05-11T08:09:15.563804Z"},"trusted":true},"outputs":[{"data":{"image/png":"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","text/plain":["<Figure size 1000x500 with 10 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":"classes = train_datasets.classes\n\ndef im_convert(tensor):\n    img = tensor.cpu().clone().detach().numpy() \n    img = img.transpose(1, 2, 0)\n    img = img * np.array(tuple(mean)) + np.array(tuple(std))\n    img = img.clip(0, 1)\n    return img\n\ndata_iterable = iter(train_loader) \nimages, labels = next(data_iterable) \nfig = plt.figure(figsize=(10, 5)) \n\nfor idx in np.arange(10):\n    ax = fig.add_subplot(2, 5, idx+1, xticks=[], yticks=[])\n    plt.imshow(im_convert(images[idx]))\n    ax.set_title(classes[labels[idx].item()])"},{"cell_type":"markdown","metadata":{},"source":"# Training model"},{"cell_type":"code","execution_count":5,"metadata":{"execution":{"iopub.execute_input":"2025-05-11T08:09:16.316649Z","iopub.status.busy":"2025-05-11T08:09:16.316293Z","iopub.status.idle":"2025-05-11T08:09:16.669233Z","shell.execute_reply":"2025-05-11T08:09:16.668649Z","shell.execute_reply.started":"2025-05-11T08:09:16.316626Z"},"trusted":true},"outputs":[],"source":"#Model\nclass Block(nn.Module):\n    def __init__(self, in_channels, out_channels, identity_downsample=None, stride=1):\n        super().__init__()\n        self.expansion = 4\n        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0)\n        self.bn1 = nn.BatchNorm2d(out_channels)\n\n        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=stride, padding=1)\n        self.bn2 = nn.BatchNorm2d(out_channels)\n\n        self.conv3 = nn.Conv2d(out_channels, out_channels * self.expansion, kernel_size=1, stride=1, padding=0)\n        self.bn3 = nn.BatchNorm2d(out_channels * self.expansion)\n\n        self.relu = nn.ReLU()\n        self.identity_downsample = identity_downsample\n\n    def forward(self, x):\n        identity = x\n\n        x = self.conv1(x)\n        x = self.bn1(x)\n        x = self.relu(x)\n\n        x = self.conv2(x)\n        x = self.bn2(x)\n        x = self.relu(x)\n\n        x = self.conv3(x)\n        x = self.bn3(x)\n\n        if self.identity_downsample is not None:\n            identity = self.identity_downsample(identity)\n\n        x += identity\n        x = self.relu(x)\n        return x\n\n\nclass ResNet(nn.Module):\n    def __init__(self, block, layers, image_channels, num_classes):\n        super().__init__()\n        self.in_channels = 64\n\n        self.conv1 = nn.Conv2d(image_channels, 64, kernel_size=3, stride=1, padding=1)\n        self.bn1 = nn.BatchNorm2d(64)\n        self.relu = nn.ReLU()\n\n        self.maxpool = nn.Identity()\n\n        self.layer1 = self._make_layer(block, layers[0], out_channels=64, stride=1)\n        self.layer2 = self._make_layer(block, layers[1], out_channels=128, stride=2)\n        self.layer3 = self._make_layer(block, layers[2], out_channels=256, stride=2)\n        self.layer4 = self._make_layer(block, layers[3], out_channels=512, stride=2)\n\n        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))\n        self.fc = nn.Linear(512 * 4, num_classes)\n\n    def forward(self, x):\n        x = self.conv1(x)\n        x = self.bn1(x)\n        x = self.relu(x)\n        x = self.maxpool(x)\n\n        x = self.layer1(x)\n        x = self.layer2(x)\n        x = self.layer3(x)\n        x = self.layer4(x)\n\n        x = self.avgpool(x)\n        x = x.reshape(x.shape[0], -1)\n        x = self.fc(x)\n        return x\n\n    def _make_layer(self, block, num_res_blocks, out_channels, stride):\n        identity_downsample = None\n        layers = []\n\n        if stride != 1 or self.in_channels != out_channels * 4:\n            identity_downsample = nn.Sequential(\n                nn.Conv2d(self.in_channels, out_channels * 4, kernel_size=1, stride=stride),\n                nn.BatchNorm2d(out_channels * 4)\n            )\n\n        layers.append(block(self.in_channels, out_channels, identity_downsample, stride))\n        self.in_channels = out_channels * 4\n\n        for _ in range(num_res_blocks - 1):\n            layers.append(block(self.in_channels, out_channels))\n\n        return nn.Sequential(*layers)\n\n\ndef ResNet50(img_channels=3, num_classes=10):\n    return ResNet(Block, [3, 4, 6, 3], img_channels, num_classes)\n\nmodel = ResNet50().to(device)"},{"cell_type":"markdown","metadata":{},"source":"# Optimizer & training"},{"cell_type":"code","execution_count":6,"metadata":{"execution":{"iopub.execute_input":"2025-05-11T08:09:16.670188Z","iopub.status.busy":"2025-05-11T08:09:16.669968Z","iopub.status.idle":"2025-05-11T10:07:03.428071Z","shell.execute_reply":"2025-05-11T10:07:03.427318Z","shell.execute_reply.started":"2025-05-11T08:09:16.670171Z"},"trusted":true},"outputs":[{"name":"stdout","output_type":"stream","text":["Epoch [1/50]\n","  Train Loss     : 1.7223\n","  Train Accuracy : 37.22%\n","  Dev Loss       : 1.6089\n","  Dev Accuracy   : 44.24%\n","Epoch [2/50]\n","  Train Loss     : 1.2403\n","  Train Accuracy : 55.06%\n","  Dev Loss       : 1.1779\n","  Dev Accuracy   : 58.07%\n","Epoch [3/50]\n","  Train Loss     : 1.0467\n","  Train Accuracy : 62.65%\n","  Dev Loss       : 1.0333\n","  Dev Accuracy   : 63.28%\n","Epoch [4/50]\n","  Train Loss     : 0.9007\n","  Train Accuracy : 68.08%\n","  Dev Loss       : 1.0775\n","  Dev Accuracy   : 63.17%\n","Epoch [5/50]\n","  Train Loss     : 0.8039\n","  Train Accuracy : 71.63%\n","  Dev Loss       : 0.8561\n","  Dev Accuracy   : 70.17%\n","Epoch [6/50]\n","  Train Loss     : 0.7209\n","  Train Accuracy : 74.53%\n","  Dev Loss       : 0.8392\n","  Dev Accuracy   : 70.44%\n","Epoch [7/50]\n","  Train Loss     : 0.6520\n","  Train Accuracy : 77.05%\n","  Dev Loss       : 0.7889\n","  Dev Accuracy   : 73.23%\n","Epoch [8/50]\n","  Train Loss     : 0.6008\n","  Train Accuracy : 78.89%\n","  Dev Loss       : 0.7704\n","  Dev Accuracy   : 74.03%\n","Epoch [9/50]\n","  Train Loss     : 0.5506\n","  Train Accuracy : 80.69%\n","  Dev Loss       : 0.6125\n","  Dev Accuracy   : 78.72%\n","Epoch [10/50]\n","  Train Loss     : 0.5141\n","  Train Accuracy : 82.03%\n","  Dev Loss       : 0.7180\n","  Dev Accuracy   : 76.77%\n","Epoch [11/50]\n","  Train Loss     : 0.4825\n","  Train Accuracy : 83.28%\n","  Dev Loss       : 0.6108\n","  Dev Accuracy   : 78.63%\n","Epoch [12/50]\n","  Train Loss     : 0.4652\n","  Train Accuracy : 83.84%\n","  Dev Loss       : 0.5900\n","  Dev Accuracy   : 79.80%\n","Epoch [13/50]\n","  Train Loss     : 0.4408\n","  Train Accuracy : 84.58%\n","  Dev Loss       : 0.6821\n","  Dev Accuracy   : 77.35%\n","Epoch [14/50]\n","  Train Loss     : 0.4264\n","  Train Accuracy : 85.26%\n","  Dev Loss       : 0.5524\n","  Dev Accuracy   : 81.37%\n","Epoch [15/50]\n","  Train Loss     : 0.3978\n","  Train Accuracy : 86.09%\n","  Dev Loss       : 0.5189\n","  Dev Accuracy   : 82.04%\n","Epoch [16/50]\n","  Train Loss     : 0.3810\n","  Train Accuracy : 86.70%\n","  Dev Loss       : 0.4877\n","  Dev Accuracy   : 83.04%\n","Epoch [17/50]\n","  Train Loss     : 0.3718\n","  Train Accuracy : 86.99%\n","  Dev Loss       : 0.4881\n","  Dev Accuracy   : 83.24%\n","Epoch [18/50]\n","  Train Loss     : 0.3524\n","  Train Accuracy : 87.78%\n","  Dev Loss       : 0.5100\n","  Dev Accuracy   : 82.99%\n","Epoch [19/50]\n","  Train Loss     : 0.3400\n","  Train Accuracy : 87.99%\n","  Dev Loss       : 0.4607\n","  Dev Accuracy   : 84.81%\n","Epoch [20/50]\n","  Train Loss     : 0.3319\n","  Train Accuracy : 88.42%\n","  Dev Loss       : 0.4954\n","  Dev Accuracy   : 83.53%\n","Epoch [21/50]\n","  Train Loss     : 0.3174\n","  Train Accuracy : 88.91%\n","  Dev Loss       : 0.4635\n","  Dev Accuracy   : 84.87%\n","Epoch [22/50]\n","  Train Loss     : 0.3004\n","  Train Accuracy : 89.50%\n","  Dev Loss       : 0.5339\n","  Dev Accuracy   : 82.63%\n","Epoch [23/50]\n","  Train Loss     : 0.2909\n","  Train Accuracy : 89.76%\n","  Dev Loss       : 0.4764\n","  Dev Accuracy   : 84.07%\n","Epoch [24/50]\n","  Train Loss     : 0.2816\n","  Train Accuracy : 90.11%\n","  Dev Loss       : 0.4909\n","  Dev Accuracy   : 84.08%\n","Epoch [25/50]\n","  Train Loss     : 0.2734\n","  Train Accuracy : 90.41%\n","  Dev Loss       : 0.4709\n","  Dev Accuracy   : 84.39%\n","Epoch [26/50]\n","  Train Loss     : 0.2625\n","  Train Accuracy : 90.76%\n","  Dev Loss       : 0.4506\n","  Dev Accuracy   : 84.93%\n","Epoch [27/50]\n","  Train Loss     : 0.2520\n","  Train Accuracy : 91.17%\n","  Dev Loss       : 0.4450\n","  Dev Accuracy   : 85.78%\n","Epoch [28/50]\n","  Train Loss     : 0.2466\n","  Train Accuracy : 91.35%\n","  Dev Loss       : 0.4392\n","  Dev Accuracy   : 85.92%\n","Epoch [29/50]\n","  Train Loss     : 0.2356\n","  Train Accuracy : 91.73%\n","  Dev Loss       : 0.4227\n","  Dev Accuracy   : 86.51%\n","Epoch [30/50]\n","  Train Loss     : 0.2357\n","  Train Accuracy : 91.62%\n","  Dev Loss       : 0.3775\n","  Dev Accuracy   : 87.24%\n","Epoch [31/50]\n","  Train Loss     : 0.2253\n","  Train Accuracy : 92.08%\n","  Dev Loss       : 0.4626\n","  Dev Accuracy   : 85.16%\n","Epoch [32/50]\n","  Train Loss     : 0.2203\n","  Train Accuracy : 92.27%\n","  Dev Loss       : 0.4010\n","  Dev Accuracy   : 86.58%\n","Epoch [33/50]\n","  Train Loss     : 0.2513\n","  Train Accuracy : 91.27%\n","  Dev Loss       : 0.4221\n","  Dev Accuracy   : 86.11%\n","Epoch [34/50]\n","  Train Loss     : 0.2239\n","  Train Accuracy : 92.06%\n","  Dev Loss       : 0.4092\n","  Dev Accuracy   : 86.54%\n","Epoch [35/50]\n","  Train Loss     : 0.2029\n","  Train Accuracy : 92.85%\n","  Dev Loss       : 0.4201\n","  Dev Accuracy   : 86.42%\n","Epoch [36/50]\n","  Train Loss     : 0.1890\n","  Train Accuracy : 93.32%\n","  Dev Loss       : 0.3886\n","  Dev Accuracy   : 87.24%\n","Epoch [37/50]\n","  Train Loss     : 0.1832\n","  Train Accuracy : 93.42%\n","  Dev Loss       : 0.3697\n","  Dev Accuracy   : 87.83%\n","Epoch [38/50]\n","  Train Loss     : 0.1756\n","  Train Accuracy : 93.89%\n","  Dev Loss       : 0.4106\n","  Dev Accuracy   : 88.01%\n","Epoch [39/50]\n","  Train Loss     : 0.1743\n","  Train Accuracy : 93.88%\n","  Dev Loss       : 0.3339\n","  Dev Accuracy   : 88.83%\n","Epoch [40/50]\n","  Train Loss     : 0.1648\n","  Train Accuracy : 94.09%\n","  Dev Loss       : 0.4596\n","  Dev Accuracy   : 86.15%\n","Epoch [41/50]\n","  Train Loss     : 0.1633\n","  Train Accuracy : 94.21%\n","  Dev Loss       : 0.3470\n","  Dev Accuracy   : 88.65%\n","Epoch [42/50]\n","  Train Loss     : 0.1582\n","  Train Accuracy : 94.43%\n","  Dev Loss       : 0.3804\n","  Dev Accuracy   : 88.08%\n","Epoch [43/50]\n","  Train Loss     : 0.1555\n","  Train Accuracy : 94.55%\n","  Dev Loss       : 0.4037\n","  Dev Accuracy   : 87.84%\n","Epoch [44/50]\n","  Train Loss     : 0.1514\n","  Train Accuracy : 94.60%\n","  Dev Loss       : 0.3885\n","  Dev Accuracy   : 88.23%\n","Epoch [45/50]\n","  Train Loss     : 0.1452\n","  Train Accuracy : 94.76%\n","  Dev Loss       : 0.4087\n","  Dev Accuracy   : 87.86%\n","Epoch [46/50]\n","  Train Loss     : 0.1421\n","  Train Accuracy : 94.94%\n","  Dev Loss       : 0.3772\n","  Dev Accuracy   : 89.02%\n","Epoch [47/50]\n","  Train Loss     : 0.1367\n","  Train Accuracy : 95.13%\n","  Dev Loss       : 0.3406\n","  Dev Accuracy   : 89.35%\n","Epoch [48/50]\n","  Train Loss     : 0.1390\n","  Train Accuracy : 95.04%\n","  Dev Loss       : 0.3577\n","  Dev Accuracy   : 89.00%\n","Epoch [49/50]\n","  Train Loss     : 0.1297\n","  Train Accuracy : 95.43%\n","  Dev Loss       : 0.3741\n","  Dev Accuracy   : 88.94%\n","Epoch [50/50]\n","  Train Loss     : 0.1261\n","  Train Accuracy : 95.51%\n","  Dev Loss       : 0.3719\n","  Dev Accuracy   : 89.19%\n","Training done\n"]}],"source":"#Optimizer\nepochs = 50\ncriterion = nn.CrossEntropyLoss()\noptimizer = torch.optim.AdamW(model.parameters(), lr=0.001, weight_decay=0.01)\n\ntrain_losses = []\ndev_losses = []\ntrain_accuracies = []\ndev_accuracies = []\n\nbest_accuracy = 0.0\npatience = 10\nepochs_no_improve = 0\nbest_model_path = \"best_model.pt\"\n\n# Training\nn_total_steps = len(train_loader)\nfor epoch in range(epochs):\n    running_loss = 0.0\n    n_correct_train = 0\n    n_samples_train = 0\n\n    model.train()\n    for i, (images, labels) in enumerate(train_loader):\n        images = images.to(device)\n        labels = labels.to(device)\n\n        outputs = model(images)\n        loss = criterion(outputs, labels)\n\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n\n        running_loss += loss.item()\n\n        _, predicted = torch.max(outputs, 1)\n        n_correct_train += (predicted == labels).sum().item()\n        n_samples_train += labels.size(0)\n\n    train_acc = 100.0 * n_correct_train / n_samples_train\n    train_loss = running_loss / len(train_loader)\n\n    # Evaluate on dev set\n    model.eval()\n    dev_loss = 0.0\n    n_correct = 0\n    n_samples = 0\n\n    with torch.no_grad():\n        for images, labels in dev_loader:\n            images = images.to(device)\n            labels = labels.to(device)\n            outputs = model(images)\n            loss = criterion(outputs, labels)\n            dev_loss += loss.item()\n\n            _, predicted = torch.max(outputs, 1)\n            n_correct += (predicted == labels).sum().item()\n            n_samples += labels.size(0)\n\n    dev_acc = 100.0 * n_correct / n_samples\n    dev_loss = dev_loss / len(dev_loader)\n\n    print(f\"Epoch [{epoch+1}/{epochs}]\")\n    print(f\"  Train Loss     : {train_loss:.4f}\")\n    print(f\"  Train Accuracy : {train_acc:.2f}%\")\n    print(f\"  Dev Loss       : {dev_loss:.4f}\")\n    print(f\"  Dev Accuracy   : {dev_acc:.2f}%\")\n\n    train_losses.append(train_loss)\n    dev_losses.append(dev_loss)\n    train_accuracies.append(train_acc)\n    dev_accuracies.append(dev_acc)\n\n    # Early stopping check\n    if dev_acc > best_accuracy:\n        best_accuracy = dev_acc\n        epochs_no_improve = 0\n        torch.save(model.state_dict(), best_model_path)\n    else:\n        epochs_no_improve += 1\n\n    if epochs_no_improve >= patience:\n        print(\"Early stopping\")\n        break\n\nprint(\"Training done\")"},{"cell_type":"markdown","metadata":{},"source":"# Result"},{"cell_type":"code","execution_count":7,"metadata":{"execution":{"iopub.execute_input":"2025-05-11T10:07:03.429079Z","iopub.status.busy":"2025-05-11T10:07:03.428819Z","iopub.status.idle":"2025-05-11T10:07:12.437978Z","shell.execute_reply":"2025-05-11T10:07:12.437308Z","shell.execute_reply.started":"2025-05-11T10:07:03.429050Z"},"trusted":true},"outputs":[{"name":"stdout","output_type":"stream","text":["Accuracy of the network: 90.89%\n","Accuracy of airplane: 91.50%\n","Accuracy of automobile: 97.30%\n","Accuracy of bird: 88.70%\n","Accuracy of cat: 83.90%\n","Accuracy of deer: 92.90%\n","Accuracy of dog: 82.30%\n","Accuracy of frog: 93.70%\n","Accuracy of horse: 89.50%\n","Accuracy of ship: 95.20%\n","Accuracy of truck: 93.90%\n"]}],"source":"#Testing\nwith torch.no_grad():\n    n_correct = 0\n    n_samples = 0\n    n_class_correct = [0 for _ in range(10)]\n    n_class_samples = [0 for _ in range(10)]\n\n    for images, labels in test_loader:\n        images = images.to(device)\n        labels = labels.to(device)\n\n        output = model(images)\n        _, predicted = torch.max(output, 1)\n\n        n_samples += labels.size(0)\n        n_correct += (predicted==labels).sum().item()\n\n        for i in range(labels.size(0)):\n            label = labels[i]\n            pred = predicted[i]\n            if label == pred:\n                n_class_correct[label] += 1\n            n_class_samples[label] += 1\n\n    acc = 100.0 * n_correct / n_samples\n    print(f'Accuracy of the network: {acc:.2f}%')\n\n    for i in range(10):\n        acc = 100.0 * n_class_correct[i] / n_class_samples[i]\n        print(f'Accuracy of {classes[i]}: {acc:.2f}%')"},{"cell_type":"code","execution_count":8,"metadata":{"execution":{"iopub.execute_input":"2025-05-11T10:07:12.439676Z","iopub.status.busy":"2025-05-11T10:07:12.439368Z","iopub.status.idle":"2025-05-11T10:07:12.794238Z","shell.execute_reply":"2025-05-11T10:07:12.793385Z","shell.execute_reply.started":"2025-05-11T10:07:12.439649Z"},"trusted":true},"outputs":[{"data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAABKUAAAJOCAYAAABm7rQwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdd3hUZdrH8e/0kknvpBdI6L1IlSKKvYCKuqhYUNe+7qq7r73r2ntFXbH3XsCGhd47AVJJ78n0mfP+MclATIAASYaE+3M518w858w595QQ55enqBRFURBCCCGEEEIIIYQQogupA12AEEIIIYQQQgghhDj6SCglhBBCCCGEEEIIIbqchFJCCCGEEEIIIYQQostJKCWEEEIIIYQQQgghupyEUkIIIYQQQgghhBCiy0koJYQQQgghhBBCCCG6nIRSQgghhBBCCCGEEKLLSSglhBBCCCGEEEIIIbqchFJCCCGEEEIIIYQQostJKCWEEEJ0sWOPPZZjjz020GWILpKbm4tKpeK///3vYR3n/fffJyIigoaGhg6qTIgjm8vlIikpieeeey7QpQghhOgkEkoJIUQP89xzz6FSqRg9enSgSxGHKTU1lZNPPjnQZRzxmkOffV0efPDBQJd42DweD3fccQfXXHMNFovF356amtriuQYFBTFq1CjefPPNTq2n+XyPPvpoq22vv/46KpWKFStWHPRxN23axJ133klubm6rbRdddFGb7292dnarfb1eLw8//DBpaWkYjUYGDRrEO++8c9D1dIWff/6ZM888k7i4OPR6PTExMZxyyil8/PHH/n3aCjZ//vnnfX7mzz333Bbn+Prrr1GpVPTq1Quv19tmHR3xWXrvvfe44IIL6N27NyqVar/hu8Ph4Oabb6ZXr16YTCZGjx7NDz/80GIfnU7HjTfeyH333Yfdbm93HUIIIboPbaALEEII0bEWLFhAamoqy5YtIycnh8zMzECXJESXmD17NieeeGKr9qFDhwagmo71xRdfsHXrVi6//PJW24YMGcI//vEPAIqLi3nllVe48MILcTgcXHbZZZ1a1yOPPMKVV16J2WzukONt2rSJu+66i2OPPZbU1NRW2w0GA6+88kqLttDQ0Fb7/ec//+HBBx/ksssuY+TIkXz22Wecd955bQY2gXTHHXdw991307t3b+bNm0dKSgqVlZV8/fXXnHXWWSxYsIDzzjtvv8e49tprGTlyZIu2v752zb8XcnNz+fHHH5k2bVqbxzrcz9Lzzz/PypUrGTlyJJWVlfvd96KLLuLDDz/k+uuvp3fv3rz++uuceOKJ/PTTT4wfP96/38UXX8wtt9zC22+/zdy5cw9YgxBCiG5GEUII0WPs3LlTAZSPP/5YiY6OVu68885Al7RPDQ0NgS4hYCZNmqRMmjTpgPulpKQoJ510UucX1A3s7/Oya9cuBVAeeeSRLqyo/TqivlNPPVUZP358q/a2PiNlZWWKxWJR+vbte8jnOxBAGTJkiAIojz76aItt8+fPVwBl+fLlB33cDz74QAGUn376qdW2Cy+8UAkKCjrgMQoLCxWdTqf8/e9/97d5vV5lwoQJSmJiouJ2uw+6rs7Q/FxnzpypOJ3OVtu//fZb5YsvvlAUpe3P0E8//aQAygcffLDf8zQ0NChBQUHKU089pQwdOlS56KKL2tyvIz5L+fn5isfjURRFUfr377/Pf+eWLl3a6vnYbDYlIyNDOeaYY1rtf/LJJysTJkxoVw1CCCG6Fxm+J4QQPciCBQsIDw/npJNOYubMmSxYsKDN/WpqarjhhhtITU3FYDCQmJjInDlzqKio8O9jt9u588476dOnD0ajkfj4eM4880x27NgB7Bk68vPPP7c4dvMwk9dff93fdtFFF2GxWNixYwcnnngiwcHBnH/++QAsXryYWbNmkZycjMFgICkpiRtuuAGbzdaq7i1btnD22WcTHR2NyWQiKyuL//znPwD89NNPqFQqPvnkk1aPe/vtt1GpVPz555/7fO2qqqq46aabGDhwIBaLhZCQEGbMmMHatWtb7Nf8vN9//33uu+8+EhMTMRqNTJ06lZycnFbHfemll8jIyMBkMjFq1CgWL168zxoOhdvt5p577iEjIwODwUBqair//ve/cTgcLfZbsWIFxx9/PFFRUZhMJtLS0lr1Onj33XcZPnw4wcHBhISEMHDgQJ588sn9nn/vYUWPP/44KSkpmEwmJk2axIYNG1rtv2XLFmbOnElERARGo5ERI0bw+eeft9inefjXL7/8wlVXXUVMTAyJiYmH+Aq11Dwk8vvvv2fIkCEYjUb69evXYqhUs507dzJr1iwiIiIwm82MGTOGr776qtV+B/pZ2Vvz58FgMDBy5EiWL19+wJrtdjvffvvtPnu3/FV0dDTZ2dmtzu/1enniiSfo378/RqOR2NhY5s2bR3V1dYv92vNZARg3bhxTpkzh4YcfbvPn9a8O9N6//vrrzJo1C4DJkyf7h5H99d8Yj8dDXV3dPs/z2Wef4XK5uOqqq/xtKpWKK6+8ksLCwv3+O9Dsxx9/ZMKECQQFBREWFsZpp53G5s2bW+xz5513olKpyMnJ4aKLLiIsLIzQ0FAuvvhirFbrAc9x2223ERERwWuvvYZOp2u1/fjjj++Q4buffPIJNpuNWbNmce655/Lxxx+3eyjcvj5L+5KUlIRafeCvFx9++CEajaZFzz+j0cgll1zCn3/+SUFBQYv9jzvuOH777TeqqqraVYcQQojuQ4bvCSFED7JgwQLOPPNM9Ho9s2fP5vnnn2f58uUthnY0NDQwYcIENm/ezNy5cxk2bBgVFRV8/vnnFBYWEhUVhcfj4eSTT2bRokWce+65XHfdddTX1/PDDz+wYcMGMjIyDro2t9vN8ccfz/jx4/nvf//rH+7zwQcfYLVaufLKK4mMjGTZsmU8/fTTFBYW8sEHH/gfv27dOiZMmIBOp+Pyyy8nNTWVHTt28MUXX3Dfffdx7LHHkpSUxIIFCzjjjDNavS4ZGRkcc8wx+6xv586dfPrpp8yaNYu0tDRKS0t58cUXmTRpEps2baJXr14t9n/wwQdRq9XcdNNN1NbW8vDDD3P++eezdOlS/z6vvvoq8+bNY+zYsVx//fXs3LmTU089lYiICJKSkg76NWzLpZdeyhtvvMHMmTP5xz/+wdKlS3nggQfYvHmzP6ArKytj+vTpREdHc8sttxAWFkZubm6LIOaHH35g9uzZTJ06lYceegiAzZs38/vvv3PdddcdsI4333yT+vp6/v73v2O323nyySeZMmUK69evJzY2FoCNGzcybtw4EhISuOWWWwgKCuL999/n9NNP56OPPmr1vl111VVER0dz++2309jYeMAarFZri2C1WVhYGFrtnv/l2b59O+eccw5XXHEFF154IfPnz2fWrFl8++23HHfccQCUlpYyduxYrFYr1157LZGRkbzxxhuceuqpfPjhh/5aD+Zn5e2336a+vp558+ahUql4+OGHOfPMM9m5c2eboUSzlStX4nQ6GTZs2AFfA/D9rBUWFhIeHt6ifd68ebz++utcfPHFXHvttezatYtnnnmG1atX8/vvv6PT6dr1WdnbnXfeycSJE3n++ee58cYb91lTe977iRMncu211/LUU0/x73//m759+wL4r8H3HoeEhGC1WgkPD2f27Nk89NBDLebZWr16NUFBQS0eBzBq1Cj/9r2Hh/3VwoULmTFjBunp6dx5553YbDaefvppxo0bx6pVq1oNjTv77LNJS0vjgQceYNWqVbzyyivExMT4f47asn37drZs2cLcuXMJDg7e537tUV9f3+pzHxER4Q+HFixYwOTJk4mLi+Pcc8/llltu4YsvvvAHgPuzr8/S4Vq9ejV9+vQhJCSkRXvze7RmzZoW/0YOHz4cRVH4448/ZJ49IYToaQLdVUsIIUTHWLFihQIoP/zwg6IovuEqiYmJynXXXddiv9tvv90/xO+vvF6voiiK8tprrymA8thjj+1zn+ahI38dZtM8zGT+/Pn+tgsvvFABlFtuuaXV8axWa6u2Bx54QFGpVEpeXp6/beLEiUpwcHCLtr3rURRFufXWWxWDwaDU1NT428rKyhStVqvccccdrc6zN7vd7h92svdzMRgMyt133+1va37effv2VRwOh7/9ySefVABl/fr1iqIoitPpVGJiYpQhQ4a02O+ll15SgA4ZvrdmzRoFUC699NIW7TfddJMCKD/++KOiKIryySefHHA41XXXXaeEhIQc9NCm5vfbZDIphYWF/vbm4Tk33HCDv23q1KnKwIEDFbvd7m/zer3K2LFjld69e/vbmod/jR8/vl31NNewr8uff/7p3zclJUUBlI8++sjfVltbq8THxytDhw71t11//fUKoCxevNjfVl9fr6SlpSmpqan+z0p7flaa64uMjFSqqqr82z/77DMF8A/R2pdXXnmlxWdrbykpKcr06dOV8vJypby8XFm/fr3yt7/9TQFaDF9bvHixAigLFixo8fhvv/22RXt7PiuKorQ4/uTJk5W4uDj/z3Jbw/fa+97vb/jeLbfcotx8883Ke++9p7zzzjv+f1fGjRunuFwu/34nnXSSkp6e3urxjY2N+/x3aG9DhgxRYmJilMrKSn/b2rVrFbVarcyZM8ffdscddyiAMnfu3BaPP+OMM5TIyMj9nqP5vX/88cf3u1+z/Q3fa+uya9cuRVEUpbS0VNFqtcrLL7/sf9zYsWOV0047rdU52vtZaq/9Dd/r37+/MmXKlFbtGzduVADlhRdeaNG+e/duBVAeeuihg65DCCHEkU2G7wkhRA+xYMECYmNjmTx5MuAbrnLOOefw7rvv4vF4/Pt99NFHDB48uFWvlObHNO8TFRXFNddcs899DsWVV17Zqs1kMvlvNzY2UlFRwdixY1EUhdWrVwNQXl7Or7/+yty5c0lOTt5nPXPmzMHhcPDhhx/629577z3cbjcXXHDBfmszGAz+ngUej4fKykosFgtZWVmsWrWq1f4XX3wxer3ef3/ChAmAr8cV+IZAlZWVccUVV7TY76KLLmpzYuZD8fXXXwO06qHSPFFx81CzsLAwAL788ktcLlebxwoLC6OxsbHV6lftdfrpp5OQkOC/P2rUKEaPHu2vsaqqih9//JGzzz7b37OjoqKCyspKjj/+eLZv305RUVGLY1522WVoNJp213D55Zfzww8/tLr069evxX69evVq8fkPCQlhzpw5rF69mpKSEsD32o4aNapFjxqLxcLll19Obm4umzZtAg7uZ+Wcc85p0ePkr5+ZfWmeMHpfvVW+//57oqOjiY6OZuDAgfzvf//j4osv5pFHHvHv88EHHxAaGspxxx3nf+0rKioYPnw4FouFn376CWjfZ+Wv7rzzTkpKSnjhhRfa3H4o731bHnjgAR588EHOPvtszj33XF5//XXuu+8+fv/99xY/8zabDYPB0OrxRqPRv31fiouLWbNmDRdddBERERH+9kGDBnHcccf5P897u+KKK1rcnzBhApWVlfsdYti87XB7SQHcfvvtrT7zcXFxgG9Irlqt5qyzzvLvP3v2bL755ptWwzahfZ+ljnCw71HzZ7+tnpBCCCG6NwmlhBCiB/B4PLz77rtMnjyZXbt2kZOTQ05ODqNHj6a0tJRFixb5992xYwcDBgzY7/F27NhBVlZWiyFPh0ur1bY5L1B+fr7/C6DFYiE6OppJkyYBUFtbC+z50n6gurOzsxk5cmSLubQWLFjAmDFjDrgKodfr5fHHH6d3794YDAaioqKIjo5m3bp1/jr29tdwrPlLU/MXvby8PAB69+7dYj+dTkd6evp+a2mvvLw81Gp1q+cWFxdHWFiYv4ZJkyZx1llncddddxEVFcVpp53G/PnzW8w7ddVVV9GnTx9mzJhBYmIic+fO5dtvv213LX99ngB9+vQhNzcXgJycHBRF4bbbbvN/6W2+3HHHHYBvmOHe0tLS2n3+5hqmTZvW6vLXIUKZmZmtAqM+ffoA+OvNy8sjKyur1Tmah4Q1v7YH87NyoM/MgSiK0mb76NGj+eGHH/j222/573//S1hYGNXV1S3C0O3bt1NbW0tMTEyr17+hocH/2rfns/JXEydOZPLkyfucW+pQ3vv2uuGGG1Cr1SxcuNDfZjKZ2qy3eR6lvYPwv2p+X/f13ldUVLQaSnoo72vzZ7K+vn6f+7TXwIEDW33mm8Odt956i1GjRlFZWen/vTB06FCcTmeL4dHN2vNZqqqqoqSkxH9p69/HAznY96j5s384fxQRQghxZJI5pYQQogf48ccfKS4u5t133+Xdd99ttX3BggVMnz69Q8+5ry8He/fK2tvePZH23ve4446jqqqKm2++mezsbIKCgigqKuKiiy7C6/UedF1z5szhuuuuo7CwEIfDwZIlS3jmmWcO+Lj777+f2267jblz53LPPff452S5/vrr26xjXz149hUcdKYDfVFTqVR8+OGHLFmyhC+++ILvvvuOuXPn8uijj7JkyRIsFgsxMTGsWbOG7777jm+++YZvvvmG+fPnM2fOHN54443DrrH5Nbzppps4/vjj29znr+Ha/sKD7uhQPzORkZGAL+RoK9iNioryT4J+/PHHk52dzcknn8yTTz7p70Xn9XqJiYnZ5+IH0dHRQPs+K2254447OPbYY3nxxRf9va2aHcp7314mk4nIyMgWE2DHx8fz008/oShKi5+N4uJigFbzwx2uQ3lfs7OzAVi/fn2H1rK37du3+yfSbys0XrBgQYuJxqF9n6UzzzyTX375xf+YCy+8sMXCFu0RHx/fZu+4fb1HzQFfVFTUQZ1HCCHEkU9CKSGE6AEWLFhATEwMzz77bKttH3/8MZ988gkvvPACJpOJjIyMNldF21tGRgZLly7F5XLtcwLm5t4ANTU1Ldqbexq0x/r169m2bRtvvPEGc+bM8bf/dQhZc8+iA9UNcO6553LjjTfyzjvvYLPZ0Ol0nHPOOQd83IcffsjkyZN59dVXW7TX1NQc0hehlJQUwPfFcMqUKf52l8vFrl27GDx48EEfs61zeL1etm/f3mJS59LSUmpqavw1NBszZgxjxozhvvvu4+233+b888/n3Xff5dJLLwVAr9dzyimncMopp+D1ernqqqt48cUXue222w4YGmzfvr1V27Zt2/yTQje/hzqdrt2ryHWW5p47ewcW27ZtA/DXm5KSwtatW1s9dsuWLf7t0L6flcPVHGDs2rWLgQMHHnD/k046iUmTJnH//fczb948goKCyMjIYOHChYwbN65dYd+BPit/NWnSJI499lgeeughbr/99hbbDua9P9ieMM3DAZtDNYAhQ4bwyiuvsHnz5hZDN5sXIRgyZMg+j9f8vu7rvY+KiiIoKOigamxLnz59yMrK4rPPPuPJJ5/cZ9h3OBYsWIBOp+N///tfq+Dst99+46mnniI/P79VT6+9tfVZevTRR1v0AjuUkG/IkCH89NNP1NXVtejJuK/3aNeuXQCtJq8XQgjR/cnwPSGE6OZsNhsff/wxJ598MjNnzmx1ufrqq6mvr/cvvX7WWWexdu1a/8pse2v+y/5ZZ51FRUVFmz2MmvdJSUlBo9Hw66+/ttj+3HPPtbv25i9Ke/coUBSFJ598ssV+0dHRTJw4kddee438/Pw262kWFRXFjBkzeOutt1iwYAEnnHBCu0IljUbT6lgffPBBu+a6acuIESOIjo7mhRdewOl0+ttff/31VkHeoTrxxBMBeOKJJ1q0P/bYY4DvCyX4ehn89bk1f+lrHkLTPG9RM7VazaBBg1rssz+ffvppi9dq2bJlLF26lBkzZgAQExPj70nT3Btib+Xl5Qc8R0fZvXt3i89/XV0db775JkOGDPHPxXPiiSeybNky/vzzT/9+jY2NvPTSS6SmpvrDjvb8rByu4cOHo9frWbFiRbsfc/PNN1NZWcnLL78M+FaI83g83HPPPa32dbvd/s9kez4r+9I8t9RLL73Uov1g3vvmwOevPyN2u73NoW733HMPiqJwwgkn+NtOO+00dDpdi3+LFEXhhRdeICEhgbFjx+7zOcTHxzNkyBDeeOONFjVs2LCB77//3v8z1xHuuusuKisrufTSS3G73a22f//993z55ZeHfPwFCxYwYcIEzjnnnFa/F/75z38C8M477xzwOH/9LA0fPrzFUMG/ztnWHjNnzsTj8bT4rDgcDubPn8/o0aNbrU66cuVKVCrVfldQFUII0T1JTykhhOjmPv/8c+rr6zn11FPb3D5mzBiio6NZsGAB55xzDv/85z/58MMPmTVrFnPnzmX48OFUVVXx+eef88ILLzB48GDmzJnDm2++yY033siyZcuYMGECjY2NLFy4kKuuuorTTjuN0NBQZs2axdNPP41KpSIjI4Mvv/zyoOaGyc7OJiMjg5tuuomioiJCQkL46KOP2pyL5amnnmL8+PEMGzaMyy+/nLS0NHJzc/nqq69Ys2ZNi33nzJnDzJkzAdr8Et6Wk08+mbvvvpuLL76YsWPHsn79ehYsWHDI8z/pdDruvfde5s2bx5QpUzjnnHPYtWsX8+fPP6hj5uTkcO+997ZqHzp0KCeddBIXXnghL730EjU1NUyaNIlly5bxxhtvcPrpp/snvX/jjTd47rnnOOOMM8jIyKC+vp6XX36ZkJAQ/5fsSy+9lKqqKqZMmUJiYiJ5eXk8/fTTDBkypF29EzIzMxk/fjxXXnklDoeDJ554gsjISP71r3/593n22WcZP348AwcO5LLLLiM9PZ3S0lL+/PNPCgsLWbt2bbtfl7asWrWKt956q1V7RkZGiy+zffr04ZJLLmH58uXExsby2muvUVpayvz58/373HLLLbzzzjvMmDGDa6+9loiICN544w127drFRx995B+K2p6flcNlNBqZPn06Cxcu5O67727XY2bMmMGAAQN47LHH+Pvf/86kSZOYN28eDzzwAGvWrGH69OnodDq2b9/OBx98wJNPPsnMmTPb9VnZl0mTJjFp0qQWQ7uatfe9HzJkCBqNhoceeoja2loMBgNTpkzBarUydOhQZs+e7e859t133/H1119zwgkntHidExMTuf7663nkkUdwuVyMHDmSTz/9lMWLF7NgwYIDTp7/yCOPMGPGDI455hguueQSbDYbTz/9NKGhodx5553tev3b45xzzmH9+vXcd999rF69mtmzZ5OSkkJlZSXffvstixYt4u233z6kYy9dupScnByuvvrqNrcnJCQwbNgwFixYwM0337zfY/31s7S/HoG//vqr/w8V5eXlNDY2+v/9mjhxIhMnTgR8c1fNmjWLW2+9lbKyMjIzM3njjTfIzc1t1VsVfL1nx40b5x/KKoQQogfp0rX+hBBCdLhTTjlFMRqNSmNj4z73ueiiixSdTqdUVFQoiqIolZWVytVXX60kJCQoer1eSUxMVC688EL/dkVRFKvVqvznP/9R0tLSFJ1Op8TFxSkzZ85UduzY4d+nvLxcOeussxSz2ayEh4cr8+bNUzZs2KAAyvz58/37XXjhhUpQUFCbtW3atEmZNm2aYrFYlKioKOWyyy5T1q5d2+oYiqIoGzZsUM444wwlLCxMMRqNSlZWlnLbbbe1OqbD4VDCw8OV0NBQxWaztedlVOx2u/KPf/xDiY+PV0wmkzJu3Djlzz//VCZNmtRiWfPmZdg/+OCDFo9vXrL9rzU/99xzSlpammIwGJQRI0Yov/76a6tj7ktKSso+l3y/5JJLFEVRFJfLpdx1113+9ykpKUm59dZbFbvd7j/OqlWrlNmzZyvJycmKwWBQYmJilJNPPllZsWKFf58PP/xQmT59uhITE6Po9XolOTlZmTdvnlJcXLzfGvdeqv7RRx9VkpKSFIPBoEyYMEFZu3Ztq/137NihzJkzR4mLi1N0Op2SkJCgnHzyycqHH37o32f+/PkKoCxfvvyAr9HeNezrcuGFF7Z4TU866STlu+++UwYNGqQYDAYlOzu71fvZXOvMmTP9n7dRo0YpX375Zav9DvSzsvdr9FeAcscddxzwOX788ceKSqVS8vPzW7Q3P5+2vP76660+ky+99JIyfPhwxWQyKcHBwcrAgQOVf/3rX8ru3bsVRWnfZ6W57r///e+tztn889HW+9ee915RFOXll19W0tPTFY1GowDKTz/9pFRXVysXXHCBkpmZqZjNZsVgMCj9+/dX7r//fsXpdLaqw+PxKPfff7+SkpKi6PV6pX///spbb7217xf4LxYuXKiMGzdOMZlMSkhIiHLKKacomzZtarHPHXfcoQBKeXl5i/bmz++uXbvada5FixYpp512mhITE6NotVolOjpaOeWUU5TPPvvMv09bn6F9/VukKIpyzTXXKECLf6//6s4771QA/8/pwX6W2tL8mrR1+evn3GazKTfddJMSFxenGAwGZeTIkcq3337b6pg1NTWKXq9XXnnllf2eWwghRPekUpQAzMgqhBBCdCK3202vXr045ZRT2vyru+g4ubm5pKWl8cgjj3DTTTcFupwDSk1NZcCAAYc1LCoQPB4P/fr14+yzz2537z8heoInnniChx9+mB07dvS4xQ+EEELInFJCCCF6oE8//ZTy8vIWk6cL0Z1pNBruvvtunn32WRoaGgJdjhBdwuVy8dhjj/F///d/EkgJIUQPJXNKCSGE6DGWLl3KunXruOeeexg6dCiTJk0KdElCdJhzzjmnXStJCtFT6HS6VotbCCGE6Fmkp5QQQoge4/nnn+fKK68kJiaGN998M9DlCCGEEEIIIfZD5pQSQgghhBBCCCGE6Gasy5dT+epr2DduxF1eTuIzTxM8bdp+H1P7xRdUvvIqzrw81MEWLBMmEvPPm9CGh3dR1S1JTykhhBBCCCGEEEKIbsZrs2HIziL29tvatb911Sp233wLYWedRfqXX5D4xBPY16+j5PbbO7nSfZM5pYQQQgghhBBCCCG6GcvEiVgmTgSgqB3721avQZeQQMScvwGgT0wk7OxzqHzllU6scv96fCjldrtZvXo1sbGxqNXSMUwIIYQQQgghhBBHHq/XS2lpKUOHDkWr7fi4xjR0CGVPPEHDL78QNHEinspK6r/7zh9sBUKPD6VWr17NqFGjAl2GEEIIIYQQQgghxAH9+OOPDB8+3H/fYDBgMBgO+7jmYcNIeORhim64Ea/TCW43lsmTiWvn8L/O0ONDqdjYWACWLVtGfHx8gKsRQgghhBBCCCGEaK24uJhRo0YxZcqUFu133HEHd95552Ef35GTQ+l99xP196sIGj8ed1k5ZY88QvGdd9LrvvsO+/iHoseHUs1D9uLj40lMTAxwNUIIIYQQQgghhBD7tmnTJhISEvz3O6KXFEDFSy9hGjaMyEsu8TVkZaE2m8g7/wKir7sOXUxMh5znYPT4UEoIIYQQQgghhBCiuwgODiYkJKTDj6vY7KDVtGxsnntb6fDTtYvM/C2EEEIIIYQQQgjRzXgbG7Fv3ox982YAnIWF2DdvxrV7NwBljz7G7ptv9u9vmTyZ+h8WUv3OOzgLCrCuWkXpffdjHDQIXWzX95IC6SklhBBCCCGEEEII0e3YNmwk/8IL/ffLHnwIgNDTT6fXgw/gLi/HtbvYvz3szDPwNjZStWABpQ89jCY4GPOYMcTc9I8ur72ZSlGUAHXS6hqFhYUkJSVRUFAgc0oJIYQQQgghhBDiiHQ05hcyfE8IIYQQQgghhBBCdDkJpYQQQgghhBBCCCFEl5NQSgghhBBCCCGEEEJ0OQmlhBBCCCGEEEIIIUSXk1BKCCGEEEIIIYQQQnQ5CaWEEEIIIYQQQgghRJeTUEoIIYQQQgghhBBCdDkJpYQQQgghhBBCCCFEl5NQSgghhBBCCCGEEEJ0OQmlhBBCCCGEEEIIIUSXk1BKCCGEEEIIIYQQQnQ5CaWEEEIIIYQQQgghRJeTUEoIIYQQQgghhBBCdDkJpYQQQgghhBBCCCFEl5NQSgghhBBCCCGEEEJ0OW2gCxBCCCGEEEIIIcTRxWu346muxmu3ozidKHY7XrsDxWH3tTkcvuvmNocDxe7A69irze7wPc7hu1abzSS/9mqgn5o4CBJKHeGsK1ZQ8dzz6BISiL/n7kCXI4QQQgghhBBCtIuiKLjLynHu2olz1y4cO3fh3LUL586duIqLQVE69HzqkJAOPZ7ofBJKHeEUl4vGP/5An5oa6FKEEEIIIYQQQohWvA4Hztw8X+C0ayeOXbtwNgVQ3sbGfT9Qq0VtNKIyGFAbDKiMRlRGA2rD3tdG/za10YDKYERl0Dc9bq82owG12dx1T1p0CAmljnD6lBQAnEVFKG43Kq28ZUIIIYQQQghxNPM6nXiqa/DU7OfSNDSuRaBjNPlDHLXJuCfMaW43Gn1hz97XBgMqkwm1wYDXat3T22mv8MlVVLTvXk9qNbqkRAxp6ejT0tCnp2FIS0Ofno4mPByVStW1L544okjCcYTTxsWh0utRnE5cxcXok5ICXZIQQgghhBBCiA6geDx46+vx1Nb6LvsJmdz+27UoVmugS29FHRzcFDi1DJ90ycmo9fpAlyeOUBJKHeFUajW65CScOTtw5uZJKCWEEEIIIYQQRxh/uFRTsydgqq319Wba+75/ew3emlo8dXWHPq+SRoMmNBRNWNg+LqGoTWYUpwOvzb5nAnH7XhOEN9932FFseyYM39PuQLHZUJxO3znVanSJiejTUv3hkyE9DX1aGprISOn1JA6ahFLdgD4l1RdK5eXBhPGBLkcIIYQQQgghehyv04m3rg5PXT3eulo89fV46ur8bZ66Wrx19Xjqm7bX+bZ7amvxHk64BKjNZjRhYahDQ9GEtQyatOHhbYZOaosFlVrdga/AvileL4rDARqN9HoSHUpCqW7AP69Ufl6AKxFCCCGEEEKIzqN4vXitNrzWRhSrFa/ViuJ0orjdvovLjeJ2gcez1/2mtr3ve9wt7zfto7hceBsa9wqY6vDW1uGpr0ex2w+7fnVQEJrQUNRhoXt6MYWGogkN26tX01+2hYSgOsKDHpVajcpkCnQZogeSUKob0CcnowkLQ6XWBLoUIYQQQgghhGhBURS8DQ14KitxV1b6Ap6mQMl/abTibWxs2ebftqddsdkC+2RUKtTBwWiCg1GHhKAJCUETEow62HdbHRKMJiS0qS3Yt70bhUtCHGkklOoGws6eRfi55wS6DCGEEEIIIcRRQvF48NTW4q6oaAqbqvBUVuCuqMRdVYmnwhdANd/2zznUUdRq1GYzarMZlV6PSqtFpdOCRuu73XRBp0Wl1e25r9W0uK/SaUHbch9fmNQcKjUFTE0BlDooCJVGOgMI0VUklOoGumqcsBBCCCGEEKJnUDwevDabr4eS1dcTqc3eS1arb2W3ykpf6FRZ5btdVQVe70GdUx0UhCYy0hfuNAVKarMZdZAZtTmo6dqMau9t/vY929VmMyqDQSbNFuIoIKGUEEIIIYQQQhxhvE4nnqrmgKgaT3UV7qoqPJVVvnmQmoe77RUuea1WXxBltXbI/EiAb2haVCTayCi0kRFoIqPQRkaiiYzwtUVFoomIRBsZgVrmHBJCHCQJpbqJkrvvpuG334m743Ys48YFuhwhhBBCCCF6LMXrBZWqQ3vqeB2OppCpCk91le92VTWeqkpf2FRV3dTm2+ZtbOyYE2s0qIOCWvZcMptRm0yog3y9ljQhoWgjI/cETFGRaCIj0YaHo9LpOqYOIYRog4RS3YS7vBxXfj7OnbtAQikhhBBCCCEOm+L14szLw7F1K/YtW3Bs3oJ961bcJSUtd1SpfBe12hdW7a+t6f7ebYrTiddqPfgCtVq04eFoIiLQRISjjYj03W6a+2jP0LjWF5XZ7JsfSaeTYXBCiCOWhFLdhD4lBQBnfn6AKxFCCCGEEKL78TQ04ti2DcfWLdi3bMW+ZTOObdvbt9qbovguTXMsKW3t0p4idDp/yKSNiNgrbIpo2RYejjYyEnVwsARKQogeTUKpbkKXnAyAMy83sIUIIYQQQghxBFMUBffu3dibez9t2Yp96xZceW3/cVdlMGDo0wdjdhaGrGyMfbN9fxDWaPYEUYqCoii+5Enx7gmpFAWlzTalxX2VVosmMhK1xSIhkxBC7EVCqW5Cn5IKgDMvL7CFCCGEEEII0cUUt7tpAm8bit3mv+21+Sb09lRXY9+6DccW3/A7b11dm8fRxsRgyM7CmJXtu+7bF31KCiqNpoufkRBCCJBQqtvQp/qG77kKi1BcLplwUAghhBBCdCuKx+Obv2nLFhw7duJtaPCFS3Ybij9karrffNvm26a4XAd3Mq0WQ0bGnt5P2VkYsrPRRkR0zpMTQghxSCSU6ia00dGojEYUux1XURH61NRAlySEEEIIIUSbvI2Nvp5LW7dg37wF+9YtOLZuQ7HbD+/AajVqkwmV2YTaaPKtIGcyoQ4OxpCRgSHbF0DpMzJQ6/Ud82SEEEJ0GgmlugmVWo1pwAC8Dgfe9kzGKIQQQgghRCdTFAV3aSn2zZt9K9ht3oJ9y2Zc+QW++ZT+QmU0Ysjqg7FPHzShoahMJtQmM2qzCZXR6L+tNplQGU3+22qTCZXJhEqvlzmZhBCiB5FQqhtJeet/gS5BCCGEEEIcpRSnE8euXb4AarNv7ibH5s14amvb3N8/f1N236bhc33RpyTL/E1CCCH8JJQSQgghhBBCtKIoCvZNm2hYtIiGn3/Bvn07tDW3k0aDIT29aehc0wTi2dloIyO7vmghhBDdioRS3ZCiKNJtWQghhBBCdDjF7ca6YiX1CxdSv2gR7uLiFtvVFktT8JSNsW82hqxsDL0zURsMAapYCCFEdyahVDdi37aNomuvA42GjK++DHQ5QgghhBCiB/BarTT8/jsNCxfR8PPPLYbjqUwmLOPHY5k6BfOIEegSEuSPo0IIITqMhFLdiCY0DGduLmg0KC4XKp0u0CUJIYQQQohuyF1dTcNPP1O/aBGNv//eYlU8TVgYlilTCJ42jaCxx6A2GgNYqRBCiJ5MQqluRBsTjcpkQrHZcBYWYkhLC3RJQgghhBBHDcXlwlNTg7u6Gk91DbrYGPSpqYEuq92chUU0LFpI/cJFWFeuBK/Xv02XkEDwtGkET5uKaehQVFr5miCEEKLzyW+bbkSlUqFPTsaxdSvOvDwJpYQQQgghDpHidOKuqcFTXYOnuhpPTQ2emmr/bXdz217bvQ0NrY5jGjaMsFmzCDnheNQmUwCeyb4pioJj61bqFy6iftEiHJs3t9hu6NuX4KlTCZ42FUNWlgzLE0II0eUklOpm9CkpOLZuxZWXF+hShBBCCCGOWIqi4C4uxr5lK46tW7Bv3YarsHBPwNTYeGgHVqvRhIaiCQnBWViIbdUqbKtWUXr//YSecgphZ8/CmJ3dsU/mIChuN9ZVq2hY9CP1ixbhKixsUbt5+HCCj5uGZcpU9IkJAatTCCGEAAmluh19SgoATgmlhBBCCCEA8NpsOLZvx751K44tW3Fs3Yp92za8dXX7f6BajSYszHcJD0cT7rutDQ9HExbeZrs6JASVWg2Aq7SM2k8+puaDD3EVFVH99ttUv/02xoEDCZs1k5ATT0JjCer85988UfmiH30TldfU+LepDAaCxo8neOpULJOPRRse3un1CCGEEO0loVQ3o09tDqXyA1yJEEIIIURLiqJ06hCwFr2ftm1t6gXlm9Zg7/mR/LRaDBkZGLL6YMzKRp+WiiY8vCl0CmsRMB0KXWwMUVdcQeTll9P455/UfPAh9YsWYV+/npL16yl78CFCTjrJ13tqwIAOfW3clZU0/PQT9Yt+pPGPP1AcDv82TWgolmOPxTJ1Cpbx41GbzR12XiGEEKIjSSjVzRgyMjD264c+Iz3QpQghhBDiKKS4XLiKinDk5uLMzcW5q+k6Nxd3WRkqoxG1yeS7mE2oTOam275rldmEeu82swmVqanNbPK3q0wmFLvd1/tp6zYcW7bst/eTJjISY1YWhqwsjNm+a0N6Oiq9vtNfE5VajWXcOCzjxuGurKT200+pef8DnHl51HzwATUffIAhO5uws2cResopaIKDD+k8ztxc6hcton7Rj9hWrwZF8W/TJSYSPHUKlqlTMQ8bJhOVCyGE6BZUirLXb7MeqLCwkKSkJAoKCkhMTAx0OUIIIYQQRzxFUXCXl/vDpr2DJ2dBAbjdgStOq8WQno4hO6sphMrGmJ2FNioqcDW1QVEUrMuX+3pPffcditMJgMpoJOSEEwg7e5Zvlbv99J5SvF7s69f7Jir/8UecO3a02G7s3x/L1CkET52KoU8fmahcCCG6uaMxv5BQSgghhBDiKOVpaMCZm9cUPO3aEzzl5u53InCV0Yg+NdV3SUvF0HRbGxeP4nLitVpRrFa8NpvvYrXhtVlRbDa8VmvT/aa25ttN+yu2PdvRqDH27o0hK9s3BC87G316Ouou6P3UkTw1NdR+/jk1H3yAY3uOv12fmUH4rFmEnHqqf64nr9OJdckS6hcuouGnn3CXl+85kFZL0KiRWKZOJXjKFHTx8V39VIQQQnSig80vrMuXU/nqa9g3bsRdXk7iM08TPG3afh/jdTqpePY5ar/4HE95BdroaKL+fhVhZ53VUU/joEi/3iOcx6tQVG2j0emmb3yIv13xeFA8nm73P2VCCCGE6FiKouBtbMRbW4tn70vN3vdr8NTW4q1puc/e8xC1olajS0xEn5qCIS1tTwiVmoo2Nvaw5mI62mjCwoiYM4fwv/0N2+o11HzwAXXffIMzZwelDzxI2aOPEXzccSgeD42//orXavU/Vh0URNDECQRPnYZl4gQ0ISH7OZMQQoijiddmw5CdRehZZ1J0zbXtekzR9Tfgrqyg1733oktOwV1e1mI4eFeTUOoI9/X6Yq55ZzXDksP4+KpxAJTcfz81775H9I03EHnRRYEtUAghhBCdRnG7cRUW4tixA0fODpy5uXiqqlqGT3V1hzWcThMV1Tp4SktDn5jYJfMxHU1UKhXmYUMxDxtK7L9vpe7LL6l+/wMcmzdT99VX/v20MTFYpkwmeOpUzKNHyx8hhRBCtMkycSKWiRMBKGrH/g2LF2NdvpzMH75HExYGgD4xofMKbAcJpY5wmTEWAHLKGvwr2qiNJhSnE1e+rMAnhBBC9ASK04kzL29P+LSz6XrXLhSXq13HUOn1aMLC0ISGogkNRR0W2nR7T5vG39Z8Pwx1UFAnPzvRFk1wMOGzZxN27rnYN2yk7ssvUZmMBE+Z4lupT3qiCSHEUau+vp66vRb2MBgMGAyGwz/ujz9iHNCfyldfpfazz1GbTFimTCH6umtRG42HffxDIaHUES4tKgi1CursbsrrHcSEGNGnpADgzM0LcHVCCCGEOBhemw3nrl2+8GnHDpzNIVR+Png8bT5GZTCgz0jHkJGJIT0NTVTUnrBpr5BJZTTKRNfdkEqlwjRwAKaBAwJdihBCiCNEv379Wty/4447uPPOOw/7uK6CQmwrV6HWG0h85mk81dWU3HU3npoaej1w/2Ef/1BIKHWEM+o0JEWYyau0klPW4AulUptCqTwJpYQQQogjjeL14i4vx5WfjzO/AMfOHThzduDYuRNXYeE+521QBwWhz8zAkJ6BITMDfUYGhowMdL16