Fashion_MNIST_Demo.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Fashion MNIST Demo.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8Kws3EV0uiw-",
        "colab_type": "text"
      },
      "source": [
        "# Project 1: Fashion MNIST Demo\n",
        "## Training a Neural Network to Classify Images of Clothing"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4gazQJclyMRV",
        "colab_type": "text"
      },
      "source": [
        "### 1. Import Packages & Load Data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_3ditccHt-rm",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "%tensorflow_version 2.x"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "a5A1AdfDuiEK",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "7d1f2e15-6d93-4fab-af47-56bd59dfc09c"
      },
      "source": [
        "from __future__ import absolute_import, division, print_function, unicode_literals\n",
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "print(tf.__version__)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "2.2.0\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ROTrGQrIu-UB",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 153
        },
        "outputId": "c95b9751-6b6b-478c-9542-dc63dcfc682b"
      },
      "source": [
        "fashion_mnist = keras.datasets.fashion_mnist\n",
        "(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()\n",
        "# split data\n",
        "# train data - teach model\n",
        "# test data  - evaluate model"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz\n",
            "32768/29515 [=================================] - 0s 0us/step\n",
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz\n",
            "26427392/26421880 [==============================] - 1s 0us/step\n",
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz\n",
            "8192/5148 [===============================================] - 0s 0us/step\n",
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz\n",
            "4423680/4422102 [==============================] - 0s 0us/step\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yUFqQgy4yStq",
        "colab_type": "text"
      },
      "source": [
        "### 2. Explore Data"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "YFEPaWFrzzjp",
        "colab_type": "text"
      },
      "source": [
        "### ```class_names``` explanation\n",
        "```python\n",
        "class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n",
        "               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'] # Set our labels\n",
        "```\n",
        "\n",
        "```python\n",
        "class_index = [0, 1 , 2, 3 , 4, 5, 6, 7, 8, 9]\n",
        "```"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DGVmx5ScvCZp",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n",
        "               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'] # Set our labels"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9TM5wWLMvC6L",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "ee3bc4e1-4a34-4116-8970-e401f1f43d74"
      },
      "source": [
        "train_images.shape # 60000 images, 28*28 (784) pixels"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(60000, 28, 28)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IvjKTWYYvLGh",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "3b327bed-a459-47e3-c7a0-eb33525e151a"
      },
      "source": [
        "test_images.shape # 10000 images, 28*28 (784) pixels"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(10000, 28, 28)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tN2WmgExvQzo",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 281
        },
        "outputId": "09bc59e3-5724-4083-bd7d-ac87b807ea6c"
      },
      "source": [
        "plt.figure()\n",
        "plt.imshow(train_images[0])\n",
        "plt.colorbar()\n",
        "plt.grid(False)\n",
        "plt.title('Ankle Boot')\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Lqo7sy670o0n",
        "colab_type": "text"
      },
      "source": [
        "We scale the values to a range of 0 - 1. So we divide the values by 255.\n",
        "* training set + testing set to be preprocesed in the same way"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GhmTcQYrvTFt",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train_images = train_images / 255.0\n",
        "\n",
        "test_images = test_images / 255.0\n",
        "# each element for each image represents the intensity of the corresponding pixel\n",
        "# with a value between [0, 255].\n",
        "# We rescale this image by dividing each pixel’s value by 255\n",
        "# scales features to [0, 1]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lpMzuWIPvUt8",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 589
        },
        "outputId": "0a98d540-a449-4b34-88b0-062b7a9e6140"
