Is_YusufovYB/labworks/LW3/IS_LR3.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4","mount_file_id":"1gkrpjeAWlWtOnSgGJKnb8Wk0XgcP3TKN","authorship_tag":"ABX9TyMJfjzH39xmfrJyANBInNm2"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"code","execution_count":5,"metadata":{"id":"8Eaox8MSUny_","executionInfo":{"status":"ok","timestamp":1765239810073,"user_tz":-180,"elapsed":664,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}}},"outputs":[],"source":["import os\n","os.chdir('/content/drive/MyDrive/Colab Notebooks/IS_LR3')"]},{"cell_type":"code","source":["# импорт модулей\n","from tensorflow import keras\n","from tensorflow.keras import layers\n","from tensorflow.keras.models import Sequential\n","import matplotlib.pyplot as plt\n","import numpy as np\n","from sklearn.metrics import classification_report, confusion_matrix\n","from sklearn.metrics import ConfusionMatrixDisplay\n","from sklearn.model_selection import train_test_split"],"metadata":{"id":"dnl7MSY3VEeG","executionInfo":{"status":"ok","timestamp":1765239844707,"user_tz":-180,"elapsed":79,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}}},"execution_count":7,"outputs":[]},{"cell_type":"code","source":["# загрузка датасета\n","from keras.datasets import mnist\n","(X_train, y_train), (X_test, y_test) = mnist.load_data()"],"metadata":{"id":"3VzhqxxVVJiu","executionInfo":{"status":"ok","timestamp":1765237242369,"user_tz":-180,"elapsed":385,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}}},"execution_count":9,"outputs":[]},{"cell_type":"code","source":["# создание своего разбиения датасета\n","from sklearn.model_selection import train_test_split\n","# объединяем в один набор\n","X = np.concatenate((X_train, X_test))\n","y = np.concatenate((y_train, y_test))\n","# разбиваем по вариантам\n","X_train, X_test, y_train, y_test = train_test_split(X, y,\n"," test_size = 10000,\n"," train_size = 60000,\n"," random_state = 35)\n","# вывод размерностей\n","print('Shape of X train:', X_train.shape)\n","print('Shape of y train:', y_train.shape)\n","print('Shape of X test:', X_test.shape)\n","print('Shape of y test:', y_test.shape)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"5Al6fTwNVK19","executionInfo":{"status":"ok","timestamp":1765237243968,"user_tz":-180,"elapsed":50,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"dc443592-c765-485b-d700-1ec98f808c82"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of X train: (60000, 28, 28)\n","Shape of y train: (60000,)\n","Shape of X test: (10000, 28, 28)\n","Shape of y test: (10000,)\n"]}]},{"cell_type":"code","source":["# Зададим параметры данных и модели\n","num_classes = 10\n","input_shape = (28, 28, 1)\n","# Приведение входных данных к диапазону [0, 1]\n","X_train = X_train / 255\n","X_test = X_test / 255\n","# Расширяем размерность входных данных, чтобы каждое изображение имело\n","# размерность (высота, ширина, количество каналов)\n","X_train = np.expand_dims(X_train, -1)\n","X_test = np.expand_dims(X_test, -1)\n","print('Shape of transformed X train:', X_train.shape)\n","print('Shape of transformed X test:', X_test.shape)\n","# переведем метки в one-hot\n","y_train = keras.utils.to_categorical(y_train, num_classes)\n","y_test = keras.utils.to_categorical(y_test, num_classes)\n","print('Shape of transformed y train:', y_train.shape)\n","print('Shape of transformed y test:', y_test.shape)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"FbJZLGLGVSmT","executionInfo":{"status":"ok","timestamp":1765237248168,"user_tz":-180,"elapsed":160,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"043c5967-826b-406c-dd6a-0b1ef3a1cd79"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of transformed X train: (60000, 28, 28, 1)\n","Shape of transformed X test: (10000, 28, 28, 1)\n","Shape of transformed y train: (60000, 10)\n","Shape of transformed y test: (10000, 10)\n"]}]},{"cell_type":"code","source":["# создаем модель\n","model = Sequential()\n","model.add(layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\", input_shape=input_shape))\n","model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n","model.add(layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"))\n","model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n","model.add(layers.Dropout(0.5))\n","model.add(layers.Flatten())\n","model.add(layers.Dense(num_classes, activation=\"softmax\"))\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":408},"id":"2Va1fgxMV1t9","executionInfo":{"status":"ok","timestamp":1765237286023,"user_tz":-180,"elapsed":343,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"3e355b8f-a860-4d66-ddfd-7b087f5eca8c"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │           \u001b[38;5;34m320\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1600\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)             │        \u001b[38;5;34m16,010\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">26</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">26</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">320</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">11</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">11</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1600</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)             │        <span style=\"color: #00af00; text-decoration-color: #00af00\">16,010</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m34,826\u001b[0m (136.04 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">34,826</span> (136.04 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m34,826\u001b[0m (136.04 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">34,826</span> (136.04 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}}]},{"cell_type":"code","source":["# компилируем и обучаем модель\n","batch_size = 512\n","epochs = 15\n","model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n","model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Y92HKIZ6WBd6","executionInfo":{"status":"ok","timestamp":1765237942967,"user_tz":-180,"elapsed":609222,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"2c6af7bf-2f0a-4d49-f6c1-a99f57038563"},"execution_count":13,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 379ms/step - accuracy: 0.5997 - loss: 1.3087 - val_accuracy: 0.9533 - val_loss: 0.1712\n","Epoch 2/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 392ms/step - accuracy: 0.9412 - loss: 0.1983 - val_accuracy: 0.9698 - val_loss: 0.1051\n","Epoch 3/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 367ms/step - accuracy: 0.9598 - loss: 0.1331 - val_accuracy: 0.9762 - val_loss: 0.0813\n","Epoch 4/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 381ms/step - accuracy: 0.9675 - loss: 0.1109 - val_accuracy: 0.9772 - val_loss: 0.0718\n","Epoch 5/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 380ms/step - accuracy: 0.9724 - loss: 0.0904 - val_accuracy: 0.9807 - val_loss: 0.0629\n","Epoch 6/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 381ms/step - accuracy: 0.9761 - loss: 0.0784 - val_accuracy: 0.9823 - val_loss: 0.0551\n","Epoch 7/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 384ms/step - accuracy: 0.9785 - loss: 0.0687 - val_accuracy: 0.9827 - val_loss: 0.0518\n","Epoch 8/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 364ms/step - accuracy: 0.9812 - loss: 0.0622 - val_accuracy: 0.9842 - val_loss: 0.0484\n","Epoch 9/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 356ms/step - accuracy: 0.9818 - loss: 0.0592 - val_accuracy: 0.9850 - val_loss: 0.0452\n","Epoch 10/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 355ms/step - accuracy: 0.9829 - loss: 0.0551 - val_accuracy: 0.9853 - val_loss: 0.0440\n","Epoch 11/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 357ms/step - accuracy: 0.9837 - loss: 0.0530 - val_accuracy: 0.9868 - val_loss: 0.0413\n","Epoch 12/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 359ms/step - accuracy: 0.9851 - loss: 0.0479 - val_accuracy: 0.9870 - val_loss: 0.0394\n","Epoch 13/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 375ms/step - accuracy: 0.9850 - loss: 0.0482 - val_accuracy: 0.9875 - val_loss: 0.0397\n","Epoch 14/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m41s\u001b[0m 371ms/step - accuracy: 0.9851 - loss: 0.0455 - val_accuracy: 0.9883 - val_loss: 0.0372\n","Epoch 15/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 370ms/step - accuracy: 0.9864 - loss: 0.0406 - val_accuracy: 0.9875 - val_loss: 0.0384\n"]},{"output_type":"execute_result","data":{"text/plain":["<keras.src.callbacks.history.History at 0x7a39d3d1b3b0>"]},"metadata":{},"execution_count":13}]},{"cell_type":"code","source":["# Оценка качества работы модели на тестовых данных\n","scores = model.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ebQfy_5VYbxh","executionInfo":{"status":"ok","timestamp":1765237970426,"user_tz":-180,"elapsed":4483,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"cc364784-69a1-434d-a2c6-df5d1e646395"},"execution_count":14,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 12ms/step - accuracy: 0.9876 - loss: 0.0382\n","Loss on test data: 0.03760423883795738\n","Accuracy on test data: 0.9884999990463257\n"]}]},{"cell_type":"code","source":["# вывод тестового изображения и результата распознавания\n","for n in [67, 69]:\n","  result = model.predict(X_test[n:n+1])\n","  print('NN output:', result)\n","  plt.imshow(X_test[n].reshape(28,28), cmap=plt.get_cmap('gray'))\n","  plt.show()\n","  print('Real mark: ', np.argmax(y_test[n]))\n","  print('NN answer: ', np.argmax(result))\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"9_djwHpkYwhw","executionInfo":{"status":"ok","timestamp":1765238265238,"user_tz":-180,"elapsed":420,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"bee94607-956b-4363-84db-1e35911e4b00"},"execution_count":18,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step\n","NN output: [[6.4946892e-10 3.8115243e-07 1.6316299e-07 9.9963105e-01 1.6378403e-08\n","  2.3533788e-04 1.6841338e-10 4.0841002e-08 3.6364984e-06 1.2934272e-04]]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark:  3\n","NN answer:  3\n","\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n","NN output: [[2.2877561e-08 9.9993885e-01 1.9471462e-07 6.8260057e-08 4.9374252e-05\n","  1.3361741e-07 3.9278180e-07 4.0640666e-06 6.2291774e-06 6.9445946e-07]]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark:  1\n","NN answer:  1\n"]}]},{"cell_type":"code","source":["# истинные метки классов\n","true_labels = np.argmax(y_test, axis=1)\n","# предсказанные метки классов\n","predicted_labels = np.argmax(model.predict(X_test), axis=1)\n","# отчет о качестве классификации\n","print(classification_report(true_labels, predicted_labels))\n","# вычисление матрицы ошибок\n","conf_matrix = confusion_matrix(true_labels, predicted_labels)\n","# отрисовка матрицы ошибок в виде \"тепловой карты\"\n","display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix)\n","display.plot()\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":761},"id":"frA_gOKkaI3_","executionInfo":{"status":"ok","timestamp":1765238422903,"user_tz":-180,"elapsed":10085,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"01391cfc-a0a1-4150-cf08-ab5ffed75ae9"},"execution_count":19,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 28ms/step\n","              precision    recall  f1-score   support\n","\n","           0       0.99      1.00      0.99       965\n","           1       0.99      0.99      0.99      1115\n","           2       0.99      0.99      0.99      1020\n","           3       1.00      0.99      0.99      1075\n","           4       0.99      0.99      0.99       959\n","           5       0.98      0.99      0.99       909\n","           6       0.99      0.99      0.99       970\n","           7       0.98      0.99      0.99      1050\n","           8       0.98      0.97      0.98       972\n","           9       0.99      0.98      0.99       965\n","\n","    accuracy                           0.99     10000\n","   macro avg       0.99      0.99      0.99     10000\n","weighted avg       0.99      0.99      0.99     10000\n","\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 2 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["# загрузка собственного изображения\n","from PIL import Image\n","file_data = Image.open('2.png')\n","file_data = file_data.convert('L') # перевод в градации серого\n","test_img = np.array(file_data)\n","# вывод собственного изображения\n","plt.imshow(test_img, cmap=plt.get_cmap('gray'))\n","plt.show()\n","# предобработка\n","test_img = test_img / 255\n","test_img = np.reshape(test_img, (1,28,28,1))\n","# распознавание\n","result = model.predict(test_img)\n","print('I think it\\'s ', np.argmax(result))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":465},"id":"V3Queia6aglS","executionInfo":{"status":"ok","timestamp":1765238579010,"user_tz":-180,"elapsed":849,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"87b90dbf-7bfa-4a0b-f3c9-a39120774c7c"},"execution_count":20,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 165ms/step\n","I think it's  2\n"]}]},{"cell_type":"code","source":["model_lr1 = keras.models.load_model(\"/content/drive/MyDrive/Colab Notebooks/IS_LR3/best_model_2l_100_LR1.keras\")\n","model_lr1.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":209},"id":"cjLq6V3qbP4U","executionInfo":{"status":"ok","timestamp":1765238742813,"user_tz":-180,"elapsed":103,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"9c22b0ee-5f9d-4714-9515-a4ada75791cc"},"execution_count":21,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_1\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_1\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m)            │        \u001b[38;5;34m78,500\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)             │         \u001b[38;5;34m1,010\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">78,500</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,010</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m79,512\u001b[0m (310.60 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">79,512</span> (310.60 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m79,510\u001b[0m (310.59 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">79,510</span> (310.59 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m2\u001b[0m (12.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Optimizer params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">2</span> (12.00 B)\n","</pre>\n"]},"metadata":{}}]},{"cell_type":"code","source":["X_train, X_test, y_train, y_test = train_test_split(X, y,\n","                                                    test_size = 10000,\n","                                                    train_size = 60000,\n","                                                    random_state = 35)\n","num_pixels = X_train.shape[1] * X_train.shape[2]\n","X_train = X_train.reshape(X_train.shape[0], num_pixels) / 255\n","X_test = X_test.reshape(X_test.shape[0], num_pixels) / 255\n","print('Shape of transformed X train:', X_train.shape)\n","print('Shape of transformed X train:', X_test.shape)\n","\n","# переведем метки в one-hot\n","y_train = keras.utils.to_categorical(y_train, num_classes)\n","y_test = keras.utils.to_categorical(y_test, num_classes)\n","print('Shape of transformed y train:', y_train.shape)\n","print('Shape of transformed y test:', y_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"-w2XrJqrb0Qk","executionInfo":{"status":"ok","timestamp":1765238860632,"user_tz":-180,"elapsed":1366,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"1fef36c3-6b34-48d0-d5fa-6bd2b996856c"},"execution_count":22,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of transformed X train: (60000, 784)\n","Shape of transformed X train: (10000, 784)\n","Shape of transformed y train: (60000, 10)\n","Shape of transformed y test: (10000, 10)\n"]}]},{"cell_type":"code","source":["# Оценка качества работы модели на тестовых данных\n","scores = model_lr1.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"M3VJoerVb8rW","executionInfo":{"status":"ok","timestamp":1765238891385,"user_tz":-180,"elapsed":4771,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"56d5e756-d6f8-4ee4-a33e-db32f219cde5"},"execution_count":23,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.9166 - loss: 0.3003\n","Loss on test data: 0.3069264590740204\n","Accuracy on test data: 0.9150000214576721\n"]}]},{"cell_type":"code","source":["# загрузка датасета\n","from keras.datasets import cifar10\n","(X_train, y_train), (X_test, y_test) = cifar10.load_data()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"T9k32HbZcuGf","executionInfo":{"status":"ok","timestamp":1765239800398,"user_tz":-180,"elapsed":12853,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"2ccb8643-f330-4e6c-a6e3-76d9de3c82c5"},"execution_count":2,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n","\u001b[1m170498071/170498071\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 0us/step\n"]}]},{"cell_type":"code","source":["# создание своего разбиения датасета\n","\n","# объединяем в один набор\n","X = np.concatenate((X_train, X_test))\n","y = np.concatenate((y_train, y_test))\n","\n","# разбиваем по вариантам\n","X_train, X_test, y_train, y_test = train_test_split(X, y,\n","                                                    test_size = 10000,\n","                                                    train_size = 50000,\n","                                                    random_state = 35)\n","# вывод размерностей\n","print('Shape of X train:', X_train.shape)\n","print('Shape of y train:', y_train.shape)\n","print('Shape of X test:', X_test.shape)\n","print('Shape of y test:', y_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"nP5ZVWTbeJj1","executionInfo":{"status":"ok","timestamp":1765239855697,"user_tz":-180,"elapsed":134,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"66d6f70c-4774-4373-8db0-aadfb2e4f817"},"execution_count":8,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of X train: (50000, 32, 32, 3)\n","Shape of y train: (50000, 1)\n","Shape of X test: (10000, 32, 32, 3)\n","Shape of y test: (10000, 1)\n"]}]},{"cell_type":"code","source":["class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',\n"," 'dog', 'frog', 'horse', 'ship', 'truck']\n","plt.figure(figsize=(10,10))\n","for i in range(25):\n"," plt.subplot(5,5,i+1)\n"," plt.xticks([])\n"," plt.yticks([])\n"," plt.grid(False)\n"," plt.imshow(X_train[i])\n"," plt.xlabel(class_names[y_train[i][0]])\n","plt.show()\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":826},"id":"oXnbRrUBcxPE","executionInfo":{"status":"ok","timestamp":1765239859750,"user_tz":-180,"elapsed":765,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"0d4d6261-4ee7-4258-a5ff-e5affa16cd14"},"execution_count":9,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 1000x1000 with 25 Axes>"],"image/png":"iVBORw0KGgoAAAANSUhEUgAAAxoAAAMpCAYAAACDrkVRAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs/XeUZNl93wn+ng+fkd6Ud13daHQ3uhtogABJgAIpkAQdhnuGZwkJ4jkEqRGXbiWBoMSVMHSaER20HFJnJZ5ZQUejHUoaiSMNKVAkAILwti3aVHV1+UqfkZHh49n9I7Oy8vu9r8sQUVkN8vfBaZy6GRHP3HfNexHf7/1aWZZloiiKoiiKoiiKMkLse30AiqIoiqIoiqL85UMfNBRFURRFURRFGTn6oKEoiqIoiqIoysjRBw1FURRFURRFUUaOPmgoiqIoiqIoijJy9EFDURRFURRFUZSRow8aiqIoiqIoiqKMHPd23pSmqSwuLkq1WhXLsu72MSnfAGRZJu12WxYWFsS27+7zqrY/hdnP9ieibVBBtP0p9xqdg5V7yZ20v9t60FhcXJRDhw6N5OCUv1xcuXJFDh48eFf3oe1PeTX2o/2JaBtU8tH2p9xrdA5W7iW30/5u60GjWq2KiMivvPmwFNztJ5dM8KnWfMg1A8cdG/+2EgVQ3uwnUD4+jocXWBGU05xMc36u4qdvh568LDqPhN6/MsCdDFPP2OehGn7GT3pQjm0HylGC5xGFuA/fLxj7cN0UypmF27zSCKEcUl0drZWh7A27xj4GFm4ji3Cf7p7aHcSp/IMvrO22jbvJ9X381E/+hATBdpv5+J/8CR6bi9c1jfFcRERsaqOVItbzxMQElKMkhvLmxhaU48T8Zmd2eh6PI8M6XFldhLJLzak/GODnBd/g8gdExKUTq1XwWldLRSj3ui0oRxGeZ5bz7YTl+lAue1iu+sFNX0+iIZSn52eNfTg+nlsnxPN6z3//3t1/d7td+e7/2/ftS/sTudEGj77jHWK72+NSa/EKvGd8Cifi2B83tmPZ2B5kgG2qmGK/lQjHxLV1fL87Vjf2EdewXVcXZvAzuEmJNjah3Fi8AGWvOAbl6ZnDxj6bK6tQ9lPsf8VqBfcZ43mOjeF1PHTkgLGPNMW6i1I8kQHVXWeIfcmjqo962CZFRGamsF1O1OpQbm41tz8bhvLH//Zf7Xv7+//805+XYmH7+paKeELX/36d9Q3s5yIiEuOcOqTr9OxL56AcDftQfupFfH1xBduOiMh4HcfRTrcD5V4f58eJcWxfQQHHgclx3F6xWDL2OaTxxXOxLmp0HX0aawbUVjodPEYREdvB8YjHzTDEY3BdnKOnp6eh3O2a+yiVsD3NL2B7rFRu9KPhcCi/9j9/eF/n4N/9n/7BbjtLUpo3spg+RQONiKSCbTbOec9efB/nkTjGffS65n2MZ2EbLxZx/vM8nN8cugsuBNg2HA/LtmXOwTbd41l8a51h24lTLA/o9aCIc7iIiGtjXdg27sPzcA7u9rFvD4dY9+OTOC+IiIyNTUG5XMU5LNtzq9rptOWb3/bwbbW/23rQuH6zXnBtKY7wQaOQ4cXxsSgF6qgFCytqJA8a1s0fNAox7SSlgxSRokcPGtTo+EHDtbFzOXQigWfuw3VxH/ygEbh8Xlgu0ja9JOdmkj6T0am7OZae/fgZ9fo+giDYfdBwHKpThx40MrMO+UGDJwLPo+5Ap8vvFzHP3aNBiR80XOO48fN8Xpbw+3PaBp2Y5/IA5N70db7QqZ1Td7xNKvt03gGVY5pgCjSBiJgPGhHVb6VsDr779TP+9f3Yriv2zrnZdC0cqpM056HQcuhul278eCzgCYr3afMsKSI27dehunZobk/o/Rbvg87L8cxrx8dh01jt0D5Smh94MvfowVVEJKUHC6EyT94u9z2qev4iZXu/eG5+ENDrWN7v9lcsFKS08wVJqYTHX6IHjV7P/LKF25tNdRZQH7To5pHHnzzJBI9h/B6bxiuHxm5jbL/FeCYikmbJTd/DDxZ8A5ukN/+8iIjt3Fwewu3TozmXjyEMzfGB3xNQ+ysUzC8h93MO3tv+bvWgkQk/eIziQQPrNEvMffCDRqlIffhWDxoF3Kd7Ww8auJE7fdCw6fVCzsO069zZg4ZQPTg095Rz5tO9D7IiIpVqDcoZ3xTK7bU/NYMriqIoiqIoijJybusXjeuke55HE/q2SIwvh8wnH/7WYEgqgZh/0k/oGykLn15zf9Gw8I/8bUqa3vzpK2OZU8xP4DnnRd+eZ8I/6eM+N7p44nZKP/VZ5j5K9EhoO/iemGQDqY11ldC3DVZqfhMQC24jowq29vyKYlz/fSDLst0n6gLJnsIB/sQfR9S4RCQwvuXCbwD4m7OQZCshfQNaCPDpf3sb+K3DtWvXoDwcYr17Hp5HQN/gsMzA5m/ERaRcxp8ux8bxm4poiD/p9yOSlNC3zTNT+POpiMjEBP4tCbF+m2trUN6KcZ/zM/j5Ws38NiWhn8VdkhAmg/aef5s/me8HYxNzu78QDNdQLtRtYLk/xDoREXHoW6m4j/KWzSHKTFgmEhTxWhfHzJ+tQ5KeDEkGMjWL8r5BiO18c5G+VaWv/IqOOYb6k/gTe5nkB70Qv12frE7iMVOb3Nw0JTn8LXO7h23ALd9cCtlYWsFj6phtaDPBa9Zex+Po74yzeePLfpBJKtnOZMtjjUVzV5KYYwX/Wl7zUVYyPYHfYDaa9CsR9UmWVIqIuAG+x6GxuUSykBrJ//gXDZqCxeFvbkWk4LDEFI8roGPib8r51+l+35TVWXQv4ZGSIa++9zI2Rn2kXDPeE9NNUJbRxL+3zK/tA0kSSZJsX5/MuOnDY09is4/wITs2/2LLEmicE7qtNpRzpDRSrmKbZkkh36zyeXCdW/R9fJrk/AqT8a9yfA9HihS6F7bp1wcrM/dhCCpYiRDhGMsSsPEJlCgWc9of/7poyAX3jOMpy3xvgv6ioSiKoiiKoijKyNEHDUVRFEVRFEVRRo4+aCiKoiiKoiiKMnLuzKORDiVJrz+bkOaMvQs57nQxvAeoQ+MVetjhnpFHI9/tTro1WhKRV7y41ect45jNFXkMJ36G2rUuLZEbu6hXrxZQ65/SkoIi5tJ5lSrrVFG7mHLdsp7OMjWA7G/JaJUwa882LWv/PRrz8/O7S9U98sgj8BqvPjHomfrrpcWrUG61cKnQhLYxVkdNY72O18l1zBVABgPU2A9DOg6q94x8MTW6rgUf65k9HCIi0zN1KCek79yiY7Jp1Y2ghOdRLJrn5VC/6FMbjajNx6RBTag9hjlt3CMNdJWWoXP37MM1llLcH9ygKO7ONRgfx368fukilNsr68bniwVsU9USXu9OH9vL2lYDyjNHjkO5UjV9QuMHcGnYy8voE9pc34DyZAV9HkePnoByv41jS9g2/RMJ+YCyENvp+Awu0+mQV2Biog7l5RVcBlpEJCbNN69SZrOnjOaozQbWpfRzNOQeemJi0t0Hle3xh1cv3C9s8cS+vuQ1eQON1Zo8c3WcInkVyjX8zNGjC1DOrmAb5lWPahVzdZwZupbjVXwP675LtPw2z6dBAT8/OYn+HhGRrS0cy1NqC4MBts9CAfc5HKK+fXbWXH673cF+wNtkHwjPJ+Pjk1Q2l79eWUafF597tmd1oizbnxXPcP+JZNfnF7oHSOgeI2/VKYu9DHQLmpAvsrGBYxV7a6Zy/IQVam++zytCcb3RapvGPST7Zsx7H/4Mt2H2dUTk8crI02GL6UPiOZhXWmOPI6/o5VGbd3K8dnxNeSWxYXjD7xdG5vLMr4b+oqEoiqIoiqIoysjRBw1FURRFURRFUUaOPmgoiqIoiqIoijJy7sijEaexxNc9GmRLYCtD3hMMSwotTtqkjVjspyBdbJbn0SDdmpXefI1kPibeZUCLFyc5ORwhnUa7g/rzblKHcnEcdbB+QLkHFmrqRUQ8F/VwXpE9MrhGvMeaQcrNSHLyQDLjqvFF3VMX9v57NMIw3M1FCWldfot0k4WCqXGsVLCe2dfBPhbbxbZUqVG6bM567q0t1NiXyjfXTfsBXseJOh5juYA63ry12qME66JFa41HdF4W5WYkpMvs9U1/S9jF9hdTe3IC0ovTmv4x6XX7Ofuo0jrzPulWV65d3P13t296PPaDsNuRZMd/YFt4jlVKWg2LmJEhImKR7ymJKP8lxHqOaG30bhe16P2cepin63vy8FEonzv/CpRPP34/lBs0Hj35uU9BeW0LddMiIr0eHsfcwSNQPn4a98Hth3X6nO0iYvZpTpvvki9rEGPdheQjGa+Y68hnNmcj4HFWrqfC53kQ9wHXKYrrbNcVe+qCAPXr5bLpnwgob6JUxFuAowfnoFwJ8LpYlHeSE/kkRw7i/OZSVgd/iL03XWpLPOSxF0JEpN3GvrbWwuNsdGkspwRkzqupj9eNfZy/cAHKW1s4zs5MT+NxUntl79v8HNaTiMj0FNb/+gb6ivb6cPL6/t0n3c0J43uKlMs5WRBC92McxdHtYh/O6OJP1HGOqOS0cdM/Sj5d6gMZ3dPFIedsYHt1jEALkYQ8GIM+3Z8YPhDKZPGx7OZ5iak+HZp/jNs33gbdI0WxmRXDdTUY4ny0sXEjZ4iv1c3QXzQURVEURVEURRk5+qChKIqiKIqiKMrI0QcNRVEURVEURVFGjj5oKIqiKIqiKIoycu7IDJ7IjYg9Num4FIJihqKI4S3mUB0TfA6yyKiS48s2npxcwzBDJlUyzKRk8E2H+PogMs24F7bQvN3eQiPQ/NQEHlOABqahhfu0CubzX5jhNpt9CtFKsC4r5HInD6okOc+YacL1bbj39/x7/83ggedLwd+uqzTEEzp39hy+1zfNpDOzGJjUSJtQZiPoVhuNUBnV8ewshq+JiAxCNOgVCmS+LKMhcDjEtpOQgbVYQGNup2MasHo9PE42q3nUFkIKRdraQiNlv2MG8VRL2GZdC4eOaIiGTp/6WWkCQ+HYzC8i0qRFFI6Nz0C5sXQjPKw3QLPnfpEO+2LtmB5TMgSvrmG4mZezWMWQjPl9MttNTKHZ8ZFjR6Hco5A2CcwAx8YamrVjCl2qlvFabJDhdH0Vz2NIba7bMIMIyzU0VrO5u9HAkL/qGJpxh2TUro2ZRu0eh3DyEHSL+WV6Fo22bs4Q5pNxeZPqMlzfPvckMsP+9gPHCsTZmS8cGtRdh4LJcubHlJqP5eJnChYFb3bJ8FzB+jmwgHUqIlKrUgAfzcFs9Oe7gB4tPNEio7fvm2bcqTK2lxqZ3Cd6eLE3+xR25uExGwZ2ESnT4gFVOs56lY6BAl+TGM+UQwZFRGapjfICB6XijfnAzwlkvNtkkuyawTmgLyFTv21eJhnSuN2jMd/z8LpNU/hjMcBzdnIWZRgMaJzI8P4qoEC/iMzfFi065FC/4pBdEZFuB+fxcEjhv2N4D2iYwSk8z8u7fab67VCAZBjhPssTuDhBnODnjfFURFzqBzbN00tLS3s+r4F9iqIoiqIoiqLcQ/RBQ1EURVEURVGUkaMPGoqiKIqiKIqijJw78mhYmSPWTuCdTfpA2yJ9f45A1HVQF+mSdpzD9SyhwBcOLMkxabgpHQdpmiPBcitEXdtyE7V2q33U9232zJCTKEX98SRpNeMA9ciNIQVLDUirGZr680KE76lSEFzmkKbUpZA2CkfMkjyNMQUm5vls7iFrSytSCLavx5Vzl+G1tEuhc10zzOhy7yqUuzFqf4sV9E8kMdaxTWGPG2tmIFtjvQnlIMAutjdwSUQkSbCOm01sG5026jCLJfRsiIiE5K3pdLGNDkgvOiQ/hdFXzV1IwmGaMfZFO8RtVIrY5qs+6pWHjtnGOxQG1qXQo4NzB3b/XfDvTWBfd3Nd7B1de9TCa9UjT0/RM4fXfoyfqddRL/wjP/JeKL/lTU9A+UtPPQvls2umztb2sB03mzg+lWt4bdpba1BOyGc0N4tembHA1EWXq7jNuXnUB/tFbPeDLvmCSGu9udU09hHRmDWgcMMx8sJFQzyPAenBS4Gpw+cEV9fHa3g9GC6JsU/tF5ZXFMvbbjMO+aakhHPVxCxeAxEzw8u3sc+tr56H8mYDr9PWJo5Hk5PoexMRKVXwuAo+tkffR19RFOJYMhziPlMKQ7Mt05sQkrct6+N86Q3wehUFr303xW3m2Uenp7EfsE8npuNkb8nk1BSUSzlhcwmF3tXHcNwslW70M67H/SBOo93Q5oz6gMXXKaeLxBRy6MXY/kp0n+JRH3baNN71zfDGQQ89Z10L66lwGCc4O0DPmlPAscryKPw4zglUTnDOTXr4nkINr2NA4cFuiu23ffWisY/GKp7X2hqWl8lb9/q3fxuUp4+fhPLKyqqxj2oN+/PMHNZdq9Xc/fedBEbqLxqKoiiKoiiKoowcfdBQFEVRFEVRFGXk6IOGoiiKoiiKoigj5448GllqS7ajz6NIAYl5zeTMXKSc19aPbdTXxaRfF1rTV2zURKaWefhD8m0MaLn+pTbqyi5sopZzuY/7iFzU/YaRKd70eN3lHooTl1ZRIx3QWtD9CA8yjU0fSJHWwpciHlfike7Qx/PIbPZkmOeRss5VaM3qPeeZ5axffbdxs1TcnXZ1dB71ss4cXvfFRfRjiIisbaImsRjgZ6aKWIeejxraLuVLdFvmOug21QtZGwwvU6GM2s3NPRpIEZFl8myUcpauLhWwH4UhXutwgO3Jc1F3WSLfx8wkZjmIiBw9uADlhPrJVgProl7F80odPAbHMwW8WZ9ySyzU7/b3eJkGw3uToyHhUKx0W4u8ubIML5ULrE03NdQ1H3X0jz/2eig/dN8pKGcdrNcjNRwT52bNHIOghH6JAWUhCI0lMWUiDV5/P5RD0uKGPbPd9+g4JyZwfKrQOvLXVlBPfGUZyxfOYS6OiIhPGTRWhm1gcxF9WyFp/2PyJm2SBVBEpEJ5DJPT6HPo7nhL2DewX/T73d08qbmjB+G1ucNHoZxx5oqIpAP0DaycfxrKG6Tz5jwiHvftvO8qaQ7u0yRcLKImPnFo/X+6Bh7lZkQ5HkbhcZcyB5J2E99ukabexj6QFEyj2oD6QUae0kGC5xHQ4M9+C9cx626c3sNxLaXyjePyvP33aCRpIsn1ts99gOadJDKzkqpFPOYy5QCFYRPKgzbeO9kD9D5EtlkHWYrXiW21WwHWcX3+KL6BsmU4ksuJzEk4bK5AefXsWXzDKt2PUJaaS/vcWmsa+9ikv5WrOKauX7sC5QvnzkB5/gTOLUFOHk1jA/16Ac1pm40buUKDO8iy0l80FEVRFEVRFEUZOfqgoSiKoiiKoijKyNEHDUVRFEVRFEVRRs4deTSSLJXrcl5WWCe08LSds4Z8lKGebivBcjNGzePlTVpDOSatsJWjQXVQUNcZ4nEt9VFXuBjSOsExvr9AOkvHNs/Lc/BvKWk3WWhpkT/CdfGYtlJT+7ZO60dvkq666OJ5l6qok22TrtCJzH3YfA1JN5i9yr/3i2q5KIUdP4JtYZ1OUDZArXhAmOkGrbntYh2VqqgdDqk9BrQIfWPT1KC6tI1SBY8rIh3v5iZqpgfUdEoV1GH6jlnzNuULLIyhrtKu0jr2lB9g2dh2CrapP5/y8TuJ0jiut71RxG0Uy6hxZjtVp2fmP2Q21ucDjzwA5a3GDX1u7N2bjJfG1UWxdrxK6RCPd/YAaubf/KY3Gp+//zR6XeZm6lC2LKz7PvXTYgXHq6plfldU9XBcLExT1gGt1e+6pIH3cJuDIYmcY2yT25tkXxm209jF9lCnrIVqCdvo5YuY5yAi8sqlS7hPai9D1gxT7s30NPpZnByPX38L+2NE/qeJHT9TEsdiusDuPluNKxIWtn0+rnUCXiuT12qQ4yNZWVqC8nNPfx7KwzZ6NGbmDkHZofGn1zMzBeYW0NcS0Zg2iLCtRBEeZ8qZPTS/2rbZ5iPybA3ouHzyYMQ0x65t4TGtr28IMwixvVXqdXyd2p/n4Njv0nEHnpkH4tN9U0y+yb3+zii6o9u3kZBllmQ7WTMJZSkJzUPVsplTM10n70uC80CLsomsDD1trkvXPjXzwFyav/jewM3wPjKl3A2ha9Bp4L3T0pmXjH0uv/A1KNfoMF1q02uUbWRT7lSlVDf24fG50jg+MYGf4fGwuYl9O8rJOWFr9XCA597f06/Uo6EoiqIoiqIoyj1FHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSORX5xFEu/oXi2bdZO0PvLYvPF5r4Qa5maIurXUvob7ozWXu7QW9lrL1FF2Q9SUDVJ8lmqnqEceZqSJTFHfx3khqZi6/CjBbdq0RrJN+lCHNIIurTue5YjnqKqkT1o6O2U9Lp43a1iz1NS4ez5qKm3Salt79JH3QiG/0lyXYGfd7SsrF+G1LEXdeLVk6kMnplAfmlLbEMp56WxhNsBkDdffnh438yYuXkXl9sYG6j/7tNY4ZxiIgzV77Ahq+r/9bY8Z+5zwcRtpG/vFOGllQ9JEX7qCuu0s5+KOF7HdV8ex3zg+1u1KE7XuWYJ1Xa7jWvkiIkdPHoPy4QfQoyHWDb1uu2Nqw/eDpDcQa8cXwXLht3/LW6H8ugdOG5+fm0DNcYGyXK4s4Rg4s4C+giMnsI7Wz+O1ExFJB6hzTmnMy0hLHXLmAPlfMvJbZJmp/c/Ie+RTXkivi33JJ3/EqcN4nlM/+G5jH3/40f8G5edfeRnKlov77PdxzEtiPMYh5SKIiIQtbFeXN5tQdnfGH8OHt0/UZiakVNz2jbjka2EjVBqZeUwrVzFr5OyLL0DZt7GOirSPWfIUZYm5jy5lqgRV7OuDIbbPfh/HlojDIygjIy+/qNvG8Sak9sgZUYUA+4Qn2Fas0Ly+Lnv2LNL+l8lPQDkFHJtR5usnIj75qzgrYe/M690Dn1qWbP8nItLt4nWcquF9z8wMecNExBVsL401vG59Cr1IyeAT0Pzo5N3BpjQ30bzea2Mfb27hOFCs4lz2ysvYZz73Z18wdhmQj+3xB05CuZ/gHDyMsA3bMd63FiyzbYRU380OtlmngPuYoDl2ZXkRyo0G1r2IyMLB41DmMaS5ccPnMQzNe+FXQ3/RUBRFURRFURRl5OiDhqIoiqIoiqIoI0cfNBRFURRFURRFGTl35NFI01SSnfWAPVLp8/rPwvp3ERHK0SiVsRz0UVM2fwDXCS9QVkRt3Vxr/eKVs1Ae0rrM2ZAyLUi365I005Wb65VFRBL2Ozh4XlGG+6wYy2djXY0VA36DFAv4t4z0yAnp5VLybLgkEHUdM4PEdvG4fcr38Pasoc65KfvB7OG53RyNxsZheO3w7BSU15dM7Xq3h1rMLWobLl03z6Jrn2Add/qoqxQRSciD4VM9WwUsp7fYx3BzFcpO1/QlfdNDD0K5GGOWRzak86ZMljEbvSf9yNRezhzE+nXJr1IgnevJ190H5dIYrq1fKNB66iKS0br/1YkZKJfrN46h1DL1pftBEBR21/H3yMP02BsegvJwYGaFnHkBxyyftOJPvfA8lDPKuHjPD74HygcWZo19FOgz7CWJQ9TdhuTfinjsJiF0luX0fcrzsKldx1cuQrnXa+IxBqhJPjRjntfP/cz/A8pffBrr6pmvod/ghTM4F6yR36LZMPuSdMnLRm0y3MlOya2DfaA6PiPl0rYW3g+wD9mU81Mpmn3syDHsl6mFk9FWCz1lr7yMdXhwAX2W9TqOAyIi7RaOWXGG7S2j+4BuH+fgHmnRiwEeY97Ukwn5kOj69Aekw6d8lJka6tvT2Oy7Gz0cc4Zb2DbKY+hJKFO/aSxegfKTX/qysY/v/O6/DuUjx49AeRDe2OdwaB7j3abXHUq6Y1yNyetXIi9gFJseqNVVnJeba5jt0NpC/0SHcm2OHMRxoWzeTElviDdx7Q7282aTfAcdPM6gQNlqTTymzQ3TH1grYz+4QtPTSm8NyiUa9zPKpFhcNlN6PMpd8SmjKyDPjk85YRnd6xZ8s+44f2Z5CX0drWZz99+hejQURVEURVEURbmX6IOGoiiKoiiKoigjRx80FEVRFEVRFEUZOfqgoSiKoiiKoijKyLkjM/i2NXr72cQh85+bUWhYr21+3EHjT5pQgNoADVx2SuYiyvFJY9PQPFauQzkRNLz0OUAtQxPOWAmNtJUiGtTDxDQ4OWT2Hq/jMdQrFGZYIPM4GdeyLTOQyCHjTT/E444p5C/NKCyITMlOTuTedZPrjY2g2Svdc41TDprbB77tne+Uyo4B6pvf8k3wWr2ExigO2xMRWVpZhvKnP/NpKLsclncAQ8R4m4uLaPASMc27bQoHEhuvtedjF/TIkD9dw/Y4M24G3WUhtmlJ0aQekPHx0AEM5ZkP8BiWz18y9jFoYX92yQh4aBKPi8M0r1zG8vnzptktjrFN/9D/gAbyaE96plGv+0Qvi8TaCS0txHgtz59H4+y7/to7jM+XHn09lDepTX36S09D+fkzaHA+cfJhKM9/O5pzRUQKdewLQgF7gWDf9ShsSmxsL66H5czKWUjCw8UpIjKcs8HXsrHNWjSfrK9iXxURGVIA36lDaJT9tm/5NiifvXgRyv/bv/v3UH7yK1819rFJhvECBQ9e91dmYoao7gee44nnbM9pfQrGW1++AOV+3wzT22pivY9NYR9baq9AubmF/T7q42IG0zmhbGOTaIydoLA818UxrdfB40yovTpFnMPjnKnHMdoojmmdLs7bKQX1dsnXGsXm/JhyUGWC7bHiYoMI6N7i6isv4TH7plm/1cD6f4kW/6hP3lggo9szFyO52wzCSGRnoYdKGY+fA9w6W03j82u0SEt7HV3Tq8v4mQ61v8DBtjAza86HzT5eu7PncCzpdiiwlEIBhzQPzdD92/E5c58JLXDQpzDQnkMLHtC9q5vhOGPnLKZUzvBvKS3i4fl43hy2l9CCCIGPAYsiIoUAj8Oie8LSnpBJl1cZuQn6i4aiKIqiKIqiKCNHHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSOPhuN44uwEv9mCekUrQQ2abZn6UCtCXbXnkj6dZJHdbhPKaxuo6x6Gpg+kQFrhwEE9Xq2CurTIwuOem8RgsqMLGBp4be2asc+Eg2noPEIbz/PM2iaUfc7HSnLEvyHWN1skbiUXHlAgjKmyFrEp4KVHyUjpnms8uAcejcmJWalWt/W97jj6J2rk0bByKmRuA/WuW21so3z+b/+WJ6AcD1GD2t4y/TpnX0YN81effBLKJ04ew2OaQ420TV6nsQAbRyUzfSESoe61TxpUz8e6SUPSpPaxH5VJ7ywiEkZN/EwTy8kA+9GVl1ELvrSM7dd2zH1Mk7a7TN6SaE8bjqg97xe1hTmxd/xOrUUcj/74jz8KZTclU5mIPPombFMPPfIYlL/9O74HypUq+gjqZWwvmyumF6mz3oRywgGMCR5X4ONoUKqgN65Sq+P7y6ixFxGxSFNs0Yg0NoHjqmXjPitlHJebm+Q7EpHmJp7rGHlR6hU8rjc9hnX75aeehvLTTz1l7MMrYZtLYvKp7fhb8oJb94OlpStSLG4f49lzz8FrDmmmhwMzUCsmo6NDc3CUUPAizQGbLfQFLK3jXCYi4pdQR3+AxrhSeRzKKdXx5CT6Prp0jK1Ojk+SwgpD8iiutvG8E/IPdCg0sBuZ17exiWPvww+ehPLVyxehXCpimy6NTWC5bvajF5/DNjmgsNUHXn/Do9Xv7/8YaFmuWDv+F5sC5NrkS7Ay8y4jo1vOFs2hy+t4j9jt4hxd30BPh8cJyyLSi9EvsbGGY0m7hf3CIt+HSwGRSYptY6pmfj8f0P1wYuM+ugVs889fwlDLwzMHqGyG6bkD9DjbFu5jawv75kyKdTM3PY/H6JoeDbeIY2qriWPu5uaN/h6xafom6C8aiqIoiqIoiqKMHH3QUBRFURRFURRl5OiDhqIoiqIoiqIoI+eOPBrNxlCCnXV16yQhK5EuM0lozWkRsX3U27kl1FVapGleWcV1wdeaqEUvFFFLLCIiKR5HiTwbxw8cgnKRdJcLC4ehfPLY6/D1w0eNXTabqLe7ePZrUH7yeVw/ezNCbeWRuVkoH6WyiIjNHgvSOLdaqF0sF1GnWKA1vYdd09/S66IeL2T54568j2Gej+QuY6WeWDvXN4tRN5nR8bSpPkRENlbQozE7ibrI5196EcphgnU8PYdtx3JMffL0LNbzyZNYz6dOoUfj4IEZKNt0ncoW6i6THH1y1kX9Z2STdnYL+1VvBftRb4h11dwwz6tHuRXFGmrZJ+ZxbfEDUwtQvnYZ+/LWwNTgl8awrzZWcU352tQNjSlf//0iKE+JvaMZzxzsL1c38Fp/+jnU0IuIXCBN+8om1uvp06ehfHAe22ibfApJ3xxnMzIoDWi9/VoZr11g41gRtjHzYpDhOM1jj4hI5mMbG1Cuj+3hWB2U8Rg3KN9hdgb1xCIiJdIPNzaaUL54+WUoT0/hNgIHv1crT6FmXkRk9jD28S71hUsvnhERkSzLDN/cfuC4mbg7eQ1Vvo4+9nurSnkqIhKT50Im61DcXMf58PJFzNRJybuwtG7m2QxCHKOuLuP4YpPnYqKMbeP+kzjxBD1sS6ub5tzV6eBxhOSnu0jH0KMQlAFdyyjn/mV+jnN98HX282T0Pe74BLa3iRncnohIv4fn0dzC9rd3HB0MTQ/O3cb1HHG9netH2TdiYfvzKZNBRKQ+gdf2GmVcdMiTMSDv39ISzuFeZnqByW4jYR/HP5fGO77WMbWNmO4pvcC8ba5RflarS/dblHmR+dh3Y8poGQzM86pTFketijkmYQf30d7CNn+EPEPlaTODaZDgWL+4iNdnuCdzST0aiqIoiqIoiqLcU/RBQ1EURVEURVGUkaMPGoqiKIqiKIqijJw78misJSXxs+1nky3S8wckF/QmTB3vLPk6XAd3b5HuOk5R6zkcoI6tFZn60APTdSxTLkZQQl2b46Neb3wateWJj+9fmEENr4jIwsJRKF8iXWuP9HljVdwnS/5aDdQhiohM0XFXK6i/HQxQLzdDaybPW6gHHWyZ++iQPjShjBFrz1rR/TgVOYvax7vN2vKa9Hc8CvUy1qGbYFtZvHzF+Pz0LF7bYhHr9IWXzkL5ua+hZ+O+U8eh3N4wfQZlB9vo6QN1KI/bqC/OVnEbEfklIhevazxsGvvs91FTb6eoeQ4tPM/YQh3m6jrmQawsmVkdDvXVIa1b37tKWtsBHsN95D241jDrLgtwm60WjjHZnuyNThfPeb8olSfE2Vk/fu4YaXdd7C+NHB9J7wrm8ETx56DcegjPeZ58BEePoq7WTsxxNiF/hEf64UoNr41Fa8C31nAcCMh/l1o50wb5NtwC1Y2FmuRKDX1FYYjtnPuiiMixQ+hXGZ/AHIL6JPqE6hVs9+/45m+G8nNLZibSxSvYjn2axyYPb4/laZLI0nn0hOwHvu+K72/XP9dpRtlGrmtep/6QcjToOpWq2N6urb8A5ZS8cL3U1OFvka5+/Qr1VQe3UfexzU+Mo2/N6+HNxbnLeI1ERHo9nGPZQnhxCb0OfaPf4HeuJZ/CsHLYJA18RLkWbgHb54A8HP3I1OE7Hs5rdcqfGYY36sJ29t+j4Qe+BIXtY0wzbEudNs5tSZyTpUZ11GrhWGNRG+ZMp7CH29zI8Qj1KdMtpTwJx8Frn9J8yCFcDnkeK2XMexIRqVAWkdh4nn3yNp2Yw7ZRpTG6Hpi/AdQD3K9lkZfJxeNsUm7YgLwqk76Z1ZFGnLGFnwn2ZKfcya8U+ouGoiiKoiiKoigjRx80FEVRFEVRFEUZOfqgoSiKoiiKoijKyLkjj0ZW8iW9vha5jTrflX4TyjN11OCKiAwE9XXtZdSG2yk+90yPoT5PLNQENnghaxHxK3hcbdIfP/3C81BeJZ3lwhbq+w7N4z4n3vBGY5+HDqJu+tChI1DudFCPfvAA5mR0yJMRkjZdRKRSR+1syUdtbFDA8y5XUM9XIu+A75na2iBGzWeaYTnasz66GyUigtfvbvPsM09KaSc7ZX4K9ddHD6Gut1I2NbZFbk6CetiZ6Ukov/gCejQm67jP+TrqLEVEggj1yK3NdSiXKAfBjZpQHrSw3KD1tFPWgorIZcpmOH8F2/RgiNe6XkN/zziF4hx54AFjH6UK6t+LpNtvt8lPtYzazqP3nYTym06eMPYxtHEbxQD3OVG/4Ttqtc219PcDr2SJ4223rfok9vsiXZtBt2l8vtfEa3V5Bf0wheJFKCcptuOQ1ng/OWeuhT4zhe24F+P66TF5r/wC9oMB7cOm/Ipi1cyfiOkrqyTGcTNi0XyCr49N4nyx0TR9Qhcuo/ftjW94FMo98h9c3UIPhkXr/t//wIPGPta3cMwbkBdo/Mj22J7E8T3xaEiabf8nIp0hZeyEeF336qmvk5HXiqxWEoc43vB1a7Sxfk4/YPbj73oQs6c+89kvQXlpDa9tUKbjJA19QjkuzZ6p/d9oYL9yXBzzYsFtDDmHKcO2kXLeiIgsruBYfmgW+0GR/BVBgHPy/AJ6jLKcr3ljyiZwyGdT2HP9MsucC+42vu+If32cozpKCzjODPpmHdoeegBKNClP0txkUa6DZFgfWcphXyIZZVJ4Hn6m36c+TveRHo2HKd1mRqF5b+GV8d7gwDyOZ+M2XuyhjcdUL+F5l3PuzAdtbOMN8ogOezh/bg3wvrKxhrlUC8fuM/ZhUaMMPPL3lW606TC8/ccH/UVDURRFURRFUZSRow8aiqIoiqIoiqKMHH3QUBRFURRFURRl5NyRR2N2rS/BjtZsjHS806T9zDZNDfXQwzWPwwR9BK6N2riCheK4mQo+FyVd06PRaaE+vVvC44zImxAK6kOXllCHmUX4/gfvR12wiMj4GHouvuWt3wHlqfE5KB89fBjKl869BOX1RdQii4gcO4DbyEie2eihttMlvWRA66UXK3VjH0VaPzrs4TXs927UbUrr3u8HK0tXpVDY1nS+8uwr8NrF+TqU89b6r4xhtojrosfi2rVFKC8tXcDyLLbPiUOmVt0LUUdZC2ld/hQ133Ef69jqke66g3rk2DG/G5iv4rX2j+K1Di1sw1Nz2JampvE8KmOmv6pAnh/XZT8C6l5n1/E8+6S19R0zYyITymIg/e2we6Nuhz1z/fT9YJB0d9dVt2OsZ8vC9tHpmDkzW1t43NUyXrtnz5yBMntRJikb4koRxw4RkQptc2wWPRsLx9FDFm7iODo9hpk7PumH2z2z7ydCem0aS2yb8hc6eF4DKtfGzLXqjx44QH/BvvCFL34Ryodn8Dw3KGthg7xNIiJjdayr2hj2jdaO7yaO9j/DQETEczzx3J12Rt6FlHMzTIm8SIb9bpnyhtwEz8snjXZ/iJ9nv6GIyFvf+Hoo33fiKJQ3Wjg2ODFqy9cvYZs+fxm15asNs+/fdx/6QsYn8TpO0HX83Be+DOXFpVUox5lZee0Otp9ND+815o+hX2qiXodywUc/Qiqmv2A4xPGefUV7P5PlfP5us9VuyDDcbn++g+OfQ8dar+E1EBEpe1iv3VXKsgmxjsmWK2RZlDTnq/KEvCMJXUuHclySAbb5pI/tsdMmjxBlr4mI+LTPsQrl04yRT5LG8VKBPG0Dc3xh31sS4/W3yE9VpHs+m8bkQc4cagc41s9QjlPv8I0xeDA0vVKvhv6ioSiKoiiKoijKyNEHDUVRFEVRFEVRRo4+aCiKoiiKoiiKMnLuLEcjjXfXm85i0rmRXtByTf3g8RPHoRxmqAV/9uXzUF5fXoJyvY663XEPdW4iIqukH/arqFM7cQLXDn7bW1HHe/Qwvn71Mmo3LUH9s4hIpYza/4dej7rV2dlTUHYoA2N6Gtci31q9bOzDDlHX2mii9t92aM14B3WEdoDHbdvmMyb/xSUNcMG+UZfpcP81ylE4EGdHZ3j+xefgtcY1PF+nZGq8xUc98sYqrjPdXkctcI38PVc8bAuHQvTaiIgEPra/koX15AV47T3SatoO6nhdj7JnOqgLFhHxSPd65EHUClemUXMv5LeIyG81zLm2SR/X7I5o6IgzrH/Lx9a0sYzep/NLWNciIu0u1l2dckpqe8pdWjN8v5ibnhF3R6N78Qr2wavr2J6yrnmtXNL39uh6RuTR6WziNqMO6moPVVFTKyJy/NhRKD9Uweyf07U6lFc3cB9fex7zYwqU0dPu5mSYkD67SuvhV2vkG6HXG1R3VcpDEhEp03H0u6jn7lG5QZk1S5tNKK+umlkdto39r9nG69PZ8a0l0f571EREPM8XbyevwWFfJL3Xtsz1/pcu4xy7uYLzRkiesTRBT4ZLXpvpSdOnliQ490+O07w9Xsd9dvE6bVw6C+Vry9g2ZmcWjH2+9//+w1CuVnFc7Ww1oZxRZlSlisfokJ9CROSVc5ib4gv5zCjXpNnGvspeAT8wtf7FlPsa1k26x7cW3YM22Gt3JAm37wM4CyKg7JJubHrUhj61J8rVKFO3T6mOM/JCRDlZIn6G93wxtccgwH7hkh8iSnGffcpt6QTm3FMg/4NDJlpLsC34NtZNGGJ7HYSm/3g4wL/FCZb5/q1cwjG3SvcarabpUYttvM8UyiQZ3zMH9wdmTs+rob9oKIqiKIqiKIoycvRBQ1EURVEURVGUkaMPGoqiKIqiKIqijBx90FAURVEURVEUZeTckRn8WccR97qJOEHjndhouJnqmYFc8118z+YGmms3ltGIkkVoREmHaMKZOTBj7KOygAbzpIiG0vI0GmXvf+gxKB+eOwrluPM1KPdyDFidCI091hDPs9FEg119HE00QQmP0S/WjH0MKWxKYrx0LgUPpkLBhCkaz1zTJyg2+aq8AJ1Z2R4jmpPmbOAuU63WpLgT2Jdk+Iwckn/52FEO9xKxXTT4lSicyiKT18PHMXDooVO4zbEgJxGrj9fJ8bFSEwrVSTkYigx2touvF8qm+XcQo1mt0SADoYfnXSCzXEZBc1HHNPv2KSnJKdah3KKgpasb+P5uhPvYyAnbtChAMfWx/Q2z/H/vJ8sXr4rjbtefR8buTgPHs3QLTawiInNHj0F5EOE4GQ7QNLgxwGsR0rVpr5mLblQmcPyo1LA8PYmLA5w4hotV/M5v/7+hvLpKC2LkmIzZeFygRQ8efRyDTg/P4Ng9pMUqFianjH1YFFDV3sK62A2y26FSxvZkbaKxu9cxA6uaW2jwX1xEs7TjbZ9nmpjtdz+IoliinTbDpmuLFvjIMrNtNFZwgZV4iP3Wp/FlfAJN0rzow8KsGdhnO7cwiZLB3KbmNKTr3KOQwPvvP2RscryG1zoms7dDc9tb3/I4lMsUSpmI2caPH0UTerWA4+on/uS/QfmFl9E8fvyBB6B85DDei4iIuB6N/w4ex3DPRGfZtx+YNiqczBF3x+hcpPHZo8UJ2gOzf/VoznV8CpulctTDPutQ20lt8z5znBYCKHjYVxsJzvM+LVzkWXwvha9vhabJvUKfGVDYrNPH46TLLAndz0WReV4R3Q8nZNQOqSN5RWyf3YTCf/tNYx9dmuc5JHAwvFHmcMmbob9oKIqiKIqiKIoycvRBQ1EURVEURVGUkaMPGoqiKIqiKIqijJw78miMHZwQb0fsuERhR2EPtXfHKcRORMRJcXfpALXkY0XUf1ZnUafrhqjX28rR2FbquN/pCdQCuw7qClfOYTieRfL0fpf2kVNjZ5//IpTPfQ19HUJBZG96wxP0MnpTuj0zSCWhkKx+D8sJBSimKQeqUbhTYmoAbdL82eTDcPaEALLmdT9I4kTiePsY+33UQD760ENQrlbRqyMisnj1IpTHLNQnP3ga287DxzCMqhrgPrPE9OuE5LkYDPA97NnILNwmSTuN4KhK2QyMzChkK4pwI8M+HkNmo0Y1jLAeQvJbiIiUx+pQLozPQXnxErbZT37+y1B+6QLq/DMbNfwiIg5pu+8/hZroo3t8N/2+eYz7Qa/ZFXtHi+xW8ByiDnljcoLtVi5fhDL7HSolvN6dTazXiELBhqlpVvnKs09Def4gato5tPTkt56E8vGjGER57qUX8Jjz/DHU7otFHGfDDo5xffJXrC+id2Bh0uy/cYrtmH1DR49hIGyNfESXP4/j9JkzZ4x9WNQBZygkNgy3+06SWwl3H88PxPfNviNi+r0yDpQTkTTGMZ7sD/LQG9Gz+OJl9Kwcq6Bv7dBB02eQ0rxheTjmuayrT0l7ziFsDn4fWiiaQXedFgaCctuwXRxbHOp3RnAmD8QiUqE2Hfi4zUNHj0L54jKOeS55Hh3XPA+bzj0t4nEWizeOy/f3fwwc9ociO96gAnk0ilWcm9KcsalSquN7+Fp2sC00W+QNdPF1PzBvRAoUVOeRl5KsDtJhX0JK26Q5mj2RIiLdEOfUAntt6N7KpfYYWdgnoqF5bSMyog4pFHBo4T4TuudrtHHuGHfM9ueyJ4juHZb2hGgP2Rh7E/QXDUVRFEVRFEVRRo4+aCiKoiiKoiiKMnL0QUNRFEVRFEVRlJFzRx6N6QlbfHf72WRsDHW80QB1cEEB9XsiIhe6qEPbclBLt+mj5mtzSNrNIerHNjdRlykiErTxM69PUQs3N4GnXOrhcQ9LqB3uDlDXViiYz2ZWnzSAq1egnGyiz+PJNfS3ODXUZdfn0RsgImLRWs4p6QbFprXLyUSR0TNlkpnrhLO236dMhyC4oenzZP/X8O71upLueEtcF3XKBR+zAi6fx/XvRUQay3hdTk7gdVsYQz22S2t+U4yLJDkaVMfFds9Sbpb+phn2iQH7KUh3Wa6ZORolWvs+JM1z2MfzaLWw/aWUweKVcB1yERG3iJr55U28/n/85+jJ+OKzuIZ8o4n9yLPNocem415+5UUoHzl2w2sQ5qwzvh+cPn5EXG+7Hyy1G/Da/Bzq1df75jGWC7Ref5f8Weu4zTDCei4K9WvPHI86lBfxhU9/FsqPP/ZGKL/tW98G5R5pb5999nncQU6GhE25A9/9Pd8N5bE65hwMSdN84hT6REIWUovI+hqO921q15s93Oai04TyC4sXoXzkxFFjH9kAt9nexOuxcm3b05flaPj3A9t2xN4JPErpGCLKeLJt8xgT+szkLGYDTc4dgXJQxLHAd3Dc9T1TIx+Txp3bk23htY1i7CcxZSS55IWwee4TkY0Gto1hSHkLNP8NejSvUyZOoWD6YNptynSg3Iga5de87R3oxQwzvA+4sIhj5DY4Ybg2Hpe9Z9xkH8p+MAij3SPcaDThtQOH8J5w4QCWRUQc8g1tLF2CcquMnrSUsko416FSMTPHbJq/MmoL9VkcixqU+dbpoj+i6FHuWU6EWEZzV5rS/RZ5H0LKwIkpkyJNzDaeUtBZRPe2MbXHcED5H5s4Pg575v0LjyEZtUfZm8HFGWA3QX/RUBRFURRFURRl5OiDhqIoiqIoiqIoI0cfNBRFURRFURRFGTl35NFYazTE21nTuh2ihtGxyW/RMfWD/Jd+yusb0/rbtNawXcI1vGPfXMc3tfHZqU1StynS2yUuvr/R2oDyxiauhV0IzCor2XhcY3XM7mjTiWc+7rMyg/r3hM5bRCTweM1j1Jja9LpFayTH5MlgTfXORvA4+T17cw7snM/fZdrtnoQ7essO6So//8WnoNzaRB+CiMj9h+tYPo7XqV6idahZA036eMs29ckZvcd1SVdJWswB5UFEMWk3yeThxaZ2vVpFzalP+2x3UZuZkd/HD7DvOj5uT0Rka4DX+6N/hpkEH//sk1Beb+P1sckHMjdp+pDSHmqge030L8zU6rv/HkZmhsl+sNlYF2enf3oFbC9F8soUq3Xj870+Xouki2NYQv3KK6PeeLqC2+zmZAm1hk0oX7mIWUGf/fSnoPzu7/9ePIYE29zmFuaD9NpmPsgJyrB421u/GcrHj3PeAu7Dp0yB1RXMbxARuUZZGz3ylAnlS7x49RUodygfplrKyaShKbFLeu1kZ47K0v0f/0S219IPd/p3TD6lJMP6sG1TQx1TfkSN2pdDc8DcAmawrC+iz62T0/54HknJg8GZA0lI+nTyaNgWzZc5/gmLPF+ei+du0TYLVeyrQYBegAEb8kRkc6uJx0n1u97C9hkKjbvUZFLWv4t5DT0L67Lo3fARDof7PwaOT05LYceryfNjp4d9ZRCaHjUzT4KySep4LxVRFkmbcoWKqfld+XCI9ZqQz+XAARqLfGwLr5y7gMdEd64TRXPcYO8JZ9oYfYLzUuj9tmfeA9p0TzfsUV4Wve5R3aYJ7tP3TS+m7988D8n19nqEbj/HRX/RUBRFURRFURRl5OiDhqIoiqIoiqIoI0cfNBRFURRFURRFGTl35NFYag7F3fFADEifZzusiTS15GlC63w7pMUkjVl/gFrgDq3HnXF2hIgUfdSUXVpB3WShhHq8MmkznTZqADst1I13c3T5nAngeKh9CxZQE+hX8Lg7pN00vBEiMuahLnVAa2indAwpramcke/Dcsy6c+gaujHW9/UMCxGRNDWv792m240ljnY8QiQPrJawziaq7GkROTqLbePwPLaFQpG0nSyBJf1slpoa2S55LliYG4W4jXCIZdfF9lii3IzKWN3YZ1BDzShroNu09rhPHgzbxnrJbFO7+fyLqM3+4ldegHKnR+3B4vX2KfeE+p2ISBpj3U0fnIbykYM39Lv9oenP2g/Onjkj1s4YOHMY+3XUxz45OTtrfD6irr38ykUozx1A35BbwXpLGuiXGMY4PomIODQWZAnqh5/6MvqZnvzSV6H8hocfhvKDD70eyp/5zGeMfT76+ONQnppAD87XnnwWyvNzc1D2KMdgg/JERIzuJ+UK9g27iu32uY/9MZS3mk0oc26QiEiB+oJl4XFNz21nA6RJLB3yjOwHcZJKvOPjSmmecNjTKOYY7VI/5HoPyccyVUf/YGPxKpQ7bfQKiphz7LCP74moPcZU7g/Rm+WR5+zIYTOfYZyOs99D70hGflCyqhjHsNU2218vwm32M6yrVoJ9M6LxzKU51w/MTCQjIoSzEyJ7z7/33yfU6fYl2vEGWeSHXSQ/Ra9nto069dH5GfRkuDXMxShN43i4Sdkdg5w4JXeiDmXOrPCr2FZeN4/tie+NWsuY9VG2zXk/oPtOScmzQeU+5QQ5dJ091/wNICZfWOzhHOoFeF5ugMc0JN+RZWFumIjI8ePotfPIK9Lq3GjjTk6Gzquhv2goiqIoiqIoijJy9EFDURRFURRFUZSRow8aiqIoiqIoiqKMnDvyaHRjV5wdXZ7nk8bf4jW8Tf1Whdad99iTEeNzT6uPHo0h6Ucz21zrOh6ijnKZdJIHaP3+I6cegHLBR717kqCWzrbNZ7NikdY3tnCfcYZ1MSA9qEWC0SQx9ecDyg3okga1Sd6AK6uoMW3T9SoUTA9DEOBxFlOsX2fPut+9oZmTcreZrpelEGxrjGcnUN86VkAN7kLFzII4sYAaxoKN19Yi35GQ1t2ijIwwMq9TTFrMMMR9JIauFvdhtK8Y6zmLzHq3BOvC8bANDxPUPDcp4yahbI7VJmptRUT+7PNPQ3l5cR3K7FOyKQ9iegK1uXv9Ftc5PHsKykUHr0d9/Mb16w32v/2JiBw4dEgcd/tcmx0cn+bn5qHsWuZY0SejwQLpbicPoHehT2v1n79K14bF5iLiFVC7m6Q4Nqyt4bX72rNfg/L3fP/3QfmhR98A5adfwPeLiDz0CPo6Ilrj//zZ81BubaKeff7gAShvNE3vSUZzysQMeng+9RR6TQZksmpT/sfMJNa1iMh4ZQq3Qb6bsR3vSRxFclG+bHz+bhOlsURpjjBdzH6c5swjGbVJlzwagwGOFQWjLWF7XFrFtiQiUixT3yQvW0zfb/Zpnmf/VZ38PlMz5nXzAxxf+gPcRm+A82UY4dwW0Pxo+Wa/6lD76SXoQYjJl8pZVuyFCzxTIz/sUzYC3eK02jfqMszJqbjbrG00xN/R7U9NYV8ZH5+8aVlEdnPYrrO8jrllwwjHKpuybirj2BbsHKtoqY7voWlEEsqwEPKzHqZMoNUU+0S8aXqzHBqHS3T/kdG43xtQlgz1CfajiYj06L4xssnn6FMWDN2fsGfowkUzA8e2cccT1Pe6/Rt10b+DOVh/0VAURVEURVEUZeTog4aiKIqiKIqiKCNHHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSMzuO95u2ZwnwPgyMTKZlAREYsM48OYjLMRGWISNJ55HEJnpNuI2GzAJJPOKxfQlDhBxqHHHn0Cyu0+GWoi04A1OY3BXBEFpFlkoBMKa+FQlDzYJNxoNXEfFAw3N7cA5TLVi2WZLqpEsD47EYY7hXtMev3ojprOSHjg9CEpFbcNdRM+GpHKZFwvJU3j8/UC1kHUQ3PfVo+uWwHDgyrUVsplM3SulKHBLxxie+mSEbvfx9cHtPhAPCAz+RYa00REug4a5rISHkM7wtc3e3QMAzzvfmgu5OAXcZtZgqbkWgHb8H0P3Afl40fQ7FvPCVQMqEmNVXGf6Z7hynIpGHGfOHby5G7I2dIymgI5hO7KVQw3ExFJLRwLHnrkQSi36fpnGV6buaNHoXzxuSeNfRimVBo7eCGPMoVksWk6KKGJ9U1v+yZjn4eO4XEdWMDx581vwc8sra5AudHBdr2ZE/ZlU0DUkx//GJS/eu4MlCcoUNGnIDlraM4fvBDHxCQFwe3MWUmy/0ZcEZHBsC3WTmDYYIB9ICAzaDw0j7FDfV/InNtqYWBtQqF/doD99gtPmu2vQyZln+a3qUlcNMHJsM5bHTyv7hCP4bkXzxn7nKjXoZxRH1jfxPHK9/G8fRp84sxsf2GKx+m5WBdpiGXPo0U6BOfT4RbdF4jIgOagkBZV2LuAzt7FWfYL17LE3bmnSihAeauJbWd6ChdrEBFpbOF7VskMXqDFCYQCbosVNJh3aVEJERGhhSRq49iH25t4DEKmaTZ2Wz5eN7tA4XwikvTx/iPzaB73sH1tZdj+khjHNjvn1py6gdi0CJFFIcoZLW6TUXsJcxaWOXsGg3h9j9r4nnvuMDSDC18N/UVDURRFURRFUZSRow8aiqIoiqIoiqKMHH3QUBRFURRFURRl5NyR0L4cFMV1TP22iIjrUriZadGQOEVNWEQ6SqEglSKFBZVs1HqGqakRs+k4XPpMq49a4OfPvwzlqblDUE4s3F65hrpLEZHxqRkoD0M8z5R0lhZpWF2Xw/RQEygikiaot+tSkFSljHr26WnUi1fJ3yKZqd+1HdImUjBUGt7QIXYHZlji3cb1bXF3tLWTkxjQ1LyIevhjB+rG521B7XkUY51GlJITJqgV9qr4eq1qhgJaGeogCxVq01V8PaYAv5S6ZIeEmX0rx88ToEfIKaKXpLaAmui4hPVQpLYVOKb3pD6NHovaeB0/E+BxHTt6GMpTk+gDWF68Yuyj38P65r672d3jEbpHgX2N5qa4O5rzgwfQAzCkEMswR8c/NVOHMlWbDOirn4KDY8GBY0egHA3NYDuLwz1XUZPM3y55JexLIWmvgxK2hwffgOF8IiIO+T7WSXvd7GA4VJ/q5tK1Rdxnzji7fPUalP/sU5+Ecu0wtlHLx760QL6R1pIZNtdp43H3qC6zHb12kjP37AebzXXpD7aPodvDuaxcxOvoiDlWtPvoPbi8iPXuU5DrlaVlKK+RN7A/NH0Cl+kzFnlrNsmnNkceoSTBMXFpdQ3Kn/jc54x9WqR5t1mPnuB85ft4TAGFCdcnzfY3MU4hsWUc/3n86lCAopDfSlLzJimL8bh9nrb3+kTuQRs8duSwFHZ8OuxX5UDDSy1zbOqTfzUkX4FN5+QL3ZPY5BmwzTYe09wwpGBVn3wg7S08zpDv3+g8i4HpL0yH5CvqYXvrsp+niG1+GOF1TzOzbbh0P+z4PE+T99cl3wfdlHOI4PbfsNynMWav/y/M8Su/GvqLhqIoiqIoiqIoI0cfNBRFURRFURRFGTn6oKEoiqIoiqIoysi5I49G0Q92PRop6bs8Wm/XdU0vxyDDv7lF1IzFQ3zuKZGG0Q/w9WanaewjpHXoU9Jqsm53cR3X1/7iU7gu+OHZo1A+ff9pY5/lKurtHFrfPPZQd+iQ7tAQxuX4YDz6m9ehtaIT3Md4Hdeb9khrPBiY64THpJsukq7Q2ZNDkWb7/4xqFwKxi9v65AGtfT1Wx2sQ5PhciuRB8R1aD5tyWSq07n6hguWEr6OIDEirmVIbtoTWvrbxOHsprbVeqUM5GEM/hohIFqBWOCSPBfebeoDXvtvFtcgHHVNba7vYrx56/SkoV4q8hj/VA/UJKzK13W6GddPr4TUu7tGgZ1a+V+xuM4wHEu9k0HR7WE/ra6gld23zHH3K0VhdRY28U8F27FK9Fim75Ym3vsXYR0QZFBfPvALlEml7U9LuDshT5tP77YKpUd5o4LmXxmh+qGBfW75yCY9xBXM1jk2i50xEpEFjVmkc3zM2hnU3Q7k3doptJqyZWSzrtM6/S2vmX/doWNG9aX+d3kDiHU8Vz7k9qp+1ZdODsrnVxHIXvTO9CLfBlrCU8gHKttkW5ifwOlRnsA4NjxB5F0LKc8osfH15C9uKiEhCfruCTZ5R6oo2zac+6d97Ode3uY4bqRVoziUfGvf+lPwXjp1zjxShJr7kYt/sD29o/6No/z0a5XJFijtzK+d/sU93fd1sfwnp+lPyaJTGcC5LhjgHDOmc/Tw/K03Lw4gDKLCtcEaZ0HVJONuKyiIiCY+htM/YwX5SHUNfb4XbvLEHkYjy2DLyDwu1efZk8H0m35uIiFj0GfZkJ3s6kqc5GoqiKIqiKIqi3Ev0QUNRFEVRFEVRlJGjDxqKoiiKoiiKooycO/JoeH5hd23ehLR15TKu4e37pnYuiDl7AfVgXRv1eBbrLElLZ3dRzygi4tJ7giLqQ/uk7Y9IZ7a8ehnKGa2Nv7CA+RQiIoM+rTsfUP5HGbX9Dq2Nb7GPRMz1jRNaf9qwB7Cu0MV6yMhTwa+LiPQ6eB6DHuop/T25Et2BqW++2zS7PQl3dIodWqealcJJjshxYg7X2SeJs1jk4RiQpjamOnaK5lrrrs9aTXyd5O/S7WM/Wm9hvUYOaVIH6KcQEYlT9ApYdJyWhde6S+uKt1uoS+938XURkZDyZ1wHt5nG2FbGx1A/Xx+rY3kaMw1ERGJad77dRb24u2c8cO07GrpGhlf2dnM0rly5AK+FXWyTRW5gItKx8Bwd0jVPTaC3qk1+i60Qr3+B8kxERMbr+LfOAvp67jtyAsoVytFwKNcno5yVmSk8RhGRjQ3UYwc0Pnkl1K+fX8JMjMUG5ldM9E0PWWEct3Hw9EkoT1bHocz+gT4dU2jnaJQ9nC/qUzjeezvzXBzemxwX23LE3unfGc0bnQ72UV7LX0RkQPNZFmO5XCUteY08Y30cn1rr5nUaH8P2VBvD9uQF5N+JcCzZWMbz4PmwXDL7fqWC+6xTe8ti/ExQQC/AYIj7aGya4+wSZaykEzjGHTiMuvs4xPbV2EI/TJKaOQQJZTeV6F5Csj3XNCcL626zeO2aBDuZOX6AbaNCHkbW+4uYOVMV8kAVyXPRpznBoeChlM03Irv94zp+oYTHwJ4MOs6ExruU5powMb01HcpG65O3xHfoHi/BY3AD3Gacmj4Qrjs+D8fj0BX6PG2PvSd5f2P/ir2nvo16vAn6i4aiKIqiKIqiKCNHHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSOhc7lSFe+6ppgEX8Ui6uAcx3yGsXq8ji/qwXh59oisCg7lOkxPm5kCrTbq1TeaDTwGyvdgnWtI64gPhqhXX1rCde9FRCbGUcc7MVGHcom0ix7pDG32aORpL6muYvJsRDFqAjs90oMOUK/r5qzU7JBHwYpQv+sm/T3/3n+PRjqMJbG3z7vbxus0UUVt51bP9Lk89SL6b4TWKHcCbF/NNtaZ46JedmYePR8iIuUqrt3Pmu/UwWu/2MH8gQ7JqpMU9co2v0FM/0OZ2huvp22VKPPGQq1xKTC9BVevYH33SavtUL9q9XltfGyPjQ3UO4uIDEk/npB/Kt6zjvjwDtbwHiVxL5bM267Pahk9AYXKFJRbDfS+iIgMybRTrGB7aGzgZ8p0bYfUJ9eXMAdIROT0Scw4mRrH41qYQi35wTkcv/pt8oGQ9vfgocPGPj9+5mUonz2HORnTC+jJSckjxuPXuTNnjX1MTqM3pErtPKIxsd/HvnJxeRnKnb7Zl4Q8Cwl5RZId31ZMXr/9olgsSGFHxx5GlFVD2VaTU3jdRUQsGn8Swblmdg7Hr5i8eCHl/nSaZj0kMenNh7T+f4b1npJePSEterWK/ovZg+Z5TU2jJ6NO+UNbDbyu3S7W1cYa9qPWpun/LFGmjUfZG6yB77TwXiQc4nmXyuY46/t4HzU1QdcjveEtuRdjYKlclsLO/MD+snYb75Xi2LyPcVjXT36IThvnCb5NSW8jc8wlf3BK36dndKUyMnSmlNHklnCcTyLztjkZ4LkmIV57jxsHjT2ZS77dnPtnPtOIjtvmuqFyxjkc/H4xfTXs2Uj2+KWSnOv7augvGoqiKIqiKIqijBx90FAURVEURVEUZeTog4aiKIqiKIqiKCPnjjwaWWbv5jF4tNa666DeMMjRedskCWMNLS+77JHuu0DrvbNeWUTE7aG2kjVmrBvkdZi9ADWSIWUphObSw+L6qNXMSOPHWsooQd2vRdpaSU3tpc+5Fxnr8/DAUtI8cw4Ce1NERIqkxWbviGOluf/eLyYr41IubXse2kX0FbRJS9xqmx6SShU13Zcu4Vr+FnmAbIc9Qfj5tGnW4ZhNviOK2mg0UQu8QRkWAbWlcgXXe2c/hohIQFrhNmmDo4gzWLCjXVnEerh06aKxjx71qwrl5hw+cgTKE5Oopy+Svnl82sxiaNFxXzyHx7G0J3shjPZ/DXkREd8qiWttj31phvXa7bAGu258vjyOWtyVtRUoB6RXr41hueij5yfukqZZRJ7+6tNQfus3vxXKC7Po0SgVcCy3IiwfODgP5Q26TiIiPRoXN4f4h+Yl9EdNT6PueYIyCV55+byxj40V9DMdv/84lB3Say+R7r7ZbEJ5atJsg8UKjv8856xf9yTco/Zn25bY1/M/aPgZH8c6zZFgy/gkav7Z1zI2hgNWt4VzVaeP/p2x6RyPRoLjS7GI7SlMKKclxDZ+4oFj+H7yJ05Mmh4NptVoQjmm9sjnFZDfYJLao4hIQhr3RhP7wWaDvHH0+RpllJSrnjAFypFwPNyKZ99on7a9/z4h13XE3bkv8zw8/s3byNbi+0ahOh3SNvj+je9bPM/Ma2MPRkL3V1lEngzqKC61hcTFMXeY07HcMTzOcbqO45TpUyliuUNzcpSTcWFZdH9GOUDsufDoPFLyw7hWjo+atsn3Dtae+0zuDzdDf9FQFEVRFEVRFGXk6IOGoiiKoiiKoigjRx80FEVRFEVRFEUZOfqgoSiKoiiKoijKyLkjM3gYJpKl22YRiwzPbFQJyFQtIpLGFP6RoHkyIeO1YcwL0GwV5gSGeD6FkZEhhoOWggBNO35Axm4KOJqZw+ApEZEFCrBiw5IlZEYiE01EYXphaJq8rIwMSmTiS8gYP+hieE7K4Xs5j5gxBQUGZDDfaw5no/h+UK2NS7m03Sb6dOnPXcYgRd8zg3yCFhrNqjUMKquOoZnStqntkFFqkw9CRDrraJYs9fFaDilkq1LFoKkyL3gwxOvc2Goa+5QWpwHdPKjn8mU05m5QeN7UnBmEOTGBdVMsokFukkymJTKLx2Se7eaYmJcvrEM5IVPf/Q8+tPvvwXAo8t8+aWzjbuNYnjg7ZvBEsH+MkbmYA0lFRFo9NJA2trA8lmHHbG9hPdn03VC/by4csbR6EcpzZOYuksG038Trv3jlKpTPLy9BOaIxUkQkSqkN0sIKLQpOrVTw9UIJx9mpadPwG4dkxl3D9sKBm1tdNPyepCDDcs6CJd0NDPULaIGM+tj2fBHljNH7QalU2l1YYUgBcCHNbdw+RUQKBRwXUzKdNslEndE2Bgm1x4LZ/ngRF5fCxxyhRTUomXd2EsefaIjba6ybixFcvIDjf0zz3ZFD2AcmxvHaFws4Pi0um0GYYUJzLvXv1RVc2GOihmNgrU5GaMtczIZDS4cRLsLh7blfuReBfVtbLRn42+dRpjGezeHcHkXMQDjPx8+kA1pkhtfAoe3lhcZltFCN7+G1jhP8DAfaejTP8zGkOSZq8fheFedHnoMHND7yWWRiLrZj0YE4vHpSRmUOvKbjzgsF5L9lVFd7h4s7WQ5If9FQFEVRFEVRFGXk6IOGoiiKoiiKoigjRx80FEVRFEVRFEUZOXfk0XAdV1xn+yM+BYuViqjXc2wzjIY9GHGMKq+Qyj7p2mzSmAW+qbHtUWgTB8QMSdMXk2/EKuLny2UM7pmeNT0aY3XUE/c4HI8C+FLSqyc27tOxzee/hIJTYtIIp6SlC8n3kQ05HNFU2HHgi2tIAG8cQxbvvz70wuLyrjdgnYJ9Nuj8aq4Z5FOp4LUsVVBH2euhr2VyZhrKMQX/DPqmBjXq4nF5ZIaxqE27Pl77aIjXcUjXvdvFtiVihhpx6FGrjeflU7955LFHoTw2Xjf2UaDAvcEQ98EhgVdWUNfvkU42Tc32d2kRvQGrl1Anbe/xgUU52tz9YHF1Uewd39fx4xgYxz6VdtvUkictvJ5zCzieBA61W/I+sNelMzB13n4VQx7bIV6rF869hNtso+7+wnnUu7sV1NSXp/A8RUTYJdRYQ9+HTx6+SxcwkK/TQ337+Lg5zp48dRLKrRaGHW500R81cwC3USxhfx+0zb7UaOA1czpY3+Xx7bBD1oHvF42NDSkUtvvSYIAeFPZ/dSIcE0VEXPLuOXRdWMcdU/BrTCr5gk+JpCIS03w3GOI2KkVsP5UxLK+v4HmdO3sRX1/HtiUi4pM/4Mihg/h6AcefXguvfRRiP6oUzPuXkDwRxQre87Cf0y/hmOn5WLdhTuCwTd7XgLT8yZ55nuf8/aDX60q8E+jZ6/XoVRwFnBwPAM9VHNjHoZs8V7GHZTA069DwilA/4dDmUon8xCnVK98XZWa9p3TusVBoM/ldOfCTj5nDgkVMnwePuS7VHd/PcTChcFC0iHCT4nl2r4fDyrlPfTX0Fw1FURRFURRFUUaOPmgoiqIoiqIoijJy9EFDURRFURRFUZSRc0cejaDg73oeMtJ3xbTGdDow1/AOSZ+XkX8idlBvl1icP0Ga+MTUmHlu4aZlyXAbUYgatEqpDuUD80ehHLimJtXOAiqTDyRBbRyvv83rI9tm1YlD9W2Txt0mnwevDc0+ETsz/QUBPXYGKXtH9vz7HkiUW/2+RDs6w5TyUaZIjz03berIPZIorpKOvEWZBqtbuE6/UJ3y+twiIiXKwahRNkeZcjM6pBVe20B9fETazmLZzKexSZvZIZ+HRTrfgDSpQ1rvvNGg8xbTSxIUUO9epDXVLQevD+s5Pd8ceuboGrabqK1tbDR3/x3FOZ1kHzhw/KC4O9c9dbETrLaw3gxNrIhMH6BMC7o2vKB6v8V1QF6GGTPzpJ+iNv+VK5eg7NE4WqJrZZexjc4cOoKfL5nXbpn2ce7F53EbY3ic5XFsT6xX98vYvkREbMq9CHwcd60+ZURQ9V+hfJD2OmZ7iIgElAFRpbyPtca2byiO9t+jJiLS7QwljrZPjDMJbMFjLeX4DLhFunQLUPCx3u0Mt+GQ58wNzH0sLuMYtrG+BuWhT5kVXfRzXbmE16nVQu/N1BTm1YiI1GroS2J/AB8369cLAedqsAJeZJCQJyZBT0yS0DjcwzYdFHDc9X3sZyIiHs3jPh1XbN3ou1m2/98Tp2m666/jtsR+WMOPISKZxdcBx1DOPWNsnkc8s/0xIfVVj/bBvhD2D/Ix8jGImPMb59NwX+V9cpnfLyJiURvm+YU/w22cPc15t3AZ+1NiOu49dWfzAHsT9BcNRVEURVEURVFGjj5oKIqiKIqiKIoycm5LOnX9J5gIljTFn1Q4bp6Xot1+D/6EFdESqbzsGL9ufD7n52tejot/vuOfxbjMx8Dn1R/wkm4iXVoWtdfn5dToJ1ZaMjClZQjjvrkPJ+MlA3GbA1qer09LnGb0/jjL+emfL1lGS6/ueb27s6wc/zx3N7i+j8GecxrSkokxXadBzrKfpGCTIS0RPKTlC8XD82fpVN6p27TEIV8Hy3Zv+jov18fSKYt+Ys37G28jS/nnaXx/v4/HwDIDERGXZAGsWnQc7Dd8DBaNB15sDj28DGYY8Xhwoy6uL0u9H+1v7372SmaylGQA9Jk86VREbc7lRsmrIIbczrGNJjnyiYRkkpmNZYt+HqdVxSWjsYGX/swcUxLBx5WSPDShdRNjWuo8ISlczH1RRELuG7eom1vWXc4Sybx8K3/mevn6cuP73f72jnu8RHlKY0XsmMfGf0lYQEFjvk2yEScm6VTOEpk8NkfUj23heZyOO+G2Q6/nXDfeB98r8NjO9w48HVpWTtvgNkrdIKbP8D54eVzJTHlMapNsh49hzxLz17e3n3Pw3jGZ98pNgSVHIuY8YPPwZyx3i9vgOo1vY5l9nke4vhy6Lvw6n0fOra059rNNgPdJ58XnnSudor/x/MKxCMa9Li93a+xBJKRxm9usbZmv3U77s7LbeNfVq1fl0KFDt9yY8lePK1euyMGDB2/9xq8DbX/Kq7Ef7U9E26CSj7Y/5V6jc7ByL7md9ndbDxppmsri4qJUq9XcJy3lrx5Zlkm73ZaFhYVcc9Qo0fanMPvZ/kS0DSqItj/lXqNzsHIvuZP2d1sPGoqiKIqiKIqiKHeCmsEVRVEURVEURRk5+qChKIqiKIqiKMrI0QcNRVEURVEURVFGjj5oKIqi/BUmyzL58R//cZmYmBDLsuTpp5++14ek/BXlHe94h/zsz/7svT4MRdG2OEL0QWNE/I//4/8ob3jDG+71YSh/hdE2qPxF+OM//mP5yEc+In/4h38oS0tL8vrXv/5eH5KiKIryl4TbCuxTFEVR/nLyyiuvyPz8vLz1rW/NfT0MQ/F9f5+PSlFGj7ZlRdl/9BeNPaRpKr/2a78mJ0+elCAI5PDhw/Krv/qrIiLywQ9+UO677