{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "id": "R3Vwrx0Xon-r" }, "outputs": [], "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", "\n", "from sklearn.datasets import make_moons\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler\n", "\n", "from tensorflow.keras.models import Sequential\n", "from tensorflow.keras.layers import Dense\n", "from tensorflow.keras.optimizers import Adam" ] }, { "cell_type": "code", "source": [ "X, y = make_moons(n_samples=1000, noise=0.2, random_state=42)" ], "metadata": { "id": "MZFSmvjDoo3h" }, "execution_count": 2, "outputs": [] }, { "cell_type": "code", "source": [ "X_train, X_test, y_train, y_test = train_test_split(\n", " X, y, test_size=0.2, random_state=42\n", ")" ], "metadata": { "id": "CF_el2TKoo6J" }, "execution_count": 3, "outputs": [] }, { "cell_type": "code", "source": [ "scaler = StandardScaler()\n", "\n", "X_train = scaler.fit_transform(X_train)\n", "X_test = scaler.transform(X_test)" ], "metadata": { "id": "EbQ8vHBJoo_6" }, "execution_count": 4, "outputs": [] }, { "cell_type": "code", "source": [ "model = Sequential([\n", " Dense(16, activation='relu', input_shape=(2,)),\n", " Dense(8, activation='relu'),\n", " Dense(1, activation='sigmoid')\n", "])" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Qe4Wi3rtopCi", "outputId": "81c98da2-d6f0-43aa-a253-aa8cc1088fee" }, "execution_count": 5, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.12/dist-packages/keras/src/layers/core/dense.py:106: 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" ] } ] }, { "cell_type": "code", "source": [ "adam_optimizer = Adam(learning_rate=0.001)\n", "model.compile(\n", " optimizer=adam_optimizer,\n", " loss='binary_crossentropy',\n", " metrics=['accuracy']\n", ")" ], "metadata": { "id": "_Usn1DMyopFW" }, "execution_count": 6, "outputs": [] }, { "cell_type": "code", "source": [ "history = model.fit(\n", " X_train,\n", " y_train,\n", " epochs=50,\n", " batch_size=32,\n", " validation_split=0.2,\n", " verbose=1\n", ")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "OW90t5NnopIB", "outputId": "5c1d6313-40b8-44b3-cc04-e410da7e6f9e" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Epoch 1/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 38ms/step - accuracy: 0.5063 - loss: 0.7271 - val_accuracy: 0.4500 - val_loss: 0.7188\n", "Epoch 2/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - accuracy: 0.5156 - loss: 0.6789 - val_accuracy: 0.4625 - val_loss: 0.6776\n", "Epoch 3/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - accuracy: 0.5516 - loss: 0.6386 - val_accuracy: 0.5500 - val_loss: 0.6364\n", "Epoch 4/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - accuracy: 0.6313 - loss: 0.5917 - val_accuracy: 0.7000 - val_loss: 0.5789\n", "Epoch 5/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 0.8375 - loss: 0.5366 - val_accuracy: 0.8438 - val_loss: 0.5224\n", "Epoch 6/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - accuracy: 0.8656 - loss: 0.4852 - val_accuracy: 0.8500 - val_loss: 0.4703\n", "Epoch 7/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 11ms/step - accuracy: 0.8750 - loss: 0.4381 - val_accuracy: 0.8687 - val_loss: 0.4227\n", "Epoch 8/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 0.8719 - loss: 0.3964 - val_accuracy: 0.8687 - val_loss: 0.3819\n", "Epoch 9/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.8734 - loss: 0.3623 - val_accuracy: 0.8750 - val_loss: 0.3510\n", "Epoch 10/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 0.8766 - loss: 0.3382 - val_accuracy: 0.8750 - val_loss: 0.3279\n", "Epoch 11/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 12ms/step - accuracy: 0.8766 - loss: 0.3220 - val_accuracy: 0.8750 - val_loss: 0.3114\n", "Epoch 12/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - accuracy: 0.8766 - loss: 0.3105 - val_accuracy: 0.8750 - val_loss: 0.3012\n", "Epoch 13/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - accuracy: 0.8781 - loss: 0.3026 - val_accuracy: 0.8750 - val_loss: 0.2945\n", "Epoch 14/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - accuracy: 0.8797 - loss: 0.2975 - val_accuracy: 0.8750 - val_loss: 0.2899\n", "Epoch 15/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.8797 - loss: 0.2929 - val_accuracy: 0.8750 - val_loss: 0.2846\n", "Epoch 16/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8797 - loss: 0.2894 - val_accuracy: 0.8750 - val_loss: 0.2806\n", "Epoch 17/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8797 - loss: 0.2863 - val_accuracy: 0.8750 - val_loss: 0.2773\n", "Epoch 18/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8797 - loss: 0.2832 - val_accuracy: 0.8750 - val_loss: 0.2748\n", "Epoch 19/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8781 - loss: 0.2804 - val_accuracy: 0.8750 - val_loss: 0.2720\n", "Epoch 20/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8797 - loss: 0.2776 - val_accuracy: 0.8750 - val_loss: 0.2696\n", "Epoch 21/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8813 - loss: 0.2750 - val_accuracy: 0.8750 - val_loss: 0.2673\n", "Epoch 22/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8813 - loss: 0.2721 - val_accuracy: 0.8687 - val_loss: 0.2645\n", "Epoch 23/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8828 - loss: 0.2691 - val_accuracy: 0.8687 - val_loss: 0.2619\n", "Epoch 24/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.8828 - loss: 0.2662 - val_accuracy: 0.8687 - val_loss: 0.2593\n", "Epoch 25/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8844 - loss: 0.2632 - val_accuracy: 0.8687 - val_loss: 0.2574\n", "Epoch 26/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8859 - loss: 0.2604 - val_accuracy: 0.8687 - val_loss: 0.2545\n", "Epoch 27/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8859 - loss: 0.2582 - val_accuracy: 