      },
      "source": [
        "plt.figure(figsize=(10,10)) # Data verification\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(train_images[i], cmap=plt.cm.binary)\n",
        "    plt.xlabel(class_names[train_labels[i]])\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 720x720 with 25 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RqxQod3GyXb0",
        "colab_type": "text"
      },
      "source": [
        "### 3. Choose an Algorithm\n",
        "\n",
        "ADAM: find individual learning rates for each parameter\n",
        "\n",
        "SPARSE CATEGORICAL CROSSENTROPY: measure the dissimilarity between predicted class probability & observed class labels\n",
        "\n",
        "RELU: introduces nonlinearity to our model "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Wvgyi9EfvWIT",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model = keras.Sequential([\n",
        "    keras.layers.Flatten(input_shape=(28, 28)), # 2d -> 1d array\n",
        "    keras.layers.Dense(128, activation='relu'), # 128 neurons\n",
        "    keras.layers.Dense(10) # output layer, 10 neurons\n",
        "])\n",
        "\n",
        "model.compile(optimizer='adam', # how our model is updated\n",
        "              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), # calc error\n",
        "              metrics=['accuracy']) # calc accuracy"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "YhT3s1xQyaeS",
        "colab_type": "text"
      },
      "source": [
        "### 4. Train Your Model\n",
        "\n",
        "$ model.fit(x, y, epochs=EPOCHS, verbose=VERBOSE, callbacks=CALLBACKS) $"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6SBYQ6lSvZzr",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "8491b030-39c5-4edc-caf4-9e3bdb8d9805"
      },
      "source": [
        "model.fit(train_images, train_labels, epochs=100)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.4968 - accuracy: 0.8243\n",
            "Epoch 2/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.3754 - accuracy: 0.8645\n",
            "Epoch 3/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.3385 - accuracy: 0.8766\n",
            "Epoch 4/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.3142 - accuracy: 0.8841\n",
            "Epoch 5/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2959 - accuracy: 0.8910\n",
            "Epoch 6/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2810 - accuracy: 0.8961\n",
            "Epoch 7/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2714 - accuracy: 0.8995\n",
            "Epoch 8/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2588 - accuracy: 0.9033\n",
            "Epoch 9/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2495 - accuracy: 0.9077\n",
            "Epoch 10/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2391 - accuracy: 0.9100\n",
            "Epoch 11/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2334 - accuracy: 0.9129\n",
            "Epoch 12/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2252 - accuracy: 0.9157\n",
            "Epoch 13/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2161 - accuracy: 0.9187\n",
            "Epoch 14/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2102 - accuracy: 0.9214\n",
            "Epoch 15/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.2063 - accuracy: 0.9230\n",
            "Epoch 16/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1987 - accuracy: 0.9259\n",
            "Epoch 17/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1941 - accuracy: 0.9276\n",
            "Epoch 18/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1900 - accuracy: 0.9285\n",
            "Epoch 19/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1842 - accuracy: 0.9306\n",
            "Epoch 20/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1784 - accuracy: 0.9324\n",
            "Epoch 21/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1757 - accuracy: 0.9340\n",
            "Epoch 22/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1705 - accuracy: 0.9355\n",
            "Epoch 23/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1678 - accuracy: 0.9363\n",
            "Epoch 24/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1620 - accuracy: 0.9396\n",
            "Epoch 25/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1599 - accuracy: 0.9395\n",
            "Epoch 26/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1560 - accuracy: 0.9409\n",
            "Epoch 27/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1490 - accuracy: 0.9444\n",
            "Epoch 28/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1486 - accuracy: 0.9437\n",
            "Epoch 29/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1446 - accuracy: 0.9457\n",