odJouvhZCCGEECJQNm3aRELCnmF1HdFLCgCvF1Qqev33ETTBwQDE3HIzRdddT9wdtwekt5SEUt1AZrTFF0qVNzA2M8rfU8pVXIzX6ZR5BoQQQogupjiduHbvxllQgDM/3x9AOQvycRUU7ncCcU1oKPrMTAwZTeFTUwiljY2Vnk5CCCGEIDg4mJBOWNhCGx2NNjbWH0gBGDIyQFFwl5SgT03t8HMesKYuP6M4aJmxFhZtKSOnrAEATWQkarMZr9WKq7AQQ3p6gCsUQggheh5PQyOuAl/Y1HztLMjHlV+Aq7jY99fGfVGr0fXqhT45CX1a+p7hd5kZaCIiJHwSQgghRJczDRtG3Xff4W1s9M8p6czNBbUabVxcQGoKaCjV4HDz6Pdb+X5jKRUNDvr3CuGOU/ozOCkM8C1x/PgP23hneQF1NhcjUsO59/SBpEUdXRNyZkbvmewcfHMP6FJTcGzajDM3T0IpIYQQ4hB4rVZcxcW4du/GVbTbd717N66CApwFBXiqqvb7eJXRiD4pCV1yctN1EvqkZPTJSb4hdzpdFz0TIYQQQhyNvI2NvnkpmzgLC7Fv3owmNBRdr16UPfoY7rJSej30EAChJ59ExfPPs/vf/yH6mqvxVFdT9vAjhJ115tE50fnNH61jW0k9j509mNgQI5+sLuKCV5byw42TiAs18sIvO5n/Ry6PzhpMUoSZR7/fxpzXlvLDDZMw6o6euRWGpYRz9eRMBiaG+tss48ahT0pGE9rxXfqEEEKI7k5RFDw1NU1hU5E/cHIXF/sDKE9NzQGPowkPbxk2+a+T0EZHS48nIYQQQgSMbcNG8i+80H+/7MGm8On00+n14AO+OS53F/u3q4OCSH7tVUrvvZddM2ehCQsj5IQTiL7+ui6vvZlKUfYx22Yns7s89L/jO16eM5wp2bH+9pOfXsyxfWL4x/Q+jLp/EZdNSOPyiRkA1NldjLh3If+dNZhTB/dq13kKCwtJSkqioKCAxMTETnkuQgghhOhaiqL4/keroABXURGu3cV7ejrt3o2ruBjFZjvgcdQWC7pevfa6xKNLTPIHT3vPuSCEEEII0ZmOxvwiYD2l3F4Fj1fBoG3Z48mo1bA8t4qCKhvl9Q7GZUb5t4UYdQxJCmNVXnW7QykhhBBCdE+Ky4WruLj1nE55+TgLC9sVOmmio1qGTvFN1wm+awmdhBBCCCECJ2ChlMWgZVhyGE8t2k5mjIUoi4HP1xaxKr+a1MggyhvsAERbWi59GG0xUN6w7xVtHA4Hjr1WvKmvr++cJ9DFyusdbC6uIy7USJ9Y3/9A+5acrkAXGxPg6oQQQohD47Va91rBbs9E4s6CAly7d4PHs+8Hq9Xo4uLQJSbuCZ0S9gRQ2rg41B21hLIQQgghhOhwAZ1T6vFzhvDPD9cx+v5FaNQqBvQK4dTBvVhfVHvIx3zggQe46667OrDKI8OzP+Xw+h+5XD4xnX+f2BdPbS3bJx2L4nCQtWa1/E+3EEKII47i9eKprsZdWoqrtBR3aRnuslJcRbv9QZSnomK/x1AZDOiSEtuc00mfkIBKr++iZyOEEEIIITpaQEOplMgg3p93DFanmwa7m5gQI39/exXJEWaiLb6Z38sbHMSE7JkFvrzBQb/4fU/ufeutt3LjjTf67xcVFdGvX7/OexJdJCOm5Qp86pAQVFotit2Oq6AAQ2ZmIMsTQghxlPHa7X8Jm5oCp9Iy3KWlvm3l5eByHfBYmtDQtlewS072TSauVnfBMxJCCCGEEF0toKFUM7Nei1mvpdbq4tdt5dw6oy9JESaigw38kVNJ/16+Vefq7S7WFNRwwZiUfR7LYDBg2KvXUF1dXafX3xUyo1uGUiqVCn1yMvZNm3Dm5UkoJYQQosO5iouxrlqFc8eOPeFTaSmusjK8te3s1axSoYmMRBcTgzY2Fm1sDLr4Xi16PWlCZCVZIYQQQoijUUBDqV+2laMoChnRFnIrG7n/6y1kRFuYNSIRlUrF3HFpPP3jdlKjgkiKMPHo99uIDTEwvV/sgQ/ew2Q29ZQqqLZid3kw6jToU1OaQqn8AFcnhBCiu1M8HhzbtmFdtQrbqtVYV63CXVy838eojEZfyBQTuydwio1FG7PX7ehoVDpdFz0LIYQQQiiKQlWjk/wqK40OD0kRJhLCTGg10vNYHHkCGkrV2108/O1WSmrthJp1zBgQx03HZ6Fr+mG5YlI6NqebWz9eT53dxcjUcN64eBRGneYAR+55oix6wsw6aqwudpY30q9XCLoUX48xZ15egKsTQgjR3XgbG7GtW4d15Spsq1ZhW7sWb2Njy53UaozZ2RgHDEAXH+cLm2Ji/IGTOiQElUoVmCcghBBCHMWsTjcFVTYKqqwUVFvJr7K2uG91tlwoRKNWkRhuIjnCTGpkECmRZlKarpMjzD3iO7bL46XO5iLSIvMtdycBDaVOHtSLkwf12ud2lUrFjdOzuHF6VhdWdWRSqVRkRltYkVdNTnkD/XqFoE+WUEoIIUT7uEpKsK1ahXXVamyrVmHfurXVynbqoCBMgwdjGj4M87BhmAYNQh0UFKCKhRBCiKOX2+OluNbeOnSqtlJQZaWiwbnfx6tUEBdixKzXUFhtw+H2kldpJa/SyuLtrRcZiQsxNgVVe8Kq1MggkiPNhBgD2+PZ4fZQXu+grN5BWZ2Dsnq7/7q0ztdeXm+nstFJr1ATv98yJaD1ioNzRMwpJdonM6YplGqaV0ovPaWEEEK0QfF4cGzfjnXlSt9QvNWrcO9uPRRP2yse89BhmIYNxTxsGIY+fVBpuv9fSoUQQojuxup088GKQn7YVEpeVSO7a+x4vMp+HxNi1JIcaSYp3NfbKTHCd50UbiIh3IRB6/ud7vUqlNU7yK1sJL/SSm5lI3lVVvIqG8mrtFJvd1NSZ6ekzs7SXVWtzhNu1vmDqtgQI3qNGp1GjU6rQq9Ro9c23deo0WlUe23/y32NGr1WhV6jQadVodOosTk9lNbZmwInO6VtBE/V1gMvmtKsqtGJoijSk7sbkVCqGzlzWCLDUsIZnhIOgD4tleDjpqFPTZMfPCGEOEopHg/OvDzsGzdh39R02bgRb0NDyx3VagzZWZiHDsM8fBimYcPQxcUFpmghhDiK1Fpd2N0eYvdaUVyIZpUNDt74M4///ZnbKnzRa9QkhptIijCTFGFqCpzMvvvhZkLN7evBpFariAs1EhdqZEx6ZIttiqJQY3X5AqsqK7kVVvKqGv29qioaHFRbXVRba1hTUNNRT/ug6TVqooMNxIQYiA02EhNiICbYQEyI0XcdbCQ2xEC4WS/fi7sZCaW6kVFpEYxKi/Df14aHk/j00wGsSAghRFdS3G4cO3b6gyf7pk3Yt2xBsVpb7as2mzENGYJp2DDMw4ZiHDQYjUWG4gkhRFcor3fw/aYSvt1Qwp87KgF47vxhTO8vfwwQPrkVjbzy204+WFGIw+0FIDnCzJxjUhiUGEZShInYYCNqdecGLCqVivAgPeFBeoYmh7fa3uBwk19pJb+qkdxKK5UNDlweBZfH23RRcHq8ON3ePW1uX1uLfdyt7zs9XgxaNbHNwVKIL1xqvo5tvh9sIMysk7Cph5JQSgghhDgCeZ1OHNu2Y9/UFD5t2oxj61YUh6PVviqj0Tcheb9+GPv3w9ivnwzFE0KILlZca+PbDSV8s6GE5blVKH8ZeXX126t57aKRjO8dFZgC29DocHP7ZxuptbkYlhLGsORwBieGYdLL74/Osqaghpd+3cG3G0poHp03KDGUyyemc0L/uCNuhTyLQUu/XiH06xXS4cdWmn5IJGw6ukko1c2syK1ic0k9x/ePJSbYiKIouMvLQVHQxcYGujwhhBCHwGu1Yt+6dc/wu02bcWzfDm53q33VQUG+8GmvAEqfliYBlBBCBEB+pZVvNhTzzYaSVkObBiWGcsKAOKb3i+WR77by3cZSLntzBW9dOto/HUcgNTjczJ2/nGW5vjmEFm4uBUCrVtGvVwjDksP9U4f0CjVKcHAYvF6Fn7eV8eIvO1vM2XRsVjTzJmYwJj3iqHx9j8bnLFqTUKqbuePzjWzcXUdssIHp/eOoePY5Kp55hrBZs4i/5+5AlyeEEGI/FKcTx65cHDnbceTk4Ni+Hef2HJwFBeD1ttpfExqKsX9/f/hk7NcPXVISKvWR9VdUIYQ4muSU1fPNel+PqE3Fdf52lQqGJ4dzwoA4ThgQR2K42b/tqdlDufSNFSzeXsHF85fxzuVj6N8rNBDlA1Bvd3Hx/OWsyKsm2KDlsonpbCmpY2VeNaV1DtYV1rKusJbX/8gFfCuzNfekGp4STv9eoei18rvoQJxuL5+v3c1Lv+5gW6lvrketWsWpQ3px+cR0suM6vveREN2NhFLdTGaMhY2768gpb2A6oE9KBGQFPiGEOJIobjfO/Hwc2/aET46cHN+/1W30fgLQREdh6tcygNLGx8tfEYUQIsAURWFTcZ1/aF7zStgAahWMSY9kxoA4ju8fR8w+JjM3aDW8+LfhzHl1GSvyqpnz6jLev+IYMqItXfU0/OrtLi58bRmr8msINmr53yWjGZIUBvie6+5aOyvzqlmVV83KvGo2FddRUmfn6/UlfL2+BAC9Vs2ghFCGp/h6Uw1LDic62NDlz6W97C4PO8sb2VnRQGG1jSiLgbQoM2lRFsI7Ya6ieruLd5bl89pvuZTU2QHfMLjZo5K4eFwavcJMHXo+IbozCaW6mcymX1zNvwz1KSkAOPPzA1aTEEIcrRSPB1dhoT90cmxv6v20axeKq+3li9UWC4bMTAy9e2Ponem/rY2O7uLqhRBC7IuiKKwpqOHbDSV8u7GEvMo9C0roNCrGZkQxY0Acx/WLJdLSvjDGrNfy6kUjOe/lJWzcXccFryzlgyuOadGjqrPVNQVSq/NrCDFqeevS0QxKDPNvV6lUJISZSAgzcergXgBYnW7WFdayMq+a1fm+oKra6mJFXjUr8qr9j02OMPtCquQwMmIsxAQbiA42EmLUdskfWBRFoazewY6yBnZUNLKjrIGdTde7a22t5vhqFmLUkhZtIS3SF1KlRplJb7oONrZvdbtmpXV2Xvt9F28vyafe4fsjVEywgYvHpXHe6GRCTQd3PCGOBhJKdTOZMb5QakdTKKVrCqXcJSV4bTbUJkndhRDicCmKgmK14q6uxlNVhbuqCk9VNZ7qKtyVVbjLy3Hu2IFjx442Jx4HUJnNGDIyfOFTZqYvgOrdG21srPR+EkKIAPB6FertbqqtTmpsLmqsTmqsTdc2V4vb20rq2V1r9z/WoFUzsU80MwbEMbVv7CGHC6EmHW/OHcXZL/7JjvJGLnhlKe9fcQwxwW33sOpItTYXc15bxtqCGkJNOhZcOpoBCQceQmjWaxmTHsmY9EjA9ztyV0Ujq/Jr/D2qtpXVk19lJb/Kyieri1o8Xq9VE23xrawWbTEQHexbUS06uPm27zrKYmjXkEC7y0NuZSM7yhrZWd7AjnJf+LSzvJEGR9u9kcH32mdEB5EUYaa83kFuRSO7a+3U2d2sLahh7V/mBAP26lEVRGpUEOlN16mRQRh1e+Zy3FZaz0u/7uSzNUW4PL70KzPGwuUT0zltSC8MWpn3UYh9kVCqm+kd2xRKlTeiKAqasDDUISF46+pw5hdgzOoT4AqFEOLIoygK3vr6poCpKVxqDpqqqnBX733bd72vsOmvVAYD+ox0jL17o89s7vnUB12veJn7SQghOpnXq7CjvIFNxXVUN7YOl/a+XWtz7bO3TFvMeg2Ts2OYMSCOyVkxBBk65qtTpMXAgkvHMPOFP8ittPK3V5bx3rwxhJn1HXL8ttRaXfzttaWsK6wl3KzjrUtHH/KcViqVivRoC+nRFmYO900lUmd3saYppFpdUENhtZXyegf1djdOt5eiGhtFNbYDHjvcrNsrrPIFVxFBesrqHE3hk2/43b7eR41aRXKEmfSoIDJiLC2uI4L0rf4oZHN6yKtqZFd5I7sqfde5lY3sqmikosFJRYODigYHy3OrW52rV6iRtOggVKj4LafC3z4qNYJ5k9KZnBWDWi1/hBLiQCSU6mZSIoPQqlU0ONyU1NmJDzWhT0nBvn49zvw8CaWEEKKJp6aG+p9/pmHRIhp+/wPFaj3wg/5CZTCgiYxAGx6BJiICbUQ4mvAINJERGNLSMPTujS4xUVa+E0KILuJwe1hfWMvy3GpW5lWxIq+aGmvbw6X3JUivIcysJ9SkIzxIR5hJT6hZR5hJR5hZR5hZT2yIkdFpES16w3SkuFAjCy4dzawX/mRraT0Xzl/OgktHY+mg4GtvNVYnF7y6lA1FdUQE6Vlw6Wj6xnfsBNshRh0T+0QzsU/Loeh2l4fyegdl9Q7K6x2UNzgor7P7rvdur3fg9ipUW11UW13+ScH3fT5tU9hkISMmiPQoC5kxQSRHBB3UBOwmvYbsuJA2Jxyvs7vIrfAFVLsqGn23K63sKm+gzu5md63d35tOpYLj+8Vx+aR0hiUHfmVFIboTCaW6GZ1GTUqkmR3ljeSUNbQIpVwy2bkQ4ijnKimhfuEi6hctxLpsOXg8LbarzGa04eFoIiN91xERaCLC0UZE+MKm5tsREWjDw1GZzTLUTgghAqjG6mRlXrU/hFpbWIvT3XK1UqNOzcCEUGKCjU2h0p6gKdysb7qvawqe9EfMqnEpkUG8deloznnxT9YW1HDpG8t5/eJRHRqEVTc6Of+VpWwqriMySM/bl40hKy64w45/IEadhqQIM0kR+583y+tVqLW59gqv7JTV+W5XNjqJDNK36PkU2Uavp44WYtQxKDGsxZxb4Ot9XW11sauigV0VVqoaHRzXL460qKBOrUeInkpCqW7ojlP6Y9Rp6NfLl+hbJh+LNjoa46BBgS1MCCG6mKIoOHfupP6HhdQvXIh9w4YW2w19+hA8bSqWqVMxZGSgNnb+nB1CCCEOjaIoFFTZWJFXxfLcalbkVrG9rHWPmSiLnhEpEYxIDWdEagT9e4Wg0xwZQdPB6hMbzBtzR3Hey0tZsrOKqxas4sW/De+Q51PZ4OD8V5aypaSeKIsvkOoT23WB1MFQq1WEB+kJD9J3aWh2KFQqFRFBeiKCIhieEhHocoTo9lSKcjAjq7ufwsJCkpKSKCgoIDExMdDlCCGEOEyK14t93TrqFy2i/oeFOHNz92xUqTANHUrwtGkET53iX6FUCCHEkcft8bK5uJ4VeVWsyK1meW4VZfWt5/NLjw5iZEoEw1PDGZkaQWpkz+vFunRnJXNeW4bD7eXkQfE8ee5QNIcxH1FFg4PzX17K1tJ6ooMNvHPZaDJjjuywRwhxdOYX0lNKCCHEEU9xOmlctpz6RQtpWPQj7rIy/zaVTof5mDG+IGryZLTR0fs5khDiSOd0e1mRV8XPW8upt7v4x/QsoiyGQJclOkhxrY1vN5SwaHMZq/KrsTpbDrPWaVQMSAhlZGoEw1PCGZESTuRR8P6PTo/kxb8N57I3V/DlumIsBi0PnDnwkMK38noH57+yhG2lDcQEG3jn8jFkRFs6oWohhDh8Ekp1Q1anmy/W7qaw2sY/pmcB4K6owJmXh3HgQNT6zlu5Qwghuoq3sZGGxb9Rv3AhDb/8gre+3r9NHRSEZdIkgqdNJWjiRDQW+Z9tIbqz0jo7P28t46ct5fyWU9FiWfdft1Xw8pwR/mkLRPeTX2nlmw3FfLOhhDUFNS22BRu1DE8J94dQgxPDMOmPzsUjjs2K4clzh3L126t4d3kBFoOW/5zU96CCqbJ6O+e9vJScsgZiQwy8c9kY0iWQEkIcwSSU6qZu/mg9AHPHpREepGfHSSfjra0l7bNPMWZlBbg6IYRoH8XpxFVWhmv3btwlJbiKS3AV78aVX4B1xQoUp9O/ryYqiuApUwieNhXzmDESwAvRjbk9XtYU1PBTUxC1qbiuxfbIID2T+kSzuqCGXRWNnPX8Hzx+zmBOGBAfoIrFwcopq+eb9SV8s6GkxfurUsHw5HBOGBDHuMwo+sQGH9YwtZ7mxIHxPHjWIP714Tpe+W0XwUYd103r3a7HltXZmf3yEnaUNxIXYuSdy8fI5NtCiCOehFLdkFmvJSHMRFGNjZzyBkYGRfhW4Fu3DmdunoRSQogjguL14q6o8IVNu4txlRTjLi7BVVyMq8QXPnkqKmE/UxvqkpN9w/KmTcM0eBAqzdH513MheoKKBge/bivnp63l/LqtnFqby79NpYJBiWFMzopmclYMAxNCUatV1FpdXP3OKhZvr+CKt1Zxw7Q+XDMlE7WEGEccRVHYVFzHtxt8QVTOXhOUa9QqRqdFMGNAHMf3jyMmRBad2J+zRyTR6HBz1xebeHzhNixGLZeMT9vvY0pq7Zz38hJ2VjTSK9QXSKVESiAlhDjySSjVTWXEWHyhVFkDI1P3CqXy8wJdmhDiKKIoCq68PKwrV+HMy/MFT7ubQqfSUnC5DngMlV6PNj4OXVw8uvh4/23TkCEY+vTucZPZCnG08HoV1hXV8tOWMn7eVs66wpoWGXSoScfEPtFMzopmYp/oNueNCjXrmH/RSO77ejPzf8/l8YXb2Fpax39nDcasl/+NDTRFUVhTUMO3G0r4dmMJeZVW/zadRsW4zChmDIjjuH5xRARJ79aDcfG4NBrsbh79YRv3fLmJYIOWs0cmtblvca2N2S8tIbfSSkKYiXcuG0NypLmLKxZCiEMjv827qcxoC79uK/f/Fap5hSlnnoRSQojOo3i9OLZtw7piJdYVK7CuXIGnvGLfD1Cr0cbEoIuLQ9crHm1cfMvb8XFoIiIkeBKih6ixOvl1ewU/bynjl23lVDY6W2zvFx/C5Gxfb6ghSWFo27HsvVaj5o5T+pMdF8z/fbqBr9eXkFth5eULR5AQZuqsp7JfHq/C1+uLKa93kB0fTL/4EMLMR07o4nR7ya9qRFHAbNASpNdg1mvRaw/8eh+Ix6uwMq+abzYU892GEnbX2v3bDFo1k/pEM2NgHFOyYwk16Q77fEezq6dkUu9w89KvO7nl43WYDRpOHtSrxT67a2zMfnkJeZVWEsN9gVRShARSQojuQ0Kpbqp3rG/Cwj2hVDIArlwJpYQQHUdxOrFt3Iht5Uqsy1dgXb0ab13LuV9UOh3GwYMw9snaEzb18oVP2pgYVFr5VSNET1VWZ2d5bjUr8qpYkVvNxt21ePfqDWUxaJnQO4pjs6KZ1CeGuNBDH7Z1zshk0qMtXPG/lWwqruO0Z37jhQuGMyI1ogOeSfst3l7OfV9tZktJfYv2hDATfZsCqr7xIfTrFUJSuLlThxq6PV7yqqxsK6lnW2kD20rr2VZaz66KRtze1kOjdRoVQQYtQXotZr2mRWAVZNA0bdtzf+9rgF+3lfPdxlIqGhz+YwbpNUzOjmHGgHiOzYomyCD/5ncUlUrFrTOyqbe7eWdZPte/u4YgvZbJ2TEAFFZbmf3yEgqqbCRF+AKpxHAJpIQQ3Yv81uimMmP+GkpJTykhxOHzWq3Y1q7194SyrV2LYre32EdtNmMaNgzziOGYR4zwrfpp6PnLdQtxtPN6FXaUN7QIofKrrK326xNrYXJWDMdmxTA8JbxDeuc0G5kawWdXj+OyN1eyubiO2S8v4b4zBnL2iLaHNXWk7aX13P/1Zn7aWg74hh+OTA1na2k9BVU2imp8l4Wby/yPsRi0ZMcF069XU1AVH0JWXDBG3cHNj+f1KhRW29hWWs/W0nq2l9aztbSBHeUNON3eNh8TpNeg16ppdHr8+7g8CjVWFzXWAw+t3p8Qo5Zp/WKZMSCeCb2jDvr5iPZTqVTce/oArE43n63ZzRVvreSNuaNICDMx++UlFFbbSIk0885lY+gVoJ6DQghxOCSU6qYym5Z2LaqxYXW6MTSFUu7ycryNjaiDZGJDIcSBeWprsa5a5RuKt2IF9o2bwO1usY8mLAxTUwBlHjESY3aW9H4S4ijgcHtYX1jrC6Fyq1iZX90qzFCpIDsuhJGp4QxPCWdkakSnfzFODDfz4RXH8I/31/LtxhL+9eE6tpbUc+uM7HYNBzxYlQ0OHl+4jXeWFeDxKmjVKuYck8q1UzP9Q/bq7C62FNezaXctm4rr2FzsC48aHG5W5FWzIq/afzy1CtKjLfRr6k3VHFZFBxtQFIWSOjtbS+qbej35ej9tL23A5vK0WZ9Rp6ZPbDC9Y4LJirPQOzaYrNhg4kON/qHRLo8Xq9OD1emm0eGm0eGh0enG2nzt9PjbrU53m9vsLi+Dk0I5YUA8x6RHdmjYKPZPo1bx31mDaXS4Wbi5jEteX06oScfuWjtpUUG8fdlo4kMlkBJCdE8qRdnPskc9QGFhIUlJSRQUFJCYmBjocjrUnzsqSY8OIibYgEqlouzRx9DGxxF22mkSSgkh2qR4vdhWr6b++x9oXLIEx7ZtrVa/08bFNQVQIzCPGI4+PR2VWr58CNHT1VidrMyr9odQ64pqW/XCMerUDEkKY2RqBCNSIxiaHEaIMTDzBnm9Ck8u2s6Ti7YDMLFPNE/PHtph8xjZXR5e/yOXZ3/Mod7hC+uP7x/LLTP6khZ14P/Pcnu87KxoZNPuuqagqo5Nu+tazbPVLMpiwOHy+M/1V3qNmvToILLigukT67tkxQaTGG6S1QiPEnaXh7mvL+ePHZUApEcF8c7lY4iV1QyF6DF6cn6xLxJKCSFED6e43VhXrKT++++p/+EH3OXlLbbrU1MxjxyBafhwzCNGokvoJROPC9HDeL0KVpeHeruLBrubeoebBrubsnoHK/N8IdT2pikB9hZl0ft7QI1IjaB/rxB0ndAb6XB8vb6Yf7y/FpvLQ3pUEC9fOIKMph7lh0JRFL5cV8xD326hsNoGwICEEP7vpH6MSY88rFoVRaG83sHGpoBqc7EvsNpV0ej/+4BGrSItKois2GB6x1qaroNJjTR3Sk8w0b00Otxc9+4a6uwunpk9lBgJpIToUY7G/EJCKSGE6IEUl4vGpct8QdTChXiqqvzb1MHBBE+ZjGXyZMwjRqCNigpgpUKI9vJ4FTYX+3raNNjdNDhc1NvdNDjcvuvm2w43DfY92xrsbhqc7r92imxTenQQI1LCGZEawcjUCFIjzd0ipN64u5bL3ljB7lo7wUYtz5w3jEl9og/6OKvyq7n3y02syq8BIC7EyD+Pz+KMoQmd2hvJ6nSzvbQBg05NWlQQBq3M0SSEEEejozG/kElBurGcsno+XlWExajlqmMz8TQ04ti+DRQwDxsa6PKEEF3M63TS+Mcf1H//A/WLFuGtrfVv04SGYpk2lZDp0zEfcwxq/ZGzdLkQYt88XoXluVV8ta6YbzaUtFj17FBo1CqCjVosBt8l1KRjcFIYw1PCGZESTqSley5a0L9XKJ9dPZ4r3lrJyrxqLp6/jH+f2JdLxqe1K1QrqLLy8Hdb+WLtbgBMOg1XHpvBZRPSMek7PyAy67UMTgrr9PMIIYQQRxoJpbqx3TV2nvt5B+nRQVx1bCYNP//M7ptuwjRiOKlvvRXo8oQQXcBrt9P422/Uff89DT/+hLdhz/AbTUQEwccdR/D04wgaNQqVLjDzvgghDo7Xq7Air5qv1u3m6w0llNfvCaKCjVoSw80EG7RYmsMlo5Zgo9bXZtBiMeqwGLSEGP+yj0GHUafuFj2fDkV0sIG3LxvNbZ9u4P0Vhdz71Wa2lNRz3xkD9tnzqN7u4rmfd/Dqb7twur2oVDBreCL/mJ4l8/QIIYQQXUBCqW4sM8Y3X0JepRWn24s+JRkAZ15eIMsSQnQyr9VKw6+/+obm/fwLinXPkuza6GiCp08n+PjpmIcPR6WRISBCdAder8Kq/Gq+XFfMNxuKKa3bE0SFGLUc3z+OkwbFMy4z6oib0+lIYtBqeOisQWTFhXDfV5v4cGUhuyoaeeGC4UQH7+kF5vZ4eXd5AY//sM0/8fjYjEj+c1Jf+vcKDVT5QgghxFFHQqluLD7USJBeQ6PTQ15lI+kpKQB4yivwNDSiscgKfEL0FJ76ehp+/oX677+nYfFiFLvdv00bH0/I9OkEH388piGDZaU8IboJRVFYXVDDl2uL+Xp9MSV1e36ug41apveL4+SmIEqvlZ/r9lKpVFwyPo3MGAtXv72KlXnVnPrMb7w8ZwQDEkL5eWsZ93212T+xe3p0EP+e0ZepfWN6bC8yIYQQ4kgloVQ3plKpyIixsK6wlpyyBnoPjEcTHo6nuhpXfh6afv0CXaIQ4hApLhe29etp/P0PGv/4A9u6deDx+LfrkpIIOd4XRBkHDJAvUkJ0E4qisLaw1jc0b30JRTU2/zaLQcv0frGcNCie8b2jZLLrwzSpTzSf/X0cl765gp3ljcx84Q8GJYaxbJdv4Ydws47rp/XhvNHJ0vtMCCGECBAJpbq5zL1CKQB9Sgq26mqceXkYJZQSottQFAVnbi6Nf/xB4x9/Yl26tMX8UAD69HSCpx9HyPHHY8jOliBKiG5CURTWF9Xy1bpivlxX3CKICtJrmNYvlpMGxjOxTzRGnQRRHSk92sInV43j2ndW88u2cpbtqkKnUXHxuDT+PjmTUJPMtSeEEEIEkoRS3VzzvFI55XuFUmvW4MzLD2RZQoh2cFdXY12yxBdE/f4Hrt27W2zXhIZiHnsMQWPHYhk7Fl1CQoAqFd2Nx6ug6cTl68WBldXbWZNfw4q8ar7ZUExB1Z4gyqzXMLWvL4g6NkuCqM4WatLx2kUjee6nHIpqbFx5bAYpkTLFgRBCCHEkkFCqm8uM9oVS+VW+iY71qb55pWSycyGOPF6nE9uq1U29of7AvnEjKIp/u0qnwzRsGEFjxxI0dizGfn1lovIj0I7yBj5aWci0frEMSw4PdDkt/J5TwcPfbSWntJ4HzxrEKYN7Bbqko4LV6WZDUR1rCqpZU1DD2oLaFr2hAEw6DVP6xnDywHiOzYrBpJef7a6kUau4ZmrvQJchhBBCiL+QUKqbG5cZxeJ/TSYhzARA0ISJqC3BmAYNDHBlQghFUXBs3+4PoazLV6DYWn5RNfTu7Quhxo3FPGIEarM5QNWKA1EUhfeWF3DXF5uwuTw89/MOjs2K5oZpfRicFBbQ2tYW1PDId1v5LafC33bNO6sprbNz6YT0AFbW83i8CjllDU0BVC1rCmrYVlqPx6u02E+lgt4xFoYkhTGxTzRTsmMw6+V/u4QQQggh9ib/d9TNBRm0BBn2vI2mAf0xDegfwIqEOLp5Ghpo/P0PGn75hcbFi3GXl7fYromKIqhpSF7QMWPRxcYEqFJxMGqtLm79ZB1fry8BfGHDzopGft5azs9by5nWN4brp/VhQELXLiWfU9bAo99v5ZsNvrp0GhXnj07B41X435I87v1qM7tr7PzfSX1Ry3C+Q1JaZ2d1fk1TD6ga1hXW0Oj0tNovNsTAkKQwBieFMSQpjIEJoQQbZb4iIYQQQoj9kVBKCCEOk2PXLhp++YWGn3/BunIluFz+bSqjEfOIEf7eUIY+fWSC8m5m2a4qrn93Nbtr7WjVKm46PovLJ6STX2XlqR+38+nqIhZuLmPh5jKm94vl+ml96NcrpFNr2l1j48mF2/lgZQFexdcr54yhCdwwrQ9JEWYURSEx3MQD32zhtd93UVpn59GzB8vcRfvhdHsprrVRUGVjw+5a1jQFUSV19lb7mvUaBiaEMiQ5jKFNQVR8qCkAVQshhBBCdG8qRVGUA+/WfRUWFpKUlERBQQGJiYmBLqdTfLWumK/XFzO1bwxnDkvEvnkzjpwczKNGoYuNDXR5QvQ4itOJdcUKGn75hfqff8b1l4UF9KmpWCZNwjJpIqbhw1EbDAGqVBwOt8fLU4u288xPOXgVSI008+S5Q1sN1dtZ3sBTi7bz2drd/inCZgyI47ppvcmO69hwqqrRyXM/5fDmkjycbi8Ax/WL5abpWWTFBbfa/7M1Rdz0wVpcHoVRaRG8/LcRhJqPzt47dpeHwmobRTU2CqutFFXb/PeLqm2U1ttp6/+I1CroExvMkKYeUEOSw+gdEywTyQshhBCiwx0N+cVfSU+pHmBrSR1frS/GYtBy5rBESu6+B9vq1SQ89ii6E08MdHlC9Aju8nIafv2Vhp9/ofH33/FarXs26nQEjRzRFERNQp+aGrA6RccoqLJy3burWZVfA8DM4YnceWp/LIbWvzbToy08ce5Qrp6SyZOLcvhy3W6+2VDCNxtKOGlQPNdP7U3v2NaB0cFocLh5dfEuXl68kwaHG4DRaRH864Rshqfse7L104YkEG0xMO9/K1m2q4qzXviDN+aO8s9D2JPU213+gGnvsKmw2kpRjY2KBucBj2HQqkkIN5HVFEINbhqGF9TG+y6EEEIIEWjW5cupfPU17Bs34i4vJ/GZpwmeNq19j121iry/zcHQuzfpn37SyZXum/xfVg+QEeNbgS+nvAEAfUoKttWrcebn7+9hQoj9ULxe7Bs30vDzLzT88gv2DRtabNdERWGZNBHLpEkEjR2HxiLLi/cUn60p4v8+2UC9w02wQct9Zw7k1HasYpcZE8zTs4dyzZRMnly4na/WF/t7sp4yqBfXTu1NZtO/1+3lcHt4e2k+z/yYQ2WjL1Tp3yuEf52QzcTeUe0aCjo2M4r3rziGi+cvJ6esgTOe/Z3XLx7V6UMM21JaZ+fpH7ezaXcdCr7FJxV8N7wKKCi+tqb25s7cyt7bmtp9j/Pdr2p0Umtz7eOse1gMWhLDTSSEmUgINzXdNvtvRwbpZXitEEIIIboNr82GITuL0LPOpOiaa9v9OE9dHbtvvoWgMWNwV1Z2YoUHJqFUD9D8JSenrAFFUdCnpgDgzM0LZFlCdDt7T1Le8OuveCoqWmw3DhiA5dhjsUyahLF/P1RqdYAqFZ2hweHm9s828PGqIgCGp4TzxDlDSIo4uBUR+8QG8+z5w7i6uI4nF27n240lfL52N1+u281pQxK4dmpv0qL2H2J6vAqfrC7i8R+2UVTjW7ExLSqIG4/rw0kD4w960vK+8SF8fNVYLpq/jG2lDZz94p+8cMFwxveOOqjjHCq7y8Mri3fy3M87sLYxSXhHCTPrSAjbEzYlhvvCp4QwE0nhZkJMWgmdhBBCCNFjWCZOxDJxIgBFB/G4kjvvJOTkk1CpNdQvWtQ5xbWThFI9QEa0BZUKam0uKhqcGJKTAXDmSSglxP64iouxrVmDbc1a3/WmTS0mKVebzQSNG+cLoiZOQBsdHcBqRWdaU1DDde+uJq/SiloF10zpzTVTMtFqDj147Bsfwgt/G86GolqeWLidhZtL+WR1EZ+v3c3pQxK4dmomKZEtwylFUfh+Uyn//W4r28t8vV9jQwxcN7UPs0YkojuMenqFmfjgirFc/uYKlu6q4qL5y3hk1iDOGNp58xUoisIX64p56Jst/nBtaHIYF49Lw6hVo1KpUOGbqF2lAhUqmv5ruQ1V0zWgArV/m689xKgjIdzU5vBKIYQQQgixR81HH+MsKKTXww9T8fwLgS5HQqmewKjTkBRuJr/KSk5ZA0NSmnpKSSglhJ/X4cC+ceOeAGrtWtylpa3206ekYDnWNzeUecQIVHp9AKoVXcXjVXjx1x089v023F6FhDATT5w7hJGpER12jgEJobxy4QjWFdbwxMLt/LiljI9WFfLpmiLOGpbANVN6kxRh5s8dlTz07RbWFNQAEGrScdWxGVw4NrXDVs0LNel485JR/OP9tXy5rpgb3ltLca2dKydldHgPojUFNdzz5SZW5lUD0CvUyM0zsjl1cC/prSSEEEIIsR/19fXU1dX57xsMBgwdsHiSMzeXssceI+Wt/6HSHhlx0JFRhThsmTEWXyhV3sCoAb5QylNVhae+Hk3w4U2wK0R3oygKrqLd/vDJtmYN9i1bWvSCAkCjwZiVhWnIYExDhmAaMgR9U09D0fOV1Nq54b01/LnTN47+pIHx3H/GwE5bnW5QYhivXTSS1fnVPLFwO79sK+f9FYV8vKqIvvEhrC+qBcCk0zB3fCqXT8wg1NTxtRi0Gp46dyjxoUZeXryLh7/dyu4aG3edOqBDVpQrqbXz8Ldb+Hi1rxO5SafhqmMzuHRCOiZ9x4RrQgghhBA9Wb9+/Vrcv+OOO7jzzjsP65iKx0PRTf8k+pqrMaSlHdaxOpKEUj1EZoyF37ZXUGt1orFY0ERG4qmsxJmXj2lA/0CXJ0Sn8tps2DdswOoPoda2mg8KfJOTm4YMxjR4MOYhQzD274/afHDzBYme4buNJdz80TpqrC7Meg13ntqfWcMTu6QHz9DkcN6YO4qVeVU8/sN2fsupYH1RLVq1ivNGJ3P1lExigo2dWoNareI/J/UjPtTEPV9t4q0l+ZTVOXhq9tBD7pVlc3p46dedvPDLDmwu37xRZw1L5J/HZxEX2rnPRwghhBCiJ9m0aRMJCQn++x3RS8rb2Ih9wwZKNm+m5J57mxq9oChs7j+A5FdfIWjMmMM+z8FSKc1L2/RQhYWFJCUlUVBQQGJi582bEWiNDjcGrdo//0nd11+jMpsxDx8uPaVEj2TbsJHaTz7Btno19q1bwfOXyZO1Wox9+2IavKcXlC5Bhg0dybxehTq7i6pGJ9VWF0EGDTHBRsLNug5732xOD/d+tYkFS32rkw5MCOXJc4eQHn1wq+J1pGW7qvhjRwVnDk0kObLrQ9Kv1xdz/XtrcLq9DEsO45ULRxIR1P5hq16vwudrd/PQt1sorrUDMCIlnNtP6cegxLBOqloIIYQQouc5nPxic3ZfEp95muBp09rcrni9OHJyWrRVv/MO1iVLSXjyCfSJiQH5g730lOohgv4yuWvIiScGqBIhOpdt3Toqnn2Ohl9+adGujYnxhU+DB2MaOgRjv36ojdI7I5BsTg+VjQ6qG11UWZ1UNzqpbPRd//V+tdUXRHm8rf9OotOoiAk2Eh1sICbYQGyIkZhgAzEhBmKabwcbiQzS73dVus3FdVz7zmr/BOLzJqbzj+lZ6LWBXUVxVFoEo9I6bg6rg3XiwHiiLAYue3MFq/JrmPn8H7x+8ah2BWSr8qu5+4tN/nmwEsJM3HpiNicNjJcAWAghhBCik3kbG3Hm5/vvOwsLsW/ejCY0FF2vXpQ9+hjuslJ6PfQQKrUaY58+LR6vjYhEZTC0au9KEkoJIboF25o1lD/7HI2LF/sa1GpCTjyR4KlTMA0ZgjYuTr4EB4CiKKwpqOHjVUXkVjb6ejk1hU52l/eQjhls0BIWpKPR4aGq0YnLo1BUY/Ov3rYvWrWKKIuB2BAD0cFGYkIMxDZdVzU6eXLRdpxuL9HBBh47ezATestqis1GpUXw0ZXHcOFry9lZ0ciZz//O/ItGMTAxtM39d9fYeOjbLXy2ZjcAQXoNV03O5JLxaR02KbsQQgghhNg/24aN5F94of9+2YMPARB6+un0evAB3OXluHYXB6q8dpHhez3I3V9sYlluJQ+cMYh+FoWG339HsdsJO+usQJcmxCGzrlpFxTPP0vjHH74GjYbQU04h6op56FNTA1rb0azW6uLTNUW8syyfLSX1+9xPr1ETEaQnPEhPZNN1hFlHRJCBiCBd0309ERbfdZhZ36LnktPtpbzBQVmdndI6B+X1dsrqHZTVOSitt1NW56Cs3kFlo4P2/Dabmh3DwzMHEWk5/HH5PVFpnZ2L5i9nc3EdZr2GZ88fxuSsGP92q9PNC7/s5KVfd2B3eVGpYNbwRG6ankVMiPRMFEIIIYQ4HEdTftFMekr1IFtK6thQVMeWkjp6BzWw+x83oQkPl1BKdEvW5cspf/Y5rEuW+Bq0WkJPO5WoefNkhbwAURSF5bnVvLssn6/WF+Nw+3pCGbRqThoYz7jMKH+4FBHku5j1msPqwabXqkkIM5EQZtrvfi6Pl8oGJ2X1vvCqzB9Y+a7r7W5OGdKLC0YnS4+6/YgNMfL+vDFc+dYqfsup4NI3VvDAGQOZOTyRT1YX8fB3WyitcwC+3lW3n9yPAQlt96YSQgghhBDiQCSU6kEyYyz8saOSnPIGdNm+L+2e6mo8dXVoQkICXJ0QB6YoCtaly6h47jmsy5b5GrVaws44g8h5l6M/Sv5acKSpanTy8apC3lmWz47yRn97dlww545M4oyhiYSadQGsEHQaNXGhRlnlrQMEG3W8dtFIbvloHR+vLuJfH63j+V92sKvC994nRZj494y+nDBAhswKIYQQQojDI6FUD5IZ41s9akdZAxpLEJroKDzlFTjz8jANHBjg6oTYN0VRsC5ZQvmzz2JbsdLXqNMRdtaZRF12Gbq9lkMVXcPrVViys5J3lhfw3YYSnB5fryiTTsMpg+OZPSqZIUlhEkr0UHqtmkfPHkxcqJHnfvYFUhaDlqunZHLR2FSZN0oIIYQQQnQICaV6kMymJc1zmlaW0qekYCuvwJmXL6GUOCIpikLj739Q8dxz2FatAkCl0xE2ayaRl12GLj4+wBUefcrq7Xy4spD3lheQV2n1tw9MCOXcUUmcOrgXwcbA9ooSXUOlUvGvE7LJigtma0k9F49LIzpY5uISQgghhBAdR0KpHqS5p1R+lRW7y+MLpVasxJmXG9jChPgLRVFoXLyYimefw7Z2LQAqvZ6ws88m8rJL0cXGBrjCo4vHq7B4eznvLitg4eZS3F7fjOEWg5bThvRi9qhkmTfoKHbaEOmpKIQQQgghOoeEUj1IdLCBYKOWerub3MpGopJTAHDm5QW4MiF8FEWh4eefqXjueezr1wOgMhgIP/ccIuZegi425gBHEB2ppNbO+ysKeG95AUU1Nn/70OQwZo9M5uTB8Zj18mtCCCGEEEII0Tnk20YPolKpyI4LprLBSb3dTa8UXyjlyssPcGXiaNfcM6r8yaewb9wIgMpoJPzcc4m8ZC7a6OgAV3h08HoVNpfU8XtOBYu3V/B7TgVNnaIIMWo5c1gi545KIjtOFkYQQgghhBBCdD4JpXqY9y4/BrXaN/Gw2zKcxOeeRZ+WFuCqxNHMumoVZY895p/AXGUyEX7ebCLnzkUbGRng6nq+giorv+dU8FtOBX/sqKSq0dli+6i0CGaPSmLGgHiZvFoIIYQQQgjRpSSU6mGaAykAbVQUwVOmBLAacTSzb91K+eNP0PDzz4Bvzqjw888n8rJL0UZEBLa4Hqy60ckfOyr5LcfXEyq/ytpiu1mvYXRaBOMyo5icHUNG0wIJQgghhBBCCNHVJJQSQnQoZ0EB5U89Td2XX4KigEZD2JlnEvX3q9DFxQW6vB7H5vSwIq/KH0Jt3F2HouzZrlGrGJoUxrjMKMZlRjEkKQy9Vh24goUQQgghhBCiiYRSPUx1o5OLX19OYbWNpf+ein35cmyrVxM0ZjSmIUMCXZ7owVxlZVS+8ALV738AbjcAwSecQPS112JIlyGkHcXjVVhfVOsbkre9gpV51Tg93hb79Im1MC4zivGZUYxKiyDYqAtQtUIIIYQQQgixbxJK9TAhJh2bi+twuL0UVFnRf/4ZtR99jHL11RJKiU7hqauj8pVXqfrf/1BsvhXcgsaPJ/r66zEN6B/g6nqO33MqePPPXP7cUUmd3d1iW3yo0R9Cjc2IJCbEGKAqhRBCCCGEEKL9JJTqYTRqFenRFjYX15FT1sCQlFQAnHl5gS1M9Dhem42qt96i8pVX8dbWAmAaPJjoG28kaPSoAFfXs+SU1XPR/GW4PL5xecFGLWMzIv1D8tKjglCpVAc4ihBCCCGEEEIcWSSU6oEyY5pCqfIGRqWkABJKiY6juFzUfPQRFc8+h7u8HABD70yir78ey5QpEo50MK9X4d8fb8DlUTgmPZKbZ2QzoFcIWo3MCyWEEEIIIYTo3iSU6oF6x/hW08opa0A/SEIp0TEUr5e6r7+h/KmncOXnA6BLSCDqmqsJPeUUVBpNgCvsmd5fUcCy3CpMOg2PzBpEYrg50CUJIYQQQgghRIeQUKoHytw7lEruA4C3thZPTQ2asLAAVia6I0VRaPz1V8oefwLHli0AaCIjibriCsLOORu1Xh/gCnuu8noH93+9GYB/TO8jgZQQQgghhBCiR5FQqgdqDqV2lDWgMhrRxsbiLi3FmZeHSUIpcRCsq1ZR9thj2FasBEBtsRB5yVwi5sxBHRQU4Op6vnu+3ESd3c2AhBAuGpsa6HKEEEIIIYQQokNJKNUDpUYGkRJpJi0qCKvTgz45eU8oNXhwoMsT3YDXZqP04YepeeddAFQGA+EXnE/kpZeiDQ8PcHVHh5+3lvH52t2oVfDAGYNkDikhhBBCCCFEjyOhVA+k16r55Z+T/fc1t94CWi36pknPhdgf+6ZNFN30T5w7dwIQNmsmUVdfjS42NsCVHT1sTg+3fbYBgIvGpjEwMTTAFQkhhBBCCCFExwtoKOXxKjyxcBufrC6ivN5BbIiRmcMTuWZKpn8FL0VRePyHbbyzvIA6m4sRqeHce/pA0qJk6FB7Gfv1C3QJohtQvF6q5r9O2RNPgMuFNjqa+AcfwDJuXKBLO+o8sWgbBVU2eoUa+cf0PoEuRwghhBBCCCE6RUBDqRd+2cFbS/J49OzB9I4JZn1RLf/8YC3BRi0Xj0tr2mcn8//I5dFZg0mKMPPo99uY89pSfrhhEkadrPZ1IHaXR14ncUCu0lJ233IL1j+XAGCZOpX4e++RoXoBsGl3Ha8s3gXA3acNIMggHVqFEEIIIYQQPVNAJylZmVfNcf1imZIdS1KEmRMHxjOhdzRrC2oAXy+p137fxTVTMpneP46+8SE8ds5gSuscfL+pNJClH/F+3lrGsHt+4MLXluFpaKTi5ZcpufseFEUJdGniCFP3ww/sOvU0rH8uQWU0EnfXXSQ+87QEUgHg8Src+sl6PF6FGQPimNZPhkwKIYQQQggheq6AhlLDU8L5PaeSneUNgK+HwIq8Ko7NigGgoMpGeb2DcZlR/seEGHUMSQpjVV51m8d0OBzU1dX5L/X19Z3/RI5A4WY9VY1OdpQ3oNKoKX/0MarffhtPTU2gSxNHCK/VSvFtt1N0zbV4amsx9utH2scfEX7O2f7hs6JrvbUkj7UFNQQbtNx5av9AlyOEEEIIIYQQnSqg40KunJRBvd3N1Md+QaNS4VEUbpqexelDEwAob7ADEG0xtHhctMVAeYOjzWM+8MAD3HXXXZ1beDeQEWMBoKLBSZ2iQRsXh7ukBGdurvSAEdjWb2D3P/+JMzcXVCoiL5lL9LXXotLrA11awLg8XqoancSGGANy/pJaO498txWAf52QFbA6hBBCCCGEEKKrBLSn1Jfri/lsTRFPnjuUL68dz6OzBvPy4p18uLLwkI956623Ultb679s2rSpAyvuPiwGLfGhvi+1OWUN/pX3XPn5gSxLBJji8VDx8svkzp7tCyhjY0me/xoxN9101AZS9XYXL/+6kwkP/cTo+xfxwi87AlLHHZ9voMHhZmhyGOePlpUyhRBCCCGEED1fQHtKPfD1Zq48NoNTB/cCIDsuhKJqG8/9nMPM4YlEW3yhSnmDg5i9eg2UNzjoFx/S5jENBgMGw56eVXV1dZ34DI5smTEWimvt5JQ1kJCSgnXpUpx5eYEuSwSIq7iY3TffgnXZMgCCp08n/u670ISFBbawACmrt/P677n8b0ke9Xa3v/3Bb7bgcHm5dmpmlw1j/H5jCd9tLEWrVvHAmQNRq2X4pBBCCCGEEKLnC2goZXN5Wn3pU6tVNM/FnRRhIjrYwB85lfTvFQr4ejWsKajhgjHSk+BAMmMsLN5eQU5ZA8elJAPgzJVQ6mhU9+23FN9xJ97aWlRmM3H/+TehZ555VM4dtauikZd+3clHqwpxur0ApEcHMW9iOmV1Dh79YRuPL9yG0+PhpulZnf4aNTjc3PH5RgAum5hOdlzbgbsQQgghhBBC9DQBDaWmZsfy7I85JIQZ6R0TzMbddbz62y5mjUgEQKVSMXdcGk//uJ3UqCCSIkw8+v02YkMMTJdVqQ4os2leqZzyPcP3pKfU0cXT0Ejp/fdT+/HHABgHDiThkYfRp6YGtrAAWFNQw4u/7ODbjSX+4HtochhXTMrguL6x/t5JJr2Ge7/azLM/7cDh8vKfk/p2ajD13++2UlxrJznCzHVTe3faeYQQQgghhBDiSBPQUOqu0/rz6Pdbue3TjVQ0OIgNMXLeqGSu3euL2RWT0rE53dz68Xrq7C5GpobzxsWjMOo0Aay8e+jfK5RxmZEMSw5Hn+yb3NyZn4+iKEdlD5mjjW3tWor++S/fPGIqFZGXX0701X9HpdMFurQuoygKP28r58VfdrBkZ5W/fWp2DPMmZTAyNbzVz8KlE9LRa9Xc/tlGXvltFw63l7tO7d8pQ+rWFtTwxp+5ANx3xgD5d00IIYQQQghxVFEpSnOfgZ6psLCQpKQkCgoKSExMDHQ5AaO4XDh27ECfnIzabA50OaITKR4PlS+9RPkzz4LHgzY+noSHH8I8cmSgS+syLo+XL9ft5sVfdrKlpB4ArVrFaUMSuHxiOllxwQc8xrvL8rn1k/UoCpwzIon7zxyIpgODKbfHy6nP/M6m4jpOH9KLJ84d2mHHFkIIIYQQQnQ/R2N+EdCeUqLrqHQ6jNnZgS5DdDJXURFF/7oZ28qVAIScOIO4O+5AExoa4Mq6htXp5t1lBbz62y6KamwABOk1zB6VzNzxafQKM7X7WOeOSkavVXPTB2t5b0UBTo+XR2YOQqvpmEVLX/t9F5uK6wgz6/i/k/t1yDGFEEIIIYQQojuRUOooUGd34fUqhJn1gS5FdKK6b76h+PY78NbXow4KIu722wg59dSjYqhmZYODN/7I5c0ledRYXQBEWfRcPC6NC0anEGo+tCGLZw5LRK9Vc/27a/hkdRFOt5cnzh2C7jCDqYIqK4//sB2Af8/oS5TFcIBHCCGEEEIIIUTPI6FUD3ffV5t4efEurp6cyRWWCuq/+x7TkCGEnXlGoEsTHcRrtVL6wAPUfPAhAKbBg+n130fQJyUd1nFrbS6eXLidMekRTO8f1xGldrj8SisvL97J+ysKcDStpJcSaebyiemcNSyxQ+ZoOnlQL/QaNX9/exVfrS/G6fHyzHlDMWgP7diKonDbZxuwuTyMTovwL+wghBBCCCGEEEcbCaV6uNgQIwA5ZQ04irZR8/77eBvqJZTqIexbt1J0w404d+7s8MnMH/luC28tyee133cxd1wat56Yfdg9hDqK0+3lv99v5ZXFO/E2zYo3KDGUKyZlcHz/uA6d+wlgev84Xpozgnn/W8kPm0qZ97+VvHDB8EMKvb5cV8zPW8vRa9Tcf+bAo6InmxBCCCGEEEK05cj4hik6TWaMBYCc8gb0KckAOHPzAlmS6ACKolC1YAG5s87GuXMn2uhokue/RswN13dIILWzvIF3lhX477/2+y7OfWkJJbX2wz724cqvtDLrxT956VdfIDWxTzRvXzqaz/4+jhMHxnd4INVsclYM8y8aiVGn5uet5VzyxnKsTvdBHaPW6uKuLzYBcNXkDDKiLZ1RqhBCCCGEEEJ0CxJK9XDNoVRuRSOqpKZQKi+PHr7oYo/mrq6m8O9XU3rPvShOJ5ZjjyXt888IGjOmw87x6Pfb8HgVpmTH8PKcEQQbtazMq+akpxbze05Fh53nYH25bjcnPbWYtQU1hBi1vHDBcN6cO4qxmVFd0uNoXGYUb1w8iiC9ht9zKrnoteXU213tfvyD326hosFBRnQQVx6b0YmVCiGEEEIIIcSRT0KpHq5XqAmzXoPbq1BsjgSVCm9jI56qqkCXJg5B47Jl7Dr9DBp+/BGVTkfsv28l8fnn0IaHd9g51hTU8NX6YlQq+NcJWRzXL5YvrxlP3/gQKhud/O3VpTz7Uw5eb9cFmzanh1s/XsfVb6+m3uFmeEo4X183gRMGdP1cV6PTI/nfpaMJNmpZllvF315dRq3twMHU8twq3lmWD8D9Zww85DmphBBCCCGEEKKnkFCqh1OrVf4hQjtqnOji4wFfbynRfShuN+VPPU3+RRfjLi1Fn5pK6nvvEjFnTof2EFIUhQe/2QzAmUMTyY4LASAlMohPrhrL2SMS8SrwyHdbuezNFdRa299L6FBtK63ntGd/451lBahU8PfJGbx3+RgSw82dfu59GZYcztuXjiHUpGNNQQ3nv7KE6kbnPvd3ur38++P1AJwzIonR6ZFdVaoQQgghhBBCHLEklDoKNA/h21HegE7mlep2XLt3kzfnQiqeew68XkLPPJO0jz7E2K9fh5/rl23lLNlZhV6r5sbpfVpsM+o0PDxzMA+dNRC9Vs2iLWWc/MxiNhTVdngd4AvI3lmWz6nP/Ma20gaiLAb+N3c0/zw+G+0RMOH6wMRQ3r18DJFBejYU1TH75SVUNDja3PfFX3awvayBKIueW0/M7uJKhRBCCCGEEOLIFPhvdqLTTeoTzXmjkxmQEIo+JQU0GhTnvnt1iCNH3fffs/P0M7CtWoU6KIhe//0vve6/D3VQUIefy+tVePCbLQBceEwKCWGmNvc7Z2QyH185luQIMwVVNs58/g/eXZbfofOU1dldXPPOam79eD12l5cJvaP45roJjO8d1WHn6Ah940N4b94YYoINbCmp55wX/6S0ruVk8DvLG3j6pxwAbju5H2FmfSBKFUIIIYQQQogjjkrp4TNeFxYWkpSUREFBAYmJiYEuJ+Ccubmog4PRRsrwoSOZ126n9MEHqXn3PQCMAweS8Oh/0Scnd9o5P1ldyA3vrSXYqOXXf04mPGj/4Umt1cU/PljDws1lAMwcnsg9pw3ApD+8uZLWFNRwzTurKKiyoVWruOn4LC6fkI66k1bV6wi7Kho57+UlFNfaSY008/ZlY+gVZkJRFM57eSl/7qxkQu8o3pw7qksmZBdCCCGEEEJ0P0djfiE9pY4y+tRUCaSOcPZt28idNcsfSEVedimpC97q1EDK4fbw3++2AXDlsRkHDKQAQs06XvrbCP51QhZqFXy4spAzn/+D3IrGQ6rB61V4+dedzHz+DwqqbCSGm3j/imO4YlLGER1IAaRFBfH+vGNIDDeRW2nl7Bf/pKDKykerivhzZyVGnZr7Th8ogZQQQgghhBBC7EVCqaOEzelhQ1EtDQ63v83T0BDAisRfKYpC9bvvkjvrbBzbc9BERZH06ivE/OMfqPSdO+TrrSX5FNXYiA0xcPHYtHY/Tq1WcdWxmbx1yWgig/RsLq7jlKd/47uNJQd1/soGB3PfWM59X2/G7VWYMSCOr66dwLDkjltVsLMlRZh5f94xpEaaKay2cfaLf3LfV5sAuG5qH5IjAzcxuxBCCCGEEEIciSSUOkqc+sxvnPz0b6zIrcJdXk7eBX9jx9RpeGVuqSOCp7aWouuup+TOu1AcDoLGjyf900+wjBvX6eeus7t45sftANwwrc8hDb8bmxnFV9dOYHhKOPUON/P+t5IHvtmM2+M94GP/2FHBjCcX8/PWcgxaNfedMYDnzh9GqEl30HUEWq8wE+/PO4bMGAvFtXaqrS6y44K5dEL7gz4hhBBCCCGEOFpIKHWUyIj2rcCXU9aAJiICZ14entpaGn/9NcCVCevKlew8/Qzqv/8edDpi/vUvkl56EW1U10zq/dIvO6m2usiIDmLm8EMftxwXauTdy8dwyXhfAPPiLzs5/5WllNXb29zf7fHy2Pdbm/ZxkBlj4bOrx3H+6JRuPcwtJsT3OgxICCFIr+GBMweiOwJWCxRCCCGEEEKII418UzpKZMb4Qqkd5Q2oNBpCTj4ZgNovvgxkWUc1RVGoeOEF8v42B3dxMbqUZFLffpvIuRejUnfNj2ZZnZ1XftsJwL9OyEZ7mOGJTqPmtpP78ex5wwjSa1i6q4qTnvqNZbuqWuxXXGvjvJeX8tSPOSgKnDMiic+vHkd2XMhhnf9IEWUx8MXV4/nz31MZ2o2GIAohhBBCCCFEV5JQ6ijRO3ZPTymA0FN8oVTDTz/hqa8PWF1HK0VRKH3gAcqfeBK8XkJOPYW0jz7GNHBAl9bxxKLt2F1ehiWHMb1fbIcd96RB8Xx+zXj6xFoor3cw++UlvPzrThRFYeGmUmY8uZhluVVYDFqePHcID80chFmv7bDzHwlUKhUhxu43BFEIIYQQQgghukrP+hYo9mnv4XsAhr590Wdm4MzZQf333xN21lmBLO+ooigKpffdT/VbbwEQe/ttRJx3XpfXsaO8gfeWFwBwy4y+HT5kLiPawqd/H8e/P17Pp2t2c9/Xm/l4dRGbi+sAGJgQytOzh5IaFdSh5xVCCCGEEEKIo4F1+XIqX30N+8aNuMvLSXzmaYKnTdvn/nXff0/Nu+9i37wFxenEkJlJ1NVXY5kwvgurbkl6Sh0lMqItqFRQbXVR2eBApVIResqpANR+/kWAqzt6KIpC6b33+QOpuHvuDkggBfDf77bi8SpM6xvDqLSITjmHWa/l8XOGcM/pA9BpVP5A6pLxaXx05VgJpIQQQgghhBDiEHltNgzZWcTeflu79reuWEHQ2LEkvfQiaR99iHn0aAquugr7pk2dXOm+SU+po4RJryEhzERhtY2csgYiLQZCTz6J8scfx7psGa6SEnRxcYEus0dTFIXSe+6l+u23QaUi/p67CZs5MyC1rMqv5psNJahU8M/jszv1XCqVir+NSWFgQijzf9/F6UMSmJwd06nnFEIIIYQQQoiezjJxIpaJEwEoasf+cf/+d4v7MTfeQP2Pi6j/6SeM/fp1QoUHJqHUUeSisal4vAoJ4SYAdAkJRMydizE7C01oaICr69kUr5eSe+6h5p13fYHUvff8P3t3HV913f5x/HXO2c66u2B0t4BSEhIqFnZ3563e5s8ObG+7W2wxMMBAUETpbhiw7s5T398fgwOTIRtsO2N7Px+PPWDf+HyvjQ04167r+nisZdIwDB77cSMApw5OpEdsUIs8d2BSKM+dNahFniUiIiIiInK4Kisro7S01P2+j48PPj4+Tf4cw+XCVVGJJSS0ydduKCWl2pHLRnfe51jMbf/1QCTti+Fykf3ggxR/8mltQuqRRwiddorH4pm3KY/F2wuxepn5z8TuHotDRERERERE9tX7H1VL9913H/fff3+TP6fw7bdxVVYSfOyUJl+7oZSUEmlGhstF9gMPUvzproTUo48SesrJHovH6TJ4fHZtldRFI5JJCPXzWCwiIiIiIiKyr/Xr15OQkOB+vzmqpEpmfUfeSy+T9NKLeEVENPn6DaWkVDvidBlszS0ntbCSib1j3MftubmUzpqFyc/PY0O32yLD5SL7vvsp/vzz2oTU9EcJPflkj8b09YoMNmaXEeTrxTVju3g0FhEREREREdlXUFAQwcHBzbZ+yfffk3XPPST871kCRoxotuc0hHbfa0fKqx1M/t/vXP7+UsprHO7jVcuXk/vkUxS8+SaGy+XBCNuO2oTUfe6EVPxj0z2ekKq2O3nm580AXDO2K6H+Vo/GIyIiIiIiIi2r5LvvybrrbhKefoqgsWM9HY6SUu1JiL83kYG1ZX/bcsvdxwPHjsUcGIgjM4uqZcs8FV6bYbhcZN17L8WffwFmM/GPP0bISSd5Oiw+/HsnGcVVxAb7cvHIZE+HIyIiIiIiIofAVVFB9YYNVG/YAIAtPZ3qDRuwZ2YCkPv0M2Tefrv7+pJZ35F5xx1E334bfv3748jLw5GXh7OszCPxg5JS7U7X6AAAtu6VlDL7+hI0aRIAJd/O8khcbYXhcpF1zz2UfPHlroTU44SceKKnw6K02s6Lv20F4D8Tu+HrbfFwRCIiIiIiInIoqtauY/sp09h+yjQAch97nO2nTCPv+RcAcOTlYc/Mcl9f/Nln4HCQ8+BDbBk9xv2W88ijHokfNFOq3ekWHcTfKYUsSy3i1CGJ7uMhJ55AycyZlM6ZQ8w9/4fZqtauxjKcTrL+7x5KvvqqNiH1xBOETD3e02EB8Nr8bRRX2ukaHcipgxMPfIOIiIiIiIi0agHDh9Fr44b9no9/bHqd9zt+8H5zh9RoqpRqZ47tGwvAl8vSySurcR/3HzoUr+hoXKWllM+f76nwDluG00nW3f+3JyH1ZOtJSOWUVvPWgu0A3Da5B14WfduLiIiIiIiI5+nVaTtzVJcIBiaFUuNwuRMVACaLheCpUwEoVQtfoxhOJ1l33U3J11+DxULCU08ScnzrSEgB/O+XLVTbXQzpGFZn10URERERERERT1JSqp0xmUxcN64rAPM25eJyGe5zISdMxeTjg9nfH8Mw9reE7KU2IXUXJd98U5uQevopgo87ztNhuW3NLeezpWkA3HFsT0wmk4cjEhEREREREamlmVLt0IRe0bx63hCO6RWN2bwnSeHTsyfd/vwTS2CAB6M7fBhOJ5l33llbWbY7ITVliqfDquOpOZtwugyO6RXD0ORwT4cjIiIiIiIi4qakVDtkMpmYsmu21D+PKyHVMIbDQeYdd1L63Xfg5UXC008TPHmSp8OqY3lqEbPXZWM2wW1Teng6HBEREREREZE61L7XztkcLjbnlO1zvGbbNhyFhR6IqPUzHA4yb79jT0LqmdaXkDIMg8d+2AjAaUMS6R4T5OGIREREREREROpSUqod25JTxtgnf+O8NxdRbXe6j2fdex8px0+lZOZMD0bXOhkOB5m33U7p99/XJqSefYbgSa0rIQXw26ZcFu8oxMfLzE3HdPd0OCIiIiIiIiL7UFKqHesYEYAB5JbV8OXydPdx3759ACiZ9Z2HImudDJerNiH1ww/g5UXi/54leOJET4e1D6fL4PEfNwFw0chk4kP9PByRiIiIiIiIyL6UlGrHrF5mrhjTGYBX52/D4XQBEDx5MiZvb2o2baJ602ZPhtiq5D75VG1CytubxOf+R9Axx3g6pHp9tSKDTTllBPt6cc3RXT0djoiIiIiIiEi9lJRq584a2oGIACtphVV8uyoTAEtICIFjjwag9LtZngyv1SicMYPCd94BIP7RRwmaMMHDEdWv2u7kmZ9qq6SuHdeVEH9vD0ckIiIiIiIiUj8lpdo5P6uFS0Z1AuDledtwuQwAgqeeAEDJd99juFwei681KJv7GzmPPApA1E03EXLCVA9HtH8f/LWTzJJq4kJ8uXBEsqfDEREREREREdkvJaWE84/qSJCvF1tzy/lpfTYAgWOPxhwUhCMri8qlSz0coedUrVlLxi23gMtF6OmnEXHlFZ4OqV5phZW8+UcKL8zdAsB/JnbH19vi4ahERERERERE9k9JKSHY15sLj0oGYNH2QgDMPj4ETa7dVa5s9mxPheZR9owM0q6+GqOqioCRI4m9915MJpOnwwLAMAw2ZJXyv182c+xzfzD6id94+PsNlFY76B0XzKmDEz0dooiIiIiIiMi/8vJ0ANI6XDKqE8f0jmFgUqj7WPj55xM0diwBY8Z4LjAPcZaWknrllTjz8/Hp0YOE5/6Hyduz85lcLoPlqUXMWZfNnHU5pBZWus+ZTTCsUziT+8QybXAiFnPrSJ6JiIiIiIiI7I+SUgJAeICV8ABrnWO+PXrg26OHhyLyHMNmI/36G7Bt3YZXdDRJr72KJTDQI7HYHC4Wbstnzrocfl6fQ355jfuc1cvMmG6RTOoTyzG9Yvb58xMRERERERFpzZSUkn3kllVTWeMkOTLA06G0OMMwyLrnHioXLcLs70/Sa6/iHRvbojFU1DiYtymPOeuy+W1jLmU1Dve5IF8vxveMZnKfWI7uHkWAj76FRURERERE5PCkV7RSx7erMvnv56s4qksE7148DMNuJ/+VVyid8xPJH83AEhLi6RCbVf6LL1HyzbdgsZDw3P/w7dWrRZ5bWGHjl/U5zFmXzR9b87E59ux4GBXkw8TeMUzuE8tRnSOwemkUnIiIiIiIiBz+lJSSOgYkhmB3upi3KY+1GSX0TQih7JdfsW3bRulPPxF2+umeDrHZFM/8ivyXXgIg9r57CRw9ulmfZxgGM5dn8NnSNJbsKMRl7DnXMcKfyX1imdwnhkFJYZg1I0pERERERETaGJVcSB0dIwI4YUA8AC/P2wpA8AlTASj9dpbH4mpuFX/9Rda99wIQccUVhJ1xRrM/89X5Kdzy+SoWba9NSPWOC+Y/x3Rn9k2jmXfrWO46rhdDOoYrISUiIiIiIiJtkiqlZB/XjO3KNysz+XFtNltzy+k4dSp5Tz9D5ZIl2DMz8Y6P93SITap682bSr78BHA6Cjz+eqJtubPZnfrY0jcdnbwTgyjGdOe/IjiSF+zf7c0VERERERERaC1VKyT56xAYxsXcMhgGvzNuGd1wc/kOHAlDy/fcejq5p2XNySbvyKlzl5fgdMYS46Y9iMjfvt8WvG3K4c+YaAK48ujN3HtdLCSkRERERERFpd5SUknpdO64rAF+vzCCtsJLgE08A2lYLn6uigvSrr8aRlYW1UyeSXnwRs9XarM9ctrOQaz9ajtNlcOrgRO6Y0rNZnyciIiIiIiLSWikpJfUamBTKqK6RWMwmVqUXEzx5MiZvb2q2bKF60yZPh3fIDIeDjJtvoXr9eizh4SS9/hqW0NBmfeaWnDIueXcp1XYX43pE8dip/TCZNC9KRERERERE2ifNlJL9evCkPgT6ehEd5AtQWy1lMmFq5mqi5mYYBtmPPEL5/PmYfHxIeuVlrElJzfrMzOIqLnh7MSVVdgZ1COWlcwfjbVFOWERERERERNovJaVkvzpHBdZ5P/6RRzwUSdMqfPttij/+BEwm4p96Er8BA5r1ecWVNi54ezFZJdV0iQrg7QuH4m/Vt56IiIiIiIi0byrVkAZZlVZMcaXN02EcstLZs8l98ikAYu64neCJE5v1eVU2J5e8u4StueXEBvvy/qXDCQs4vCvNRERERERERJqCklJyQPd/u46TXvqTd/7cgWEYVK1eTcl3h98ufJXLl5N52+0AhJ13HmEXXNCsz3M4XVz30XKWpxYT7OvF+5cOIyHUr1mfKSIiIiIiInK4UFJKDuiI5DAA3l24g/zFy9lxxplk338/rpqaJn/Wsp2FfL40DcMwmnRd244dpF9zLYbNRuD48cTceUezDhk3DIM7Z67h1425+HiZefuioXSPCWq254mIiIiIiIgcbho12MblMvh7ewFLtheRUVxJld1FRICV3vHBjOoaSbyqQNqkY/vG0TlyMyn5FXxZFcKEuDgcWVmUz5tP8ORJTfKMkko703/cwCdL0ugRE8TApFC6NVESx1FUROqVV+IsLsa3b18SnnoSk8XSJGvvz5NzNvH5snTMJnjxnMEckRzerM8TEREREREROdw0qFKq2u7khV+3cNRjv3LxO0uYtzmX0ioHFhPsKKjgfz9vZvQTv3HRO4tZnlrU3DFLC7OYTVw1tgsAby7Yge/xUwEomfXtIa9tGAY/rMliwjPz+WRJGgDXje/aZAkpV3U16Vdfg31nKt4JCSS9+gpmf/8mWXt/3l6wnZfnbQNg+rR+TOwd06zPExERERERETkcNahSatxT8xjcIYzHpvVnVLfIereyTy+q5JuVmVz/0QquG9+Vs4d1aPJgxXNOGZTAc79sIaO4ip/7juIo3qBi/u84i4uxhIYe1JpZJVXc8/U6ftmQA0DnqAAem9afYZ2apqrIMAyy7rqbqpUrMQcHk/T6a3hFRjbJ2vvz7apMHvxuPQD/ndyDM4fq+0BERERERESkPg1KSn1w6TC6Rv975UpimD/XjuvKFWM6k1lc1STBSevhbTFz5dGdufebdby1sZxRPXri3LSR0jk/EXbmGY1eb9nOIi58ezHlNQ68LSauProL14zriq93bVtdlc1JeY2DqCCfg465ZOZMSn/4Aby8SHzhBXy6dDnotRrijy153PLZSgAuGpHMNWOb93kiIiIiIiIih7MGte8dKCG1N2+LmY4RAQcdkLReZxyRRGSgDy7DoHTyiQCUzpp1UGv1jgsmItDKoA6hfHf9aG6e1MOdkJqxaCeDHvqJZ37edNCx2nbsIPuRRwGIuvEGAoYPO+i1GmJ1ejFXfbAMu9Pg+P5x3Du1d7MOUhcRERERERE53DVq0PneHE4XHy1O5e+UApwugyM6hnP+UR3diQVpe3y9LXx42TA6RwZiysth6wtPYktLw1VRgTng3xORNoeLL5alc+bQJCxmE35WCx9dfiSxwb5YzHWTNx3C/am2u/h5fQ4Pn2zsc/5ADLudjP/ehlFZif/w4URcemmjP9bG2J5fwcXvLKHC5mRk1wieOWMA5kbGLCIiIiIiItLeHHRS6v5Z69ieX8GUPrHYnQYzV6SzOqOEF84e1JTxSSvTMza49jdxcSR/9hm+vXsdcCe7ZTsLuePLNWzJLafG4eTikZ0ASNjPbo3DO0UQ5OtFfrmNlWlFDOnYuBlTeS++RPWaNZhDQoh/bDomc4MKAg9Kbmk1F7y9iIIKG30Tgnn1vCH4eCkxKyIiIiIiInIgDU5KzV6bzZS+se73/9iSz9xbxrqrWMZ0j+KUl/9s+gilVXI4XfxujmTSvyR8yqrtPDlnEx/8vRPDgMhAK7HBvgdc2+plZnzPaL5ZmclP63IalZSqXLKEgtdfByDugfvxjotr8L2NVVpt58J3lpBWWEXHCH/euWgYQb7ezfY8ERERERERkbakwSUkny9N4/L3l5JTWg1A3/gQ7v5qDfM25fLL+hwe+3EDAxJDmytOaUVcLoOpLyzgyg+WMW9zHobDgbO8os41P6/PYeIzv/P+X7UJqTOOSOSXm4/m2H4NSxJN6l2bAJ2zLhvDMBp0j7OkhIzbbgfDIGTaNIKnTGncB9YI1XYnV7y/lA1ZpUQG+vD+JcMOaSi7iIiIiIiISHvT4KTUWxcN5cQB8Zz1+t+8++d2Hp3Wj0AfL576aRNP/7yZuBA/njtrYDOGKq2F2WxiVNdIAJ7/YjFbxo0j9/HH3Oef+Xkzl7+/lOzSajpG+DPjsuE8cdoAQv2tDX7G0T2isFrM7CioZGtu+QGvNwyDrPvvx5GVhXfHDsTefVfjP7AGcroMbv5sJX+nFBLo48W7Fw/VcH8RERERERGRRmrUsJ0TBsTz9bUj2ZRTxgVvL+bkQQl8d/1ofrxxNA+d3JeIQFWKtBeXj+mM1WJmRZmJVa4gir/+Bnt2NgBT+sTi42XmqqO7MPvGMYzclcBqjEAfL0Z2jQDgp/U5B7y+5JtvKPtxNlgsJDz55AEHrx8swzC4/9t1/LAmG6vFzOvnD6FvQkizPEtERERERESkLWv0oPMQP2+mT+vPopQCbvlsFUf3iOLmid0Pate9kY/NJaO4ap/j5x/ZkYdO7ku13ckj329g1upMbA4XY7pF8dDJfdUm1QrEBPty2hGJfLQolfeHncHEdb8S/s67xNx5B73jg/nzjvFEHmKS8rwjO3JUlwiO7fvvLX+21FRyHnwIgKjrr8Ovf/9Deu5uLpdBQYWNnNJqskqqyS6tZmVqMV8uT8dkgmfPHMiIg0i4iYiIiIiIiAiYjAYO7MkoruLR7zewNbecnnFB3H1cL0L9rbz421a+W5XJPSf0ZlyP6EY9vKC8Budej9+cXc55by3i48uP5KguEdz91Rp+25jLU6cPIMjXm3u/XYvZZOLLq0c0+Bnp6ekkJSWRlpZGYmJio+KTf5daUMm4p+fhdBlYXE5e+PtVJn0zA6+wsBaLwbDb2Xne+VStWoXfEUPo+N57B9wNEKDG4SS3tMadbMrZ9Wv2Xr/mllVjd9b/7fHQSX04/6jkJv5oREREREREpL1qj/mLBldK3fzpSqKCfLjzuJ78vjmfu75aw5sXDuXmid05cUAcd81cyxdL03np3MENfvg/2/1embeNjhH+HNk5nNJqO58tTeO5swa5q1GePG0Axzwzn+WpRQzu0HKJD6lfhwh/zhyaxEeLUhlUlYV/eTFFH3xI1A3Xt1gM+a+8StWqVZiDgkh4/PF9ElIbskr5eX0OWSXV5OyVdCqssDVofZMJogJ9iA3xJSbYl7gQX0Z0iayzE6WIiIiIiIiINF6Dk1JrMkr48