0.8687 - val_loss: 0.2517\n", "Epoch 28/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8875 - loss: 0.2548 - val_accuracy: 0.8750 - val_loss: 0.2487\n", "Epoch 29/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8875 - loss: 0.2514 - val_accuracy: 0.8750 - val_loss: 0.2457\n", "Epoch 30/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8891 - loss: 0.2489 - val_accuracy: 0.8750 - val_loss: 0.2435\n", "Epoch 31/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8906 - loss: 0.2460 - val_accuracy: 0.8813 - val_loss: 0.2394\n", "Epoch 32/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.8922 - loss: 0.2422 - val_accuracy: 0.8750 - val_loss: 0.2367\n", "Epoch 33/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8953 - loss: 0.2392 - val_accuracy: 0.8750 - val_loss: 0.2338\n", "Epoch 34/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8938 - loss: 0.2360 - val_accuracy: 0.8813 - val_loss: 0.2291\n", "Epoch 35/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8969 - loss: 0.2322 - val_accuracy: 0.8938 - val_loss: 0.2261\n", "Epoch 36/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.8984 - loss: 0.2283 - val_accuracy: 0.8938 - val_loss: 0.2224\n", "Epoch 37/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9016 - loss: 0.2244 - val_accuracy: 0.9000 - val_loss: 0.2189\n", "Epoch 38/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9047 - loss: 0.2208 - val_accuracy: 0.9062 - val_loss: 0.2148\n", "Epoch 39/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9062 - loss: 0.2171 - val_accuracy: 0.9062 - val_loss: 0.2102\n", "Epoch 40/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.9125 - loss: 0.2129 - val_accuracy: 0.9062 - val_loss: 0.2074\n", "Epoch 41/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9125 - loss: 0.2087 - val_accuracy: 0.9125 - val_loss: 0.2035\n", "Epoch 42/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9141 - loss: 0.2052 - val_accuracy: 0.9125 - val_loss: 0.1991\n", "Epoch 43/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9156 - loss: 0.2013 - val_accuracy: 0.9187 - val_loss: 0.1941\n", "Epoch 44/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 5ms/step - accuracy: 0.9172 - loss: 0.1974 - val_accuracy: 0.9187 - val_loss: 0.1905\n", "Epoch 45/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9172 - loss: 0.1935 - val_accuracy: 0.9187 - val_loss: 0.1878\n", "Epoch 46/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.9203 - loss: 0.1895 - val_accuracy: 0.9187 - val_loss: 0.1838\n", "Epoch 47/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.9203 - loss: 0.1854 - val_accuracy: 0.9250 - val_loss: 0.1793\n", "Epoch 48/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.9234 - loss: 0.1822 - val_accuracy: 0.9250 - val_loss: 0.1766\n", "Epoch 49/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - accuracy: 0.9234 - loss: 0.1774 - val_accuracy: 0.9375 - val_loss: 0.1710\n", "Epoch 50/50\n", "\u001b[1m20/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.9234 - loss: 0.1743 - val_accuracy: 0.9438 - val_loss: 0.1678\n" ] } ] }, { "cell_type": "code", "source": [ "loss, accuracy = model.evaluate(X_test, y_test)\n", "\n", "print(\"Test Loss:\", loss)\n", "print(\"Test Accuracy:\", accuracy)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "MaA-lbAJtO7C", "outputId": "aa5d2a6c-b11b-43b1-a7fe-89a786d046d8" }, "execution_count": 8, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - accuracy: 0.9400 - loss: 0.1575 \n", "Test Loss: 0.15747053921222687\n", "Test Accuracy: 0.9399999976158142\n" ] } ] }, { "cell_type": "code", "source": [ "plt.plot(history.history['accuracy'], label='Training Accuracy')\n", "plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n", "plt.xlabel('Epochs')\n", "plt.ylabel('Accuracy')\n", "plt.legend()\n", "plt.title('Training vs Validation Accuracy')\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 472 }, "id": "E8F5j9_ctO9Z", "outputId": "55abd648-b151-4564-917d-2ffe98513900" }, "execution_count": 9, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAHHCAYAAABDUnkqAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAaf1JREFUeJzt3Xd4FOXexvHvpm16gRRCS2jSpCg1IoIUEZQDiIIIUixYQFH0VREVxKPYDqLiEQvFRhEOIIiiiNgQBekIovQakgDpfXfePzZZEhJIIckmm/tzXXuZnZ2d+e0E2ZtnnmIyDMNARERExEm4OLoAERERkbKkcCMiIiJOReFGREREnIrCjYiIiDgVhRsRERFxKgo3IiIi4lQUbkRERMSpKNyIiIiIU1G4EREREaeicCNSCqNHjyYyMrJU7506dSomk6lsC3JShV2ryMhIRo8eXeR758+fj8lk4vDhw2VWz+HDhzGZTMyfP7/MjikiZU/hRpyKyWQq1uOHH35wdKlOJSYmBjc3N0aMGHHRfZKSkvDy8uKWW26pwMpKZ8GCBcycOdPRZVzUkCFDMJlMPPnkk44uRaRScnN0ASJl6ZNPPsn3/OOPP2bt2rUFtjdv3vyyzvPBBx9gtVpL9d5nnnmGp5566rLOX9mEhobSu3dvvvjiC1JTU/H29i6wz7Jly0hPT79kACqOffv24eJSvv8uW7BgAbt37+aRRx7Jtz0iIoK0tDTc3d3L9fyXkpiYyKpVq4iMjGThwoW8/PLLagkUuYDCjTiVC784f/vtN9auXVvkF+rFvpAv5nK+3Nzc3HBzc77/9YYPH86aNWtYuXIlt99+e4HXFyxYQEBAADfddNNlncdsNl/W+y+HyWTC09PTYecH+N///ofFYmHu3Ln06NGDn376iW7dujm0psIYhkF6ejpeXl6OLkWqId2Wkmqne/fuXHnllWzZsoXrrrsOb29vnn76aQC++OILbrrpJmrXro3ZbKZRo0a88MILWCyWfMe4sM9Nbl+M119/nffff59GjRphNpvp0KEDmzdvzvfewvqRmEwmxo8fz4oVK7jyyisxm820bNmSNWvWFKj/hx9+oH379nh6etKoUSPee++9YvXjGT9+PL6+vqSmphZ4bdiwYdSqVcv+Of/44w/69OlDcHAwXl5eNGjQgLvuuuuSxx80aBA+Pj4sWLCgwGsxMTGsW7eOW2+9FbPZzM8//8xtt91G/fr1MZvN1KtXj0cffZS0tLRLngMK73Pz559/0qNHD7y8vKhbty7//ve/C21ZK87vt3v37qxevZojR47Yb2Pm/q4v1ufm+++/p2vXrvj4+BAYGMiAAQPYu3dvvn1yf0f79+9n9OjRBAYGEhAQwJgxYwr9nVzMZ599Ru/evbn++utp3rw5n332WaH7/fXXXwwZMoSQkBC8vLxo2rQpkydPzrfPiRMnuPvuu+3Xo0GDBjzwwANkZmbmq/lChfVnioyM5Oabb+abb76hffv2eHl58d577wEwb948evToQWhoKGazmRYtWvDuu+8WWvfXX39Nt27d8PPzw9/fnw4dOtj/TE2ZMgV3d3diY2MLvG/s2LEEBgaSnp5e9EUUp+d8/3wUKYYzZ87Qt29fbr/9dkaMGEFYWBhg+0vb19eXiRMn4uvry/fff89zzz1HYmIir732WpHHXbBgAUlJSdx3332YTCZeffVVbrnlFg4ePFhka88vv/zCsmXLePDBB/Hz8+Ott95i8ODBHD16lJo1awKwbds2brzxRsLDw3n++eexWCxMmzaNkJCQImsbOnQo77zzDqtXr+a2226zb09NTWXVqlWMHj0aV1dXYmJiuOGGGwgJCeGpp54iMDCQw4cPs2zZskse38fHhwEDBrB06VLOnj1LjRo17K8tXrwYi8XC8OHDAViyZAmpqak88MAD1KxZk02bNvH2229z/PhxlixZUuRnySs6Oprrr7+e7OxsnnrqKXx8fHj//fcLbTEozu938uTJJCQkcPz4cd544w0AfH19L3r+7777jr59+9KwYUOmTp1KWloab7/9Nl26dGHr1q0FOp4PGTKEBg0aMH36dLZu3cqHH35IaGgor7zySpGf9eTJk6xfv56PPvoIsIXSN954g1mzZuHh4WHfb+fOnXTt2hV3d3fGjh1LZGQkBw4cYNWqVbz44ov2Y3Xs2JH4+HjGjh1Ls2bNOHHiBEuXLiU1NTXf8Ypr3759DBs2jPvuu497772Xpk2bAvDuu+/SsmVL/vWvf+Hm5saqVat48MEHsVqtjBs3zv7++fPnc9ddd9GyZUsmTZpEYGAg27ZtY82aNdxxxx3ceeedTJs2jcWLFzN+/Hj7+zIzM1m6dCmDBw92eMuaVBKGiBMbN26cceEf827duhmAMXv27AL7p6amFth23333Gd7e3kZ6erp926hRo4yIiAj780OHDhmAUbNmTePs2bP27V988YUBGKtWrbJvmzJlSoGaAMPDw8PYv3+/fduOHTsMwHj77bft2/r37294e3sbJ06csG/7559/DDc3twLHvJDVajXq1KljDB48ON/2zz//3ACMn376yTAMw1i+fLkBGJs3b77k8QqzevVqAzDee++9fNs7d+5s1KlTx7BYLIZhFH6dp0+fbphMJuPIkSP2bYVdq4iICGPUqFH254888ogBGL///rt9W0xMjBEQEGAAxqFDh+zbi/v7vemmm/L9fnPl/p7nzZtn39a2bVsjNDTUOHPmjH3bjh07DBcXF2PkyJEFPstdd92V75iDBg0yatasWeBchXn99dcNLy8vIzEx0TAMw/j7778NwFi+fHm+/a677jrDz88v37U0DNufgVwjR440XFxcCv095+5X2PU3DMOYN29egWsbERFhAMaaNWsK7F/Yde/Tp4/RsGFD+/P4+HjDz8/P6NSpk5GWlnbRuqOiooxOnTrle33ZsmUGYKxfv77AeaR60m0pqZbMZjNjxowpsD3vv/aTkpKIi4uja9eupKam8tdffxV53KFDhxIUFGR/3rVrVwAOHjxY5Ht79epFo0aN7M9bt26Nv7+//b0Wi4XvvvuOgQMHUrt2bft+jRs3pm/fvkUe32Qycdttt/HVV1+RnJxs37548WLq1KnDtddeC0BgYCAAX375JVlZWUUeN6/cFp+8t6YOHTrEb7/9xrBhw+wdgfNe55SUFOLi4rjmmmswDINt27aV6JxfffUVnTt3pmPHjvZtISEh9laivC7393uhU6dOsX37dkaPHp2vpap169b07t2br776qsB77r///nzPu3btypkzZ0hMTCzyfJ999hk33XQTfn5+ADRp0oR27drluzUVGxvLTz/9xF133UX9+vXzvT/3FpPVamXFihX079+f9u3bFzhPaTsoN2jQgD59+hTYnve6JyQkEBcXR7du3Th48CAJCQkArF27lqSkJJ566qkCrS956xk5ciS///47Bw4csG/77LPPqFevXqXseySOoXAj1VKdOnUKbXb/888/GTRoEAEBAfj7+xMSEmLvjJz7l/ClXPhlkht0zp07V+L35r4/970xMTGkpaXRuHHjAvsVtq0wQ4cOJS0tjZUrVwKQnJzMV199xW233Wb/AunWrRuDBw/m+eefJzg4mAEDBjBv3jwyMjKKPL6bmxtDhw7l559/5sSJEwD2oJM3bBw9etQeCHx9fQkJCbF/MRXnOud15MgRmjRpUmB77i2RvC7391vYuS92rubNmxMXF0dKSkq+7aX9M7J37162bdtGly5d2L9/v/3RvXt3vvzyS3s4yg3DV1555UWPFRsbS2Ji4iX3KY0GDRoUun3Dhg306tXL3icpJCTE3s8t97rnhpWiaho6dChms9ke6BISEvjyyy8ZPny4Ro2JncKNVEuF9ceIj4+nW7du7Nixg2nTprFq1SrWrl1r7wtRnKHfrq6uhW43DKNc31tcnTt3JjIyks8//xyAVatWkZaWxtChQ+37mEwmli5dysaNGxk/fjwnTpzgrrvuol27dvlafC5mxIgRWK1WFi5cCMDChQtp0aIFbdu2BWwtUL1792b16tU8+eSTrFixgrVr19o76ZZ2iH1RyuL3WxZK+3v+9NNPAXj00Udp0qSJ/fGf//yH9PR0/ve//5V5rRcLCxd2sM9V2P9XBw4coGfPnsTFxTFjxgxWr17N2rVrefTRR4GSX/egoCBuvvlme7hZunQpGRkZlz3FgDgXdSgWyfHDDz9w5swZli1bxnXXXWfffujQIQdWdV5oaCienp7s37+/wGuFbbuYIUOG8Oabb5KYmMjixYuJjIykc+fOBfbr3LkznTt35sUXX2TBggUMHz6cRYsWcc8991zy+J06daJRo0YsWLCA3r178+eff9o7sQLs2rWLv//+m48++oiRI0fat69du7bYnyGviIgI/vnnnwLb9+3bl+95SX6/xW0BiIiIKPRcYButFBwcjI+PT7GOdSmGYbBgwQKuv/56HnzwwQKvv/DCC3z22WeMGTOGhg0bArB79+6LHi8kJAR/f/9L7gPnW5Xi4+PttyvhfItVcaxatYqMjAxWrlyZr9Vq/fr1+fbLvSW7e/fuIlsiR44cyYABA9i8eTOfffYZV111FS1btix2TeL81HIjkiP3X9R5/wWdmZnJf//7X0eVlI+rqyu9evVixYoVnDx50r59//79fP3118U+ztChQ8nIyOCjjz5izZo1DBkyJN/r586dK9CKkNvqUpxbU2C7BbVt2zamTJmCyWTijjvuyPc5IP91NgyDN998s9ifIa9+/frx22+/sWnTJvu22NjYAkOkS/L79fHxKdZtqvDwcNq2bctHH31EfHy8ffvu3bv59ttv6devX0k/TqE2bNjA4cOHGTNmDLfeemuBx9ChQ1m/fj0nT54kJCSE6667jrlz53L06NF8x8n97C4uLgwcOJBVq1bxxx9/FDhf7n65geOnn36yv5aSkmIfrVUchV33hIQE5s2bl2+/G264AT8/P6ZPn15gOPeFfx779u1LcHAwr7zyCj/++KNabaQAtdyI5LjmmmsICgpi1KhRPPzww5hMJj755JMyvS10uaZOncq3335Lly5deOCBB7BYLMyaNYsrr7yS7du3F+sYV199NY0bN2by5MlkZGTkuyUF8NFHH/Hf//6XQYMG0ahRI5KSkvjggw/w9/cv9pf1iBEjmDZtGl988QVdunTJNxy6WbNmNGrUiMcff5wTJ07g7+/P//73v2L1SyrME088wSeffMKNN97IhAkT7EPBIyIi2Llzp32/kvx+27Vrx+LFi5k4cSIdOnTA19eX/v37F3r+1157jb59+xIVFcXdd99tHwoeEBDA1KlTS/WZLvTZZ5/h6up60QkQ//WvfzF58mQWLVrExIkTeeutt7j22mu5+uqrGTt2LA0aNODw4cOsXr3a/ufkpZde4ttvv6Vbt26MHTuW5s2bc+rUKZYsWcIvv/xCYGAgN9xwA/Xr1+fuu+/m//7v/3B1dWXu3LmEhIQUCE4Xc8MNN+Dh4UH//v257777SE5O5oMPPiA0NJRTp07Z9/P39+eNN97gnnvuoUOHDtxxxx0EBQWxY8cOUlNT8wUqd3d3br/9dmbNmoWrqyvDhg0r/cUV51TxA7REKs7FhoK3bNmy0P03bNhgdO7c2fDy8jJq165tPPHEE8Y333xTYJjpxYaCv/baawWOCRhTpkyxP7/YUPBx48YVeO+Fw54NwzDWrVtnXHXVVYaHh4fRqFEj48MPPzQee+wxw9PT8yJXoaDJkycbgNG4ceMCr23dutUYNmyYUb9+fcNsNhuhoaHGzTffbPzxxx/FPr5hGEaHDh0MwPjvf/9b4LU9e/YYvXr1Mnx9fY3g4GDj3nvvtQ99zzvMujhDwQ3DMHbu3Gl069bN8PT0NOrUqWO88MILxpw5cwoMVy7u7zc5Odm44447jMDAQAOw/64LGwpuGIbx3XffGV26dDG8vLwMf39/o3///saePXvy7ZP7WWJjY/NtL2xYdV6ZmZlGzZo1ja5duxb6eq4GDRoYV111lf357t27jUGDBhmBgYGGp6en0bRpU+PZZ5/N954jR44YI0eONEJCQgyz2Ww0bNjQGDdunJGRkWHfZ8uWLUanTp0MDw8Po379+saMGTMuOhT8pptuKrS2lStXGq1btzY8PT2NyMhI45VXXjHmzp1b6OdeuXKlcc0119ivZceOHY2FCxcWOOamTZsMwLjhhhsueV2kejIZRiX6Z6mIlMrAgQP5888/C+17IuKMduzYQdu2bfn444+58847HV2OVDLqcyNSxVy4RME///zDV199Rffu3R1TkIgDfPDBB/j6+laJVeal4qnPjUgV07BhQ0aPHk3Dhg05cuQI7777Lh4eHjzxxBOOLk2k3K1atYo9e/bw/vvvM378+DIZjSbOR7elRKqYMWPGsH79eqKjozGbzURFRfHSSy9x9dVXO7o0kXIXGRnJ6dOn6dOnD5988ol9tmaRvBRuRERExKmoz42IiIg4FYUbERERcSrVrkOx1Wrl5MmT+Pn5aZE1ERGRKsIwDJKSkqhduzYuLpdum6l24ebkyZPUq1fP0WWIiIhIKRw7doy6detecp9qF25ye9YfO3YMf39/B1cjIiIixZGYmEi9evWKNUKu2oWb3FtR/v7+CjciIiJVTHG6lKhDsYiIiDgVhRsRERFxKgo3IiIi4lSqXZ+b4rJYLGRlZTm6DJEy5+7ujqurq6PLEBEpNwo3FzAMg+joaOLj4x1diki5CQwMpFatWprrSUScksLNBXKDTWhoKN7e3vrLX5yKYRikpqYSExMDQHh4uIMrEhEpewo3eVgsFnuwqVmzpqPLESkXXl5eAMTExBAaGqpbVCLidNShOI/cPjbe3t4OrkSkfOX+GVe/MhFxRgo3hdCtKHF2+jMuIs5M4UZEREScisKNXFRkZCQzZ84s9v4//PADJpNJI81ERMShFG6cgMlkuuRj6tSppTru5s2bGTt2bLH3v+aaazh16hQBAQGlOl9pNGvWDLPZTHR0dIWdU0REKjeFGydw6tQp+2PmzJn4+/vn2/b444/b9zUMg+zs7GIdNyQkpESdqz08PCp07pRffvmFtLQ0br31Vj766KMKOeelqHOuiAhw9iDE7XdoCQo3TqBWrVr2R0BAACaTyf78r7/+ws/Pj6+//pp27dphNpv55ZdfOHDgAAMGDCAsLAxfX186dOjAd999l++4F96WMplMfPjhhwwaNAhvb2+aNGnCypUr7a9feFtq/vz5BAYG8s0339C8eXN8fX258cYbOXXqlP092dnZPPzwwwQGBlKzZk2efPJJRo0axcCBA4v83HPmzOGOO+7gzjvvZO7cuQVeP378OMOGDaNGjRr4+PjQvn17fv/9d/vrq1atokOHDnh6ehIcHMygQYPyfdYVK1bkO15gYCDz588H4PDhw5hMJhYvXky3bt3w9PTks88+48yZMwwbNow6derg7e1Nq1atWLhwYb7jWK1WXn31VRo3bozZbKZ+/fq8+OKLAPTo0YPx48fn2z82NhYPDw/WrVtX5DUREXGYk9tgyWh4ux18N8WhpSjcFMEwDFIzsx3yMAyjzD7HU089xcsvv8zevXtp3bo1ycnJ9OvXj3Xr1rFt2zZuvPFG+vfvz9GjRy95nOeff54hQ4awc+dO