z4plUpy/Phx+Uf/6B/tplR+5CMfkV/8xV+UZ555RizLEsuy5CMf+cg9PBPlGxVtg8p+8iM/8iPyUz/1U3L58mWxLEuOHj0q73jHO+Qnf/In5Wd/9mdlampK3vWud4mIyJ//+Z/LE088IUEQyPz8vPz8z/88pDS3221573vfK+VyWebn5+XDH/6wyg+UV6Xb7cr73vc+qVQqMj8/L7/5m78Jrw+HQ/n7f//vy4EDB6RcLsub3/xm+eQnPwnv+cxnPiPf8i3fIsViUQ4dOiQ//dM/Ld1ud/f1o0ePyi//8i/L+973PqnVavLjP/7j+3FqyjcYt2qLm5ub8r73vU/Gx8elVCrJd33Xd8nLL78M7/m93/s9OXTokJRKJXnPe94jv/VbvyX1en0fz+I1TKbs8nM/93PZ+Ph49pGPfCQ7d+5c9ulPfzr7vd/7vSzLsuyXf/mXs89+9rPZhQsXsv/yX/5LNjs7m/3Tf/pPsyzLsl6vl/29v/f3sgcffDBbWlrKlpaWsl6vdy9PRfkGRdugsp80m83sl37pl7KDBw9mS0tL2erqavb2t789q1Qq2Qc+8IHspZdeyl566aXs6tWrWalUyn7iJ34ie/HFF7M/+IM/yKamprIPfehDu9t6//vfnx05ciT72Mc+lj333HPZe97znqxarWY/8zM/c8/OT3nt8nf+zt/JDh8+nH3sYx/Lnn322ex7vud7oL28//3vz9761rdmn/rUp7Jz585lv/7rv54FQZCdPXs2y7IsO3fuXFYul7MPf/jD2dmzZ7PPfvaz2aOPPpr9yI/8yO4+jhw5ktVqtew3fuM3snPnzmXnzp27F6eqvMa5VVv8vu/7vuyBBx7IPvWpT2VPP/109q53vSs7efJkFoZhlmVZ9pnPfCazbTv79V//9ezMmTPZ7/7u72YTExPZ2NjYvTup1xD6oLFDq9XKgiDYvam7Fb/+67+ePf7447vlD33oQ9kjjzxyl45O+auAtkHlXvDhD384O3LkyG757W9/e/boo4/Ce/7hP/yH2enTp7M0TXf/9ru/+7tZpVLJkiTJWq1W5nle9h/+w3/Yfb3ZbGalUkkfNBSDdrud+b6f/ft//+93/7axsZEVi8XsZ37mZ7JLly5ljuNk165dg8+9853vzP7BP/gHWZZl2Y/+6I9mP/7jPw6vf/rTn85s2876/X6WZdsPGj/wAz9wl89G+UbmVm3x7NmzmYhkn/3sZ3dfX19fz4rF4u5nfuiHfih797vfDdt973vfqw8aO6hHY4cXX3xRhsOhvPOd78x9/d/9u38nv/3bvy2vvPKKdDodieNYarXaPh+l8pcZbYPKa4XHH38cyi+++KJ80zd9k1iWtfu3t73tbdLpdOTq1auyubkpURTJE088sfv62NiYnD59et+OWfnG4ZVXXpEwDOXNb37z7t8mJiZ228tzzz0nSZLIfffdB58bDocyOTkpIiLPPPOMPPvss/Jv/+2/3X09yzJJ01QuXLggDzzwgIiIvPGNb7zbp6N8A3Ortvjiiy+K67rw+uTkpJw+fVpefPFFERE5c+aMvOc974HtPvHEE/KHf/iH+3AGr330QWOHYrH4qq99/vOfl/e+973yi7/4i/Kud71LxsbG5Pd///cNHZ+ifD1oG1ReK5TL5Xt9CMpfYTqdjjiOI1/96lfFcRx4rVKp7L7nb//tvy0//dM/bXz+8OHDu//Wtqwo9xY1g+9w6tQpKRaL8vGPf9x47XOf+5wcOXJEfuEXfkHe+MY3yqlTp+TSpUvwHt/3JUmS/Tpc5S8h2gaV1yoPPPCAfP7zn5csy3b/9tnPflaq1aocPHhQjh8/Lp7nyZe//OXd17e2tuTs2bP34nCV1zgnTpwQz/Pki1/84u7fNjc3d9vLo48+KkmSyOrqqpw8eRL+m5ubExGRxx57TF544QXj9ZMnT+rKUsptc6u2+MADD0gcx/D6xsaGnDlzRl73uteJiMjp06dh7BMRo/xXGf1FY4dCoSAf/OAH5ed+7ufE931529veJmtra/L888/LqVOn5PLly/L7v//78qY3vUn+6I/+SP7gD/4APn/06FG5cOGCPP3003Lw4EGpVqsSBME9OhvlGxFtg8prlZ/4iZ+Qf/bP/pn81E/9lPzkT/6knDlzRj70oQ/J3/27f1ds25ZqtSp/62/9LfnABz4gExMTMjMzIx/60IfEtm2QWymKyPavEj/6oz8qH/jAB2RyclJmZmbkF37hF8S2t7/7vO++++S9732vvO9975Pf/M3flEcffVTW1tbk4x//uDz88MPy7ne/Wz74wQ/KW97yFvnJn/xJef/73y/lclleeOEF+dM//VP5nd/5nXt8hso3Crdqi6dOnZLv//7vlx/7sR+Tf/Ev/oVUq1X5+Z//eTlw4IB8//d/v4iI/NRP/ZR867d+q/zWb/2WfO/3fq984hOfkI9+9KM69l3nXptEXkskSZL9yq/8SnbkyJHM87zs8OHD2T/5J/8ky7Is+8AHPpBNTk5mlUol+6Ef+qHswx/+MBh9BoNB9oM/+INZvV7PRCT7V//qX92bk1C+odE2qOw3eWbwPAP3Jz/5yexNb3pT5vt+Njc3l33wgx/Moijafb3VamU//MM/nJVKpWxubi77rd/6reyJJ57Ifv7nf34fzkL5RqPdbmd/42/8jaxUKmWzs7PZr/3ar0HbC8Mw+8f/+B9nR48ezTzPy+bn57P3vOc92bPPPru7jS996UvZd3zHd2SVSiUrl8vZww8/nP3qr/7q7utHjhzJPvzhD+/zmSnfaNyqLTYajexv/s2/mY2NjWXFYjF717vetbv62XX+5b/8l9mBAweyYrGY/cAP/ED2K7/yK9nc3Nw9OJvXHlaW7fktXFEURVFGQLfblQMHDshv/uZvyo/+6I/e68NRFEXZN37sx35MXnrpJfn0pz99rw/lnqPSKUVRFOXr5qmnnpKXXnpJnnjiCdna2pJf+qVfEhHZlRcoiqL8ZeU3fuM35Du+4zukXC7LRz/6UfnX//pfyz//5//8Xh/WawJ90FAURVFGwm/8xm/ImTNnxPd9efzxx+XTn/60TE1N3evDUhRFuat86Utfkl/7tV+Tdrstx48fl9/+7d+W97///ff6sF4TqHRKURRFURRFUZSRo8vbKoqiKIqiKIoycvRBQ1EURVEURVGUkaMPGoqiKIqiKIqijBx90FAURVEURVEUZeTog4aiKIqiKIqiKCPntpa3TdNUFhcXpVqtaqS6IiIiWZZJu92WhYUFse27+7yq7U9h9rP9iWgbVBBtf8q9Rudg5V5yJ+3vth40FhcX5dChQyM5OOUvF1euXJGDBw/e1X1o+1Nejf1ofyLaBpV8tP0p9xqdg5V7ye20v9t60KhWqyIi8hv/0/9LioWCiIjUygV4jy0JlAeDyNxQwYdiP8b3xL0+7rdUgbLl4JN0kqQ5R4vv+ZM/+W9Qfuncy1CenJyEsutilRQKeJ6W6xh7vHzlMh5XjHVx5OgRKEcRnne73aZ9Fo198Hs6vQ6UDx5agHKvP4Byq9WCsu94xj7mZ2agXKvVoLyxsbH77zhO5BMff2q3bdxNru/jv/6n/1XK5ZKIiKQU/2JZ+EQdhaGxnZjaW5pi++FvagK+9vR63j4GQ/xbsRBA2XFv3uW4/TkOtrfAxz4kImLRtwnG90103Fma12/2vv3Ov7GybO4XeH3SBPtEoVgytlEuYbu36dyj8Mb1a3e68uhbvnNf2p/IjTZ4/tIVqe70CyvFc3So5jPJqWdLY4teK2RmT5E4xb/xOHP95Xa7JfcfO7Lv7U/E2+3Pt+qnuS3t6/wy2sosKud9k0l1yG3eprHb+PidH2T29fYrjhNLze05fBp0mAkd981H2Zx95mDUxJ6PZFkmkoX7Ogc/8vb3iONu3zuMj+H92fr6KpQfeuCUsZ23vfFhKPOc3G7jPWBrEEO52R5CeUCvi4jYdGGuLi/hNpp4b1Qs1aG8ttmA8nDrHO6zddXYZ7e1BeWY7gGF5lzPx7muUMF7r8EQ7+9ERKItPK5igPXfGfRwHwW8xzt68jiUv/td327s4/UPPgTl4RDr92vPPbPntaH88//lf7mt9ndbDxrXB7RioSDF4vbNV6lINwX0oGFb5g250E2XxPiemDpeqUg3eg4OagndvOy8C0qexzduuA2XHhy4zJ/Pe9DgbfIAwtvgKcA4Bs/cB7/HOA/ahxvd/P1Oznnwcfq+d9PXRf5iN6V3yvV9lMslqdzmg0aYc6x3+qBhPGTS63n74AeDIrVhfpBgbvmgEVAfktfGg4Z9iwcN7qvFvAeNMv6Nzz0MzS8v9utn/Ov7qdZquw/g+qDxjc3X86Bxnf1uf2JZu//+i+w7+3ofNKjOuHz9r1Dit3AdGh//Cxzk13le3CvzDsE4jbvQFm5RVQZZtr9zsON6uw8arodfel3/+3X8nLmqWMIxPo7wi7mInhtCwT8EIffPWz9oeD4eh+ulVOYvA+m8HJyTbb7fk5w52KKxn64Rv5/nzzwpEl9nfg+/zvvgLzn5i1QRkVKJ52Cq/7z7j9tof2oGVxRFURRFURRl5NzWLxrX6XQ7kiQ7TzgJPolOjOHPJ6tr+DOaiEh1CmVKG60mlJM+/ixWpCdNfnjt9fCnIhGRSgV/TjK+YS7wEzU+eXbaKDEaDPA8Z+bxJy4R8ykwjvFAPQ+f9PlboG6nc9PXRUQcejoN6NuEAtVVYQxf72zheZWLpjxrnKRSMUm8vL1P3fb+fzObJalkO3I5luLwU3WWmr92cVvgbwT4Fw6G95H360SlgvvgX1pu9fTPr/MxcdsSMb9lML8N4d/8b97ts5yf9I1vS+h1ljnxMbBcMMvMuuZfPbgc7pGqhTmytf0gkxu1ydVkfjObtwH9ReO1Qt6ViOj6RDyO7PSDMGd82ReyLF8SJbf5zfYtmx/9Ukw/gdhUTvib2+0P3fQzbsLHyQd184PM+yUq+zq/1Xfo18c45xhS2q9Lp85XxjhNA3Mftxoe7rURO3TKu9/4X9nE+7UwxXuK1Y45Vy2uN6H81scfhbLr4lx2YQnlQs0e9rulJfM+c31zE8qVafSWNPsrUO5HWOnF2jiUu028l/I8896pVMJz7fdJqk73gG5xDMoz8yivb7c3hOmxcCbG+vdIxlip4z58kuQfO37S2Mccyef/43/6AygvrdyQoeVJx18N/UVDURRFURRFUZSRow8aiqIoiqIoiqKMHH3QUBRFURRFURRl5NyRRyPwfQmCbb3aVrMJr5Vp6Vr2LYiYLve6XYfy5nDtpvtnnTeXRUw/BK8cxEvHRrTMwRZ5GSLSxE/OTBn7PHkStW68lGyjgTpDXjqvXkVvRN55VctlKPNSoB1jiVw87zJdj4X5OWMfrSYu0carE8V7NHnG8m37wNZWW+Kd68XH5tFKEHbOyl22Zy7puxdj+Vq6DoZPIUcvyz4Q9jvcaZnJe539EHwMt4K3mXdetwrk4dV5buWHyfOadMirxP6UwWCw573dmx7PXcOW3a9njOW1qd6cWwviTW/RbVyLm73/dvZxr3XeIrd33HefvP5L14NWsMl233dnfWxk7Fl16pb8RerYMB7R+Rsr25j92CK/g01TBfsfUnPNJz4oKuWd/519Z2qs4GOsEpT3KV4lE181avsW9f8XWjVszzbvRR8K40ScnRVGyd5q+JvOXjSXgR0v4S3nd/21vwbldhvH9bVGE8qZi/cxxRLeF4mIdJfxPnKDfLexjfNMHOKSuo0tvA/q9tehbHdxeVwRkQKt0Ok4eP9VrWG5G5Jng7zDdh/v50REfLrn623heVTr6JM+ePQYlGdn8Z4v5AsoIhcvX4HyFz7/OfzMHqN0kjOHvxr6i4aiKIqiKIqiKCNHHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSOPRqVa3U0EH3ZRQ9ag2Pb62ITxeU5oFB9332viNjnNOuzhur3DIa4jLCLiUbZBuYy5Gr6HWrn77kMdG3s8vvKVL0OZdeQiIo6Lx9kmv8TqKq71PE6ejFKA2rvGmrmGchKh0LVcRU1ft4fH1djA6zFGGRlN9o2ISCCcxIz1vVeXbH+9Uax/Ab7y1WeksJMZMT+H6z0fmJ2Gsm+ZCZaphZpC9g1wbgN7BDivIi93g70HrOW+lV7+L6LZ5/fweYxCk2/mYNBa+VSXt3o9T+PO7Y1zSvYeA3un9os4iyXe0alyGLrht8n5PAeD3yrtlbNs+NoWcvJwGLNdc5u65SbuGCMPhtsxv5/K98rBYVOX9igH53oyuGu99r6jMzT7eXk4X2fFpuRlKMbmWvrcIm2uK05avoX/yxy/cjIuOMGd/FMxZ/TQJgZ0XnkxKS69x7NofKJtprewnuRdi683uf1uk6WxZKm982+qpBC9C7Gfc3vp4P3V+Yvnofz8i2egfHUDPRtzc4ehPDWB876IiOfiwHz+/EUoBxaOqRPkG0l6eP+WDvA+03fN9mrTwFGtoV+CYs+kNcD5KwzJD8qTi4h0e1gXPCdXy3iPd/DoCSjHQ7w+/+cf/ldjHzWaT65eWYRyZU9eHs8rN+O1N1oqiqIoiqIoivINjz5oKIqiKIqiKIoycvRBQ1EURVEURVGUkaMPGoqiKIqiKIqijJw7MoP7vi/+TmCfT8bY1iYamOcXDhqfb1CQXTdCc0pK5qJut4dlMmInOWZc9r+xEW12dhbKf+tv/QiUX3zhRSg/99xzUF5bw/AWEZGV1RXjb3th0zD7vdoUEmiY50QkYxMouYt6tNUkQpNewcf3FwM0xYuIlFx8T8cwjd7YR/b1ugr/Avz5Z760axA+tIBm8EcefADKx08cMT7vFrC5s9mYYXMlvz9vMQI2LnJwIsOLD7BJ+lZG3rzjNNrbLQzH3CKzzOxXe8PyREzjNgd08nHzPos5JmY20vNnwAyeE2q5Hzz/0lelXNkOiYqG1MdooYlygAtRiIiM18ah7FG/HPSxnldoIYnG5iaUFxbmjX3Ux8agPDFeh3JA4VJJhvVsUXvg8u0EwRmfoTaZ3mpRhNyt3mq/twp+47fnmIrJ0Rsm2CbjnTlqkLMoyGuPvPO/s3Gbx5YKBRq+sWYG2L7hwAEoTxxAA69Lh+DSvM/zH4+7lmPOj2FMiybQWBLSeNELcexuUnmD5mQRkReWl6B8boim4ZgWU5GY2vRtNE9+z2vNHJ5Ynoi1PX7wsaUp1nnUNxfseOmll6D8Ly9+Dco2BSoXKmj2np/CeX9m3BxjywG2l3YD702jDE3V9Umcu2Yr+PmtAY7RPGaLiPR7FHZMcyibvbMMx+CNdQqrTs1FFpII22hAiwh5PtZFpYYLMn3585/BfTZwLhEREQpibq/xe260cb5fvxn6i4aiKIqiKIqiKCNHHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSOPRurYku7oI+0C6tqcIurHEgpmERGJWfuboqax6Jeh3Nps4sGSBLJUxGMQEbE5Q6aHx3WQtP3zM5NQ/jf/62dxA0PU1q0vm7q2zQ56SQ4dRo1qrYLa7T4FwgQunsfkJGqsRcxAmPl50noH+Hqy2IdykXSLM1N43iIiCekII9IE7g1FuhcejY2t7q6HYauJmsiVpWUov7nzmPH5Bx68D8qlErY3lxoYex16PbzOeT4B9mTcKoDvVl4GI4TrNjTW5mcQPq9bhevl/Y09Ggx7T5i8Y+TjupkvJLrF/u8W/99/8zviB9vnttVEHfcY6dVrJeyjIiJTddQcT0/PQblawdCldg/roEuhWGcuv2Lso1ZG7e7xo6iRP34E/UtjE+jz8Gz037kcRJiZ2tyENMlD0shzP/BIi50aPhBzH4azyAioo9cNffutAxWvhzFeJ6FyvHNc/L59Y+9BG2PwbZgAbK5n8nPdIlCy4OP4drpuejS+/+TDUN48gnNu+wi28ZSGig7NpzYF/BULZhhrpYAb8Tz8TCbYnmLyMEoLx3J7y6y7pQ305fzef/53UH55Cb2aoUXzCR2DldsCqZXfbCi/B6mWrpWIY+30AQ6G5Xu+0Owjy8voOeu4eJ/y3//wD0P52RdwfFtevgzlJx5/yNhHrYrzeoXG1N4GeWqHOI6XyCPUjPD1YWLeNg/7eB4u1YVP918F8u9RHrM0N837zAK1J/a9DQbYhq9ew/Pke6ZogMcsIpIM8ZqxJXTQv9Fv8gKLXw39RUNRFEVRFEVRlJGjDxqKoiiKoiiKoowcfdBQFEVRFEVRFGXk3JFHIwp7EjnbuqzxCdS9Tc+i5n8QmhkD1Qp5KgJcjzggXZs1SVrODHWVjm2uZ+xSDoFNQkZDZz9Endqxg6hXvnIG132eLJr6UNuidelj3KdDa4+7Ph4jH3OxZGYvuC4+Ew4GWL8e1d0hWsu8WqtC2bJM/aRN+8jouJPoxmeSHA313SaNs11ddj/BttDcQv3hl77wRePzXK8PPHg/bp/WhU7Jg5HF7OHI0aqTNj1NyA9h6CyxGLPvgzXVXBaRlK5FxtpJXu+cfSN0jIZeXsxcBI900+ynuJUPJM/fwlkcnKuxd5t3og8dJedfOSeut30Nh9QHr2boE/Idc6wQ8qW9/kH0En3L274NytUqrfE+hv24WjZ9ag5pwTMbr9XVTew7fRvPYyzAax2QH8E1I1BkaQ0zBj7zGVyz3ae150/f/yCUDx86CuVKyVwf3zL06+wdodwfIw8EyWtDPs1JvoXXMNmZT27lg7p7ZHu0+Xz8XKaxRkQyqgUeThzybHDbaZIuf6tt5k2EF1BH/6loEcrRHI67hRCPM0xprPGxzbuJOXaM0Rg4Tu3HI408n3hCbXqQk7E0/8Drofyd3QaUm//7/wHlRfYpkc/SzslEMmaUmwZp7H8bHPMicb3tY2qQxt8mz2zimv2rs4Hz9JBO4dDCUSh/5ZmzUL68fBXKVs4+POrDU3O4zZaHc9VUFTMsSuRV3WrhvdXVZczlEBFJ6X6kVECfbUjtc0g5GZ5PY6xtXttBlzwVdP+RBJgPcvnSFSh3W+gNlsj0aAwpxymhfeyd5/Pytl4N/UVDURRFURRFUZSRow8aiqIoiqIoiqKMHH3QUBRFURRFURRl5NyRR6Nx9YL0d9awzljz6GM5Dk0dpZOQhpY0iq6NWk2LdGqpzZkDpkcjjkhv7uJnLly4BuUvffGrUH7jG94A5c4y6tweidH7ICLy4pV1KF/ZRB/I5OQElD0Hj7FcRD1pnvckJd2q6/r0OmrrSmXyuzh0PXKuPEtG/SJ5RfZ4ODIONdkHrOyGRyOltvTYGx6B8lYDdZciIs88/SyUFw7htRyj9bclJsWs4Y8wNYq8Dj0fJ1s0eK1/W9gvwWuxm7CXQWJ8l0N645QOMiPddZ4u2CEfEXuCWLIeBAG9fnOvlIiZ1cFr+O/NHEnukUfDyuLdNlgMsA7iGI8/GppZH6dOPgDlxx97HMr1OnrdKjXM4ihVcKywcvJsPI+8VnT9v3oe/RSrT52B8uuOHoLyibk6lNMM8wRERJ752jNQ/vhn/wzKfVpnPvjTP4byd37Hd1L5u4x9FD0U0vuU1dIf4hi4vEyeGXr/7CxmmIiI+Dyukg4+3dEl89y0f2Sv8m8xBh8/L0aDPpJk7NnAthLRd5GFFOeREwVzIinFpAVfwb56+WsX8f0FbNOT0wtQdqhfdXL6VSPEfa6VKauqgNuo1rAtlYvYNnq+eV7LIbbhNzyAeSFfnf80vv/KJSg7GbYtO0fjznkfeX65e8n3/PV3SKG4XXfLa014rdXHeWh1zfTvdGfrUI4HmBfx0ssXoWxTxpjrYR2ubpj7WFrGuT8I8FpPzR+E8pFZ9AAdq9K1fxGv41bX9B/3utjeeFzmchw1oczZRIWCed07fcrNoPp2IsroirGvJpSLFjjm7ww8j7OPLYrDPe+9/TFQf9FQFEVRFEVRFGXk6IOGoiiKoiiKoigjRx80FEVRFEVRFEUZOXfk0Whvrkm0o0veDFFjPSTxZ2DnaPiHqCmzSSPmuqiTtD3Sj5L2OI5MjdiQ9pHRYUxNTEP5qa88CeX1aVz/eHUJ120+cQj9FiIik0XciT92DMoPPvYQlBsN9ImwlrvdMjWAWy2sb87miELU0sW09v34JPotvMB8xkxt/EzRw+ZR2KMJDnM8OHcby7bF2tHxlyvop5idnYXyVB11lyIizzz/NSifPYPa9CfeiHp5VtDGKdbPda3qXjgvgLWXrJHmXtLv4FrYwxSvU2KZXbZNGSIBGUHq46jz90ron/ApP8W6jfWxr2dJ7JbJr+D57OG4tZ7zVlkbe70ohi9ln4iTnoi1XV+c05AmeM7F4pTx+e/9nv8OyvefxjyJpaVVKK8sYQbBlavorzDyAUTkxH3HoVydxOPoUztu9NFzsdrD9jSV4Ngx2EJdtYjIM88+h++h8cELaBtDHOM+8cmPQXl9Y8XYx8ljR6B8gLKCrlzDcfXKFfTXJeRFOnwItyci8sY3vBHKGfkgkp1L3m6TD+GeQHk4ZLIbijlGG63FIk8K5eNwXtJpmqPfVjCzYsYznKvu7+E4ebmJ811wH865MeejkLbcy/l+1BfU8qc9PO6Q9ez0+UrK5jnz/mXYp3ueDpYfm8V7ixeuXYDySoLH7eTsI8v4mr22vgv+gXe/U6rV7bl1QHlhK+TJ+OJTmIEhInLpEtZJjbyka5SzUShi2+j1cB//7ROfNfYxiLANs/cvimn+C3B+rFSx7Rw5hJ6hlQ3TI3T27Au4T7q0fkAeR8qZi8j/4/tmjhD7cjPyS7nkIe21sC4zzsSIzDk0SW7u70QfmHo0FEVRFEVRFEW5h+iDhqIoiqIoiqIoI0cfNBRFURRFURRFGTl35NGwi47YO5rggoea2wKtO+3nPMPEPmnbyKNhUTaDRT6ElLTjbk6WQ+bie8YnUON3+o3ol/jTj/4RlL/wyku4wQi1cwmHTYjIVgt19ekYroXfbuP67k8/jfvodfHzrkv5FSJSKqHnYNBDXfXmJmoXxydR47fewO3NLZj68ekDeNxhhNdrry7evgfrew/jSJydNlAu4/lxW6iV6sbnpyfQX3P+7CtQfvQhzOLweE19C9uWZZvdh9tHgXxGDmXBXLuEa3Svr+GFurKCOssri2Y+SGMDP1MgHTV7NI6fOgHlE8dQ635gAf0uIiI+5WLYNp/XzdsDZ2JwzoaISEK+iyHp+Pd6OO5kDe9RMjtVEc+/3tYo5yPG9nDy2JuMz8chvufzn/8ilFnre+kS+g6KBRzPxiZrxj6uLGObKlE+TJxi+zh17CSUD1Wxb4WbTSgnnC8jIrOUfXD61OugPDM7A+WNdcwe+tM/wXH4M59Dz4aIyAsvota/VMZyt4/thecLzoL5wlc+Yezjk5/4KJQjyqSxd7xJYU6Ww/5gyfV2l9H5lct4nY8/gP1cRKS5iePJ4lX0BGUOrec/wDp959g8lE9aZj/OaN444eJ73rCI/hZniLr9Cs11gY/X2cvxqWWUV5RQiEhC+RT+JRxHXfKUpQVzDm6SH6qU4D7eXMO+uTiHOS3/qYFzdD/HZ+bQn8xx7t7maoyVPalVtusqoXu8ko/XeWmlaXx+fWWR/kLe3iKOZ5cWL0O5Rd6olXVzHzXKHrJs9O/YlGfi2nitq2TvrDTxouRdAYtud4tF3Eelim14MKB7CcH3J6HZNjJqL4FLbSPG+8iErL4ZXa8oyskB49wc8l6myY1j4PHnZugvGoqiKIqiKIqijBx90FAURVEURVEUZeTog4aiKIqiKIqiKCNHHzQURVEURVEURRk5d2QGH9qy+2iSUSJJSsaSQY5RpFBCU05EkWjhLcx7YQ8DSjgwS0QkTfFvkxRW9bqjh6DceuwNUH7mBQx1O3kKw69OHKwb+/zTL/8bKM/Oopmy20Ez+JNfeR7KMYWk1HPC5o7QcXtksHN9fGYMKbjwwgU0Yb3wEhqhRUTe/YPfBuVylUKQ9piL7BxT/N2mN+jvhu+M17GOp6YwLKkamAsFtBbQ9PzyeayDpcVlKN//IIapXbqGAWBL18w69KnNHjuKhsCEgi5f+hq2t/o4mmYvXsTAyGeef9nYZykgsyR9f3DtKhofn38RtzE1iSbSb/9r7zD28cgbcBGFMhlxEzItemT+5r6cR5KSQe4mBvI4x5C8H0RpX2QneKtAhlEOcAwHuGCDiMgf/V//Ecor62j27g9x8Qk2f5+8734o9+j9IiIvv4xBlF0KgRwjw+UR6js19yCUrYyuZU7Y58FD+Jm1dTRxLi3jMXTRFyuvfxCN880t/LyISKN5DsqLK/ge1715UFdKgVVBYAZubjZxm80mHuji8vYYkcS3b4QcJZaIXO8WHAZ6YAEN+f/D//Mnjc9fpgUw/rd/8a+h3G83ofxEFdvKN1WwHBnRdyJJGd8zOYWLS7xriPN4YYhjh8t9O8FrYOcE9XIb7VOIbkJ3Og4t5JFQoG00huOwiMhwFk3GhR626eBlNLX/wEEM7t1wcCx/cpGN0SIt4dDF1xbnXzkjlZ2w3IUD2OcDB+9bKjlz8KMP4yIR7Q6OkV/46otQjikUMKb7O4sD5URkZQ3DPh26Vy0VcL6zBRfBKRbJ9E/jermM90UiIg4tbFStlamMn6HTlqiFCyg4rjm/TS7UoWwn2I+6IdbNgMY/cfDzrYhWCBKRgBavEVoAJ9tzz85hpjdDf9FQFEVRFEVRFGXk6IOGoiiKoiiKoigjRx80FEVRFEVRFEUZOXfk0egMQol2tNgRBRZZJNfyAwwgERFJQ9SUpSwH8yiwz8JyuYwawCgyQ022tlD8lpKO1bJJD+qh16E+gXq9Bx56PZQPzOHrIiLH7/8KlMfnUCvrFshPQf6Kbo80qI55WVwKYRuG6PvoUoDfxgaqOxsbm1DOLFNjvHx1A8r33Y/68MDfU3f3IC+tHw7E2tEd9vqsZcc6HSONpIipYe520C/x4vNnodwhLfFnPv8FKC9R2JWISLWEes7T96GOdXoc2/BYuQ7l8XHUyycp6tIHQ1O7WaYgKSG9sufh6z1qO1tNLH/0ox839nGN/Cvf9m3fCuXxqTqULdvsm3th/byIGU7ledjmwRPBCUn7xHpjXRx3u349j44hxWvvzJvBh2N11HmHGbbb2QBDJas13MbkLI4/m+ewfYiIpBRexna5jOqOtbZG13bwOuQFpSYJzgfPfO1zuAkHNfBH5h/GDdBkcGABvXEiIrNzOB41ty5CudPCNhpR2GqcYpssFrB/i4i4NT5XrKtKZbt/RmEiT30WPVv7Qbb7f+b82NzCML4vfQavgYhInXIGX1fE9lileea/K+B4dZTmdefIKWMfxYM45vWL2KKcM9hmawkHX+J1iSIK7ozN6xaSn6vv4HGG1FdtC9uC38ZxtXjR3Ee5gSGTyQbOl+EyegNmqJv8jSr6RU/MY12LiPyXFfRxXAk5LO7efjf8R3/0f+165eZofHvwdeizcsT0Mpw6dhjKK+tYh3Mz6BtY3cCAvmYXy3xfJGIGPa+vou9qfgrH2IJfh7JP4Y1XrpI3k66ziEipiOfK4bMhhc/y/dpWE/vuqePoJxUROXUYj9uhfVxZwbq5vE6d3UPvVFgy5+gieTQGdG+a7J1M7iA0V3/RUBRFURRFURRl5OiDhqIoiqIoiqIoI0cfNBRFURRFURRFGTl35NGIwlCsHTNGTPow1vlGQ9MD4Ka3WPt+gPqwkHTcvBZ/3tr8Pq3x3myj5q9J2v61LdS11UhDXalSXoBjek8efvRRKNse+gOW19AfUR8jrRxpicfrdWMfjY0mlC9eRN1hp41+A44Y4aoql00PQ2MJ9XitKdQRjk3f0Fkn90AjHyepWDu6QPZoJAlpbCnjQESkVsXsjVoF9ccvPPkUlD/5RfRktCnHJQ3NOrAmqaIzWsO7WIfyseP3Qdn2sX31aU35vB5kUT+x6fuDjDJPJidQKzw+htr39VXUuouIPP0k5n2US1iXb/2WJ6Bco5wTzsRgP0be324ne2O/scTeze9JSOLqkQ9hLKcf+x5qed0u6oHZR5CR+c2iftftUr8XkZTySNgPE5HGfUj6Yb4OUYha35TKIiKFAM99bgY1xlmK7ToIsD1ElC/T7ZoZSb6PY3G9ehTfkOF0trxyHsqtDo5vqxuYYSIiUvZwHzxlOTv908rtiXcfS24M7Rn1j/UG6t3/y//vPxiff3AM+/79LvbT+yt1KB+htuDG5P3roLZcRGRlGdtXZxLrdGqI84q1Re2L/INDGs8s2xzbOwU8zrCI/WpAmQ6cQVLawjl6uIplEZFhiJ+pDfDeoZBg3WxQ3kJWx3n/wap5Ho0Ut/EfKWsj3juxZ/tvlVxZurbrYTj/8rPw2uWrS1A+fvwx4/Mnj6P3ankVfS/zs+j7uLSIGVArW00o2zkejYC8vJUxvKcbdLHNdlrYb16+hGPVl5/DfJRzF8yMn7EKfqawheNX3KMxlsbtqQqex+yE2TYCB692ldpXTGa8PoUVDSzcpjOF9SIiMuijX9OJsY3be/xUaSaCSTKvjv6ioSiKoiiKoijKyNEHDUVRFEVRFEVRRo4+aCiKoiiKoiiKMnLuyKPhlIviBttaMjtl7TC+NwrNdaiFtMK30m0npEAcDkk/lqPh5r+1e6gi2xpguUK6yVIZ17V3aC3/5RVTvz49jdkHpSqudb9Mek/OGKnV8Bi4XkREFhdR/8i66lIZ9Xe8FjSrOYdDU2d95Qqu4V2fRB9HZeLo7r+TZL/VoSKZZe02tCGtrd5uoR4xplwHERHfw3rnemad+ViVtmHhPu2C2f4mxsnjU8Q6nJ3FLI/6BLadzTatG97CsuPeust69J4wwmtdoMyRXg/7lR+gplpExLJRn/zkk6jPtV2syyfegvrciYk6lDPbbONpghpT4x175ckcDrFPRFEi6U5OSeCT5pU1sK5ZjyF528hOIUN63aEMC/Zb8DggItLrof6X69W1cJuGJyPCsfvSpYtQHp9EDbSISEb7WKbxqkYZAhF5NBqbOC6vruNYJCLieriPiTr2nfGxE1A+chBfX1nH/IbFpTPGPjaaeNzFIvaVJNzuj1F4b9rfXjLqIfytod0z20Z1Cq/9ZAHHxDpnXbl4ngPyjC0tXjL2cXmL/CsFvC4p+ShrQ8q08LA9XqJ8rSXP9ElOU5uMKS9ri3yQThH76uyxOpSXV/H9IiLxKo7FxwTrqtjBz/TouNemcDwotc05+PEq+uX+1Mespo09H7kHUVbiObZ4zvb1m6QxfXUNj/XqlT8zPn/4MOZobLYoD6yL40A0xDot0xxtUQ6aiEjg4/3UGPkJWyvouYhjrMnVBl7nLs2Prp3jPyZf0WQN9zlBuV7HF9DDFpSwXxaLOf5E8kf5Ps7zUxO4z0Eb6+roAzgnf/55c4x9+Sx6Zhya192xG204TVORpunRykN/0VAURVEURVEUZeTog4aiKIqiKIqiKCNHHzQURVEURVEURRk5d+TRSB1Lkh3NVnoLjb5bMHWUtCS8uOSn4PXfQ9IKp+wDiUyNY2CjZq/VR83ftXXUEQrp3HgfrTZq/6OQFs8X06PhFVAj2OniuuGOg/tkj0ae92RqCn0fc3NzUA5D8myUcI1l1m2ff+WisY/FxRUopxae6+TcDf1omOfBucukckOm75EHpdXEvJRuu2583iuiRtajNlqt4nU4XMA6bLexLdk5KtlaBduff4v8EpfOo01tpdPCfQauqUlljf1wQPpi8kM0qa44g6RcxPMWEYnpeofkkfnqV56B8tRkHbf5yANQ9j1z6OExhaM29uaFpBxisU8k8Y1WOKS1+AOXxzxzDIxjrke8NkMqJxl+F1QsUJZETlYH9/2NdVwn/v5TeC0W5tE3dOYMehfYG3f06EFjn40mji/tFq5/39hAb5sj2NeiCK/nxARq1UVELBvfUyD/UxjxfIL1UPSPQfn+U0eMfVy9iu14q4WejVQ6O9u+9x4NIZ8kjwyHJiaMjxSojfYHOIf6AW4loPaa0gQZ+uYY+NYD2J4WhziGPXMN2+PckHIPaK7arOF1vPzEg8Y+jzx+P5RrNM4GG6g9F9Kel0vYr1YumBkrg//6RSi3BnhvEFiUm0EejJkOjrvzFdPDddHH+p8hH9h6aPpu9pNOtyVeuD1nTU1j++ps4HVbXsYMEBGR//yf/w8oZz7NhwW8z6mPUR4T+XMabRybREQkxbnF8bB9TcwdxX1M03w3wGtfr5KP6T70mYiIlMhzNlnHbU7QeRSon1kuZ8QZuxArxvMKyK+SUb+ZIP/xiRM4/j172cyK8Wl+sai/O96Ne4s0MX2Wr4b+oqEoiqIoiqIoysjRBw1FURRFURRFUUaOPmgoiqIoiqIoijJy7sijESeJ2HH+s0kUoh7RMlfBF99FPXpKGnfWvVokVMtS1ERTUUREElpff0g+j5Ut1EkWHdQIRqQT7/ZRs1YuoNZORCSgXAw+bs6s6FG2hx9gvcSxqT8vkr+gWkXd4fIyaqBdylJgX0iexDgjzW9zEzWoS0s3PBxxtP8aece2d3X6vo91znr+MCdfgLMbEtL5F8mzkVA2wDStG97tYv2IiDhkROJ1+B1a373XR0/G8gpqwkPyWxQDbK8iIp6D55XSdYzJg9HvsbcA20Zzq2nsg9twqYwa1NYWHuczT78A5dk5zFGYmUEtrkiOJ8PFsSbbcx6c9bB/OHLdo8Ea1SzFft/JWSe/1cG+PwxxG/0BXpt2C+u1WsN+//hjuDa6iMily5eh/PDDj0B5dnIWypevXoGyTfkyJ04cp9dNATGP9sUCTy2opR5G6Ae7dBnXdK9UzHF2cvwQHkcF+0Knj9r/9TXUIPd72GbG66aH4dSxd0C53UW99pWl50REJPJiETF1/PsKTYDTlA1xfHLG+AjP00PBa2nTPGGHuI8mjaGrGerCRUQeoTGu0sdxstXGObhF/ogsxWN0qT0WZ3AsERHxJrBflGvo8UkLNMfS+GHTvD9+3PTvhFMvY7mFbbjl4Pwx7GEewxjlmkyNmX67FZo/Fsiz8ZLc2EYm+5+l0Wp3xNvx15UqWOerK9j/alWzD6+sYT9fbuB4ODV7CssLR6Hs8nwamjXAY6hk2KYLDra3lHKFAso/eZC8XGFotvlwgNd6kjwZ5RK2DYpDkj5nxIk5xlbL5J+g+8zBEMsu3W+/ePYilL262cbnT+CYmDZxbrCSG+UkSQRffXX0Fw1FURRFURRFUUaOPmgoiqIoiqIoijJy9EFDURRFURRFUZSRc2cejcFQ7B0PhE0is5Q0+ykLrkXEIn2na+PuY9LMe6TDL5BPIXRMDXRGqkWX/BONHmriJ0qk+WNdOJ2H66HuTcSsiz7p6nnt/KtXaZ3mcdSTWpbpbxkMUMNXJD1uSNpbzkbo9ShbIQe+YhXSYJaKN3SHkbv/Ho1CUNit624HdZLXltCjMj+Zsw4/ZVQkMdZZtULradN16FOWRIV8MiIiro2+Du4GgwEe94DyKBobqHNNEtIr22bGxcxUHcq9Hn5mpdHEbZKi3qK+OyAPkYjpG/JoPXOLPD9nz1yA8sIB9AW87ZvfZOzD9ei4Utap3uhn3C/3i2Toiux4MzjT4vAB1LxOTZo+lHIF22VEbbDXx34+OYP15tPa6VOuOYT3aIybnsfMnauXcX17zsnokrZ8/hBq/Wtiaq8tizxTKa7h3mxuQbk+ged9dRm9SewjEhEpFbBvzE5j3Rw6hPkNPq2fXxjH9tVoYNaHiMhmswnlEyfwmp48sZ2ZNBwMReRLxufvNpnIHkMM9oGSQ5krtqnz7pPvrJXgmDZM0fdis1Y8o3X1M/O7yvYmth9JcIybprEiTHFMbNrYHsfJxyYvm8rwYIj7HNAY59J52+Rjcx2c14u2aWIskL/TSXBODW3cRkb3BR71s6RF9SQiRTJPHvKwv9tyw++SiUiOTfWuMhhGEu/UZXMLj3+D5q4oNn2S7oCybhK8/6qN4bjBPsoO+Vwsx8wisT32o9JcQW241cb2NVfB98/N4Ji9umLeS2XkXS4U8Lxsuvfl+WswIM8hXnYREalUKafFuLfgjCY8psvX8DwHk+iHERGpz+EYWh4j/8qeLI8oiuTpr6Jv6dXQXzQURVEURVEURRk5+qChKIqiKIqiKMrI0QcNRVEURVEURVFGjj5oKIqiKIqiKIoycu7IDG5lllg7RpooRJOOT+bQYWwGalGWnqRk0HLIkJXGaHXKyHFqWqZFHDLAxWSu6pJRcryEASU2GbosC6uIQwNFRJpNDIYSMigNKDwupLrbaqKpKsnZB9cVm6HZbMTXo9MiQ10OHLAzPY3BSKXyDaNgFO5/YJrrOLtm8GSAdbq0jMbO/ikMGRMRKfhk+CMzb3+ABlXPw+fwAfnfS0XTmG1zCCUZthqbaJgL6BhCOi9u42M1M7CvSsFlm2TS69JCAhm16ZjaG/dTERHXvXmYobjY77odrMunn3oeyocPo+lMROTwUfxbRn3X3rN4hLH/fSKObMnSnQUJKPTr2OH7oPy2b36n8fkwpsUC2CRI5QGZIdkCH9ima/DkqZNQbtFYcfIkvt5uY6DaH/7R/wnl4xReNkcGdRFz7B6rYbheOMQ257vjUD64gHUnqfkdWKmE5u44wnabRFh3MzNogq/VsK5mZ/AYRMyFFNpbuDDC5NT2mOhYdzR13h0o3C0VbFthaJpxh9Rv1odobG3R4hS2habWKcFxwK2ZCx6IYL+oemjwffwQth+HFn1IfWzzdcHxbSpnLgvP45jH8z4v7MHlNKKg1Zz5rUKf8avYfnpk9rZKOD8EFC4XrZjBb5MRzgcHaNzdG6aZiUiyz2ti1Ovj4u0siOPyPR8tgtNMzfZXIENzQCF0AS12UaDyOAXhrbfN69S3cVzgEEqXglY9B7dRpABlj/pV4JtBi50WLnbB875fICM3jW+lMm7Tss17QL+AdVH08bw4qDDOcJuxi4t6WI65YE7BwTY5N473x/XSjb48HA5F5GPGNvLQXzQURVEURVEURRk5+qChKIqiKIqiKMrI0QcNRVEURVEURVFGzp0F9qXZbtCNRWF7rod6sEGOxjFLWL+OZcq3EYf+EPZRA+hToJ+ISEreEPY2JBSyEw/x/XaAelLXQW1dv2fqKjkArVTCbXAglkehf6xvZg+HiBnOwvr1AgX4uRS0lFE9uDkGl9oY6ScLHHyT5P57v7DSTKwdlbrvYnvLLDzfhIOmRMShNup6HAaE1zblYDuHdL2GYl5kSH6I8fE6Hiddt8Y6hkAtL61CuUahiWM1U1fZoJCxy9euQjkm31FAgUY2+Zpc99ahlC7pXrl92nQ91lbxGL/y5WeMfYxP1qFcKFEo4B5NepTjAdsP7MwReyekjOwT8rVnz0I5Cs0wqeo4Xs/qJOq8ixQC2UuwPZVJ4xxn5hgYUagVe6/GanUoV0gn/e7v/h48JhpbGg30GYlc1+ve4NiR01A+sIC+kJDef//Jx6BczfEixRQA1qR277t4Hq6Dxx3FWJeubfZfz8L39Nuo/V+6cklERMKhGRa775AQvFbHeadaMwNFF7srUK6Tv8sl31l7iON8sICejNd9+1839mEXsWM4pEe3PBwbrBjHm8Sh+wKywvmBeV5SoxBJ9mSQh8zIGaTxxG4NhAlb6GUaUMhkchZDSofr6CVJqS053aa5D2qS4+QHcPfMQVkmEu1zbu5YfUz8Ha9jh/xMEZn7ygVz/HNo3iiWsP2VK9iGPbr4HNJZnzDvQ9bJo8ghf0Ub9zFWx7bhu+jLGlLYaByZc0+vj3XBt0d1GtdD8pc5Po5V/YHpQ7LoPjEIsG5cB4/TpTZv2diWCo55HrNVbIALs+i1O3Rg/sYx5twLvxr6i4aiKIqiKIqiKCNHHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSOPhm07u3puizSQvR56HyzLfIaJKRcjTVEjxt6FlGSWrANm3fj2Nnn9bJtep8yADMse6ddD0uMVfLPK6lXU/PXJ91Es4Hn5lOeQscA9R/vPf+N3VCuoUc1IL8n5H0Fgarsd8iAMaY31OAn3/HufxaEiEkfx7jWvkpa4SbrMVy5eMT5fpnWoK2Okl6+j/tgvoKaxN0RNYpLjQ+okWM+sQfXJJ7LaxgyWQQ+3OTkxDeXNTdRhioiEdBwJ9QvW2BfYXxGRfyfHo8F+qDimfAdub9RCQxIfX76E+mYRkcZGE8oHypiDsLe/5/X9/SDwRK5Xn0Oa1y7lUXz5y18yPj+IUcvL68jPHzgA5Te+5Q1Qdst4baLINFuFJNwe9FFzzL60lWXU7XNf6nbx8/0BnqeISEz5IBtr+B7fx/NcmJuHcnPjFSiHkan/7ZKmPUnxPHs9KnfxPDlXoj/A8xQRSUIc87bIBxLsjCFJsv8eNRERa+d/IiIZfU/ol8eobGas2C4e98Jx9NI45Ek8fwXHUWsL/Tmbn/4zYx+BTfk3lPdhO6gdtzOa92musshLY+eMTwnNy5Zz8/Eho26T0NuD0MzpsWicjcmn47SxzTo0ltt0L+HkhGCEZJ60+JpeudHGM8kEW+vdJ05isXdyKFZX2auFx14smR6N0MhGwzrwA/zMsI/vv7q4COXUNb2YPZqben0sR3TP1ylguU6HPSBvzWBgjk0ZmX5sytkp0f1WFOOY6riUiTE076/OvoznfvoY+ieCAtZ/rYzbbNP1OXEKczVERI7N4ZjBUTy+fyNbLaZzuBn6i4aiKIqiKIqiKCNHHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSOPRpalu1psi9bJT0mjzX6L7c+gRqxPuRjsrygUUQNtCYrn8nTarB23SasZBHjKDmkiQ9LokjxZgsDMMbi6uAzlYhG1/+/+TlxrfEga6f/8h/8Vyqxvz8MmjWkmqDO0jZwTWkecRaoiMkbrsBeKuI04vrceDSu9kWzhkPdmbW0dys9+zdRQP3Aa9cilsTqU5w8dhvLMLPojmlu4DzvnOb3ZaEK5RZ6KxhrmZPQ6KIKcnEDdJOcqPPX0U8Y++UpMz6K3obG+hq9P4XVOIzyPft9cQ56zNjyPvE8J6pXZsyFy81wNEZEXXzgH5bmFKShne9bXT+5B+xMROXVqXjx/+1xcB/03RQ89PqvNnGMcYj3MT+H1PjyB68RPkNY3bmDuylrb7Me1OmZzeNT3/+xjH4Py0089B+UerY8fBDgOlyqmv6tYQm0/ryO/Rb6PzXXUG1+9hBkEa2voGxExPX1j4zgWZzSdFQt1KNeqWB6nsohIrYLXozeNbbC9o9fmeWa/yKz0RkYEjeFNyoLYCk0Fv039tjQ5AeXNNvb9jYjGAsoLaFw01/sv0bW3SIdPXUBiasIW5YM4dJ458Sdi9gKEfZA8/aU0oQZG0IZIQKbRW23DyPKgA09d0wcipNW/RL7AONvj0TC8nXefOL7h011fxXnFFWwblRyPxgb5WNZp3l5fxX5/4PBRKLc7uI9mw8yz8Yu437EyzndRhP1iYwv9ghUaZ4TuIfPqnffZI4/FWgM9a1FG82ETx8evfvWMsY+1Fbx3+M5vfxzKTzxxCsrueZwrCkO8F3n9cZxrREQmxnCsv3YNPaR7q+IWNihAf9FQFEVRFEVRFGXk6IOGoiiKoiiKoigjRx80FEVRFEVRFEUZOXfk0bAsOzcfQ0TEobWxXdfcNGvb8nwcN9uGdxuiMPZ5sC8kIi35ZhN1bHEHNalphPq+ZtvMMVhZQa3iww8+DOXT990H5Te96TEof+LP/xyPMTJ1h0lCHhjKvLBJ/zk3j1rjEq3Xf/7CZWMfgwFqF1nrvTdzhPNH9oOJclGcHV9OhfwjW21sf0eOoN9CROT40YNQHquj/jqmtlM0PELkz3HM9juM8TrQ0unytRdepPfjPr/7u78PystLqFmtj+M1ERE5f/USlOdmUXtp1etQDimPZmYKPR3djnle3R5qa1mlGgSU70C5GQllO8SRqXF/5Ryu2f/Ymx6EcrV2wxORxGaGyX4wd2Bq1+dlW9g+1hZx7FhbN8eKjLxtKyHqg6s29tMXKDuiOIb1PLGAulwRESvBurl2FcenL37+81BeXsbXs5TyGXw8z9l57DciIi3Km+CcCR6Xiw5e/wLZPrivioiMT6CfoFLF7CCPsjqqFXw/Z9iUc3Imshiv4YtnsL+61+e5e6CPFxERK5Xs+pxG02FI+RVxznRpkS0gofmxQ28IyHcwdPC82zl5IjF9JiQHRUJtwabRxCbzg8UZUjmGDMODQWXrFi4OziTxuKJExGMLBjeBhD0c5MngNmP42ERcwb9d6qBGPt6zzdvxco6aKPFF4u3O2thE38GBWbxXctijIiL9Hs49Q/LaDSmjYm4efZKyhvcoGfspRKRWw3uDlQ2sw1IF53E7pJygGN8/SXlbpa6Zo9EjL9PKBt5X9oe4D573ry7jXHF5CT8vItLvYF197svo4zj94OugXK+jh7C1cg3K4SZ6IkVEYv8IlD3K3CrtzeRKb9+npr9oKIqiKIqiKIoycvRBQ1EURVEURVGUkaMPGoqiKIqiKIqijJw7zNHIdrWPvI44+y2qFdS1iYj0+qhtu74m+e7BkCeD1/O3aHH2cgU1aCIitSqtmUwawC7pChsdXMc5DfDzRR91hr2hqUnt9vA4CwXUAod03hu0RvzMDK6/7/vmZVmirI6xMdQnT0+jHvngwXkoxwl6NtbWcU1mEZFuF6/HYEia5soNLX8U7v868vMz07tthDX6HVrf3ae1/7fBY2YPRkr62MvnX4bywhx6GV555RVjD5aL22Rd+dHjJ6HsFVEn/uib0b/zqU98CsqD0My4mBjHfTTWUd85O015IA3UoPbJm1Momdr1iHT/MWmzWXcdsUafPD15OuvNJvbNmPwuhT11ldwjjbzru+Lu+lHwGHoh6o+btHa6iIjlokdj6GG77XRfgrIf4HdBE3XyIZzHcUFEZLOFet9WD/XBnRb284PzOFbwefFa9xl5fEREjhw4AOU6+YLq41iensI2y7ks+ckIeFxra+gt2SBddKeFrxtbS+rG32LSTj/55NNQLtW2x132oOwXe2M0OLuqVMC2US5gtomISE/QDFOk8crysZ/XXNxmRNdgKTXbwnONDShfo37Bnosqzfsu+ZgGNPbk9XzL8D/kvOkm8Hjk5LQ/l95UoGyhoYttuJNi37apzdRyvuc9MY3zdJ+zO/aUt095f8fBJCuJnW23oVYXr8sBup3sds22sUV5EZMz6MWam8Z7oTXK6mht4fnWamaumeU0oRxFON+5Gd47cVfuk9fGG8c+Uinj50VElhs4L69vYr5Ml+bYJMO2MYhofnRyxj/yKF9dwnH9xbM47r/pdUehbMnzUN5YxPwkEZFCAT2grof3Duke302a48F5NfQXDUVRFEVRFEVRRo4+aCiKoiiKoiiKMnL0QUNRFEVRFEVRlJGjDxqKoiiKoiiKooycOzKDt9st8YbbH/F9NJW5ZHLMfYQh70iBjLCWjR9irwm/nuQE3thk0HLIWFankKeYTTdkKmt1OGjFNMDYFFZYrpIJj+qiWEZz0bFTGC537SoGq4iIBGXaRwHrrlbB8xpS8JRNdTc7j6YrEZE2mUYjMlzXajeM8uFw/wPTJmdmdhcd2FhDM3uxiKbFuQMLxucPHTsKZcfG5s+hc0tX0QxeiNGwZXMan4gcPnIMyufOXYCyT4auJ554HI/xCJrj7n/ofij/ycc/ZuzTvUUgVnMLTcnFEi6i0BtgW+nkBBJx/Zqdk0K6qC0ZwZmxuZgAm5YHAzQTDvo3ysO+aTTcD9wgFDfYrt+MFg8Yn8H2U7tKKXQistHAc7QpAJXNyNYAx6OtTTQ8pwMz3FNoTEupzVXo+j/xpjdCud9H4+IXvoABf3lhiQ+9HsMVDx08BOWtFrbBXh9NoT1aUGOYYzjnBUh6FCI5HOI22LDtedjf2x3TrG9beA3vfwD7X38nTDWOYzkjGJi1PziSb5QXkYzaUs6KC56LbTIgA3lMi02UBOtjQGNgoWgaY6VCxtg1vNaSYpt2PFp8gsavpTZep8Q2by6M8DzCCMsjE/Xt2Fp5HxMB9iOviAvg8HG7tIDK6ZoZfOkX0Nw8oH6xN0xze2Ge/V2UYP7ASfGD7etVGsNg2ItXcJGbSgUX1hERiSO8tpMTWAen78PFUjY7OA50XRx7kgTHUxGRrSYuRuC72L7iIY4bKbXpKMZxYkjzEN/viYgERWwLbgE/E5L526dFGOKc8zChYEsKKK1N4r3HzBy2x2yA1+fSurlYBpvvyzN4faLODZN7v3c7x7xzrLf9TkVRFEVRFEVRlNtEHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSOPhuc74vnb+rSggNpNLmeW6Z9ISeQ4TqFNAwo1YV2375P/Ikcrx0rMYZd8B7QP30NtXRzica9RwIxY5j5LZTz31RaF4fmoZUyLqAmcP44hKTOHzbDDAnkyLrxyCcr1Sh3KrE9uUEjbxALWvYhIvIYa0vlDGFBn7/E02Pb+B6aN1cd3vUE26eMPHz0O5Xd/7/cYn5+dQT3x+gpep8Yqahg90gJ3mxiI4+SEAsYhajFTCowMSQM9SYF+xRL6e+YOYhBapW4GFF08fwXK1zW0u5BvaUDH6Hmo2+73TI9GiY7LCOwM/JuW2U81HGI/FBGJKQBqeRn1ovPze8KssnvzHcleGwCHEI6Po571277tIePzV6+hfjgk3XarhePVJvXbZEihYWNmaCmHKW60cBtjMzjejNWwX5QoyLJEXrp+jofn5ZfPQvna4lUoh9TmMgpfJauKEd4qYobC8vhfreK4yb60gPprqWTWXSHAdn7f6dN4XDt1M+gP5LMf/4zx+bvO+NiNyiJ/jkV+ifXQ9Lmsd3EMm+pjsFjURV/BNLWlJcHx63LLDBCNyDcwVcQ6TSKcO4o2hQZS26j5eF4D13RUpNR+MvJkpOktPBr0cppj2uD32D72i4qNY96EjRr6rIBjYGqb9xJXGujBWqFrnBVu1EWWZSIDvJ53mwOHj0lh53q+7e3vgtee/fKfQ7m5YXoAChQiyWGgT331K1B+4JE3Qbk+hnXc3DLP37FxfAvIOxOmeE9nORRiGZFviTwcaWre2xpjiYPHNRzgZ1xqKyG9LpnZNgrkA5kg/8Q3fes7oDxfxWNor1zEQxSsexGRK+QPrlt4DximN/r7cGDOA6+G/qKhKIqiKIqiKMrI0QcNRVEURVEURVFGjj5oKIqiKIqiKIoycu7IozE+OSH+TtZAtYK6N8tGUWN/YGo3gwLp0mLSkNI2XFr33HbxuSjMyTHgrI1qHddybpBHY6tH3oXxeSinHh5Ts2muvV4p1aF87hqur745wH1EFtbN+DQeo5Wzqne5gvo8v4R65RLp91iROkdelfVVU583MWPq//eysXnjM1Fo5iDcbTzfFd/fbhNv/aY3w2sLB3Dd/vqY6XMpllBTWyVt+sYqejYKJdxG4+oSlGszM8LECWotTz/wOig/+ijlfcxj3ge36YS0xUXSO4uYHoskwmvjsN6d9cqUs2B75rCQksciI52qudY4btNoLzlr4UcJ6pE3NppQbrdvtOFe3xxf9oN4OCXOTrZAmuExcKSFbZnrjE9M1qE8NYltqER6YtaaP/0V1DA//9Qzxj5YX96j9c7TCMeKtRVs1+xtSCI8seHQ1Oaub2DfmRTM6QkMD09Ar2OZPWkiZpYLv4eznXib/DqXRURcBz9j9B1vWzud52PaD0oz82Jd96ZQn0tpHLi8aWrkF0k3v0BZIlu0tn5Cno1VB9vCpaY5j2zRcfEYFpIhZyVDLblFbT6k2SzJ+Xr0Vjkat4Jn3DRnDrbpe9mwh+e5sdWEckwHFVF5JSfHpeSQ19XH8b40dWO8yNJEWtf216MhtrPr+Tty6hF4qVjDsezM888aHw/b6IMc9PD4bcp5cf06lCuUEcTjo4hIt49zqOvhuDFO/WSyin6Ig1U8j43L6Ok4UDUzyF44exHfM4u+3Aa1DfZqsl+nWEWfiYhIRu2vPIHHubiM/p6ZEm6zUMdjqnbN8e+ll7E/b3roKUz3eLbCHJ/lq6G/aCiKoiiKoiiKMnL0QUNRFEVRFEVRlJGjDxqKoiiKoiiKooycO/JoiG3v6rmbbdTWsba8WkX9+zao615fR13voUOos+d10nkt9kolbx833+fkAVx7mJbsFt9H/XIwQG157OX4Qkq4j80h6tw6q7hWea+H+ryMNKycHyIi4hdRT1edwHPv9EkPTtsojKP2eLZk+gvmF/Bvgz5qUBuNPXq9HI393ebgwtyuLvu73/VOfJHO18pZaz2J2buA7Wvh0FEot1t4rS+evwzlY/OYcSEiklDOysQU1qlP+tDlNdRAPnPmHJSv0rrWrS1sSyIiHuVmBAH5pTr4Gc4jsG7Do2FTX+RcjU4bdaycmxFTngh7PkREIro+62uoOcUcF3Od8f1geuKEFArbfSlJsc/FMfbjXs/sIx3yS5x75WUoOzZemwp5s5ZXMJ9ibR39FSIiDl2/jLTh7RaO3a+cwzbH426pgGPHzAxm1oiILBzAvjA+jhpjHqvZbxEYbdjUD3O75awN9pZwmc8rrw05Nm7TovdkOz5BzinaL8YqE2I728doBaiRbnex3FjBsUVEpB1Rv6MAimYbx/wXV3H88QtYP52BmdXRp3sB7umJMTTnhFbsIWPHoTl0fN2YSv8cj4aF5+6XyU9FHtMeeTA43yZnmpdBgvVZpn4xMXHDH5AmsbSuvWJu5C5SKQW7XsfOkPJRptED8Ogb32J83orQrzo1if7UyYVTUF7axHsln8a2sTH8vIiIbeP45jpY72XKfDt5BLMipsvYj+zwCJRPv+5xY5/ioW/jiTEc/yLybnZ72DY++/mvQvnSFcpiE5EO+YvdAo6pn6JtpL06lMfKOOZaBbPVpxbW3bXFRSgHe+6ZovD2fZL6i4aiKIqiKIqiKCNHHzQURVEURVEURRk5+qChKIqiKIqiKMrIuSOPhhd44u9oZ1tD1BKy/rVYNNdB39pCfZ7rsoYW39/torbcIv17HJtZDqyd7ZN3oVBBvTFnEEQZLYZPNVSfNPMZun08r2JAOl+P1tOmvIDCLdZ7FxFZXV/Gw/JRZ+hTRkREOlmbPAteYF56i7TcY0XUAE7M1Hf/PexTPe0DRw4tSGlH2z1WQb1hRP6dYg217SIiiUW6alqD2yaN7Yn7H8Z9ZPj5yviEsY/PffHLUH7uBdTgu6x/J43pufMXoLy5jm2r2TDXTe9TXww8bE8hZVh0KFOlUKa+yjkbIjKk9fOnxupQjob4ukPmp5TqemiZfdem9fWXlnDN9V7vhka1f49yNOZmDuz6C4Yh1uOQ6iDwTP0698sGeXSWl1Gb2+3hGBj2Uac7PmW2QY+8CzxW8HhTKmE/Z3/F9PQ0lOsT5hrv5TLl/Nwis4LLDvkp8nxq/Df2DfHrvAX2bLjk+RAx5zH2L13Pekpj87P7QbVYFsfd3jfJ+aW3hX0iyunHFs13qxvoJ2x2MR9kPcJtFijEIs0xTKQWv+fmGB4Mg5t7OPLga52XtwB7oF1kOftk/06lhmN3EGCbCGMcD1Lqu3ltPCPvml/Cea42Xt/9dxKbftG7zYHpSSmVt8cL9o2ubmCdNxyzzudmDkP58NFjUP7K1y5BebOL84RvYx2W+KZRRO47ip6LuRn0TxR9vI61CnpNvAz7QPmBN0J5ZuGosc9vqqI/xaY52HUpHyXF8zpy9PVQvrac49HooQ/ylcvoz7t4ET2N6008hu4A62o4MK/PeK0O5bCD83g02OMtCc357dXQXzQURVEURVEURRk5+qChKIqiKIqiKMrI0QcNRVEURVEURVFGzh15NAbDUNIdHT/rfqcmMZ8iS039VrFEujUPn3Ni8i54PmrKUlqAu9FATZqIqXtkza3EuM8haft5rXbO7khMabmUC0V6D+paByFq/krkpyiQn6Xbw/eLiNhUVzZphwMXt+EIHuiQMjGSBLWOIiIFWqO6T9r+vWvbD+P992hImuwGn2w2KceFfArFyDy+jJpCf4ga18Ul1MsXCujHOXYS1/h+5fx5Yx/9NmrqowjrsFpFXW+FMgruO3YUtzeD2s9+L2fdetJKsl+lS8e0tYV11w6xLXAmhohIt4/bCEjnmpAS26J+55Emv2yb+uQB6aI31ptQbmzcuD6DnPX794MkySRJtsfAJKaMhRTrJPDNc5ybwus5VsH2cGB+Acp90nUn5H3xXdPPVSmi5rhEOm++FmamBeuL8byMMTXnb7fKsDD8Fn+BXB7e5q3KvA8rpw1SVMKrHpfL3o19Ym5mUtwdn0VMOQZhjbw2Y2bOVLOBnowL1zAno7mBc2pGvshBmjMB3oIsLzBiL7d6/TawaOy4dc4J7dMiJ0mOpSNKcb5YX8e6LBXZG0ceDQ7tyvWe4HEUqC9XazfmpDjaf49GqeDt5lBM2eSDJA9kGJrjRBjj+Xz1GfRkbLSxzizy8VZKeH92+gRmr4mIvP4+zPQpF+jeiS5uTJfFc3A8LMzgva3kZHRNlvG82B7F2WndJp5nrYq+twOH0MsiIlIfx/68soI+jsVlzOYoWDh3NLdwXu/1zfbz8CN4z5O6eI3D/o199Hpd+aP//XeMbeShv2goiqIoiqIoijJy9EFDURRFURRFUZSRow8aiqIoiqIoiqKMHH3QUBRFURRFURRl5NyRGVws2fUvcQBJSgYbNudufwbNQQk5qwcDNMx47s3D9RzHPPxqFQ0zQYAm6WSIZqtuHw0yRTKDL69iUF6hYAbBlQq4z5RM7UmEdeOVyURKdceGTxGRgEzDvTaZueP/P3t/HiXJVZ75429kRO5ZVVlbV1fve6tb6pZaC5JAC5YEYgcdxmb44pEZs3oOq83mg8HwtRnzM5vx2B7b+HcQDOPBNhjwGIQFEhKS0L611N3qfa/urjWrcs+MiPv9o6qr6nluqKtbZFcJ9H7O0VG/lZlxb9y4S0Tm89wXzbppMqiHdTKRRiSrcmLYNpSfSKq1GZN6vTb/RrRmoyHNKYPn/oNoIgtDMiN79jM0J98yBk1dbNiqUPIq3rwgGWFivHwrJt5Jkkks7mK7JxOULI8MqpyUstmwzZici4pNiOUS9o0amcfLVMZEEU1lIiJFMt+XJnDcHD2CptKJCSxTKBlkIh6RMDLE8V2jZHWjYzNmcE6ON180m81pczQbhdlEHYVJYzvMNneKiCyi5HiWJ5U3u4jogx4lTON6WjGZpjm52VyJ8ib/RkZret1xzmwO589zAj8RkVjslzN7s2E40osbO3N6uem2aIGB+fmwbvUKSUytaZywzadxX6NktSIiFRpTw4NoKB0cwPWuRhuT+HVcd3jjCRHbpMzG7JCS0nEyTzu5HvXHiAvn0Fze04NJ2vyAjcqUcDjOm8jY8xOveYGP55Glub5zVnI9EZF6xD0Rk8ngMZatxQ1IOrpmziuq7c83zWZNms2p+Y8M9B0daGgulO358MhRTMLapOuQz+F6uGrlIog3r8fNMpZHJFB2BY9Zq9C9EvUvn/pTnDbYcD28l3I58a+IGErmyz04laIkqp0dEIcG19zShJ2Yt7sT+8bqZZiYsL8XY07uyskPJ2r2eeTb8P42RRuHNGbdL0dtGvNc6C8aiqIoiqIoiqK0HH3QUBRFURRFURSl5eiDhqIoiqIoiqIoLeecPBpOGIozpYX3KGlJabwAca1qJ51rUBI11jTHKTGUT8lrXBfL7KYkgSIitRrq0iqkz0slKTkVJbOKkY+knXSWjbrtTahQMrxcG+rvJE2a0hhq42Kk9026dhKuwgjq4dizEQrpR0M8jxxpP92YrbMeGccERGn6TGZWYi/XmX99qBNzpnXXBUo6x4kWvUSEB8BjjTd+Jk19gXW6hjSpnZ2oSRWxteWxJJbBul4Wc7I8OR7HOqdSdt+QEPtPs4nvacvhdWQPUJX0y0HQbxXB30jUaVydWIPa7lOUzIp121FJ38olnDMGTww852eiPj8fGGOmNeSsJefEdtwnn+t4Z4SnDu5fEd8VOexX4tfnSJ43Zx2jktVx8juqp9U2pP2dy0cS9be5PBf8Onvhos6avSSRmdsWkLWrV00nceMEcIayhIURyfUMjfUm+Qbq5FOr03ra8CmO8B00aT1k7wj7JXzqr+y3szxDEWMmRn+64IILsJ4NnH+q7F9xscxE3J5n63VsT/b0dXfhepCjebdImnb234mItLdjAs/2TrzHmZh1GrVaVX5kHeH8kkh6kkhOjuUaXecR8vGdGLITKpsYXod1a/D8LtyIa8/aVZjgNEVzV2Xc9hOy8yBO95kBjZNmk/or9Wm+V8p59rzO9wrch9mjGEviPNPdnYfYhLb3JEnrCY+LMvldCuPYPw8OYFvtOzVmleGSf2r5YvQM9szylpRLZ/azzUZ/0VAURVEURVEUpeXog4aiKIqiKIqiKC1HHzQURVEURVEURWk55+TRcN2YuFP6XN7De2wM9V5RGttsFvfoZZ11KkU5BUhFy5rGKG0x76/Pe1fPpYk2DXydfQrxhK2rTJDeWCydL9Jo1OgvrNu3P5+m/B1ssUhlsQ4pD9uyNI769ygNamce9x6vkM+mWplpy4XIo5FOpySd4T4yCft9YnFbw8+5NWIOdn+XEodwTwkM9z+7HpyfpElH4UvLGnuPxg1rPaN0vaw9d8k/FaNCnYByWpAu043oG3HeVz6Nfpb2dhwnK1ah1jaYwzcgIsLpYxpVHMtufCauVnkMzQ+O40zPOzyXcL6AKNirwHOgNadRbOW0iCiD81xYmnbqY3PlzXAs35G9bHCZnPPCymkRsT5AnSI6SGh5MM5cb+5kJM2O1Pq7LzBPBtPX2yOZzORawFpzq69EfD7G5xfQuLRk19THYzj/GNaii4jj0ziYo56cg4v7o7Vm8/FEhGf7OOf5MuxfIX+LQ3N7VK4Oh3X4NO+yT4l0+WFw5lwLUeXG4zjPLnJn1rlKxc6Tcr45fPjQ9D3R4aPoyxsax/rEKZeXiMj6NSsgXrcS/aw9WWyjyijlZyKfTJnziYmIQ3OPFz+zR2PcygdB+VHoPNracK0TETG8hrrsB6V1nd4fc+j9EfPj2Ah+pljGcz9KnoujR0fodfTQDJfte7gmeZmeofuo7q6u6X/Xa7YP+7nQXzQURVEURVEURWk5+qChKIqiKIqiKErLOSvp1OmfLmFrV/rdr0E/acX4Z0QRiXu0xWWM5RT83EM/sfL2fYH942ODJD28rV3dO/O2rHNJGSKlK/TrcZRsDOrU5DrQdn6h/flGHX9SpF/aImI8Rr2GZZoIlUcsmOMzs5r7dF+Yc3vOFnC6jErV/pn0ND5JAGLxiG0/WTolv6R0KkI20PTOLJ2y6kl93nXO/BNrdP+bQ8JjSXzwmPUmHjNq69g4/41OveajlKlWx2vFP1eflXSK+p/rz5JO1SZlfPPR/2aXU6vNnCfL2niuiGrHOaVT1h6t5y6d4mP88tIpKjN4HtIprre1VS0SJYtludVcn+GY5TOR26Q6Z9efKpVJ2cB8979qZUauMD/SKXr7eZBOsfTz+UineBz8+kinaP1wZ+pZrc5fH5zuf7Pk1NbWx3VcA6K6UpXk2OVyCeJSEu/X4i6dP28xXLYltJZ0iu47A2qvSpklaFRzHiMRg2Q+pFNcr1KZUzngeXCKCft62dIpv0H3AiHfE866/lNr/Nn0P8ecxbuOHTsmy5cvn/NgyouPo0ePyrJly85rGdr/lOdiPvqfiPZBJRrtf8pCo2uwspCcTf87qweNMAxlYGBA2tra5kzupLw4MMZIsViUJUuWzPkLzi+L9j+Fmc/+J6J9UEG0/ykLja7BykJyLv3vrB40FEVRFEVRFEVRzgU1gyuKoiiKoiiK0nL0QUNRFEVRFEVRlJajDxqKoiiKoiiKorQcfdB4Dl7+8pfLhz70oYWuhqIoyq8khw4dEsdx5Mknn1zoqiiKiIjcdtttks/nz/iez3zmM3LJJZdMx29/+9vlTW9603mtl/LCQe/9Wo8+aCjKrwm8QCpKFLqQKvPF2dzYv9D4yEc+InfeeedCV0NRfm3QBw1FURRlGmNMZGJIRXkxkMvlpLu7e6Grofya0micOWn0ryP6oCEi5XJZbr31VsnlctLf3y9f+tKX4PWxsTG59dZbpbOzUzKZjLz61a+WvXv3wnu+9rWvyfLlyyWTycgtt9wiX/7yl3/lvslRFp4wDOXP//zPZd26dZJMJmXFihXyuc99TkREPv7xj8uGDRskk8nImjVr5FOf+pQ0m5PZPW+77Tb57Gc/K0899ZQ4jiOO48htt922gGeivBB5+9vfLvfcc4989atfhX7iOI7cfvvtctlll0kymZT77rsvUjLyoQ99SF7+8pdPx2fqr0wQBPK7v/u7csEFF8iRI0fO41kqreLHP/6xXHPNNZLP56W7u1te97rXyf79+0VE5O677xbHcaRQKEy//8knnxTHceTQoUNy9913y3/9r/9VxsfHp/vaZz7zGRGZe009/UvIv//7v8vGjRslk8nIf/pP/0kqlYp84xvfkFWrVklnZ6d84AMfkGBWxu2zWatFRL7//e/L+vXrJZVKyc033yxHjx6dfm2uX4bDMJQ/+7M/k9WrV0s6nZaLL75YvvOd7zzPFlYWkrnu/er1unzkIx+RpUuXSjablSuvvFLuvvtueM99990n1157raTTaVm+fLl84AMfkPKsbOOrVq2SP/mTP5Fbb71V2tvb5d3vfvd8nNoLCn3QEJGPfvSjcs8998gPfvADueOOO+Tuu++Wxx9/fPr1t7/97fLoo4/Kv/3bv8kDDzwgxhh5zWteM32Td//998t73/te+eAHPyhPPvmkvOIVr3jOxVZRzsQf/uEfyuc//3n51Kc+JTt37pR//Md/lL6+PhERaWtrk9tuu0127twpX/3qV+VrX/uafOUrXxERkbe85S3yB3/wB3LhhRfKiRMn5MSJE/KWt7xlIU9FeQHy1a9+Va6++mp517veNd1PTmf8/cQnPiGf//znZdeuXbJ169azOt6Z+uts6vW6/OZv/qY8+eSTcu+998qKFStael7K+aFcLsvv//7vy6OPPip33nmnxGIxueWWWyQMwzk/+9KXvlT+4i/+Qtrb26f72kc+8hERmXtNFRGpVCryl3/5l/Ltb39bfvzjH8vdd98tt9xyi/zoRz+SH/3oR/K//tf/kr/7u7+Dm/yzPe7nPvc5+eY3vyn333+/FAoF+c//+T+fdZv82Z/9mXzzm9+Uv/3bv5UdO3bIhz/8Yfnt3/5tueeee876GMoLg7nu/d73vvfJAw88IN/+9rdl+/bt8pu/+Zvyqle9avrhdf/+/fKqV71K3vzmN8v27dvln/7pn+S+++6T973vfVDOF7/4Rbn44ovliSeekE996lPzeo4vCMyLnGKxaBKJhPnnf/7n6b+NjIyYdDptPvjBD5o9e/YYETH333//9OvDw8MmnU5Pf+Ytb3mLee1rXwvHfdvb3mY6Ojrm5RyUXw8mJiZMMpk0X/va187q/V/4whfMZZddNh3/8R//sbn44ovPU+2UXxeuv/5688EPfnA6/tnPfmZExHz/+9+H9/3O7/yOeeMb3wh/++AHP2iuv/56Y8zc/fXgwYNGRMy9995rbrzxRnPNNdeYQqHQylNR5pmhoSEjIubpp5+e7jdjY2PTrz/xxBNGRMzBgweNMcZ8/etft9bBs1lTv/71rxsRMfv27Zt+z3ve8x6TyWRMsVic/tvNN99s3vOe95zzcR988MHp9+zatcuIiHnooYeMMfY8Onsc1Go1k8lkzC9+8Qs4p3e84x3mrW9969k0ofICYa57v8OHDxvXdc3x48fhczfeeKP5wz/8Q2PM5HV/97vfDa/fe++9JhaLmWq1aowxZuXKleZNb3rTeT6bFzbeAj3fvGDYv3+/NBoNufLKK6f/1tXVJRs3bhQRkV27donnefB6d3e3bNy4UXbt2iUiIrt375ZbbrkFjvuSl7xE/v3f/30ezkD5dWHXrl1Sr9flxhtvjHz9n/7pn+Qv//IvZf/+/VIqlcT3fWlvb5/nWiq/rlx++eXn9P65+utp3vrWt8qyZcvkrrvuknQ6/ctUUZln9u7dK5/+9KfloYcekuHh4elfMo4cOSKZTOZ5HfNs1lQRkUwmI2vXrp2O+/r6ZNWqVZLL5eBvg4OD53Rcz/PkiiuumI4vuOACyefzsmvXLnnJS15yxrrv27dPKpWKvOIVr4C/NxoN2bZt29k2gfICYK57v6efflqCIJANGzbA5+r1+rSH56mnnpLt27fL//7f/3v6dWOMhGEoBw8elE2bNonIuc+tv2686B80FOWFwpluwh544AF529veJp/97Gfl5ptvlo6ODvn2t79taUoV5fmSzWYhjsViYoyBv82WoJztQ8NrXvMa+da3viUPPPCA3HDDDb98RZV54/Wvf72sXLlSvva1r8mSJUskDEO56KKLpNFoTN/wz+4js/vHL0s8HofYcZzIv52NjKtVlEolERH54Q9/KEuXLoXXksnkvNVDOf+USiVxXVcee+wxcV0XXjvd90ulkrznPe+RD3zgA9bnZ8tDeW59sfGi92isXbtW4vG4PPTQQ9N/Gxsbkz179oiIyKZNm8T3fXh9ZGREdu/eLZs3bxYRkY0bN8ojjzwCx+VYUeZi/fr1kk6nI7dW/MUvfiErV66UT37yk3L55ZfL+vXr5fDhw/CeRCIBxkhFieJs+0lvb6+cOHEC/jY7J8aZ+utsfu/3fk8+//nPyxve8AbVsf8KcXqd+6M/+iO58cYbZdOmTTI2Njb9em9vr4gI9BHOmRLV185mTX0+nO1xfd+XRx99dDrevXu3FAqF6W+fz8TmzZslmUzKkSNHZN26dfDfaa+T8qvBXPd+27ZtkyAIZHBw0LrWixcvFhGRSy+9VHbu3Gm9vm7dOkkkEgtyXi9EXvS/aORyOXnHO94hH/3oR6W7u1sWLVokn/zkJyUWm3wGW79+vbzxjW+Ud73rXfJ3f/d30tbWJp/4xCdk6dKl8sY3vlFERN7//vfLddddJ1/+8pfl9a9/vdx1111y++23i+M4C3lqyq8YqVRKPv7xj8vHPvYxSSQS8rKXvUyGhoZkx44dsn79ejly5Ih8+9vfliuuuEJ++MMfyve+9z34/KpVq+TgwYPy5JNPyrJly6StrU2/ZVMsVq1aJQ899JAcOnRIcrncc34jfMMNN8gXvvAF+eY3vylXX321fOtb35JnnnlmWiJypv76jne8A471/ve/X4IgkNe97nVy++23yzXXXHPez1P55ejs7JTu7m75+7//e+nv75cjR47IJz7xienXT99cf+Yzn5HPfe5zsmfPHusX1lWrVkmpVJI777xTLr74YslkMme1pj4fzva48Xhc3v/+98tf/uVfiud58r73vU+uuuqqOWVTIpMbcnzkIx+RD3/4wxKGoVxzzTUyPj4u999/v7S3t8vv/M7vPO/6K/PLXPd+GzZskLe97W1y6623ype+9CXZtm2bDA0NyZ133ilbt26V1772tfLxj39crrrqKnnf+94n73znOyWbzcrOnTvlJz/5ifzVX/3VAp/hC4gF9oi8ICgWi+a3f/u3TSaTMX19febP//zPwTA5Ojpq/st/+S+mo6PDpNNpc/PNN5s9e/bAMf7+7//eLF261KTTafOmN73J/Omf/qlZvHjxApyN8qtMEATmT//0T83KlStNPB43K1asMP/9v/93Y4wxH/3oR013d7fJ5XLmLW95i/nKV74CRstarWbe/OY3m3w+b0TEfP3rX1+Yk1Be0OzevdtcddVVJp1OT/cTIVPvaT796U+bvr4+09HRYT784Q+b973vfdNmcGPO3F9Pm8GfeOKJ6fd/6UtfMm1tbWDYVV64/OQnPzGbNm0yyWTSbN261dx9991GRMz3vvc9Y4wx9913n9myZYtJpVLm2muvNf/yL/8CZnBjjHnve99ruru7jYiYP/7jPzbGzL2mRpnIoza74A0Lzva43/3ud82aNWtMMpk0N910kzl8+PBzlsNlhGFo/uIv/sJs3LjRxONx09vba26++WZzzz33nFPbKgvPXPd+jUbDfPrTnzarVq0y8Xjc9Pf3m1tuucVs3759+hgPP/ywecUrXmFyuZzJZrNm69at5nOf+9z06ytXrjRf+cpX5vnMXlg4xpAIV2kJ73rXu+TZZ5+Ve++9d6GroiiKoiiKoijzzoteOtUqvvjFL8orXvEKyWazcvvtt8s3vvEN+Zu/+ZuFrpaiKIqiKIqiLAj6i0aL+K3f+i25++67pVgsypo1a+T973+/vPe9713oaimKoiiKoijKgqAPGoqiKIqiKIqitJwX/fa2iqIoiqIoiqK0Hn3QUBRFURRFURSl5eiDhqIoiqIoiqIoLUcfNBRFURRFURRFaTlntb1tGIYyMDAgbW1tmu1aERERY4wUi0VZsmTJdCbN84X2P4WZz/4non1QQbT/KQuNrsHKQnIu/e+sHjQGBgZk+fLlLamc8uvF0aNHZdmyZee1DO1/ynMxH/1PRPugEo32P2Wh0TVYWUjOpv+d1YNGW1ubiIjEk15Ln2bnOha/7rpuy8p+vkTtBuz7/hlj4c9wSHFUs3BbcD34GDEX3++cxTce9jGfe+djY4yYYKZvnE9Ol/H5P/q4pFJJERFZs6wP3pPw8Hy//W93WMf53o9/BnE8kYQ4m8lBnKG4rb0d4u6eHquMl730GogvueQSiPOdnRDff9/9EP+vb34d4pGRUxCnknGrzM1r1kDcTmWMjpchHh48ga8XCnjAmD0tpHN4nT0H+9Omjashfvs73gVxKpWCOB5PWGXETIAxjXc/DKf/XS6X5eZXvWpe+p/ITB/84j/cIelMVkREXBfbwPPwnGIxeyB7NAwT1NR8TB63Dh0zFjFZuDTBeFxPaleuJo97vCoiQUSZjuAxQ/pQGGIdrDKcxhmPJyLixbB9HeovfoD9PKAywwDr3fSxTBGRgOrV8Jv4uj9ZZrVSlg/+zivnvf/91n9+lyQSk+3QnsUx1d2B7bMoZ18nXps6cni++XY8XzFYRtjE6/LgrrpVxmAJO3W5FkLsh/iZZoCvB/UKxLVmFeJ6rWSVaRp47X0fj1GuYpnlMr7fUIcNDNZJRKTh1/A9TYx5WJgA2zaVwna5/MKVVhkx6vaFMtbr1FBxpvwglH17D8zrGvwHb7hRkvHJ8+ihiaMji+tlrrPbOo7J45rpbNgCcX3ZhRA3YrjmGoeuk2f3P8/BcRD6+BlX6N6I778oDh3sCw6/QUSS5EJwfXyPQ3WI0zyTpTI8l+4hReTg8cMQL1qxDuKqwXsDnzskhxHzeBDyPSDWy4Qzn6mWS/LeV192Vv3vrB40TlfIcZwFfdB4of5k98vXkzpl1EI+5zHPfIzz0XZGzLxck9NlpFJJSU/dsGYzaXgPP2gk4vYNOdeVf+6L0SzPD7aeh8MlHlFGKoX1ymazEOdyOBmn0vh+LtOuo/3AGKd68bnHPYznKsNa7SI+49KDBpfJ552m8/xlHzROM19zwuly0pmspKceQPmhgM8p6lp5MRyn9oPGma/NWT1oOL+uDxr4xYBj+AseLIMfNIKzetCgBZ8fNJp4YvPd/xKJhCSmviBJJrE9UhSnU1EPGng+mTTd8KSpzxo8ZkhzDRU5WccGvqdB49bhDhULKaTrSj0w8O1514R8K4OxSzduPNfzrWPUd2w8FkMem9zc1Jf48/G4ffvFU683x/wwWe78rcHJuCepqbk+TRNHJoHXJRPROQx94eRkMhC7/IWW9aBBfcOz15E4PWgEdJPvvQAeNBLP40Ejk8E1NUtt5czzg8aZjsOoGVxRFEVRFEVRlJZzVr9onC/4W60X6i8WrcY+b/7W2m6HudrK/gbm3Ntyzl9BZhViRCS0vgc6v2xc3jP9S0Y+g99aNAP8BmDf/n3W50P+poL+0Gzit33lCv68zu2RTNjfphw4sBfirq48xO3t+C1EjuQP5TLKAsqVIsRh0/42L1ZAKdQVG5ZCfDSB9e5O4+uDHVinQ6dGrDJCat9YAus9NDIGcXFiHOL2jjzEqaTddh59U8TfAI6OT0z/25InzhNtKVcy6clvFbl+Hn3ZyPJFEftXsbl+sbJ/4Zj7l8oYtaNLX5PG+GtSmn84Tgi2tWt9JS3C8w3/+MS/cPg89uibcydiafL4F0eWetKvar5gXCdVkFe3z4MlNAmS+VSm5DLxJs4N88X129KSSU+2lR/gLzJ+vQBxs2bXcXQM55MDh/A96S58/6aN/RB3ZVGmedWF9rfWJ0ewoZ/ah2WcGCOJG10Y18VjJtMot2mKLdUI4zhvOiS3khjJZ2LYDkFtFN9ex9dFRBzqCyaYQ25F/bNCKp9Hdg5aZYyP4tzb3oEXZMmSmbk78H0Rsde580qxLhKfPO9KA0/IK+N1HDxmryPl+naIN7n4C3/3UpROjdM3/XVSLvgRc6xLYzgZp1+vWErF9z10PEfoW/3A/iU06dAvfR6rI3BOHR8agvj48QMQX7J1k1XGsl6URCc9+uWafi1vGO6feDw/4ldjXht8+pXEmfWrsBe3ZWvPhf6ioSiKoiiKoihKy9EHDUVRFEVRFEVRWo4+aCiKoiiKoiiK0nLOyaMRi8WmNcHnshVqqwjDM+/i8EJhTq+J5f7HOKot7T+xZ+PMdXg+/herHgvsocm3paY9DQnabWLXM4cw3n/U+rzrkj6etOghaxrJl1Ct4paJw8OosxQRefKJxyCuVVEr3J7DnSP4wqYzqE9unkTda5yNJiKSqRUg7i3juXsNPEYihjtA+e0dEA9VbP9DvYLnUaujPnNkFD0aB/bshHjzJtKcRuxs1SDNr+3DiD3Hv+eP9nRcsulJ3epcO0JFjhY+bR6ndFrs+zibXafmGvvhHHM3T6u8y1QQYdGwq0Flkq/DsB+HWyuw+yBr5BvVAsQDA/shznXiFtjpHGqcmxXU5YuIjAweg7g0PgzxoQMHRUSkXj97fXIr2bC+a3oOLNEWrUM0V+wcwK2xRUT2HsQ5K077LS/JYZsNDOIWrn7nBMQ9bbhrkIjIihSu05kEzjf7B/DaPrYL/RBjY+i36OzCebszh/6wKEpN3K2o4WOcoB3MhPwtbhOvu4jI2KlDEA8P4XajMdpS14R4PYyPfbxejejjNJDqdfQDpFIz68dC+NTW3vRSyaQn2z8cxzm/SWtEMGF7hJJj2H+8JPaVeIJ8B+yPoOPxPCIikqSppFnD6zI2hNd2af8SiPmQnuB1zLdjfxYRObwfPRZF8oFUS1iHE0cPQdyewnFYmbD7XzaN9w7FAnp8fNpd0qMdvhLkq/Qj7p+b1s0oLkCz+6fHi9MZeGHeqSuKoiiKoiiK8iuNPmgoiqIoiqIoitJy9EFDURRFURRFUZSW07I8GnZeh/nNsTBfnI/z4mNGZZz2SH/HGRuDAOOQ9/T+NcARd3p/fY+0xT/5+f0Ql2q0ab5MZtWdTUj7bTebpAelSx2jvbDdiHwnAWUbPj6Amu/HHkMPxybyLizuR430/n27sUzXFsh3GdRRD+7HXB5jtE99zeuGuNmOeTViEflRmgHpjckrMkJ74+/ctQfi178O2yXm2Tprv4HnUaliPDuXR+Dja/NFKuFKaiqd9/OxLBn+DOfe4Oz1lveKvFmRZbB3hPJi0IditFc992HDuTwSdu6EZhM/M0767XIZdfhLl6Iu2qX5yzF2P3d81IDvfvZRiHfueAji1etxbIWC4//QAeyjIiJHDmNegpjBfj8yPKmdXqg8Ln6tKv7UfvmcRyTfgTkJNm9cYX2+twu9CuPjOI6COPaV4UFs88IozmfFRZR4Q0SWL8Yylq7Edo8ncezvP4xzx6FjxyHOUo6MZcsxt4eISIpyCiRTWIdj4wUsYwjPi1ItyKIue37q71gO8cl2/NDwKfTGDQ+dhNiN4e1WvYG6fRE7b45LY3PP7mem/82e1fnAW7lYvKlcVskQr32S7lEWhfb32F4NvU2JvmUQF6nZQ1qT2R0RlO02TKbwXUET+3izjD6RlCzG95M/LGlwbqsMYY4oEZGEwc8UCuj/atIanKZbvKNHcS5atXSRVUaRfJCZPHrOShNYZpoyh+e7e/GArj2PN9jfR16TYNZa4sbOvv/pLxqKoiiKoiiKorQcfdBQFEVRFEVRFKXl6IOGoiiKoiiKoigtRx80FEVRFEVRFEVpOedmBnecGQckGQpDMoc+H8s0G5yt4u1sLfZ7OLbMlWTodTghCdeJj2c/mxkr0RuZiqltYlTvTAYdUJmsbURLpfFv+S40YhVLaJgbGsGEL40GGprCIKrt8NwMJwWE2IhIROau84gJzXRblspo8Np3ZADiqGSObLoPyAzuGE4yRgZDn021di9f2otGa+PhEBs4iWbKDevXQ7x182aIH3ngQYh7XNvk3kZGNFPDay0NfH14Ak1lwwZNY1FG3EYNDZuGXMw1Soq0/ZmnIT5y5AjEPYtsQ6dHJjyX23eWGX+hknU2mr7Em83IOrCRM6qOrntmo7aVBHCO+jiuXUbooNPQ4dmYjPQH9mJyxaET2EdPDuJcsmgJGrlFRC7Zdgm+J4d1iLWhQbOvF+NB2kygGmGUPXUcNzl48tG7ID5+5BmIm1U041Zq2L8OHT5klTFWGIE4pLGVSU8arn1/fue+0xQLRQmn5vI2WieSnOwxwqzZpA0XBsfQ2DpYQKNsOoPzV5KuqxunuUZEkmk0/A6MYht2JDFB6LYtaHxt0HpZpetWrtqJFnOduB5etB7jC2nDjHseofWxjubwjUt6rDLa23BuH12B4/3UECYvvP9R7CMTZFyuNey5PJ/FpGxZujc4fmqmfy6EGdyt+uI6k9fDS+D5P/kwbXRywRbr8wHNA6UsGpJNEvtbmgzLGUqUWaVNJkREJiYKEBcn8D2lUbz2Tz+G62G9RubxIr6eTthzbkDzwelNI06zaBH28b37cM6tlDGRJm/6ISLS3YX97yHaWCaI0+YQeezDNUqg6KZx8wgRkc5eXJc76T3hrPUmGT/7NVh/0VAURVEURVEUpeXog4aiKIqiKIqiKC1HHzQURVEURVEURWk55+TR8M1za4Yt+8TzqAwnmppLoBydO4/8EGS6cOnZiqVwMSo0CNh/YWtzE5TAqou0dJkk6hITMdQ2LutHLV3CztcnyRQmPWqQD2QnaYsTdGXjcdR61mp24/nNMz93Ggln/duIiK0xPZ94niOeN3l9fnLvI/DansPo0fBILy8i4pMHgBP2uQ42WizE2HXxwnR2oCZXRGQ1a9MTeO2rBjWm5QrqP9evXwNxpg01km2+nSyoLYX9z/Owb1AoR4dQs3qkfgLirk7svyIiOdKDD4/hMThB5P6DByF+4EH0mlz/GzdZZcRi2CdzlHjJzLo+YWJhElIaiU37UwzNFYY9To7dB/m7nbm+6XEoY1+M56+IIzgufsaja/Mf//YDiP/9O/8IsWmilvzECRxb111/nVXmFZsw8dbGjRdCnM7g/BWQH8oE2L8e3b3dKuOun/4bxHv3PAlxvTwIseeg7r4RkEergb42EZEm/S1ge8vUlMc+vPmi3qyLO2WL8Bzyj2RwHmhvt5f3zRtRK34RXbeJCWyzsXFsjwIlXHM8u4zxMrbNRBGP0cxin/XS6PPYsBJ9CuUavr9QxjlTRCQmpMOvn4J4cS8e8+VXb8AD0LLelrKvby6H830sxLYMqU+sW7ka4sERrNPwMHqIRCY9YLNhn83KxTPrQdMP5Ed3221xPkm5CUm5k2PZFaxrvg29N/09mHxWRGSkiv3HCPkEHLpXojXZc9A/sf0JvA8QETl6HOerHrofM+RtGRvCeyeX5vWE4PsXdWGiPBER10qyTInvYpyZleZt8rv09ts+uAs3bIX4ocefgHh0FOe/sSH0W8VWYxn7D6DHQ0Rk68XbIF6+YiXEJ0/NlFGpoOfjTOgvGoqiKIqiKIqitBx90FAURVEURVEUpeXog4aiKIqiKIqiKC3n3DwaTX8mLwV5HzhfRVS+CQvLJkD7vzusRybTRkQRrJPklACGPhNwDgIqoq0NcwysW7vWKnPLVtTOrVmN2sx8Ox7DDdDbUCvgnsv9+XarDCF/wSOPPo7HGEC95ynaX79Ae3bHIvbgLpOW2zeo6QtnXWNjQpH62Wv0WsGze49KZiqfyP/+1x/DaxNVPL+kZ+vj67QHt+/jZzgPgomTh4P2AN/QgbGIyKWL8VqH1KcrIV6XoIyei/41mFdjSf9iiCf223vIV3zK9+FhJx6pkCbVRa1xKoPnwTkvREQ6O2k/bfa3uDiVlIqo83/iySchfvmNtkfDxPAYVdqb3Jl1ferh83GB/fLExJn2cfF8xDl4OBYRifF7LF8HeRc4zwaNSZcnNBFxXLzeR/fgnu0//PY3ID5+cA/EmRzq2d/5zv8K8cbVq6wy/+Ubt0FcfeubIb7yupfhBxp4/drJVxJvoL5YRGRi5DDEjqC23yE999BoAeIa5ZCo1myPWbOObRcENH5Lkx4Gzhs1X/hBQ04Pi1qD8rjQuGctuohYndLz8Bh9fTh/rViG/sFsDl+vVW3P4kiR1hoX37NjB3rCymXyJTg4T/d3YX/s7bA18r2L8G+Do6i7P2Vwrervw3wB5RJ6U4bH7P4Xj+E8uWwxtk2GfJQSz0N48iS2w6l2O1dMQL6HJNpuxMzyUdbqTfnR3dYhzisD9bKkp66nb7DNSpRz5VjT9kB1xvE69cSwDUshtjHPd14c40y7vQZnhvE6dNB8Vqtguy+m3FcZ8gbmkugfy2Vsb2Yyhe9pa89D7MaxbXhed+h+JYy6uSXPX/+SpRDHc1hGs4jjv1bE65X1bDPw8b24Fhx5dgfEZta9Ro3yjZwJ/UVDURRFURRFUZSWow8aiqIoiqIoiqK0HH3QUBRFURRFURSl5ZyTR8NxPMuLMetViKJyXFiftDwY3hljiwidLG9PzJ4NIR8C51tYuXIFxFdddRXEmzdvtspcsQI/k82iJjCTQi1cexIreWLPsxA7RVvb2NuRh7jjiisgvnQT7lt/zzO7If7eXfdA7PuogxWJ8NVYez/P0j6a+d9H/l/v+LnEp7SOuw7hnuS5LO3HHZHJJSgXrb+dETr9zixqN7vdCJ/LAOrI20gfuiiD/pvK6HF8/6ZNEG+9GP0/33nmaavMXwzgeXV5eO5lH0+kSnrSPGk125Yvt8qokJek3kB9fGcetbdBiFrjhx/BPbv37tpllbH10ssg5lwxYTij/Q7C+c3hMk3MF4lNlm0NF/ZTuPb3ODHS2cbIV0AWHvCliIg4NO4cNpWJSIx8G7+452cQnzp2COJ8G2qO3/zW34L4xptugPi2//l3Vpn3//znEN/wxtdgPem8ef6pl1FD35EjvbuIxCmnADdvg3wfwwXss4kUvs7+BBGReAL/1iyRr2PK6xZGJ3E674xXqtKYMh4ayunUS+thKm23oRunfCa0xtbofL0OnCsSpFf3I/JKhT7ODcbH67bvCPon1q/phfiCNZhLKEt5qryE7b/LpnEcjBVQ+98kv0qC2qGWwTnweMT66Bpsq/EC9tkdw5i/4cgQ9r8u0tC3ZcmAISIBeRIScZoDUzPHiMXn/3vikbERSdUm671z5zPwWiqBa93+ZzGvg4jIZVdcA/Glm3HdTjjYn3iM8pjvW4ZeGxGRGnkSU+Qrqjbw9UwSr30yxL6UzON5JSLGVXsMr2VQwrhJ5rxMCu8DUjTPH9yx1ypjcBfeW4wNHIXYhNhnwwD7W8NHj0bGtdeOBvneYmw7mpV4LuAkQ2dAf9FQFEVRFEVRFKXl6IOGoiiKoiiKoigtRx80FEVRFEVRFEVpOefk0XDd+LRHIyTNoyHNapSXg//Cut2QdfWk1+N9641ja8S4jFiMcgzQXtcXbcK8BVdd+RKI2ZPR24t6UhE710Yuh7pDL0777TdRK8di73LZzk+RJr+ES7rVVB51hplOzL/QsxjPc/wAejhERJoh6vN4T2/ISbIAHo2Hn352WgfP+ne+LsWi7cfgPstGohj12e421Gau7kJdZW0ctcYiIvsnsNw1i3CP7uwK2hd8GN9fOYV7zF937fUQ3/6jO60yHx7DHCpZ0oN20N7jcdp6vDuLGv14Z5dVxoE9YxA3yaMRj2P/W7lsJcQF2tf+n//lO1YZfZQzJN+DOmtn1nk5EWN/Pog5RmJTZfPcEnPIQxDxeY88GTGa8wKaE21j29zelLCJ1+LIoUMQx0n3vOGCdRBv3Ixzxf/8m7+C+L7/sPtgLoNjZdd21G9vvvAiiGs0Tg7sR5/a0iU4bkREOkhr/ejD6NMaHEZvW72JfTSTw/POd6LfQEQkIF8QTbOSzU22bRgaGSrg/DgfdKTS0/kayhX0UwQ+5SJxbA+AkP7cc7H/NclyMThSwD/QOnTqhL1W3fPoIfwDrRWZFF2HdqxTs4l93E/i67UaXlcRkXGa77s6sf8kQ/KpUS6FXAbvC1avxLlHRMSQf6Iwjpr4g0fRk1Fu4Drf14U+tmybfX2ScRxHWfJ3NsOZY1aqdjucb3Y8tkviick6lSYw14gbYpuuW42+URGRg0dxfdtMeczSlNohTn0nThNie9P+rrzTp3wSIzgvZOrY590mjqMEzdxFygdSTdplJnLY3/wJbAtD62NnAucy4+DrI8dwTRcRGaX5zCHPmqGxzOeRJj+f49v3cHXKxeOS7212Shz3HKY//UVDURRFURRFUZSWow8aiqIoiqIoiqK0HH3QUBRFURRFURSl5ZyTR2M27MF47vwas98zRyzkyWAdNmnq2RciYmv3uYyVK5dBfNVVV0K8ceNGiJcuw5wCvb22dtOjMj3S402UUD/arKEG1cTR01ETe5/mcdLf1mif7xHSrZoc1nPdReg98V370g8NHaW/oAgv4c1oSsMwkBMHh6xjnE/KdV+cKY9GMoltxDlA6g3UXU5yZl2/R/kkcin0LrikaRwdQd+CiEhYRT1n0mA94jFq0/Y8xCePo4Z16+vxur2CchqIiPzs3nuxXrSfuyFd9apu3Hu8YwnuW3/kyB6rjBL5htjPwp6NgMTePd3YH8cKBauMZ3fsgPi6G/Fc07NypcQ4icV84cv0sHBIz89erEREf3PJB+WSztYP0DfQpL3KOT+JETuPgRvDvyXYSyJYZo72hb/nZ+jB+Lf/+38hzoa2+ySo43n9z7/6G4g9ylvwptdino2161dBnE7a60lnewfEx48O42faUQPvuDh+gwa1i5e3yki14RzQ3Y3vyaQn69Bo+nLoOOYmmg8WtbdLNjM5D8cX4ZgKDOUgiNlzvKGN8WsN7E8pyicR1imPSB3XnSd27bfKiNM4WLMS55stG9FPZwx6GYo015Rpbas0bG9CvYb1rDRHIW5vwzW2VCZ/QZ3nE7vtXA89FX2L8xBfmURf2u59ByGu1fG8Jsr2/NDXQ7p68tcFjZl6BgswBzpumzjuZB9avw7vjZ548BGI2zZxbiuRsIx9tL2B7ZxIYP+klFCSLOEf0kfQFyMiktiD9zGL+xZBXKpiHy5Svp1GlXLJtON1b+uz7wGHC3gvxNfm5CDWyad5PJfDcceeRxERQ/6JwMN5vE73ax55NLi3xQO7/3iUyCndxE/NtrnGgigXYjT6i4aiKIqiKIqiKC1HHzQURVEURVEURWk5+qChKIqiKIqiKErL0QcNRVEURVEURVFazjmZwYOw+Zym77mt4JaX2/pQjA8SsPmb3h+zn5PCAA0x7W2YZO2iLWj23rTlAoj7+1dD3NGFRqJ4xm6yMEAz29h4AeKRAiZvOXAYDb+DR9C4NnAIE1GJiASUDKdvGSY3S7ZjwpiTVWyHgQk0OHX3oyleRGTNqj6IOzLYvkuXzLRFvV6Xr37FNg2fV4LGdMIpE8Osc9w3gsA2yfLmAS6ZpD0Pr+04mb+fOolJ58KxglVGr4NG/wlKqnXoJBrPuiihX0/PWojfsHwFxDf8xm9YZXbmMcHeE089BvHoECb/YUPxrr07IfYn7ESEbhoTDCXr2L6cZGuihGbL9ja6XnU728/ACRwXjQqOK2eWua1WpqSX80Q8qEs8mDTqJVwyg1MbBJQUTESk2URDaBDiZxJtaJxN53D+EdogwxE76VIige/ZSKbNR3+Gbd+gjRNiNUpkR8bGZoTJ3YT4t4GTg1jmo9gn3/m7/xXiVCfOR1HJMJctWQrxRZs2QBzLovk0CNFY6pNhvX9J3iojTWboTAaP2Z6bXE/q9flPliYi4scm/xOxr30izuZPe31skPl7dJTmSUqSK7TGnhjGtcqNMK1euHIJxJkMbXjg44YZhhJdGocM6ik8rxTNRSIi1TTOL6UJ3KhjlJLr5XK4UYBP9w0ci4g0yBjrl2kzkASex9o1uEY3yMReqdvJN2Ocr5OSsAWzbpqCs7rrai1dvYskkZw0RzfruMnNJkr8mYjI6LZsCd5fcSLFkDY04Ontzu/ixhR7f/pzqwx/DI3Z7lZMupzvxzl14MQRiJu04UF7iNex/8ItVpnlJJ7HWAOPsaQDN7I4dRI3bInRGDFJ22htGrzmYvs6CfxMiZK7hgkcy0kTYeaO43sanMBv1hioRmwK8lzoLxqKoiiKoiiKorQcfdBQFEVRFEVRFKXl6IOGoiiKoiiKoigt5xwT9j13wrMzp0KbhP0dYYias3xnHuLVq1HPd+jwIYhHhm0dLxs9Fi9G38G2bdsgXkFltOcwmVCddZQV1N6JiKVrDSjhXpGSHj36zAGID+1FbXpQt8tw46jvdChnTJIeGfcdRV3+eBl1sW4D9ZUiIsvWo7Z203rUdrfnZs6rWo1KiHd+CcJwug/Fqcf5Pl4nz7X1g5z/0aX3hCHqJMMaXocCHaDQjPAZ+Pi3JQ0sI0PHCBoFiF+VIE14ByYhu+rqq6wycznULOc7MK4Oo2Z1aBj7xiNPPg6x69kJI10X/xantnPoelSoDwcBXp900p56KtSnnnjyGYhXrpnxr5Qr6HWYL8aHd0mzMqnvdsib1awWIJ4YjfBaNTHJXL2B47J32SUQr9mI17tK3oBK2R7HvsE5MN9O187DyeLhhx6F2GtDPTH3cj+wteUJ8nGwfW77DryWP7vrLohvfO2NEEdI5KW3E71I2y65EOLH92LyuFIF2yadRO/JeNFOOOomshAPHcG5ecOGSY9fPaIN5oOR8TGpNiavZyqJvoQsJV5s1qNWZewbxQk8j6FhbLNR8joMTWCff+0rrrZK4HEwOnYMyxxHX4dDiceSGUyQlqf7hvZ2e34S0pInk9iHx0o4X5TIq+JRHXzP9vhVq6SjJw9WNoV16FuMdRgZw7Hb3o2vi4hMkJekWKVEqbM09KY5/z6h1Wv7JZWeHEcTg3hd8ytwrZKG7R/r6sVzDuh+zaFLWypgf7yLkon6B7EOIiIdKezTR4cPQ7x4C/oevVEs9PA+TK5XreM4u/87/2iVOUS+onQXtkV/H95bhQFeu54Uzk0revHeS0RkEc1Nno/je8/u3RA3fOw7CZov8uQPFREZdrHf18gnnZiVcLHq2mPkudBfNBRFURRFURRFaTn6oKEoiqIoiqIoSsvRBw1FURRFURRFUVrOOXo0zh7OWSASnfdiNu201/DLrrkG4g0bcN/0XzzwgHWMOO3rfQl5MpavWEVlou63XkWN5LM7McfA4iX4fhGRjm7cl/nkMGrNH3gM800MjqM+r0b7GWfbbe3mhgtQsxej8zx0FPc3L1GegcV96D3JJXFvaBGRK6+9EuNLL8IyzUy9SyXUls8LjjP5n9j+njp5AmKu3bUd0pGzJ8P38bpUm/h+N4bHzKRwL3YRkTod4yhpbLOkj++iPC83vurVEHsJLHPt2jVWmckEappXLcOcBPk0HqMwit6mux/GHAc/ufOnVhnHKMdFOo2a0pB8Ab6P12esgPlD/KzddqUytlXo4Lg4Nis3Q7W6MHk0Hrnv3ySZmBx7QR012r1d6I1xAttrVSri/unpNrw2zSb2yaBWptexXUdHbZ9aYFBzHJLPbPkynK+e3oVlFOlaZbOo7Y1nbI28X8V+X6KcA3v2o3/i3vtx//ttL7kEX7/L7oPlkUMQ1xqoz/ZczN3R00v7xsexzyRTto+rvQPrnUVZtFTrk3VoNM5en9xKUq4n6am5rUZ+wWaN8k/E7evkxfH8+pdg/zsxjH36ngd2QbxkMfadwgDOCyIi2S7sw66Lc0OM9vN3YljvGvkpjo3heTpewSqzuxfn0Z5F6HVrE1wvgwDP2yG9eVsGjyciYhxsm9DHdb6znebEkPpbAq9HKm6vUalObKsapzWZ9ZlkYv6/J+7IxSSdmRw3+QzeU3S34/wXRniE+lfh2jRBXtFO8gIawTaeoBwsbsbOJVKMY6Nl01iPfQXssyeamPPpcAV9dCMTuL5W4na7HziA81vsFPaF4RE8Zv9S9A775ENq23qpVcbSNmzvxmAB4sWCk9Vy8sj4I9h/V/bbfTxzGfreqpSbx521lJzLPaD+oqEoiqIoiqIoSsvRBw1FURRFURRFUVqOPmgoiqIoiqIoitJyzsmj4TiOlQvjNFGejLnew56NiQnUyhUKBYhvuBH3Wr/6pS+1yggC0ueRyDaZQr1xQPsE12hv7KCJOsu4Z+t6aWt7ufv+7RA/9CTub+wb1KQaqsOyXkqSISKpHO3vPoo66sFhjMukd/cb2LbXXXedVUZXP+YU2XcU9d/lwsy+81Vqp/kgDIPp/heQR4P7VjKJukoREdfD7h6EqF33Sf/uUptXK9gXcmnsSyIiS5asgvjEEOpBRwvopbl842aIr7jsCjwgj5mI/rd8Bfp3lq9cCnFIOS/WkFfl0hteDvGGFfYe3l/56lcg3jeO++vnMqjPrZP2lv0x5Yrtsdi+HXMtXHgR+at6Zvb99jgpyjyRbhYl5Uz2o7qP2vFEiLrcFOVtEBHJJlGjzClLONdDpon9JSQPkOfZ+URSadTeVurYr6956RaIt1x+CcR33P0gxMUyzi1rF+etMk+dwLli4jjON/EMenKODuBe9d/4/98G8d0/xf3yRUQuuhDHY7YN82BsXofzaoz6SMzFmD1XIiIB7T3vG9Q516d0505jYfpfGNQkCCbrVKriHByLYWeqRtTx8EAB4v2H8dru3o9a8oMDGJeLqMu+J7DzuKzYiPpzQ74QXi9HSes9NozXYEU+D3E6Yg7cHWCuhE3r8DMh5dlIkb8uT/6qMCJNlFOhdZvyYyWy6AtJprGesSTlUPLte6kaHXOsyO07c8xKdf7zaDz58GOSSE72s/4leJ8SW0b5wybsOb4sByE+fgr7V2EY18s85X4oVnCe6enNW2WEZZyXy3WsR5FyD8WTWO/ly3GOrtO4umj1ertMmv8C8kdk6VK1lbCOi1I4t9WP2jmYnhrB/GtBBe9fQvKNLS6S9+4AzrkDxp7/rr3iJRA3KL9HOKtPZxz0PZ0J/UVDURRFURRFUZSWow8aiqIoiqIoiqK0HH3QUBRFURRFURSl5Zy3PBpRzOXRKJEecftTT0G8fj1q4y6++GKrjHSEbn42Hmugs6jNdA3WadVK1Ov10z7iIiJHhlCAd/h4AeJ4gvYr9vE8E3HUai5fZue4CJr4mdER1CfzHt19q9BvEU+gvjSZpg3iReSJZ9BLUqAyju6d2VPdb86/PtSYUERO59HA8/F91Ctmk/b5cX9rUK4Hl15vUv4Bz+D7gxLqm0VEFm3CPumSnrhaRQ3u5s2ol0+lKQcCacRjjq1PjrlY74A/Q7r+kM6Tc2Dc8IqbrDIeeuB+iJ/953+B2E/h9QgDjD3yiaRStn+hMI7t+RDlWth8wdun/x2L0JfOB0t6XEknJ8+l6aMPKBGnXC4x7D8iInz5ON1LIobj3DRRZ+sE1CfDCK9UiO1Yq9Le/FWs9/U3vBLivYdQC/zQg6jtvfB6zGckItKRxj619wSeR0cW58A9O/dCvPvpZyE21H9ERGoV1AQv7UNNvEeNa5rYVg6NC/ZkiYiwraEZ4GeqUzkf6rGF8WhUA1+cYLKtOR9FMoF1HRix/Tvf/B76Bw8