cbRdIwI4OjuUYx6/Df3ua7RQXx21VF8tCj1oAOxOVx8vSKDy0Z3xmQysTa9BLvTqDOPqGt0IAmhfizfqaRUa/HQSX25fHRnwpf8QebPRRTOmEH4JZdgCWyamU7lNQ7mrM0mraiSm47pXudc5fLl5L/6KgCx99+Hd0JCnfMOp4sL315MbllNvWtbvczE7Uo2xe5KOMUE+xIbsust2JeoIB+8LY0avSYiIiIiIiIiDdDgpFTfhBCe+Xkzpw5O5M+t+fSMDdrnmnOGdzjoQH5an01ptYPThtSWqOWV12C1mAnx865zXWSglbzy+pMMADU1NdTU7DlfVlZ20DHJgVnMJjpFBmBMmkh+cjK2HTuoWLCA4CmTm2T9vLIabvl8FV5mExeP6ESIf+3Xg7OsjMxb/wsuFyEnnUTI8cfvc+8fW/LJLash1N+bC45KJm5Xoml3xVOovzcmk6lJ4hQRERERERGRxmlwUuqZMwbwyPcbeOi79fSOD+bRaf2aNJBPl6QxtnsUMcG+h7TO9OnTeeCBB5ooKmkok8VC7AMPYAkNwbdHjyZbt1NkAN1jAtmcU85vm3I5eVBtNVT2gw9hz8zEOzGRmHv+r957v1qRAcDJAxO4eWL3eq8REREREREREc9ocF9SYpg/r5w3hJ9vPprnzhp0yMmjvaUXVfLn1nzOHJrkPhYV6IPN6aKkyl7n2vxyG1H/sqvbnXfeSUlJiftt/fr1TRan/LuA4cOaNCG126TetfObflqfDUDJrFmUzpoFFgvxTz6BJTBwn3vKaxzu608ZlLDPeRERERERERHxrAYlpSptjkYt2tjrP1+aTkSgD+N77tm9r29iCN4WEwu35ruPbcsrJ6O4isEd9z9PysfHh+DgYPdbUNC+bYbS/OzZ2RiOxn0d7M+kPjEAzNuUR9mOVLIfeBCAyGuuxn/QoHrvmb02m2q7i86RAfRPDGmSOERERERERERai8olS0i76mq2jB7Dhp69KPvllwPeU7FoMSnTprGxX3+2TppM8cyvWiDS/WtQUuroJ+fx8ryt5JZW7/cawzD4Y0seF769mHf+3NHgAFwugy+WpXPq4ES89hooHezrzRlHJPHw9xtYuC2fNekl/PfzVQzuEKoh561czpNPsnXiJEp/nN0k6/VLCCE22JdKm5PvHnwBV3k5foMGEXnllfu95+tdrXunDErQ3CgRERERERFpc1xVVfj07EHMvfc06HpbejppV11FwLDhdPr6K8IvuICse+6h/I8FzRzp/jVoptQnVxzJk7M38b9fttArLpj+CSHEBPvg42WhpMrOltwylqcW42U2cc3YLpwzvGODA1iwNZ+M4irOOCJxn3P3TO2N2bSBqz9cjs3hYkz3SB46uW/DPzrxCEtgINjtFLz+OsHHH4fJfGi715lMJib1ieH9v3Yyv9KXwQEBxD/5BCav+r98s0uq+XNbbYXdyWrdExERERERkTYocMwYAseMASCjAdcXf/IJ1sQEYu64HQCfLl2oWr6MwvfeI3D0qGaMdP8alJTqEhXIq+cPIaO4ih9WZ7F4RyHLdhZR7XAS7m+lT3wwj03rx9ge0VjMjatKGdM9ih2P7btzGoCvt4WHTu6rRNRhJuyccyh48y1qtmyhfN58gsaPO+Q1j/Yp5wPDRYlPILH33Ys1cd8k5m7frsrAMGBochhJ4f6H/GwRERERERGRw13lypX4H3VUnWMBI0eRM326hyJqxO57AAmhflw+pjOXj+ncXPFIG2AJCSHs7LMoePMtCl57jcBxYw+phc5ZXk7C0/fzYW4hyROPJuTEE//1+pnLd+26pyopEREREREROcyUlZVRWlrqft/Hxwcfn/1v+NZQzrx8vCIi6xzziozAVV6Oq7oas2/TbWjXUIfWVyWyH+EXXojJaqVq1SoqFy85pLVyHn4EI20nMRFBxB6gV3ZDVikbs8uwWsxM7Rd/SM8VERERERERaWm9e/cmJCTE/Tbdg5VMza1RlVIiDeUVFUXIqdMo/vgTCl5/nYDhww5qndIffqDk66/BbCb+ySewBAdTUmkn2M+r3uqr3QPOx/WMIsTf+1A+BBEREREREZEWt379ehIS9nT+NEWVFIAlKhJHQX6dY478AsyBgR6pkgJVSkkzirj0UrBYqFyxAntubqPvt2dmknXf/QBEXnUlfoMHc8m7Sxj88M9szinf53qny+CblZkAnDJo/zOnRERERERERFqroKAggoOD3W9NlZTyHziQyr/+rnOsYuFC/AYObJL1D4aSUtJsrImJJDz7DF1//QXv6OhG3Ws4nWTedjuusjJ8B/Qn8uqrMZlMmKhNPv20Lnufe/5OKSC7tJpgXy/G9Yxqoo9CREREREREpPVxVVRQvWED1Rs2AGBLT6d6wwbsmbXFGrlPP0Pm7be7rw896yxs6enkPPkkNSkpFH70EaWzZxN+4YUeiR+UlJJmFjxpEl5hYY2+r+DNt6hcuhSzvz8JTz6Jybu2FW9SnxgAflqfs889X+1q3Tu+fzw+XpZDiFpERERERESkdatau47tp0xj+ynTAMh97HG2nzKNvOdfAMCRl4c9M8t9vTUxkaRXX6Vi4V9sP+lkCt95l7iHHiJw9CiPxA8HMVNq5GNzOeOIJE47IpGEUL/miEnaKNuOHViTkw94XdWaNeS9UPtNFHPPPVg7dHCfm9ArBpNpDWsySsgsriJ+19dglc3J7LW11VPTBmvXPREREREREWnbAoYPo9fGDfs9H//YvgPSA4YPo/NXM5szrEZpdKXUJaM6MXtdNmOe+I3z3lzEt6syqXE4myM2aSNcFRXsOOdctk09wV1G+G/XZt76X3A4CDp2CiEnn1TnfGSgD0d0rK28+nmvaqmfN+RQXuMgMcyPIR0aX5klIiIiIiIiIi2r0UmpS0d14scbR/PNtSPpGh3I/d+uY9gjv3LvN2tZm1HSHDHKYc4cEFDbfudwUPDOu/96bc5TT2HbuROvuDji7r+/3h32JvWOBeCn9XvmSu3ede+UQQmYzfveIyIiIiIiIiKty0HPlOqbEML9J/Zh0V0TuHFCNz5ZksaJLy7g2Of+4LMlaRiG0ZRxymEu8sorACj+/HMchYX1XmPPyqL48y8AiJ/+KJaQkHqvm9i7dq7U3ymFlFTayS+vYf7mPABOHqTWPREREREREZHDQaNnSu1md7qYsy6bz5ems2BrPoOSQjljaBLZJdU8MWcTC7bm8/zZg5oyVjmM+R91FL59+1K9di2F779P9E037XNN4bvvgcOB/7BhBBx55H7XSo4M4JzhHegTH4zFYuKrFZk4XQYDEkPoEhXYjB+FiIiIiIiIiDSVRiel1maU8PnSNL5dlYnZZGLa4ATumdqbrtF7kgGT+8Ry4osLmjRQObyZTCYirryCjOtvoGjGR0RcdhmWwD1fM87iYoo+/xyAiMsvO+B6j57Sz/373bvuqUpKREREREREpPnYs7LAZMI7tnasTtXq1ZR89x0+XboSduYZjV6v0e17J764gO0FlTx8cj/+vmsCdx9fNyEFkBTuxwkD4hsdjLRtQRMmYO3SBVdZGUUff1znXOFHH2FUVuLTsycBoxq+HeW2vHJWpZdgMZv0NSciIiIiIiLSjDJu/S+VixYB4MjLI/WSS6levYa8//2PvJdeavR6jU5K/X7bON6/ZBjH94/D21L/7f5WL546fUCjg5G2zWQ2E3FZbRVU+dzf3HPHXFVVFH3wIQARl11W73Dz+mSVVPHgrHUAjOkWSWSgTzNELSIiIiIiIiIANVu24NuvPwClP87Gp1s3kj/5mPgnn6Tkq68bvV6j2/cKym3kldUwqENYneMrUouwmE30TwxtdBDSfoRMPR6zny9BxxzjTj4VfzkTZ1ER3omJBE+Z3OC1Xp23jfmb8wG17omIiIiIiIg0N8PhwGS1AlDx118Ejh8HgE/nTjjy8hq9XqMrpe79Zi1ZJdX7HM8preaeb9Y1OgBpX0ze3gRPmYLJqzYfajgcFL7zDgDhl1zsPt4QyZEB7t9P6BnTtIGKiIiIiIiISB0+XbtS/OknVC5dSsXChQSOHg2AIzcXS2hoo9drdFJqS245feND9jneJz6ErTlljQ5A2i+XzUbhBx9iz8jAEh5O6LRpjbp/U/aer7f1WaVNHZ6IiIiIiIiI7CX6llso+vQzdl5wIcHHH49vz54AlM39Db/+/Q5w974a3b5n9TKTV15Dhwj/Osdzy6qxmBs2C0ikas0a0q+7HmdREQDh55+H2de3wffXOJz8uDbb/f5P67IZ1im8yeMUERERERERkVoBw4fR/a+FuMrLsYTsKVgKPeMMzH4Nf02/W6MrpUZ3i+KJ2Rsprba7j5VU2Xli9iZGd4tqdADSPlmTk3GWlGDYbJisVsLOOadR9/+2MY+SKjshfrV51Z/W57gHp4uIiIiIiIhI03NVV2PYbO6ElD0jg8L33sO2fTteERGNXq/RlVJ3H9eLM177i5GPzaVPfDAA6zNLiQzy4dkzBzY6AGmfLEFBWMLCcGRlYQ4Oxhwc3Kj7v16RAcCpgxOZsSiV1MJKNuWU0TO2ceuIiIiIiIiISMOkX3MtQZMmEnbWWThLS9l+5lmYvLxwFhURc8fthJ19dqPWa3SlVGyIL7NvGs2dx/aiW3QQ/RJCuO+EPsy5aQzxoX6NXU7aqaqVK3FkZQHgzM+nctGiBt9bUmln7sZcAE4/IonR3SLxMptYn6m5UiIiIiIiIiLNpXr9evyHDAGgdM4cvCIi6Dr3V+Iff4zCDz5s9HqNrpQC8Ld6cc7wDgdzqwgA+W++CYC1c2dsKSnkv/YaAUce2aB7v1+Thc3pomdsEL3igrl3ah+ePsObED/v5gxZREREREREpF1zVVdjDggAoOLPhQRNnIjJbMZvwADsmZmNXq/RlVK7bckpY96mXH5en1PnTeRAarZto/yXXwGIuef/wMuLyr/+pmrNmgbdv7t175RBCQB0iPBXQkpERERERESkmVk7dKDsl1+xZ2VRsWABASNHAOAoKMQcGNjo9RpdKZVaUMkVHyxlU04ZJmD3aOnd++6lTD++0UFI+1Lw1tsABE6YQOBRRxFy/PGUfPMN5X/8gV+/f99CMq2wksU7CjGZ4MSB8fuctzlcWL0OOtcqIiIiIiIiIvsRec01ZPz3v+Q89hgBRw7Hf9AgACr+/BPfXr0avV6jk1IPzFpHUrg/H11+JKMfn8s3142kqNLOw99v4O7jGh+AtC/27GxKZs0CIPLyy2p/ve5aws4/H7++fQ54/zcra6ukRnSJIC5kzwyzlWnF3PfNWgJ9vZhxWcPaAEVERERERESk4YKnTMZ/yGAceXn49OzpPh5w1JEETTym0es1uqRkeWoRN0/sTniAFbPJhMlkYmhyOLdP7sH9365rdADSvhS+9z7Y7fgfcQR+AwcCYE1KalBCyjAMZu5q3Tt5YEKdc2H+3qxKL+HvlEKKK21NHreIiIiIiIiIgFdUFL69e+PIzcWenQ2AX//++HTu3Oi1Gp2UcroMAn1qC6zCAqzklFYDkBDmR0p+eaMDkPbDWVJC8aefAhBxxeX1XmPPzcWRn1/vuTUZJaTkVeDrbWZK39g65zpGBNAzNginy3DvzCciIiIiIiIiTcdwuch76SU2HTGUreMnsHX8BDYNHUbeyy9juFyNXq/RSakesUGszyoFYGBSKK/NT2HpjkKe+3ULHcL9Gx2AtB9FH3+Mq7ISnx49CBg9ep/zhTNmsG3CMeS//Eq9989cXlslNbF3LEG++w42n9Q7BoCf1mngvoiIiIiIiEhTy3v2fxTN+IjoW26m01cz6fTVTKL+cxNFH84g77nnG71eo5NS143vhmHUjje/eWJ30ooqOf21v5i3KY/7TzhwC5a0T67qagrf/wCAiMsuxWQy7XONT5euGHY7xV98gT2nbrWT3eli1qra7SWnDUrY516ASX1qq6fmb86j2u5syvBFRERERERE2r2Sr78m7uGHCDv7bHx79MC3Rw/CzzmHuIcepOSrrxq9XqMHnR/dPcr9++TIAObeMpbiShshft71JhpEAIpnzsRZWIh3QgLBxx5b7zX+w4fhN3AgVStXknXvPSS9+qr7a2rBlnwKKmxEBFgZ1S2y3vv7xAcTH+JLZkk1C7bkc8yuyikREREREREROXTOkhKsnTrtc9zaqTPOkpJGr9eoSim700WXu35gU3ZZneOh/lYlpGS/DIeDwrffASD84osxedWfCzWZTMQ++AAmq5WK+b9T9OEM97mvdg04P2FAPN6W+r9sTSaTu1rqp/XZTfkhiIiIiIiIiLR7Pj17UjTjo32OF82YgU+PHo1er1GVUt4WM/GhvjhdRqMfJO1X6Zw52NPTsYSFEXrqtH+91rd7d6L/+19yHnmE3CefxH/YMBzJnd1JplP207q323H94sgrq+GYXqqSEhEREREREWlK0bfeQtpVV1Px11/4DRwAQNXKVTiyskh6/bVGr9f4mVLjuvLknI0UV9oa/TBpfwzDoOCNNwEIO/88zH5+B7wn7LxzCTh6DIbNRuattzJneSrVdhedIwPonxjyr/cO6xTOS+cOdldMiYiIiIiIiEjTCBg2jC4//kjQMcfgKi3DVVpG0MRj6PzdLEq++bbR6zV6ptR7C3eys6CCYY/+SmKoH35WS53z39+w765q0n5VLPiTmo0bMfn7E37OOQ26x2QyEf/oo2w//XRCTzuVr9bW7qZ3yqAEtYmKiIiIiIiIeJB3TDTR/7mpzrHqjRsp/vJL4h56sFFrNTopNamP2qKk4Qre3FUldfppWEJDG3yfV0QEXX78kdxqgz8f+xWAkw/Qure3rbnlLNiSx4UjkpXIEhEREREREWmFGp2UuumY7s0Rh7RBVatXU7loEXh5EX7RRY2+3+zjw7eLtmEYMDLejzhTDeB/4OfanBz//B/UOFwc2SWCnrHBjQ9eRERERERERJpVo2dKiTTU7llSIVOn4h0Xd1BrzFyeQefiDG798lEyb78dwzjwkH0/q4XR3aIA+GldzkE9V0RERERERESaV6MrpTrd+T3/1gyVMv34QwhH2oqalO2U/fILABGXXXpQa2zIKmVjdhldvbzwLcqj4vcMij74kPALzj/gvZP6xPDLhhx+Wp/NDRO6HdTzRURERERERATSr7/+X887S8sOat1GJ6VeO29InfcdLoN1mSV8uSyD/0zUi3+pVfD2W2AYBI4fj0/Xrge1xtcrMgDoMrw/MUfdRs5DD5P71FP4Dx+Ob49/byOd0DMaswnWZpSSUVxFQuiBd/0TERERERERkX2ZA4MOeD7kpJMave5BDDqP3efYcf3i6B4TxKxVWZw5tEOjg5C2xZ6T494KMuKyyw5qDafL4JuVmUDtrnthfYZQ8ccCyufNI/PWW0j+/HPMvr77vT8i0IcjksNZvL2Qn9dlc9HITgcVh4iIiIiIiEh7Fz/90WZZt8lmSg1KCmPhtvymWk4OY4XvvQ92O35DhuA/eNBBrbEopYDs0mqCfb0Y1zMak8lE3CMPY4mMpGbLVnKffOqAa0zqXbtT5E/rNVdKREREREREpLVpkqRUtd3JOwu3Exu8/8oVaR+cpaUUf/opABGXH1yVFMDMXa17x/ePx8fLAoBXRATx06cDUDRjBmXz5v3rGpN611b1DU0Ox+ZwAbVfqy7XgYeli4iIiIiIiEjzanT7Xv/752Ay7Rl1bhgGFTYnft4Wnj1zYFPGJoehoo8/wVVRgU+3bgQeffRBrVFlczJ7bTYA0wYn1DkXOHoU4RdeQE3Kdvz69PnXdTpE+DOiSwSXjOqE1as2//rC3C18tCiVYZ3CGdYpguGdwukVF4zF/G/j+0VERERERESkqTU6KXXP1N51klJmE4QHWBmUFEaIv3eTBieHF1d1NYXvvw/UVknt/XXSGD9vyKG8xkFimB9DOoTtcz761lvBYsFkPnCh3weXDq+TcFqRWkxRpZ0563KYs662rS/I14uhyeEM6xTORSOS8fW2HFTcIiIiIiIiItJwjU5KnX5EUnPEIW1Ayddf4ywowCs+juBjjz3odXbvunfKoATM9VQwmbzrJj9tqalYO9Q/YP+fFVDvXjyMNRklLN5eyKLtBSzdUURZtYO5G3NZnlrEFaM7u6+dsy6bMH8rA5JC3C2EIiIiIiIiItI0Gp2U+mxpGgFWL47vH1fn+Pers6iyOzltSGKTBSetX43DydqMUiyGi4IZX2PxCyPpvEuowYyPYTS6Wiq/vIb5m/MAOHlQwr9ea9hsZN3/AKWzZpH8+Wf49ux5wPWtXmaGdAxjSMcwrh7bBafLYENWKX+nFGBzutxJMMMwuP/bdWSVVGP1MjMoKZThncIZ3jmCIR3DVE0lIiIiIiIicoganZR6Zd42Hjml7z7HIwKt3DVzjZJS7cw9X6/ls6Xpte/0OR/6AJuBe2ZjNoG/1Qs/qwV/qwU/79pfA3y83L/3s3rhv/u81cLWnHKcLoMBiSF0iQr894d7e+MsLsaw28m49VY6ffEFZt/GDdu3mE30TQihb0JInePVdheDO4SxaHsB+eU2Fm0vZNH2Qpi7lchAK0+ePoBxPaIb9SwRERERERER2aPRSamM4iqSwvz3OZ4Q6kdGcVWTBCWHh50FFXyxrDYhFW0vp8owUW31x05ttZHLgPIaB+U1jkavfaAqKQCTyUTcww+RctJqbFu3kfvEE8Tee2+jn1UfP6uFl84djGEYpORX1Lb7pRSwcFsBuWU1zFqVqaSUiIiIiIiIyCFodFIqMsDKxuwyksLrJqY2ZJUS5m9tssCk9Xtl3jZcBoyO9uKu1+/H5OdH17m/QnAIlXYnVTYnlTYnlTYHVTYnFTYnVTbHrmN7nbc7qKzZdczuIMTPmzOHNmx2mVd4OPHTHyPtssso+uhjAkaNJmj8uCb7GE0mE12iAukSFcjZwzpQbXfy6vxtXLbX7CkRERERERERabxGJ6VOGBjP/d+uI8DHwvBOEQAsSinggVnrOWFA3AHulrYio7iKL5fXVkmdteEnAEJPPw2vsNrd8oItZoJ9W2Y3xsBRIwm/8EIK33uPrLvvxvebr/GObp4qJl9vCzcd0939vmEY3PDJSo7uHsWpgxMOesdBERERERERkfam0UmpWyb2IL2oinPfXISXeU+b1rRBCfx38oEHTUvb8Nr8bdidBkfG+NL56x/Ay4uIiy7yWDxRt9xMxaJF1GzcSNZdd5P0xustkiD6fk0Ws1ZlMmtVJn9syePhk/sS1ELJOBEREREREZHDWaOTUlYvMy+dM5jt+RWszyzF19tMj9ggEuuZMyVtU25pNZ8sSQPgnMxFAIQcfxze8fEei8lstZLw1JOkXXElYeed22IVS8f2jeO/kyt55ufNfLMykxWpxTx31kAGdQhrkeeLiIiIiIiIHK4anZTarVNkAJ0iA5oyFjlMvPFHCjaHiyFJIXR/60sMIPSsszwdFj5du9JlzmxM3i1XqWQxm7h2XFeO7BzBDR+vILWwktNf/YubJ3XnqjFdMJvVziciIiIiIiJSH3Njb7jqg2W8Mm/bPsdfnb+Na2Ysa5KgpPUqrLDx4d+pAFwaUYFRWYlXXBx+Awd6NrBd9k5I2bOycFW1zI6QQzqG8cONozm+fxwOl8ETszdxx8zVLfJsERERERERkcNRo5NSi3cUMq5n1D7Hx/aIYvH2wiYJSlqvtxakUGV30i8hhP5LfwEgePLkVjfgu2zub6ScdDI5TzzRYs8M8fPmxbMH8fip/Qjy9eLsYR1a7NkiIiIiIiLS/hTOmMHW8RPY2H8A2884k6rV/14cUfjee2ybciwbBwxky9hx5EyfjqumpoWi3Vejk1IVNQ68Lfve5mU2U1btaJKgpHUqqbTz3sKdAFw7qiMVc+cCEDxlsifDqpfJx4qrtJTijz+hbFecLfJck4kzh3bgzzvG15krtWRHITUOZ4vFISIiIiIiIm1b6Q8/kPvY40Reey2dZn6Jb48epF52OY6CgnqvL5n1HblPP0PktdfS+fvviXv4YUp/+JG8Z55t4cj3aHRSqmdsEN+tytrn+KxVmXSLCWySoKR1eu+vHZTXOOgRE8RR+Rtx7Wrd8x0wwNOh7SNw5EjCL74YgKy77saekdGizw/eawe+DVmlnPvmIk55aSHb8spbNA4RERERERFpmwrefY/Q008n9NRp+HTtSuwD92P29aX4y5n1Xl+1YgV+gwcTcsJUrIkJBI4aSfDxx1O1Zk0LR75Ho5NS14/vxgtzt3DzZyv5Ylk6XyxL5+ZPV/LSb1u5fny35ohRWoHyGgdv/7kdgGvHd6V8zk8ABE+a1Opa93aL+s9N+PbujbO4mLRrrsVVUeGROIoqbAT6eLE+q5Spzy/gs6VpGIbhkVhERERERESkdSsrK6O0tNT9VlNPe51hs1G9bh0BI45yHzOZzQQcdRRVK1fWu67foEFUr1vnbvGzpaVR/vvvBI4Z0ywfR0M0Oil1TO8YXr9gCDsLKrnn67U88v16skqq+fCy4UzuE9scMUorMOPvnRRX2ukcGcCx3cMp/+03AIKPneLhyPbPbLWS+OILWCIiqNm0iYzbbsdwuVo8jhFdI/nxxtGM6BJBld3JbV+s5oZPVlJabW/xWERERERERKR16927NyEhIe636dOn73ONo6gYnE4sERF1jlsiI3Dk59e7bsgJU4m6/np2nHseG/r2Y9vESfgPG0rkVVc2x4fRIF4Hc9P4njGM7xmzz/FN2WX0iA065KCkdamyOXnjjxQArhnXleqFf+KqqGi1rXt7846PJ/HFF0i94ELKf/2V4s+/IOzMM1o8jphgXz64dDiv/b6Np3/azKxVmaxILeL5swcxeK/ZUyIiIiIiItK+rV+/noSEBPf7Pj4+TbJuxaLF5L/+OrH33oNf/wHYUneS8+h08l5+mahrrmmSZzTWQSWl9lZe4+DblZl8uiSVNRklpEw/viniklbkkyWp5JfbSAzz46SB8eTe/hzQulv39uY/aBBxjzxM5dJlhJ5yssfisJhNXDO2K0d2juDGT1aQVljFwq35SkqJiIiIiIiIW1BQEMHBwf96jVdYKFgsOP8x1NyZX4BXZGS99+Q9/zwhJ55I2OmnA+DboztGVRVZ995H5FVXYTI3upnukB10UmpRSgGfLklj9rpsYoJ9mdwnlgdP6tuUsUkrUONw8tr82iqpq8d2weKwu1v3glrhrnv7E3LiiYSceKKnwwBgcIcwvr9hNO8v3MHVY7u6j0//cQNrM0oY1TWKUV0j6RMfjNnc+pN+IiIiIiIi0rJMViu+ffpQ8dffBB1zDACGy0XF338Tdu659d5jVFVh+udrTLNl10nPzD1uVFIqt6yaL5al89mSNMprHBzfLw6bw8Xr5w+hW4za9tqiL5dlkF1aTUywD6cNSaRi/jx3655fK2/d2x/D4SDvxRcJO/10vPcqiWxJwb7eXPePjQF+3ZDL1txy/txawONAmL83I7pGMmrXW1K4v0diFRERERERkdYn4qILybzjTnz79sWvfz8K33sfV1UVodNOASDz9tvxio4h+pabAQgcN47Cd9/Fp1cv/AYMwLZzJ3nPP0/guLGYLBaPfAwNTkpd+u4SFm8vZFzPaO49oTdHd4/GYjYxY1Fqc8YnHmR3unh53lYArhzTBR8vC/mz5wC7Wvc8UNrXFHKffIrC996j/Ld5JH80A3NAgKdDAuDV8wazYEs+C7YW8HdKAUWVdr5fncX3q7NICPVjwe3j3O2S1XYnvt6e+UtDREREREREPC/4uONwFBaR98LzOPPy8enViw5vvO5u37NnZoFpz+v2yKuvApOJvOeex5GTgyU8nKBxY4m66SbPfAA0Iik1b3MeF41I5rwjO9IpsnW8iJfm9c3KTNKLqogMtHL2sA64amoonzsXOLxa9/4p/KILKfn+e/eOfIkvPN8qEmxdo4PoGh3ERSM7YXe6WJ1ezB9b8vlzaz7dY4LcCSmny+Co6b+SFO7vrqIakhyGj5eSVCIiIiIiIu1J+HnnEn5e/e16HT94v877Ji8voq67lqjrrm2J0BqkwUmpz686is+WpHHCCwvoEh3ItEEJnDAgvjljEw9yugxe/q22Suqy0Z3xs1oo+3VX615s7GHbugfgHRdH0osvsHPXjnx5z/7PXc7YWnhbzAzpGM6QjuHcdEx3jL36ezdll1FUaaeosoTV6SW8PG8bvt5mhiaHM7pbJKcPSSIswOrB6EVEREREREQOrMHlIYM7hPHYqf1ZfPcEzh3WgVmrMhn+6C+4DIM/tuRTXuNozjilhf2wJouU/ApC/Lw578iOAJTubt2bPLlVVBYdCr+BA4l75BEACt54g+Kvv/ZsQAew9y6HveODWXTXBJ4+fQDTBiUQHeRDtd3FH1vyefSHjVz0zuI6SSwRERERERGR1qjRu+/5W704Y2gSZwxNYlteOZ8tSeOV+dt4fPZGRneL5M0LhzZHnNKCXC6DF+fWVkldMrITgT5ebaZ1b28hJ0ylZttWCl59jex77sXaoSP+gwd5OqwGiQn25dQhiZw6JBHDMNiSW868TbnsKKjkhvHd6iSxRERERERERFqjRiel9tYlKpA7j+vFbVN68suGHD5fmtboNbJLqnnsxw3M25xHlc1JckQAT57en/6JoQAYhsGzP2/m4yVplFbZOSI5jIdP7qe5Vs3o5w05bMopI9DHi4tGJANQsWBBm2jd+6eoG27Atm0b5X8uxFlS7OlwDorJZKJ7TBDdtQOmiIiIiIiIHEYOKSm1m8VsYnKfWCb3iW3UfSWVdk59ZSFHdYng3YuHERFgZfuulrHdXp2fwjsLd/D06QNICvfn6Z82c8Hbi/j5P0dr97FmYBh7qqQuHNGREP/aP4s9rXuH76579TGZzcQ//ji29HR8u3f3dDhNyukysJhVMSUiIiIiIiKtk0ezC6/M30Z8qC9PnT6AgUmhJIX7M6Z7FB0jaqugDMPg7T+3c/34rkzqE0uvuGCeOXMAOaU1/LQ+x5Oht1nzN+exJqMEP28Ll4zsBPCP1r0pngyvWZj9/eskpOy5uRhOpwcjOjRr0ku48O3F3PPNWk+HIiIiIiIiIrJfHk1K/bIhh34JoVwzYxlDHvqZ4577g48Xp7rPpxVWkVdWw8iuke5jwb7eDEwKZfnOIk+E3KYZhsELu6qkzh3egYhAHwAq/vyzTbbu1adyxQq2nzKNvGef9XQoB63S5mD+5jy+XJZOUYXN0+GIiIiIiIiI1MujSanUwko+XLST5IgA3rtkGOcd2ZH7v13HF8vSAcgrrwYgaldyZLeoQB/yymvqXbOmpobS0lL3W1lZWfN+EG3I3ymFLNtZhNXLzOVjOruPl/44G2h7rXv1sadn4CwooODNtyj+6mtPh3NQhnUKp098MDUOFx/tleQVERERERERaU08mmEwDIO+8cHcNqUnfRNCOGd4B84e1oEZi3Ye9JrTp08nJCTE/da7d+8mjLhte2HuFgDOPCKJmGBf4B+te5PbXuveP4WcMJWIq68CIPvee6lcvtzDETWeyWTi0lG1rZfv/7UDm8Pl4YhERERERERE9uXRpFR0kC/douvuGNYlOpDM4ioAogJrEyP/rIrKK6/Zp3pqtzvvvJOSkhL32/r165sh8rZn2c5CFm4rwMts4qqxXdzH67TuDWzbrXu7RV1/PUGTJmHY7aRfdz229AxPh9RoU/vHExXkQ05pDT+uzfJ0OCIiIiIiIiL78GhSakjHMFLyy+sc255XQUKoHwBJ4X5EBfmwcGuB+3xZtZ2VacUM7hhW75o+Pj4EBwe734KCguq9TuravePeqYMT3Z9/gNLZ7ad1bzeT2Uz8Y9Px6d0LZ2Eh6VdfjbO8wtNhNYrVy8wFR3YE4K0F2zEMw8MRiYiIiIiIiNTl0SzDpaM6sSK1mJd+28qO/Aq+WZnBx4tTueCoZKC2DemSkZ14Ye4Wfl6fw8bsUm7+bBUxwT5M6h3jydDblLUZJfy2KQ+zCa7eq0qqtnXvN6B9tO7tzezvT9LLL2OJiqRmyxbyX3rJ0yE12jnDO2D1MrM6vYRl2hhAREREREREWhkvTz58QFIor50/hCdmb+K5X7eQFObHvSf05uRBCe5rrjq6M1U2B3fOXENptZ2hyWG8d/EwfL0tHoy8bdldJXXigHiSIwPcxyv+/BNXeTleMTHtpnVvb96xsSS99BKF739A1PXXeTqcRosI9OGG8V2JCvKhb0KIp8MRERERERERqcOjSSmACb1imNBr/1VPJpOJmyf14OZJPVowqvZjU3YZs9dlYzLBteO61jnnbt2bMrndtO79k1///iQ89aSnwzho143v5ukQREREREREROrVPjMN4vbSb7VVUsf2jaVbzJ75Wy6brd227u2PYRjkv/oqlcuWeToUERERERERkcOeklLtWEpeOd+tzgT2rZKqWNC+W/fqU/ThDPL+9xzp115H9abNng6nwexOFx/8vZOTX/qTihqHx+IwDIO1GSU4nC6PxSAiIiIiIiKth5JS7dgr87bhMmBCz2j6xNedOVQ6+0cAgtrRrnsHEnrqNHz79cNZXEzqRRdRvWmTp0NqEIvJxNsLtrMyrZgvl6d7LI7nft3C1BcWcOfMNR6LQURERERERFoPZRvaqbTCSr5akQHAtePrVknt3boXPOXYFo+ttTL7+9PhzTfw7dsXZ1ERqRceHokps9nExSOTAXjnzx24XEaLx7Aus8Q9UP/zZenM35zX4jGIiIiIiIhI66KkVDv16vxtOFwGo7pGMrhDWJ1zat3bP0tICB3efqs2MVVcXJuY2rjR02Ed0KmDEwny9WJ7fgW/bcpt0WfbnS5u+2I1DpdBsG/t3gp3zVxDlc3ZonGIiIiIiIhI66KkVDuUXVLN50tr27iu/0eVFEDZnNpd99S6Vz9LcHBtYmp3K9+ll+EsL/d0WP8qwMeLs4d1AODtP7e36LNf/z2FdZmlhPp7M+v6UQxIDOG2KT3w9dbXloiIiIiISHumV4Xt0Ou/p2BzuhiWHM7wzhF1zrlsNsp+nQtA8BTturc/luBgOrz1Jn4DBhBz+21YAgM9HdIBXTgiGYvZxJ9bC9iYXdpiz53UO4ZBHUK5/4Q+dIwI4OtrR3LSwARMJlOLxSAiIiIiIiKtj5JS7Ux+eQ0fLd4JwHX1VEnVbd0b2MLRHV4swcF0/GgGISee6D5mGC0/r6mhEkL9mNInFoB3Fuxosed2iwnii6tGcNLAeIA6yajiShs1DrXxiYiIiIiItEdKSrUznyxOpdruYkBiCKO7Re5zXq17jWOyWNy/t+fmsvOcc6lev96DEf27S0Z14pheMUwbnNDszyqqsLl/bzGb9qmM+mV9Dsc8M5+XftvW7LGIiIiIiIhI66OsQzuzIrUYgJMH7ds+pda9Q5P39NNUrVjBzosvabWJqSEdw3jzwiP2adtsatvzKxj1+Fym/7ABu9NV7zXVDif55TZembe1RdsJRUREREREpHVQUqqd2ZBV++K/d1zwPufUundoYu65B78BA3CVlLDz4kuoWrfO0yF5hMtlcPsXq6mwOVmbWYKXuf7ZUcf3i2Ni7xjsToPbv1yD09V6Wx9FRERERESk6Skp1Y6UVNrJLKkGoGc9SSm17h0aS2AgSW+9id/AgbhKSki95NJWm5hKK6zk4e/W893qzCZf+8NFO1m8oxB/q4XHpvXf70Bzk8nEQyf1JcjHi1VpxbzTwrsCioiIiIiIiGcp89CObNjVIpUQ6keIn3edc2rdaxqWwECS3nwDv0GDahNTF19C1drWl5j6dlUmby7YzivztjXpcPa0wkoe+3EjALdP6UlSuP+/Xh8b4sudx/UC4OmfNpNaUNlksXiSYRjc+81aJj/7O1klVZ4OR0REREREpFVSUqod2d261ysuaJ9zFX+qda+pWAIDSXpjV2KqtJTsBx5odbvynTOsAz5eZtZllrJ4e2GTrGkYBnfOXEOlzcmw5HDOP7Jjg+47a2gSR3YOp8ru5K6v1rS6z9XBmLEolff/2smmnDL+2lbg6XBERERERERaJSWl2pE9Sal6Wvdm72rdm6TWvaZgCQwg6Y03CD7xBBJfeH6/LWyeEhZgZdrgRADebqK2uc+WprFgaz4+XmYeP60/5v3Mkvons9nEY9P64+ttJjbElxpH/YPRDxdrM0p48LvaQffnDu/g/jyLiIiIiIhIXV6eDkBazoasMmDfpFSd1r1j1brXVCyBASQ88USdY86yMixB+1aqecIlI5P5eHEqP63PIbWgkg4R/95qdyAWs5lAHy9unNCNTpEBjbo3OTKAubeMJT7U75Bi8LSyajvXfrQcm8PFMb2iefjkvp4OSUREREREpNVSSUw74XC62JxTf1JKrXsto/SHH9g2cRJVq1d7OhQAusUEMaZ7FIYB7y7cccjrnTYkkV9uPppLRnU6qPv3Tkgdji18hmFwx5dr2FlQSUKoH0+dPsBdIbchq5SNu2a6iYiIiIiISC0lpdqJHQUV1Dhc+Hlb6PCP4dNls+cAat1rTobLRdEnn+IsLq7dla+VJKYuGZkM1LbelVXbD2qNvRNIsSG+WBrYtrc/GcVVXPzuEuasyz6kdVraVysy+H5NFl5mEy+cM4hQfysAny5J5bjn/+C+b9Ydlsk2ERERERGR5qIMRDuxflfrXo/YoDpJg9rWvV8BCJ4y2SOxtQcms5mkV17G74ghuMrLaxNTq1Z5OiyO7h7FoA6hnDk0CYez8QmTvLIaTnhxAb9vzmuymD5dnMq8TXnc8/VaSqoOLlHmCVP6xnL6kETuOLYngzuEuY+P7haFt8XMou2FzGvCz5OIiIiIiMjhTkmpdmJ/Q87drXvR0fgNGuSJ0NoNc0AAHV57Df8jjqhNTF16GVUrV3o0JpPJxMyrR3DP1N6EBVgbff99365lbUYpj8/eiMvVNFVA14zrSufIAHLLapj+w4YmWbMl+Fu9ePL0AVz6j/bF+FA/LjyqdifCJ2ZvarLPk4iIiIiIyOFOSal2YndSqndc3SHb7ta9yZPVutcCzAEBJL32aqtLTB2MH9Zk8cOabLzMJp5oxG57B+LrbeGxU/sD8MmSNBZuzW+SdZuDYRjMXptVJ9FU3+fzmrFdCfLxYkNWKbNWZ7ZkiCIiIiIiIq2WshDtxMZd7Xs996qUctlslM3dteueWvdajDkggKTXX8N/6FBcFRVULFni6ZAwDIO/Uwp4+qdNDbq+qMLGvd+sBeDqsV3oEx/SpPEM6xTOeUd2AOCOmWuosjmbdP2m8v5fO7nqw+Vc+eGyf50XFRZg5aqxXQB4+qfN2ByulgpRRERERESk1VJSqh0oqrCRXVoNQM/YPZVSFQsX4iorU+ueB5j9/Ul67VUir7+OiEsv9XQ45JXVcN6bi3hh7lbWZpQc8PoHv1tPfrmNbtGBXDe+a7PEdPuUnsSF+JJaWMmzv2xulmccitXpxTzyfW174VGdIw5YcXbxyGSignxILazk48WpLRGiiIiIiIhIq6akVDuwu3UvKdyPIF9v9/GyH2cDat3zFLO/P1HXXuv+3Luqqki76mqq1qxp8Viig305rl8cAG//uf1fr/11Qw5frcjAbIInTuuPj5elWWIK8vXmkVP6AvDLhhyq7a2nWqqkys61Hy3H5nQxuU8MF+/axfDf+Fu9uGFCN8IDrPh5N8/nTERERERE5HCiTEQ7sH73kPNYte61ZvkvvUT5vHnsOOdcCt5991/bwZrDJbsGdM9alUluWfV+r9u9095lozszaK9d5prD+J4xPHfWQH64YTS+rSSRYxgGt3+xmrTCKhLD/HjitAENnst11tAk5v93LGcMTWrmKEVERERERFo/JaXagQ275kntvfOeWvdan4jLLydo4kSw28l97HHSr7kWR1FRiz1/YFIogzuEYncafPj3/tvLHjipL29ecAQ3T+zeInGdNDCh1SSkAN5duIPZ67Lxtph46ZzBhPh5H/imXbwt5jrViiIiIiIiIu2ZklLtwMbsXZVSe+285951b9Ikte61EpaQEBKef46Ye+/B5O1N+W+/sf2UaVQuW9ZiMVw6qjMAM/7e+a/tcsf0jmnxRJHTZfDWgu1szS1r0efurbjSxlNzaofB33VcLwYkhR7UOrt37Xvzj5QmjE5EREREROTwomxEG2d3utiSUw7sqZRy2WyU/forAMHHTvFYbLIvk8lE+DnnkPzZp1iTk3FkZ7PzggspmfVdizx/cp8Y4kN8Kaiw8e2qTPfx8hoH932zloLymhaJoz6Pz97IQ9+t544v1+BytWxr426h/lY+ueIoLh6ZzEUjkg96naU7i7jqw+U8MXsT6UWVTRegiIiIiIjIYURJqTYuJa8Cm9NFgNVCUpg/oNa9w4Fvr14kf/EFwSeegCUoCP9hQ1vkuV4WMxeOSKZTZAABVi/38Sdmb+S9v3ZyybtLWnzW1W4XjkgmwGph6c4iPly00yMxAPRLDOG+E/o0eI5UfY7oGMZRnSOwOV08+/OWJoxORERERETk8KGkVBu3e+e9nnHBmM21L6LVund4sAQGEP/443T65mu8Y2Lcx2tS/n13vEN10chkfr35aI7vX7sb36KUAt7/qzYJdNuUnoeUjDkUCaF+3H5sTwAe/3EjGcVVLfbsL5alszajpMnWM5lM7o9l5op0NmV7riVRRERERETEU5SRaOM2/GOelLF365523Wv1TCZTnYRU6c8/k3L88eQ+8yyGw9Esz/TxsrgTmFU2J7d/uRqAs4clMbJrZLM8s6HOG96RIzqGUWFzcvdXa1qkamtlWjF3zlzNtJcXNmnyaGBSKFP6xGIY8OSuOVUiIiIiIiLtiZJSbdzunfd6xtbOkyrf3boXFYXf4MGeDE0OQvWqVWAYFLz+OjvPvwB7ZuaBbzrYZ9mdHDn9V3YUVBIb7Mudx/Vqtmc1lNls4rFT+2O1mJm3KY9vVjbfxw+1g82vnbEcu9NgYu8YuscENun6t07ugdkEv2zIYdnOwiZdW0REREREpLVTUqqN292+t3vIeeVffwEQNPEYte4dhqJvvZWE/z2LOTCQqhUrSDllGmVz5zbLs278ZAUlVXYAHp3Wl2Bf72Z5TmN1jQ7k+vFdAXj0hw3UOPa/S+ChMAyDWz9fTUZxFR0j/Jl+ar8mb13sGh3I6UOSAHj8x00em9clIiIiIiKHp8IZM9g6fgIb+w9g+xlnUrV69b9e7ywtJfvBB9k8ejQb+/Vn2+QplM+f30LR7ktZiTYsv7yGvLIaTCboGVvbvlezYwcAPj17ejAyORTBU6bQ6auZ+Pbti6ukhPRrriX70Udx2WxN+pwrj+6C1WLmvCM7ML5nzIFvaEFXHt2FaYMTeO+SYfh4WQBYsqOQOeuyqbQ1TVvjWwu288uGHKwWMy+dM7jZknI3TezGoA6hXD2uS7OsLyIiIiIibVPpDz+Q+9jjRF57LZ1mfolvjx6kXnY5joKCeq83bDZSL7kUW0YGic89R+cffyT2oQfxivHc6z2vA18ih6vdVVIdw/0J8Kn9o7bvTAXA2qGjx+KSQ2dNSiL5oxnkPvMshe++S9H7HxA4egyBo0c12TMGdwhj7QOT8bZ4ZrD5v7F6mXnmjIF1jr35Rwpz1uVg9TIzoksEE3pGM6FXDPGhfo1ef3lqEY/9uBGAe07oTd+EkKYIu15xIX58dc3IZltfRERERETapoJ33yP09NMJPXUaALEP3E/5/PkUfzmTyCsu3+f64pkzcZaUkPzxR5i8a3/obk1MaNGY/0lJqTZs4655Urtb9wyHA1tGBgDWjh08Fpc0DZPVSswdt+M/fBhVK1c1aUJqN6vX4VNM2TU6kA1ZZaQWVjJvUx7zNuVxzzfr6BUXzMTeMfznmG4Nbr/7bEkaDpfB1P5xnDe8Zb9XXC7DPWheRERERESkPobNRvW6dXWSTyazmYCjjqJq5cp67ymbOxe/gQPJfvAhyubOxSs8jODjpxJx+WWYLJYWiryuw+cVpzTa7kqp3UPO7dnZYLdj8vHxaHmeNK2gceOI/s9N7vftOTlkP/QwrooKzwXlAf+d3JP5/x3Lz/8Zw+1TenJExzDMptrvgz+35tdJSC1KKfjXNr9HT+nHAyf2Yfq0pp8jtT/Vdicv/baVqS8saLY5WSIiIiIi0vqVlZVRWlrqfqupqdnnGkdRMTidWCIi6hy3REbgyM+vd117Wjplc+ZguJwkvfYakVdfTeE775D/yqvN8WE0iCql2rD17iHntfOkbDt2AmDtkKQh522UYRhk3XkXFQsXUrFgAfHPPI1fnz6eDqvFmEwmusUE0S0miKvHdqGwwsZvG3MJ9N3zV11xpY1z3lyExWzab5uf2WziwhHJLRq7YcB7C3eQW1bDR4tSuXhkpxZ9voiIiIiItA69e/eu8/59993H/ffff+gLu1xYIiKIe/BBTBYLfn37YM/JpeDtt4i67tpDX/8gKCnVRtkcLrbllQN72vdsqbVJKW/Nk2qzTCYTEVddSU1KCradO9lx1tlE33wz4Rde0C4TkeEBVk4dkljnWFphFfGhvqQVVtVp8wvy8WJgh1BeP/8I/KwtX7rqZ7Vw4zHduPurtbw4dyunH5FEoI/+ihYRERERaW/Wr19PQsKeWU8+Pj77XOMVFgoWC85/DDV35hfgFRlZ77peUVHg7VWnVc+nS2ecefkYNhsmq7VpPoBGaH+vUtuJrbnl2J0GQb5eJIbVVoDsGXKueVJtWcCwYXT++iuCJh4Ddju5jz9O2pVX7beEs73plxjC7/8dx0//GcNtU3q42/zKahz8sSWf//262WOxnXFEEp0iAyiosPHmHykei0NERERERDwnKCiI4OBg91t9SSmT1Ypvnz5U/PW3+5jhclHx99/4DRxY77p+gwdj35mK4XK5j9l27MArKsojCSlQUqrN2pi9q3UvNtg9E8e2c1f7noact3mW0FASnn+e2Pvvw+TjQ8Uff5By8ilUb9zo6dBaBZPJRPeYIK4Z25Uvrh7B0v+byNOnD+DWSd25YXw3j8XlbTFzy6TuALzxewr55fv2jouIiIiIiABEXHQhxZ9/TvFXX1OzbRvZ9z+Aq6qK0GmnAJB5++3kPv2M+/qws8/CWVJCziOPUrN9O2Xz5pH/2uuEnXuOpz4Ete+1Ve4h57vmSQHYUndVSnVU+157YDKZCDvrLPwGDybzllsxXC792e9HfW1+nnJc3zj6JaSwJqOEl37byn0ntJ+ZYCIiIiIi0nDBxx2Ho7CIvBeex5mXj0+vXnR443V3+549MwtMe2qRvOPiSHrzDXIee4zik07GKyaG8PPPJ+Lyyzz1ISgp1VZtyCoD9syTMpxO7GlpgNr32hvf7t1J/vwzHPkFmP1qWzkNlwtHVhbee/UpS+tgNpu4bUoPzn9rMZ8sTuOmY7oT4uft6bBERERERKQVCj/vXMLPO7fecx0/eH+fY/6DBtHp00+bO6wGU/teG2QYhrtSandSypGdjWG3Y/L2xis21pPhiQeYfX2xJu5JQBW+/TbbTjiR4q+/xjAMD0Ym9RndLYpbJnbn+xtGKSElIiIiIiJtlpJSbVBeWQ0FFTbMJugRU9u+t3uelHdSUp1J+9L+GC4XFQsXYlRWknXHnWT+9zac5eWeDkv+4foJ3egcFejpMERERERERJqNklJt0Ibs2ta95MgA99b2miclu5nMZpLeeIOoG28Ai4XS775j+ynTqFq1ytOhyX6kF1V6OgQREREREZEmp6RUG+Ru3YsNdh+z7dyVlNI8KQFMFguRV19Nxw8+wDs+HntaGjvOPY/819+osz2oeJZhGNz2xSrGPPEbS3YUejocERERERGRJqWkVBu0Z57UvjvveXdUUkr28B88iE5ff0XQsVPA4SD/hRew7djh6bBkF5PJhMVswmXA4z9u1PwvERERERFpU7T7Xhv0zyHnALadOwCwdlD7ntRlCQ4m4ZlnKBk1CldNDT6dO3s6JNnLjRO6M3N5Bkt3FvHrhlyO6R3j6ZBERERERESahCql2phqu5NteRXAnqSU4XJhT00DwJqspJTsy2QyEXrqqYSfc477WNW6deRMfwxXTY0HI5PYEF8uHtkJgOk/bmBrbpmHIxIREREREWkaSkq1MVtzy3G6DEL8vIkL8QXAkZODYbOBtzfesbEejlAOB4bdTuYtt1L43nukHHc8xV9/jeF0ejqsduvqo7sQ6u/NtrwKJj77O9fOWE5xpc3TYYmIiIiIiBwSJaXamN2tez1jgzCZTADYdu4EwJqQgMlLHZtyYCZvb6LvuB2vqCjsGRlk3XEn208+mbJfftFcIw8I8ffm8yuPYlLvGAyj9vs8yNfb02GJiIiIiIgcEiWl2pgNWbWtPXXnSe3aea+jWvek4YLGjqXLT3OIuuVmzCEh1GzZSvp117PjzLOoXL7C0+G1O91ignj9giOYfdNoHjmlHxZzbdK52u7kuo+W83dKgRKGIiIiIiJyWFFSqo3ZXSnVe++kVGptpZR23pPGMvv5EXn55XT9+ScirroSk58f1atX48jL83Ro7VbP2GCO6hLhfv/zZel8tzqLs17/mzNe+4v5m/OUnBIRERERkcOCklJtiGEYbMzed+c9e+quSintvCcHyRIcTPRNN9H155+IuuVmgiZNdJ8r++03arZs8WB07du4HlGcf2RHrBYzS3YUceHbiznppT/5aV02LpeSUyIiIiIi0nopKdWG5JTWUFRpx2yCbjGB7uO2HbtmSqlSSg6RV2QkkZdf7p5X5iyvIOuuu0k58SQyb78dW3q6hyNsfxLD/Hno5L78cfs4Lh3VCV9vM6vTS7jig2Uc9/wfVNQ4PB2itBHlNQ5sDpenwxARERGRNkRJqTZkd+te56hAfL0tABguF7a0NEAzpaTpuSor8B86FAyDkm++Zduxx5H94ENq7/OAmGBf7pnamz9vH881Y7sQ6ONFfKgfAT57NjdQW580xsq0Yn5alw2Aw+ni2hnLOf+tRRRWaOdHEREREWkaSkq1Ieuz9m3dc+TlYVRXg5cX3vHxngpN2ijv6GgSn3+O5M8/J2DkSLDbKfroI7ZOmkzuM8/iLC31dIjtTkSgD7dN6cmft4/ngRP7uI9nl1Qz4Zn5fPj3TmocTg9GKIeDNeklnP/WIq6ZsZwFW/LZllfBsp1FLNpeyMkv/cnmnDJPhygiIiIibYCSUm3IBndSKsh9zLZz15DzhHhMXl713idyqPz69aXDW2/S4b338BswAKOqioI33sCeleXp0NqtEH9vksL93e+//9cOUvIq+L+v1zLmid94a8F2qmxKTsm+1maUcN5biyirdjAwKZRBHULpERvEV9eMoEO4P6mFlUx7eSFzN+Z4OlQREREROcwpKdWGbMyu/cn13pVSu5NSGnIuLSFg+DA6fvIxiS+/TOTVV+Hbo4f7XMWixRg2tf14yg0TunH/Cb2JC/Elp7SGh75bz4jHfuWZnzaRV1bj6fCkldiQVcr5by2ipMrO4A6hvHvJMHcLaLeYIL6+diTDO4VTXuPg0veW8sbvKWoLFREREZGDpqRUG1Ftd5KSVw5A7/p23tM8KWkhJpOJoPHjiLrhBvcx286dpF56KduOPY6iTz7FVV3twQjbJ19vCxeN7MT8/47jsWn96BDuT1GlnefnbmXy/35XS5+wOaeMc99cRFGlnQFJtQmpQJ+6FbbhAVY+uHQ4Zw9LwjDgkR828OScTR6KWEREREQOd0pKtRGbc8pwGRDm7010kI/7uG3nrqRUB+28J55jz8jAKywMe0YG2fffz9YJx5D/yis4i4s9HVq7Y/Uyc9awDvx261hePncwA5NCOXlgAj5euzZHMAyWpxa1qeqXdZklvPlHCpuyNQdpf7JKqjjnjdoh5v0SQnj/kmEE+3rXe63Vy8yjp/TjvhN6E+TjxfH941o4WhERERFpKzRkqI3YsNeQc5PJ5D5uc1dKKSklnhMwYgRdfppD8WefUfDeezgys8h77nnyX3+D0FNPJfLaa/AKC/N0mO2KxWziuH5xHNs3FrtzTwJq6c4iTn/1L3rHBXPFmM4c3z8Ob8vh9fOLGocTw8C9C+lf2wp4+PsNWC2buG1KDy4Z2Qmz2XSAVdqXmCBfJvaOYVVaMR9cOowQv/oTUruZTCYuHtmJkwcmEBZgdR+vqHHU2fFRREREROTfHF6vNGS/NmTtO0/KMAx3UspblVLiYWY/P8IvvJCuc+YQ/+ST+PTqhVFVRck332Dy/vcXwNJ8TCYTVq89/xRsyy3H19vM+qxSbvp0JWOe+I3X5m+jtNruwSgPrLzGwXerM7n+4xUMeegXvl2Z6T43uU8s0UE+2JwuHv5+Axe+s5jcUrWQ7s1sNvHIyX359MojCfW3HviGXfZOSC3bWcToJ37jl/UagC4iIiIiDaOkVBuxd6XUbo68PIzKSrBYsCYkeCo0kTpM3t6EnDCVTjO/JOmtN4m5804sgYFAbSI164EHKP/jjzbVPnY4OWtYB/66YwK3TOxOZKAPWSXVTP9xIyOmz+Wh79ZTUePwdIhuhRU2PluSxqXvLmHwQz9z3UcrmLUqk/IaB3+lFLivSwr3Z9FdE3jklL74epv5Y0s+k//3Oz+38+RJakEl93+7DrvTBdQmpoL207LXEO8u3EFhhY3LP1jKq/O36XtYRERERA5INfZtgGEYeyWlgtzHdw85946Px2Rt+E++RVqCyWQicOTIOscq//6b4o8/ofjjT/Dp3p2ISy8h+LjjVEnVwsICrFw/oRuXj+nMtyszeeOPFLbklvPLhhzuOq6Xp8MDoLTazvBHf6nTepgc4c/kvrFM7hPLwMTQOtebTCbOHd6R4Z3CueHjlazPKuXy95fyyCl9OXe4ZzeCKKywsSWnjAFJoe6Ww+aWXlTJ2W/8TUZxFV5mE/83tfchr/nMGQMI9vVixqJUHvtxI5tzypg+rZ97XpmIiIiIyD8pKdUGZJZUU1rtwMtsomt0oPu4bedOQEPO5fBh7dSJ8AsvpOjzz6nZvJnM2+8g99n/EX7BBYSecbq7okpahq+3hTOGJnH6EYnM35yH3Wlg2TWLqcbh5MaPV3LakETG94xu1hlNW3PLmLMuh6ySKh4+uR8Awb7eDEoKo8LmYHKf2kRU95jAOjP16tM1Ooivrh3B0z9t5usVGUzuE9tscR9IUYWN1/9I4b2FO6i0OYkMtHLRiGTOO7Jjo1roGiuzuMqdkOoUGcAVYzo3ybreFjMPn9yX7jFBPPjdemYuz2BHfgWvnX8EUXttwNHUHE4XZpNJc8JEREREDkMmo43X16enp5OUlERaWhqJiYmeDqdZ/LI+h8veX0qPmCDm/GeM+3juM89S8PrrhJ1zNrH33uvBCEUax1lSQtEnn1L44Qc48/IBMAcGkvzZp/h0bpoX0HJoPl+axn+/WA1A56gALh3ViRFdIjEMAwPoEO7vHpCeW1ZNYYUNwwDDANeuf3YMAwwMuscEuSuEMouryCyuosbh4s+t+cxel01KXgUAZhMsufsYIgJrExzVduchVRaVVtvr7DD326Zcju4W1SLJjZJKO6OemEtZdW07pJ+3hSq7EwB/q4Xp0/px0sCmb7vOLqnmzNf/YmdBJR0j/Pn0iqOIDfFt8uf8sSWPa2Ysp6zaQUKoH19ePaJJnuNyGWQUV5EU7u8+duorC9mWV87R3aMY1yOaMd2jCA9QdbCIiIgcftpD/uKfPFop9ezPm3nu1y11jnWOCmDuLWOB2hccj3y/gVmrM7E5XIzpFsVDJ/dt1p+4Ho7qa92DvXfe82xrikhjWUJCiLzyCsIvvojSb7+l4O13ALAmJ7uvcZaWYgkO3s8K0txGd4viyqM789GiVFLyKrj7q7V1zv9x2zh34uDNP7bz+u8p+11rzk1j6BFb+/fXp0vS9vl3wWoxM6JrBJP7xOKzVxLqUFvd9k5IzVpVOyR9VNdInj5jADHBTZ+o2TuJFuLvzbge0WzNLeemY7oxrmc0P6zJ4tX5KWzIKqVn7F7zAZ0uvJpgB8Tc0mrOeeNvdhZUkhjmx0eXH9ksCSmo/fr4+tqRXP7eUrrHBBF9kP9u55RWszKtmFVpxaxOL2FVejGVNifrHpjs/lz2jgtm2c4ivlmZyTcrMzGZYGBSKON6RDOuRzR9E4IPWEEnIiIiIp7h8fa97jGBfHjZcPf7XuY9//F+6Lv1/LYxl5fPGUyQrzf3fruWqz5cxpdXj/BEqK3Wxux9d94DsKXWtu9p5z05XJmtVkJPO42QadNw5OZi2vX3g6u6mm3HHodv3z4EHXMMAcOG4d2hg154tqDYEF/uPLYX14/vxmdL0vjw753kltVgAvjHH0OA1YuIACsmkwmTqfa0ea/fW/aqTArz96ZjhD8Wk4le8cFM7hPLuB5RhzSAuyFqHC58vc0s2JrPlP/9zmOn9m+y1r6SSjtvLUjh/b938vU1I0mODADg0Wn9CLBa3F+3Jw1M4MQB8azJKHEn6QBu+3I1hRU2rhzThSM7hx/U17nLZXDJe0tIya8gIdSPjy8/koRQvyb5+PanS1QgX10zEm+vPa11NocLb4vpgB/Dm3+k8OYf28muZ5dEHy8z2/Mr3P/m3X5sT04YEM+8Tbn8timPDVmlrEgtZkVqMR8tSuWvO8e7761xODXjSkRERKQV8XhSymI2Ex20709qS6vtfLY0jefOGsSIrpEAPHnaAI55Zj7LU4sY3CGspUNtterbec8wDOw7ds2UUqWUHOZMZjPesXsSBJWLF+MsLKRi/u9UzP8dAK/oaPyHDcN/2FACR4/GOy7OU+G2K4E+XlwyqhOXjOq032tuPKYbNx7TrUHrXTSyExeN3P9azeW0IYkMTArlxk9WsC6zlCs/WMbZwzpwz9Re+FsP7p/Kkio7by3YzjsLtlO2a9fCz5el8d/JPYHaz90/mUwm+u81pL2k0s53q7OwOVzM25THgMQQrjq6C5P6xNZJ5h2I2WzizmN7cc83a3n3omF12t+aU4j/nmSiYRjc8vkqLCZ48OS+pORVsGpXFdTK9GLeuOAIukTtmRuXXVqN2QTdY4IYkBjKgKRQBiSF0D0myN0aCrWfx2GdwhnWKZzbpvQku6R6V4Iql8Qwf3cCzOkyGPX4b3SKDKitouoZRY+YICWzRURERDzIozOlnv15M6//nkKQrxc+3mYGdwjjtik9SQj1Y+HWfM55cxGr7ptEiN+e/9SOfGwuF49M5rLR9c+Vqampoaamxv1+RkYGvXv3brM9mZU2B33um4NhwOK7J7gTfI78fLaMGg1mMz1WrsCs3fekjanZvp3SWbOoWLyYqlWrwW53n4u55/8IP/dcAJzFxTiKirAmJ+vFpxxQjcPJMz9t5rVd7YadowJ4/qxB9E0IafAaJVV23l6wnbf/3O6eGdUjJoibjunG5D6xjZ5ZtSO/gjcXpPD50nRqHC6gdqfBy8d05tTBiY1qY2yqVsCDsSa9hJNf/hOnq/7/djxzxgCmDa79dzqzuIr0oir6JgQfdFKwvuef8OKCOsfiQnwZ2yOacT2iGNk1koB6EoUiIiIiLUUzpVrYwA6hPHX6ADpHBZBbVsNzv2zmjFf/Ys5/xpBXXoPVYq6TkAKIDLSSV16znxVh+vTpPPDAA80dequxKbsMw6j9vOxdcbZ7npR3XJwSUtIm+XTqRNQNNxAFuKqqqFq1isrFS6hcvJiA4Xtagkvn/ET2ffdhiYokYOiwXdVUw7B2UpJK9uXjZeHO43oxpnsUN3+2kpS8CvL/5d+cf3K6DKa+8AdphVVAbTLqxmO6MeUgklG7JUcG8PDJ/bjpmO68v3AH7/21kx0Fldz91VrKqh1cdXSXeu8rqbRz06cruOu4XnSLqW0H9FRCCqBfYggfXDKMaz5aTnGlnTB/79rqp8RQBiaF1qmAjg/1I76J2wv7JYbwx23jmLcpl7kbc1m4rYCskmo+XpzKx4tTuW5cV26d3AOorerS3w8iIiIizc+jSalxPaLdv+8VVzuYdNRjc/l+deZBD7C98847ufnmm93v766Uaqs2ZO1nntTO3UPONU9K2j6znx8BRx5JwJFH7nPOUZCPydsbZ14+pT/8QOkPPwDsSlINJfrWW/GOj2/pkKWVG9k1ktk3juHXjbmM3evfqvoqjcprHO7ZUBazidMGJ/H9mkxunNCdY/sefDLqnyIDfbh5Ug+uPLoLny5J45MlqZw1NMl9fn1mKaH+3sSH+lFSZef8txexOr2EzOJqfrxxdIvsKnggI7pG8vedEyiosBEf4tviiZ+kcH/OPyqZ849Kptru5K+UAuZtzGXuplzG9YxyX/frhlwe/n4943vGML5nNMM6hWP18lxCT0RERKStalV16iF+3nSKCmBHQSWju0Zic7ooqbLXqZbKL7cRFbj/XXx8fHzw8dlzvrS0tFlj9rSN2fvOkwKw7dwBaMi5SNQ11xBxySVUrVpN5ZLaSqqqlStrk1Q/zib2/vvd15bOng1mM4FHH43ZR7t8tndhAVZOG7KnbDq9qJJz3ljEXcf1YkrfWMqq7bz75w7eXLCd584a6E5eXTW2M9eP79psSaCAXXO8Lh65p9rPMAzu/noNa9JLOHFgPCl5FaxOLyE8wMrzZw9qFQmp3Xy9Lc0+ZL2hcezeoe/+f0wymLsplx0Flbz9Z20bZoDVwqhukYzvWXt9dDPszigiIiLSHrWqpFRFjYOdBZWcMsiHvokheFtMLNyaz7H9agcWb8srJ6O4isEdNeR8tz1DzoPqHLen7q6USm7pkERaHbOvLwHDhxEwfBhwLa6aGqpWrcK2bRuW4D0J3cL3P6Bq+XLMQUEETZpIyAkn4D90KCaLdusSeGXeNlILK7nqw2VM6BnNstQiiitrZ5l9tSLDnZRqqd3d9q4yKq9x4OtlweEymLk8A4BQf28+vHR4nZ38pH7/rNi667hejOkWydyNtTv65ZXVMGddDnPW5QCw4PZxJIa1zLB4aRpOl8HdX61hZ0ElT5zWv8WG/YuIiMi/82hS6pHv1zOhVwwJoX7kllXz7M9bsJhNnDggnmBfb844IomHv99AiL83QT7e3PftWgZ3CNXOe7sYhsHGXe17PWPVvifSUGYfHwKGDSNg2LA6x/2HDcWemYkjO5uSL2dS8uVMvKKjCT7uOIJPmIpfnz4eilhag/tO6EOQrzev/b6NXzfmAtAlKoAbJnRjan/PtoAG+Xrz8RVHsiqtmNd/TyElv4InT+tP7/jgA98s+wj08WJK3zim9I3D5TJYl1nK3F1tfmXV9joJqbu+WkON3cX4ntGM7h5JsK/3v6wsnvL47I18siQNgGmvLOSdi4Y2agMDkdbC7nRx5mt/UVxl56urR9bZ5VRE5HDk0d33rvtoOYu3F1JcaSc8wMoRyWH8d3IPOkYEAFBtd/LI9xv4dlUmNoeLMd0jeejkvnUGeh9IW55en1ZYyegnfsPbYmLdA1Pc8y4Mw2DzsOG4ysro/N0sfLp29XCkIocPw+WiatkySmZ9R+mcObhKSgAInDCBpJde9HB00hos3JbPjEWpTOodw9T+8VhaUWucNL9qu9M999LmcDH4oZ8pr6ndZdHLbGJocnhtm1/PaLpEBWhgeivw45osrp6xHICEUD8yiqsI9PHilfMGM7pb1AHuFmld3v9rB/d+sw6A584ayEkDEzwckYg0pbacv9gfjyalWkJb/kOdsy6bKz9YRq+4YH68cbT7uKOwkC0jRoLJRI+VKzQbR+QgGTYb5Qv+pPS7WQQfdxxBxxwDgC0tjYxbbiVk6vEEH3ssXlF6USPSHjldBou2FzB3Q20VVUpeRZ3zx/eL46VzBwNQ43CyIrWYiAAr4QFWQv2tSmi2kJIqOzd8vIK+CcFceXQXrnx/GX+lFODrbeaP28YTFaT/J8nhoazaztgn51FQYWPa4ASeOWOgp0MSkSbWlvMX+9OqZkpJ42x077xXd16IbedOALziYpWQEjkEJquVoPHjCBo/rs7x0u++o3r1aqpXrybnsccJOPJIgqdOJWjSRCyBgR6KVkRamsVsYkSXSEZ0ieT/pvZmZ0FFbZvfxlwWpRTW+fc5o6iKs17/2/2+2QSh/rUJqvAAK6cMSuDsYbUt91U2Jz+tzyYiwMd9PjzAqh0AD1KInzdvXzQUE2A2m3j3kqH89/PVjO4WqYSUHFZenb+NggobnaMCePzU/p4OR0SkSSgpdRjbPeS89z923nMPOe/QscVjEmkPQk8/HXNgECXfzaJ61WoqFi6kYuFCsu+/n8Bx44i56068Y2I8HaaItLCOEQFcPLITF4/sREWNA4drTzG6zemiU2QAhRU2SqrsuAworLBRWGED4MjOEe5rM0uquPGTlfusH+TjRXiglXOHd+CKMV2A2k1iPl6cSniAlYhAH3clVniA1d1m2B7VOJz8tC6Hqf3jMJlMdarSfLwsPHfWwDqtlbml1UQE+qh6TVqtrJIq3vxjOwB3TOmJt6U2Sb0jv4LNOWVM6hPryfBERA6aklKHsQ3ZtUmpfYec11ZKWTtoyLlIc/CKjCT8/PMIP/88bKmplH7/PSWzvsOWkkLFH39gCZ7uvrbir78wBwfj2707Jm8NIxVpLwJ86v4Xq2dsML/dOhaoHVRcVFmbkCost1FQYaNr9J4qS8OAIzuHu5NWhRU2XAaU1Tgoq3FQUeN0X5tVUs3D32+oN4ZAHy8uGdWJmyd2B2pbf178bSsRAdbaKqxAK9FBPnSLDmpTVViGYXDv1+v4dGkaK9OKuWdq732u2TshlV9ew+mv/UWv2GD+d9bAdp3Mk9br6Z82U+NwMSw5nIm9a3/wtTajhGmvLMRqMfPLzaHEhjR87q6ISGuhpNRhqrzGwc6CSqC+9j3tvCfSUqwdOhB59dVEXHUVNRs2UJOyHbOfn/t81v33Y9+ZislqxadXT/z69sO3X1/8+vXD2qkTJnPbeSEoIg3jbTETHeS7341bukYH8skVR7nfd7kMSqrsFO5KZMXsdZ/VYuaEAfEUVtRQUL4nieVwGZTXONi78CentJrX5qfs8zxfbzODksI4a1hSmxia/MHfO/l0aRpmE4zpfuCZf+syS8kqrmZnQSXnv7WINy44glB/awtEKtJwR3aO4M+t+dx5XE93UrV3XDB94oNZkVrMQ9+td8+wExE5nCgpdZjalF07Tyo6yIeIwLrzEGy72/c6qn1PpKWYTCZ8e/fGt/een8gbdjvWhEScRcW4SkupXrWa6lWr3ef9Bg0i+eOP3O878vKwREZqty4RqcNsNhEWYCUswEqXf+RYOkT488LZg+ocMwyD0ioHBRU1BPru+a+ev9WLi0cmuxNXBeU2MoqrKKmy81dKAaO7R7qvzSmt5o3fUxjWKZyhyeGEBRweSZqF2/J5YNZ6AO44tidHNyApdXT3KN67ZBhXfLCUJTuKOO3Vv3jvkmEkhPod8F6RlnLakEROHBBfp6rRbDbx8Ml9OeGFBXy/JoszNuc16GteRKQ1UVLqMLV7nlSvf8yTgj1JKW+174l4lMnbmw5vv4VhGNh37qRqzVqq166p/XX9eny6dnFfa9hsbB0/AXNQUG0l1V4VVV4REf/yFBGRukwmEyH+3oT4120Zjg/1474T+tQ55nIZbMsrZ/GOQoZ32vN3zaLthby5YDtvLqidYdMtOpChncIZlhzO0E7hrTJhk1ZYybUzluN0GZwyKIHLR3du8L1HdYngi6tGcOHbi9maW860l//knYuG0Tt+3/9niXhKfW22feJDuHhkJ95asJ17v1nLnJvGqAVVRA4rSkodpvaXlHIUFeEqKQHAmpTU4nGJyL5MJhPW5GSsycmEnDAVAMPhwFVZ6b7GlpqKYRg4CwupmP87FfN/d5/zio8j/Lzzibjk4haPXUTaNrPZRLeYILrF1B0F0CHcn7OHdWDJjkK25pazZdfbR4tqf/D16nmDmdI3DoBquxMfL7NHqzwrahxc/v5Siirt9E8MYfq0fo2Op0dsEDOvGcFF7yxmc045Z7xWWzE1pGNYM0Ut8u+cLoPL31/Kcf3imDYoAfN+BvH/Z2J3vl+dxc6CSl7+bSs3T+rRwpGKiBw8JaUOU3uSUnX/E7l75z2vmJg6c21EpHUxeXlhCd6TVPbp2pUey5ZSs3FjbSXVmjVUrV2LLSUFR2YWhtPhvtZVXU3N1m349e1T39IiIodsYFIoA5NCgdpdApfsKGTJ9kKW7ChkbWYpA5P2JGreWrCdN/9I4YjkcEZ0ieCsoR3ws7ZspcZf2wrYnFNGZKAPr50/5KArReJD/fj8qhFc/v5S8stq6BQZ0MSR1s/pMlibUYLFbKJbTCA+Xqp0EZi5PJ25G3NZsqOQCT2j99tGG+jjxX0n9ObqGct5dX4KJw9KoHNUYL3Xioi0NkpKHYZcLoONu2ZK/bNSSvOkRA5fZh8f/AYMwG/AAPcxZ3k51WvX4Z2Y6D5W+sOPZN11F779+hF29tkEH3csZl/tuCMizSM8wMrkPrFM3rXlfKXNgb91z38hV6QWU1Rp5+f1Ofy8Pod3/tzBY6f2Y0SXyP0t2eSO6R3DOxcPI9DHi7iQQ/uhXIifN+9fMoziSjvhzThLq9LmYMGWfH5en8PcjbkUVNgAeOK0/pxxRG21e1ZJFSl5FfSKC27WWP7NVyvS2ZhdRkZRFcM7hXPakKQWTzq2R1U2J0//tBmAa8d1PeBctyl9Y5nSJ5a+CcEkhOkH0yJy+FBS6jCUVlRJpc2J1ctM53/8BE8774m0LZbAQAKOHF7nmD07C5O3N9Vr1pC1Zg05jz9O6CmnEHbWmViTkz0TqIi0G3snpABePncwazNLWLy9kPcW7iC1sJJz3ljE2cM6cOdxPQn29d7PSofOMAx3m15TDnj29bYQG7In8fLRolS25JZxz/G999tC1VAbskp5as4mFmzNp8bhch8P8vXCbDLRe68fOP68Pod7v1kHQFyIL73igukdF0zv+NpfO4T7H1I8LpdBRnEV2/LK2ZZXwba8cgzDYPq0/u5rXp2Xwqac2h+Gfrc6i2d+3sz5RyVzwVEdifzHZjvSdN7+czvZpdUkhPpx0YjkA15vMpl45bzB2ixFRA47Skodhna37nWPCcTLUnfgoW3nTkBDzkXasqhrriHsrLMo/vJLij/5FHtGBoXvvkvhu+8SMHIkSa+8jMl6eOyUJSKHP6uXmcEdwhjcIYxzh3fgsR83MmNRKh8vTqXK5uB/Zw068CIHYVN2GXfMXM2zZwwkuRnb7NIKK7n3m7U4XAa5pTU8fcaABrcHGobB5pxyDAx6xtYmm6xeZn7dmAtAYpgfE3vHMLFXDEM7heP1jwST2WSiY4Q/OwsqySqpJqukmrm77gX49IojGd65dkB9Sl45ZdUOesQG7ROfzeGqMyT70R82sGBLPin55VTbXXWu9fO28MjJ/dzJrqn94ziqIoJQf2++XJ5OWmEVz/+6hdfmb+PacV25YUK3Bn0upOEKymt4Zd42AG6d3L3BX297J6TsThd2p2ufJLKISGujv6UOQ+uzdrXuxda3815tUsraQe17Im2ZV3g4kZdfTsQll1CxYAFFH31M+e+/g2HUSUg5y8uxBGquhIi0jCBfbx45pR9T+8fz4HfruaWZBi4XV9q4/P2lpBZW8tiPG3n1/CHN8hyApHB/njlzILd8tpLv12SRV17DG+cfsc/uhrvZnS6W7Cjkl/W5/LIhh9TCSo7rF8vL59bG2CUqkPtP6M2RXSLoERP0r5Ut5x3ZkfOO7EhZtZ2N2WVsyCplfWYp67NK2ZRdRq+9dgf88O9U3v5zO2ZT7TN6xAZRXuNgW145pVUOVt470f2slLwK1u/6Iae3xUSnyAC6RAXWvkUH4DQMzNRee/1eSafrx3dj9tpsXv99G6vSSwjx2/M52Ltq7XCWWlDJIz+sZ21GKc+fPZAhHcNbPIbnf91CeY2DvgnBnDQgodH3r0or5vYvVzM0OZyHTu7bDBEK1FYarsssZXNOGaO7RxIdpFEK4hmFM2ZQ+NbbOPLz8enZk9j/uxu//v0PeF/J99+TecutBE6YQNJLL7ZApPVTUuowtLtSqmfcvkkp++72vWQlpUTaA5PFQuDRRxN49NHY0tNxVezZ0c+ek8u2yZMJHDeWsLPPxn/o0DbxgkFEWr+jukTwww2j6vyd8+ScjfSJD+G4fnGHtLbD6eK6j1aQWlhJYpgfj07rd6jhHtCJA+KJDLBy5QfLWLy9kNNfW8i7Fw8jPnTP7J4f1mTx07psftuUR0mV3X3c6mXGYq5b2X7RyE6Nen6QrzdDk8MZmrwnQeJwuupUzHtbTEQEWCmosLl3S9xbXlkN0cG1L5ovG92Js4Ym0SU6kKQwv30q7/fHYjZxfP84jusXy6LthfRPDHGf+3J5Bh8t2skVY7owsXcMlkNsc/SUmSvSmbMuB4BL3l3KF1cdtc/ulM0pt7SaGbt2ubzruF4H1Z5ZYXOwMbuMTTllnDYkkQG7Ni2QQ1dWbWfBlnzmbsxl3uY88spqAPjy6hFKSolHlP7wA7mPPU7s/ffjN6A/he+9T+pll9Plxx/wiojY73229Axyn3gSvyOa74c6DWUyDMPwdBDNKT09naSkJNLS0kjca1Dw4WzU43NJL6rio8uH1xki6iwpYfPwIwHosXwZZn9/T4UoIq1A0WefkX3vfe73rV27EHbW2YScdCKWoJb7D7aIyNIdhZz26l8ATOkTy4Mn9znoF3APfbeetxZsx99qYeY1I9xtcS1hQ1YpF72zmJzSGuJDfPngsuF02bXL2ckv/cnKtGKgdjj8+J7RHNMrhjHdI1ushcowDHLLatyVVMG+3nSJCqBLdCARAdZm/cHEiS8uYHV6CQCdIgO4dFQnThuSeNA7IbYUwzAoqbIT6l9bZVxtd3LXV2tIyatgZVoxcSG+zLxmxCEP0G+MJTsKmbsxl9un9DzoNf7z6Uq+WpFB34Rgvrl21GGXJKy2O/Eym9wJ02U7C5mxKJXBHcIY1CGUHjFBDU6mNoV5m3J5/fcUluwoxO7c8/I5wGphZNdIXr/gCPexjxen0jHcn6O6ROiHgdJojc1fbD/jTPz69iX23nsAMFwuto4dR9h55xF5xeX13mM4new873xCT51G5dJlOMvKVCklDVdabSe9qAqgziBM2LPznldUlBJSIkLYGWfg168fRR9/QsmsWdi2biPn4YfJfeYZQqZOJer66/CKarrBwCIi+9MvMYQbJnTj5d+2MntdNn+lFHDP1N6cOjihUS/avliWzlsLtgPw9OkDWjQhBbW7Hs+8ZiQXvb2Y7fkVRAbsGfR99rAkhncKZ2LvGAZ1CPNIEsBkMhET7EtMsC/jekS36LPfvPAI3l+4kw/+3sn2/Ar+7+u1PPPzZi44qiPnH9mRiFY4FH1LThn3z1pHcaWdb6+rTdz4elt45oyBFFXYOO3VhWzLq+DCtxfz+ZUj9tuy2dT+WRV3MO46rhe/bshhbUYpH/y1o9HVeZ5Q43Dy++Z8vl+dyS8bcnnlvMGM7lb7/5QFWwqYuTyDmcszAPC3WuifGMKgDmEMSgplRNdIAn2a5qVttd3Jou2FdI4MICm89jVVeY2DhdsKgNqk67ge0YzvGc3QTmH4eO1JvBZX2nhw1nqq7E76JgRz+ejOHN8vrkUTaNI2lJWVUVpa6n7fx8cHH5+6f48aNhvV69bVST6ZzGYCjjqKqpUr97t2/ksvY4kIJ/S006hcuqzJY28sfXccZjZl186Tigvxdf9EZ7c9O++pdU9Eavn26kXcgw/Q7ff5xPzf/2Ht0gWjspKSb7/FtNc/bOW//07lkiW4amo8GK2ItFU+XhZuntidb68bRb+EEEqq7Nz6+SoufGcJGcVVDVpjRWoRd81cA8ANE7px7CG2AR6shFA/vrhqBBN6RbM2s8R9/MyhHbjzuF4ckRx+2FWlNIXoIF9undyDhXeM5/4TepMY5kdhhY3//bKFWz9f5enw6iittvPQd+s59rk/+HNrAVtyy1mbUVLnmrAAK+9dMoyYYB8255Rz5YdLac4Gk9oqt+omWy8qyIfbdlVaPfXTZnJKm27tplTjcPLrhhxu/nQlRzz0C5e/v5SvV2ZSXuNg/qY893Vje0Rxw/iujO4WSZCPF5U2J3+nFPLKvG1c8cEy0gr3jC/YmF3KyrRi/R44JQAAWExJREFUbA5XfY+sV1ZJFR8tSuWy95Yy6MGfufDtxXy9IsN9fnS3KO6d2pvfbh3Lb7eO5d4TejOqW2SdhBSAw2XsqhA0szajlBs/WcnRT87jrQXbKa9xHMJnStqb3r17ExIS4n6bPn36Ptc4iorB6eT/27vv+Kiq/P/jrzslM5PeGykQSugoUkSaUgRUVgVFERVW/Sq72Lvuqiju6tp/Yll3RXDta1vRFRRxbShdFKSo1AAJCSGB9Gn398eEgTGhaUgIeT8fj3lk5pwz9547mZvJ/cw5n2P9xTQ9a2IC3p07691u5bJllL79NmnTph2Nbv8qGinVzOzNJ9WpnnxSe5Oc27O18p6IhLJGRRF/8QTiJlxE5eIluDdtwhq97+9I4cMPU/PTzxh2O84e3Qnv3ZvwXr0IP+EELBFHb1UrEWlZOqdH8+4fT+GfX27k8U9+5Isfi7jguW/47OZTDzmSoFWsiy6tokmKdHB9E6/4FhNu57lLeh26YQsU4bAxqX8bLj45m7k/FPCPLzaEjNLZWV7D5uKKJkkg7vebvPPtNh6cs5ad5YEvYYZ3TuGuMzuTlVB3lkFGXDgvXtaHSS8sYfLgtkd1KtacVQXc+O8VXDOkPVNOa9cg27yoTxZvLdvKirxSpn2wmqcu6tkg220o+burOP3xLyir3hesSY12cmb3NM7snsYJGbHB8h6ZscHcWH6/yc9F5Xy7pYRvt5SyJn8PHfbL+/XPLzby9vKthNksdGsVw4mZsfTMDkz7238aZlm1h79/vp5P1xYFr7H2Sol2YN9vxcoYl53LBhx6tFlipINp53TlhuEdeOmbzfzrm01sK61i2ger+X+f/MiT40/k1EYexSjN0+rVq2nVat9CB78cJfVr+Mor2H7rbaRNuw9bXNxv3l5DUVCqmQkmOU+tmw/Gs1kr74nIwRmGQUTfPkT07RMsM71eHO3b4y0txVe0k6qly6hauoxiAKuVqOHDyXji8Sbrs4gcX2xWC384tS2nd0nhtre+55J+2Yc1tSU52slr/3cyPr/5q5I/S+OyWS2c1T2dM38xom3Wgk089b+fOSk7jtHd0xjYIYmcxIijnntnV4WbK15cwvItpQDkJEZw9+jOhwwQdEyN5rNbTj2qubHcXj9/m7uWao//iEb3HIrFYnD/OV353VNfUVRWQ7XH12Q5vjw+P1+vLya/tIoL+wS+QE+NdpIY6cBlt3JGtzRG90jjxMy4Q57fFotBh5QoOqREcUHvul/Gu8IsxIbbKa30sGxzCcs2l0DttN/0GCf/u+VUHDYrDpuVF7/eTHmNF8OAEzJjGZKbzGkdk+mSHv2b3pPxEWFcN6w9Vw3O4Z3l23j+yw3klVSGTDl2e/2E2TRxSeoXFRVFdPTBp6jb4mLBasVXXBxS7ttZjC0xsU57T94WPNu2kfeHP+4r9Af+5qzp0pW2cz4kLKvxB7goKNXMrM4PTN+rd6RUcPqeRkqJyOEzbDZaPfYYpmni2byZiiVLqFq6lIolS/Buzw/JUWf6fGy+5FKcXboERlL1OumgK3uIiBxI26RI/n1VP/a/7vvohwI27azg8gFtsFktmKbJ8i2lnJQd+Eb3WE+aLXX98sK+xusjzGrZFywgMApuQLtEBnZIZGSX1KOSfyfWFcgHFR5m5dqh7bmsf5vDDgjs/77buLOCz9cVNmiOplcWbWZzcSWJkQ6uHJTTYNsF6Noqhnf/2J/uGTGNnnTb6/PzzYZi/vt9PnN/KKC00kOUw8Y5J7bCabdiGAavXNGX1Ghngwaa7z+nG9PO7sqm4kqWby7h27zAiKq1BWVEOm3BKXdhNgs3DO9AXLidwR2SjkreM6fdykV9s7iwdyar8/eQGrNvgYcrX1oa+Dkoh345SoouR84IC8PZpQsV3ywkatgwIJDovGLhQuImTKjTPiwnhzaz3wspK/p/T+KvqCDlzjuwp6Y2Sr9/SUGpZsTnN/mx4CBBqS3KKSUiv55hGIS1bk1Y69bEnX8+AJ5t2zB9vmCb6rVrqVq+nKrlyyl56SUAwtq2JbxXL5ydOxN+Uk8c7Rpm2oGIHP/2vxDdU+3hT++uYmd5DR+uzOdv53Vnwc/FTPtgNVef1o6bR+Q2YU+lofzpzM7838Ac3vl2G1/+VMSSjSVsK63ijaV5zF9bGDKyan1ROZlx4b9qNInPb/LvpXmM7pFOpMOGxWLwyPk9CA+zhQQGjsSuCjfnPfs1xRVu7DYLE/r+9v+5d1d5eHL+TwDcMLw9EQ2UrHt/e6e9NZYlm3bxzvJtfPRDAbsq3MHyxMgwRnVNo9K9b8RWeuzRWdXQMAzaJEbQJjGCsScFVjCrdHsp2B2aW+vyw5iS1xAsFoOurWKCj7eXVvHFj0X4TfhsXRFdW0Vz5aC2nNH16ARl5fiVMGki22+/A2fXrri6d2PXi//CX1VF7JhzAdh+223YklNIvulGLA4Hzg4dQp6/d0XuX5Y3JgWlmpHNxRVUeXw4bBbaJIbmePGVleHbtQsAe6ZGSolIw7DvN5cdICwri1ZPPE7l4iVULl1KzY8/4l6/Hvf69QAk33JzMChVs349BdPuJywzA3tmVuBnRiZhmRlYYhr/G1sRObZFOWzcOiKXaf9dzXdbdzN6+lf4/IHE0nERYYd4tjQnydFOJg9uy+TBbaly+1i0sZgvf9pJeJg1+Nng95tc8NxCqtxeTs5JYGD7xMOe6rdk0y7ufu8H1uTvYVNxBXeM6gRATlLkb+p3fEQYE07O5sn5P3HXf1aRGOlgRJffNrLg2c/WU1LpoV1yJBf0yvxN2zqUsmoPT3zyExP6Zv3m1+JgPlm9g9cWB74sT4gIY2TXVM7snkbfNglNughAeJjtqB73kUiPdfHpTacy46uNvLksj1Xb9nDta9/yt1gXlw1ow0V9snCFaWSoHFr0GWfg3VVC0fQn8RXtxNGpE1n//Edw+p5nez4Yx3agU0GpZmRN7dS93NSoOn/Q907dsyYmYo1UUmIROTqsUVFEjxxJ9MiRAPhKS6lcvpzKpctwr1+Po2PHYNuaDRuoXLiQyoV1t2OJiiLl9tuJHTsGAG9JCdWrVxOWmYk9LQ3D3jjLbovIscMwDMb1zmRwbhJ//s8q5q3eAcB5J2VwWf/WTds5OWpcYVZOzU2uk9upYE81pmlS4fYxf20h89cWAoGpfgPbJ3JW93QGtA/NmbJjTzUPfLiG/6zYDkC000ZWfN0E5r/FDcPaU1RWzWuL87jmtW95+fK+9Gnz65K2byut4oUFgVxHt4/seNRHyNzz3g+88+021hbs4eXL+zbIl0M+v8kH328nOyGCE2pHZF0+sA17qj2c2S2dk3PiNfLnAFonRhwwKXqYzcIlJx+/s19M02R9UTlLNpWwq8KNw2bBYbfSKtbJkI4pwXbLNpdgMQIruDrslkC7X9wXiL94AvEX152uB5D90r8O+tz0B+uu6tfYFJRqRoIr76XWnbrn2bI3yblGSYlI47HGxhI1ZAhRQ4bUqXN160bagw/gyduKZ2se7rytePLy8BYV4S8rC1nVr2r5crZOuTrwwGLBnpaGs3s3IgcMJGLAAOwpWqlGpKVIiXbyj0tO4qMfdrC+qJzLB7TRyMoWKD3WxZI/DWNNwR6+/GlnyFS/15fkERseFgxKVbq9PPbxj7y2eAsVbh+GARf2zuTm03MbPE+QYRhMO7srRWVuPlmzgyteXMKbk08ht55FiA5lRW3S9b5t4hna6eh/zl03rD3/XZnPgp+Lmf3dds4+odWhn3QAHp+fd7/dxrOfrWfjzgoGtk/kpcv7ApAc5eSBMd0bqtvHvf2Tor+9fCuzV2xnXK+MYH3+7ipSoho271ZTqfH6uPrVb1m6aRcllZ469f1yEkKCUpe/uITSetpBYFrqe1P6Bx+f/dRXYBghZdI8KCjVjASDUml1P/SUT0pEjjX21FRizzmnTrm/qgrP1q3YUvb904FpEtauLZ68rZg1NXi2bcOzbRtlc+YC0OqxR4k+44xG6rmINDXDMBjZtWkSrsqxw2Ix6JIeQ5f0mDpT/UZ02fcZsmjjLp6vXV3txKxY7v1dF7pnxB61ftmsFp666EQufn4RSzeXMPGFxbz9x1NodYT5kc7snsYJWbFUe3yNEnjNTohgymnteGzej0z7YA2n5iYT4zqykcnVHh9vLs3j759vYFtpFQCx4XZ6Zcfj18qYv4nTbmVC3+yQXGVen58Jzy/CabNyy8hcTu2Q1CyC9BU1XpZvKWHJphI8Pj+3jQyMpHfYrKwrKKOk0oPTbuHEzDgy4ly4fX5qPH46/CK4mxHnIsppo8bjp8brp8bro9rjr91W6Ai8baVVGjnVTCko1YysPViSc628JyLNhMXlwtG+fUhZ1LBhRA0bhmmaeIuKcG/cROWihZR/tYDqlStx9egRbFv61luUzfuEiAEDiBw4AHt2drP4B01ERH6bA031K6lw0ys7jgt6ZzK2Z0ajBEacdivPT+zF+X//hgiHDdevXBnySANZv9VVg3P4z7fb2LCzgkc/Xsd9Z3c97Oe+vWwrD85dS1FZDUDtaoFtmNA3+6gkaBf4cUc5RXtqKKvx8vuZS+jTOp5bR+bSq/WvmzJ6tBSV1bBs8y4WbyxhyaZdrM7fE8wJGOWwcfPpucH0M/ee3YUYl52u6TGHXMTgg2sG1ikzTRO3zx/c/l4vX9EXv7+BDkgalf56NBO7Kz3BbyM61huU0vQ9EWn+DMPAnpyMPTmZiL59SLr2Wny7d2ON2bdiTdkn8yn//HPKP/+cHYA9I4OIgQOIHDCA8L4nK6+eiEgLM6ZnBmN6Zhy6YQOLDQ/jlSv6Eum0ER52+JdVyzbvwjAMembFHcXe1c9hs3L/OV256PlFvLRwM2N7Zhz26nxev5+ishpaxbq4anAO43plBlfRk6Ojc3o0X9x6Gs9+vp5ZX29i8aZdnPf3bxjaMZmbR+TWO1jhaDNNk60lVWTul6/thjdW8NXPO0PatYp10adNPL1ax+Hx+bFaAu+V03J/21RVwzDqHRHVsZ4UN9I8KCjVTKwpCEzdaxXrqneY7d7pe/YsTd8TkePL/gEpgKQbbiC810mUf/kVlcuX49m6ldLXXqf0tdcxwsPp8M3XWBwNm0NERESkPsnRzpDH/1tbyMD2iQdM7u3zm9z5zirW7Sjj0fN7MPakxg+mndIukbNPSOe9Fdv529y1vPp/J9dpU1xewwsLNtIuOZJzTwz08dwTM7BbLZzVPf2QI1yk4cRFhHHnGZ34ff/WPDn/J/69dCvz1xby6bpCPrx24FEPTPn9Jj8XlbNoQzELN+5i8cZdgZFRfx4WzNnWp008O8tr6N06EITq3Tqe9EYeBSjNl4JSzcTB8kn5yivw7QxEpjV9T0SOd87cDjhzO5BwxRX4KyqoWLSYiq++ovyrr7CnpoYEpPKumow1NoaIAQNw9eiBPSMDw6J/pEVEpOE9/b+fefijdYzrlcHfxnavd2r528u2sm5HGTEuO8M6pdSzlcbxpzM74bRZuWlEh5DyHXuq+ccXG3h10RaqPD4y412M7p6OzWohzGZpkhFpEpAW4+KBMd35v4E5PDrvR3aVu+m4Xw6mGq+vQXMqffXTTl5auCm4Qt7+wqwWftxRTr/aoNQ1Q9px7dD29W1G5JAUlGom1uYfOJ+UJy8wSsoaH4816shX/hARaa4sERFEDTmNqCGnAYEg/V7e4mLKP/8cgN3vzQ60Dw/H0aEDjtxcIk45hegRpzd+p0VE5LjUISUKiwH/XrqV5CgnN4/IDamvdHt5dN46IHARHxN+ZEnGG1JylJO/nbdvhby8XZX8/fP1vLl0K25fIDFPt1YxXD2kHRblbTym5CRF8vRFPanx7kuQX1LhZsQTXzD2pAwmD2p7RO8tr8/P6vw9LNqwi6GdkslJigSgYE81H/2wAwCX3cpJ2XH0bRNPnzbx9MiMDZm6qdye8lsoKNVM7J2+V3+Sc+WTEhEBQvJJWaOjyZo1i4oFX1Hx9TfU/PQT/spKqlasoGrFCkyvJxiUMt1utt54I4727XHm5uLIzSUsKwvDqlwZIiJyeIZ3TuGv53bj9ndW8tT/fiYpysHEU1oH62d8uZEde2rIiHNxSb9jJ+VGwe5qLvzHwmD+2t6t47h6SHsGtU9UsOEYtv+oqP+s2EZhWQ3PfraeVxZuZvKpbfn9KW1whdX9P8bj87Nq224WbdzFwg3FLN1UQnmNFwDDIBiUGtAukVtH5tK3TQLdWh06KbnIr6WgVDPg9flZp5X3RESOiGG3E3FyXyJO7gs3gen14t60iep166hZ9yOuE04Itq3ZuJHyT+ZT/sn8fc93OnG0b48jtwPRI0YQObDuCjAiIiL7u7BPFoVlNTw270emvv8DiZEOzuyeRlFZDX//fD0At4zIPWaWrvf7Tab9dzXbSqsY2D6Rq09rR9+chKbulhyhSae0JiMunEc+Wse6HWU8NHcdsxZs4pqh7bmwdyb22hxna/L3MPbZr6l0+0KeH+Ww0btNfEjy8tQYJ388tV2jHoe0TApKNQObiiuo8fpx2a1k7feHYi/3lsBIKXv2sfONi4jIscaw2XC0a4ejXTs488yQOlt8PCl/+hPV69ZSs+5Han76CbO6muqVK6leuZKwzKxgUMq9dSsF06YR1ioDe3oattQ07Olp2FNTsSUnY9j00Soi0pJdM6QdRWU1vLRwMze8sYK4CDsfrsynwu2je0YMo7unN3UXgywWg6tPa8fVp7VrkpXcpGEYhsHwzikM6ZjMeyu28di8H9laUsVd/1nFyq2lPHReDwDaJEbg9ZnEuOz0aRNP3zbxnJyTQKe0aKwWjYqTpqH/nJuB1bX5pHJTo+r9Y7Fv+p6CUiIiv4YtKYn4Sy4OPjZ9PtxbtgQCVD+uI+KUfsG66h9WU/H5F1TUtyGLhdS7/kzc+PEAeAoKKPtkPva0VOxpadjS0rDGxmo6hIjIccwwDKb+rgs7y2uYs6qA1dv30CMjlnnRO7jzjE5YjrGLfwWjjh9Wi8GYnhmc1T2d1xZvYfqnP7Ny255gvdNuZd6Ng8iMCz/m3ofSciko1QyszT9wPikAj6bviYg0KMNqxdGmDY42bWDkiJA6Z5cupE6diic/H29BPp7t+Xjy8/Hs2AEeD9aYmGDb6tWr2XH//aHbdjqxp6VhT0sj/veTgiOwTK8XDEN5rEREjgNWi8HjF5zAeSftZGjtKnu/OyH9mJm2J8e3MJuFiae05oLemewsrwmpy06IOMCzRJqGglLNwJraoFTntLor6/krK/EWFQFKdC4i0hjCMloRduEFdcpNvx/vzp1YI0KTrUcNHx4IWuXn4ysuxqyuxr1xI+6NG4k9b2ywbcXCRWy99lpcnTvj7NYNV/duOLt1x94qXSOrRESaIafdGgxIAQpISaNz2q1kxNVN/yJyLFFQqhlYk3+QJOd5eQBYY2NDvp0XEZHGZVgs2JOTQ8rCe/UivFev4GN/TQ3eggI8+QV48vNDkq1Xr1qFWVlJ5dKlVC5dGiy3xsfj7NaVpGuvxdWly1E/DhERERGRxqKg1DGupMJNwZ5qIJBT6pfcm/YmOdcoKRGRY53F4SAsO5uwehamSPi/K4gaNpSq71dStfJ7qleuonrdOny7dlHx+Rck33BDsO3u//6X8vnzcXbrHhhR1akTlnB9EyoiIiIizYuCUse4vVP3MuNdRDntder3rrynJOciIs2bYbUGVweMHXMuEBhZVbN2LVUrVwVWDaxV8dUC9nw4hz0fzgkUWCw42rcPBKi6diP6zDOxRipnhIiIiIgc2xSUOsatKaidupd6gCTnW/YmOVdQSkTkeGNxOHD16IGrR4+Q8rgLxhGWnU3VqpVUf/c93qIiatato2bdOnjrbaLPGBVsW7n8Wwy7HWenjhg2feyLiIiIyLFD/50e4zqnRXPxyVl0z4itt96tlfdERFoc1wknhOSj8uzYQfXKlVR9vxJvURHWqH3TvQsfe5SqpcuwRETgOqkn4b17E9G7N84uXTDsdUfgioiIiIg0FgWljnH92ibQr23CAevdm/dO31NQSkSkpbKnpGBPSSFq2LCQctM0scUnYImMxF9eTsUXX1LxxZcUAUZ4OJGDB5Hx+ONN02kRERERafEUlGrG/FVVeHfsAMCuoJSIiPyCYRhkPPn/MH0+qteupXLJEiqXLKVq6VJ8u3dj1rhD2m+78UbCctoS3rs3rhN6YHE4mqjnIiIiItISKCjVjLnz8gCwxMRgi4tr4t6IiMixyrBacXXpgqtLFxImTcL0+6n56Wfw+4Jt3Fu37UucDoE8VD26E967N+EnnogjtyP2lOSm6L6IiIiIHKcUlGrGgknONUpKRESOgGGx4MztEFJmjYwgdeo9VC5eQuWSJXiLiqhauoyqpcsoBhImX0Xy9dcD4CksZOdTTxOWlYk9IzPwMysLa2Rk4x+MiIiIiDRbCko1Y8onJSIiDcUaG0vchRcSd+GFmKaJZ/NmKpYEAlQ1a9bgaNs22Na9YQOl//533W3ExWHPyiRh4kSizzgDAH9NDb7S3diSkzAMo9GOR0RERESOfQpKNWNaeU9ERI4GwzAIa92asNatiTv//Dr1tpQUEv/4R9x5eXi2bMGdl4dv1y58JSX4SkrwV1YG21at+I4tEydiOJ2EZWbsG1mVmUVYZgbOLl2wJSY25uGJiIiIyDFCQalmzL13+l52dhP3REREWhJHmzYkXXtNSJmvvBxPXh7uvDxcXboEy707i8BiwayupuannwO5rPaTet+9xI0bB0D12rXs+tdLgeBVbdDKnpWFNTZWo6xEREREjkMKSjVje6fvaeU9ERFpatbISKydOuHs1CmkPObMM4kePhxPfj7uLXm487bgyduKZ2se7rytONq0CbatXr2G3e+8U2fblogI7JmZJN98M5ED+gPg270bX2kp9rQ0jLCwo3twIiIiInJUKCjVTPmrq/Hm5wMaKSUiIsc2IyyMsOzsQ35eOTt3IvHaa/DkbQ0Gr7w7duCvqKBm7VoMy77RUmWf/o/8O+4AiwVbagr2tHTs6enY09Kwp6cTOXgQ9rS0o31oIiIiIvIbKCjVTHm2bgXAEhmJNS6uiXsjIiLy2zk7dsTZsWNImb+6Gs+2bbjz8nDuNy3QX16O4XRiVlfj3Z6Pd3s+VcuWBeszZzwfDErt+fBDdv7jnyFBK3t64KctLQ1bYiKGxdI4BykiIiIiQQpKNVP755NSng0RETleWZxOHG3bhqz+BxB/ycXEXTwBb2ERnu3b8Obn48nPx7NtO578/JBRWTUbNlKzdi01a9fWu4/M558PTgusXLaMysWLCctpi6NtDmFZWZoeKCIiInKUKCjVTLk3BfJJaeU9ERFpqQzDwJ6SjD0lGU488YDtYseOwdWtK57t2/Fszw/8rA1ieXfswJ6eHmxbsXAhO6c/te/JVithmZmE5eTgaJtD3PjxIe1FRERE5NdTUKqZcm9RknMREZHDYU9LO2B+KdPjAas1+NjZuTMxZ59NzYYNuDdswF9RgXvTJtybNlH+6afEnDsm2HbXK69Q9vG8wIiqNoGgVVhODraUFI1iFhERETkMCko1U5690/eylORcRETk1zLs9pDHUaedRtRppwFgmibewkLcGzbUBqk2EpaZEWxb/f33VC5aROWiRSHbsISHE5aTQ8bTT2FPSQHAW1KCJTwci8NxlI9IREREpPlQUKqZcm+uDUq1VlBKRETkaAhMD0zBnpJCRL9+derjL7+c8JP77Re02oB7yxb8lZVUr14dshBJ4cOPsPvdd7GnpxPWpk3g1jobR+19W2qqRleJiIhIi6OgVDPkd7vx5OcDEKbpeyIiIk3C2aEDzg4dQspMtxt3Xh6e7dux7Jcg3VtQAKaJZ9s2PNu2UfHVVyHPy/12OYbLBUDZ/Pn4y8uDwStrVNTRPxgRERGRJqCgVDPk2boV/H4s4eFYExKaujsiIiJSywgLq3e1wMwZz+MrLsa9cSM1mzbh3hjIU+XeuBHT58NSG5AC2DVzFpVLlwYfWxMSCGvTmrDWrXG2b0/8xInBOm9xMYbDiSUiXCOtmjnT46kznVREROR4p6BUM+TeXJvkvHW2/gEVERFpBgzDwJaYiC0xkfDevUPqTL8/5LHrxBPBYsG9cSPeoiJ8xcVUFRdTtXQZFWlpIUGprVOupmrFCgy7HWtcHNb4eKxxsdji4rClpJJy263BttVr1wIE2sXGKr/VMcA0TSoXLqR41iwMw0Lm359t6i6JiIg0KgWlmiElORcRETl+GBZLyOPkm24M3veV71v9z71xI6bXG9LWX1EBBEbZeAsL8RYWButsaWkhQamCqfdStWJF8PHeEddh2dk42rYl+fbb9GVXIzHdbvbMmUPxrBepWbMmUGix4NmxA3tKCqZpsvUPf8TVsyex556DLSmpaTssIiJylCgo1QztHSmlfFIiIiLHN2tkBK6uXXB17VJvfc77s/FXVeErKcFbUoKvpBRfSQm+khKwWUO3FRODNSkRX0kpeL34KyvxV1biycvDvWEDKXfcHmybd/XV+Ip3EdY2B0ebnMDPtm2xp6djWK3Ir+MrLaXk329S8vLLwQCi4XIRe+65xF96SXC1xqpvv6X8s88o/+wzip58kqjTTiV23DgiTjlFr7+IiBxXFJRqhoIr72UrKCUiItLSWVwuLC4X9vT0g7bLfO7vQGDKmL+sLBDIKiqiZuNG8Jshbau+XRGYNvjttyHlhsNBeK9eZM14Pljm3roVW1KSpgMehj0ffUzRY48BYE1KJH7CxcRdeAHW2NiQds6OHUn7y18offNNqlasoGzeJ5TN+wRbehqxY8cSe/752JOTm+AIREREGpaCUs2Qe+/0vWxN3xMREZEjYxgG1uhorNHRhGVnE96rV0i9aZpkzXiemvXrca/fQM2GDbg3bMC9aRNmTQ2mzxfSfvPFl+DdsQN7Rgb2jFYY1n3/Xjo7dQqZjrj1mmvwV1Tu3VPIdsLatiP1T3fua3vDDZiVVdizs3C0aUNY69aEtWmDLSWlWUwzNE2Tqm+/xayuJuKUUwCIOft37PnwQ2LOOYfoM88IWaFxf5bwcGLHjiF27Biqf/yR0jffYvfs2Xi357Nz+lO4TjhBQSkRETkuKCjVzJhuN55t2wCwa/qeiIiINDDDMHB27IizY8eQctPnw7N1K/6ammCZv6YGf1UVmCaevDw8eXmhG/OHBrAqFi3Gv2dPvfv1V1aFPK5atjwkR1awfy4XEf36kfnM08GymvXrsSUnY42KOqxjPJpMr5eyefMonjWL6u++J6xtW3Len41hsWBxOsl+cdYRbc/ZoQOpf7qT5Jtvouzjjyn/7HMi+vUL1u/8xz/xV1QQe95YwjIzG/hoREREji4FpWr5fD48Hk9Td+OQ3Fu34k9JwXA68UZF4auubuouyS/Y7XasyvcgIiLHGcNqrTNK2+Jw0GHhN/iKi6lZvwFP/vZ97Q0Da2JiSPu0e6f+Iln7vhFP1ri4kLapd9+Fd2dxSKJ399atmFVVmN7Q/9k2T7gYX2kp1sREwlpnh4yscrRr1yh5OH3l5ZS+9RYl/3oJz/bA62CEheE68QT8lVVYIyN+0/YtDgcxo0cTM3p0sMzvdrNr5kx8JSUUP/ccEaf0I/b884kaOhTjAKOwRKT58fv9uN3upu6GNABdK9ZlmKZpHrpZ87V161YyMzPJy8sjIyOjTr1pmhQUFFBaWtr4nfsV/NXV+HbtwrDZsGnY9jErNjaW1NTUZjG9QEREpLkwPR7ceVvB58XRvj0QWKFww6hReIuK6n1ORP/+wRxYpmmy/ZZbsUZHYYmJwRYbiyUmJpAEPjYWe0rKIXNz1af0nXfZ8de/4i8vBwIBtrjx44m7aDy2XwTmGpLp9VL2yXxK33yTiq+/htp/663x8cSccw6xY8fgaNv2qO1fRI4+t9vNxo0b8fv9Td0VaSAHu1Y8VPzieNTiR0rtDUglJycTHh5+zAcRvCUleK1WLJGRhP2Kf5rk6DJNk8rKSgprpxukpaU1cY9ERESOH4bdjiOnTUiZNTKC9l9+ga+8HPemzYERVXtHVm3ahLNzp2Bbs7KSPR98cMDtRw4bSuZTTwXamiYbzjgTS0REMGgV/BkbQ1jbtkT27w+APS0Vf3k5YW3aED9pEjFn/w6L03kUXoFQhs1G9MgRRI8cgXvrVkrffpvdb7+Dt7CQXS+8gGGzkXzjDYHj8XjANDWCSqQZMU2T/Px8rFYrmZmZWCyWpu6S/Aa6Vqxfiw5K+Xy+YEAqISGhqbtzWDymidViwRYejr0R/tmRI+dyuQAoLCwkOTlZwzNFREQagTUyElfXLri6djlwI4uFlDtux7d7N77SUnylu/fd370be9q+L/z8FZW4N2484Kaihg8LBqXCTz6ZrFkzCe/TB6OJLhrDMjJIvu46kqZMofyLLyh95x2ihg8L1pd/9RXbb76FiIEDiRpyGpGDBtVZ9U9Eji1er5fKykrS09MJDw9v6u5IA9C1Yl3HTFDqmc9+5qG56/h9/9bcMzrwz0S1x8df/ruG97/fjtvrZ1D7JKad05WkqIZZcnhvDqnmdIL7a+cS61uuY9ve95TH49EfGhERkWOExeUifuLEw2vrCCP71Vfx7d4bvCoNBq98paW4uvcItjUMg4iTTz5a3T4ihs1G1JAhRA0ZElJeuXAh/ooKyubOpWzuXLBaCe/Zk8ghQ4gacppWdRY5BvlqVzsN07XfcUXXiqGOiaDUd3mlvLpoCx1TQ1dMmfbBav63tpBnLupJlNPO3bNXMfnlZbz9h1MadP/H+pS9/ZnBoFTDBObk6GhO7ykRERGpy7DbCe95YlN3o8Ek33Yb0WeeSdmnn1L+6f+o+fFHKpcsoXLJEgr/9jfafjRXgSmRY5SuLY4vDf373PXKK+ya8QLenTtxdOxI6p//hKt793rblvz73+x+bzY1P/0EgLNLZ5JvuOGA7RtDk09Krajxcv0bK3hwTHdiXPZg+Z5qD/9emsefz+rMKe0S6ZYRw8Pn9WDZ5hKWbylpwh43HdPvD+QDAAxHw0bLW7duzRNPPNGg2xQRERGRY4NhseDq3p3k668nZ/Z7tP1kHil33kl4v5NxtG8XEpDKv2cq2++4kz3z5uGvqGjCXouIBOh6tX57PvyQwgf/RuKUKbR5522cublsueL/8BYX19u+cvESos88g+wXZ9H69dewp6ax5fIr8OzY0cg936fJg1J3vbeK03KTGdA+dGWSVVt34/GZ9G+3r7xdciStYl0s39xCg1IeD+FduxLerRvWsDAMw6hzmzp16q/a9pIlS7jyyisbpJ+vvfYaVquVKVOmNMj2RERERKRhhWVkEH/pJWTPnEmbd98Nlvvdbva8/z67332Xbddcy4/9TmHLVVdR8vrr1Kxfj1k7nUhEpD71XaMeK9erp556Ktdff/1v2saxpnjWi8Sef35gtdV27Ui9dyoWp5PSt9+pt32rRx4m/qKLcHbqhCMnh7T7p4HfT8U33zRyz/dp0ul7s7/bzg/b9vDe1f3r1BWV1xBmtYSMngJIjAyjqLzmgNusqamhpmZffVlZWcN1uImZbjcb/vc/LGFhOHJyeOONN7j77rtZt25dsE1kZOS+9qaJz+fDZjv0rzkpKanB+jljxgxuvfVWnnvuOR599FGcTZiQ3e12aw62iIiIyEEY+/2vaFitZDz7LOWffkrZp5/iycuj4vMvqPj8CyB0hUKAmo0bCcvObrIE7yJybMnPzw/eP1avV48XpttN9Q8/kHjl/wXLDIuFiH79qFqx4rC24a+qxvR6scbEHKVeHlqTfXpsL63ivvd/4IkLT8Bpb7jkXg888AAxMTHBW+fOnRts203NdLtJTUwkLSOD1NRUYmJiMAyD1NRUUlNTWbt2LVFRUcyZM4eTTjoJh8PBV199xfr16zn77LNJSUkhMjKS3r1788knn4Rs+5fDIQ3D4Pnnn+fcc88lPDyc9u3bM3v27EP2cePGjXz99dfcfvvtdOjQgXfeqRuhfeGFF+jSpQsOh4O0tDSuvvrqYF1paSlXXXUVKSkpOJ1Ounbtyge1SzdPnTqVE044IWRbTzzxBK1btw4+njRpEueccw5/+ctfSE9PJzc3F4CXXnqJXr16ERUVRWpqKhdddFFwKc69fvjhB8466yyio6OJiopi4MCBrF+/ni+++AK73U5BQUFI++uvv56BAwce8jURERERaS4Mq5WIvn1IueN22n78ETkfvE/SjTfi6nUShsuFs0OHYFtPYSEbRp3Bj716s/niS9jxwIPsfv8DajZsxPT7m/AoRKSp7L02PVavVw/m7bffDl6ntm7dmkcffTSk/plnnqF9+/Y4nU5SUlI477zzgnVvvfUW3bp1w+VykZCQwLBhw6j4DdOfy8rK2LNnT/C2/8CbvbwlpeDzYU1ICCm3Jibg3bnzsPZT+Ogj2JKTiTilYfN2H4kmGym1cttudpa7OWv6V8Eyn99k8aZd/Oubzfzrsj64fX52V3lCRkvtLHeTFHngJN933HEHN954Y/Dxtm3bDjswZZomZlXVrzia385wuQ6Z8Mw8zJX3br/9dh555BFycnKIi4sjLy+PM844g7/85S84HA7+9a9/MXr0aNatW0dWVtYBt3Pvvffy0EMP8fDDDzN9+nQmTJjA5s2biY+PP+BzZs6cyZlnnklMTAwXX3wxM2bM4KKLLgrWP/vss9x44408+OCDjBo1it27d7NgwQIA/H4/o0aNoqysjJdffpm2bduyevXqI16RYP78+URHRzNv3rxgmcfjYdq0aeTm5lJYWMiNN97IpEmT+PDDD4HA+2TQoEGceuqpfPrpp0RHR7NgwQK8Xi+DBg0iJyeHl156iVtuuSW4vVdeeYWHHnroiPomIiIi0lwYhoGjXTsc7dqReOX/Yfp8mPtdGHny8jCcTvyVlVQuXUrl0qXBOktEBEnXXUv8pZcCBINUGlEl8tv5KysPXGm1YnE4Dq+txYJlv1ktB2praeDV6pvyevVAli1bxrhx45g6dSoXXHABX3/9NX/84x9JSEhg0qRJLF26lGuvvZaXXnqJU045hV27dvHll18CgdFh48eP56GHHuLcc8+lrKyML7/8EtM0f/Vr9MsYxj333POrpz4eyM5//JM9H84h+18vhrxnGluTBaX6t0vko+sHhZTd8tZ3tE2KZPLgtqTFOrFbDb7+eSejuqUBsL6onG2lVfTMjjvgdh0OB479XtA9e/Ycdp/MqirW9TzpCI+kYeQuX4ZxiJPdf5hBqfvuu4/hw4cHH8fHx9Ojx75li6dNm8a7777L7NmzQ0Yp/dKkSZMYP348AH/961958sknWbx4MSNHjqy/f34/s2bNYvr06QBceOGF3HTTTWzcuJE2bdoAcP/993PTTTdx3XXXBZ/Xu3dvAD755BMWL17MmjVr6FD7LVxOTs5Bj7U+ERERPP/88yHT9i677LLg/ZycHJ588kl69+5NeXk5kZGRPP3008TExPD6669jtweCoB32+ybw8ssvZ+bMmcGg1Pvvv091dTXjxo074v6JiIiINEeG1Rry/2r4SSeRu3QJNRs2UP3DaqpXraL6hx+oXrsWf0UFlujoYNuqb78l76rJODt3xtmlC87OnbGnpmCNjw/cYmIUsBI5TAe7Zo0YPIis554LPv6x/4ADDrwI792b7Jf+FXz889Bh+Erq5m/utHbNb+htXU11vXowjz32GEOHDuWuu+4CAteCq1ev5uGHH2bSpEls2bKFiIgIzjrrLKKiosjOzubEEwMrtObn5+P1ehkzZgzZtYtGdOvW7Yj7sL/Vq1fTqlWr4GNHPUEjW1wsWK34fpHU3LezGFtiYp32+yue8QLF//wnWS+8gLN2dlFTabKgVKTDRm5qVEiZy24lNtweLB/XK5P7/7uGmHA7UQ4798xeRc+sWHpmHTgodTzb+83UoYJSvXr1CnlcXl7O1KlT+e9//xs8YaqqqtiyZctBt9N9v2UhIyIiiI6OrjPlbX/z5s2joqKCM844A4DExESGDx/OCy+8wLRp0ygsLGT79u0MHTq03uevWLGCjIyMkGDQr9GtW7c6eaSWLVvG1KlT+e677ygpKcFf+23dli1b6Ny5MytWrGDgwIHBgNQvTZo0iT//+c8sXLiQk08+mVmzZjFu3DgiIiJ+U19FREREmjPDZsPZoUNgWt+55wBger3UrN+APSU52K76hx/wl5dTuXgxlYsX19lOq8cfI3rUKAAqly1j18svY4tPwBofhy0+Hmt8Arb4OKzx8djT07G4XI1yfCLS8JrqevVg1qxZw9lnnx1S1r9/f5544gl8Ph/Dhw8nOzubnJwcRo4cyciRI4NTB3v06MHQoUPp1q0bI0aM4PTTT+e8884jLu7Xxy2ioqKI3i+wXx8jLAxnly5UfLOQqGHDgMCo1IqFC4mbMOGAzyt+/nl2/v05sp7/J65uXX91HxtKkyY6P5S7zuqMxVjDH15ejtvrZ1CHRKadc/ReNMPlInf5sqO2/UPt+2BM08T0eAJtDxGU+mWg5Oabb2bevHk88sgjtGvXDpfLxXnnnYe7duTVgfwyQGMYRjCYU58ZM2awa9cuXPsdi9/v5/vvv+fee+8NKa/PoeotFkudIZCe2tdkf788/oqKCkaMGMGIESN45ZVXSEpKYsuWLYwYMSL4Ghxq38nJyYwePZqZM2fSpk0b5syZw2effXbQ54iIiIi0RIbNhjM39EvGuIsuIrxvX6pX/UD1D6uoXvcj3p1F+HaV4C8rwxq3b7pNzU8/UzZn7gG3v38Aq+Lrr9n53D+wJcRjS0nFnpqy72daGrbERIwjTAUhcqw76DXrL97vHRZ8dYCGwC9GJ7ab/8kBGjasprpe/S2ioqJYvnw5n332GR9//DF33303U6dOZcmSJcTGxjJv3jy+/vprPv74Y6ZPn86f/vQnFi1aFJwxdLQkTJrI9tvvwNm1K67u3dj14r/wV1URO+ZcALbfdhu25BSSbwqkONr5z3+y88nppD/yCPZWrfAWFQGBKZqWJhpwcUwFpd64ql/IY6fdyrRzuh7VQNT+DMM45BS6pmJ6PGCaYBgYBxjNcyALFixg0qRJnHtu4I1ZXl7Opk2bGrR/xcXFvPfee7z++ut06dIlWO7z+RgwYAAff/wxI0eOpHXr1syfP5/TTjutzja6d+/O1q1b+fHHH+sdLZWUlERBQQGmaQbzb604jFUF1q5dS3FxMQ8++CCZmZkALN0v58Hefb/44ot4PJ4Djpa64oorGD9+PBkZGbRt25b+/euuGikiIiIidQUCVbmBaSJjx4TUmW53yMWxq+eJpNx5B97iXfh27cJbsgvfrhJ8xcV4S0qwxu9L6uvesoXKRYsOuN/0Rx8h5swzAahauYo9H3yALbU2aJWaij01FVtSUsgKhCLHuiPJ8XS02jakxrhePZROnToFcx3v368OHToEcxzbbDaGDRvGsGHDuOeee4iNjeXTTz9lzJgxGIZB//796d+/P3fffTfZ2dm8++67Ifmuj4boM87Au6uEoulP4ivaiaNTJ7L++Y/g9D3P9nww9v19LX3tdUyPh237pdMBSJwyhaRrDjxV8mjSX99mwqzZl0/qUAnRf6l9+/a88847jB49GsMwuOuuuxo8gvzSSy+RkJDAuHHj6vTvjDPOYMaMGYwcOZKpU6cyefJkkpOTg0nNFyxYwDXXXMPgwYMZNGgQY8eO5bHHHqNdu3asXbsWwzAYOXIkp556KkVFRTz00EOcd955zJ07lzlz5hxyWGNWVhZhYWFMnz6dyZMns2rVKqZNmxbS5uqrr2b69OlceOGF3HHHHcTExLBw4UL69OkTXMFvxIgRREdHc//993Pfffc16OsnIiIi0lL9chZAcDrgYYjo35/0Rx7Bu7MI745CPAX5eAt24NlRgHdHIfbU1GDbqpXfs+vFF+tuxGLBlpRE2l/+QuSAwJeO1WvWULFwEYbNhmGzgs2GYbNj2KwYNhuuk07CnhyYnugpLMS9aVNIPVYbht2GYbViS0pqsot9keagMa5X9yoqKqozsCEtLY2bbrqJ3r17M23aNC644AK++eYbnnrqKZ555hkAPvjgAzZs2MCgQYOIi4vjww8/xO/3k5uby6JFi5g/fz6nn346ycnJLFq0iKKiIjp16nRUjuGX4i+eQPzF9U/X2z9nGEC7T+c3RpeOiIJSzYTpDuSTshxi6l59HnvsMS677DJOOeUUEhMTue22244oAfzheOGFFzj33HPrDZiNHTuWSy65hJ07dzJx4kSqq6t5/PHHufnmm0lMTAxZSvPtt9/m5ptvZvz48VRUVNCuXTsefPBBIBC9fuaZZ/jrX//KtGnTGDt2LDfffDP/+Mc/Dtq3pKQkZs2axZ133smTTz5Jz549eeSRR/jd734XbJOQkMCnn37KLbfcwuDBg7FarZxwwgkho6EsFguTJk3ir3/9K5fWriQjIiIiIk0nLDOTsNqR8L9k+nwhj50dOxF/+WV48wvw7NiBt6AAT2EheDx4d+zAEr4vnUPl0mUU/u1vB9xv5j+eCwalKr78kvw//fmAbVs98TjRtYmXq77/nuKZMwnLzCIsKxN77U9bSooSvUuL1RjXq3u9+uqrvPrqqyFl06ZN489//jP//ve/ufvuu5k2bRppaWncd999TJo0CYDY2Fjeeecdpk6dSnV1Ne3bt+e1116jS5curFmzhi+++IInnniCPXv2kJ2dzaOPPsqo2mnGcnCG+VvWKWwGtm7dSmZmJnl5eWRkZITUVVdXB1eGc+63FOaxyJOfj7e4GFtCIva01EM/QY6Kyy+/nKKiImbPnn3Qds3pvSUiIiLSUpl+P77iYjwFO3DktAnmVCn/8it2z56N6fWA14vp9WF6vbWPfSTfeguu2tW19sz9iKInn8T0emvb1t58PvB4SH/kEaKGBFJXlLz+BgX1LOtuhIVhz8gg5U93Eln7pai3pARfSSn2jFa/6otpaf50TXF8Otjv9WDxi+OVRko1E2ZtkjfDoQ+kprB7925WrlzJq6++esiAlIiIiIg0D0bt1D1bUlJIeeTAAUQOHHBY24geOYLokSMOq234ST1Jvu02PHlbcG/egjsvD8/27ZhuN+4NG0Jyx5bNm0fB3feAYWBLSw0ZXWVLTCRy8CBsCYH8Wp5t23Bv2YJhtwe2YbMF7tvsGGF2bImJWGovfk2vN5Cr1mY74rQgIiINTUGpZsLv3pdTShrf2WefzeLFi5k8eTLDhw9v6u6IiIiISDPkaN8eR/v2IWWm14snPx/3li04O3feV15VhREejllZiXd7Pt7t+SFJ3bNfezUYlNrz8byDTjfMemEGEaecAkDpW28HR2vtDWIZEeHYYmOxxsSSdN21hPfuDYB70yYqly7FGhsbeouJOeLFl0RE6qOgVDNgmua+kVIKSjWJzz77rKm7ICIiIiLHIcNmqzc3VvzEicRdeim+4mLcW/ICo6u25OHO24KvpBRrbGywrTUmBkf79pgeT+Dm9Ybc3/8awvR6992vbUNlJb6inQD4q2uC9ZXLlpH/57vq7bclMpL0vz1I1NChAFSt+oHd772HNTYGa2QkhsOJxeXEcLqwuJw4O3UKjkjzV1XhLy/HcLmwOJ1a/VCkBdPZ3wyYHk9giK1h6BsJEREREZEWwjAMbImJgeXde554wHaxY84ldsy5h7XN2HHnE3PWmSGBK395Ob7SUnylpTg7dQy2tSUmEjF4ULDOV7ob/+7dAIGgkmNfPpyadWspeemlA+53/4Tv5Z9/zrbrb9hXabdjcToDASqXi+SbbyL69NOBQLBr1wszsERGYYmKxBoVXfszCktkFM5OHbGnpQH7ktsbVuthvRYi0vQUlGoG9h8lpXnfIiIiIiLya1nCwuAwZ19EDh5M5ODBIWWmz4dvz55AEvaU5GC5o0MHEq68El9JCf7KSvzV1ZjV1YGfVVVY4+P3bcPtBsMIfPEO4PHg93jwl5UF6j2eYFvP9m3s+XDOAfuYeu+9xF0wDoDKRYvYctnlWMLDsUTVBrEio7BERWGNiiRmzFgiBwQSyft276Zq5SpsiQlY4+OxxcdrxJZIE9BZ1wzsDUpp1Q0REREREWlKhtWKLS4OW1xcSLmrW7fgioSHEvO73xE9ejSm241ZVYW/uhp/VVUgiFVVTVjr7GBbZ24uKXfcjq+sHH9ZGb7yMvxl5fjLy/CVlYesTO4rKwcIBMUqK2HHjpD9hvfpG7xfvWYNeVdcsd+BGVhjYwNBqoRE4iZcRHRtLllfaSlV332HNSERW0I8toQEpVURaSAKSjUDZo3ySYmIiIiIyPHDMAwMhwMcDg422S4sO5v4iRMPa5tRQ4fQ/usFgeBVMHC1L4jlCpkCaeDo0AFvcTG+khLw+/GVlATu//Qz0WeMCrasXrOGvKsmh+zLEh2NLSEBa0I8CZMmETVsGADurVspffMtLC5XYMRWeOCn4XJhCY8grHU29pQUoHa6oc+n6zxp0RSUagZMdyDZoP5YiYiIiIiI1M+w2bDFx8N+UwUPJOLkvuTMfg+onZJYUhIIUBUX4y0uxtW9+77GFiuOzp3w7SzGu2sXeL349+zBvWcPbNyId/Tvgk09W7ZQ/NxzB9xv8i23kHD5ZQBUr1rFpgsuDOTUCg8P3CLCAyO24uJwnn02tGoV7KO/sjKQL8tmC/y0WJTeRZo9BaWaAX8wp5SjiXsiIiIiIiJyfDGs1n0J5esR0bcPOe+8A4Dp9+PbvRvfrl14dxbj21WMs0uXYFtbcjJxl16Cv7ISs7ISf2VVcDqhv6oKW9K+ffgrKwN3PB78u/clkd/L2vfkfUGpGjfuzZt/0XEDw2rFsNqwJgTyYkFghUXf7t1gtWJYLGCamKYJfj/4/cEAGASuNb1FRYH8Xn5/oG3tT/x+rHFx2BISAm1ranBv2IgRZg/kO/7lzWZTkEyOmIJSxzjTNPclOndopJSIiIiIiEhTMSyWYE4tR9u2deod7dqReuedh7Wt8D596LBoIf6q2sBVRSX+itqVEEtKsHTvTul+7S1OJ6bPh+n1BoJGphlYRdHrxerzB9uZbjee/PwD7teWnBwMSlE7SuxALPslnccwMH1ezCovVFXV3W58Avb0fSsh+kpK9gWs7Hatiij1UlDqGGd6PIE/OIaBYbcDMGnSJF588UUAbDYb8fHxdO/enfHjxzNp0iQsFkuj9O21117j4osvZvLkyTz99NONsk8REREREZHjgWG1Yo2JwRoTU299dXU1bNwIgCXchaNdu2Cd6fcHglM+H6bXFzqAwWLBGhMTqPf7AysdWiwYhgUsBhbHvhk4ht2OLTk5WBdsa7EErkH3SyFj2O042rYNJKh3u/F7PMH7pseDEXaA69XoaLp26MC4s87i0gsuwOp0Bo47Kmrfsbjd+0Z2/cZpiaeeeionnHACTzzxxK/ehjQeBaWOccFRUnZ7yIk5cuRIZs6cic/nY8eOHcydO5frrruOt956i9mzZ2NrhOVMZ8yYwa233spzzz3Ho48+itPpPOr7PBC3202Ycm6JiIiIiEgLYFgsB8w5bHE6CcvMPLzt2GzYk5MPr61hYLhc4HLVqTNrR27tNeL00/nHX/6Kt7qKHQU7+PjLL7j5r3/lnblzeWv6dFxOJ9QGpfxV1bg3bqhzfFgsYLFiS0wITk30ezx4i4r2Ba8sVrDWBtGsVqyRkYd1LHLsaJwhNfKr7Zu6F5pPyuFwkJqaSqtWrejZsyd33nkn7733HnPmzGHWrFnBdqWlpVxxxRUkJSURHR3NkCFD+O677wD48ccfMQyDtWvXhmz78ccfp209Q1H3t3HjRr7++mtuv/12OnTowDu1c6z398ILL9ClSxccDgdpaWlcffXVIf266qqrSElJwel00rVrVz744AMApk6dygknnBCyrSeeeILWrVsHH0+aNIlzzjmHv/zlL6Snp5ObmwvASy+9RK9evYiKiiI1NZWLLrqIwsLCkG398MMPnHXWWURHRxMVFcXAgQNZv349X3zxBXa7nYKCgpD2119/PQMHDjzo6yEiIiIiItJSGYYRCAzVcrpcZPU6iZwBA+h33ljufvRR3n3rLT7+6ite/d//sEREAIHrwiun/JGsQYNIOflkRl1+Od+vW4fp9/Pjzz/jyu3A2nXrgts1PR6eeOIJcnv3xltYiKcgH8+2bbjz8vBs3XpYfX377beD16mtW7fm0UcfDal/5plnaN++PU6nk5SUFM4777xg3VtvvUW3bt1wuVwkJCQwbNgwKioqfstL1+IpKLUf0zSpdHub5GbuF1UOYQSGV1och05yPmTIEHr06BESIDr//PMpLCxkzpw5LFu2jJ49ezJ06FB27dpFhw4d6NWrF6+88krIdl555RUuuuiig+5r5syZnHnmmcTExHDxxRczY8aMkPpnn32WKVOmcOWVV7Jy5Upmz55Nu9rhpn6/n1GjRrFgwQJefvllVq9ezYMPPoj1COcYz58/n3Xr1jFv3rxgQMvj8TBt2jS+++47/vOf/7Bp0yYmTZoUfM62bdsYNGgQDoeDTz/9lGXLlnHZZZfh9XoZNGgQOTk5vPTSS8H2Ho+HV155hcsuu+yI+iYiIiIiInI0HOy6strja/C2DcGw2Rg2ahQ9evTgvXnzsNSOtjr//PMp2rWLOR9/zNLlyzlpwADOvOoqKhIS6Dp0KL169uT1998P2c4bH33EheedhzUuDmtMDJbIyEDy9npGcP3SsmXLGDduHBdeeCErV65k6tSp3HXXXcGBHUuXLuXaa6/lvvvuY926dcydO5dBgwYBkJ+fz/jx47nssstYs2YNn332GWPGjDnwtbwcFk3f20+Vx0fnuz9qkn2vvm8E4WF1fx17k+gdro4dO/L9998D8NVXX7F48WIKCwtx1Aa1HnnkEf7zn//w1ltvceWVVzJhwgSeeuoppk2bBgRGTy1btoyXX375gPvw+/3MmjWL6dOnA3DhhRdy0003sXHjRtq0aQPA/fffz0033cR1110XfF7v3r0B+OSTT1i8eDFr1qyhQ4cOAOTk5Bz2Me4VERHB888/HzJtb//gUU5ODk8++SS9e/emvLycyMhInn76aWJiYnj99dex1+bo2tsHgMsvv5yZM2dyyy23APD+++9TXV3NuHHjjrh/IiIiIiIiDe1g16yn5SYx8/d9go9PmvYJVb8IPu3Vt008b1zVL/h4wN/+x64Kd512mx488zf0NtShrlcfffRR3nvvPd55//3A9eoll/DUU09x/1//CsDPmzax/PvveeWNNwirXZnwSDz22GMMHTqUu+66CwhcC65evZqHH36YSZMmsWXLFiIiIjjrrLOIiooiOzubE088EQgEpbxeL2PGjCE7OxuAbt26/ebXpKXTSKnjjGmawdxT3333HeXl5SQkJBAZGRm8bdy4kfXr1wOBgNKmTZtYuHAhEBgl1bNnTzp27HjAfcybN4+KigrOOOMMABITExk+fDgvvPACAIWFhWzfvp2hQ4fW+/wVK1aQkZEREgz6Nbp161Ynj9SyZcsYPXo0WVlZREVFMXjwYAC2bNkS3PfAgQODAalfmjRpEj///HPw9Zg1axbjxo0jonZ4qYiIiIiIiPw6jXG9ejBr1qyhf//+IWX9+/fnp59+wufzMXz4cLKzs8nJyeGSSy7hlVdeobKyEoAePXowdOhQunXrxvnnn88///lPSg6ycqEcHo2U2o/LbmX1fSOabN8NYc2aNcHRSuXl5aSlpfHZZ5/VaRcbGwtAamoqQ4YM4dVXX+Xkk0/m1Vdf5Q9/+MNB9zFjxgx27dqFa7/hkX6/n++//5577703pLw+h6q3WCx1hkB69l+KtNYvA0UVFRWMGDGCESNG8Morr5CUlMSWLVsYMWIE7trcXIfad3JyMqNHj2bmzJm0adOGOXPm1Pv6iYiIiIiINIWDXbNafrFq3bK7hh12269uO+23dewwNMb16m8RFRXF8uXL+eyzz/j444+5++67mTp1KkuWLCE2NpZ58+bx9ddf8/HHHzN9+nT+9Kc/sWjRouAxyZFTUGo/hmHUO4Wuufj0009ZuXIlN9xwAwA9e/akoKAAm80WkiT8lyZMmMCtt97K+PHj2bBhAxdeeOEB2xYXF/Pee+/x+uuv06VLl2C5z+djwIABfPzxx4wcOZLWrVszf/58Tjut7h+27t27s3XrVn788cd6R0slJSVRUFAQEkVfsWLFIY9/7dq1FBcX8+CDD5JZu9rE0qVL6+z7xRdfxOPxHHC01BVXXMH48ePJyMigbdu2dSLpIiIiIiIiTeVIrlmPVttfozGuVw+lU6dOLFiwIKRswYIFdOjQIZjj2GazMWzYMIYNG8Y999xDbGwsn376KWPGjMEwDPr370///v25++67yc7O5t133+XGG2/81X1q6ZpvBKaFq6mpoaCgAJ/Px44dO5g7dy4PPPAAZ511FpdeeikAw4YNo1+/fpxzzjk89NBDdOjQge3bt/Pf//6Xc889l169egEwZswY/vCHP/CHP/yB0047jfT09APu96WXXiIhIYFx48YFA0Z7nXHGGcyYMYORI0cydepUJk+eTHJyMqNGjaKsrIwFCxZwzTXXMHjwYAYNGsTYsWN57LHHaNeuHWvXrsUwDEaOHMmpp55KUVERDz30EOeddx5z585lzpw5REdHH/Q1ycrKIiwsjOnTpzN58mRWrVoVzJW119VXX8306dO58MILueOOO4iJiWHhwoX06dMnuILfiBEjiI6O5v777+e+++474t+NiIiIiIhIS9ZU16t7FRUV1RnYkJaWxk033UTv3r2ZNm0aF1xwAd988w1PPfUUzzzzDAAffPABGzZsYNCgQcTFxfHhhx/i9/vJzc1l0aJFzJ8/n9NPP53k5GQWLVpEUVERnTp1atgXr6Uxj3N5eXkmYObl5dWpq6qqMlevXm1WVVU1Qc9+vYkTJ5qACZg2m81MSkoyhw0bZr7wwgumz+cLabtnzx7zmmuuMdPT00273W5mZmaaEyZMMLds2RLSbty4cSZgvvDCCwfdd7du3cw//vGP9da98cYbZlhYmFlUVGSapmn+/e9/N3Nzc0273W6mpaWZ11xzTbBtcXGx+fvf/95MSEgwnU6n2bVrV/ODDz4I1j/77LNmZmamGRERYV566aXmX/7yFzM7OzvkNTj77LPr9OHVV181W7dubTocDrNfv37m7NmzTcD89ttvg22+++478/TTTzfDw8PNqKgoc+DAgeb69etDtnPXXXeZVqvV3L59+0FfjwNpru8tERERERE5NjTXa4qmvF41TdMcPHhwcP/736ZNm2aapmm+9dZbZufOnU273W5mZWWZDz/8cPC5X375pTl48GAzLi7OdLlcZvfu3c033njDNE3TXL16tTlixAgzKSnJdDgcZocOHczp06cf8etzsN/rweIXxyvDNI/v9Qu3bt1KZmYmeXl5ZGRkhNRVV1cHV4xzOp1N1EM5Fl1++eUUFRUxe/bsX/V8vbdEREREROS30DXF8elgv9eDxS+OV5q+J7Kf3bt3s3LlSl599dVfHZASERERERERkUNTUEpkP2effTaLFy9m8uTJDB8+vKm7IyIiIiIiInLcUlBKZD/1LUcqIiIiIiIiIg3P0tQdEBERERERERGRlkdBKRERERERERERaXQKSgHH+QKE0gT0nhIRERERkYaga4vji36foVp0UMputwNQWVnZxD2R483e99Te95iIiIiIiMiRsFqtALjd7ibuiTQkXSuGatGJzq1WK7GxsRQWFgIQHh6OYRhN3CtpzkzTpLKyksLCQmJjY4MfJCIiIiIiIkfCZrMRHh5OUVERdrsdi6VFjylp9nStWL8WHZQCSE1NBQgGpkQaQmxsbPC9JSIiIiIicqQMwyAtLY2NGzeyefPmpu6ONBBdK4Zq8UGpvSd6cnIyHo+nqbsjxwG73a6ot4iIiIiI/GZhYWG0b99eU/iOE7pWrKvFB6X2slqtenOIiIiIiIjIMcViseB0Opu6GyJHhSalioiIiIiIiIhIo1NQSkREREREREREGp2CUiIiIiIiIiIi0uiO+5xSfr8fgPz8/CbuiYiIiIiIiIhI/fbGLfbGMVqC4z4otWPHDgD69OnTxD0RERERERERETm4HTt2kJWV1dTdaBSGaZpmU3fiaPJ6vXz77bekpKRgsTTObMWysjI6d+7M6tWriYqKapR9ijQHOjdE6tJ5IVI/nRsi9dO5IVK/4+Hc8Pv97NixgxNPPBGb7bgfQwS0gKBUU9izZw8xMTHs3r2b6Ojopu6OyDFD54ZIXTovROqnc0Okfjo3ROqnc6N5UqJzERERERERERFpdApKiYiIiIiIiIhIo1NQ6ihwOBzcc889OByOpu6KyDFF54ZIXTovROqnc0Okfjo3ROqnc6N5Uk4pERERERERERFpdBopJSIiIiIiIiIijU5BKRERERERERERaXQKSomIiIiIiIiISKNTUKqBPf3007Ru3Rqn00nfvn1ZvHhxU3dJpFF98cUXjB49mvT0dAzD4D//+U9IvWma3H333aSlpeFyuRg2bBg//fRT03RWpBE98MAD9O7dm6ioKJKTkznnnHNYt25dSJvq6mqmTJlCQkICkZGRjB07lh07djRRj0Uax7PPPkv37t2Jjo4mOjqafv36MWfOnGC9zgsRePDBBzEMg+uvvz5YpnNDWqKpU6diGEbIrWPHjsF6nRfNj4JSDeiNN97gxhtv5J577mH58uX06NGDESNGUFhY2NRdE2k0FRUV9OjRg6effrre+oceeognn3ySv//97yxatIiIiAhGjBhBdXV1I/dUpHF9/vnnTJkyhYULFzJv3jw8Hg+nn346FRUVwTY33HAD77//Pm+++Saff/4527dvZ8yYMU3Ya5GjLyMjgwcffJBly5axdOlShgwZwtlnn80PP/wA6LwQWbJkCc899xzdu3cPKde5IS1Vly5dyM/PD96++uqrYJ3Oi2bIlAbTp08fc8qUKcHHPp/PTE9PNx944IEm7JVI0wHMd999N/jY7/ebqamp5sMPPxwsKy0tNR0Oh/naa681QQ9Fmk5hYaEJmJ9//rlpmoFzwW63m2+++WawzZo1a0zA/Oabb5qqmyJNIi4uznz++ed1XkiLV1ZWZrZv396cN2+eOXjwYPO6664zTVOfGdJy3XPPPWaPHj3qrdN50TxppFQDcbvdLFu2jGHDhgXLLBYLw4YN45tvvmnCnokcOzZu3EhBQUHIeRITE0Pfvn11nkiLs3v3bgDi4+MBWLZsGR6PJ+T86NixI1lZWTo/pMXw+Xy8/vrrVFRU0K9fP50X0uJNmTKFM888M+QcAH1mSMv2008/kZ6eTk5ODhMmTGDLli2AzovmytbUHThe7Ny5E5/PR0pKSkh5SkoKa9eubaJeiRxbCgoKAOo9T/bWibQEfr+f66+/nv79+9O1a1cgcH6EhYURGxsb0lbnh7QEK1eupF+/flRXVxMZGcm7775L586dWbFihc4LabFef/11li9fzpIlS+rU6TNDWqq+ffsya9YscnNzyc/P595772XgwIGsWrVK50UzpaCUiIhII5syZQqrVq0KyYEg0pLl5uayYsUKdu/ezVtvvcXEiRP5/PPPm7pbIk0mLy+P6667jnnz5uF0Opu6OyLHjFGjRgXvd+/enb59+5Kdnc2///1vXC5XE/ZMfi1N32sgiYmJWK3WOpn9d+zYQWpqahP1SuTYsvdc0HkiLdnVV1/NBx98wP/+9z8yMjKC5ampqbjdbkpLS0Pa6/yQliAsLIx27dpx0kkn8cADD9CjRw/+3//7fzovpMVatmwZhYWF9OzZE5vNhs1m4/PPP+fJJ5/EZrORkpKic0MEiI2NpUOHDvz888/6zGimFJRqIGFhYZx00knMnz8/WOb3+5k/fz79+vVrwp6JHDvatGlDampqyHmyZ88eFi1apPNEjnumaXL11Vfz7rvv8umnn9KmTZuQ+pNOOgm73R5yfqxbt44tW7bo/JAWx+/3U1NTo/NCWqyhQ4eycuVKVqxYEbz16tWLCRMmBO/r3BCB8vJy1q9fT1pamj4zmilN32tAN954IxMnTqRXr1706dOHJ554goqKCn7/+983dddEGk15eTk///xz8PHGjRtZsWIF8fHxZGVlcf3113P//ffTvn172rRpw1133UV6ejrnnHNO03VapBFMmTKFV199lffee4+oqKhgboOYmBhcLhcxMTFcfvnl3HjjjcTHxxMdHc0111xDv379OPnkk5u49yJHzx133MGoUaPIysqirKyMV199lc8++4yPPvpI54W0WFFRUcGcg3tFRESQkJAQLNe5IS3RzTffzOjRo8nOzmb79u3cc889WK1Wxo8fr8+MZkpBqQZ0wQUXUFRUxN13301BQQEnnHACc+fOrZPUWeR4tnTpUk477bTg4xtvvBGAiRMnMmvWLG699VYqKiq48sorKS0tZcCAAcydO1f5EuS49+yzzwJw6qmnhpTPnDmTSZMmAfD4449jsVgYO3YsNTU1jBgxgmeeeaaReyrSuAoLC7n00kvJz88nJiaG7t2789FHHzF8+HBA54XIgejckJZo69atjB8/nuLiYpKSkhgwYAALFy4kKSkJ0HnRHBmmaZpN3QkREREREREREWlZlFNKREREREREREQanYJSIiIiIiIiIiLS6BSUEhERERERERGRRqeglIiIiIiIiIiINDoFpUREREREREREpNEpKCUiIiIiIiIiIo1OQSkREREREREREWl0CkqJiIiIiIiIiEijU1BKREREpJEYhsF//vOfpu6GiIiIyDFBQSkRERFpESZNmoRhGHVuI0eObOquiYiIiLRItqbugIiIiEhjGTlyJDNnzgwpczgcTdQbERERkZZNI6VERESkxXA4HKSmpobc4uLigMDUumeffZZRo0bhcrnIycnhrbfeCnn+ypUrGTJkCC6Xi4SEBK688krKy8tD2rzwwgt06dIFh8NBWloaV199dUj9zp07OffccwkPD6d9+/bMnj376B60iIiIyDFKQSkRERGRWnfddRdjx47lu+++Y8KECVx44YWsWbMGgIqKCkaMGEFcXBxLlizhzTff5JNPPgkJOj377LNMmTKFK6+8kpUrVzJ79mzatWsXso97772XcePG8f3333PGGWcwYcIEdu3a1ajHKSIiInIsMEzTNJu6EyIiIiJH26RJk3j55ZdxOp0h5XfeeSd33nknhmEwefJknn322WDdySefTM+ePXnmmWf45z//yW233UZeXh4REREAfPjhh4wePZrt27eTkpJCq1at+P3vf8/9999fbx8Mw+DPf/4z06ZNAwKBrsjISObMmaPcViIiItLiKKeUiIiItBinnXZaSNAJID4+Pni/X79+IXX9+vVjxYoVAKxZs4YePXoEA1IA/fv3x+/3s27dOgzDYPv27QwdOvSgfejevXvwfkREBNHR0RQWFv7aQxIRERFpthSUEhERkRYjIiKiznS6huJyuQ6rnd1uD3lsGAZ+v/9odElERETkmKacUiIiIiK1Fi5cWOdxp06dAOjUqRPfffcdFRUVwfoFCxZgsVjIzc0lKiqK1q1bM3/+/Ebts4iIiEhzpZFSIiIi0mLU1NRQUFAQUmaz2UhMTATgzTffpFevXgwYMIBXXnmFxYsXM2PGDAAmTJjAPffcw8SJE5k6dSpFRUVcc801XHLJJaSkpAAwdepUJk+eTHJyMqNGjaKsrIwFCxZwzTXXNO6BioiIiDQDCkqJiIhIizF37lzS0tJCynJzc1m7di0QWBnv9ddf549//CNpaWm89tprdO7cGYDw8HA++ugjrrvuOnr37k14eDhjx47lscceC25r4sSJVFdX8/jjj3PzzTeTmJjIeeed13gHKCIiItKMaPU9EREREQK5nd59913OOeecpu6KiIiISIugnFIiIiIiIiIiItLoFJQSEREREREREZFGp5xSIiIiIoAyGoiIiIg0Lo2UEhERERERERGRRqeglIiIiIiIiIiINDoFpUREREREREREpNEpKCUiIiIiIiIiIo1OQSkREREREREREWl0CkqJiIiIiIiIiEijU1BKREREREREREQanYJSIiIiIiIiIiLS6BSUEhERERERERGRRvf/AW/HUVIk9euZAAAAAElFTkSuQmCC","text/plain":["<Figure size 1200x600 with 2 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":"fig, ax1 = plt.subplots(figsize=(12, 6))\n\ncolor_acc = \"tab:blue\"\nax1.set_xlabel(\"Epoch\")\nax1.set_ylabel(\"Accuracy (%)\", color=color_acc)\nax1.plot(range(1, len(train_accuracies)+1), train_accuracies, label=\"Train Accuracy\", color=\"tab:red\", markersize=3)\nax1.plot(range(1, len(dev_accuracies)+1), dev_accuracies, label=\"Dev Accuracy\", color=\"tab:blue\",  markersize=3)\nax1.tick_params(axis='y', labelcolor=color_acc)\nax1.legend(loc=\"lower left\")\n\nax2 = ax1.twinx()\ncolor_loss = \"tab:red\"\nax2.set_ylabel(\"Loss\", color=color_loss)\nax2.plot(range(1, len(train_losses)+1), train_losses, label=\"Train Loss\", color=\"tab:red\", linestyle='--',  markersize=3)\nax2.plot(range(1, len(dev_losses)+1), dev_losses, label=\"Dev Loss\", color=\"tab:blue\", linestyle='--', markersize=3)\nax2.tick_params(axis='y', labelcolor=color_loss)\nax2.legend(loc=\"lower right\")\n\nplt.title(\"Accuracy and Loss per Epoch (ResNet50 on CIFAR-10)\")\nplt.tight_layout()\nplt.show()"}],"metadata":{"kaggle":{"accelerator":"gpu","dataSources":[{"databundleVersionId":46718,"sourceId":3649,"sourceType":"competition"}],"dockerImageVersionId":31011,"isGpuEnabled":true,"isInternetEnabled":true,"language":"python","sourceType":"notebook"},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.11.11"}},"nbformat":4,"nbformat_minor":4}