+vXrx/Dhwzl79uxF909NTeX111/nk08+4aeffuLo0aP5WpJeeeUVPvvsM+bNm8eGDRtITEwsECoKk5SUxJIlSxgxYgS9e/cmISGBn3/+2f56cnIy3bp148SJE6xcuZIdO3bwxBNPYLVaAVi9ejWDBg2iX79+bNu2jXXr1tGxY8ciz3uhp556igkTJrB371769OlDeno67dq1Y/Xq1ezevZuxY8dy5513smnTJvt7Jk2axMsvv8yzzz7Lnj17WLBgAWFhYQDcc889LFiwgIyMDPv+n376KXXq1KFHjx4lrk9EpFwZBuxfBx/9C97vDn8uB8MKlizbw0E0iV8R0rIstHjuG4ece8+0Pnh7lM2vaNq0afTu3dv+vEaNGrRp08b+/IUXXmD58uWsXLmyQMtBXqNHj2bYsGEAvPTSS7z11lts2rSJG2+8sdD9s7KymD17No0aNQJg/PjxTJs2zf7622+/zaRJk+ytJrNmzeKrr74q8vMsWrSIJk2a0LJlSwBuv/125syZQ9euXQFYsGABsbGxbN68mRo1agDQuHFj+/tffPFFbr/9dp5//nn7trzXo7geeeQRbrnllnzb8oa3hx56iG+++YbPP/+cjh07kpSUxJtvvsmsWbMYNWoUAI0aNeLaa68F4JZbbmH8+PF88cUXDBkyBLC1gI0ePVrDt0Wk8rBkw54VsGEmRO+ybTO5Qqtb4ZqHodaVjqxOLTfVRfv27fM9T05O5vHHH6d58+YEBgbi6+vL3r17i2y5ad26tf1nHx8f/P397VP5F8bb29sebMA23X/u/gkJCZw+fTpfi4mrqyvt2rUr8vPMnTuXESNG2J+PGDGCJUuWkJSUBMD27du56qqr7MHmQtu3b6dnz55FnqcoF15Xi8XCCy+8QKtWrahRowa+vr5888039uu6d+9eMjIyLnpuT0/PfLfZtm7dyu7duxk9evRl1yoictkyU+D39+Htq+B/d9uCjbsPdH4QJmyHW953eLABtdwUycvdlT3T+jjs3GXFx8cn3/PHH3+ctWvX8vrrr9O4cWO8vLy49dZbyczMvORx3N3d8z03mUz2Wz3F3f9yb7ft2bOH3377jU2bNvHkk0/at1ssFhYtWsS9995rX2LgYop6vbA6C+swfOF1fe2113jzzTeZOXMmrVq1wsfHh0ceecR+XYs6L9huTbVt25bjx48zb948evToQURERJHvExEpV399BV+Mg7ScrgjewdDpfuhwN3gX/g9JR1HLTRFMJhPeHm4OeZTnbYgNGzYwevRoBg0aRKtWrahVqxaHDx8ut/MVJiAggLCwMDZv3mzfZrFY2Lp16yXfN2fOHK677jp27NjB9u3b7Y+JEycyZ84cwNbCtH379ov2B2rduvUlO+iGhITk6/j8zz//kJqaWuRn2rBhAwMGDGDEiBG0adOGhg0b8vfff9tfb9KkCV5eXpc8d6tWrWjfvj0ffPABCxYs4K677iryvCIi5WrbZ7B4uC3YBEXCTf+BR3dDt/+rdMEG1HJTbTVp0oRly5bRv39/TCYTzz777CVbYMrLQw89xPTp02ncuDHNmjXj7bff5ty5cxcNdllZWXzyySdMmzaNK6/M3/R5zz33MGPGDP7880+GDRvGSy+9xMCBA5k+fTrh4eFs27aN2rVrExUVxZQpU+jZsyeNGjXi9ttvJzs7m6+++sreEtSjRw9mzZpFVFQUFouFJ598skArVGGaNGnC0qVL+fXXXwkKCmLGjBmcPn2aFi1aALbbTk8++SRPPPEEHh4edOnShdjYWP7880/uvvvufJ9l/Pjx+Pj45BvFJSJS4X6dBd9Otv3cdgT0fxNcK3d8UMtNNTVjxgyCgoK45ppr6N+/P3369OHqq6+u8DqefPJJhg0bxsiRI4mKisLX15c+ffrg6elZ6P4rV67kzJkzhX7hN2/enObNmzNnzhw8PDz49ttvCQ0NpV+/frRq1YqXX37ZvgJ29+7dWbJkCStXrqRt27b06NEj34im//znP9SrV4+uXbtyxx138Pjjjxdrzp9nnnmGq6++mj59+tC9e3dq1apVYFj7s88+y2OPPcZzzz1H8+bNGTp0aIF+S8OGDcPNzY1hw4Zd9FqIiJQrw4Dvnj8fbKLGw4BZlT7YAJiMshxvXAUkJiYSEBBAQkIC/v7++V5LT0/n0KFDNGjQQF8oDmK1WmnevDlDhgzhhRdecHQ5DnP48GEaNWrE5s2byyV06s+6iFyS1QKrH4Mt82zPe06Bax8FB47avNT394Uqf/wSp3bkyBG+/fZbunXrRkZGBrNmzeLQoUPccccdji7NIbKysjhz5gzPPPMMnTt3dkhrmohUc9mZsHysbc4aTHDzG9B+jKOrKhGFG3EoFxcX5s+fz+OPP45hGFx55ZV89913NG/e3NGlOcSGDRu4/vrrueKKK1i6dKmjyxGR6iYjGT6/Ew58Dy7uMPhDaDnQ0VWVmMKNOFS9evXYsGGDo8uoNLp3716mM1OLiBRb6llYMASOb7bNXXP7p9Coas6MrnAjIiLizE7vOT+L8EUZ8MtMiN0LXkEwfCnUbV/EeyovhRsRERFnYxhw6CfY8CYcKP6iu+leoWzvNo+UpHqw93SpTx/g5U77SMfNf6NwIyIi4iysFti70hZqTm6zbTO5QP0ocDPbdjEgOSOLxLRsEtKySEzPIivbShwBzIi/jeMrEoA/LquMq+sHsuzBLpf5YUpP4UZERKSKiklM51xqFqbsNPz3LaXGjtl4JB4BwOrmSULToZxrM5Yj1lD+OHKWPw6fY8fxeNKz8k/a6uHqQuNQX2q6uVCzDOpqEupXBkcpPYUbERGRsmIYkHwajLKf8d1iNTgYl8yO4wnsOhbP9uMJnElMZoDLr4x2W0OIKRGAc4YvH1tu4KP0Gzi7xR+2HAGO5DtWoLc77SOCaBdRg/aRQbSqE4BnGa5n6GgKNyIiIpcrOxN2fQ4b3oK4feVyClegSc7j1tyN5vOvnySET039+cKlB+lunpjM2FthArzcuToiiPYRQbSPDKJhsC8uLo6bkK+8KdyIXffu3Wnbti0zZ84EIDIykkceeYRHHnnkou8xmUwsX768wBIDJVVWxxERqVDpibBlPvz2X0iyLbZrYAIXNwwAw8CAnJ9z/otBaWd8MGH7+9JkyvkvYAprAVEPUbvlIJ5wdeOJy/1MTkDhxgn079+frKws1qxZU+C1n3/+2b6CduvWrUt03M2bN+Pj41NWZQIwdepUVqxYwfbt2/NtP3XqFEFBQWV6rotJS0ujTp06uLi4cOLECcxmc9FvEhEBDMPgTEomMScP47nlA+ruX4iHJRmAsy41+Mx0Ex+kdiPRKHotuuIID/CkXUQQHSJr0C4iiGa1/HBz1bKQRVG4cQJ33303gwcP5vjx49StWzffa/PmzaN9+/YlDjYAISEhZVVikWrVqlVh5/rf//5Hy5YtMQyDFStWMHTo0Ao794UMw8BiseDmpv8VRSqD5IxsTsWncSI+jVMJ6ZyMT+NkvO2/pxLSMCccZDSruMX1Z8ymbAD2W2vznuVmvrB0IRN3wNZBt3agJ+EBXtQO9KJ2oGfOf72oHeBJWIAn7i6XDikmE07VD6YiKf45gZtvvpmQkBDmz5+fb3tycjJLlizh7rvv5syZMwwbNow6derg7e1Nq1atWLhw4SWPGxkZab9FBfDPP/9w3XXX4enpSYsWLVi7dm2B9zz55JNcccUVeHt707BhQ5599lmysrIAmD9/Ps8//zw7duzIaVY12Ws2mUysWLHCfpxdu3bRo0cPvLy8qFmzJmPHjiU5Odn++ujRoxk4cCCvv/464eHh1KxZk3HjxtnPdSlz5sxhxIgRjBgxgjlz5hR4/c8//+Tmm2/G398fPz8/unbtyoEDB+yvz507l5YtW2I2mwkPD2f8+PGAbbFLk8mUr1UqPj4ek8nEDz/8AMAPP/yAyWTi66+/pl27dpjNZn755RcOHDjAgAEDCAsLw9fXlw4dOvDdd9/lqysjI4Mnn3ySevXqYTabady4MXPmzMEwDBo3bszrr7+eb//t27djMpnYv39/kddExBmlZ1n47Pcj/GvWL3R/bX2hj+tfXcfk6S+zZdq1HJnalNgXW+D2TjsiPruWzl/24pZf+jN+9228dHwk85Pu42vXxxjmth6zKZu9bs15N/wFFnVYQrO+D/LWiE6sHN+FzZN78dcLN/LD/13PwrGd+c+QNjx2Q1OGdaxPtytCaBLmh7+nO14erpd8KNiUnv65WBTDgKxUx5zb3btYK7C6ubkxcuRI5s+fz+TJkzHlvGfJkiVYLBaGDRtGcnIy7dq148knn8Tf35/Vq1dz55130qhRIzp27FjkOaxWK7fccgthYWH8/vvvJCQkFNoXx8/Pj/nz51O7dm127drFvffei5+fH0888QRDhw5l9+7drFmzxv7FHRAQUOAYKSkp9OnTh6ioKDZv3kxMTAz33HMP48ePzxfg1q9fT3h4OOvXr2f//v0MHTqUtm3bcu+99170cxw4cICNGzeybNkyDMPg0Ucf5ciRI0RERABw4sQJrrvuOrp3787333+Pv78/GzZsIDvb9i+0d999l4kTJ/Lyyy/Tt29fEhISSrV8xFNPPcXrr79Ow4YNCQoK4tixY/Tr148XX3wRs9nMxx9/TP/+/dm3bx/169cHYOTIkWzcuJG33nqLNm3acOjQIeLi4jCZTNx1113MmzePxx9/3H6OefPmcd1119G4ceMS1ydSlSWkZvHJb4eZ/+th4pIzC93HgywGuv7Cfa5f0sjl1PkXivFPfusVfXG59hGa1+9M9VwFr/JTuClKViq8VNsx5376JHgUr8/LXXfdxWuvvcaPP/5I9+7dAduX2+DBgwkICCAgICDfF99DDz3EN998w+eff16scPPdd9/x119/8c0331C7tu16vPTSS/Tt2zfffs8884z958jISB5//HEWLVrEE088gZeXF76+vri5uV3yNtSCBQtIT0/n448/tvf5mTVrFv379+eVV14hLCwMgKCgIGbNmoWrqyvNmjXjpptuYt26dZcMN3PnzqVv3772/j19+vRh3rx5TJ06FYB33nmHgIAAFi1ahLu7rXn5iiuusL//3//+N4899hgTJkywb+vQoUOR1+9C06ZNo3fv3vbnNWrUoE2bNvbnL7zwAsuXL2flypWMHz+ev//+m88//5y1a9fSq1cvABo2bGjff/To0Tz33HNs2rSJjh07kpWVxYIFCwq05og4s5Pxacz55RALNx0lNdMCQJ1AL+6+tgGt69r+IeWamUjIvgWE7pmHR1oMANnufsQ2u5Pshj2p6eeJt8clvhr9wnEJiij3zyKXR+HGSTRr1oxrrrmGuXPn0r17d/bv38/PP//MtGnTALBYLLz00kt8/vnnnDhxgszMTDIyMvD2Ll6nt71791KvXj17sAGIiooqsN/ixYt56623OHDgAMnJyWRnZ+Pv71+iz7J3717atGmTrzNzly5dsFqt7Nu3zx5uWrZsiavr+Wbb8PBwdu26+PopFouFjz76iDfffNO+bcSIETz++OM899xzuLi4sH37drp27WoPNnnFxMRw8uRJevbsWaLPU5j27fOv2ZKcnMzUqVNZvXo1p06dIjs7m7S0NI4ePQrYbjG5urrSrVu3Qo9Xu3ZtbrrpJubOnUvHjh1ZtWoVGRkZ3HbbbZddq0hlty86ifd+OsDK7SfJttqGITWr5cf93RpxU+tw3F1dIPEk/PYu/DEPMpNsb/SrDVEP4tZuNOFmx046J2VL4aYo7t62FhRHnbsE7r77bh566CHeeecd5s2bR6NGjexfhq+99hpvvvkmM2fOpFWrVvj4+PDII4+QmVl4k21pbNy4keHDh/P888/Tp08fewvIf/7znzI7R14XBhCTyYTVevGJs7755htOnDhRoAOxxWJh3bp19O7dGy8vr4u+/1KvAbjkdA7Mu6r3xfoAXTgK7fHHH2ft2rW8/vrrNG7cGC8vL2699Vb776eocwPcc8893HnnnbzxxhvMmzePoUOHFju8ilQqlmzbEgKHfso3GV621SA100JqZjYpmRZSMyycSc7gZEIa7YH2LhAW6EnzcH/CAzwxHQOOAenx8NdXYM35/zGkGVzzMLS6Ddw8HPABpbw5PNy88847vPbaa0RHR9OmTRvefvvti94mycrKYvr06Xz00UecOHGCpk2b8sorr3DjjTeWX4EmU7FvDTnakCFDmDBhAgsWLODjjz/mgQcesPe/2bBhAwMGDGDEiBGArQ/N33//TYsWLYp17ObNm3Ps2DFOnTpFeHg4AL/99lu+fX799VciIiKYPHmyfduRI/lnxfTw8MBisRR5rvnz55OSkmIPARs2bMDFxYWmTZsWq97CzJkzh9tvvz1ffQAvvvgic+bMoXfv3rRu3ZqPPvqIrKysAuHJz8+PyMhI1q1bx/XXX1/g+Lmjy06dOsVVV10FUGDI+8Vs2LCB0aNHM2jQIMDWknP48GH7661atcJqtfLjjz/ab0tdqF+/fvj4+PDuu++yZs0afvrpp2KdW6TSyErD2PYp2b+8jXvikQIvuwH+OY8CL+RKBQ5cuEOO+lHQ5RFocgMUMVJJqjaHhpvFixczceJEZs+eTadOnZg5cyZ9+vRh3759hIaGFtj/mWee4dNPP+WDDz6gWbNmfPPNNwwaNIhff/3V/mVSnfn6+jJ06FAmTZpEYmIio0ePtr/WpEkTli5dyq+//kpQUBAzZszg9OnTxQ43vXr14oorrmDUqFG89tprJCYmFggJTZo04ejRoyxatIgOHTqwevVqli9fnm+fyMhIDh06xPbt26lbty5+fn4F5pkZPnw4U6ZMYdSoUUydOpXY2Fgeeugh7rzzTvstqZKKjY1l1apVrFy5kiuvvDLfayNHjmTQoEGcPXuW8ePH8/bbb3P77bczadIkAgIC+O233+jYsSNNmzZl6tSp3H///YSGhtK3b1+SkpLYsGEDDz30EF5eXnTu3JmXX36ZBg0aEBMTk68P0qU0adKEZcuW0b9/f0wmE88++2y+VqjIyEhGjRrFXXfdZe9QfOTIEWJiYhgyZAgArq6ujB49mkmTJtGkSZNCbxuKVDYZ2Rb2HjhM5m8f0OzIQvyt8bgDZw1f/me5jgQj/z8u3V1N+Hu542d2w9/LHX9PN5rW8ifI+xItMCYTNLgO6hXdv1CchOFAHTt2NMaNG2d/brFYjNq1axvTp08vdP/w8HBj1qxZ+bbdcsstxvDhw4t9zoSEBAMwEhISCryWlpZm7Nmzx0hLSyv28SqbX3/91QCMfv365dt+5swZY8CAAYavr68RGhpqPPPMM8bIkSONAQMG2Pfp1q2bMWHCBPvziIgI44033rA/37dvn3HttdcaHh4exhVXXGGsWbPGAIzly5fb9/m///s/o2bNmoavr68xdOhQ44033jACAgLsr6enpxuDBw82AgMDDcCYN2+eYRhGgePs3LnTuP766w1PT0+jRo0axr333mskJSXZXx81alS+2g3DMCZMmGB069at0Ovy+uuvG4GBgUZmZmaB1zIyMozAwEDjzTffNAzDMHbs2GHccMMNhre3t+Hn52d07drVOHDggH3/2bNnG02bNjXc3d2N8PBw46GHHrK/tmfPHiMqKsrw8vIy2rZta3z77bcGYKxfv94wDMNYv369ARjnzp3LV8OhQ4eM66+/3vDy8jLq1atnzJo1q8DvIy0tzXj00UeN8PBww8PDw2jcuLExd+7cfMc5cOCAARivvvpqodch77Gq+p91qZrOJGcY3/4Zbbz01R7jvreXGfOeHWqkPBdiGFP8DWOKv3H02UbG8888bIx453vjxdV7jI9/PWR8tyfa+PNEghGfkmlYrVZHfwRxkEt9f1/IZBilnQT68mRmZuLt7c3SpUvzTbk/atQo4uPj+eKLLwq8p2bNmrz66qvcfffd9m0jRozgl19+ydeEfymJiYkEBASQkJBQoKNreno6hw4dokGDBnh6epbqc4k40s8//0zPnj05duzYJVu59GddKoJhGByKS+GPI+fYcvgcfxw5y4HYFJqZjjLW7Uv+5fIrbiZbC+VRj8b80/guAjsM4cp6NTC7aY4Xye9S398Xcthtqbi4OCwWS4G/gMPCwvjrr78KfU+fPn2YMWMG1113HY0aNWLdunUsW7bskn04MjIyyMjIsD9PTEwsmw8gUolkZGQQGxvL1KlTue2220p9+06ktDKzrUQnpHMiPo1dJ+L54/A5thw5x5mU3EELBp1d9vKs+yq6u+6wvy+1ble8uk+kfqPrqV+Meb1EisPhHYpL4s033+Tee++lWbNmmEwmGjVqxJgxY5g7d+5F3zN9+nSef/75CqxSpOItXLiQu+++m7Zt2/Lxxx87uhxxQlkWK/uikzh2NpWT9mUJ0uw/xyVnFLoYpKcb3FNzN3dkr6B2yh7bRpMLtBgAXSbgXVv9JaXsOSzcBAcH4+rqyunTp/NtP3369EUneAsJCWHFihWkp6dz5swZateuzVNPPZVvMrMLTZo0iYkTJ9qfJyYmUq9evbL5ECKVxOjRo/N1IBfJlZ5lITYpgxA/c4mm809Iy2Lr0fO3k3YcSyAt69IjHT3cXKgT6EXjUF861fWid9Z66v01B5dzB207uHnCVSMgahzUuPjf2yKXy2HhxsPDg3bt2rFu3Tp7nxur1cq6devsa/VcjKenJ3Xq1CErK4v//e9/9tEihTGbzVr1WUSqjTPJGWw5co4/jpzjj8Nn2X0ikUyLrV9LTR8Pagd6ER7gWWAxR39PN3adSLDfTtp3OqlAS0yYZzYta7oQFuBFLX9PwvzNhAV4UsvPk7AAM0HeHpgsmbBzMfz+HqTE2t7oFQQdx9oePsEVfEWkOnLobamJEycyatQo2rdvT8eOHZk5cyYpKSmMGTMGsA3RrVOnDtOnTwfg999/58SJE7Rt25YTJ04wdepUrFYrTzzxRJnW5aA+1iIVRn/GnYNhGByITWHLkbP2UHIwLqXAfm4uJrKtBmdSMjmTksmuEwnFOn5ETW/aRQTRIbIG16d9R9jPT2M6kwZnillgQD2IGm9rrTH7luCTiVweh4aboUOHEhsby3PPPUd0dDRt27ZlzZo19s6QR48etc/6CrYRHs888wwHDx7E19eXfv368cknnxAYGFgm9eRO2paamlqsGWFFqqrUVNtisIUtMyGVR3JGNqfy9Gs5FZ/GificnxNs2zOzC87K3STUl/aRQbSLqEH7iCAianoTn5rFyYQ0TsWnczIhjZN5jxOfztmUTJrW8qN9RBDtI4O4OiKIUL+ckXS/zoL1ufNamYpe0DfsSrjmIWg5CFz1Z0wqnsOGgjtKUUPJTp06RXx8PKGhoXh7e9tn+BVxBoZhkJqaSkxMDIGBgfbZpqXiZVlso4tO5QSXE3mCRm5n3cT07CKPY3ZzoU3dQNpH5oSS+kEEXmpCu5IwDPj+Bfg5ZwmVqPFww7+LDjci5aBKDAWvrHI7M8fExDi4EpHyExgYeMmV2eXyGIbB2ZRMW1BJSCswsuhkfBoxSYWPLrqQn6cbdXL6xeTrKxNg21YrwNO2MGRZs1pg9WOwZZ7tec8pcO2jCjZSJSjcXMBkMhEeHk5oaOhFFz0Uqcrc3d3zraYu5xmGQWJadp5WFNttoNyfz6YUvdBslsXgdGI6GYXcLrqQh6sL4TlBJTzQkzqBXoQHnO/oGx7giZ+nA27rZGfC8rHw53LABDe/Ae3HVHwdIqWkcHMRrq6u+gIQqUJy+6fYgkmeWz3x6aRnX3oIM0BSejYn49NIzSx63+IwmSDE10x4oBd17AHG9nN4TqtLTR8PXFwqWUtIZgosHgEHvgcXdxj8ga3vjEgVonAjIpVebv+UkznB5UTOrZ1TCSXrn1JcNX087C0qubeBwgO8CPY1U1QWcXUxEebvSZi/Jx5uVWzl6dSzsGAIHN8M7t4w9FNo3NPRVYmUmMKNiJQbi9UgJik9XyfZUwnpeabkv7isbCvRibZbQsXtn+Lv6Waft8U+h0uAFz7mov+q8/Zwtd8KKslkd04j8RR8egvE7AHPQBi+FOp1cHRVIqWicCMiBVitBnEpGZyMT7ff6olOKNntnZPx6UQnpmOxls2AzEv1T6kTaLvl41uMEFMlJMfAzs/B7AetbgMP7/I7l2HA0Y2w/D6IPwp+4XDncghtXn7nFClnTvI3gUjZMgyDc6lZ50e5xKcRe5G1cxzJ3dWFWjkjaHL7chSnlSIpPSv/7Z3clpWcocjRCen2WW0vl1vObRpbAPE839ekiFE3tts75pzWlEraP6WsnTkAv74N2xeAJWfB33XPQ6f7ocM94F2j7M5ltcK+r2DDm3B8k21bjYZw5woIiii784g4gMKNVEtpmRb7EN1T8ekF5xhJSCM9q2y+3CtagJd7zu0YW5Co4eNBXHKGvTXlZEIaScXon+JiglA/T1t/k5zjlez2jhd1Ar0I8TPj6uyh5HKd2GILGXtWAjkJuvbVkBpna01Z/yL88gZcPdK2LlNg/dKfKzvDtjzChrfgzD+2ba5maDsMrn8GfEMu++OIOJom8ZNKxWo1OBCbzM7jCcUaSlsUA4Ok9OwCM7ueSy3eMP9gX7O9RSTM34yrS+XqIJqWZSE6TyhLyih+p9q8ISi3RSXvrZ4w/3KaP0VsDAP2r4MNM+Hwz+e3N+kDXSZAxDW2uWb2rLDtE73L9rrJFa4cDF0ehlqtin++9AT4Yy78NhuSo23bPANsLUId7wO/sDL6YCLloyTf3wo3UixHz6RyKiGNVnUD8Pa4jAa/tHjbX+QWW7jItFg5ciaVg7HJHIxL4WBsSpkNxS2K2c2FIB8Panh7EOTjTpC3B0E+HgR5u1PDx4NAb3fcK1mYKUpqloX4lCzOpmVyLsX2SM7Ixt/TjcCcz2r7bB54lmYkT63WENy47AuvChJPwbHfwSiDFr20c7B5DsT8aXvu4mbrW3PNQxDWsuD+hgEH19tadw7+cH57o57Qegi4FjEj8clt8Mc8yEyyPferbWsBajfK1q9HpApQuLkEhZuSybJYmfX9fmat34/FauDqYqJFuL99Mb32kUGE+XsWfaCEE2RsmIX7to9wySq4sJ9UIU1vsrUs1O/k6EoqRsxf8Otbtg6+1jKe2NPdB9qNhqgHIaBu8d5zcpvtltKeFSUPWiHNbL+7K28FtzJaokGkgijcXILCTfEdiE1m4uLt7DhuW0E42NeDuOSCQ3jrBnnRPiKIdpE1aFDTJ2for22qeWL20j1uIddn/oi7ydYic9BaixiC7O93d3XBz9MNP7Mbfp7ueJtdcUF9NCqd7HQ48cf55/U6w7WP2G6jVLEWrmI5stHWUvL31+e3hbWy3cq5XCYTNOwOHe4Gr6Aidy/U2UPw+2yI3l30vp4Btv46TW5wzt+VVAsKN5egcFM0wzD4eOMRpn+9l/QsK/6ebvx7UCv+1aY2J+PT+OPIObYcPssfR86x91QiBUf6GnQw7eM+t1X0ct1m3/qbtTmfug7kUOA1tKkfZFt9OKIG9Wp4aYHSqiL275xWjMVgyQm6wU1t/T9aDan6rQFWqy3MbHjTdgsKABM0vxmumaB5X0QcSOHmEhRuLi06IZ3/W7qDn/+JA6Brk2Beu7UNtfzcbf0ELpCcmc3u4/FsP5bAjmPxBJ/bxp3WFVyRuRcAAxNx9W4gveN4aja95vL660jlkXjK1mrwx1zISLRt8wuHzg9Cq1uL7gNS2RhW+HvNBSOIPKDNMFs/mOAmjq1PRBRuLkXh5uJW7TjJMyt2k5CWhdnNhaf7NefOzhG4ZCbBh70gbl/xD2b/Yni4+nZArQ7SE2DLfNj43/MjcKo6cwB0uMs2t4yfVk4XqSxK8v2tf0YLCalZPLdyN19sPwlA67oBzBjSlsahvrYdVj9W/GDjFQTtxuR8MWhoqdPzDLB1UO10v63D7cZ3IHavo6sqHf+60Ok+WwdfT/3DR6QqU7ip5s6mZNL/7V84EZ+Gq4uJcdc35qEejc/Pb7JjMez63Da3xpivq88IGSkZNzNcfaftISLiYAo31dyHPx/kRHwadQK9mHXHVVxVP8/IjbMHYfVE28/dn1KwERGRKkFjAquxhLQsPtl4BIAp/VvkDzaWLPjfPZCZDPWvga6POahKERGRklG4qcY+/vUwSRnZNA3zo1fzC/rHrH/Jtt6NZwDc8j64uDqmSBERkRJSuKmmUjKymbPhEAAPXt8o/2rLB3+0LdIH8K+3IbCeAyoUEREpHYWbamrB70eJT80isqY3N7euff6FlDOw/D7AgKtHQYsBDqtRRESkNBRuqqH0LAvv/3wQgAe6N8I1t9XGMGDlQ5B0CoKvgBunO7BKERGR0lG4qYaWbDlObFIGtQM8GXRVnsX6/pgD+1bbJuAb/CF4+DiuSBERkVJSuKlmsixWZv9wAICx1zXEwy3nj0DMXvhmsu3nXlMhvI1jChQREblMCjfVzBfbT3IiPo1gXw9u71jftjErHZbebVv1uXEv6PSAY4sUERG5DAo31YjFavDfH/YDcPe1DfF0d7X1s/n2GYj5E3xCYOC74KI/FiIiUnVphuJqZM3uaA7GpuDv6caIjrVh5xLY8Cac3mXbYeBs8A11bJEiIiKXSeGmmjAMg1nr9+NFOjMb7MHvvcch4ajtRXcf6PEMNOnl2CJFRETKgMJNNfHz9r+4MXYuo8zfEngo2bbROxg63w/t7wbvGo4tUEREpIwo3Di7s4cwNr5Dp80fc51bhm1bUAO45iFoewe4ezm2PhERkTKmcOPMjv4G82/CZM3GDOwyGlK//yQCrh6staJERMRpaViMMzvyK1izOe5Wn2GZk/m87ccEtB+iYCMiIk5N4caZJccA8GV6GzZzJfd1b+TggkRERMqfwo0zSz4NQIwRyMCr6lA3yNvBBYmIiJQ/hRsnlnL2JACxBPCAWm1ERKSaULhxYlkJ0QDUqRtJoxBfB1cjIiJSMRRunJhXRhwA5sBwB1ciIiJScRRunFVWGmaLbbI+k1+Yg4sRERGpOAo3zipnpFSG4Y6nb5CDixEREak4CjfOKifcxBKAv5eHg4sRERGpOAo3zipnGHisEUiAl7uDixEREak4CjfOyh5uAhRuRESkWlG4cVa5t6XUciMiItWMwo2zym25IQB/L62PKiIi1YfCjZOyJtkm8FPLjYiIVDcKN07Kknh+XSk/T4UbERGpPhRunFXObakUj5q4upgcXIyIiEjFUbhxRoaBa2osABnmYAcXIyIiUrEUbpxRejwu1kwAsr1CHFyMiIhIxVK4cUY5w8ATDG+8vX0cXIyIiEjFUrhxRpqdWEREqjGFG2ekCfxERKQaU7hxRnkm8AvwVrgREZHqReHGGeW5LeXvqdmJRUSkelG4cUb221JaNFNERKofhRtnlLflRuFGRESqGYeHm3feeYfIyEg8PT3p1KkTmzZtuuT+M2fOpGnTpnh5eVGvXj0effRR0tPTK6jaKiK35Qa13IiISPXj0HCzePFiJk6cyJQpU9i6dStt2rShT58+xMTEFLr/ggULeOqpp5gyZQp79+5lzpw5LF68mKeffrqCK6/ktGimiIhUYw4NNzNmzODee+9lzJgxtGjRgtmzZ+Pt7c3cuXML3f/XX3+lS5cu3HHHHURGRnLDDTcwbNiwIlt7qhVLFqSeAWyLZuq2lIiIVDcOCzeZmZls2bKFXr16nS/GxYVevXqxcePGQt9zzTXXsGXLFnuYOXjwIF999RX9+vWrkJqrhJQ4wCDbcOEcfmq5ERGRasdh44Tj4uKwWCyEhYXl2x4WFsZff/1V6HvuuOMO4uLiuPbaazEMg+zsbO6///5L3pbKyMggIyPD/jwxMbFsPkBlldOZ+Az+WHFRuBERkWrH4R2KS+KHH37gpZde4r///S9bt25l2bJlrF69mhdeeOGi75k+fToBAQH2R7169SqwYgfIMzuxt4cr7q5V6lcsIiJy2RzWchMcHIyrqyunT5/Ot/306dPUqlWr0Pc8++yz3Hnnndxzzz0AtGrVipSUFMaOHcvkyZNxcSn4RT5p0iQmTpxof56YmOjcAcc+DDxA/W1ERKRactg/6z08PGjXrh3r1q2zb7Naraxbt46oqKhC35OamlogwLi6ugJgGEah7zGbzfj7++d7ODUtmikiItWcQ+fmnzhxIqNGjaJ9+/Z07NiRmTNnkpKSwpgxYwAYOXIkderUYfr06QD079+fGTNmcNVVV9GpUyf279/Ps88+S//+/e0hp9rTHDciIlLNOTTcDB06lNjYWJ577jmio6Np27Yta9assXcyPnr0aL6WmmeeeQaTycQzzzzDiRMnCAkJoX///rz44ouO+giVj2YnFhGRas5kXOx+jpNKTEwkICCAhIQE57xFNbcvHP2VcZkP49n2Vv4zpI2jKxIREblsJfn+1lAaZ5OvQ7FWBBcRkepH4cbZ2PvcqEOxiIhUTwo3ziQzBTKTAFvLjcKNiIhURwo3ziSn1SbDZCYZL4UbERGplhRunElOf5uzpiDApHAjIiLVksKNM8kJN3EEAmgouIiIVEsKN84k57bUaWsAgFpuRESkWlK4cSY5LTenLLbx/wo3IiJSHSncOJOccBOjlhsREanGFG6cSZ45bjzcXPB013pbIiJS/SjcOJO8sxN7qtVGRESqJ4UbZ5LbcmMEEqClF0REpJpSuHEWVusF4UYtNyIiUj0p3DiL9HiwZgFwBn+FGxERqbYUbpxFTn+bdLcAMnHXBH4iIlJtKdw4i5xwk+xeA9AwcBERqb4UbpxFTn+bBNeagMKNiIhUXwo3ziKn5eacSyCgcCMiItWXwo2zSIoGbBP4gRbNFBGR6kvhxllcsGimJvETEZHqSuHGWeTcljqZrUUzRUSkelO4cRY5LTfHM/0AhRsREam+FG6cRU7LzZGMnHDjrXAjIiLVk8KNM8jOhLSzAJy0qOVGRESqN4UbZ5ASC4Dh4kY8vri6mPDxcHVwUSIiIo6hcOMMcm5JZXsFY+CCv6cbJpPJwUWJiIg4hsKNM8jpTJzpGQLolpSIiFRvCjfOIKflJtVDSy+IiIgo3DiDnJabZHdbuNHsxCIiUp0p3DiDnJabBFfbiuAKNyIiUp0p3DiDnHBz1hQI6LaUiIhUbwo3ziAn3MTlLJqpcCMiItWZwo0zyAk30TmLZirciIhIdaZwU9UZhr1D8amcRTO1IriIiFRnCjdVXWYyZKUCWjRTREQEShFuIiMjmTZtGkePHi2PeqSkclpt8PAlJsMNULgREZHqrcTh5pFHHmHZsmU0bNiQ3r17s2jRIjIyMsqjNimOnP42+IaSkJYFKNyIiEj1Vqpws337djZt2kTz5s156KGHCA8PZ/z48WzdurU8apRLsYebMIUbERERLqPPzdVXX81bb73FyZMnmTJlCh9++CEdOnSgbdu2zJ07F8MwyrJOuZic21JWn1DSsiwA+Hu5ObIiERERhyr1t2BWVhbLly9n3rx5rF27ls6dO3P33Xdz/Phxnn76ab777jsWLFhQlrVKYXJabjI8g+2b/DRaSkREqrESh5utW7cyb948Fi5ciIuLCyNHjuSNN96gWbNm9n0GDRpEhw4dyrRQuYgLFs3083TD1cXkyIpEREQcqsThpkOHDvTu3Zt3332XgQMH4u5esJWgQYMG3H777WVSoBThgkUz1d9GRESquxKHm4MHDxIREXHJfXx8fJg3b16pi5ISyGm5ic9ZNFPhRkREqrsSdyiOiYnh999/L7D9999/548//iiToqQEclpuzpmCAM1OLCIiUuJwM27cOI4dO1Zg+4kTJxg3blyZFCXFZLXaw02coXWlREREoBThZs+ePVx99dUFtl911VXs2bOnTIqSYko9A4YFMBFj0dILIiIiUIpwYzabOX36dIHtp06dws1N86tUqNwJ/Lxrci7DNq9QgLfCjYiIVG8lDjc33HADkyZNIiEhwb4tPj6ep59+mt69e5dpcVKEQmYn9vdUwBQRkeqtxN+Er7/+Otdddx0RERFcddVVAGzfvp2wsDA++eSTMi9QLiF30UzfUBLTsgHdlhIRESlxuKlTpw47d+7ks88+Y8eOHXh5eTFmzBiGDRtW6Jw3Uo7yttzE5bTcKNyIiEg1V6p7GD4+PowdO7asa5GSytNyk3BMi2aKiIjAZawttWfPHo4ePUpmZma+7f/6178uuygpJq0ILiIiUkCpZigeNGgQu3btwmQy2Vf/Npls6xlZLJayrVAuLk+4SUzTbSkREREoxWipCRMm0KBBA2JiYvD29ubPP//kp59+on379vzwww/lUKJcVM5tKYtPCEkZ6lAsIiICpWi52bhxI99//z3BwcG4uLjg4uLCtddey/Tp03n44YfZtm1bedQphclpuUnxCAZSAIUbERGRErfcWCwW/Pxss+EGBwdz8uRJACIiIti3b1/ZVicXl50B6fEAJLjY1pXy9nDF3bXEv1IRERGnUuKWmyuvvJIdO3bQoEEDOnXqxKuvvoqHhwfvv/8+DRs2LI8apTC5I6VcPThn9QbUaiMiIgKlCDfPPPMMKSm2WyDTpk3j5ptvpmvXrtSsWZPFixeXeYFyEfZh4GEkpNv622hFcBERkVLclurTpw+33HILAI0bN+avv/4iLi6OmJgYevToUaoi3nnnHSIjI/H09KRTp05s2rTpovt2794dk8lU4HHTTTeV6txVVnK07b+anVhERCSfEoWbrKws3Nzc2L17d77tNWrUsA8FL6nFixczceJEpkyZwtatW2nTpg19+vQhJiam0P2XLVvGqVOn7I/du3fj6urKbbfdVqrzV1mFrSulcCMiIlKycOPu7k79+vXLdC6bGTNmcO+99zJmzBhatGjB7Nmz8fb2Zu7cuYXuX6NGDWrVqmV/rF27Fm9v72oYbvLMTqwJ/EREROxKfFtq8uTJPP3005w9e/ayT56ZmcmWLVvo1avX+YJcXOjVqxcbN24s1jHmzJnD7bffjo+PT6GvZ2RkkJiYmO/hFHJbbnwUbkRERPIqcYfiWbNmsX//fmrXrk1ERESBULF169ZiHysuLg6LxUJYWFi+7WFhYfz1119Fvn/Tpk3s3r2bOXPmXHSf6dOn8/zzzxe7pioj74rgCbm3pUq9moaIiIjTKPG34cCBA8uhjNKZM2cOrVq1omPHjhfdZ9KkSUycONH+PDExkXr16lVEeeVLt6VEREQKVeJwM2XKlDI7eXBwMK6urpw+fTrf9tOnT1OrVq1LvjclJYVFixYxbdq0S+5nNpsxm82XXWulk5ITbnxC7etKKdyIiIiUos9NWfLw8KBdu3asW7fOvs1qtbJu3TqioqIu+d4lS5aQkZHBiBEjyrvMyik51vZftdyIiIjkU+KWGxcXl0sO+y7pSKqJEycyatQo2rdvT8eOHZk5cyYpKSmMGTMGgJEjR1KnTh2mT5+e731z5sxh4MCB1KxZs6QfoerLTIEs20SK+ISQkHYU0FBwERERKEW4Wb58eb7nWVlZbNu2jY8++qhUHXeHDh1KbGwszz33HNHR0bRt25Y1a9bYOxkfPXoUF5f8DUz79u3jl19+4dtvvy3x+ZxCbn8bNy8w++m2lIiISB4mwzCMsjjQggULWLx4MV988UVZHK7cJCYmEhAQQEJCAv7+/o4up3SObYI5vSGwPsaEnTSe/DUWq8HvT/ckzN/T0dWJiIiUuZJ8f5dZn5vOnTvn6zsj5Sj5fGfi5IxsLFZbPlXLjYiISBmFm7S0NN566y3q1KlTFoeToqQUHAbu4eaCp7urA4sSERGpHErc5yYoKChfh2LDMEhKSsLb25tPP/20TIuTi8gdKeUTcn5dKa0ILiIiApQi3Lzxxhv5wo2LiwshISF06tSJoKCgMi1OLiJPy835FcE1O7GIiAiUItyMHj26HMqQEsnT50Zz3IiIiORX4j438+bNY8mSJQW2L1myhI8++qhMipIipORO4BeiYeAiIiIXKHG4mT59OsHBwQW2h4aG8tJLL5VJUVIErQguIiJyUSUON0ePHqVBgwYFtkdERHD06NEyKUqKkGfphcT03BXBFW5ERESgFOEmNDSUnTt3Fti+Y8eO6rkUQkXLSoPMJNvPeUZLqeVGRETEpsThZtiwYTz88MOsX78ei8WCxWLh+++/Z8KECdx+++3lUaPklduZ2NUDPAMUbkRERC5Q4tFSL7zwAocPH6Znz564udnebrVaGTlypPrcVAR7Z+IwMJnOz3OjcCMiIgKUItx4eHiwePFi/v3vf7N9+3a8vLxo1aoVERER5VGfXMg+DDwEQC03IiIiFyj1zG9NmjShSZMmZVmLFEeeCfwA+1BwzVAsIiJiU+I+N4MHD+aVV14psP3VV1/ltttuK5Oi5BLyLL0AkGCfoVjhRkREBEoRbn766Sf69etXYHvfvn356aefyqQouYQ8LTeGYZyfxM9b4UZERARKEW6Sk5Px8PAosN3d3Z3ExMQyKUouIc/SC+lZVjItVkAtNyIiIrlKHG5atWrF4sWLC2xftGgRLVq0KJOi5BLyLL2Q25nY1cWEj4erA4sSERGpPErcofjZZ5/llltu4cCBA/To0QOAdevWsWDBApYuXVrmBcoF8iy9YJ+d2NMt30rtIiIi1VmJw03//v1ZsWIFL730EkuXLsXLy4s2bdrw/fffU6NGjfKoUfLKs/RCQoqGgYuIiFyoVEPBb7rpJm666SYAEhMTWbhwIY8//jhbtmzBYrGUaYGSR1Y6ZCTYfvYJISFW4UZERORCJe5zk+unn35i1KhR1K5dm//85z/06NGD3377rSxrkwvl9rdxcQevIM1OLCIiUogStdxER0czf/585syZQ2JiIkOGDCEjI4MVK1aoM3FFSMkzO7HJpBXBRUREClHslpv+/fvTtGlTdu7cycyZMzl58iRvv/12edYmF8rT3wa09IKIiEhhit1y8/XXX/Pwww/zwAMPaNkFR7lg6QWFGxERkYKK3XLzyy+/kJSURLt27ejUqROzZs0iLi6uPGuTC+WZwA8UbkRERApT7HDTuXNnPvjgA06dOsV9993HokWLqF27NlarlbVr15KUlFSedQrkm8APzi+aqXAjIiJyXolHS/n4+HDXXXfxyy+/sGvXLh577DFefvllQkND+de//lUeNUquC1puEnMWzdSK4CIiIueVeig4QNOmTXn11Vc5fvw4CxcuLKua5GJS1KFYRESkKJcVbnK5uroycOBAVq5cWRaHk4uxL71guy2lcCMiIlJQmYQbqSDJGi0lIiJSFIWbqiI7E9LjbT/7hJKZbSUty7bUhcKNiIjIeQo3VUVufxuTK3gF2WcnBvD1LNUSYSIiIk5J4aaqyLv0gouL/ZaUn6cbri4mBxYmIiJSuSjcVBXJ+ee4UX8bERGRwincVBX2pRfCAIUbERGRi1G4qSoKTOCXsyK4JvATERHJR+GmqtDSCyIiIsWicFNVaNFMERGRYlG4qSpSLjKBn7fCjYiISF4KN1VF7mipnKUXzqao5UZERKQwCjdVRe66UjktN/tjkwFoEOzjqIpEREQqJYWbqsCSBWlnbT/7hGK1GvxzOgmAK8J8HViYiIhI5aNwUxWkxNn+a3IB7xqciE8jNdOCh6sLETXVciMiIpKXwk1VkNuZ2DsYXFz5J8bWatMwxAd3V/0KRURE8tI3Y1VgX3rB1t9mX7Stv02TMD9HVSQiIlJpKdxUBXkXzQR7f5um6m8jIiJSgMJNVZCcf12pfTnhRi03IiIiBSncVAV5ll6wWA32x9huSzVVuBERESlA4aYqyLP0wtGzqWRkWzG7uVCvhrdj6xIREamEFG6qgjxLL/xtvyXli6uLyYFFiYiIVE4KN1VBnqUX7JP3heqWlIiISGEUbqqCPEsv7Dtt629zRS2FGxERkcIo3FR2lmxIPWP72SdUyy6IiIgUQeGmsks9AxiAiSzPIA7kLJjZRLelRERECqVwU9nZl16oyZFzGWRZDHw8XKkT6OXYukRERCophZvKLvn8SKncZRcah/nhopFSIiIihVK4qexSzo+U+lvLLoiIiBTJ4eHmnXfeITIyEk9PTzp16sSmTZsuuX98fDzjxo0jPDwcs9nMFVdcwVdffVVB1TpAcsE5bq7QzMQiIiIX5ebIky9evJiJEycye/ZsOnXqxMyZM+nTpw/79u0jNDS0wP6ZmZn07t2b0NBQli5dSp06dThy5AiBgYEVX3xFSTm/rtTfhxVuREREiuLQcDNjxgzuvfdexowZA8Ds2bNZvXo1c+fO5amnniqw/9y5czl79iy//vor7u7uAERGRlZkyRUvZwK/bK9gDp9JBRRuRERELsVht6UyMzPZsmULvXr1Ol+Miwu9evVi48aNhb5n5cqVREVFMW7cOMLCwrjyyit56aWXsFgsFz1PRkYGiYmJ+R5VSk7LTYzVH4vVwN/TjTB/s4OLEhERqbwcFm7i4uKwWCyEhYXl2x4WFkZ0dHSh7zl48CBLly7FYrHw1Vdf8eyzz/Kf//yHf//73xc9z/Tp0wkICLA/6tWrV6afo9zltNwcyfABbK02JpNGSomIiFyMwzsUl4TVaiU0NJT333+fdu3aMXToUCZPnszs2bMv+p5JkyaRkJBgfxw7dqwCKy4DOS03f6fY5rVpoltSIiIil+SwPjfBwcG4urpy+vTpfNtPnz5NrVq1Cn1PeHg47u7uuLq62rc1b96c6OhoMjMz8fDwKPAes9mM2VxFb+NYLfah4LvizYBFw8BFRESK4LCWGw8PD9q1a8e6devs26xWK+vWrSMqKqrQ93Tp0oX9+/djtVrt2/7++2/Cw8MLDTZVXupZMGyfdWucLdCpM7GIiMilOfS21MSJE/nggw/46KOP2Lt3Lw888AApKSn20VMjR45k0qRJ9v0feOABzp49y4QJE/j7779ZvXo1L730EuPGjXPURyhfObekDK8aHDqXCWg1cBERkaI4dCj40KFDiY2N5bnnniM6Opq2bduyZs0aeyfjo0eP4uJyPn/Vq1ePb775hkcffZTWrVtTp04dJkyYwJNPPumoj1C+cibwyzDXxDCgho8Hwb5V9BabiIhIBTEZhmE4uoiKlJiYSEBAAAkJCfj7+zu6nEvb+Tksu5eYmh3peOIROjeswaKxhd+yExERcWYl+f6uUqOlqp2clps4AgD1txERESkOhZvKLKfPzfFM2wgphRsREZGiKdxUZjkT+B1IOz+Bn4iIiFyawk1lltNyczDNG4ArNMeNiIhIkRRuKrOcPjexRgChfmYCvZ1wLh8REZEypnBTmeXMThxnBOiWlIiISDEp3FRWVuv50VIKNyIiIsWmcFNZpZ0DwwLAGQLU30ZERKSYFG4qq5zOxAn4koWbll0QEREpJoWbyiq3M7HVNgtjk1C13IiIiBSHwk1llduZmADqBHrh5+nu4IJERESqBoWbyipPZ+Im6m8jIiJSbAo3lVXK+TluNFJKRESk+BRuKqtkzXEjIiJSGgo3lVVuy42GgYuIiJSIwk0llZ14GrDNcdNYI6VERESKTeGmkrIk2VpuXH3D8PZwc3A1IiIiVYfCTWVkGLil2frcBIbWcXAxIiIiVYvCTWWUdg5XIxuAsPC6Di5GRESkalG4qYxyJvBLNLxpXDvYwcWIiIhULQo3lZCRbOtMHGsE0CRUw8BFRERKQuGmEkqIOwnYRko1DPFxcDUiIiJVi8JNJXQm+jgAaR418HR3dXA1IiIiVYvCTSWUdMbWcmN4hzi4EhERkapH4aYSykyIBsA9sJaDKxEREal6FG4qo5wVwf1q1nZwISIiIlWPwk0lcyA2GXPGGQDq1490bDEiIiJVkMJNJfO/P44RYbINBQ8Mb+TgakRERKoehZtKxGI1+H7rXgJNKRiYoIbCjYiISEkp3FQiv+yPwy/5kO1JQF3w8HZsQSIiIlWQwk0lsnTLcRq6nALAFHyFg6sRERGpmhRuKomEtCy++TOaRibbHDcEN3FsQSIiIlWUwk0lsWrHSTKzrbT2tA0DV7gREREpHYWbSmLpFtuSC83dbRP4odtSIiIipaJwUwnsj0li+7F4vFyy8U/PuS1VUy03IiIipaFwUwksyWm1ubVBFibDAh5+4KelF0REREpD4cbBsi1Wlm89AcAt9VNtG4Mbg8nkwKpERESqLoUbB/t5fxwxSRnU8PGglb0zsfrbiIiIlJbCjYMt/cN2S2pA29q4nd1v26j+NiIiIqWmcONA8amZrN1jW0fq1nZ1Ie4f2wsaBi4iIlJqCjcOtHLHSTItVpqH+9My3D9PuNFtKRERkdJSuHGg3LltbmtXF1JiISMBMEGNho4tTEREpApTuHGQfdFJ7DyegJuLiQFta0Pc37YXgiLA3dOxxYmIiFRhCjcOsnTLMQB6NAulpq/5/C0pdSYWERG5LAo3DpBlsbJ8m20m4tva17NtVH8bERGRMqFw4wA//R1LXHIGwb4edG8aYtuYe1squLHjChMREXECCjcOsCRnbpuBbevg7przKzijlhsREZGyoHBTwc6mZLLuL9vcNoPb1bVtzEqHc0dsP6vPjYiIyGVRuKlgK7efIMticGUdf5qH+9s2nj0IGGAOAN9Qh9YnIiJS1SncVKCEtCwWbDoKwG3t6p1/wd7fpokWzBQREblMbo4uoLrYsD+Ox5fs4FRCOj4ervyrTe3zL57RsgsiIiJlReGmnKVnWXhlzV/M23AYgMia3rwxtC1BPh7nd9KaUiIiImVG4aYc7TqewKOfb2d/TDIAIzrX5+l+zfH2uOCy596WUmdiERGRy6ZwUw6yLVZm/3iAmd/9Q7bVIMTPzKu3tub6poV0FjYMiNtv+1nDwEVERC6bwk0ZOxyXwqOfb2fb0XgA+l5ZixcHtaJG3ttQeSVFQ2YSmFygRoOKK1RERMRJKdyUEcMwWLDpKP/+ci9pWRb8zG48P6Alg66qg+lSI6ByOxMHRYKbuUJqFRERcWYKN2Vk8eZjTF6+G4CohjV5fUgb6gR6Ff1G9bcREREpU5Vinpt33nmHyMhIPD096dSpE5s2bbrovvPnz8dkMuV7eHp6VmC1hRt4VR1a1w3gmZua89k9nYoXbCBPfxuFGxERkbLg8JabxYsXM3HiRGbPnk2nTp2YOXMmffr0Yd++fYSGFj5br7+/P/v27bM/v+Rtnwri6e7K8ge74OpSwlrsE/ipM7GIiEhZcHjLzYwZM7j33nsZM2YMLVq0YPbs2Xh7ezN37tyLvsdkMlGrVi37IywsrAIrvrgSBxvQBH4iIiJlzKHhJjMzky1bttCrVy/7NhcXF3r16sXGjRsv+r7k5GQiIiKoV68eAwYM4M8//7zovhkZGSQmJuZ7VBqZqRB/zPazWm5ERETKhEPDTVxcHBaLpUDLS1hYGNHR0YW+p2nTpsydO5cvvviCTz/9FKvVyjXXXMPx48cL3X/69OkEBATYH/Xq1St0P4c4ewAwwDMQvGs6uhoRERGn4PDbUiUVFRXFyJEjadu2Ld26dWPZsmWEhITw3nvvFbr/pEmTSEhIsD+OHTtWwRVfgn3ZhSu0YKaIiEgZcWiH4uDgYFxdXTl9+nS+7adPn6ZWrVrFOoa7uztXXXUV+/fvL/R1s9mM2VxJ54/RmlIiIiJlzqEtNx4eHrRr145169bZt1mtVtatW0dUVFSxjmGxWNi1axfh4eHlVWb5UWdiERGRMufwoeATJ05k1KhRtG/fno4dOzJz5kxSUlIYM2YMACNHjqROnTpMnz4dgGnTptG5c2caN25MfHw8r732GkeOHOGee+5x5McoHQ0DFxERKXMODzdDhw4lNjaW5557jujoaNq2bcuaNWvsnYyPHj2Ki8v5BqZz585x7733Eh0dTVBQEO3atePXX3+lRYsWjvoIpZN3wUzNTiwiIlJmTIZhGI4uoiIlJiYSEBBAQkIC/v7+jisk4QS80QJc3GByNLi6O64WERGRSq4k399VbrSU08i7YKaCjYiISJlRuHGUvMPARUREpMwo3DiKfTXwxo6tQ0RExMko3DiKWm5ERETKhcKNo2gCPxERkXKhcOMImSmQmLMWllpuREREypTCjSOcyZnfxrsmeNdwbC0iIiJORuHGEXJvSWnyPhERkTKncOMI6m8jIiJSbhRuHEELZoqIiJQbhRtH0IKZIiIi5UbhpqJZrVowU0REpBwp3FS0xBOQnQYu7hAU4ehqREREnI7CTUXLvSVVo6EWzBQRESkHCjcVLXeOG3UmFhERKRcKNxXN3plY4UZERKQ8KNxUNE3gJyIiUq4UbiqSYWgYuIiISDlTuKkoVgt8+QgknQJXD92WEhERKSduji6gWsjOgGVjYc8KwAT9XgevQAcXJSIi4pwUbspbRjIsHgEH19vmthn8IbQc6OiqREREnJbCTXlKPQuf3QYn/gB3H7j9U2jUw9FViYiIODWFm/KSeBI+GQSxf4FXEAxfCnXbO7oqERERp6dwUx7OHIBPBkL8UfALhzuXQ2hzR1clIiJSLSjclLVTO+HTWyAl1rbEwp0rtIaUiIhIBVK4KUtHfoUFQyEjEWq1ghHLwDfU0VWJiIhUKwo3ZWX/d7BoOGSnQ/1r4I5F4Bng6KpERESqHYWbshIYCR6+0LA73DYf3L0cXJCIiEj1pHBTVoIbw93fQmB9cHV3dDUiIiLVlsJNWarZyNEViIiIVHtaW0pEREScisKNiIiIOBWFGxEREXEqCjciIiLiVBRuRERExKko3IiIiIhTUbgRERERp6JwIyIiIk5F4UZEREScisKNiIiIOBWFGxEREXEqCjciIiLiVBRuRERExKlUu1XBDcMAIDEx0cGViIiISHHlfm/nfo9fSrULN0lJSQDUq1fPwZWIiIhISSUlJREQEHDJfUxGcSKQE7FarZw8eRI/Pz9MJlOZHjsxMZF69epx7Ngx/P39y/TYUpCud8XS9a5Yut4VS9e7YpXmehuGQVJSErVr18bF5dK9aqpdy42Liwt169Yt13P4+/vrf44KpOtdsXS9K5aud8XS9a5YJb3eRbXY5FKHYhEREXEqCjciIiLiVBRuypDZbGbKlCmYzWZHl1It6HpXLF3viqXrXbF0vStWeV/vatehWERERJybWm5ERETEqSjciIiIiFNRuBERERGnonAjIiIiTkXhpoy88847REZG4unpSadOndi0aZOjS3IaP/30E/3796d27dqYTCZWrFiR73XDMHjuuecIDw/Hy8uLXr168c8//zim2Cpu+vTpdOjQAT8/P0JDQxk4cCD79u3Lt096ejrjxo2jZs2a+Pr6MnjwYE6fPu2giqu2d999l9atW9snMouKiuLrr7+2v65rXb5efvllTCYTjzzyiH2brnnZmTp1KiaTKd+jWbNm9tfL81or3JSBxYsXM3HiRKZMmcLWrVtp06YNffr0ISYmxtGlOYWUlBTatGnDO++8U+jrr776Km+99RazZ8/m999/x8fHhz59+pCenl7BlVZ9P/74I+PGjeO3335j7dq1ZGVlccMNN5CSkmLf59FHH2XVqlUsWbKEH3/8kZMnT3LLLbc4sOqqq27durz88sts2bKFP/74gx49ejBgwAD+/PNPQNe6PG3evJn33nuP1q1b59uua162WrZsyalTp+yPX375xf5auV5rQy5bx44djXHjxtmfWywWo3bt2sb06dMdWJVzAozly5fbn1utVqNWrVrGa6+9Zt8WHx9vmM1mY+HChQ6o0LnExMQYgPHjjz8ahmG7tu7u7saSJUvs++zdu9cAjI0bNzqqTKcSFBRkfPjhh7rW5SgpKclo0qSJsXbtWqNbt27GhAkTDMPQn++yNmXKFKNNmzaFvlbe11otN5cpMzOTLVu20KtXL/s2FxcXevXqxcaNGx1YWfVw6NAhoqOj813/gIAAOnXqpOtfBhISEgCoUaMGAFu2bCErKyvf9W7WrBn169fX9b5MFouFRYsWkZKSQlRUlK51ORo3bhw33XRTvmsL+vNdHv755x9q165Nw4YNGT58OEePHgXK/1pXu4Uzy1pcXBwWi4WwsLB828PCwvjrr78cVFX1ER0dDVDo9c99TUrHarXyyCOP0KVLF6688krAdr09PDwIDAzMt6+ud+nt2rWLqKgo0tPT8fX1Zfny5bRo0YLt27frWpeDRYsWsXXrVjZv3lzgNf35LludOnVi/vz5NG3alFOnTvH888/TtWtXdu/eXe7XWuFGRAo1btw4du/ene8euZS9pk2bsn37dhISEli6dCmjRo3ixx9/dHRZTunYsWNMmDCBtWvX4unp6ehynF7fvn3tP7du3ZpOnToRERHB559/jpeXV7meW7elLlNwcDCurq4FenifPn2aWrVqOaiq6iP3Guv6l63x48fz5Zdfsn79eurWrWvfXqtWLTIzM4mPj8+3v6536Xl4eNC4cWPatWvH9OnTadOmDW+++aaudTnYsmULMTExXH311bi5ueHm5saPP/7IW2+9hZubG2FhYbrm5SgwMJArrriC/fv3l/ufb4Wby+Th4UG7du1Yt26dfZvVamXdunVERUU5sLLqoUGDBtSqVSvf9U9MTOT333/X9S8FwzAYP348y5cv5/vvv6dBgwb5Xm/Xrh3u7u75rve+ffs4evSorncZsVqtZGRk6FqXg549e7Jr1y62b99uf7Rv357hw4fbf9Y1Lz/JyckcOHCA8PDw8v/zfdldksVYtGiRYTabjfnz5xt79uwxxo4dawQGBhrR0dGOLs0pJCUlGdu2bTO2bdtmAMaMGTOMbdu2GUeOHDEMwzBefvllIzAw0Pjiiy+MnTt3GgMGDDAaNGhgpKWlObjyqueBBx4wAgICjB9++ME4deqU/ZGammrf5/777zfq169vfP/998Yff/xhREVFGVFRUQ6suup66qmnjB9//NE4dOiQsXPnTuOpp54yTCaT8e233xqGoWtdEfKOljIMXfOy9Nhjjxk//PCDcejQIWPDhg1Gr169jODgYCMmJsYwjPK91go3ZeTtt9826tevb3h4eBgdO3Y0fvvtN0eX5DTWr19vAAUeo0aNMgzDNhz82WefNcLCwgyz2Wz07NnT2Ldvn2OLrqIKu86AMW/ePPs+aWlpxoMPPmgEBQUZ3t7exqBBg4xTp045rugq7K677jIiIiIMDw8PIyQkxOjZs6c92BiGrnVFuDDc6JqXnaFDhxrh4eGGh4eHUadOHWPo0KHG/v377a+X57U2GYZhXH77j4iIiEjloD43IiIi4lQUbkRERMSpKNyIiIiIU1G4EREREaeicCMiIiJOReFGREREnIrCjYiIiDgVhRsRqZZMJhMrVqxwdBkiUg4UbkSkwo0ePRqTyVTgceONNzq6NBFxAm6OLkBEqqcbb7yRefPm5dtmNpsdVI2IOBO13IiIQ5jNZmrVqpXvERQUBNhuGb377rv07dsXLy8vGjZsyNKlS/O9f9euXfTo0QMvLy9q1qzJ2LFjSU5OzrfP3LlzadmyJWazmfDwcMaPH5/v9bi4OAYNGoS3tzdNmjRh5cqV9tfOnTvH8OHDCQkJwcvLiyZNmhQIYyJSOSnciEil9OyzzzJ48GB27NjB8OHDuf3229m7dy8AKSkp9OnTh6CgIDZv3sySJUv47rvv8oWXd999l3HjxjF27Fh27drFypUrady4cb5zPP/88wwZMoSdO3fSr18/hg8fztmzZ+3n37NnD19//TV79+7l3XffJTg4uOIugIiUXpksvykiUgKjRo0yXF1dDR8fn3yPF1980TAM2+rk999/f773dOrUyXjggQcMwzCM999/3wgKCjKSk5Ptr69evdpwcXExoqOjDcMwjNq1axuTJ0++aA2A8cwzz9ifJycnG4Dx9ddfG4ZhGP379zfGjBlTNh9YRCqU+tyIiENcf/31vPvuu/m21ahRw/5zVFRUvteioqLYvn07AHv37qVNmzb4+PjYX+/SpQtWq5V9+/ZhMpk4efIkPXv2vGQNrVu3tv/s4+ODv78/MTExADzwwAMMHjyYrVu3csMNNzBw4ECuueaaUn1WEalYCjci4hA+Pj4FbhOVFS8vr2Lt5+7unu+5yWTCarUC0LdvX44cOcJXX33F2rVr6dmzJ+PGjeP1118v83pFpGypz42IVEq//fZbgefNmzcHoHnz5uzYsYOUlBT76xs2bMDFxYWmTZvi5+dHZGQk69atu6waQkJCGDVqFJ9++ikzZ87k/fffv6zjiUjFUMuNiDhERkYG0dHR+ba5ubnZO+0uWbKE9u3bc+211/LZZ5+xadMm5syZA8Dw4cOZMmUKo0aNYurUqcTGxvLQQw9x5513EhYWBsDUqVO5//77CQ0NpW/fviQlJbFhwwYeeuihYtX33HPP0a5dO1q2bElGRgZffvmlPVyJSOWmcCMiDrFmzRrCw8PzbWvatCl//fUXYBvJtGjRIh588EHCw8NZuHAhLVq0AMDb25tvvvmGCRMm0KFDB7y9vRk8eDAzZsywH2vUqFGkp6fzxhtv8PjjjxMcHMytt95a7Po8PDyYNGkShw8fxsvLi65du7Jo0aIy+OQiUt5MhmEYji5CRCQvk8nE8uXLGThwoKNLEZEqSH1uRERExKko3IiIiIhTUZ8bEal0dLdcRC6HWm5ERETEqSjciIiIiFNRuBERERGnonAjIiIiTkXhRkRERJyKwo2IiIg4FYUbERERcSoKNyIiIuJUFG5ERETEqfw/XQLmibxqeakAAAAASUVORK5CYII=\n" }, "metadata": {} } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "wwFc-R4KtO_m" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [], "metadata": { "id": "nbww4QCJtPD9" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [], "metadata": { "id": "2U9UCh7ctPHC" }, "execution_count": null, "outputs": [] } ] }