cQW15mvIzhYJ9xwTop/jZU3b/S+zA/sI5AvyAvt90cBBkyetQ6se54sKV3cLs2F/AeC/2v0Wd6MnoyWGZyxbhepHK2vPTfspV1UP5GdrX49x+6dUbIR5LYDucGrc9DE4M6zk2Sr7V8Zn2r9Xs+eV8c/zAsMSncnls2Xw5vOZ5mOfBF7tvfPd7t0NcGUVPRnMQ4/5OynNWLkA80rTniZ4yXodYhvKdCM5/9Qn0G/YGlO+kB8+rq2Tf+/yXdegnrAziHFykef/USbyuix0sM3kc6yQiks9jW1SyeNBTdD8yksD1aHyCPBUdtseimMA+3RDK6+TPvF4Mzj6XkP6ioSiKoiiKoihKy9EHDUVRFEVRFEVRWo4+aCiKoiiKoiiK0nJalkfjbD+PoB7MkFZ8717U8e7csQPirVu3WmWwDt8lbXiGciOks+jpKE8UID41iD6Fzt4lVpl7D5yE+OQoHqNB+2XHaX/3tg7UpAaBrb1kOVypgPrbZgP1dhNURt8S9JYcPo7aXBGRBnkSOtuwbWqzBMx+c/41yrM9Pob01iHl1eC8DSJ23+BUDIb0yE3yfbSlUT/b2237dWr0mSrt4d3RiVr1NatWQszn4TmoJ43KVxPSqXox7PMnD+6HuEHa9WUbMJdHphc1qSIi/+nW34H4uz++A2LuDjzu4ux/idDg8yUbH8M91g/tn/EOVGsRG93PAxOjR6WZmDy3VIr9YHitnJjdB3mvcxPDfmzIb+NT7ocEeX7icfy8iEjoojbaI4/Yrmcw58DyNegTWtKXh3jFMpwz163G+UpEJJfEet/9CJZRLqAmuTqC1zbfhXVsz6F3TkSkXMKxlKL97bPUlg5p/5vkK2tGXJ84tb+hPfbjzqTuuSahiKBfYT7w3KR47mSdGgGeX91g31i8mLyBInLVpejdm6BcB3Xa/7/RwLlivIb9l/ujiEisSW1ouM/i6/l2HEdt7eRTqOJc8eg+XJNFRMp1mrvJBzLYwPNcGmDblOm6Vwdsf0uxhGOx3IZlVp8ZgHjxihUQr70U71diSdvjN1FBb8n6GLZNpTpzPSoV1ODPBy+59GXT/rq9z6IXZ92mDojHx2yPRkA5U16yeg3Ey9deAPGep/Ger0Tey5pr9z8vIK9WGfvPs48+AfGxY8ch5nV963K8jjJq547JUP9zKM9Y6OC46qP7lwq15RPH7T6+9hL0f+Yuw7baPYA+t4HBIxB3ZHAuW5aw19DNKfKthpQrata9ReicvUdIf9FQFEVRFEVRFKXl6IOGoiiKoiiKoigtRx80FEVRFEVRFEVpOQuzGf0UrKM3tGfvsmWYw+Kyy3Hf5q4u3FdYRKTZPLNuLAyxjHoddWqsqX92L+4pX6jYmsD7HtkDcamCOsR8vgfiOOnZu7s7IY559v7G1Rpq5bIZ1Jhu3IBax/Eansfew6jXq1VtjfziXtQm9uaxjMwsTbrvzv8zahgG0z6fMCRNLl1337fPL2b5NvAYIfkfXPIR1Ououzw2hJpcEZEC59YgHXh7BjWmJ/fshDigfcHjKXPG10VEmnXsG0888hjEd919L8SjE6gxfdXNmDfjFTffYJVxAfmhrr7mZRA//sTTEK9cjt6TUrEA8fi4vU94gepVruO5Hjs0o/uv1+dfnywiIo2ZXC4e5TGIUw4eV+y5wqU8BQ5pd7mLcr6YoEmejgiPRsCfCbAPnTg+CPHoYAHiZZQryFyC82wqhe8XEekgO0B7G5774BiOz6X9/RA3mjgPl0u2Rn7DRpz/e3rQ91EfPgRxSLkufPIG+GL7nZqknW42KF/P1LX35fl7FX8ZiuWa+FO5PbiJeHd/P7Q9JCuXor/mVS/HnCg/+fk+iCeKWAj7K/zAbkNOMRLn3DHUdOwp45i9To0If2AihgdNeZwPBCmQbr/aJK9K3c6V0KQ+OjSBx0iTn6r0749A/N5VmGsh0bncKsOp7oK4M49epc6OmbYoleffpxaYugRTa++Op3GdGRw6BrGJuEXozZIvdwRzk6ylfBSp5fj+3Y9iPqeKa+dyqIbYf9wGrhXVKs4bXg69C4vW4NpVE1pz7RRdctcuXP9S3Eepzyd8bJwyeaMmXDvHSngQ7zO7L8L7yvFGAeIaleH7WKfUML5fRMQr4pzRTs1ryjPjolk+e4+a/qKhKIqiKIqiKErL0QcNRVEURVEURVFajj5oKIqiKIqiKIrScvRBQ1EURVEURVGUlvO8zeDPJ3Eff4YPkUpicppLL7sM4osvxoQlpxPHzIZNwJykbXgIE0U98TSaeNJJPGYyhcmDHnjgAavMw0fR2Nqs4okVAzQjZSi5VamEZTq2h1SGqN41MqvVycxWoGRn42NouuIkSiIiw0OnIF67HBO39fXNmNYb9fk3os32ageUwTA0FIe2SYw7HOe+Y9NszcG+lKUm8yu2YXWkRsnSXDQluj7Wq4P6QjKNYyAgI1utYrf7D777fYjvvv9BiLM5NI2l0ujc/dfvfA/iDesxqZeIyOp16yH+/T/4fYj/3z/5M4j3PIvGtSZtstDVhsmdRETi5IQeoaRuMW/m+sWChTHj+s2mNGXyGjYbOAa5RlFzJOeIcyjJXCjUj8nG6iVxyuZEiCIiIRnGSxXcoCCewD7VkcfP5/swKenQMJlcazhPiIjEKJHW8lV4fW98zY0Qv/1tt0L84AO/gPhv/ubvrTIWr1wFcWcv9o+Dp9DILGS0b3DbRnzNRv5JqVLy1NNJZdk0Pl+MTfhSbUzWoVyhZI5pnKCGhu2EaUMjeD7tObxOV1+yEeKndmAisWPD2OacdHfyT9SnyUvLJn2eq6u00YPnYp/3IpKxerQ5iUNlJGic8CYLTdpbwnXs69sMKRkrJS8MaKOHh3ZiIrgVdz0F8Stf+1KrDOqikqIkscGsRIRxb/7nwMLEgCSnklgGBs3AJwdxPeSNdURE2lK48Y3XjptClCih7QUbsT9OPH4fxOWqXUa+juPAT3DiTlxDkxls4zj1nQm6t0pR4jsREbcX6108hfdb3Xk872YF1w5D6/6aNfZGAX4R61Gh+48qmbvD4zjvOw72z2rBvpf4h8/+OcSxCpYZztocoh6x4c5zob9oKIqiKIqiKIrScvRBQ1EURVEURVGUlqMPGoqiKIqiKIqitJxz8mg4jvOc3gzDgvcIXBe1c5w8z4tjdXxKwjYyMgJxd3e3VUY8gfo5j8qcGDgB8f49qOtdsQKTtYiDdRoaxjqIiHik6cslsI02bUTN84WbLoD43gcx8c2z+zBJoIhIzMPzWtqPSbXa2lHjN1LAZ8hMKonvb8tbZYTU3tVyAeLlfTM67Hotwkhy3nnuPhaQXtD37cSNnkeJoCzPBh6/Tp4NU8My3IikhVxDh/7S04560CuvQ+06Jw1sUKLGp59+xirzX7//bxDHU6iX7+hAr81jD/8c4p2UbOiG38BkfCIiK1ejb2PlUtSQdrSj1rtO+txMFuuUytpZj3LkPxg4gfrwvbOSZ86VmPN8UayMSjM+2W+qTUz8FKf5Kx63tbyJBCWTorkjxq9TbEifHhh7PnYpU1YQYiLENevxmKkMei4yWZwreheh/jiZsxM1xV30ma1ch5rkzZegx+eSa66AeHAQ6xCVtDRG/rkqja066/JpLMVoPDuh3XbJGF7DkDxWzSltv7dAX9Fl2lOSTk32qzInBaNEd+tWYRJXEZHVK/Gc06Rfj2/GE7vmyksgvv3n6P+65xf2fOTTuh7jhH2G1mhqy1oN9esxF8d6LmX3DYccUp7x6HVer8iv4+M86/u2xy8kIwff8hgaiyuX9EE8eALvPY5QslYRkfY06uZdwXONJ2bGZuwM6+H5oi2fltRU/7vqZTiGM22YDHJ4FH0KIiJHD6Fv4OlD6PnZefQ7EKco2+ORcTzmym5c20REPPJUxMgzxF7ABiVYPvAsXpfOSzZBPFSx/TuDo3geSUqsGwxjvUO6dBNVrMN41fZ/ZnK4ZuaG8P7XUHJRTphY9+jeImFPYqUmjr2nd2yHODXLu8Tj/EzoLxqKoiiKoiiKorQcfdBQFEVRFEVRFKXl6IOGoiiKoiiKoigt55w8GmFoZlIRWPJW1rvb+i32ZDA12j/72d27Id63D/0Uq1fb+/2nKbdGgjwbS5cshfiG37iB6oB60EcfexLieoQ2vDiOusNsrg3iTWsXQ3z5JRuwjCdRB1dn7a2IJQg9OYRekZUrUA960YXoA/Fp0/hMGvWUIiLJOL7n2FFs/1hzRiPYpPwO88HsJnAo2Qj7K4IgyqOBfSFO+57PpfvnyxJE7aXv4zhIpbBNl3Shdr17+QqIQzom5+H42U/vtorcs38vxNUy6jufeRo9QKGPOswy7ZV96qSdJ8FvoHY4S3rc17/htRAPnMA95I8eRb/FvoO2D8mha9afw+np8JEjM/UJIvKkzAOxhEhs6pIEBscA773vROxzH8Z8eg8d36M/kK7WxGietSdi4e+P2tox3rgZdc31JuYBcmQZxi76io6fsn1qyRSee7GE1/KRBx+G+C23DEB8733oGzpx4qRVxsgg9qFqaRfExsW2CEPyW1DuhChbIQ9pzuFwOn9PLDb/OQxERJLpmCTTk9ezizxmnlA+JgfHuYhIOo4nHXcoFwR5GfI5jF950zqII6xW8sR2vE71OpaRpnXGCckfQdMwa80d3/YHlsmjl6Bx5FLf4GEWkGi+Wrfnl6CJf3PjDr2OFW/L4Jq8me4Dxkvo2RARGZ/A3CfxURxr8Vn+lHJl/tfgzq4+Sacn+9nJwSF4zXVxTehdhPdBIiJL+9BX8LdP/m+Iiw30k21Yh/d4OfKWJh3br5NI43VoGuwbyRT6WcMarpc+eTwM+S0akWsP+T/JP5N08d5j+MQgfrxO/k/PzhEXvwjbwiPzU9PBMkfj2A71JI39HvTiiYis6sI+O0H3gNllM33YNH2RIwetY0Shv2goiqIoiqIoitJy9EFDURRFURRFUZSWow8aiqIoiqIoiqK0nHPyaKSS8ZncAyRwZblrGKFj80gYaeU1oKOMDKGO7QTlwIjS2KbSqCeOJ1DD104a3GUG63B8ALXB7AWoVuz9jV3Bg7qkOb3nrjsg3vH0UxAPDqH+PZOy99+PJVBP19OF+scY6fP27EH98onjqInOZGyPRoz2Fg9qmCdg9YoZfW69hnWeD8CHYVirTv0xwj+RSmIb1sij4Qek4SbdrpVCJqIDcq6YONUjR/lMYpyLg8ZNs446ax4TIiLFCdTYF0u4J3dzGLWay/pQh3nZtm0Qt3Wgj0TEHrtC59m/pB/iU6ewniMjuM94o27ri7m9xwSvR6w+c8zgHPbwbiWO64kzpffmMZdIJ+m99vc4vjTP+J6QckE4hucWyrPh2nr1GOWHaMviWC8Use2ffPIYxPneKyHesRPnvJ17cC4REYkl8T2lMtZhzUrqo0WMTw3h3J5vx9wdIiL5DLZNYQK9AJ7B9m8aHN81Gt+xmK3v5rQk1ZDyLZjTx7Y+Oi/EE+50LhbXw7olSYPtRizvPMZSLrZZtYHXsRnDeFEXasff/NotVhlXbcMcO9LEPprJkvfqOGr9v/8jzM0xUqS8Go499juyuGYaek+zhuPOBPh6oYjrWSnC/7CiLw9x0MDzqpPO/pm9hyF+6UsvgTjfYffxk0PoUZAmtr83q1qVqu3BOd8MD9cklZrsQw8/hPcYIwWse0dnl/X5G65+JcSL8ugX629Hf9gVl18M8a4G9t+OiHUgkca+UC5ivXqW4loVBHitDx9B/2B3A8dZNmF7G4Yo90uS7iszlNvq2m04x6aOYJ6NaoQPLrViLcTH6X4m4LwYvJZQ7DdsT2qccoXl03SfmZ3ps7FzyGWlv2goiqIoiqIoitJy9EFDURRFURRFUZSWow8aiqIoiqIoiqK0nHPzaMTC6f3D59pF3IlHaIdJj+zRYw5XJqS9+/fsehbin9x5t1XGYtKKc66NTAa1crwf/5HDhyCOu6hrW7ca83CIiEwUChB3kTaxQntyd/ehDnHVetTEnziFmlURkVwbauWW9OOe3Ox36cyhV2VRL2ohT520tf6cX+GSC1F/u2XjTNtWK7jf93wQmlCcqZ5nyBcTkpbaEVu7mUujvrhWw7hBuUEapOlmYhE6bY/2pc/SXtfZJOrCOedFpYj+ilwWr/vmzZutMv/xn/4PxKk07hPOOv5GA6/zqeOo0V9EHg4REUN6drInSN8i7I8Z8qJUSnieMc+eHzJU7wq1f3pWno2F8mhUm3UJp/qgRxNYjPI2uNxIIiLkgxKfPBjkhXEsYxAdLYhoB/ImhFUs88A+HPs7duO+8Te/pgPiho/xjmftcRFLYy6hkOq9dhOeV6mJuulUEtvyhpejhllEZO0anHsfeAjHa63O/ib8vBFcTzw3aj98rEeD9tB3pkwcIZs55glPZtZJv479i/OEsD9RRKTewGtdp9xCDnnqHgkAAOpbSURBVGnLE4b8guyNC22d9uJe8v8F+JkEackHRnCuKFEuqxp5ERYvtvMz/Oc3XwZxTxeu88VxXK/KFSzj+Cnsj8Wi7cXcvAHnuAcfx3lz7270dw7RMe598GmIr4lhThIREZe8JjHqj7MjNzb/3xOn0zlJTeUqSyTxOhw5gvmclhk7F8QDDz0E8aJevPe5/hWY1yyge5LRpXjvVB8vWGUENRzXCVpXhHJx9HRQXyGPbdPH45WKdpklWlN5Lhofxc+sX4b3pa+7/EKIjzyIPl4RkQcL6JmdKFDuF/LNdoa87uPx2sdtj09XFeeHt1zycoiPJWbOq16vy53WEaLRXzQURVEURVEURWk5+qChKIqiKIqiKErL0QcNRVEURVEURVFazjl5NDxHZMqiEeHRwL9ESos5t0HAeQr4GLTHPPkpKhXUk4mIHKdcG7t2o6/DI5+IQ7kQyqSZT5DO1RFbkxoa2ufbw/N8xXW/AfGVV18Pcb4jD/HIqL2HcmEM91lesXIlxLkc6mINtd3eg7in910/u98q4+SJUxCzDySemNFcsm5xXjDP8W8RCWh/eInQ8Ccpb0Yugz4W38dr2xhHTSTn6og79nN6jv6UIp1+QL6D0UFs864+9BglM6iDvfyql1plXnHl1RA/vQO1wIb6OOvOL7gA9aJ9i2yPRoP2iE8mUUvcpGMu6umBuKOddP8ReXa4OdvbUL8b+LPGexiKCI6J+aAeBNOTYEAmnRhdWy+if7Avjee8cA7viTVHxiImWvIJNX3U7nZ34Ti4cBOOg/I4zqGXbEJvxIF9dg6eI4Ooax4rUh0q1O+HcWz192Of683bZQQB5RgwMXod286nmD2ClZqdK4GPyXmUYjIZmzldiucHv2bEPz2n0BiqNqnNG7ZHyCXP4alxGkN0/m1Z1NkHTVpzI3wuZLGw+qxfx/jeBzBvwdaNS/B4tNYMkJ9CRKSjDXNSpMmeksrjeSxfgvPT+vVYZiJp+1vi5FPzKT/IXvI+XXIJ5j0YmsB1/R//1fZJXnP9RogvWL8I4sCfGUdeRA6d842XDMVLTo6rji6cN9ry6IXo6s1bnz944iDEr3vtayFu+ti/du9B30f3Olyrnn12p1XGvl37IE46eO1fv+VSiIslzOnjJ/H9nV24Dt39k7usMo2LfXpiFI/pVXFQNH+Bx7jhlW+HeFE39k8Rkf3H8VzDZejxSdJcFfD9Nvki27LoTRERiY3hvWxfJg9xMTmzltQifJbPhf6ioSiKoiiKoihKy9EHDUVRFEVRFEVRWo4+aCiKoiiKoiiK0nL0QUNRFEVRFEVRlJZzTmbweMx77oR9DodnY5ZDswobG9kMvmLlCohvuvFG64i5PJpOB04ch/iZp56AeP/eXRCPkhF7ooQJ1EzEs1mBEqmsWouGpYsuugDirhwaaT0HjUJrlttm3EIbJjUKyTSViqERK+ah6W/9cjQXDW5AM7mISHFsGOJhMiqnYjOmqGp1/hP2zYYT9pHfWZzQNinGDBpSXRe7f28nmr5qlLym1iCzr2v38XTszJsN1CkpICfsq9ewzGYT+8ZyGgMiIh/52Ccg/v4PfgDx9icexTIqWObWiy+G2EQkgavT9Y4n0AhWKqFBszCOcf8STLR08iQmtxIRqVRwrBVDMuPPSg42l2n6fBEEgQRT81QqRcnOIt7LeNYcd+bY98+cNNJ17fnID8mwS31y+Qo0cfYvQ+O1Y9AMvnYZ1uHGq7qtMnfswzKffKYA8bIOnNMu2XQF1rmA5smBw49bZQyexLncJXOuUCI4L06biVCyRC8RlVAR54SQNpkIGpP9znEXqP+ZcNrkGRpO9kgbl8Ts/tek7mLoDqBZQzNosYbzT4yO6YltmnYoSamhPlqawL6yrAfX7BuuQUP09n0DEA+PokFYRCSTwLGYIqNqg5oiyX2Hxp1p2Nc3nsSDbF2HRu0fZvGYfd1otr3gpasg/l//5xGrjNGT2DblJTjvlqozc3e1Zm9Mc74xTk3M1GYEmSwnYsQ2y+fxnkVEZNcBNMDXHDzfPfvxfuzRJ/B+7fW//TaIX/qam6wyqgVcW558GJPfnRjDuaa3CzcSWLZ+A75/BO8JG0nbBD1RxTW1Rt0rncD7s2fGsE/fuR/r+PIevIcUEQkL2MerlNx3RR9uaDDcia/X6L7TN5TIUEQatFbk1i6HuDwyM/bq57Afhv6ioSiKoiiKoihKy9EHDUVRFEVRFEVRWo4+aCiKoiiKoiiK0nLOyaPRqNckFpmJ72zhz1JCJUpuFk+hxtEjTf0p8hCIiBwdQB1vmbRzPmney+PjEB/Yi/pPQ3pTN2Hr2jo60f9wwYWoec+2YdI1Pm8RTrRUEyabQb3j0BD6KUZG8RideSyTpdwXbFhjlXHowCGIn3gMNaQP3DXTtpzcbr5h7bTVl4ytTw591B/HSdPMn1m1FDWPew4egbgZ4RMI6Nk9m8L+kk6jPj6Rxj7OGv1SEb0OnmfrXhcvxsSKb/t/UMd6+bZtEPvkE+HETyXSfoqInKL+lslhvZtNPOZ4EcfV6AgmBiuX0X8hYvtsYlSvXG6mLYMglOODdmLL803ccSU+dY3ipGd1uUtGzJXsXYuxp2cOj4ZLbWKPAxFxsF97lCXQpTJiIV67WuUo1kFwPlrSay8bqSwm9auUscxqqQDxiYOYpG3sJI6tZNL2gA2O4txerWK9Y7EExZQMkaYEJ2afR5PE/JZdaaq5o5p9PghMXfypgRIjD6NLCSSLVTuxXSKNfpwEranxFLUZrU2GEvr59aj+R21IyTzJPij5dqwDJwVsT2GZS/vsZI5unLw0dC/h0AJYr+Mcx4l86007mWO1iuOqRPNofz9q/Rf149zf24dz/7XX2WvwxCieeyPAMkLTjPz3fNGZ65N0evK8Th55GF4rjRQgrozaCVVjdTyfQ89ictmhAfRwDA8cg/jwkw9AvLgP1z4REa+O81VQwbVo53as95vffAvEjQZe5zvvfxCPH7EG+3Vcz5b2o7fhwk2bsA4PYB3uPobJ+Ipt9tzkdOCa69LlrxTxvMdrOIdWCjgfFH37d4YDBTzG0vi1EOfTM36qmoPz7ZnQXzQURVEURVEURWk5+qChKIqiKIqiKErL0QcNRVEURVEURVFazjl5NEwQinkOjwbnwGD9aORnrD3k8fXTWsDT1Enfd9+991nHHJtAPV4qk4K4Qp6MI4dQjxyjjcVjLtZh+Yq1VpnbLr8S4mQa9wWvNsh7kkGtpks6bT+w985nPbJHbVOpobYuQV6UeAJ1hemM7TXpIl/HwKH9EB/ZN6OnXKg8Bqex9PxcnYg8GnXSCkuctMGsHW5DzW0+h9dtjHJgiIiwuyaRwv7X3dMLcSqLeuNyCY+ZdVEHGUTkuGB9cTqF13rxYvSaVIu4j7hH+UUaE7a2tnIK22qU9ODPPI55D9iDUWG9uGOfR6OBHppkIo+v12f6dLBA/S+TSEoqPjlReYa9DvjeVNLWsPrkh6hQrpZUEq+d5cmg3Am1OraZiIgbQy0v6+rFw7HBx6yQn4LzqgSCxxcRqQeUK4E+M3gA98f/4l/8/yBuc1FPvOkiu+1GhnF//HIJ29KhPpWgccCeH/briYiUilgPh76LO+1RrEfkWZgPGs1QXHfy+iXIh5BI4FyTdm0tebWKM1SjSX4K8gTxnFimdSgM7TaMkQ+JfS/1GsZDIzgGRos0B+bwGnS222vXwCn0axqqQ5K8lkma+5MJfH86becHCQMca088g/cOXd3Y/j19GI+V0RfS22dfn6MDeH8yNIb9sX3WubPvZD5Yu3K9ZLOT4//Ky6+G1zIJnBeOHsP2ERGpjuO68It77oE4S57FShHf/7Mf/l+IOzvyVhmcCyZJeS8W96OndnwC18MR8pYkKEdLOio/EvW3jWvwPvGG66+H2Cnjdd31MPphU47tYayRMcwhj4Uf4thNxbH/ZcmPJYF9L//U7kMQnxgcgjiXnjmmEzt7o5r+oqEoiqIoiqIoSsvRBw1FURRFURRFUVqOPmgoiqIoiqIoitJyzsmj0Z7LiDvlxWB1l0M+A94fPgr2aLC206M8B2MnTkAcIcOXEmnfyuN4ihXSSbJeNPRRd9ZOetDrXnaNVWaVtG5PbMc9kVevXAGxE6JGMOahBjBqb/xaE3WH7ZTHIBlHHWKdvCpeexfWwUX9nohIkvZYzyTwmF25GU1pEIZyElMrnHccx5nuM45gG5FFaHqv+dnUqV0T9J6QfEVV8nT093ZDPFGx9/qvh1SRJPafBHmGiuOoD23P5yEuUx6NJOXhELHHXoo0pck4jqPxcdSg7t29HQ9Yt8/rGPmKYpQ75v/cfhfEQcDjCH1L5ZJdRoJy1FRpH/DZA36hPEJhOJNbIUb9KWBfVISG1XjYp0LS2TfJLxHS3BLQ/v5uhE47bOK4NZRXw8rVQePAxCh3h4Na8oCOLyJiQvaE4THGRnA++t5//ATia7bivvM9i3GsiYiMjZE/QCj/C83lhtaCtnbKy8SThogENK+wLj8+Nc9ynob5YmSkKqnkZNvyMrGkG9e6xT156/OFBvofRsbRs5Gh+Spskj+niW1WqdntwEOzXCUfB+UrqtXx9ZMj+HpvF/bxRkTuDr4XSMbZW4N9pUZ1mihj3B5y7isRh3JHDR7HttxyMXrhGuRNMXTB2rO21ylPfdSv4NjL9y6a/ncitHN9nG8OHNw/7Z1dtQrH7OrVeJ/TjPBAnRpBzf/OXXivdHAf+kILGfILUhuOk+dWRKRYQc+P5+G4yC/CtWv1xvUQN3bvxs8n8PP9eTt3xyDldOvpwfmrRh7avpXLIH5yJ3ocw247V0zok5+K7lesnG+0BrOH0G/Y16dG/qiBw5jf6NKtMzni3Ij77+dCf9FQFEVRFEVRFKXl6IOGoiiKoiiKoigtRx80FEVRFEVRFEVpOefk0WjLpWdyPjxHPo3TsA74bGCPRkD7FRdHByG+8vIrrGOkspj7YA9p/nadGIC4SbpLj/bXXr5yJcR13lhcRJ5+9gDERwdRN3hqCPdEDtagftmQLrha52wMIl6c/Suox8t4qK0tVrHM4ngB4mYC8zmIiAwO43t4j37PndF6OzL/GnnX86b7VUh9g/XWVd8WELqk7+ygPbuLJfRDlKp4jCSVsbQHfS8iIsepDYs11NEWxvD1U8cOQ+zQGOhZijpYN2Hv7x74+JkE7Z8dVtAHUi6gnnTp8n6IKyOYr0BEZP8eHEc/+9F/QLzzCH4mRX6f7s5OiN2YrS/u6sT2HBg4BnHcm/leZKE8GvUwFJny4TQpl0JMSPMakWshTdcvEJwL/BrNRy6NezpeyrO/K4qn8TOGNPFV0o5zXh/2bDgunkc2a+//30ziMS/agp6cZAfOV8ePoVcu3oHnXQlsD09bB/apUhm12DwzlyrYx2hYSDppr1E+XTLOK3F6Cgyt0uaH0kRDmonJsguUR2SUci4cOmnnw+nsQO9Bjebxegzn/Bh5hgz1jWzC9vr5NDen4uSDJN/Rpg2omfeS3MtxzHTkbG9DNol9g3MneOTniWewDhMNbDtj7D5eKmB/W7ciD/GqJbim8r2Fobb0I+YHHs+jw7gmLe6dGavVmp1D53zjJVyJT3k32UPn01hpozxUIiIb16Mfon8x+h1ObrgA4mIB76V2PrMD4t179lhlDE1QDgryWf3jP/8TxP92+48g5rxmSfYtRQx9nmN98tQODeGaW/fx9ZDmVLfd9mJmKG9TtYLHaND9mkN+UY/uybNZ2weygnJu1clL2THr/joeO/vHB/1FQ1EURVEURVGUlqMPGoqiKIqiKIqitBx90FAURVEURVEUpeWck0cjnkqJN71vO+q9zs6SwW+i/dtJL2pI81co4B7MO5582Cqhp3sRxCcPoga+cOI4xEEKtZvLlqOGcOOFF+HxhlAzKSKy/whq4EkqK7sPYsKJK7aS5tnFOjTrtn49k0GdYJzzltAzY7od9ZET47g/8o5nca9oEZGHHnsSYt7/3JvtA3HOYRPlFpHwktMejRppuEnKLqGxn6Fr1K7sAUolUQtcJX/F4GgB4nVL+qwy2JMxQr6PQgmvQ0BazYkx7OMBaT/DCF3k0pVrIR46egjiUwdxr/JUAsddg/KFbD+Ae2eLiGx/dh/Eh0n/HQa8v3kBYofzmkToXItF1OPGKTdMOEvzHJVrZj6ohaGYKe1rjOYr7oNRqRY80s3WKCeAS/v9S0hac8qJUq/htRMRcSn/jUP7yNdJsxzSMlCl/e9DQc+Ya+z5qUR6bdbAr1mNunpKqyLtORyvdYMeDhGRjhRpp+tYRj6LcSaHGmROceM3ItqO2t9Q25hgqg4RXr35oLczJanUZB/wXPL60SJcnEBPgYhIlfJFNAM6Bq0r8STGZNeRfNrOqdIgfxz7Ongq6CLvjUMDKaQxsH617S9MunidwgZ7frDPduSwA2bi5F2JGFe5LJaRa0dviUvreEBtWycNfRDYHovuDlznh0/hejE8NONT5fwj88HqVSslO5X/g3NHDA/jfU6pRF4JEaHUD9JB9ykd5Bto0np6xaWXQbz/IPpjRUQeeAJzUuzbT2vXYbonpLWKR7ZHlXbM3De7Q6cw59uFmzZCfPIk3ofy7VQmjrmwRER68tjv4zFcCypFnIMnSjiHVqs4jx87hB5IEZGNG7Ge7KF5/PGZtq1HeImfC/1FQ1EURVEURVGUlqMPGoqiKIqiKIqitBx90FAURVEURVEUpeXog4aiKIqiKIqiKC3nnMzgjhcTZ8rw9HwS8tkHpJBMN3FKSmdCNAY9/sSj9jEp45JLxh03gwmGXMF4+VJMXnbZZWg+emQ7GolERMqVZyGuNzH5yrN70XQzMFSAeHUKTT4mItlckoxmruVFJHO+h+bLUTIlf/9Hd1pl7CVzUMJDQ1IsmKnDWfihWk48EZ/uI00f+4JHiY4SaTvhTbGC5qUStUmcjsHmXjY5nhrFTQBERBbn0dw2MILvOXoKDXPFQgHiWhENdKeOH4W4pw8T6oiIHC6jYbBwAvuo38TXY3E8z5PUH598BvuziMiJITR/F8lY5pBJPSRD8fg4G73txIPGQfMkT04zG1GIhM7CJOyrNQMJp8YaJ4nkb21MzK5jjPybJsB2SGaw/6RS2I89Dwd+rWGbpqs0ByZpk4NmE48xOobHmCjj2IqlaCCwI1hEqpQ8L+nhvBqn9aI9Q/MZGdibEQkZE3E0ima7MQnkxAT2yfEGnkeNk2RFzLPpBJpxm7SpxOlkdGaBzODpXCjp1GTbhGTyzyT4OtuTdJnmvKCO5zdBSeAqJTzGimVLIe7rssuokwm6QolP4x7WM5PAYzRo7nBCrKMR+7rFaCw6Mex/wzTPFmo4L/t0OaP2mnDYsetjn41Rf0skcP10E3i9YsY+j7489r+ebpwPZk+bC5Gw7/jxo9Mb0ywmo3CG7q1KtPGJiIjfxHOeoOtiAhz3qTjeS3X34pjv7MT7MxGRpaswyfLRY3hfs28fmsOPHTtOMa65JU4AGPX9PCVjPH4Uj3HsCG6w8uwOTDzo0MYUpmJf25EyGsybtGHBxDiO7RwlFD5IJvgd25+xyhBKbDkyUoC4Jz9zzEbz7Puf/qKhKIqiKIqiKErL0QcNRVEURVEURVFajj5oKIqiKIqiKIrScs7Jo+HF4+J50R6NuZLyTP2VYjoGeTRcl+Ic6vXEsasfkL4zyTpJSgJWKKM+uUhJZxw6XrVoJ6HxG6hVi7moszx6YhDifYdRa9ffh1q6uGsnQWJFO78jpL+MFlAz/Z0f3AXx40+jTlFEJEF65CRpgGOzhKthbP41yrGYJ7GphFKexy2CGslICwlpYmt1bKMgwDbMkc/DpTJHKUGOiEiqA70xHl3LkSLqKAcHsS8s7u6GOB7Ha1AZGbDKHD62H+LyOPopHNLoSwK1tIMF9E8YY+vj2S/VpGSanoctniC9OE8IYYQ+uVLB65FL4XjvbJvRKwdhKDJse2TON/VmKGbKoBTS/JSkaxVE2EjqdTzvbBp9B/k8zgUZer1WR91zGKFXr4eUlK2Gn6k2sGKFErZ7qYrXNhnDcRAae35ir1u9TElJczgnpnKky6f5hDXLIiJBE4+RTmHbuDFqG/JxcfKvuBu1foT0HuyD9anEhMH850oTEZEwaEwnx+zKYnv0UvKziJylUm3idUokcL4aLJAXi6a43m5u86ikh1ivLBZp6fDZy9TguYHW4ErJThQWT+B14rFXGMW+0aAxQlO/pJN4niIiDvnC2DcZq2NbhB62g1AdTYTPrOmQP4X8dMEsHyHXeT4YnyhIoznZ/mNjI/BaF61dS5bYfkKf5p5TdG80PlGAuGawA5ZprWprw0SLIiKLlqDPdnEPJnFe1oevFwq4jtR5niBvTb1hJyx99tldEP/Hf9wB8b99/18hDmg9LNewTz/48ENWGUOnsL2Hh3GscjbEq6+/DmKf7pG2Xn6pVcZll74E4hIlep7tDY5qh+dCf9FQFEVRFEVRFKXl6IOGoiiKoiiKoigtRx80FEVRFEVRFEVpOefk0UgmzuDRoPeeTZoF9nGYCO3vbELS1MbJfyEiEpujXoGPGsh2ev3UcdTA/+A734F4z5Ehq0x/AjV+sST6OGo+6tV3PvE4xBes7IN4WZ+tO3ToTAzp7YpV1FnfftcDEN9z/3aIgyDi0hvKjUB5S5Kz9jt3/flPpGHCQMxUO7jUF4KA9syv2f4J3mu9Sm0WJrE/5dKosU2St6EeYVMZo3wCCQffNFZET9BD2/G6XHbRhRD396DutVK28yZwzgGfzrNJ5+nSvvQN8kZUa/b+500aN4Z01HXS3rI3KpvBtqzWbJ21T76PgITWs305TmB7E+YDJ3Cn5z72kNGllngswmvFum66VhXKiRJSvoY4abZdzy4jDMmTUSE9uuC18eg8+NunsEmejYSdoybGgnFqjEQM58DOPHoDaob6V9PWryfILyGUu0UoF0eK9vUPQuxzMcvpZudssGNv6v8Lk8cl6SYl6U62Jc9PuRTliEra62M6xLXFcShXlUvjNofXMZ3GMqpN26ySSuJ7UuT58in/Q8BjmcKQzCZhyp54HRoHSZqf+jvxvItV0pfT51PUlhFvkRh5LFzKB+IlsJ4lmrvrdbsPBS7Wm6+PN2sIVGvzbxSq12syZZOUkMbAwADmoyhG+FkXL8I8LKtWYM6LIcobNHjyJMQu3VkGvu0RGj2F92g58nGkXJyLejrQF1dL4jzRoHuL9nacu0RE2i6/HOLuLjzm7t27Id57AH2VzVH0W+zYu9cqI0serHXbtkC8ctVqiJcuXQZxZ3se4rhrzw8h5Vjq6MbzyKVnOmAtYg1/LvQXDUVRFEVRFEVRWo4+aCiKoiiKoiiK0nLOSjp1euta35/5We/8SKfO/P4w5DfYH5hbOoU/Tfr0s61Przdo61rft3+uDANKH097H9LL0qjjT05l+km1hDugiohILCS5QxzLKFbxTGtVlA4FPp5H6Ns/24YkXwhCrLgfzrTN6XbjbY3PB6fLMCaU07/W2tsp8/apdr2s/ka9g38KDijm16POPaRjsuSNJRfc/+oNvAa1Ol23CKmCJZ3i7U2pz7qCx2zQMVmyJCIShGdub3ssn7lto9purms4W2Jx+trMR/+bXU7TnynPiZ25DWJRW0Dz32hrTyeG/cE4ND/RdWiEtoSsRm1dp+vJ2xzWG3RMki25JBFxxO4fMa4GHbPe4K2lcW6pkdQlSjrluiyto2PUeSydWd4Xi1ileMdRly7X6bY5/f/57n+z5TKui+O4TLEb2HWrU/9haU6F5ptKnfs4yU8jpCtBgO8JWTpV5/kGr1OV5zyav6IkQ45H19baypz7CtXbmvNsWR1Lp3i7Wzck6RRJvmo1LLMZIZ0KXTyGVcasy1Gbaof5XINrs7Z+5evK2FvQi5QreF+SiqPMs0Kvs7zZkk5FSBjj3MdJrlqjY/IazJKgJkmnfGP3ed4St16nrbWtNRbLPKt7C74/oXtVLqNBdajTeYVuRP/zsdwY2Rm8WZLY2tR97Nn0P8ecxbuOHTsmy5cvn/NgyouPo0ePyrJly+Z+4y+B9j/luZiP/ieifVCJRvufstDoGqwsJGfT/87qQSMMQxkYGJC2tjbrlwzlxYkxRorFoixZsmQ6id75Qvufwsxn/xPRPqgg2v+UhUbXYGUhOZf+d1YPGoqiKIqiKIqiKOeCmsEVRVEURVEURWk5+qChKIqiKIqiKErL0QcNRVEURVEURVFazovmQePlL3+5fOhDH1roaijKWaH9VWk12qeUFzraR5VfFw4dOiSO48iTTz650FVZcF40DxqKoiiKoijKixd9mJ1/9EHjecKJ/BRFUV5M6Byo/KqhfVaZC2OM+BGJKJXnz4vqQSMMQ/nYxz4mXV1dsnjxYvnMZz4z/dqRI0fkjW98o+RyOWlvb5ff+q3fklOnTk2//pnPfEYuueQS+Yd/+AdZvXq1pFIpERH5zne+I1u2bJF0Oi3d3d1y0003Sbk8k+3yH/7hH2TTpk2SSqXkggsukL/5m7+Zt/NVfjUol8ty6623Si6Xk/7+fvnSl74Er4+Njcmtt94qnZ2dkslk5NWvfrXs3bsX3vO1r31Nli9fLplMRm655Rb58pe/LPl8fh7PQvlVQOdA5YXCXPNevV6Xj3zkI7J06VLJZrNy5ZVXyt133w3vue++++Taa6+VdDoty5cvlw984APQ91atWiV/8id/Irfeequ0t7fLu9/97vk4NeUFytvf/na555575Ktf/ao4jiOO48htt90mjuPI7bffLpdddpkkk0m577775O1vf7u86U1vgs9/6EMfkpe//OXTcRiG8ud//ueybt06SSaTsmLFCvnc5z4XWXYQBPK7v/u7csEFF8iRI0fO41m+ADEvEq6//nrT3t5uPvOZz5g9e/aYb3zjG8ZxHHPHHXeYIAjMJZdcYq655hrz6KOPmgcffNBcdtll5vrrr5/+/B//8R+bbDZrXvWqV5nHH3/cPPXUU2ZgYMB4nme+/OUvm4MHD5rt27ebv/7rvzbFYtEYY8y3vvUt09/fb7773e+aAwcOmO9+97umq6vL3HbbbQvUCsoLkd/7vd8zK1asMD/96U/N9u3bzete9zrT1tZmPvjBDxpjjHnDG95gNm3aZH7+85+bJ5980tx8881m3bp1ptFoGGOMue+++0wsFjNf+MIXzO7du81f//Vfm66uLtPR0bFwJ6W84NA5UHkhMde89853vtO89KUvNT//+c/Nvn37zBe+8AWTTCbNnj17jDHG7Nu3z2SzWfOVr3zF7Nmzx9x///1m27Zt5u1vf/t0GStXrjTt7e3mi1/8otm3b5/Zt2/fQpyq8gKhUCiYq6++2rzrXe8yJ06cMCdOnDA//elPjYiYrVu3mjvuuMPs27fPjIyMmN/5nd8xb3zjG+HzH/zgB2FO/NjHPmY6OzvNbbfdZvbt22fuvfde87Wvfc0YY8zBgweNiJgnnnjC1Go1c8stt5ht27aZwcHBeTzjFwYvqgeNa665Bv52xRVXmI9//OPmjjvuMK7rmiNHjky/tmPHDiMi5uGHHzbGTC6y8XgcOsljjz1mRMQcOnQossy1a9eaf/zHf4S//cmf/Im5+uqrW3Vayq84xWLRJBIJ88///M/TfxsZGTHpdNp88IMfNHv27DEiYu6///7p14eHh006nZ7+zFve8hbz2te+Fo77tre9TR80FEDnQOWFwlzz3uHDh43ruub48ePwuRtvvNH84R/+oTHGmHe84x3m3e9+N7x+7733mlgsZqrVqjFm8kHjTW9603k+G+VXieuvv376YdYYY372s58ZETHf//734X1zPWhMTEyYZDI5/WDBnH7QuPfee82NN95orrnmGlMoFFp5Kr8yvKikU1u3boW4v79fBgcHZdeuXbJ8+XJZvnz59GubN2+WfD4vu3btmv7bypUrpbe3dzq++OKL5cYbb5QtW7bIb/7mb8rXvvY1GRsbE5HJn4X3798v73jHOySXy03/96d/+qeyf//+83ymyq8K+/fvl0ajIVdeeeX037q6umTjxo0iIrJr1y7xPA9e7+7ulo0bN073zd27d8tLXvISOC7HiiKic6DywmCuee/pp5+WIAhkw4YN0Hfuueee6b7z1FNPyW233Qav33zzzRKGoRw8eHD6uJdffvn8npzyK8m59pNdu3ZJvV6XG2+88Yzve+tb3yrlclnuuOMO6ejo+GWq+CuLt9AVmE/i8TjEjuNIGIZn/flsNgux67ryk5/8RH7xi1/IHXfcIf/jf/wP+eQnPykPPfSQZDIZEZnUzs+eTE9/TlEUZb7ROVD5VaBUKonruvLYY49ZfSWXy02/5z3veY984AMfsD6/YsWK6X9zn1WUKLifxGIxMcbA35rN5vS/0+n0WR33Na95jXzrW9+SBx54QG644YZfvqK/gryoftF4LjZt2iRHjx6Vo0ePTv9t586dUigUZPPmzWf8rOM48rKXvUw++9nPyhNPPCGJREK+973vSV9fnyxZskQOHDgg69atg/9Wr159vk9J+RVh7dq1Eo/H5aGHHpr+29jYmOzZs0dEJvum7/vw+sjIiOzevXu6b27cuFEeeeQROC7HinImdA5U5pO55r1t27ZJEAQyODho9Z3FixeLiMill14qO3futF5ft26dJBKJBTkv5YVPIpGQIAjmfF9vb6+cOHEC/jY7J8b69eslnU7LnXfeecbj/N7v/Z58/vOflze84Q1yzz33PK86/6rzovpF47m46aabZMuWLfK2t71N/uIv/kJ835f/9t/+m1x//fVn/DntoYcekjvvvFNe+cpXyqJFi+Shhx6SoaEh2bRpk4iIfPazn5UPfOAD0tHRIa961aukXq/Lo48+KmNjY/L7v//783V6yguYXC4n73jHO+SjH/2odHd3y6JFi+STn/ykxGKT3wGsX79e3vjGN8q73vUu+bu/+ztpa2uTT3ziE7J06VJ54xvfKCIi73//++W6666TL3/5y/L6179e7rrrLrn99tvFcZyFPDXlVwidA5X5ZK55b8OGDfK2t71Nbr31VvnSl74k27Ztk6GhIbnzzjtl69at8trXvlY+/vGPy1VXXSXve9/75J3vfKdks1nZuXOn/OQnP5G/+qu/WuAzVF6orFq1Sh566CE5dOiQ5HK55/xF94YbbpAvfOEL8s1vflOuvvpq+da3viXPPPOMbNu2TUREUqmUfPzjH5ePfexjkkgk5GUve5kMDQ3Jjh075B3veAcc6/3vf78EQSCve93r5Pbbb5drrrnmvJ/nCwn9RUMmv5H7wQ9+IJ2dnXLdddfJTTfdJGvWrJF/+qd/OuPn2tvb5ec//7m85jWvkQ0bNsgf/dEfyZe+9CV59atfLSIi73znO+Uf/uEf5Otf/7ps2bJFrr/+erntttv02zwF+MIXviDXXnutvP71r5ebbrpJrrnmGrnsssumX//6178ul112mbzuda+Tq6++Wowx8qMf/WhaBvOyl71M/vZv/1a+/OUvy8UXXyw//vGP5cMf/vD09qOKMhc6ByrzzdnMe7feeqv8wR/8gWzcuFHe9KY3ySOPPDIti9q6davcc889smfPHrn22mtl27Zt8ulPf1qWLFmyUKek/ArwkY98RFzXlc2bN0tvb+9zbjV78803y6c+9Sn52Mc+JldccYUUi0W59dZb4T2f+tSn5A/+4A/k05/+tGzatEne8pa3yODgYOTxPvShD8lnP/tZec1rXiO/+MUvWn5eL2QcwyI0RVF+5XnXu94lzz77rNx7770LXRVFURRFUV6kqHRKUX4N+OIXvyiveMUrJJvNyu233y7f+MY3NDGaoiiKoigLiv6ioSi/BvzWb/2W3H333VIsFmXNmjXy/ve/X9773vcudLUURVEURXkRow8aiqIoiqIoiqK0HDWDK4qiKIqiKIrScvRBQ1EURVEURVGUlqMPGoqiKIqiKIqitBx90FAURVEURVEUpeWc1fa2YRjKwMCAtLW1abZhRUREjDFSLBZlyZIl09lczxfa/xRmPvufiPZBBdH+pyw0ugYrC8m59L+zetAYGBiQ5cuXt6Ryyq8XR48elWXLlp3XMrT/Kc/FfPQ/Ee2DSjTa/5SFRtdgZSE5m/53Vg8abW1tIiJy5ctuEs+b/IgXT8F7HMeFOBaxaW5oQnxPDJ+MvUQc4o72Dog72xMQxz0sU0Qk39UNcXd3F8TZTBriRBLjTLYd6yxYx8GTA1aZx4/sg9gPfDxGiI3B7RAGZ3598j0U0x+CgGJq/1JpAuL9u7ZbZcSoOXOZNnx91lOr7/ty7wMPT/eN88npMt78iY9IPJkUEZFVWy6D94yNHof42Ild1nHqo0WIwyZep9+49KUQX7B5K8Q/OYDH3HHvHVYZXXnsf1dvuRLL9PHCxOPY6KVyAeLBQexvO47utspcsWwlxNdcfC3ESzt7IG7SjtaP78djPrr7YauMWAzHXqUxBPHyRbgIDY2OQVwYOwlx4FOHFpHF+Q0Q100Z4mMHn535fDOQvf/+xLz0P5GZPvjHf3yLpFKT8xR/idP06xAbY5+jwx+iccq7jfO3h76PfTZw7CncODiPNpsNjBtN/gRE1RrGx48PQ5xK2vNu0sX+MTaE16570SKIx+sjWIMAz/OKS15llXHkIPahx7ffhWX0YtsGAc6jXiyJBwztb+FiMWxPYzXvZNs0m4H89Ec75r3/rVm3Vlx3sv2LxeKZPiL1WsP6W3sbrm+8bpRKeMx2WoNPr//Tnw/ttWquPpxO4XXgtYz7+FzHExEJaME73UbP9Rk+b74XaUbMTx7db9j1wvdzLfm8woi243rye2aXGYahnDx5cl7X4JUv2SCxqXbIJfHeKtaL91K5iG+5Tw4chHjJ6iUQV2sliLu7ce0SGtNx157/2tuxPUqlcYhTOaxXdzfOTcNDuHYdP45rXU9P3ipz9eoVEIcVrGfawT4/PIrHHBvHMqs1u//FYjivjwzjPV02noF41arVEB89jPdImSS+X0SkVqtBHKfxPjZr6fCbTXnohz88q/53Vg8apzu/53niefGpf+NJO7GzeNCgQRNzcVDF4/QgkcA4kcSLlYh40Eil8AEoncbOn85g4yatB40s1pmmi3TavjhJqpcbYL3Ox4OG9WBhPWjQDS21JU/Ek3/DmBeVqJ/H5uNn1NNlxJNJSUxd31QGr1OiitcxTouZiEiQxBvBkM4nRQ+hmVwOy6DXvSSOgck6YjunqL/N9aDhh1jHJJ1HVJkJek86i2Vmc9hWDeobfN58DiIiMbqR9OhmNpHGOsRT9P4E9iUnZvcbLjc0eEPsxu3par5+xj9dTioVn3nQoPHiNvmmIGK8/NIPGnTDdBYPGjEXj2kPY55/ztxHEwm7zAQt+PZnsE5xuoPnBw2exyePQX2K5v94HE/M+iKLL1jkgwbdTD7Hg8Zp5rv/ua47PXfPJVeIep3/Zvc3bkOKaZGISsI1Vx+2HwLw82e6uY6q4+R78DNzPWjwMa3zjLiBsfrGHA8aPMVFPVgwc/WnqLRn87kGxzx3+kHD5fsDmp+9qHsMGrO8LnghjWle73x60PAi5iL6TLxJcRKvdTJN9530ea6jVaeIY/C1TtKDRiLJ97p4TD+0ryk/aHjc3nFak7kMep3LFLHvI7l9ox4Yzqb/qRlcURRFURRFUZSWc1a/aJwmHk9O/5LB36Ia+ubfhBHfddDTktDTeYZ+fVi6BH82i5nqGd8vItLdhT/1CskXKmX8aS7u4VMfP5wlk/jNWi9JAEREKqUCxhWsZ7OJ31I3Ghj79O1JImF/G1+rVSCu11imceZvkZp1/Ems0cBYRCSdxnONufQtz6xj8reF84ITm/xPRNIJ/JbeoW8Qjh89an28OjxIf8HuPzCErycPHIA4aOI37PGIb6wXdWD/aGvvhHi8iD/jBnSdlvb0Q1wbx/fnEvbPlN3pPMQrlq2F+KlnHoG4K4fv76VfXa5Yt8UqY/ueZyCOh/zNKP2KV8FxV+PzrqOMQESkfzmO3aEiSj+Mqc/6t/3T8nxw7NhhSSYn+006g+M0Sd90ua49RvgX1bbcc8sTRexvqfibW5asTr5H6D1nll/xWK7TN4Bcx442+1ddT7Aee2KHIV6+tBfirkWo6R0fxzotWbTYKuORB5+GmH/1uHzbeoiN8DfI/I10xBzGPzjFcJ6NJybfUKs15fYf2PLT803g+9NzPf/izNTFlk7xN5ZR35DPhr8F5W+xo76lt/qw9esCvl6p4JrMdeI6sJpiEuw/3Mf51zDrW9g5fnURsc+Lj+HRelmr4X2A1S4R14/rPVcd5pu1bd70r5W5RAFea8aPQdyZss+vpwfX2GYZ5Tx5D8+/W/AecPESXF+jfjVJJVCGVEqgjHPZCpT5Fgr7IfbrpyBOpHAchRNYZxGRsZ3PQryoF9cyVu/0prFt8nHs8/sP4vwpItLwsT8t6yQVQYBllo6j1LR+ahTiptjKhXIJx6KEeM+z6MKLZz4fO3NfnY3+oqEoiqIoiqIoSsvRBw1FURRFURRFUVqOPmgoiqIoiqIoitJyzsmjEQT+tC6R1a2saQwcW7vZ9FHrVq+iT6CHdG28+U0sxOom4rY+r1ZlvSc+S3V0o/Y314Wa+HQW9ch+iDq0eMrWpS1ZgduIVUiPXimiZnBiAl/nHQZ6F2GdRERGx/AY5SJubTY+XqBjYvvXKqhTNIF9HvbOHPi6mfU6e3Lmg4nCyPT2toUh1FEe3YdbzzYLBevzdfLSdHTi1nq7j6MnI92F2/fxVnsHIrw0ZfLSjFSxzOFB1E0uI09Gb1se4vEsejxesu4Sq8wV/ah3z1F/6krjuFrUjufRT9v1+U177K7uwTKOF05AXKyhlrMQw/5qaqinTxhbH/r4U7itbveydRDHvZl6xszZ60NbSf+Svuldpzo6cK7gXY/CCB8J71DHevO5NPP8ul+vW+9hrbhjjVWchx3yKjg853l4Hu1t9rWL044ouSzG2RSWsawHd3QbP4X96dmn0BMkIlIv4xzWnsW2XL0M53a2rzi0400lwqfm0/Z+Hmmrs9lJX2ClYvsf5hv2Hdj+C3scVyo4P7FPgHdpTKZ4G/u55332GTQpbjRo7Joz70LF3pqGtT2zCO9/lSEvFJ8XjyPeaa0eMa7sLXKxfX0f6zXXzlZRsB+F27LRmOl3Z7OLVasx2byEU7sdpTroOscLGAt6CkRE8kuwP8XbaPtk3oWR7hlNivpChBd4hLaO5d3pRsq0fe0pvJdI0ZbOSbpuw0O4NbeIyLEh3BZ6rIb3Zxna2XF0GNuuXKatuCN2fgxo3l6xBtfkWgH737M7cGv8cp3un13b41ylsZhIYvt67ky9jaseDUVRFEVRFEVRFhB90FAURVEURVEUpeXog4aiKIqiKIqiKC3nnDwaIuHUfyJhwPtUc14NG9YKh6Sz5n3n02nU8XoOvt9wumyxU3V0dKIevb0DdfdJyvTdbFK+iTrqgp2IMj1BbVzSxfdwngw+jzhlnoxF7H/e1Yl68BRtJR4EWO9SBTWmzTrv6W1rbVkvznv4e7MytzvNKJ3s+WVibFi8KV0ya6dD2jM/aKAWWUQkTtmrU9S/JshPMVZDLWeu0Q7x0BDn5RCJUc/fd2wvvqGE1/bSNRshzrbjdd685VKIjWf7kho0FodpL+zl6zdBzNk+dz71FMRl0sKLiGy88CKIX3LZSyDesXsHxNufeRLi6gQec0m/nY9GaA7JdXVDnByeGauBzH//ExHp7e2R9HQWWBznCdo3PirVTIPGTa1+Zs08a8VZh+9F6L4d+v4o4EzL1uxMeTRoriiMoq8oa0t7pT2D/TYRpzJDPObQSdQPnziCe/Dv33PQKiNBc7Xr0v72NZwDc3kc34Y8NG5E9nHOPh8LKNvuVB91xdbwzwfxRGLaD8ka/dn6/cnXI1Zhh30FOHewt8F1zpzXJSrfBNejUcfYpfWOPULcX7m7RjoTHM4v45wx5vsVK4t8RI6LavXMayh72/gYli8kwmPBn2FfR2JWNueF8GgM1kfEncrenae8QclOrE9HEnNdiYhUyVuazGN/Mw75WnyMj4zgvBGVRyPp4bVt78pDPFJBj0W8Hc+jTD7fGOUX61rSZ5W5YgPmrsrSvRRNfzJ2DHNxnDyAvpJLLkN/oohIIkO51MYpx0+Mcl504fx3aBjPy3Ui5gfyrfUuIg/NLF+SCc6+/+kvGoqiKIqiKIqitBx90FAURVEURVEUpeXog4aiKIqiKIqiKC1HHzQURVEURVEURWk552gGd+S0cdBYRiQ0lrgRiX3YKBsnM1WWTDe5HCfwO3MyFxGR9g40mbLZu17FZHnDA5hoJfTRYMOGzrhrN5nhRD1kqOHXqyUsM0HnXS3ZCWEcMu74ZExLxslE1YZGIL4cnBhIRCROBiZ+T2JWsrGzST7UaqrF8Wkz4qnj++E17hthhNEpncpDzEkMq6NottqX2gfxijj2x7BuG5KLo2ggr1TQgNWXx80JGmTudduxjsbDxD3V0C6zPI4Gu1oTDZ5LszgGRmvYd+55+EGI9xzBxIUiIpv37YH4/e98D9argscMqYyuHJqFLcOniAgl1zyxfzvE5dHRmc83