            "Epoch 30/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1410 - accuracy: 0.9471\n",
            "Epoch 31/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1380 - accuracy: 0.9484\n",
            "Epoch 32/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1343 - accuracy: 0.9497\n",
            "Epoch 33/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1338 - accuracy: 0.9489\n",
            "Epoch 34/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1317 - accuracy: 0.9502\n",
            "Epoch 35/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1270 - accuracy: 0.9520\n",
            "Epoch 36/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1248 - accuracy: 0.9530\n",
            "Epoch 37/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1253 - accuracy: 0.9530\n",
            "Epoch 38/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1190 - accuracy: 0.9563\n",
            "Epoch 39/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1197 - accuracy: 0.9553\n",
            "Epoch 40/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1181 - accuracy: 0.9556\n",
            "Epoch 41/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1142 - accuracy: 0.9580\n",
            "Epoch 42/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1125 - accuracy: 0.9578\n",
            "Epoch 43/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1085 - accuracy: 0.9586\n",
            "Epoch 44/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1104 - accuracy: 0.9584\n",
            "Epoch 45/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1048 - accuracy: 0.9603\n",
            "Epoch 46/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1041 - accuracy: 0.9610\n",
            "Epoch 47/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1029 - accuracy: 0.9611\n",
            "Epoch 48/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1012 - accuracy: 0.9620\n",
            "Epoch 49/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.1019 - accuracy: 0.9625\n",
            "Epoch 50/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0976 - accuracy: 0.9637\n",
            "Epoch 51/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0977 - accuracy: 0.9629\n",
            "Epoch 52/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0952 - accuracy: 0.9646\n",
            "Epoch 53/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0933 - accuracy: 0.9642\n",
            "Epoch 54/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0924 - accuracy: 0.9648\n",
            "Epoch 55/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0906 - accuracy: 0.9653\n",
            "Epoch 56/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0891 - accuracy: 0.9663\n",
            "Epoch 57/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0867 - accuracy: 0.9674\n",
            "Epoch 58/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0857 - accuracy: 0.9674\n",
            "Epoch 59/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0853 - accuracy: 0.9682\n",
            "Epoch 60/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0862 - accuracy: 0.9676\n",
            "Epoch 61/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0818 - accuracy: 0.9686\n",
            "Epoch 62/100\n",
            "1875/1875 [==============================] - 5s 3ms/step - loss: 0.0827 - accuracy: 0.9692\n",
            "Epoch 63/100\n",
            "1875/1875 [==============================] - 5s 3ms/step - loss: 0.0829 - accuracy: 0.9692\n",
            "Epoch 64/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0796 - accuracy: 0.9696\n",
            "Epoch 65/100\n",
            "1875/1875 [==============================] - 5s 3ms/step - loss: 0.0786 - accuracy: 0.9706\n",
            "Epoch 66/100\n",
            "1875/1875 [==============================] - 5s 2ms/step - loss: 0.0774 - accuracy: 0.9708\n",
            "Epoch 67/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0762 - accuracy: 0.9718\n",
            "Epoch 68/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0752 - accuracy: 0.9716\n",
            "Epoch 69/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0756 - accuracy: 0.9716\n",
            "Epoch 70/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0718 - accuracy: 0.9723\n",
            "Epoch 71/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0726 - accuracy: 0.9735\n",
            "Epoch 72/100\n",
            "1875/1875 [==============================] - 5s 2ms/step - loss: 0.0718 - accuracy: 0.9740\n",
            "Epoch 73/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0721 - accuracy: 0.9734\n",
            "Epoch 74/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0696 - accuracy: 0.9735\n",
            "Epoch 75/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0692 - accuracy: 0.9739\n",