FyZhn+u500ml2Khdp6SFfmBfK042xgn82Ooahmc+zzBi241Cicz8PBVzIk4yqVaqOK8GPs5nftPeLKBawXq7MezX5TKOg3ZKTNnd1QvxT/b83CpjaT9u5LF5KyazLBewjHgcx07dIbN0wm67mId9ME1JrZypDUyaEQnd5oNmoyHBlAGW5+e2NhxjE+O4zojY15rN3FZCPneOOMpvTotmKkOmexrnDZpH2XDeJHO560atPVima5mosS+w6ZoT9nGiQhGRCq253JZ2ckP8vN/kzWzsOZDnRb4es/eiicjHeN5pTzjixSfrVDmFm0QkBcefn7TnrrY4jqcEbY4Rc2mzDEp815XAk04n7fuxTtpQpUKbm0wcH4Z4cd8KiHvovtNz0dReq9rnVS7ivUON5kzXYJ/uSuNGJ8t7sH8uyuF9gohI04xC7FPCa4lh2yztRtP6SBLn5KBuD97eDpyHvQDf89Qjz858Xs3giqIoiqIoiqIsJPqgoSiKoiiKoihKy9EHDUVRFEVRFEVRWs45eTRiMWc6SU1oOCET6r8sraeIOCTo7MyjFq4rz9o41I+mMpSAKbC1cvEEauEaVdT4NUjzJ6R550RwbpI0umIniJEY/43PnRISkTQuS7r8dIp12yLlIiWZIT1eljL4BQ5q/trasG3HRjBBjIiIO0eyoIWmOjE+XccnHv0ZvBa62Khdvai7FBFxfGyzkVOH8A0+tntQZe0wXuc28v+IiMRItzs6iHrQtIs63nHSrsczmBRwmLwPEpGwL+bgdUtS0q2eLF77GiVzPFFE7eeJUayziIh/AD0aRynB2oEjhyE+uPtZiDN03oFrZ30LAtRij+zBJICZ2efh24kz5wUTTP4nIkLX2m9ineoN20PWaOD19EjPHjYxrtYoYR+dd5ROtknvsZS4NF/xEWpUZormI8+a70SaTfxMRx6vb5LmloC8J8MFnJfrgd12GVqt+jN5iMMxPGYzjbHXgXNiGLPbzuHkqnFK5DblhfPiEeaE+cDEpj0OrNH3OTFjxBjhlalmyCOWxjbK9aIPhhNGNskfJiKSTOIx2IPYpHHC3oYm6fb5ViKdwuOLCJoXRCRNc2COPIvVOurbOdFvVK7DePLM9WRDZ5wS2sV5rEZcnzIlW/XIZ2TMrHERcY91vimN1cSdWoNilLDUzeGYL1Uj7gHb8HyWrlkC8eApXGfKJfJo5NF/0duF/VNExPiU+JnuCTeuX4r1LJL3JsD5rUqJQGNi358dPYSJeatVbJtVq7ZA3N3XD3G+B4+5cvVyq4xHnrgH4loD+xPP27USJhTesfcUxG1Z9ImIiCTIH8WJVv1wxq8ymTDS9hNH8cK6k1QURVEURVEU5dcCfdBQFEVRFEVRFKXl6IOGoiiKoiiKoigt55fIo4EaNJ9yRYhjP8PwZ3KkHe/M5yHOd6BevVJH3W5pHHMWiIj4p45D7JLnIpUgH4JDOt4sajnZp+B69nnF46gHTZCWs0LaOSeGOrjuHtTribH1ybUa7gXNOS9SDuoKA4PxsqWohTx1AttJxPbVsEcGxNwLsId3rTohsSl9aKNIFXCwPZYt2Wh93gSofx04gPrDnsW4h3RvRx5iL459x4/ZQt4GaUrNKOmJO3EMdPVg3hefxs1EhfShSVv36pfxPYlO1LGONrGtjpO/4uTAAMT1UXv//ZKH+ttCqQDx0Ah6NIoFfD2dR11sZRSvxeSbMDQ1bN+6N3Meob8AHVBk0pcx5c3wXPKDkQY7DOxrFfdYc42fiZH/IUUabZfyxUiUVcVguU0WnNPc4VBuINPG54HzUSIekUsoPLOuPpvCeldKOCeepPwzErE//tAweomKpxZDvKQD5zjX4DycoLk9TNh5TsKQPDHke6hOrUHViBw684ERM52/weE11vB8ZM9PIZ0P9w3OeZEhr0N5AsdtLm771OLUh9kzxCZF1oWnSFNvqAhe00VEfIPreDKNk0lAC5ZP/s6QxkyD/Rciks7gMeMB1rPepPxZMbq3oHuPVNL2qVUNHqNaxPbO5mc08kEQiOBUft4ZKU1M55rpW4b+iGSe/Dt1ex0J27BNCn4B4hrdj7X34j1ivhvjgwNHrTJiAbZzvh1zUrgGX3cSmCfj6acPQjx4Es9jy4WXWmV2963GuA1z/qxfsQFiv4l95777HoH4wcPoVRERGRrFe7ZFlFcoRnm+jgzgmryoB++nu/O2v2VkCOdhywb9PH27+ouGoiiKoiiKoigtRx80FEVRFEVRFEVpOfqgoSiKoiiKoihKyzknj8aMQ8Mm8EnzGLERdaWMWrfDFdSDteVQj9yzCDXzpQJqdOvjGIuINH3SE2dRf+c6qNWsV7FOLula4yQ29iPMCak0lpHJoXZuvIj+imwbxh3tqJ0rFu3zSpFWNkb1MqQPr1bwvPoW5SFesXyZVcbI2Dj+gXwfrjvzXBqa+X9GTaVz03k0LrzkKnjNIRlwvgOvgYjIEGktMzHSH1cqEPcuQv9EWx73nU612RrHDtLxug7uj815Eeo5fH2cxlEjxOvc7kTk0cjS/u5pHNZjpLEvnEJd68QQejSModwdIuKG2Ee7yE8V+nheHu0hv3gF5jXp7EPPhojI7v078ZiU58ANZ51HuDB5NDzPE2+qD3oe+b8oH0Auh14ZEZF6gG0bch4Dmn9iFLuky/cCe0/3pEP6dB+PUS5hHVIxfH+2DcdFvUl7qUfMgQ3yNjiUf4KsJuKF2EcHRwsQnxqluUhEnCTOs0dP4nsWL8LxzWluTInart2ew5oBavMbdTyv+JQ/JYjIkTIfJBJJcae8cy556DjHRcy1l/dmiPV2KPdDVyfOm300B44YHNdu0u4LPrVZs4zrnUe5gNhfEU9gZ7G8cWFEmeSHqpN5KZfAcdKVxrk8JH9LlEejWsX1gb2YKfJ5kBVTOhehVyDbYc8PuT6cZycG8V4gN+t+xm/6snfHbusY55O2VH46j4YX4HVKUXdb1IueKBERJ419YWQQ8zCUh/E69PTgMSbYbuajL0FERKheB5/FeaJYwDqsWrkO4s4U+i0uvgb9not67RwXPKf296J/rLsD+9tEEfvSloteAvGhw+ivEBGJe9g3nn7mKYj9GI7tDvJg9PX0QXxiwM6Bkc7hHDtBbVWZNbbZ73Um9BcNRVEURVEURVFajj5oKIqiKIqiKIrScvRBQ1EURVEURVGUlnNOHg1jAjFT2nxDHoyQ986O0LCWy+MUFyAeOI77F58aPAHxxZsvgDgd8ZyUIWFuOodxo4Y63vHRYYidBmrtHNKep9vyVpmmDbVz6Qzq3Dq7Uedaq6M+L6A96BuNCI08nWqKzrNWwvOqVwoQNxu4P/eSpajXExHJ5c/sLZFwRkvLmtb54KLNWySenNRfrrngIngtJM1+NiLfyUrad3ppF16XQh3baNFibKNFpF92t6BPRETk1DBubD5G/aunB7Wao2OowfXCIxB3daCuN0Y6YRERn3xJScrD4tSwfx3djV6IehH7TujZ17ad9tdPUy6GZg31yWnKWXD4yD6Ic/3ov5qsKNYzRn2sXpiZP8JgYfJoVCplMWayno0G1jdB2vK2NluDLZTfhufRZpOuJWnoQ9LYx0iPLCJSKuD1rE5gn/FCrMME7Xc/wT6RJI6lbBfOd5MHxTCkatU4l8vxIYit/dubER4/MggeO1WA+KIqjt+0j/Nw4eQgxJ0pHIsiIsbFcj1q/9M5HkJ//uc/EZGent5pj5BLi8LoKM4lYYSXxqEcFJy3xSUXZpq8DStXodcqJbZnrErzySDVi/tKndZYQ/5DN4VzTSwiR5dfozmPjsGfYV8kU63aa3AYopekpxvnZs5rUPdx3MUoP0gya+cg4XpLDctMzDI7Nd35z+WS85LTHpuAcn5M0Hh0m7hmiIgsXornXBzCPCEpB8dsg3yTtSKWmYrbPkmyp0p1DPtoVzt6LjpzayFetxzzmuU78D7g1EnbQ2tCPNdaFa91MYH9b/tO9GDEKCdTPIN9S0QkVcdJ1fHQW1kuYrx0Gd1rUA6coVHbo1EpkS/SofvM5sx9llGPhqIoiqIoiqIoC4k+aCiKoiiKoiiK0nL0QUNRFEVRFEVRlJZzTh6NMAgkPK11ZH0WacxYajj5+SbFeIxKBXWRO57ZDnF7BvWiWzZvs8pIUt6MZm0C4uIoaoOHTqIPZCKO51Gvok+BtkcWEZFMG+7lbGhv/DhtIp9KYVyronauHqEPDZq0Fznpbxtl1Dg3KnjeYcAXxM5DkO9ETXm2HfWPg7PaKjQRF/g8MzI6Kt6UznVsxw54Ld+N+tjREwesz7u0v/uKriUQL+5C38CpcdR0N8Yx30ClafslMinsf+suwT23169YD3Ef5ZNokiY1RXvMNyIGVkccx0WHg/2LUnHIZVsvxTKoK9QDu2909aKfJZNGTWqlhtpZ/gajNlaAePTEcauMiZOY38Mh30cwK/fCQnk0giCYzlfAeQxYXx2l864H2AdTKbx2nI/Io834Y3TeQRHfLyLikEY57+L8lCMPWd3BOpWKOHdkyW/jlyP8CeSvIRuIVHzKxTGBfawnhXPPWNJuO4/8Aw75C2Ix7HXtlN+I00rUK3YZThaPESdPw+k8J5zvZL5YvLhP4lNrFJ+vnUfD9k+EnCeKfAPsXeA8UospT1AXzXciIgH1lzXdqBUPyE/nU70D8tdVKQ9QvWH3eUN9ox7ge4rke0xRvgBDPrdYzL6+qTTOgR0dOK7ynbheVus4ttnWWBnHdV9EJCjiWExQHqZkbCZmf8180NEWl3h8stye5TigutsxHmJvjojs341/CwzdG1HqjXga55V28sM6vu3R6GzDdfwll6K3d+eukxA3KUdUsYr9b6x4CuLDh3CdEpn0Ts0mTjlWBofxvvOe++6BeHSU5tycnR/EcbEvtFNujuPH8J5njHxvGcq31bfI9kkeLOL9MI/N+iy/pzkHn67+oqEoiqIoiqIoSsvRBw1FURRFURRFUVqOPmgoiqIoiqIoitJy9EFDURRFURRFUZSWc45m8FBCZ9IcwpZUP+DkMbZhqy2NxrN8OzqrjWCiFI/MbB2d+P7uxWi0nawYGlSGj2HCtIETaPDdsQcTp6QS2CRsMsu1o+lYRKRZQwNX0MCYDXeWiYuM9UGE0bVaRpOwX0MjWdBEM26DTOzxDJqmUkk0FomIDFMCl7YubO9MZsaw6Xl2QsbzTb0ZSuBMtk26gdfZNNC01IxIJlOtouHq+FBAr5MpP49GtUoXGiF77FxpsrEX++RlF22FeE3/SohPJ986TaGEBq62NBrVPC+iUCJGBk42dG189esgftMrX43v9+22Cz3ss4UJNLcNF3BclScKEMdpM4LBw7ahrklGSOENB2YnT1uAzQhERHK5NslkJq+B72O7JmlMNSKSlrrks3fqdIyQxmUFvwuqFSmhX81uh0VtOEdlM9SHXOxDXhdtHsDJL7PY72s014iIFCuYjLVC5tvhKs4tvsE6XbxkFcTuiN0HDX0vtnwxmiGTZKzvINN7zMFjDtOGGSIi6XY0pTs0dk5vaMIbm8wXuY626cSQhtaJNqo790cRkaBK15baaHn/MojX9OKGGV1NXNez9r4REpBH1HdwjvM8NKV6dF9gaA1u0IYYpbo9rjiZ4whlbcvmsW38BCUYruB6mUzZ8ywn5OzM57EOtCEGd5E0bQrjxe2EnrluvB5BJ/b5cNa6VqfNTeYDzwvF8yYbm5P+hjVMVtvTayfEHDyJ88KiRfiebBqvfb2BY7Q8ToliyxiLiKxaggn4hk5g/6lW8MJUq7jmDtRxbfOb2MmdiISRhw5jot0iJU0dGkQDepLM4uUKvp7vtI3aufY8xCdO4oYq7M12Xd7oAT//+ONPWWVUqzS26Ji53MwxwjCUahHb7rnQXzQURVEURVEURWk5+qChKIqiKIqiKErL0QcNRVEURVEURVFazjl6NPzp5F+GdLyNBmocncDWD6bjKPhathKTlXX3sX4dNWa9vT0Q16t2wptEHLWXjRp6G06cwoQxp0ap3oL6vWxbHuKeXlvX210nvwS1TSqJWkw+L9fDdnFi9vOfT1nXGpTYK0Vaf8fBMrw4JdeJ0AA2KcvWCCXcgWMugES+GVTFTJ13lhIOZrJ4vpW9tnYwR9pf9iKUyAdDudKkTzCb0A2XXmSVsYySN65csgLiNCW4avrY3zgRXpZi17GHbGjwPDiNjk/JqLwYHiOdwjLCiDw8bIkYGsJj5nM4Nleu3Ajx0WefgXhiDJMgiYgETRoHIY4DB5KnLUzCNM/zpscv5zXkBH6cjE9ExCOfgOvjOSZcvBYTBZyfEg3sP0kWxIuIR8eMGaxXYNjDg8fIpNCT4ZIvqD1u66LbSHPcIJ9aRwLnwEIax1qnQQ/ZGkqmKSJyhJI8+oaSrJE3qUHeuYkKzgler63D52ktRn9oTp1Xszn/HjURkbrTFDN1nrxMBOSLjHv2OsJ56Dpy6JVZ2Y3tvq4T1+hwHL024tjt4HAhjZBeJ48iTWlOiNfNpbZu54siImkHj+mmsQ+fMHhM9nA0qvh6Jm73jRjZhuJx7PNOET0aSaEkxgFej0ZE4kGX5mZeD2b77aKSIp9v6vWiBFPz8ugoXuf2NDbQ8eP2HN9PvqrOLlxT0ylso3IJ59DHH0RvX3cO+6eIyEHyXh04cAjiZA7bONeGdcikMxA7dK8xMmLfW0xMYH8KyDOapXGWoMyEvYtw3BUK9r1tiubl0WEci5UK9uF9ew9RHbFdmg3bYOVQ/+P7jcqseyRjzj5prv6ioSiKoiiKoihKy9EHDUVRFEVRFEVRWo4+aCiKoiiKoiiK0nLOyaPhN+siZlLX1aB90oMmaolT8Qh9aAp1aiEVb0i7Wa1jGYf274Y4l7Srv2Qx5n5wQ9TA+7QPuEtaTM5XcfAY6gwTEfrkbA51lEtXbYLYSaGYMsb7MFPujxhpvUVE3ASW0azhZzzS2XdQkodGgOedydl7ePf24WcmSqRxLs7oEKNyBJxvauWauPHJ8+h0UF94agT38C4O477UIiLpHvSlpOK0h/yqNRD3dGE+gpdvfRnE62nPeRGRWgnzCRjO50Hy5RgJrXmPbt4bO+qrgVoVtcEjE1iHbA71oAnqXyGZMkKrUBHj0n7udCJXXH0TVpP2qf/mV/8M6xhxfQx5CRzhtnEi/z2fBKErwZSXKaBrVWvitfaMnW+C/RNeHeewseOY96dyCo/h1fDzJyfQRyUiMpCh/ENd2O+7FmG+ogztr970KWePj8erVXFeFhFx6XJ0deAxk5SHpZ2058nFOK9G+VvaO3H9OHUK+9Cu7egDclyc+3tWYzvUPVuj7JEXTnzs5+7UNXcX6Du68YlxiU+tQUEdz290DPtCI8JHwmsL+7UMzQU8t2Qtn5vtxTydZ2HWXzBy8dpmMhjX6tj/GpS3hfXvIiKO4HllqL+l6CPlYdTZF6lP10gPLyKSpb95ZOIrFgpYT7rX4Lm+VLJ1+OzzymTQL2Bmzc0LsQb3LemWxFQfcFy852s28bolEva90rp1qyE+fhLX7Sb5ecIm3qe0ZdDL4IS4tomITIzjtSyV0D/hC/kgs+yh5f6J90XsfxURiZFHSGhtSCSo79Ah2H9Rq9p5evbuwfvf4SFcKxxymPGtx7GjOF/GI+5lOzrwnqdJw7s0Kz+bibhPeC70Fw1FURRFURRFUVqOPmgoiqIoiqIoitJy9EFDURRFURRFUZSWc04ejXqjJn4wqUWr017FnoOasrJv+wwaBjV8hb17Ie44iX6I/kW4N7/fIO1w0t7rupv8Eh7tud3TgXq8QdqvuEa5Oao11PsdPm5ry3t7Udd24TbSZsex3jXynsRpf+04+TFERNrz2J6mgDr8Jmlr+5augvjY0SNYRsQ+4ak0thXr9WbvH+03bZ3s+abm18Wd8mYYg/rXk7THfjVCR54hj1AmgR6N9Rsx98PWDZshXrtyLcQR29RLvIHXLmDdJPlx2JPhk/44SOD7ExE5Vh547HGIv/7db0N861veCvErX3Ytlslizgj/A4/mwkQB4tEK9vHLLrwO4jUXvgTiwbv+r10GabvjtKd6EMx6fYE8Gk2/Iael1zHS8nLehpjYOttOD/NFHD9wAuIT+wcg7knhGIwbbJNs2vYy1Hzs+8ODOGdxHoM61TvfgbrnOg31iXGce0RE/Caeq0f9OqRcHbUK1tGnMjIZWyN/+CiO8WQCz33FiuUQV+o4D1cpt4eTtseSQ/Vk/xLb6+abweMnxDudM4nqVi6jZl7ciMq6ONYrlGeKP1On5BFpyhEVC+11oE7tXvdxrOaof3VkMfcQj+waXTcx9rhyyFvDOW46SFffHuAYGC1jfxyr2P6qZgbr4bl4+1QYL0DMfdwj/4Xv23k0QpqLC0XK2zVr3ms27XY433S05yQx5Y01cbrOdL4rV6EXTETkJN3jcf6JJOXs6SB/YRDg3DM2Yee0WLIY546rX7YF4h27DkNcLmG9OZdJZxfO2eN0nUVEQhoHrov9LUbxKPkrCgW8P3v88SetMritXBqrnJ6mQR4ua8k09vwQUG6xJOVHcmKz5otzSGWlv2goiqIoiqIoitJy9EFDURRFURRFUZSWow8aiqIoiqIoiqK0nHPyaNRqlel9ngPa25r1YSOkJxMRERf1oKxZrLShP4IltK6gpjGdR+2ciIhLuum2NtThX7AB3x+QzjJBmrSQ1OmeY+sqGdZeFsdRR8ga53QGy0ykbH9L0sX9tD3SR1Yof0N71yI85vAIxFF7cHukI+R9kuv1GY3qQuhD04msuPHJ69W3aAW8VqO6llKkVxaRjesuhriPcols23QRxKsXYxlttFe2a8jbICIxFzWmMYPCSMNidCKsY98JktjOJsJb06RjVss0NmlvciEduvh0LaOE6LTndm0cx2p9aBDiod17IE7mcKzGU9ifRURCElY3SQQKdivnHASiLcTzmtN5AjjfSJL8YEHJniuOHD8IcXkQ9cHd2TzES3tQ5xxUsY1MaOfDGRnDa+GRl8GQJ+PoyX0QJ9fiXvcxynOQjNl9kH1noyOY08GjcVEYw/6TpHwBbXn7vHJZ1F6P0by6aGkfxMNl1EEPjg5BvLwPPR0iYvUr1l4HU3202Zx7HTgfjA2NTK/BhsZHQPr+VCZijBm8Tpw3o0FzWonyUHVS/hMJI3J10Diu01oRsLcyhbEbkM+yxnkMbH9WmvIUxGgOLJewnv3kCzlVxPVznL0rIlKgdZtn/3oNy2TPFovkeb4TEXF4Dqnxe2Zej/J4nG8mihOSqE/1vyTdx9BtSzZr+6x2PrMDYh7nbbROsH+iTvNMYOxcEA2/AHG+M08xXvsSlcHXoFLBe4nubvu+kw0LlQpemxr7JcgHUixiGRPj5M0RO8eKnTcDeySnueC8GZy3SkSkQl6leByPOdsXonk0FEVRFEVRFEVZUPRBQ1EURVEURVGUlqMPGoqiKIqiKIqitJxz8mj4flOMmdQMBgHrA1Ev1ojQsPo11Kll23CPZEohIEdPoda4M4PV9SL06iHpyzu60auQSqNuMJFE/XF/Xy/EzTrqLHtpD3ARkT7avz0kvd7EOOqVT544BvGSZfh5E6FBdQzpWMmLEpC21iUdtaFL3bSun71/dJH2ZZ+9T7vPuv55YPWK9RKful6vvOoqeM1zroB4z0Hcl1pEZMtG3E9749JlEAesz6Y9pd04XpdYRE4Ll/THrKP04ramdDa5Nsz1kaT+GdU3rrsW82JcftllEOcz6FNyXKqTS30pol58phu3bsPX+7ohbovhMdu7sQ59nfY4Yo3zww8/BPHQ8IzG3kTom+cDzzXiuZP9JAywf2STeI6H99o5dwoH0CfQmcxD7Ic4Liu0N32MfEJjY/Y+8uMF9MfVa1imF6d5lLS/TSqzczH6RE4N47wsIjI4hB4wM4JxWxvpmimPQeBQ3oIEejhERJYuXwJxNcR6HjiBYz7VgWOxf/FiiB3PHktlyqMUt4a4Q/+fX2rF0vS849N85dJ1dZN2jpUkeSwSCWyjsRJqw6sBehtWbtmKB/Rtn1omiWO7msRjVOJ47YcbeB0rJey/PM46Ir2ZeMxqldYnuh/pa8djtE9gf52o2h4/PtNxqmc2S/Ms+3vIUxG6Ees8ze88zTmzrjnnZJoP/EY4vaYl6X6suzsPcblsj+GVq3AMxhPYV8ZH8TNBE/uwR2M2l7fXke4eXItKZfTbrF2zBuJdz6KfkJf1rq48xIsX4z2liJ3DZngE40KBPEOUp6VUwvezn0JErLw5MeorhozS7KGAPFRCnsfT7yFPVqNOHqy47bs5G/QXDUVRFEVRFEVRWo4+aCiKoiiKoiiK0nL0QUNRFEVRFEVRlJZzTh4NI+G0TMzas9flQ9kCMN73m/eZrjqoU/N91Jx15/IQuzFbpz1OfoggXAlxvpc0gmncazyTQ80faybz3bY+L93RBXGMtLJhgLrX4cEBiDu7UVNohPYqF3s/4wblRoiR4K5I+tFKDbV27Ulb2+iT3vbEiZMUn5j+d7AAGvln9+2a1iFnfo57Yb/imhsgvvqSy63Pp1KUC8KgZvZnd94D8eh4AeKeLiyzO8KvkyadbprysrQlUePokuaex4jrkZ4+beuuYzE8L4+0micof0CTdNdz+a1ERBzKB1Ih79I47TU+Trk9HBrrl1yMnhoRkQnSuTYdPNenD8zkoPAbDTn22DPWMc43fqMh/tQlSbh4rUsjqAWujdj69XwKPWBx8pSdHMFrVW1SO9J8dPL4CWE4V4tHXyetXbwK4lSCvFk0dwxRToyDR9BjJiIyWChAXAtQ61s5fBziS7agj6hnEc6rx04ctcpIUj6PSki5hELsY3EP/Qc9/dj2QdzOAVGsY9vFE+RpmJp/HMf+7HxgZGbH/hhrsqkvsW9BRCRJnoyYg9e+TN6E4ydxrXrlFVdCHHp2vomQpo+6j3Na1WAbF8m7YMgl1kP5jlJpOz9IgfJg1Hy8Pi7dn7TlcC5f3oP3BcOUM0NEpCF8z4OvG3rdpXHFcRBGrKEh+27IyzRr3TULYBMqFmsSn6rTcBm9WquWrIK4GuHTbcvitUul8dpmkhiPDOFctGo1zhNhrccqw29gH2+j3EQercn5PPoiU5TXJZHEa7CI/IgiIkeOoLdkeARz+Bw9inPo/j3oC0mRt5P7q4hIaHBOdemer0F9x3G4g3LeDbsDuTSn+AbHkTdrTjGhvb49F/qLhqIoiqIoiqIoLUcfNBRFURRFURRFaTn6oKEoiqIoiqIoSsvRBw1FURRFURRFUVrOOZnBwyAQmUoCwqli4pQ8z4lVhfHIZOp6aGJNJDDubGdjLZoBMynbNN0kE1iFTKq9/Zj0KUfJf3KUWCqewDLZPC4i4rhY7yaZ24oTaGgqjGJyoHIRX5eIpGw1SnY4MIBGrI4OrOfwKJqPqmQGb+uwE8IEdH1GyAR6fGDGeHouRqBW4TerYsxklz05VoDXHjt0COLtzzxtfX7nQ5gAbnkPmkMnCni+D9x3L8QpMoWlk3bCSI8GRpz6eMzyx1GCJnIYcoK/dMa+bi4lXIuxmZtCK3EUX8vQTgRl6G9BA49Ro7hKCR0NJZTMUGJCEZEkme2lDft017IZI2Czbhtd54NmI5CmO2XIdPCcR0/gOPYCe7OAGBlGKzU001Ya2G7jY9gnx0poUh07ha+LiCTIBLhx3WqInSRO+1VKmBYG+P3T3oOHsE4RycwKlGxxaKJAx8T3j9NmAnkH2+WxnbbRP5XD8VZtYttlO3G96F6MRtEYZd+rB3bSUc/O0AecToLFybDmi1xXfnq8O3E2bp55gxAREdfF84uTOXxk5BTE/XmcIzOUZK4S0Q5jlPTroWefgJhN1bEuHCd5ui25cjH23/Fx3FxFROTw4UMQl2k+6sxjX+hsxw1c1lPblcqUQFJERkNcQ0cmcOMGNusGZGrnPhPjXRrETvAqAX5mdrJNdwGmwMOHjos71QdWbMCNTYYG8b6mO8I03dGJ8/7Ro9jfXEpMTNOKpDy8/+pfucEqY2wY55axUewv2Ty2aTaH80YY8HWjeaNmbwQxSvdbhw9j8tAdz+yHOEMb03R14zhzjH1/NXgS7/kMbWYTp4TCPDQdoc0jQrv/+XNsDDM7Ue65zIH6i4aiKIqiKIqiKC1HHzQURVEURVEURWk5+qChKIqiKIqiKErLOTePRjiTLsjSdROd+Q7rb5Uqaud6KUlTjHRp/X2oW0vGWJNmV79Jor7CGOoGl/prIM60Y4IYTpCWzdDrcTthWoM076NjYxCPk/a/2USNX4kTlUVo5DmBS6OBbSkO+lVOkl6yWsc61pv29XM9PLdtl2NypvSsJEfNZlN+evu/Wsc4n3T0rxVvSlNcK2KCnH3bH4O4LWd7adKUYO+OH/4Q4tDHNnVIqxmQptGPSFpo2P9ACXCCKup4Q9LgBpREhxO0lR27bzic5I++P+BvEyIcGFiHiHfw31jvGVIpTT4mifQrZfIliUhbgO2fII9DvXtGS+s3bH39fODG0uLGpnTEddTZVsbJpzJmJ6yKUR8rFDGx0/FhSthHmtlyE8+7LWt7XeqUHPHgICbebMbwGAmH+w+el3FQN53utMsMKG9bg/TDG9ehljpFyffue/wpiHcNYJ0nK4Jzez6Pc+JS0uFn8zjXOy72wTAioVic5tkEeaROJ6yKxxfGo7FkTf+0Tr/OPiiaK5xYRB1pjU3HUWffRp6yK7dtgdinBJK1iDlwhBLUjgQFfAP5PKpFXP8KRTzmBVm8T3Dqtkb+ZAHXu1RnHuKyS9e6jfygIer0Ny7DRL8iIqYb+/0jTz8C8VAJx67vn3mOisjJZnkfAxrviVmemggZ/3mnLeWJN+UtWd6Dftd0Eusac+geRURKdVy3h4bQo9HVjokTDx3AYzTKmEDyeJf9XXmOEjx65IXpIK+vP4H1Lo5jmcuXrId4fMzuf0cO4Xx1YN8BiP+/9v48SLKrPPPH37vmXpW1V/WullqtFlqRkBACgw0YIzZ5+GFMMCMUyGBsC4MZs9iAjRnb4bGFMN49jL8WDhODMROMCQ9iwIBkSYD2llpSb2r1vnetud/190dVV9XznKtecHaVUL8fQkG/lZl3PefcezOf5zxxhD64gSG8P3FcHNsGh8z754kTeB/ZIW9dqRfbuC0UcDqD/SrqmB4u38HP5ChgOFrkOzqb5qe/aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK6jDxqKoiiKoiiKonSds/RoLKiyAtK31uuos6z0mhozP4c+gnIR9V8Oqb4G+3AZrSZqP+MMfShHUAQh6u1a5OEokgbSpTwQm3wLrmt6NFILD6PFenXyUzgu6ts7NKd8EJr7lS+iXt12cTs7Aepx603UQlqkw67VSVQtIj09uG/rL0CN8/DwyPy/2+3Wkns0htduEG+uDbVpLmubtIR+FXWaIiK9Q3ieep9BHeXxnTh3v8siWjr3tmt2H4s0tp7HORo0L7WD7+e8CtbsemJOns5KS0dO7fMwJtg2lpfxuuENoe8oUotexfeT9UQS39yPmRpmRPjkd0nLC7rpOKOPLAU5ryi5uWydiSPoMzl8CP0WSd3UwMYhz8WPyzg0if22xt4qOpCDVfO7og5p3PeQX2uqjcscG8L57osue5FwG6sV7GsiIk1qp729mEe0amwM6t27cF757zy0GepORvsY6sX+li9j3+oZwNfdPO5nTB4P3zXX4do4rvI15mQeTBguj0doZM2Q+LnZ/TZ8U7Q/bsYxNHI0QqyHBM9tPo/tjb0QnhnrIyF5KVddugq3k7pFh8arapt04nnUs7cyzAmlMWzDAeWhtIt4rA620U8xUMD9rsZmGxcP718uWov5HvlpylUiHw/7WrN8rmGA40PYNn0OC+9d+jZ4zUsvk9xcDk+uiNt6Ygr7tG3eKknbxs+sW7cS6pFh9MYc3HsY6v3PTUFdrowIM0z3MTnKQjuwH5f5+ON43S8Xq1BXe7FttTtmjhB7e1PKUCmTn2xwBD1B01N47cv75v1LdRDbdP8g7vsll1Whrk1h23nswb1Q9xRxjBYRcW1s9y3yDx9ddH3SHA1FURRFURRFUZYVfdBQFEVRFEVRFKXr6IOGoiiKoiiKoihd56w8Gq7jim3PPpu0SV7YaOKcvo5j6kOLZZyHOiGtZaWIGsjTqdE7nbbxDhGay74xBXV9GjWmvVXcphzlZCSk0Y0cUxvOsRfssWAtpuOgsDUgXabrm8LXDukxbVpGrY7HguWbtoXbMDWBx2F2Q3FHekuoI/TthWUk9tJP4h1FtlhzGuMkRT1sGGNTnsnQx8/k8D0DF18NdWsaPUBhA3WTCR3zKMnQyAY0lzUdU/YuWDZ5GyhvIiVvRGqZ3w3wmeAWak6nT74Qej22zHPLfdWmoSNJ2RciVON2c7+aXSi1e9LfOs4i3WpizmW+FNQb4xIns22vST6hfQf3QR3VzDaYCOm4yfcz3cTjdHwGdbYhnSvO4RARCakNJhGeu0aMY/VEC2vXwnbfaOD87cmzuJ8iIq0mjj+XXXQR1MfGcZm1Dq6z2UbPmF8wc3BKZRyPBoerUF+0AddZLJG2v4XrKBRMHX6Z1sGZSEk8eyyzMnSWAttb6CYeZV4IeTRsJ2OefJ9zQfD1As2jP1HDcy+k4R6soHdQRKRNWTG2h9vBm+WRhr5K2VV8fc0VzHWuK1Wh3jd5DGq6PMjxiM6rg9vcR8sTEWm3sI1XfDwWI8OY45J42EbYK5ckZhviDJyYMkPAJ5uRJ3KuKfd4ksvPHsxQ8B4iV8TrYamCfUlEJKUMi4EK+gRqdfYA4cnv78e2cfwYnmcRkSb5U0eG0Aey+fEduIwTODZN5dhvjPtRzsjo4jyQ6gBuZ72F/ShI8Dy/6W2vh/rZHbiNIiKrL8Rj94obL4W6mMcxdc9zB/Dzq7DfFDxsryIiO7cehPrgfvTnFfsXrslxnMjUlv3GMrLQXzQURVEURVEURek6+qChKIqiKIqiKErX0QcNRVEURVEURVG6zll5NBx3waPhkD40oPnhm6T7FRGxSaft0zLy5Otok26X5+2tNc0siD7SLVoWaszGj+McytV+mkOetMERzeUfZ2jk2ZMxNYm66UYDNYMO5TNENCd7lJpzZ0e0rz3VIahrDdI8U+1YuI2FAvphZrcL962c8573ddtwBpx7jh+ZEGdOz8u5IB7pk3M5U0dpkz40zqP2sn/j5VBPHtgJtUvaYD/Do5HSvNMSUBtuYHu0bDzmFrUFm/T2ElM9+ymoEpvbqKnVxpfJN5LRxj0aKnzymqRkBOmQ/jhO8PxkzcBdHl0Hdf8VN0IdWAv+hijTn3XuqTcmJE7mjgX5K5w89onDh3Cu/tnPoK67dwD7cWkIl7lyE+qLj55ADfNzuw8Zq4hIBM+ZO0fJTzdx+AjUvottLJdjn1GW9wT/Nkn94Nl9NId7P+7nuguHoU59cx09vbgfYyvRwzMwiGN5LkdZQ5RXlJXD1KLrVkzXnFx+drvd+DR96hxhxbP/iYjEKW6/TT6pKDTHaIc6nkVOSKeM14V2hOuoU/5E3s/IsiI/V5ECFVK6pkZkPLLp0tQW7OtRxuDR46Imnr2Uic9jJC7keITtteShd1NEpEIZI0eOks+xSN438oty7kVWDkEc4/1LFPP9zMJ+8PKXglY0KUk422ZyJbyvufolG6C2LPP6+OwBvDc60sT7sXoN++jUNF53enrXYF3C8VNEpEgen1YD28LRI3iup2ewz1vs1xnAtjBijxrrnKnjMnzKfkma6AmamEI/6DPbtkLd6UwZ68jT8d598EdQrxmtQr1yNY5/IyPYsWqTeC8iIvKzb7wSak/QQ3Nske+w3Q7kiS1fNJaRhf6ioSiKoiiKoihK19EHDUVRFEVRFEVRuo4+aCiKoiiKoiiK0nXOyqOxmFwO9V7sMwgjU7vZJo2s10KtnEuZAhMuah77+qtQN9vmc9LxiSmoB/rwM/VpnM/48P7noOY5u0s9/VD7+Yx5w2m/psZRxxrS/O09FdJ/kmej1TH9LYeO4jzNnDnAPpF2E/V3Lh0q1oKKiJSK6FngLJTFmuY4zlLZn1ta9Zo43uyxtkhjG5JHI2ibPhfxUbOYp89EHTxPAWm4UzpmcUZbyPehZtSJUV8c1lGr6Xs0r31KHo0W7kf7AGpaZzcUP8PycYv6YpLgG1wX64pnDgs+dQyH9OBOHnXYbTq2vE6r39RA966/DD9TqOJnFvmCOKdjqfA8SzxvtjN5RexU17ziEqgHhs19nKqjzpYsGzJko774qqtxmWGCuuwntmw31tEJ8PyNH8f28fQzu6Guk29o9dpVUN/4iiugrg7gmCgism8PejB2PvE01EdquN9DF66H+ppRrFM2E4hIfx8em9ER1A8HHe7zNEbwNSo0NeQdyjRKybd20tLQCZcnxyUOwnllPnUpcXzcX9cMopKwg+/xcziGORaOR2GK7Y0zWCLbvM67bB0IyEtC17u0g+fBL+Ex79CYWG+ZY3uJvJUJ+0A4G8jwlOE6xxNTv54jT1ZIOTrNBO9nPJ99aeThyBjDOFeJs1IW52iw53UpqLdOSDB3rCrDuD/5Ih7TJDa3b2AQ+2zaxmM0TTlnFt3nPLkZx5WRwXXGOn7h7b8IdRDgdkxP4DonpzGL45kdj0J98CDeexWKvcY6e3vRL9aO6DpO13nLxvuCZ7Y+R6+jh0NEZNUF5KGt4jhdJFuq52L79Gl8qBTN+5cJus/csQu3a3jdVYu28cw9QvqLhqIoiqIoiqIoXUcfNBRFURRFURRF6Tr6oKEoiqIoiqIoStfRBw1FURRFURRFUbrOWZnB4zieD5nxPDTWFktoLOHgIxGRIGZDFpmNyeg4PT0NdW8FzYD5jNC5Gn3GpXXkClNQez4avHIlNHC6Pro1o4y0oHabwlo8XOeKMQzdqtXRNDY+iQbhJMowMlNQ2+5nt0HdW8XAq2IJjd2FPO7H1GRGmBiFrHlkYIoXG+wywobONUnYEWve4EnGuojMxq5pUuylMCqbguriEM3gA6MroB4/sgfqqIHnTUTE99GgNTWJRjOeOIAPY8nFLjm2ZjXUuUrVWOcMTYAwM46GOp8D/WjiAD9Eo66HXUJERNoFNPGVBlZRjdvV24OGOXcGzW3HMgyd0xROWGhiP7EWGXNjw/i7NFiWK5Y1e45iC812PQPY7zeW0CAoItIJMFQuIcNyqYRttFLB/SwW8eRcsBaN2iIizQa+55v/9wmo93jYHtpkSr3q8nVQv+pGDOISCsITERkY4f3AvlTOY7u+7IqLoLZtNpKaZms21/J7OgHuSJzwJAg4ZthGsKU5AUabrknO3DKiZOkDS2eJ5eT3gzZtKx9DO2vCBDKIpzQWWC0K2qSPd2gWhigjvLHoYhsep8lQEgqUzKe4USWHPt/EsSPiGVtExCbTdI5CAhOaYMWYTILOZy1vji9tH98zMTUFdVDFo+WSwdy2qP2mZhtKaJKVvIP70Vo0YUkaLv01uG+4LLn87H709OMxcul+QTL6V08F94fbU28vTyKC93OTU1iPH33GWMf/Tr8G9U+/5mdpHbidUYT1BXTN3b0PJ8/Yv9cMSe3rp/uvMt5HFvM4gUatjiGpjoVjquvRLCEiMjKM12CfLtTT09hPXJpMyaWJLdLAHGNnargd+/fjvh5vLiwj4DDhU6C/aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK6jDxqKoiiKoiiKonSdH9ujwaE7fg41ZVaGPq/dwZCSZgvrfB61me2QwoLqpKEfMoOjLNI42pRaFFII2+Q06ux7GqhXb1LdbpneBod09dUBDG3Lkc8j2YfhVruefRa32TOP3cqV6Bd4Zit6NJoN1KBectmVuE7S0sax6WEokucljFDDlyxS7CaGevfc4xUL4sx5gyxqf5xWM9bE8yYictHUAaifIp/RsRPYFlZf8zNQuw3yDEzg8kREkhkMhGwcRH1nauF2Ox5ud7ODusrth7G95Suo8RcRqZAfp1QexHUK9pvGBGo5Y9JuVvvRCyUi0nvNm6HmULcdT9wP9ZGntkBdP3EC6nzV7LtjV2+EOs2R5nexptlZnsS+cqkixeJsu7Ft0nXTuZcIj7uIyNjQKNSszU0S7HPtNgaHtVPs5z1lMzyqNYXrrY9ju7YjHBOtEI/lcD+OV2lEeuICtjcRkZVrqP+tuArqNgUVpoL74VBAH4dLiYh0Au7T2D48F9st+598CuwsccKViLTI++PEGLx1UldvL1NipGVZYs+ZLzjwzaFrneeYiX2coZZmeA4XE5I30CEdfqON13ARkb4SjR9kFgla2MaLDrY3j/pEu4bnJM64t4jpYOTJk9iYxvbm0rFyyN/SDEyPaWiRh7GEY3lC1+2UbB58zU0yvCZWSmGFNB4s9gYth09odOWgFIqz+50vTcFrrovjQm3GvAa7OTzuhyjcWBy8LszU8Vo1tgJfP7QPrysiIk9v3Qx1tYrtqVLGeseOJ6GOyFuT8/E8Hz2K46GISBjhuciRl8R2cRwplPC85grYNi6/HK+FIiKjw9jG69MYrjdex+uPTe21VMLxLs0KHU2qUL70ZXgfORMsnONOxww8fT70Fw1FURRFURRFUbqOPmgoiqIoiqIoitJ19EFDURRFURRFUZSuc1YejcXzkKekD3Q8XFQub84DzHOUp6RR7AQ0pzdpMY9Oo+av1IPZHSIifhH/llo8cThqTMMAt6E2jZroND2I78+Yv786iHMouy5qADmrw7LxWLFWOFcytcMjq9ZBbdNc41ueQp1hTFkc7GkY6Mc5mUVEhgZQ2x+HqMGLFtVReOb6vG7RM7Ra3Nzsfqekj/fJ3+NOmk17/CjqOf0i6j1HLsa8gBXr0Wtj1/D47B/fb6xj+jDqN8MQt2NoDL02VdLsh230gbBHqDODr4uI1KdI1x/ge1wL+1G+H/dj5JJLoF49hu1ZRKTnQsxrOPTkg1DvvP9HUNs8vz7pl1uszRWR2jien7iI40G6yH8VB8uTo+HIQhSBRaEENmnLKxXTh1KuoI45DLAfNRp4LutN9FuUyI/Tiszvig6eQK3uTAt1zuxbGx5Bn0elimNiK8TzksvIQMnlaSwOcbtCykSJKLulTZk2Ps/JLyI+eXYa1DdyVZy73udxl3wVncw2RNtB16B5b+KZTyHfVdI0nfdJCufj0DXZuPZlfCamLIeUhs04xT4Y0nWlFps+gz7jPOBCI7J1sJ+i2abzQr4FK8NWElFmSoeuTy3yhxbp+unR/UuQ4WFsBHhv4JbI/0k+DyfB1126BqcZX/OmlA/FXhF/sY/SWvrviTthS6xgdj8symmYoKyS/bvNvInB1TTW9OK9zuQUnvv+QWwbY0N47SoVzPPk2ThO7N7zENRvfvO1UF9+5SuhvvdezOZ49jkc/wb6zHvbIEQfXL2B9wHlHjxXbg7H+XUr8D6gUDT9fZyxksvjfh6awOO/6ZL1uABqcC3OtROR1Ob7FfSEevWFMbXdzvB4PA/6i4aiKIqiKIqiKF1HHzQURVEURVEURek6+qChKIqiKIqiKErXOSuPRpom83OTpzxJOS/YMTW2NmkKLdKLui5+JqJ1TDdRGPvcvsPGOoYHcA7vQgk1gZMWrqOniHq7NumPcz7WXoZ2uN3E99g0v3vM2lnSxa5ZfxHUfaNjxjoKRdyPcg9q55ot1EAHVJeq6MkYGUZNoIhIjubHr9dRk7rYY8N+m6UgCFNJ5gS6idD84nTe/AEzb+JAHttPMYf7OzQ1DnW8dx/UORvf7zioyRcRsT3UjLplbPMRnZepo9iGyzQ3u5/DdaTDZm5CXx/ua9kl79PIaqgtagvRccx1ee7ZncY61vtVqA8+tx1ql9pDHNGc8ZTVwb4REZHW9BS+R2jfF/WbJGsO8CXAcWxx5valTVryOOIsCLN98LgZhKgddz08jvkCZVrQmNlom1reoRXYRlavQ11zu4X92vNp7n7yLoQBtvskNg0KFuVNWHR+PWqThRy28zAkL0CGByyiNmWRB6ET4LHg/eLgiSyPBm83fyYOZ9tgeBb65O6y4NEIA9yGAnkhfA89KiIiAbc/ysGYbqCfJ+A7BIs9HeZ9wAxlv9h0qXBdytVI8FzPdPDzoeDrYWi2v2Pj5Aeg05grkl8ih9sQRbjMVkbbODGDWv00j8fCo/uXnMvjFx4rPn8iZv/2aAwJFo178Wnuwc4Ftu2IPTfWnziBWRGtaex/1WLV+HxCXpqIsrqa1K9iytuZrmF2xPoN5jo4Ysl3sB9cdS3f82H78n1sfz1lXGAuZ977eAVcR7kH/Z29fZRVNIrHYXAYPUNpYo7rcYxtstHAeuOleB85NIz3kZMnsG+3yXMkItLXg2P97n07oN65c8EXx2P2qdBfNBRFURRFURRF6Tr6oKEoiqIoiqIoStfRBw1FURRFURRFUbrOWeZopHJynvGEMjB4Du8sHPJt2LZ16tdJgxjTPNSTDdTviYg0mjg//0qKBKgOkm61pwqlRdtguZTPkJEPwlNu8/zCFu0n52b0DK3DbRxeaawj7ARUoz5v5Rh+5uhRzP/o70PdNs9dLiISZsyrvJjFOnzW5C8JrZqk8dxxoPndLY+01BOmftAnXXhnHPMGwgi1mjma29opYV0JTB15uUrekBg10I6Px61noAp1sYznJUyoi7qmR6iPmnRuBvvAYzvRazK+5TGoG/v2QJ0ENNG9iBx6BrWabrVMNbav8MgxqH0XtZ9+2Wx/bdruHOVU5Bf5V6x4uTwazrw/iXMZcrlT5zaIZGQd0BhXq2E2BI+RIXlTHMvss4ODmGPw2tdfA7XvoCdny5NPQb1jK+bDBK0RqC9Yv8pYp1PGcTKgLBfbwe0s9+L7jx3lvmisQvhy5brsLcFjF07hNvD5sG3ze7ZSCdt10KFMkebsNafVWvocIRERsaz560kcRPQSXU9t8/Je8FDzbyen9ktY9P68jW3ccU0f0gz50FJqw7kCjmHtEK/jMfko7SJ9PjGvPY6Hx4LH2ZBylywH9zONcB1+wRxnY/Ym5clzQcfOp2yOiBp1aJttqNXCsdem62xnUf8PoqUfA6caqeTm7v3yMY75SUg5QgNmjtDuPY9DPdCHfsEiHdNRHHpk5BL0m/UUzPaXJ69SmfImxo/hvVGaoK93aBCPeX0Gz9OxcfQ6iIisXnkB1OsvZo8G3o/0VMkv1sFlVipVYx3T05jVkVA/KOTxGvv4o0/jMkt4b5LPmX7PnTsPQH1oP16TJ2cWjm0UnblHSH/RUBRFURRFURSl6+iDhqIoiqIoiqIoXUcfNBRFURRFURRF6Tpn5dFYTCqsDUa9VtYUzw7NpW/TBNusaE5oIQ69n/MoRESOTeD8w0F7CurhDs33L1Woyz2k422hti4QU/sftFGTWqFsjnKFNIArMNegMoB6PitDW9uYoTmrSQfr0uTRg4Oox+vtQT1ejvR8IqZ+3CIN8+J57HlO+6UgaM2IE81qMnt68JjmSIO7IkNju/7qi6HeeQDnRc+PrYC6MIh60OlxPAeV1aYG1S+SxruBunGJUIPbmsF5wY8fPQJ1SHOTt47h6yIi2zj/o4Z6z+nxKfwA5T9wng2fdxGRqIn74VbRBzAwjGaow8fRo9E3gFpcyzXbeNLE/r5qLS6zumJhGWG7LVu+YSzinDM9PS1BMNu2fB/16j09eEzYTyEi0qbcgoh8QTxGcm6PkS+Rmv2w2UC/g2tXoe6r4rG/cD3Ot77x4rVQ735uF9TjJ1ArLCKyjpbBESIVWmeY4n5M13E8k9RsHyUaV8kmKDblLQTkoepQbkGWr7Ddwe3I+XhO07nxP824DiwFaZxIEs1udxrh9ic0r309prFHRBLyceQpp0co4yK1yIcQ4tjBuRwiIomRd0Lji0VtmE51knImC2VLeKZHI7ZxOyLycMUp+iM408vL03HI8FfFNG5y/07pGtyOcOymSBZJbLMN8d8C8uEEi/I9gowcjnPNY1smxJ3zv7zxcryerr30Sqif3Pdt4/PlHI7pXkhZVj24/9U16OWqT2LuVMXHa7SISLWM12D2tx7cjePjSy5HI8g11+B9wAXrq1BP10xvcP8AbodfxHX2VCljxcf9Pn4M25aTMf5Vy3gNPXYM/RO7j+CxqU1h2zm2H1/P53B5IiK7d+HYPjVBWT0DC+NhaiciYl4LstBfNBRFURRFURRF6Tr6oKEoiqIoiqIoStfRBw1FURRFURRFUbqOPmgoiqIoiqIoitJ1zsoMnqbpfMBUmrD5+9T17B+xZJNXTOY8rvmpaGbGNKKEAb6rTqE4fSGapGdm0AT23D4MLOmpYLjeyKhpPvLJiJajEDa/gCbGSg+acFJK/Gs30UQmIlJvoEmx00ZDEofN5Qu43fkimqc93wxMa9RrUFtkmGu2FsyF7Y4Z6nauGegtijtnwF11IQbk2B4ac/s4XElErrryMqhnKniujzfR+NQ5hOap+hSayJpNrEVEmsfQBN06jkbtcApf7xzFdQRNNIUlbTyvhhlYTJPh6YLJLAq+5J6a4YOUhNpotYJmthVknD8cUNgmBWKNrMfzJyKyZgRNee4QGgGnWwtBS5EsT2BfvdGQOJ49fuUy7lORgjjDjNQ504DMRlkOMUXjK5/LVtPsh57L5ll8PQpwsoCBftzuoSGs4wTPbb1ujk/btqJhPJ/Dc3fxpeugrh2dgjohU3shb16aiiXc9zRl4yz2jUIetyEkszRfX0REInqPleI4e/L88LqXCiu2xY5nj0OewvJyNtZhxhjoUMihRYGPEU2q4dCEKy5dE6LMdWCb5QkNohTHOJ9mDuBl8r1ElDEJDIeX8bm1LHw9ICO9JTyumoNglOB2xbwdtM56G834noftMc4IyOXt5rF58SQE5oQ8557x8UAcb7YN7DuE17/9J56Bup03x+iBPrwP2fbEc1A7Odyn1ZTYlyMDc71u9sOxYZykpdnAa+zqC/E8iI+TwoiH91prNlShrlRwMh8RkYDGjQMH8DofBjT5Dt0/W4Jtq93EezERkV4KyV2zGk3r43ncBs+ewgVQsu/hQ+b980pKuL78MpxEqDC2ENbaaYfy6ANnNiOL/qKhKIqiKIqiKErX0QcNRVEURVEURVG6jj5oKIqiKIqiKIrSdX58j4bhyTDebX4+Y3mLiSLUqbG2kzWRnQ5qPUVEbAu1cP39qAXvra6BenoKNYJRjPrjYh7fL7GpkeeQNj+H/geb9KHtNq4jJv272GbYXKuJusGIt4MkpR7pd/0CHhfPJ52iiNRmZugveH4WBwSFgXkczjVrhnvFn9N+rx5G3fgJCuVpTVAAmIg8cs/9UG9+djfU0zU6xhSSGMyglrNTMz0aCQX0xbRdrPP1OqQVTvBEJnQOLMf8biDDUkFvoBCuLP8UbKP5ukV64pi8I40IP3PRG14HdX4F6kODHlNbOxFjX5wkj0xjaiGgKAmWRyNfyOelUDgZ2Id9jAO0bDvjzNBYwMGbPBbwOtj30WxkBPbV8NyUK7wduJ0utanpGfQuWS626RWrUMcrIlIuY7Ddczvx3B3ch8vwSzj+1OrYl/r6zUtTKlNQs4/DZX+LhcfGtnBcLRTMMZDPWUr9rzj3mXS5vqOz0tn/RMTzcX/IPiHFnLl/7J9wM4IzYZm0/z5dk9kzlAW/xyMvieHFpB2xqX06TkbYJ41ZId1LsNeJ+5lNbSfia7KYAcG863x/4ri8TOx3YcYYliSG4Q5KnwMWlxirZInlz27ToSaGzfoU7ji40tzWiQD7+XiA19hVI+g7iAt4rleuxGDQ8SNmgO3+adwu9vM5OfQdNIX6SRGvVaGH93M1Pkci0iaPRoI2Nwl9HOdTB9tKaQS3YYT8iiIiU9Po9+T7SpeCMlcN4DI8l4KkR83xobcH/S3TM7jd9cWrPIumqL9oKIqiKIqiKIrSdfRBQ1EURVEURVGUrqMPGoqiKIqiKIqidJ0f26ORkB4xSUijljFHOWsceV5z/ozjoKYsidCT4bqmSKycQ42f76Aeb/fuR6BuRwehvqT/Yvw8rSPomHNDxwXURDcp88I4FE3SevqoCYwS0/9Qm0J/AGcnsEZVSGvsUs5Eu23uRxSdOrNhcXZGlj/mXLP5kYfEcWc1wtueeBpea9NBjtKM89RGD0q9TueJzm0cYUaBleDrVmTOIc+aZomxPjkH/vzLpPe0BPsEa8Sz/BWce2HZLtXk+6BlWNSYSr1mVsyaSy6BevXV2E/SQdSLjvuonR2v74e6Sf6XrL8lbTr+i7XZzmmdKecE25n9T0SkQ1kyUYTHnXXiIiItyr9pUx2RFyaKcZk89/50zRwr2h1s18ensK61cLvKlIlyYhr7yXQdz0t6HLdZRKSYxzbTpmZ6+DDqi1evxvdPT+N40grN8aVSwWMx1I9je4VzMygbwSV/QSFnZgmF5LPhfI9oziMTZ2SkLAWOa8/nGJBEWxLSyHcyjmGO/H8p6bo5L4fbH3uGsjwaRj4W+x1ou4VyqNiDkaaU3RGZ9xbcj8IQzyMPm7aNG5Ek2JfZHyoiYtG+RuRT5IwSh7wmKd3vZHm42I/CnqzFmVt8rpaC0LtMkrljc7iJx9xLUN+//fF9xud7fHyP7eP92p5JbF8HyDZ6pIU5GitHNhjraAZ4LtshemLzHnpqnQDbW62BGRZlwfHRDbgBm5kmSQ63qx7hsQroHrBaxfGwM22OTeztHZ/AHIyJcWzzlTKOj7HhYxoy1vHcXlxHq4VtdCZdaI9R58zHQP1FQ1EURVEURVGUrqMPGoqiKIqiKIqidJ0zkk7Ny6UWyVNY5sS18XOpiNg2yULo90xzGRHVp5dnsYQrpmlgY5pelJfBU+zylJVZkqF2G39mbbXwZzJjKkSeJo9/rjZ3S9okI2HpFG+X3yYpQgt/Eutk/OzF62Ap1eJ1nDwup5sqtRucXEe86NxEIZ9XajupKSmJ6dwmXHP7otqidfCUryKmdCqNuY3TB3iZ9BOsIZ3KmnqWpVPCy6RVUvtj6VRW3+XjHVD7Slv0kz9N