            "Epoch 76/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0691 - accuracy: 0.9735\n",
            "Epoch 77/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0649 - accuracy: 0.9761\n",
            "Epoch 78/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0662 - accuracy: 0.9749\n",
            "Epoch 79/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0667 - accuracy: 0.9755\n",
            "Epoch 80/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0659 - accuracy: 0.9753\n",
            "Epoch 81/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0665 - accuracy: 0.9755\n",
            "Epoch 82/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0648 - accuracy: 0.9752\n",
            "Epoch 83/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0623 - accuracy: 0.9769\n",
            "Epoch 84/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0610 - accuracy: 0.9782\n",
            "Epoch 85/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0635 - accuracy: 0.9759\n",
            "Epoch 86/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0586 - accuracy: 0.9783\n",
            "Epoch 87/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0591 - accuracy: 0.9775\n",
            "Epoch 88/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0617 - accuracy: 0.9773\n",
            "Epoch 89/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0580 - accuracy: 0.9787\n",
            "Epoch 90/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0586 - accuracy: 0.9777\n",
            "Epoch 91/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0575 - accuracy: 0.9786\n",
            "Epoch 92/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0555 - accuracy: 0.9795\n",
            "Epoch 93/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0560 - accuracy: 0.9786\n",
            "Epoch 94/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0574 - accuracy: 0.9780\n",
            "Epoch 95/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0530 - accuracy: 0.9800\n",
            "Epoch 96/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0566 - accuracy: 0.9787\n",
            "Epoch 97/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0538 - accuracy: 0.9804\n",
            "Epoch 98/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0501 - accuracy: 0.9812\n",
            "Epoch 99/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0529 - accuracy: 0.9803\n",
            "Epoch 100/100\n",
            "1875/1875 [==============================] - 4s 2ms/step - loss: 0.0524 - accuracy: 0.9803\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tensorflow.python.keras.callbacks.History at 0x7f91048d6dd8>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "TFjf-KYvygA_",
        "colab_type": "text"
      },
      "source": [
        "### 5. Test Your Model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "k08X4tffvbkW",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        },
        "outputId": "7a7c80f4-9752-445f-a788-3af5c48c592b"
      },
      "source": [
        "test_loss, test_acc = model.evaluate(test_images,  test_labels) # performance on test dataset\n",
        "\n",
        "print('\\nTest accuracy:', test_acc)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "313/313 [==============================] - 0s 1ms/step - loss: 0.8500 - accuracy: 0.8756\n",
            "\n",
            "Test accuracy: 0.8755999803543091\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "siVhyAoAvegc",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "test_model = tf.keras.Sequential([model,\n",
        "                                         tf.keras.layers.Softmax()]) # logits -> probabilities"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ykutq7Anv9IZ",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "predictions = test_model.predict(test_images)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AHiO-Ru4wBcP",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        },
        "outputId": "da148ca1-3a80-4886-cca7-a1ccea3081f2"
      },
      "source": [
        "predictions[0] # predict label for each image. let's check 1st prediction"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([2.15304794e-33, 9.75221635e-30, 1.73758690e-20, 5.06884449e-32,\n",
              "       2.20430262e-30, 1.89682851e-06, 1.21014814e-26, 4.28366042e-14,\n",
              "       7.71200972e-25, 9.99998093e-01], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bDFKvG62wJi-",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "9fdb061b-06be-4c9e-a817-d5e07a11fbe2"
      },
      "source": [
        "np.argmax(predictions[0]) # highest confidence value between 0 - 9"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "9"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uJucEq2aep5Y",