5Ri16Hy1zfYXd2h8oNqKF7bz5PS2S9H+Fq+ntXha35Sn3Tz1FJsiIi3qdx06Diydsm1uo/h6O6Mfdzos0cDXA5JwdGiazZimhQ0CapOW2e5d2k6WxQrLegJ+Py3TVD5Kh6aCbrdxHZ7QsaSrmxtxTzDHiJC2i6VTSTJ7MFtz8rOlbn+LpxXn8SeR009jzeMTTyXL10+HLkY0dJyRdMrgdNIpm9vv6b8P7ZDslaVTrGi1SDqV8v1MnHHsaDtYZsfSqZjaThyyDM9YhTFHMY8h6aLzEXZmF7Ck1+BF7S+iPm9ZNMbH5tgU8b0PSxBpTE2prQQ0rXq7Zd6PJXzPxjJxi88bxSa0ePpvvL9zXbM98nU6IZk134cGPJb5tI2JuQ7ej06Lr8l0v+bQNnCcRGCen6BD8nmqF89if1I6eCbtz0rP4F0HDhyQ1atXn3ZhyvnH/v37ZdWqVed0Hdr+lOdjKdqfiLZBJRttf8pyo9dgZTk5k/Z3Rg8aSZLIoUOHpFKpnP7bCuW8IE1TqdVqsmLFijP6xuk/grY/hVnK9ieibVBBtP0py41eg5Xl5Gza3xk9aCiKoiiKoiiKopwNagZXFEVRFEVRFKXr6IOGoiiKoiiKoihdRx80FEVRFEVRFEXpOvqg8Ty85jWvkQ9/+MPLvRnKecqtt94qN9988ynfs27dOvnTP/3TJdke5cXL6ca6H7edfeYzn5Grrrrqx94u5fxDr7vKUpOmqbz//e+X/v5+sSxLNm/evNyb9KLjjHI0FEV54fHwww9LqVRa7s1QXuRoO1MU5cXKt771LbnrrrvknnvukfXr18vg4OByb9KLDn3QUJSfUIaGhpZ7E5TzgNO1szAMxfO8U75HUV4IBEEgvu8v92YoLyB27dolY2Nj8opXvCLzdW0z/3FUOiUijUZDbrnlFimXyzI2Niaf+9zn4PXJyUm55ZZbpK+vT4rForzxjW+UnTt3wnu++MUvyurVq6VYLMrP//zPy5133inVanUJ90L5SeRrX/uaXH755VIoFGRgYEBe97rXSaPRmH/9jjvukLGxMRkYGJBf+7Vfk3BRQjdLWizLkr/+67+WN77xjVIoFGT9+vXyta99bSl3R/kJJYoiuf3226W3t1cGBwfl05/+9Hzi6/O1s7e+9a1SKpXkD/7gD0RE5I/+6I9kZGREKpWK3HbbbdJut5djV5SfEE533e10OvKbv/mbsnLlSimVSnL99dfLPffcA++5//775VWvepUUCgVZvXq1/Pqv/zqMn+vWrZP/9t/+m9xyyy3S09Mj73//+5di15SfEG699Vb54Ac/KPv27RPLsmTdunXymte8Rm6//Xb58Ic/LIODg/KGN7xBRETuvfdeue666ySXy8nY2Jh84hOfkGhRcnutVpN3v/vdUiqVZGxsTD7/+c+rFHAOfdAQkY9+9KNy7733yr/8y7/It7/9bbnnnnvksccem3/91ltvlUceeUS+8Y1vyA9/+ENJ01Ruuumm+Zu+Bx54QD7wgQ/Ihz70Idm8ebO8/vWvn7/4KsrzcfjwYXnXu94l733ve2Xr1q1yzz33yH/6T/9p/gbv+9//vuzatUu+//3vy5e+9CW566675K677jrlMj/96U/L29/+dnniiSfk3e9+t/ziL/6ibN26dQn2RvlJ5ktf+pK4risPPfSQfOELX5A777xT/uf//J/P+/7PfOYz8vM///OyZcsWee973ytf/epX5TOf+Yz84R/+oTzyyCMyNjYmf/VXf7WEe6D8pHG66+7tt98uP/zhD+UrX/mKPPnkk/KOd7xDfu7nfm7+S75du3bJz/3cz8nb3/52efLJJ+Wf/umf5P7775fbb78d1nPHHXfIlVdeKY8//rh8+tOfXtJ9VF7YfOELX5DPfvazsmrVKjl8+LA8/PDDIjI7Hvq+Lw888ID8zd/8jRw8eFBuuukmednLXiZPPPGE/PVf/7X83d/9nfz+7//+/LI+8pGPyAMPPCDf+MY35Dvf+Y7cd9990J7Pa9LznFqtlvq+n371q1+d/9v4+HhaKBTSD33oQ+mOHTtSEUkfeOCB+ddPnDiRFgqF+c+8853vTN/0pjfBct/97nenvb29S7IPyk8mjz76aCoi6Z49e4zX3vOe96Rr165Noyia/9s73vGO9J3vfOd8vXbt2vTzn//8fC0i6Qc+8AFYzvXXX5/+yq/8Svc3XnnR8OpXvzrdtGlTmiTJ/N8+/vGPp5s2bUrTNLudffjDH4Zl3HDDDemv/uqvwt+uv/769Morrzxn26385HK66+7evXtTx3HSgwcPwude+9rXpr/1W7+Vpmma3nbbben73/9+eP2+++5LbdtOW61Wmqazbffmm28+x3uj/CTz+c9/Pl27du18/epXvzq9+uqr4T2//du/nW7cuBHGyL/8y79My+VyGsdxOjMzk3qel/7zP//z/OtTU1NpsVhMP/ShD53rXXjBc97/orFr1y4JgkCuv/76+b/19/fLxo0bRURk69at4rouvD4wMCAbN26c/6Z4+/btct1118FyuVYU5sorr5TXvva1cvnll8s73vEO+eIXvyiTk5Pzr7/kJS8Rx3Hm67GxMTl27Ngpl3nDDTcYtf6ioZyOl7/85WJZ1nx9ww03yM6dOyWO48z3X3vttVBv3boVxsiTy1CULE533d2yZYvEcSwXX3yxlMvl+f/uvfde2bVrl4iIPPHEE3LXXXfB6294wxskSRLZvXv3/HK5rSrK6bjmmmug3rp1q9xwww0wRt54441Sr9flwIED8txzz0kYhnDf19vbO9+ez3fUDK4oy4TjOPKd73xHfvCDH8i3v/1t+fM//3P55Cc/KQ8++KCIiGGwtSxLkiRZjk1VFEBnoVLOJfV6XRzHkUcffRS+bBERKZfL8+/55V/+Zfn1X/914/Nr1qyZ/7e2VeVs0TbTXc77XzQuvPBC8Txv/uZOZNb8vWPHDhER2bRpk0RRBK+Pj4/L9u3b5dJLLxURkY0bN85r+07CtaJkYVmW3HjjjfJ7v/d78vjjj4vv+/L1r3/9x17ej370I6PetGnTf3QzlRc5i8c3kdl2s2HDBuMm7/nYtGlT5jIUJYvTXXevvvpqieNYjh07JhdddBH8Nzo6KiIiL33pS+WZZ54xXr/ooot0liClq2zatGnen3uSBx54QCqViqxatUrWr18vnufBfd/09PR8ez7fOe9/0SiXy3LbbbfJRz/6URkYGJDh4WH55Cc/KbY9+wy2YcMGedvb3ibve9/75G//9m+lUqnIJz7xCVm5cqW87W1vExGRD37wg/JTP/VTcuedd8pb3vIW+d73vid33303/MymKMyDDz4o3/3ud+Vnf/ZnZXh4WB588EE5fvy4bNq0SZ588skfa5n//M//LNdee6288pWvlC9/+cvy0EMPyd/93d91ecuVFxv79u2Tj3zkI/LLv/zL8thjj8mf//mfG7MAnYoPfehDcuutt8q1114rN954o3z5y1+Wp59+WtavX38Ot1r5SeV0192LL75Y3v3ud8stt9win/vc5+Tqq6+W48ePy3e/+1254oor5E1vepN8/OMfl5e//OVy++23yy/90i9JqVSSZ555Rr7zne/IX/zFXyzzHiovJn71V39V/vRP/1Q++MEPyu233y7bt2+X3/3d35WPfOQjYtu2VCoVec973iMf/ehHpb+/X4aHh+V3f/d3xbZtvQ8U/UVDRET+5E/+RF71qlfJW97yFnnd614nr3zlK0Gj9/d///dyzTXXyJvf/Ga54YYbJE1T+eY3vzkvbbnxxhvlb/7mb+TOO++UK6+8Ur71rW/Jb/zGb0g+n1+uXVJ+Aujp6ZF///d/l5tuukkuvvhi+dSnPiWf+9zn5I1vfOOPvczf+73fk6985StyxRVXyD/8wz/I//pf/2v+lzdFeT5uueUWabVact1118mv/dqvyYc+9KGzmgr0ne98p3z605+Wj33sY3LNNdfI3r175Vd+5VfO4RYrP+mcyXX3lltukf/6X/+rbNy4UW6++WZ5+OGH52VRV1xxhdx7772yY8cOedWrXiVXX321/M7v/I6sWLFiuXZJeZGycuVK+eY3vykPPfSQXHnllfKBD3xAbrvtNvnUpz41/54777xTbrjhBnnzm98sr3vd6+TGG2+UTZs26X2giFjp4t+ClK7xvve9T7Zt2yb33Xffcm+Kcp5gWZZ8/etfl5tvvnm5N0VRFEVRzlsajYasXLlSPve5z8ltt9223JuzrJz30qlucccdd8jrX/96KZVKcvfdd8uXvvQlnUdeURRFURTlRc7jjz8u27Ztk+uuu06mp6fls5/9rIjIvMT+fEYfNLrEQw89JH/8x38stVpN1q9fL3/2Z38mv/RLv7Tcm6UoiqIoiqKcY+644w7Zvn27+L4v11xzjdx3330yODi43Ju17Kh0SlEURVEURVGUrqNmcEVRFEVRFEVRuo4+aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK6jDxqKoiiKoiiKonQdfdBQFEVRFEVRFKXrnNH0tkmSyKFDh6RSqWicuiIiImmaSq1WkxUrVohtn9vnVW1/CrOU7U9E26CCaPtTlhu9BivLydm0vzN60Dh06JCsXr26KxunvLjYv3+/rFq16pyuQ9uf8nwsRfsT0TaoZKPtT1lu9BqsLCdn0v7O6EGjUqmIiMi3HtwqpfLsv20Hn2Bcx4PatsxFWxJDnUoCdbt2Aup6fQrq5sw41P/+r3cZ6zh07AjUft8aqB9/dDPUvQMroX7tW94OdY/XgnqDs8tY59oyvqevpwx1oQ9PwmQdj8Ngfz/USVAz1pG28DOtJIK6GdShPjKNx7bZxG1MUjxfIiLTNXzPZYMh1FV3YbtqzVCufP//nm8b55KT6/iZ175MXHe2XcWC2xYkeHx8N28sJ4kxMqbV7kDtOA7UruNDbbsFqL2cuQ4nxeMetxtQ51xcZpJgP0oT3EbLxjqOzdgbx8ZvmDwX9yPo4HkNAzx2pWLJWCYTRdje2rQMEWpPKX3rZeHnPdccH+KIxgNqs34+B9tzz49+uCTtT2ShDW5af+FCO0nx3E3MTEI9MzVhLCdOcB8tOp/8ZSG2ahE7wTdYTkYMEn/hyG3MxTektE1pL7ZR64Iivt7E94uIpJPUHtbjZ5zxAOp4xwwtgPYj61tTek+Orjk9/VWoO2ETtyHFNujHZht0i9jHhdp9bu7cx0kiO05MLHn7++WPfEL8uXFn+7PPwnuOj2N7s2xzjI+pcVg2HoN8uQfqCy7aCPWqVWtxu3qrxjrKdEyqVby+VSq9p9wGPs+WRd+WZjUNi9oPfcTsJXQcjDdkxYvx33hDqJ/9OF/80yqoa4ptL4ztzfqMvOeVa5f0GvyF22+SQm6uXVl4nXHonjCOePQSkYivC7gMPm9BiOMGH1PPN9u40H2lzaMojQNcp3TdX33JFVAXRvCeUURkeAXe442NjOI20L1F5NA2Rjh+Os22sQ5u4+YofOp+klBjSmJzCQ/fvxnq734Lx5hmZyF8MAg78v99844zan9n9KBx8qeyUrki5crsQHQuHjRc6dDr2ACsGA9+Lmc2Ms/D9fo+NhrjZpLeny/ghaZAqyg5OWHKRdyvSgnfUyzjMiNq2D30ehJQRxCR1MZ1uAk1TA8/Uw/x/RbdAGc9aIR0o1cuYkut0E2yiCzJz6gn1+G67vz5tWhE5gHZzbiRTeim3aWbCMfBz7hU29RWPM88hvygYdPNDN9gJwm2x9M9aNi2OTg49LMlP2ikMd0E0jqy9oMxboATvujifqV0ReDPZz1o2DQeRO6pj93scpfmZ/yT63Ec53kfNPjn46xt47/xW4z6LD//PB86u5oeXC2XLmB0b5D1GaHPWA5v92nO2xmcV14GH3+btokf0uyMdRgSAKq5ry11+/NzecnlZx80PI+ubS72Y8vJ6NfcL3nMo2X69GVKroAPkPmMLykKJfyirViuUI0PM3Y3HjRonEzPwYMGX3N4GekSP2jMb8USXoMLOW/+QcM63YOGY8ppUmMcOPWDhsPn9cd60KA+Swvha1VK/aZUxD5QLNGXESJSqWA/6KEvm8/6QcMxr3WpRfdwxjvoWBoPGnhPmPWgUaIvWnJ0/xwn5perZ9L+zuhB4yRhGEo494TpGDdI9E1dik+iIiI2NTKXLkZByAcbd3J6/CjUh3ZsM9YxPYW/BkwfxIcXuj+XiL41PbLjCagng91QX3uNeaD7ytjIcjSw2j34rVA7om+Yc/SNdGJ+ExC6eDyjFAf8IMaHGztP3w5PHoDayTg/RZe+QabOIIsHfB78l4AkCRa+EXboF542/qITe+YxtGmbw4gfbH16nY6HhQ+6nfaUsQ6fbvJzNMCEIQ0WdPPDN/38S0IQmhfAPA0GIT9k0n536NcIy8L9zOXMh2m+4PGvIkIPWJ0ObnexiPuVZmo6cd/aHfpWZ9HdAB+XJcOy5m+CQ/oVsdOkb+nNcVws4wGNLqTG3Qk9UNPFZjDjZtKnC/xR+gLBeA6hc5EM4hiX5ulCvSfj27Yatoc0oItaGfuB5dP5b3N/Ndt5Sn+zUvxM1MZ2zHePNn9xkPFlmEtHJ+Q2ObfZGad2SbAs27zxnoO/VMt60Igs/iKDbrIC/AW2M3kM6gm6gB5um9cRPjY9AwNQj63BX0VGV+K3wYNDY1AXCng9tRzzZjvhmyqqs36fQIxecfq38APRGfwod7bweLC4q0bch5aAUj4nxfxsu+Ivm/gbc36GmP0jP6jTwxmdqSjG19sBtresywh/gRDH/Gs6fUlu0800jSt16gMDK0yZUJ7G3JTu4WKP7pfpPiGka8f4XvwlQUTEob7nFvA6bdEXDTYrMuhBxOEHfBEJmtNQN1r4K2knXFhmEOL906nQWacURVEURVEURek6+qChKIqiKIqiKErX0QcNRVEURVEURVG6zll5NGaZ1b+lPEtIylrjDI0tiTfZnNJqoearp9wHdbVnCOojh8zZmTwPdWtXXnkt1N/9/vegXj+M67ioB/V85QS3aShnav9dQY+GY6N/QnI4y0acI6NQD37eNKaJWDFq+Dya5ccjc3eB/AUVHxdaLZgCUpeMxnkH9bqBLBzbYAnmjmfCKJyfQMBirTHtTsQGaDHNkxHN3GWnqGFMjAZLZtPEPAaOhe2PJfkReRscmgGI9fIR6Usz7DuSxDTJAh0Lwzfi8zay1jZL0YwLdUhbG5EPIA7JaG/TOrN2hE5ioYifWezLiLM+vwQEnc68IbjUQj3rMPknDmZotI2tZl82HXrHMJziG4KMcbZMemCfmnFA7SUpkH64jy4LAWmvG2bfYk+GTNFMLoM4Pjk5EnB32A9mrMLQq8d0LDoBjtVsMnbJ2JylUbZIZ+7ThkQnZwnL7CPnnjRNJJ0bl7ifnokpkyeXcGjMz9H+DlDbWFXFa1UUmD6QBnllZiZxJsht44eg3rUDlzk0ghr40TGcOXLNuguMdZYqVajZ1G4YY9m1wbr+jGOZpOwvwNcddqd0oYlY9F3wYv8Bz7+wFOSc2f9ERGK+5vL1MuMWwZgdzLhuY+3yBA80BrCNVETE8+k6TgeqSMZtNrFHCXrQ2g28z4yb5n1nkYYzh5YR0wQ/FrWl1hTOqLpr8yPGOiLyT6Q2+SBpIiPfx9rwpPGMCSKy66nDUDfxFhD8UUmcZcLJRn/RUBRFURRFURSl6+iDhqIoiqIoiqIoXUcfNBRFURRFURRF6Tpn5dFIk3R+ruQMaTDAacUipr6YNbdJTEnNLtZ7922FutEhAZmIrBxEz8Xb3/kWqIMO6kN/6srVUL/6qguhtuu4zWXB9HIREctCD4YtlIpLORn5HgwscguYIulZpv48SffheyhGoBTTfOZt1AgWeihUkDIzZteB77EFt9PrXTg2Qc6cS/9ck6bWfJtxKfXWc/E8NTPmd+d5nyNKZWa/REA+A8/GZboZ4TU2dSnOm2g38Lj19JKf59TWp0wi0tw7rHulhXIYUNChjBbbzKgwwuhs1q6T34W1tcZ86WYb5/1gj8ziMM4lykkzqM9MzOukqyn2oQJ5X8Y75snjNnW6/TCyI0jU3MoIXepwe6DXjU9QTkZKMSrWOPktMrJc2LOQzmCbsgZJM5+nXI0a99fTJxFy++iQDpqsKuJzcFdGAKRQllNK60ib0ckXMrZvaeFt47bBfXT2j5TLQC87pKHP0ZiYo3E2l5HpUcihBr5/AK8jTWqztTaOyxOH90A9eQQzoE4cwmwrEZHePvRvVnowjby3H+8LBobw9TyFDCYZIRDc7Nnb5pwuTJPHdmMNGXDg+aLDnZGHd86x0ljsOW2/EZhJFx7O1RAxx3ijT7PvSLi9kmctMtdhkW0oX8L2OLwWPT+5Ml2DQ7xG16bQH1sbN+8BW1OYtZGE6KeIyIPm5HGQrR3eD3V7Ej0bIiIJ+W6b7SbUHbr+FMizwXki7Yx7pInjlE0UkL94UZZYEGmOhqIoiqIoiqIoy4g+aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK6jDxqKoiiKoiiKonSdszKDx2k8H5TFPicj9CvDh+aSeykN0SBjk7ktbhyFenLb/VCvHTANW6vH0NTFYSw3Xb8S6qvWoRGo10fjj1tBE2OcjBnrjG00G8VkRnJ9NA17Ab5/uo77/ey2bcY61lfReFPxK1BHCZqHyvFxqC2/DnVomyaqtLwO6sLQ9VAXhy6d/7c9UxORTxnLOJdUCuV5Q3AzQiOUTca0rMkIOmT0bHXQ9JXSMqIAzVJtOmQVMnSJiMQUFFjtRTNVy6b2RAYvt4iv++ShjTK+GnAdfFM+h/XAAG5DuYRtxyZzeLtlGv1373wW6pQDy8j459EyO3Ssvbw59IQdbONxiMY0v7DQj9IME+pSELbb823NphBMW9iEfXq7p+Ep5iBKfj+10VxGO+dMrITt33zoKDyPJ+mw6hQImRVWR9thT5PpvU2fKeL5N45D1uk1QmLpdQ7NomWkHOiX0YYCGiP4YJ5cxXJZwZM0mTfZstmWzd886YOIiCXcZqmmZVgU9kmZpsZkBbPbgceVJ6eoUKhuuYDXQ7sf9yuKcOzoBHiNFhGpHcHrwZHdu/AzNBHIwDCawddvfAnUQyvQMCwiUqoOQJ06eDB4P7mfGAGwGRMeGKGLdCO1+NC6yzIEpnKy9RuBhXwAMrCMjo5ji2cY6rH2qG2lPAmOiETUhUtFPG+DKzEQsjKAbcGmIN/a+ATUE8fx3kpEZM/2Z6ButzDUz04oRJXCQ9u1SVxgRuAw92cvh9fxNgWrcl91XbwxDRLz2BUKeO+Qy+N2NjuLj82Zh+bqLxqKoiiKoiiKonQdfdBQFEVRFEVRFKXr6IOGoiiKoiiKoihd5ywD+xJJT+pDSWvH2jsOExIRCWN6riExnRNMQT2+51Go63sfg3qoaGrM+ksoTMv7GFry8ivW4+spajunQtSxVRzUwXGom4ipc03J/2BbqHur1VBzuvkR9J48/L0vGuv41Xf9DNQ9fSNQR00M9HMS9GQ4xUGo3f7LjHXkxvBvThm1jLGzELwUJxRyswT0lErie7PnpzWD3oZqL4ZCraKQHhGRg4ePQM1+Cot9BtQ9IgpgS3KmPpl10zYFP5WK6CEqFFEfunrNCtwGSh3z8vh5EZEgwH41PTUF9UsuwxDKXA7buENGkKhj6kNPHMdAoonj6AnyaRlphMemTR4NO29+x8Ehfw4d3niRBjXOCGpaEhaNczwGRpFhjjA/zhLs06yORxuXxpqBnDmEsz8pYcMcl72omWeNvUXaX95vEUHxuIhIQO+pkWeD0/TYL8FGk4y/GV4S2m/XJ38Ba+gDs52n5AtyirgMuzS7nWmSiOAQuySkSTqv/TfCzUjPniamhprHI/a2cePgUMPUx7Ej4zIv7Rb6IfI5vAbbHEJH++F7FBrWwfCz/c/htU5EpH8Ax80VY2uhbnVwu6cn0P/54L2HoS5TAKCIyPpL8Pq4+gIcV8s96IUzNPXkd8nIszND7qhbLO7byxHYl4olSWaYpjkEZL3L4RGPQ3NpHOD7ypjuvxLbHP/sHI5nPf14jS2W8F7BSrFt5Cr4esjezNAMqkua5IGdwTbcotfrE+jzcIXH2AwPLW8INY6I7qeTBtZ5ulZYRniiSN7Bcdrl4N1Fbdg2omCfH/1FQ1EURVEURVGUrqMPGoqiKIqiKIqidB190FAURVEURVEUpeuclUdjMawHPf0MyiIp6+0C1K1Z4zj39YGHvwP1+lH0JWxtoE5fxMzqKNAc8Q5pNWfiKtS7m/j6KtKSjxZRwyYiYiWo2XNIq23RXM/HD++H+l+/+jdQXzmCczCLiAx4uIx4GpfhW6jHc2nuaLf3EqjtkauNdaTF1VB3SC9py8I6YjH1zeeaXLEk/kmNcAPntm626RxYpn4wR/O353Po42g3aRkk6i4U8PNZPqSeHvT0jIxi7koxjzrekbFhqMtl1DOnKc0z7uHrIiLTU+h/KBZQY1osVqEeHcW2MTWDGuh2RgjOhRs2Qh12cN7w44dQc5qwX4H0ypGhNxXxaJ7vOMU232ou9PcoQ1+6FNiWNa9rt+h7mpjlxxkZA8ZM+px9QK+fJmZDvKx1WJRHxJ6KQcpqGcY2FdHnoxzppj3z+6k0ZP8ErXMKz2Vaxm0w8hsyryjJKSrTsyDU32Of+m/H1FoL7btY2G7juRyfOEtgvwQkcShJPNtKDC8gvdfJGJ8428Wh63hvGccOnzwaeZr/f3rGvB4++gSODX09uMzBvj6o6zOYi7Fnz3aojx1FT0bYNnN+Nl6MORj9VVxHtRd1+pUS7keLrh/twPR/7n/yYaiPP7cD6nI/3p/09uE6R8ZGcZsov0FEJEcemITOqm0vjBDL4dEQy5q/90u5B55BuAx7MLibR9QeQxrwvApes0vUtkREcj3oY+wZQn8q5wpZKbbhhDwYNr2/VDSvwXGK90N1ypgIOugFNoYPGv8yx5eI+prhT8HPtJq0zog8QxkNyHdonE7w3iC1F/pVapl9//nQXzQURVEURVEURek6+qChKIqiKIqiKErX0QcNRVEURVEURVG6zll5NBzHEceZ1Qga8z0bk7ObGnmP19bCXIPmgSegHiAt8NiGa6De/hzOfS0i4pEW3CGtnGPjdk20MQ8iLKKOshnshNq2TF2vRX4FO0HtWjR9COpnH/9/UF88hF6Tt7z6SmMdXoLaOYu0i45ThTq2UKOaOqhJjQLMQRARSXPoH0hd1PLDXPfWj23v+bEZGuyXXG5W2+1XUG89MYn7s3v3c8bn2VVyYgY9Qq6DuvEemv+9UkH/RS5nZomsWbMOas9DTekMZajUdqH+OIrIl9BCnWXQMXWRzaapJ17M6tWoHf7Z1/8ULpOyA6IM+8PAMC4jl98NNferDulcXZu0xxk+kIREvjGZHjqLcg/iF4BHQ8gTYGx/Vt4E7TZnCjiny9ngrIQzcMeFo5RxsgLbZBhim4otPLbpKtIkF8x1Wsepd9VJB03DppMjHwktkv1RIiI26btZI57ysaFsl4aRK2H2m7xP7+Bxd+5Qmde/pSFN0oV10zWA5e+ekZEhUiAfVH8/XieKBTzXhw4cwHVwXhb1axERi679g0PoQ5uZRH/dIw//COp6A3XhxSJea17/utcZ67z6ypdCvWsf5v4Ije0l2s8SZS9UCqYOP6VzHlD/rx3H6/yJQzi273kWj9XwKN5riIisWI0+ycExzLIqL/LQLP0VWMQRS5y5MSfhHBsa/1xukBlE9JmEbhId8kX2j2FeSnUQ25aIiFvEz1SH8D6GPRbsZQpDvEYnIY5tzbrpDa6P4/1Hs93AZdA9oVC2Wsx+v9Q8dpzzZfG9LXku2EPaJM9GmXxKIiLFHJ7TImUR1VoLbTjLo/p86C8aiqIoiqIoiqJ0HX3QUBRFURRFURSl6+iDhqIoiqIoiqIoXeesZH5Jmkoyp9E0NdKsDzM/75AmdnLXo1BP73wQ6qFh1I9GPmrlUtecT9tzSW9HWrmU5ituJqjX61io73PJi2BbGXp4B3VsFs0vPL4f5xXf0I/LeOMvvArqvox5msOEtdmkTyaNfOLQHOsh6vOcadKwiojN88zncT7qJFmorcT04JxrklZDkmS2DYz1oZ9kJWmNh6v4uojIjn17oD5Gvo6QNIeJi8fD91HTWO0hD4uI7NyB69i/D31ESYz9pEjn2qV5613SrFqu2WV5u6II+8nRY3iu7r//B1D39lehXkk+ExGRqRr2ozbNC+642D45FyGKSaOaMQW3TfOCxxHP025l/3sJSWVhuviE/BGcm5GeycTyrKM/zW6xRr6TMYI3R7A9WJSTYbEHg4whdgvbSzyB51qK5vdTzqXY31war5JJXKc1hW3UIj13tgeCszrwVc52Ym11zj2DvuRS7hJlcZz0CWXnfJx70iSVdM4bwFklvP9ZlEroK+PPnCCteb2OPjbWeedLZo7BGOnor7/ueqj//d7vQX3kyFH8/Er0Llx66QaoX3rNy4x1jo5gXtEzu9Bb4tPYzvvNx9LIgRERy8Y26lO/qXo0HqSow2928H7l6H7TR3iUMrYuuQL39fIrFvyb7nI0wSSd96bZPHSdyfZwNpePfbDSW4W6NIAejL4hbBulXvRNiogU6G/VYczRSMn7VzvBbR6vdY0ZrCfHMfdFRKQ5je9xqK0YB4s9GZSgxLWISMr33JSrYdgeycMVkv8zIypG8uTl7Sdf6oxU5//thBk5RM+D/qKhKIqiKIqiKErX0QcNRVEURVEURVG6jj5oKIqiKIqiKIrSdc7OoyHpwlzxJMjjuYjTjBwNi/wS0f4tUOcS1NTGcQ3raEroDcY6Uhs1tXGIn5kkHVssqKPk3I2cT7r9DI8Gz2cspJEv0HZefSFqWHnu/DjJeP6zyJ9i6MFpAnj2lsSkiU5MnWEyvRfq0B/CN+QXtN5RuvQ5Bj05R/K52XYVNbEt+TQP+to+9GyIiAxXUU+8lrTEh4+iVnNivEE16pUdCz0sIiLTU6RnJy9Ljk62T/6eHGnC+wfRB2IX6DyLSE8P7hdnb4Qkxgw62BbqdXx/p8OJIyIOzb9/2RUvgXrnU+hDioLjuMwzyL1waR22g5/xF4050TLlaCz2aHAf5C3K8miY2n5+D4+r+GpC2UJHR8250KNh/FtKORlumz0ZpPUdx/Zid2gM9DKOPfW/pEqesX58u0tepeQEzk2f5dEwMkOoL1ns26HcjLyLx8XNuPylpK326D2tOZ1zkpyB/+YcEMfxgj+SNoF9Ba6fcXmn6/bMDF4HQvK1ODQ+dTqoy+5EmHkhIlLtxzGLvQ0pHTvuEX19qKlvNHGbvvLVrxnrLJcwG0Y89KJceTVdywibtjHL78JtknMjOLfEpZAcp4DjWzFv3iM12rivAV3nFttAvGXwaASdtrhzI11E2RAe+ZtyeRwTRMy8nJQ8iPle9HqVqC4X8Lz6hvdBRMiLMD0xCXWzgV6Z+hT2gZmZKayn8bpf42u8iKQhnutyCa/Tfh7HoiSmbCMHj1XYMf0PnOOSkO8x4ntwukfzPDw/7OUUEaHYDHFtHJfDpLHo3+rRUBRFURRFURRlGdEHDUVRFEVRFEVRuo4+aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK5zVmbwxVZI9uDwE0vONc18jT1PQJ1M7YO6SIaugk3BUi0ynoWmKTGx0aA706BwljYaheI8mngqZXy95JLhJTFDAiMKFmu0yeCUx9ATDtuLUjLLZRicEgpwSdgwnpCRlgLREmlTjSYfEZGgRgbzXjJ7LQ7q4kCaJcC1UnHnQmgCMjiP17FtlPIZpmkKnxnuw7rexn2amECD1mQdTWWtDprHRURsMqQWi9geXUpZKpU4sI8mJ+DAPtvsV56PywxC3gY0i3s5NMX6ZEDPOrOrVq+C+porXw/1D0b/Deq9z+6BeuuWXVB3QnNShd5e3E5XaPKIRQbwKMpI/FsC4iSdzwpM7VMbubMw3kGnM6aQJSemPlnF9hKNmuGexRz+bTiPxzVtornx+FEM7wwjMjZW8PNB2zQBdp5Dg2RxPbq/3SE0cTYtfH86heOXddw8v2wqdjh0jY5uGKDZkdfpebhOETMEMIjJONpqzb1veczgURyJHc9eCxLaBjY0exmBhPyeHJn4eWKJCo2ZU1NTUE9SmJmIiEPhsbt374Z6z549UPs+jnljYyuhPnDoINSbH37IWGc+h+fykiuugtp2Tn29OpPwQ/Nv3AZOXbN5PMvHnKPxns3Oi19d+shckSSNJZm7X2kH2Ed5dwqp2YcTDnam89KO8J6udewE1NMTaNzOMjS36G9uHsdDx6NJIWgSklYL+/zUDN4rdQJzv3qK2E8SG69vuQL2M8/BdYa0zLYxtYhIQu2v1cHP2HQ98vn6ROtMbXMikZgm+ij3UxueWrjPsrLCq58H/UVDURRFURRFUZSuow8aiqIoiqIoiqJ0HX3QUBRFURRFURSl65yVR8OzLfHmQpJYrpiQT2HqAAZ4iYjUn/oW1DnyP3AIl0M67KiF+rw0NLXCFoXGtGkZg3nccK+Ey7CTKahLKYYGWhlBYWET/xaGqIXLG8E1FIjlUBBQbOrwI14t12TKsCjcJWY5XYbGOKSQv7h5GOrmouCvWg113ktBOvc/kYz2R2E1HCYkIkJvkT37cP8e234I6pKPwVFr16yGenjQDIHqNFHfyXrlnh70Ib385S+DepCWmdJ3AYmYmlTWH/Op5TCr40ePQt1q4zZ3AlN7GVM40MDQCNSDI6NQrxjB1w/uxWN96JAZ9NVq4X6wPj7oLGzXcgX2xYnMezSShALjqFFmOTYMLTidX4u++ik42CcbLq/T/K7oqhWboPaOUZvpR79E1cLx6sARDFsU0vq6XkbQHemFR9q4jkv6L4F6ewnb4HMtbHO+mP6JcorjqE8eCw6Cm5yagLrVJK21nXH9EPZ94DLDcHYQWS6PRpwsDuzj0FaEQzZFTD+ETW22XEZP2YoV6JfIk9693sKQVxGRRgN9G/v2oRdzehr7/giNFeUeDGmzjqJOP07MntUhP05AOn2+PvDpy7BknAH4ocRoO1jHwqHG5hJTi3ypNM7Zi/bD5gvaUmCls/+JeR5iw6JijtEO+YY88pM1W3jeWgH20RYFTNabpkcopA3xfBw3Kr1V/AD5lppNHMsaLRw3ihXT21Au4zraHfKL2djvIhrvWrUpqOOM0Nw0xnuJkMKp7RA9aL5Px98m/0/ZvH/xq+ite8nQxVBPWAt9sd0x/crPh/6ioSiKoiiKoihK19EHDUVRFEVRFEVRuo4+aCiKoiiKoiiK0nXOyqNRyPtSnPMb8BS9+3bjPPkP/58vGZ+/ON0GdU+FVt9BvZ2dx+egiHwHPI+ziIhPuRilHOrWVpZRb2fZqB9NyAzhxujRiCxTnxdFuJ1uhLrCHAlAmzHq9aZpLnInQ93dX0bNs0fekYj07Gl66lm2szTGDs2fXz/yGNRuZWz+30kdj+tS4HnevC6b20J/X5Xebe4f55VYFs59PbYSsyJKpHHmZI6gXRMmIp14u4PtqVDE83LNtVdCfdlll0N9JlJwnk+fP9QkHeuRI5ibwH6Hbdu3G+twSdvtOliPjqCWOw2wfQyP9NE6zRyXfBHbeF+E56fZWuhXYWhqWJcES+al2azfZ30/1yIiHnVLIwuCPtJfwDbYpCFzIIfHVURkXRH9Mj/Ycx/Uo1XUwF960YVQR6R3nyY9cWiZ2vAqZQWtpkyUTX1j+HrlAqi/WkfttW2ZY/um0lqofRc1yi4dy8c3Pwj19BTm4KSZXjj6G5+f9OT/L49HI4kTSea2kdufQxks+Zx5eS8VaT5/8ttEEZ7rYgH7eWHVCqh3PrfHWMehw+jH6i2jR2xkFNtnpcRZMDhO26Qtt23z2hYluN1GxojjUE3+Chq3s84v+zyM72lpu7gvm56NjHXwkEHXOXvRdtnL0AbTJJ33Qhk+0IhyHiLze+zevgGo3R4cv1ot9tbgeQ3If8FtQ0TEofPEviQ+pvUaXh9Tuk9wyVvTmpky1sneuZiuTyem8P6sRl5Oi9YRZPgfLDLmVsiPnKMstTSP11M/h/2wZxj7sohI/2q8/8hV0Zf6stzCsWo0GyJ/aSwiE/1FQ1EURVEURVGUrqMPGoqiKIqiKIqidB190FAURVEURVEUpeuclUcj77uS92c/4tD87WvHMHPg2Rj1sCIiNoU5NJukMW1STkZPFWrW2HcyptLf/MgjUPPc1i973Ubcpgh19m2LtJyUxxBbrNQXCVkPSlrZR3dgPsPXv4fehy3PHoDasUwN6ssuQa3cm34a92PjKtTfCWltjSmuM/ShLs393EeCcn+RD8SLzTnozzW5XEFyJzNJaG7sdsBty8z5sCi/5PgEzrO//xjWdog6yaKLmsdKxdTHW9Q+EvI/WClqN48fR79EGOI2su41O5yB5l4nLWeaYht2KHcjpm0cHcV57UVE+gexf8ekZR+mHI2kjbrX1avRwxEbwS4iNmlOgwC3y88taFCDZfRonNRec4SFzacqQ0JdoH30yANQp+PKcnTHw5WOFM02eOIQtqkTJ8ahLlI2h432CemroIcjnyPfUWDqhz1qg6sHcbvy5HdasfoiqAee/hFthHnwNl5wKdRsp5g4jtkcFntoOCwh4/zYdBL5HFrz/pzlIYwSEXt2x+MQ+3VPEdtGf495gawUsF8Oj2C/7nTwoPaWsZ+5NuZsZGUlCF2/OpSxJQ6O3TNtfL0RYs6GbZ+6T4iIJCHlndDNwfQ0Xg/sCunwKd/BzVoJ/c2itpLQOMs+Eb4XMdqjiKTkL4gTPP7WomNh2cuQo5EkCx4HY1vp/izM8KiVaGwpY+1FU/QJvM8oFPAaHGQcw7CO5zrs8DUVtzuhgcSjfJ6cT94bMdtGSH7hZ3fth3rvUby3HRjF+7lqP46X0xkRFV6O8tnK6Is7ehS9UUN0f3Ld1S+H+oKNmG0kIlKo4LW/QOvoGV7IWDqbLDX9RUNRFEVRFEVRlK6jDxqKoiiKoiiKonQdfdBQFEVRFEVRFKXrnJVHI45bEsezH/E89AQ4lDcx4Jnz5Edt1Ns5FuvXKTcjQi1cu411mCFRPL5nB9QXrcV5mx25GGrW64lDmlPahsQ1NYEuaTEf23Ec6j/5x/8H9YNb0ZMRG5Nnm9zz0FNQf/uRLVB/7NY3QP3aK1BrF1NugWWkQohIh+awnpiCevq5hddrrQwR4TmmUOmTQmE2xyRqYU5DvYb718ow8AwNUXuKUAs8TfNpO3Re0zx+vi+PWQEipncpCXlecMoqqeM6+dmfdbyWMZe7OQf84UOoD80XMfulXMK+2/FQXzo1g3pSETNrI4zw/LPGebqFff3IEdTPz9TMDBKe6z6mXJdwkSZ9uTwai7eIxx/XIeV+xtc4/Cef5vMne40kNBm/S16HuG0eh92HduM62UxC42yrjRrmDaTdLRZRR/3UlseNdfq07z7lMwQR+YRIB53ScbA81GKLiEx1cMzizJoD49imWnSCuG9mnR+OCOE8hZP5Ucvl0QjCWNK5jBH2c5VIv75uzbDx+TwediPXp9qLHgzfpX7fwXE3jsz2l6boweA2zP5AjoOwHH6dvA9Jhi+ElsHj6rO7sE+UCpjdUaS6UDTbXy6H+8Wf8Xxs8w75sdi7kuXR4HyyhDyi6SJPTJrljznHOGIt5HzF7F8l30uefKMikitS+6JxYpDan0snttnE9jYVml4/zkILU7wWxZzNQdcSy8O6RBlmA304HoqINOl+4/g0LoNurSSl3IwGtdd8jrNlRDwPx79GgMuYCmhcn8T9fOuGK6Bec8kGYx0x+e/SCO+rekqL9jOrHz4P+ouGoiiKoiiKoihdRx80FEVRFEVRFEXpOvqgoSiKoiiKoihK1zkrj0YrTsWJ5zRzNMF4EKIOLhJTSx4EpH2jnIaANIxRjPV0E/VjYWDqQ32SjZVIdNsRXEbHRh2bR9sdCOoMrcj0njz1HOYv/PcvfgPqR/dOQR3bqJm3Kd8hSjKOHekfH3p6H9Sf+NOvQf2p298E9ZuuWoXb8Jypw+8cp/MR4zqdRfPpJ+2lz9E4Ot2WfGd2G6IEj9kEaf5bJzBLQETETkg3TjkZlsX5EqihjVI6PuzvEbNDpaQTjx32IeHrrFfmbwI8DmsQEZ6uvH8AfUn8iZj2I6b2FpAOW0Tk2CGcM7vTi/2ir4e0tQ6KwT0P2zwfW5G5jIBF8DusRUfDWqbvSBLLmtdWR6Q959nV7QwNNreYPI2BNrWXToc02jbqxI9OYUaGiIg3gedvdGQF1CtHULtf7u2H+qdf93O4QPIFHdiLPjgRkTjGvnSY+l+HMmiSwwehrjewfa3sx5wNEZGWhW0ssXD8H1qB2UKWhW3wwLNPQl2bwHnnRURsm8cA7p/J3P8vj0sjDDvz196A9NQe6d0rFcq8EJGeUp7+Qn2ObSw03jQonyjKyFSJqd3TZcTIn+Acnwbp3VlDn2RcHxk+P7yMWh37iEP+sHLJPHatNl77e3spA4LGvHIZx8hiEetyyfSBcIZDSn6DdNG+c+bGUuC6tnju7An1yYMSUt/p6cPrkIhInnxEDt1HFsgDG+awTVvkZ237ptfUvG7QdZzbAudBeOTtonU0aUwWEZlukI+IxjvXx9fDNt6vNGfI7xKZ/gf2BBVLWLdrmF2XkH+lOYPXirBeNdbRoOtJcwbbfLrI32f6S58f/UVDURRFURRFUZSuow8aiqIoiqIoiqJ0HX3QUBRFURRFURSl65yVR6M+eULSOV17IFPw2u5H/h3qqfEjxucrNmrfXKpLVdT0HSLd2mM7cC7sNos/RaRN8rmI53quky63hl6FiZDmYC6OQt3rscZV5Mv/72GoHyFPRuqhli4mb0ChgKdhdGDQWEcvaeAlRv3diUnU/P3Zl/F8rK3cBPXqKXM/Jo+hlnGK9LsT8UIWQjMw568+13z/kR3izmlYB3rJL9E8AbU3bmrXD+zEYzROWSIJ+yUiUnvS/NuSmFrNlJ7dOTcjJmk3K71d0rkeP4L96LltmJ8iIvLSV90Idam3D+qwRV4m0m4GbdSoPv3Eo8Y6JihTZWAA18Hz0k+Po16UvQbtjqlxdxzsBzwNfWGRXtex2RGxRFjW7H8iEtO55RwgLyMep8WxPc6pfR7TOfIMjKJHo9M2++HKIczQuebal0M9VK1AHVAmjevjuVy7Epc3NjpmrHPfgT1QpyT2P3Ecs4X2Po1ZHK0Q20d/caWxjjzNwR+F5JdzcUwbuxDfX+jBcXXbQ98x1lGbxOsDZ9QsN0HYmc+hCAL0yfHc/DZntIjZj2dmsK70oI9gxegaWj8ec87yEBGJbezHEV2m2Q+RxKf2ZKTkycjyPqWcN0Svs6+DzysNu5IvmjkGM3W8fgTkp5qYxFwmznLKTeM4y/4EEZGxUexrQwNVfEPy4+UYdA0nmf1PRCwft9/z0V+SK5selJi22aVBvtXgfCz0AfClzOOLhIj0VnB8myIPRo3WwWNVgXwhNo3K0zPmcT82idtpk19qdBR9cc0ZbEttujCkGdeOsIHrYD9VgXJeogQP1q4tT0A9aJkeiwP7D0HtFdG/1z+0cD8ctMz7n+dDf9FQFEVRFEVRFKXr6IOGoiiKoiiKoihdRx80FEVRFEVRFEXpOvqgoSiKoiiKoihK1zkrM/h93/xnyednDSetE2j2jA6jue8lRdMoUs6j+Xbl2rVQl8YwpOmxf38G6h2TaFRphabZqBGjAeY4hfp1KNitvQtNw0dsNIH1X4yff2oHhvOJiNz7+B6oU5+CpciUs3IVGsw3XXox1ENDQ8Y62OAUddAIWJtEk97RvTuh/sv//QDUfYl57PYdRMPmsRYeq2ONBePfcpgkn9kzIfacYbiUw/2/Yg0e88qgaVg93EKHVYcMqLZL4Uhs9uXHcts8Buzhcl38kEuBfewGb9N5PXL0KNRPPfWUsc6XXHctrsMiMxsZpz2XX8dt2rIFg81ERLY9sw3qcrkH6sFBbLM2ud7bFO4zPGy28Q6FfrbraOJzF5lIk3jpw6pERCzbng/sCwLchiKdWj8jXLFB55tHyfwA9svWBdjv0zKey7xtDuGXr78a6g0X4bg6RIGONgc2tvA8cPCdX0KDoIhIT3kK6pAmvIhS3M7xBl4/UmqDjmNOVsGXK568gY2mHARX7EVDZjVjjGhOoRnc4v4612F5koelIgjakqTx3L9xzE9ocop22wze3L4V+/H4OF7PLrwIzd9VCnOMIg5qNY2xAQXbpTQhC483bA7n8YmGBXFcs83HZCAPI1znzPQUfoD7IW1T2DKvjzZdx10eysmQHlF7LNA4PDOJE5iIiDg0IqxYgRMYWItC+qxlCOyzLFusuWNlrJ0nPokzzOo0JPK5596Wo4Mc0OQD7YzAyIgmyjnduFDgcMYUX281aQKEjOM+TebuQgGN2UMDeL3ccQLvtSybjPQFc/xrB9ifQ7oGVihAst7CY7Nnz16ovQ5OXiAi4lBo9sr12P8rxUXbdRaTEegvGoqiKIqiKIqidB190FAURVEURVEUpevog4aiKIqiKIqiKF3nrDwaj27eIt5cEInXQR3cag/1Y9ZQ1fh8jfTEO5uojfv+P/8Q6h8+tQ/qqQau087QyYZtFAE+vh214fdfhPWezaitm0gwwO+/rKJtfOg5Y51TNdSqWaTlHOxDfd7VV18OdaW/CrXnmCE0rTbq7YI2CledHOnFhzFQbdt+PD97ycMhItKkQJhUONRoQUfI/oWloCOJWHPKUJe27cIL0e8zPY76fhGRXvJxHD+CeuzpE8egTkgPGkWou4zJDyQiYpFmueDhZ3wPz+0EBdt993vfh3rLZgzZuWjtKmOd/H3B9AQu8+D+g1CvWr0C6vFx1IuWMsKqNm3aBPXkBB3fFPdr7XrUem9+8CGofc/8jsMIMyQNaGNmoX1yqNdSsdijEVKqUkwCZMOPIyIW9Zs6hRQma3Cs6JSxX1sp6d0HTS157yrUdQ+QJyNfwM+sWoHheA75rxpNHHuuu+5lxjqf24btPIzw/PgVHI/iI89CfXw3XT8Mt5NITNrrThvH7iQizbCDuuck5DHUHCMs9g+Q7p7D45aaTqcl8ZwXI4zweIRkZpicNENLE+pk5RK2t2IRA/uazQa9jtrxvl78vIjIzAEcf1jLzT40z8Pz5Pro5WzTtS4jy2y+T56kQdey7VvR75kjf12FPJDjh/cb6+BwuempKdxOC8fNXgo/tCp47ILADEwj243UpvFY7ti2sB+8j0tBnKQSzbUhDrJrNvE8zUyYHoChUbx+5fN4TGrk/Gg3p6D2XWobGXewCXkoAuonJWrDHrW3JoWgzjRwP3JF9EKIiKQpjneXbLwM6tHhKtR7duP915Ej6MW0G7hNsyvBsloiXySHv9L9tpfHcd8uYPsUERldgedndO0FUPuLvJm+ES/7/OgvGoqiKIqiKIqidB190FAURVEURVEUpevog4aiKIqiKIqiKF3nrDwa23cdEPukf6COerzyxaj32hfR3MQi8u0f4RzeRyd3Q33kGGVzkMbWsnnOZVOt6dJ8xJt3oP58vI56u/oM6nYvW4ea05lJnHv9/mdQSyciEpFW28/hdr7k8kuhHhxEzXSH9MxxRkYF6wg90hlO0zzhMXkDJI/7les151jvBLjeNCDN8+K5yZfBo5EmDZG5eZ49armOT/pZ3nYRiSw8hja1lYTme7dIW+zQ/Np2bGbFGFNLk9+GrQVbtjwN9b79B6Detm0r1MWyqclPSSv5zNP4mX+460tQ3/TmN0Dd24vLvHjjBmMdQwMjUO/Zhdv56ObNuEzyHTUaqKc/ehgzcURESj04ZkR0DjuLPFo8T/5SAR4Neo3V+1k+A8fH73bqVWzIKct/LVyqS/Ozt13zOHR8/Ft/H86F7lNfabbJm1VHoXiljBt1yWVXGuvMVUjvS5r5JKWslgb6o3wH9ysjokbCDnoqxg+jhy9o0lz2tN2tGuYW1CePGOuwjbAcJJk7p1k+gaUgTiKx5roF51MMDuB57u0x/RO7m3jMJianoB4do3nz12Gf9DwcKwb60dsgIrJtO17XO6SrD8jfmVCuQa5IWnLyOuVyZsZAvYPeypj8Og43KFpni3yWJ06YGRc9nGVFGUc9K1DPXipiPzt2FD0z40dMH8jLrr4Kt+MYttE/+7MvzP87XAafWrvdEnvOj5Am5Emj/Kasm8tWE+87fA+XUSrjONLo4DEv9VahXlXCWkTk2HG8j9y6Ff0QMW035wTVGnhP2KHjXHDMwcl18W8+5X+sWIG+yHf+4v8P6m3btkN95BD6RUVEKpRdtWIV5gA1qV89uWUH1FdcdQ3UF6zDPDcREb+M/b/ch++p9CyMqdYM9rlTob9oKIqiKIqiKIrSdfRBQ1EURVEURVGUrqMPGoqiKIqiKIqidJ2z8mhMjJ+Yn2c8nkE92M4c6nqf2o1aUBGRHcdQn2dbqMXM5VEPyhp5Vsbx3Nmzy0C9XZPmFt9B87WTlE6Gr8FtOHQC37/7SJYuDRcyNIp69uFR1LkFAW6T0LzPcWzuF+cG+OTRyNEcyZLicSgVUN+cY5ODmBkPAXtHFs3BzhkbS4HVac/7dCwPj1mtgXVqkUdFRIo5PCZ5F4+BFeMyHPKh2PR6wudRRKIOaebpPTxH/ARlXtjk6bCogbYCU5c7PY1t8uhh1PW6tMydO1G7eeON10F9wQXrjHW0GrgfzQa2pyQhX8Ag6uM3XYq+j5D0pCIiHfJkuKTbP3h8QTcdZfhjlgLLssU+6dEgLxV1Y0ndjCyIfvIFjVJNzdamfmx4H2LTi9SM8VwVKBelr4JjBftdxqfRx5ZQlkLSMPuWX8Jxk7dr+9E9UG85hD4ii3TPU1N7jXWE47hdJ/ZjFkdEXhPXwzEy7KCHI03MvmRTVoIYuRlz/XEZPGoiIhIE89tUpnnzy+RlCElrLiJSo7Gi3cDr9vgx9BHUVk5BXSzi+6s+HlMRkdpRPLdJHuf7bzSxvbUox8ehc8Dz/Q8Noo5cRMQin2SdMiYSWmYjwGNTrVahvvhS9FWKmL6cZhvbT0r3Ggd2oO4+T9lBg32YLSMi0lNCT0Kzhm1+166FNh9n9P1zTT7vSH7OgxrwtY78ZM3alPH5E0fx2hRHeAwGB7He9FLM7HFonKlPm+1vqobXpsEh9MROTWAfCOi606bzWiRvzpq1mDskIuIfRU8P57bwxeHNb0Gf5LXXXgX1kYPogRQxM28OUQ7Y1h04ZkZ0rxCSN2V4zXpjHR71Nc/D2l10z+Rm3EM+H/qLhqIoiqIoiqIoXUcfNBRFURRFURRF6Tr6oKEoiqIoiqIoStc5K4+G6ztiz3k0EtKOH6uh5jGmzAsRkeogziXsejR/8QTq3Kzw7J+DentRU9ZbQX1o2Ka5+TuoneutoLZ892HUADaapq7Xd3Gdq1bifpJ0VmZmUHfp0rHM+eY84UJ68CbpEAsF1C6GNu5nqYTb6Djm+fFy6B+ISbsdL9YlL4NGOWw35j1CxxLUwz66GTWR69atMz7v5FCjyOfFp97g2ng8rBSPWZSV5UAa+oDek9AyHMryoEgM8fKor58h7bGIyIFDB6E+QZrnoSHUNOdJW5nLkeaeaxHZ/vQTUD/x0Bao3TwdmyZqudesxj6xY9cuYx0T1C8SXIS0F2nwIyOwZGnwnIUxsEWq7Yjk/EFGGETUh21KKuQTIiE419zteBwWETlUxznY2ym2Qc/H81uibBbXJl9Qh8Y8y2z3pTyOWbUWjk8/3P8I1PvqqC+upDg+7Qw2G+vwp6lBtHAMsCjnJqTtTmOss8ZAQ4hv1HMneZksGnYaiz3nR1hH15m+Cmq4O03To8G5F+vWod68VMLxplnH83j4EGrH9+xCv5eISI68SQ3qqzN07XLI+5aj+4JGHa/BLfIciYgMDg5C7Xk4lgQhesLGJ9CLUqKMgmqf6QOxqV94dfRvHjpImV3HMGfDp+Ny1UtMH0i1Fz0KR4/i8Q7aC30gy591rrEcS+y5/XBiPB5RgOcxCqm/ikjQwnPZCXDssQpYj5MHw23geaxUzKwYjzLEOP+k08HjNt2YgDqmQXdsCO8hV1N+hYjIQF8V6gcfwuvl/v2YG7VnD57XwT4cP3soT0TE7JvtAI/F3n17cBnkxauUybOWZOSABXi87QTHEHvRkJs0TH/M86G/aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK6jDxqKoiiKoiiKonSds/Jo5Mq98/P8OzSHd0dQy3Xh+guMz5dpruogQA3f449gpoBHgvWE5jRPM3wCIyOocfRcfE/dQV2bW6S8iTzu196juF/tDN/IQA9q5wYHUN/Z5syBCLchoee9JEPbbZGWn2TX0iY9ruuS9p8oFEyda2OG9HmUM7E4VyLr2J9roqgllj17fgJBffb4BOrS856pD+2QsLrZQK1mtYLazoKNdd5FzaPj8hz7IkIeDMvCOiWvzdQk6nhLFVxmnppbbRL1pCIi27Y9DfUqmue7UKLsjuN4rCYnsd+1Guaxe/yhx6DetRUzDFauxayYJx59HOoOZTFMTE8Z62g38ZzGTTYkJNn/XkIcz13wqZFmO6I+EWXk/KRF8mhYuAybxtXUxv206HUroxvWQjzW4y2cN36FoObYp+3sqaLuuUjHOs449Lynz03uh/rpo+jJ8ShPJp3GvjiZYJsUESkO4ZhWDvDYORMcZIKDZEpeATvj/LApJqV6PsdnmXI0ektl8eY8DCPDVXhtZBj7YLttZj71t6agvuCCNVCnKR5Ti67BLcrAiFLTTzi25iKodx5Ev0RE1oKePmyPfT2oT7cpS4LHKxGc319EpN3G62FIOVQueUgT8tIdO4Lj8uw68DNt8gC1aJ2jY6jlb8zgdk9l7Eccr4bapuvFYptHRtzWuSexJU3mxj+j13MOlekhsQK8F6o38T4kP4CZF4e2YRbJsW3boB4YNjMtckW8TvcVcNyIycd7ZAr7SYG8DSOU7dFfMu+dhnrQBxJehf6b7bvRk/bow+hZG+3HMXdwoGqsI6KO88SOnVDH1MYHy9iXe3y87yx5GR4NB9dhhXhsTuxb8IPWyKN0KvQXDUVRFEVRFEVRuo4+aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK6jDxqKoiiKoiiKonSdszKDF/uHxJkzXUVF/KjvoWlpYBQNXiIiSUChfmSos9iIRo9B/FTE5nARkUIOA/eOHMaglFoLja55Cv9xHTQKHZ1CA00qpsm6QmF4HpnG6jNTUDeaaLqukPmoZ7BqrCOM0HgVN9D4E1B4i0Nm8DwFapXLGPAnInLiGAYOcaBiumgT0mUw49pJKNbcRlgUSFgkU/9Ar+mU23MADaoSodnbp4A+18J1lAt4Xu2MUEqGQ8FCClkKWmg6bE3gefRcNIk1O6YB68iBfVBff93NUO+noJ4TJ3CdU5MYXlWbmDLWMXEUzWxF6v+eh72z0aBJFChoKQ3NY9eZQTN4u4afidoLbS5eLjP4osC+lMzgMZkh7YxN5L1OUmqnVFs0lrD7O2+Z4YoXjqIZd7yDptNmRCFMPOkB9XvH5nZvrFIe2/8U1F9+9BtQn5jCNpaQMbsR4rlPqL2IiDR8MnP34djdU6PjT2GsCfXnLCM9G8TZ8O/MLTJJl6f9VSuleTM4zxlyYD8Gd4aROalDnHD4Ip2HOn7GFjzGaYJtY6ZuGkqPnUADabOB57ZAIaSlnirUUUpBi3SfEAZm25iZwXVymCpfDXopxC1H18sD+3BMFRGxqG10AlxHoVSF2qcJD9pkWGfzuEhGSC7NvODYi5bBY8cSYNsiztyELDZ1IGNrMsbomCYFaVEbDijode0FOJbt24LjzM6ncJISEZEc3dVWSnj9y/ei4Xz9CN4zVqhtjI7g+1evXmWsc2pqCmoOqG21sc1OkwF9716c8ODEcbwXExGJIuwXZQpYXrN+LdTPbsFj8+D/wzF5+rAZmtvXj/eyKQUsHt6+MAlMo232w+dDf9FQFEVRFEVRFKXr6IOGoiiKoiiKoihdRx80FEVRFEVRFEXpOmfl0fiZV1wvfm5Wz5vG+IwyQz6EE4f3Gp+fmkCdLstcHZ+ee1jjF1HIToZE7PARDDRzPNTnjfSj3m5oCMP1Kr0oGhyvo8cjzThiuSLq2oRCdmYocKhMmvkNGzDccGQMg5dERCbGMegm2I+hayFpnAPyw7CA0vFNbbeTw79FpA+1Fwf2Wcvg0UjT+d2wSZ/a6qC2M0lMD4AlFCBEemWSjUtEAX9WCXW8UWAeAytF3WTiYB1R27BIaB1SSF2uQAFvGR4h1tQfOXwE6scf3wx1u43H6rmdGPzTmDCDpMoUNJdbhR6smNoDjwcpBV1OT5hhYuPHcHywYuxspfyClynik7VEOLYl9pxGWWzW82Oby2WEuvkHsF8WLNQDt/O4Xx3S0Ec+LjMRsw3mEjxuO47thrq/gOu8YvXFULdCHFiP13BM/d6zDxrrvPuZe6Ce7ExBTfY7Cam9pEJ9MUt/3qZj00a9dxzisUlZQ26zHyYjGJUHSn7LyWUuR1iaiHiWNR+wGFA/3r17D9QuX09FZGQMvXn1GrbHfXvRv/XkZgxMa1Jg34H9ONaIiEzOoI/MyeE6e3owAM2h8xJH1MaNwEizzbfIe8neOJ/GyLxHfjzy4nSapr+FwxxjHsvL+HqzicehRF7OKgUYi4jMzOB1vtHCfuH4i45lbPpjzjWWiFhzncLm6yPd0CUZyZ4xhRW7No5Ve7c8AfW6jRh8d8NPvRrf/8yTxjoOPoehfu0G+gwSWmf/6mGo+4bRF1ko4n1RsUL3eyJ8Z2GsY9UqDBZ0criOY1N43k/QNouI9FP7WTuE43hcw+vnSIECZWfQ9/HsD//dWEelSn5jGucKi085BVaeCv1FQ1EURVEURVGUrqMPGoqiKIqiKIqidB190FAURVEURVEUpeuclUdj/YoRyRdm58B2HHxGOXIYxVzHD6IuWESkE6CmK6ZMAZ77Og5p3nTS7XY65jzUh4/sgXrVWpzPuFxBbXnQQW+DZeEh6ZAu2LFNjbyTQz1oo4V6O9YqWhYu40c/2gx1sYzaOxGRjRdfQsugN6R47DodrBN6pnQ91v6bf2tbeHzdRXONZ2WYnGtcNzevs+5YqPWcIk3jjn1m2yjSPOfVCmqHrRAPqkcabpcyDSzL1MgmCWXB0IkydK2ksefsmJDng3fN81abwn3/7re/B/XRY+jn6e9FHeaJQzhnfMEz/S2s3bRoP0Nqf6zz79Ac4DaHAIhIoYDeJZLzir1ou+zlsWiIbYk4c6fUpeyQKMFjUHUxL0BEZKwH52DvLeP41AhR132CtLuTRXx9pojjl4jI/bvRQ2HT/P3s0RgpVqH+4bM4//r3dj0M9YE6ZqqIiMQO7rtH3qKwSRkW5PFz8uS/q5kn2CLPRb+D+UOVIi6z3cJjlUacq2GOYQmprXmd6cn+agzAS0PUaooVzY7DCQW1cO3E5uW908JzP34MvQi1aex0Tz+N/q0W5ZvYljke9fdgLsHatehBnGk0T1mz94n9FnZWkAvB2Rt8DQ4pq8N1yA/GvksRKRSwP9cb7AuMqcZ1+uSLbDbQYyQisnc/Zj3ZDq5z1QUb5/8dhoE8/eRDxjLOKUksksxlWZFHha9tUWz2YfZ2WuSzOrFrB9Qzx9AzVKpg27L5gikijo/jQhSS34buI9s0LlSo20RtvL6y90ZEZHQljuOuh9fcE5O4n4lH9750W9lJzHWUC9h+WscxNyepn4C6r4T9JiLfiG2Z44Pv4Dpc8u26i86xa2uOhqIoiqIoiqIoy4g+aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK5zVh6NZqMuydzczTwneUia7Hwe9dYiIh7NZe2SdpglfVEHtXOFHD4XrV8/YqyjVMZ1rFg1BnW1H2uHNKauh/OCR23UHrtphrchh9rEToD6OtdFndv+fajfm5pEHXa9gdo7EZFyEfM+imU8dpzHEJG3JCEtY5KYGvkc6fGa7C+Acuk1yn6uMK/PbcW4/U3ypOw+aGocPR//1lvBNptLUdPokIQ75+Ex9zzzOd2mZ/dCDjW2vRWcPzuXJ98R+ZJmpilvIkMXOTX9NNQtmt+6UsV1eikuY2QQs2V81zy3LumLXfIZpeQ16cS4Dc06egnqVdOH1B7Gzxw6gPN+N2oLOtcoXR6TRhyFks61QT+HY0FPCfMBRsp4XEVESh5pv0+g/rdEx77k43Fa0cbPHwnMdj7ZwTbTofHp0T049/zkDOZk7D6BHoxjDRyveL58ERGHMkRCzjmhK01KY3tK45ldM/1PFQvb4KsuuBzqcoDH7thBHEenGzjOHp0xs1zqHfZo4DJPJvmky+TR2H/ggLgnPQsO5To4eJ7zRdSqi4h0Wnhc9+7ZA/XkJB6TMMBleh6eg56S2Y8vuRhzWX76p18D9b0PPAD1409vhTpfRO8cezL4nIiI5HzKK6KbiZgyJ3rK2I8GB7CvZq3DuF85gv1iso6+wIF+vGY7Do6ZM3XTo5HP4X2Tk8frh7fo+pE4pj/rXONYljhzxyYm/xLZdiXl3BoRw4TokK/IjdFP0T6GfXZizy5cXC7jPtMYQ2lsisk/2MCcM5cu/MWeKtTNjIyLp7bgtSolb2VjAr0mR/bgGNtMsG0MeOb1rdTETLd4Cpdhsf/FxWMd07jNOWkiIkkT2zDdnojjL/SB1AgZen70Fw1FURRFURRFUbqOPmgoiqIoiqIoitJ19EFDURRFURRFUZSuc1YejSTsSDInd6Npqo05fnnOaRGRnh7Uioc0t35CuraUdN4rxnAO+huuv8pYh5ejPI/xKagPHzyA25lHPWhzFW53I2GdG26TSFamBZZtyvtYuYJ8I1XUDO7caWaQtGhOeJ89MMZ871iHnGGS4dFgXw2/Y/E55/O/FPiuJfac7tMJaZ50nhPaMjew2URNa6NF2Q4ki0wiynER1Hq6iZk3kaesjQplkwz0oua02IvtLSXvSbuGOsp2YOoqiz2ok+4hz0WjjbpXj/w8BY901qk5LPC+Jy5tB7WnnEXHhvwMNhtgRKRcxvY3OT4O9fT4gqY5XoYcFxGRYr48nyG04eKN8NrAMOm8MzYxblNuD3mLODzEIs9O3KRsl8DUKFdtPNa1PK7jRB3n6s+vJE1zBZfph7i8IDL9Ex3KI+L2wfPdW+TxSkkM7PSZeUWb0kGoV9IyOwFq3tcNoGemSf2kRv1CRKRBY7VF/oB0bg7+dBk8aiIizSCWkxYNHuMpHkCS2PRz+S7u3/Q06s0PHTIzUhbT14fHtKdsnqeci222RTkEAV3X2W8VhLiNPnnhivkMn6TDfkKsW9TvGgGee7s+BTVnd4jI/LXnJKFQdhX5VJsdrP08+kJCMfuuleJ9lE1dLVzk64jCM88x6Ba2vXAN5uPB8SZeRh4T3zdYfJdBbcOn1z3KKooyPGqcUyaUJ+PSvUEyg/6JDuVj9Y8O4zY45r3FUw/+AOpGDdv84AAu45K16C+28+inSmvoFRYRCfdjpo1PXsuUPEB8Y+r6+HrQMX0gSYz9hL2+vr1wv5JG5r3w86G/aCiKoiiKoiiK0nX0QUNRFEVRFEVRlK6jDxqKoiiKoiiKonSds/NoRJEk0azujueZtmge9XrdnGu4SPN6t9uoxeztRQ1j7xhqntetXQk1a7hFRMoVXEZtGjXx4ycmoT5+4hmo0yZq6SbJC2C5GbpI8nEEpKMvFlF36eVIvN0mnWFGVsKJcdLs2VUoc6TxYwUxa9rTDI8G65FZ52otElguh0K5kPfn9fEdG70NIenGYzEF8illpoQxC0Zxr3Lkr0gCmmM/zfBo5EpU4zJiWmdA89qX6fOJUP5Ex5w7vVXH9pOjfhZF+Jm+Iuqsw4j08pF57ELSs5t6cDw2OcrMCVM6PxkmH87NaTawH0TRwmeyPEZLwXUvfan4c/t20boL4LWANKu1AMc3EZEOnU9Dr07LiFv0/iYex6Rt6mwtyiwptPE4JsfxM+E4aZRJ6ttLvrRS0dTIRyXKMcAhT1L6Siuh/lkjbXChSHkjInKhjR4Nl45d6mDtkra/leDrRtaHiDhy6syGxDrp0VgeCgVnPkcjpT7EvgI/QyPvWngMVq/Aa2zew/PCeUtlyp8oZa3DxXXMUE5LQP2CM1h8GndL5P8sF03/5/Q0ZiGE5G3KU56RpNjI2y18f4ZFw8iZKuQ5i4OyYEjrzzkHrmt+z+uQ18Qlk4a76N7AyrhPONfYYol9MksmYR8WvjcWs3+lMXue6DOUq2EYYA3PlLmNfGngq1mOjnFE3q5WA70zHrW3nG/e/ZTo+jY9hfembfJurl+xAuqxtaNQ2x0zA+fZ2j6o6ycwu8Nh3xtdpH2HfZZZHg3ywIR49OJwoY3H6tFQFEVRFEVRFGU50QcNRVEURVEURVG6jj5oKIqiKIqiKIrSdfRBQ1EURVEURVGUrnN2ZvAkkDieNZiwSY4DvdLIDFJxfDTZcHDKhvVroe7rQfNVq4mmnekprEVEggjNbb09VagLBQzoS2I0uzyx8xjUjRa+zmYtEZGUw6jIFZV30dzWU8TjwIFG/QMUoCYizSYezyYZlhwPa8ti0xTuRxSZRiDbwc94ZGTuNBcMwUm69IFpA71lcedMVW6bw7rQGBdGGYZVsnA2aTICKybzlJFAhJ+3YzOsyqOgOsOkTobyDocIptimEzJjWY65X0mIpqzp42hEK1TQWDaVx+1u1ShsLTQD2dj4l/BXFNQeHA7hovCwNDb7UbOG650cn4HaXRTEZFlm+10Kyrm85PzZc9Cu47nKUX8ZLeFYMwv204COU4fGjiYZ82fo3HgZoV0BhZPF1MaEgirjJvaDtInLLAa4TRwaKCIiITaIhIyuFpmG3RwdB/Lquq7ZtxLB68E4TXLgOGjO9WmsnmyiYTjIaOdZQW2LmQ8YM1Jal4aN60fE92Yv2zyhhzF+exnjk0fXbacfasdZD3WJTPk+hX4lGYZ6z8Pz1A7J7E3nxScTa47M4cP9uI2+b46Bz9H4z1GMjovb5Hq4X65LoW6eeWuUpzbr+Xi83TybvfFY8UQhhYI54UG5VKEa15nPL3SUTqcj/2Ys4dySysJECHwPyFMkZE04Y0yjQIvgeyeejMCh16M4y3CO/dqmAD+H+gn35XwZg6V9jyaeaZuTfPSW8T3TZBi32zghwp4tGPDXmsR73/VrMZxaRKSvFydxqZ84ATXf41lkBudJF3jCFhGRFt0XRnT/EizqZxwCfSr0Fw1FURRFURRFUbqOPmgoiqIoiqIoitJ19EFDURRFURRFUZSuc1YejTSNJZ3TFMfkbWB9+8YNqPUUEel0UNP16CObod67Zz+uj/R3rEEt5FG/KCKy9yDq1nzSTa9ahVq4fBH1eC6FW9kt8oFY5iGzSHPKOt/6FGrNS6T/dCjNaoA0qSIihw/hfnU6qJ2rcPANa+qT03sqOPwmIT1l8jz/XiquufxSyc1phGsdVOFyYNxMzQyMrJG2ssW63hr6YAoU0OSRDyZsmRrUdgN14xYfKeo3thGWx8uk88jJZ2KG5zmkvWStcG0a97POwYzGGkxs0txbpNVO6djGFGjUapjegriD+5bz0VtSWhR8GcWxCGVYLgVT4+PzgX0zU1PwWr6Ix7lSMkOXesi3kScNfI70wOUcLZM0s53Y1Ml2iuT7KeAYFie4jJA8PuxbS8lLl6VRDtnn0cH24JNNxG+SFyIgj4exBpGWhe22Q34oh46dRS354CR5sjL6kmvTmGckglnwf0vNiuFeyc+1Cd4y9lG5GRrsnjKOYeUyttGcj2NeLo81h+nxOCAiEtK9wJGj6I0ZG6zi6wcwMDIM8DxHHWy/vmOOu8MDeB23rF6oOWwvX2DvA9b8fhGRQgHbl5/D67iXJx8SHat8Do91Pp/l0cDxoUB+OnuRzr7VMvvhuca2LbHnvIs2eRjZ95lmxFpaltFq6XW6HtJ1JaGxK7Mbsm+IfHAO+4vZM0T3mZ0ZbL+1Jt7PiYi0ptEX6QmOqXkKXozaGCR9/FmsO0cPGOswvE3kl4oNvwr55OhYu+xVEdO/EpJHNFwU0sf+01Ohv2goiqIoiqIoitJ19EFDURRFURRFUZSuow8aiqIoiqIoiqJ0nbPyaARBLJY1q8viObpT0rJmzRHtOqjpWrduDdQlmkO6HdAcvh3UdfMcvyIiieDfak3Uvm3Ztg1q3z+N7pL07WFiaqLZk5GnecTzJTwWTfIC7D14EOqZjPmJG3UUORdJW2vRHMlCmng+P6b2WCQmbaNNWRxg4sj4/LlmqFKS/Jznppri/rOfJ+6rGp/vkL4zojm6A/JXtEm73qAMjKlxMyvGozm7WZNqk6HCjrG9GQ4NmzwdGbpyVqpyxgn7ddL01BkU3FYyVmEs06K8hyTgOdVpLn2bghNEJHRoDm86p9GivhdlzN+/FFS8VHJzeSpBSuMRjU/ToamhrtVwPAqE2gvpuMsVHBP7KqhFr2bovFOHxizKXgloXG3lsJ1HecrNcPHcdiinQ8Q8Vy7lFjh1XEd4AnX3YQ09V/GEqYNOaL0h9S2L9rsW4zJrdfRt8Zz9IuawZvO0/9byejQKhfz8GMh6ds604GwIEZFSEdtXgXwErPNuzOAxa5EuP804hmFM54XGvEsuwoyAwV70U3QoB8Gla3JWjgb/jT0Wrovb4Lkp1eSbdE3viZEdxtdch8d+fN22XarN/XDoPZzxYC863tEyfE1s2/bzejTYC8g+XhExOliWjwPg6yf5FKysPDDONePrn3HfSPdG5LeY3IPraLfN635MGT158hG5lCvk8a03eSGShukx7TjURqn5seeCx2Tjno/bb8Yy0pTy8RbdM2XnpGSjv2goiqIoiqIoitJ19EFDURRFURRFUZSuc0bSqZNSis4iaQBPl2rILbJ+UiXpCU+ryFIormP6mcyczkskEfq5KD71NK9GfZbvz9pO3i+h1w2Zz2nWmfU3PhbGsQxPdywzpFP0Hp4ydvE2nJxKMVNm02Wy2l9A8iA+prztIiKdlKU4NG0nSdaCiOQeIR3zDOkeH+fTS6fw8+dEOsXHqgvSKd5Q6zTHnzbBqEVMORRL+aLYNt67FO1v8XqCRf0qZBkA7ZNtmztpJ3ggeZJfy8K/dDok5/N5+uQM+U+MywipHbN0qpPS2EFyjZhkcSxhFcn4mZ6amBPwGEnbSONXVt9KSFLD0+7ysQhjlkqewThrzPGdPf1mvITj3+L1tBdNEX9a6VSGdMWnqdVZymJcZ3g6brqun4l0KqQpvNvUfjo87tJ5i+k8Zx1y/ltKbcGl5kSKVYlcmgL1x5FOUX+3SMJjSqfM83N66dTCMk9Ob7uU1+DGomn1Ox0en3mcyJj+lHbZIm2iE/PYg+vo8DgSZRxDvjelqWUT+9TSKZfGQ7eF7ZXbr4gZ3RDSdka0nyw1lpAvqMYqxCI5FkuneD+imJdJ9w4Z7S8w7nH4BmVhma25fTyT9melZ/CuAwcOyOrVq0+7MOX8Y//+/bJq1arTv/E/gLY/5flYivYnom1QyUbbn7Lc6DVYWU7OpP2d0YNGkiRy6NAhqVQqxlO9cn6SpqnUajVZsWKFYQrrNtr+FGYp25+ItkEF0fanLDd6DVaWk7Npf2f0oKEoiqIoiqIoinI2qBlcURRFURRFUZSuow8aiqIoiqIoiqJ0HX3QUBRFURRFURSl6+iDhqIoiqIoiqIoXUcfNM4Re/bsEcuyZPPmzcu9Kcp5iLY/RVHOZ3QMVP4jvOY1r5EPf/jDy70ZLwrOuwcNbTzKcqLtT3mx8pnPfEauuuqq5d4M5QWOjoGKcn5x3j1onI40TY10Z0VZKrT9KYpyPqNjoKK8uDivHjRuvfVWuffee+ULX/iCWJYllmXJXXfdJZZlyd133y3XXHON5HI5uf/+++XWW2+Vm2++GT7/4Q9/WF7zmtfM10mSyB//8R/LRRddJLlcTtasWSN/8Ad/kLnuOI7lve99r1xyySWyb9++c7iXygsVbX/KC51TtamPf/zjcvHFF0uxWJT169fLpz/9aQnDUERE7rrrLvm93/s9eeKJJ6BtK8pidAxUXog0Gg255ZZbpFwuy9jYmHzuc5+D1ycnJ+WWW26Rvr4+KRaL8sY3vlF27twJ7/niF78oq1evlmKxKD//8z8vd955p1Sr1SXcixcu7nJvwFLyhS98QXbs2CGXXXaZfPaznxURkaefflpERD7xiU/IHXfcIevXr5e+vr4zWt5v/dZvyRe/+EX5/Oc/L6985Svl8OHDsm3bNuN9nU5H3vWud8mePXvkvvvuk6Ghoe7tlPITg7Y/5YXOqdpUpVKRu+66S1asWCFbtmyR973vfVKpVORjH/uYvPOd75SnnnpKvvWtb8m//du/iYhIb2/vcu6K8gJEx0DlhchHP/pRuffee+Vf/uVfZHh4WH77t39bHnvssXkp6K233io7d+6Ub3zjG9LT0yMf//jH5aabbpJnnnlGPM+TBx54QD7wgQ/If//v/13e+ta3yr/927/Jpz/96eXdqRcQ59WDRm9vr/i+L8ViUUZHR0VE5gelz372s/L617/+jJdVq9XkC1/4gvzFX/yFvOc97xERkQsvvFBe+cpXwvvq9bq86U1vkk6nI9///vf14nseo+1PeSFzujb1qU99av6969atk9/8zd+Ur3zlK/Kxj31MCoWClMtlcV13vm0rCqNjoPJCo16vy9/93d/JP/7jP8prX/taERH50pe+JKtWrRIRmX/AeOCBB+QVr3iFiIh8+ctfltWrV8v/+T//R97xjnfIn//5n8sb3/hG+c3f/E0REbn44ovlBz/4gfzrv/7r8uzUC4zzSjp1Kq699tqzev/WrVul0+nMN8zn413vepc0Gg359re/rQOc8rxo+1OWm9O1qX/6p3+SG2+8UUZHR6VcLsunPvUplaAoXUPHQGU52LVrlwRBINdff/383/r7+2Xjxo0iMtvOXNeF1wcGBmTjxo2ydetWERHZvn27XHfddbBcrs9n9EFjjlKpBLVt25KmKfztpB5ZRKRQKJzRcm+66SZ58skn5Yc//OF/fCOVFy3a/pTl5lRt6oc//KG8+93vlptuukn+9V//VR5//HH55Cc/KUEQLOEWKi9mdAxUlBcn592Dhu/7Esfxad83NDQkhw8fhr8tno97w4YNUigU5Lvf/e4pl/Mrv/Ir8kd/9Efy1re+Ve69994fa5uVFw/a/pQXKqdqUz/4wQ9k7dq18slPflKuvfZa2bBhg+zduxfec6ZtWzm/0TFQeSFx4YUXiud58uCDD87/bXJyUnbs2CEiIps2bZIoiuD18fFx2b59u1x66aUiIrJx40Z5+OGHYblcn8+cVx4NkVlt8YMPPih79uyRcrksSZJkvu9nfuZn5E/+5E/kH/7hH+SGG26Qf/zHf5SnnnpKrr76ahERyefz8vGPf1w+9rGPie/7cuONN8rx48fl6aeflttuuw2W9cEPflDiOJY3v/nNcvfddxsaUuX8Qduf8kLlVG1qw4YNsm/fPvnKV74iL3vZy+T//t//K1//+tfh8+vWrZPdu3fL5s2bZdWqVVKpVCSXyy3T3igvVHQMVF5IlMtlue222+SjH/2oDAwMyPDwsHzyk58U2579Hn7Dhg3ytre9Td73vvfJ3/7t30qlUpFPfOITsnLlSnnb294mIrPt66d+6qfkzjvvlLe85S3yve99T+6++26xLGs5d+2FQ3qesX379vTlL395WigUUhFJ//7v/z4VkXRyctJ47+/8zu+kIyMjaW9vb/obv/Eb6e23356++tWvnn89juP093//99O1a9emnuela9asSf/wD/8wTdM03b17dyoi6eOPPz7//s997nNppVJJH3jggXO8l8oLFW1/yguZU7Wpj370o+nAwEBaLpfTd77znennP//5tLe3d/6z7XY7ffvb355Wq9X5tq0ojI6ByguNWq2W/uf//J/TYrGYjoyMpH/8x3+cvvrVr04/9KEPpWmaphMTE+l/+S//Je3t7U0LhUL6hje8Id2xYwcs43/8j/+Rrly5Mi0UCunNN9+c/v7v/346Ojq6DHvzwsNKUxJBKoqiKIqiKIryY/G+971Ptm3bJvfdd99yb8qyc95JpxRFURRFURSlW9xxxx3y+te/Xkqlktx9993ypS99Sf7qr/5quTfrBYH+oqEoiqIoiqIoPya/8Au/IPfcc4/UajVZv369fPCDH5QPfOADy71ZLwj0QUNRFEVRFEVRlK5z3k1vqyiKoiiKoijKuUcfNBRFURRFURRF6Tr6oKEoiqIoiqIoStfRBw1FURRFURRFUbqOPmgoiqIoiqIoitJ19EFDURRFURRFUZSuow8aiqIoiqIoiqJ0HX3QUBRFURRFURSl6/z/AfY5SwBcxW8jAAAAAElFTkSuQmCC\n"},"metadata":{}}]},{"cell_type":"code","source":["# Зададим параметры данных и модели\n","num_classes = 10\n","input_shape = (32, 32, 3)\n","\n","# Приведение входных данных к диапазону [0, 1]\n","X_train = X_train / 255\n","X_test = X_test / 255\n","\n","print('Shape of transformed X train:', X_train.shape)\n","print('Shape of transformed X test:', X_test.shape)\n","\n","# переведем метки в one-hot\n","y_train = keras.utils.to_categorical(y_train, num_classes)\n","y_test = keras.utils.to_categorical(y_test, num_classes)\n","print('Shape of transformed y train:', y_train.shape)\n","print('Shape of transformed y test:', y_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"3fe_3k8Uee4D","executionInfo":{"status":"ok","timestamp":1765239870538,"user_tz":-180,"elapsed":455,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"d61c0026-2f06-4878-9b1d-12580ea9d18f"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of transformed X train: (50000, 32, 32, 3)\n","Shape of transformed X test: (10000, 32, 32, 3)\n","Shape of transformed y train: (50000, 10)\n","Shape of transformed y test: (10000, 10)\n"]}]},{"cell_type":"code","source":["# создаем модель\n","model = Sequential()\n","model.add(layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\", input_shape=input_shape))\n","model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n","model.add(layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"))\n","model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n","model.add(layers.Conv2D(128, kernel_size=(3, 3), activation=\"relu\"))\n","model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n","model.add(layers.Flatten())\n","model.add(layers.Dense(128, activation='relu'))\n","model.add(layers.Dropout(0.5))\n","model.add(layers.Dense(num_classes, activation=\"softmax\"))\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":504},"id":"QV8mqAIvep1E","executionInfo":{"status":"ok","timestamp":1765239877984,"user_tz":-180,"elapsed":5142,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"a1164ef1-6c80-49cc-f2ee-f33f8599869e"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n","  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential\"\u001b[0m\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │           \u001b[38;5;34m896\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │        \u001b[38;5;34m73,856\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m128\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m65,664\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)             │         \u001b[38;5;34m1,290\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">30</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">30</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">15</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">15</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">2</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">65,664</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,290</span> │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m160,202\u001b[0m (625.79 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">160,202</span> (625.79 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m160,202\u001b[0m (625.79 KB)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">160,202</span> (625.79 KB)\n","</pre>\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"],"text/html":["<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n","</pre>\n"]},"metadata":{}}]},{"cell_type":"code","source":["# компилируем и обучаем модель\n","batch_size = 64\n","epochs = 50\n","model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n","model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"eRutWFYse5eZ","executionInfo":{"status":"ok","timestamp":1765240059049,"user_tz":-180,"elapsed":169608,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"e835fa53-6fb0-4a3d-93dd-2e5da962f61e"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 10ms/step - accuracy: 0.2665 - loss: 1.9447 - val_accuracy: 0.4852 - val_loss: 1.4141\n","Epoch 2/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.4775 - loss: 1.4451 - val_accuracy: 0.5650 - val_loss: 1.2281\n","Epoch 3/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.5397 - loss: 1.2815 - val_accuracy: 0.6018 - val_loss: 1.1288\n","Epoch 4/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.5841 - loss: 1.1718 - val_accuracy: 0.6170 - val_loss: 1.0916\n","Epoch 5/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 5ms/step - accuracy: 0.6163 - loss: 1.1004 - val_accuracy: 0.6434 - val_loss: 1.0126\n","Epoch 6/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.6398 - loss: 1.0222 - val_accuracy: 0.6596 - val_loss: 0.9966\n","Epoch 7/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.6629 - loss: 0.9663 - val_accuracy: 0.6488 - val_loss: 0.9930\n","Epoch 8/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 5ms/step - accuracy: 0.6819 - loss: 0.9165 - val_accuracy: 0.6808 - val_loss: 0.9155\n","Epoch 9/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.6976 - loss: 0.8693 - val_accuracy: 0.6846 - val_loss: 0.9188\n","Epoch 10/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.7092 - loss: 0.8309 - val_accuracy: 0.6960 - val_loss: 0.8803\n","Epoch 11/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.7252 - loss: 0.7833 - val_accuracy: 0.6866 - val_loss: 0.9156\n","Epoch 12/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.7389 - loss: 0.7513 - val_accuracy: 0.6980 - val_loss: 0.8891\n","Epoch 13/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.7489 - loss: 0.7227 - val_accuracy: 0.7106 - val_loss: 0.8728\n","Epoch 14/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.7589 - loss: 0.6988 - val_accuracy: 0.7116 - val_loss: 0.8715\n","Epoch 15/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.7630 - loss: 0.6719 - val_accuracy: 0.7134 - val_loss: 0.8539\n","Epoch 16/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.7742 - loss: 0.6419 - val_accuracy: 0.7150 - val_loss: 0.8817\n","Epoch 17/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 5ms/step - accuracy: 0.7751 - loss: 0.6425 - val_accuracy: 0.7134 - val_loss: 0.8575\n","Epoch 18/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.7923 - loss: 0.5986 - val_accuracy: 0.6882 - val_loss: 0.9823\n","Epoch 19/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8005 - loss: 0.5771 - val_accuracy: 0.7208 - val_loss: 0.8856\n","Epoch 20/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8014 - loss: 0.5661 - val_accuracy: 0.7152 - val_loss: 0.9009\n","Epoch 21/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 5ms/step - accuracy: 0.8071 - loss: 0.5448 - val_accuracy: 0.7080 - val_loss: 0.9332\n","Epoch 22/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 4ms/step - accuracy: 0.8152 - loss: 0.5233 - val_accuracy: 0.7128 - val_loss: 0.9202\n","Epoch 23/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8201 - loss: 0.5059 - val_accuracy: 0.7152 - val_loss: 0.9343\n","Epoch 24/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 5ms/step - accuracy: 0.8243 - loss: 0.4981 - val_accuracy: 0.7188 - val_loss: 0.9274\n","Epoch 25/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8289 - loss: 0.4826 - val_accuracy: 0.7162 - val_loss: 0.9568\n","Epoch 26/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8365 - loss: 0.4606 - val_accuracy: 0.7162 - val_loss: 0.9787\n","Epoch 27/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8361 - loss: 0.4606 - val_accuracy: 0.7208 - val_loss: 0.9641\n","Epoch 28/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 4ms/step - accuracy: 0.8425 - loss: 0.4403 - val_accuracy: 0.7202 - val_loss: 0.9633\n","Epoch 29/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8440 - loss: 0.4314 - val_accuracy: 0.7254 - val_loss: 0.9901\n","Epoch 30/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8516 - loss: 0.4154 - val_accuracy: 0.7136 - val_loss: 1.0164\n","Epoch 31/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8546 - loss: 0.4067 - val_accuracy: 0.7190 - val_loss: 1.0651\n","Epoch 32/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 5ms/step - accuracy: 0.8592 - loss: 0.3928 - val_accuracy: 0.7224 - val_loss: 1.0705\n","Epoch 33/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8589 - loss: 0.3900 - val_accuracy: 0.7110 - val_loss: 1.0371\n","Epoch 34/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8632 - loss: 0.3763 - val_accuracy: 0.7196 - val_loss: 1.0296\n","Epoch 35/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8702 - loss: 0.3570 - val_accuracy: 0.7188 - val_loss: 1.0846\n","Epoch 36/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 5ms/step - accuracy: 0.8721 - loss: 0.3516 - val_accuracy: 0.7166 - val_loss: 1.1253\n","Epoch 37/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8725 - loss: 0.3537 - val_accuracy: 0.7172 - val_loss: 1.1199\n","Epoch 38/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8694 - loss: 0.3607 - val_accuracy: 0.7152 - val_loss: 1.1645\n","Epoch 39/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8754 - loss: 0.3421 - val_accuracy: 0.7154 - val_loss: 1.2121\n","Epoch 40/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8731 - loss: 0.3501 - val_accuracy: 0.7184 - val_loss: 1.1481\n","Epoch 41/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 5ms/step - accuracy: 0.8793 - loss: 0.3328 - val_accuracy: 0.7174 - val_loss: 1.2047\n","Epoch 42/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8836 - loss: 0.3210 - val_accuracy: 0.7140 - val_loss: 1.2677\n","Epoch 43/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8847 - loss: 0.3154 - val_accuracy: 0.7098 - val_loss: 1.2376\n","Epoch 44/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8894 - loss: 0.3046 - val_accuracy: 0.7088 - val_loss: 1.2208\n","Epoch 45/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 5ms/step - accuracy: 0.8886 - loss: 0.3104 - val_accuracy: 0.7046 - val_loss: 1.3501\n","Epoch 46/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 4ms/step - accuracy: 0.8900 - loss: 0.3018 - val_accuracy: 0.7086 - val_loss: 1.3483\n","Epoch 47/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8901 - loss: 0.3028 - val_accuracy: 0.7100 - val_loss: 1.4048\n","Epoch 48/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8948 - loss: 0.2922 - val_accuracy: 0.7044 - val_loss: 1.3963\n","Epoch 49/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 5ms/step - accuracy: 0.8944 - loss: 0.2900 - val_accuracy: 0.7124 - val_loss: 1.3789\n","Epoch 50/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 4ms/step - accuracy: 0.8971 - loss: 0.2795 - val_accuracy: 0.7118 - val_loss: 1.3672\n"]},{"output_type":"execute_result","data":{"text/plain":["<keras.src.callbacks.history.History at 0x7d9528b78e60>"]},"metadata":{},"execution_count":12}]},{"cell_type":"code","source":["# Оценка качества работы модели на тестовых данных\n","scores = model.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"VmfQQpj_gqMH","executionInfo":{"status":"ok","timestamp":1765240127129,"user_tz":-180,"elapsed":5274,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"37d2725b-b26d-4c69-a409-c50730619384"},"execution_count":13,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 9ms/step - accuracy: 0.7178 - loss: 1.3206\n","Loss on test data: 1.3243911266326904\n","Accuracy on test data: 0.7181000113487244\n"]}]},{"cell_type":"code","source":["# вывод двух тестовых изображений и результатов распознавания\n","\n","for n in [67,3]:\n","  result = model.predict(X_test[n:n+1])\n","  print('NN output:', result)\n","\n","  plt.imshow(X_test[n].reshape(32,32,3), cmap=plt.get_cmap('gray'))\n","  plt.show()\n","  print('Real mark: ', np.argmax(y_test[n]))\n","  print('NN answer: ', np.argmax(result))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"D0Jd2q8hg2Iq","executionInfo":{"status":"ok","timestamp":1765240271211,"user_tz":-180,"elapsed":609,"user":{"displayName":"Мирон Романов","userId":"18135774377279153892"}},"outputId":"7774e53c-ec9d-4dc7-b07d-e3465fdf903f"},"execution_count":16,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step\n","NN output: [[2.0852229e-03 6.4687323e-05 8.8319254e-01 2.7147874e-02 2.0701988e-02\n","  5.4570869e-02 5.0194338e-03 6.9489344e-03 1.2296445e-04 1.4538057e-04]]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark:  2\n","NN answer:  2\n","\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 63ms/step\n","NN output: [[4.66867859e-05 2.89780496e-06 9.21415904e-08 6.26062393e-01\n","  2.08341021e-06 3.73860687e-01 2.05569340e-05 5.99638597e-08\n","  4.45279193e-06 1.07312246e-07]]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark:  4\n","NN answer:  3\n"]}]},{"cell_type":"code","source":["# истинные метки классов\n","true_labels = np.argmax(y_test, axis=1)\n","# предсказанные метки классов\n","predicted_labels = np.argmax(model.predict(X_test), axis=1)\n","\n","# отчет о качестве классификации\n","print(classification_report(true_labels, predicted_labels, target_names=class_names))\n","# вычисление матрицы ошибок\n","conf_matrix = confusion_matrix(true_labels, predicted_labels)\n","# отрисовка матрицы ошибок в виде \"тепловой карты\"\n","fig, ax = plt.subplots(figsize=(6, 6))\n","disp = ConfusionMatrixDisplay(confusion_matrix=conf_matrix,display_labels=class_names)\n","disp.plot(ax=ax, xticks_rotation=45)  # поворот подписей по X и приятная палитра\n","plt.tight_layout()  # чтобы всё влезло\n","plt.show()"],"metadata":{"id":"GyU5B4mrhx4T"},"execution_count":null,"outputs":[]}]}