        "colab_type": "text"
      },
      "source": [
        "```python\n",
        "class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n",
        "               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'] # Set our labels\n",
        "```"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OlljmZhcwcUT",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "93f444fa-e1f9-44e1-b16c-0fd28dbb933d"
      },
      "source": [
        "np.argmax(predictions[0]) # class name: ankle boot"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "9"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LAQNVj45wd-0",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "5596f462-7494-442d-da4d-30a9327cec34"
      },
      "source": [
        "test_labels[0] # examine test label; correct prediction"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "9"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Xo7zA7ALwf8I",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "def plot_image(i, predictions_array, true_label, img): # helper functions\n",
        "  predictions_array, true_label, img = predictions_array, true_label[i], img[i]\n",
        "  plt.grid(False)\n",
        "  plt.xticks([])\n",
        "  plt.yticks([])\n",
        "\n",
        "  plt.imshow(img, cmap=plt.cm.binary)\n",
        "\n",
        "  predicted_label = np.argmax(predictions_array)\n",
        "  if predicted_label == true_label:\n",
        "    color = 'blue'\n",
        "  else:\n",
        "    color = 'red'\n",
        "\n",
        "  plt.xlabel(\"{} {:2.0f}% ({})\".format(class_names[predicted_label],\n",
        "                                100*np.max(predictions_array),\n",
        "                                class_names[true_label]),\n",
        "                                color=color)\n",
        "\n",
        "def plot_value_array(i, predictions_array, true_label):\n",
        "  predictions_array, true_label = predictions_array, true_label[i]\n",
        "  plt.grid(False)\n",
        "  plt.xticks(range(10))\n",
        "  plt.yticks([])\n",
        "  thisplot = plt.bar(range(10), predictions_array, color=\"#777777\")\n",
        "  plt.ylim([0, 1])\n",
        "  predicted_label = np.argmax(predictions_array)\n",
        "\n",
        "  thisplot[predicted_label].set_color('red')\n",
        "  thisplot[true_label].set_color('blue')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8-GAjWN4whXM",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 211
        },
        "outputId": "584fee84-5697-4062-cbbe-575db686bb88"
      },
      "source": [
        "i = 0 # view predictions[0]\n",
        "plt.figure(figsize=(6,3))\n",
        "plt.subplot(1,2,1)\n",
        "plot_image(i, predictions[i], test_labels, test_images)\n",
        "plt.subplot(1,2,2)\n",
        "plot_value_array(i, predictions[i],  test_labels)\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x216 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9ZHc5n1KwjSx",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 211
        },
        "outputId": "62e1219f-499c-4290-dc06-5274352e25a7"
      },
      "source": [
        "i = 12 # predictions[12]\n",
        "plt.figure(figsize=(6,3))\n",
        "plt.subplot(1,2,1)\n",
        "plot_image(i, predictions[i], test_labels, test_images)\n",
        "plt.subplot(1,2,2)\n",
        "plot_value_array(i, predictions[i],  test_labels)\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x216 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7vkYB1B6wxaq",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 729
        },
        "outputId": "d5d9741b-ee0a-4642-f7fd-4fe9a504b180"
      },
      "source": [
        "num_rows = 5 # view every prediction\n",
        "num_cols = 3\n",
        "num_images = num_rows*num_cols\n",
        "plt.figure(figsize=(2*2*num_cols, 2*num_rows))\n",
        "for i in range(num_images):\n",
        "  plt.subplot(num_rows, 2*num_cols, 2*i+1)\n",
        "  plot_image(i, predictions[i], test_labels, test_images)\n",
        "  plt.subplot(num_rows, 2*num_cols, 2*i+2)\n",
        "  plot_value_array(i, predictions[i], test_labels)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1UAAALICAYAAACXcNrvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdeZgdVZ3/8c+hk5B09j0hgXQCCTthM2wKKIqACKKMwIw4OI7ijKjo4/xEUUTHhcFxBhlHUdkcBJQlCKIICAhE1iQkEAiBkAUCZN83sn1/f1Slcs7pe6tvd3X3vd39fj1PP5xzT3XVuZfUt6tune85zswEAAAAAGiZ3ardAQAAAADoyLipAgAAAIACuKkCAAAAgAK4qQIAAACAAripAgAAAIACulW7A0BzDRkyxBoaGqrdjU5v5kxp27by7d26SRMn7qpPmzZtuZkNbfueAe2PuFObiDvozFoad/L+fsd/u9E8eTGHmyp0OA0NDZo6dWq1u9HpOZffvm2b5P9vcM4tbNseAdVD3KlNxB10Zi2NO3l/v+O/3WievJjD8D8AAAAAKICbKgAAAAAogJsqAAAAACiAmyoAAAAAKKCqE1Uwm1JtYjYldFa1FnN27NgR1Dds2BDU+/bt26L9bty4Majvtlv4/VnPnj1btN+2QsxBZ1ZrcWfdunVBfcmSJUG9vr4+K2/dujVo23333YO6H8O2b9+ee9wtW7Zk5b333ruyzrYh4g5aW1VvqphNqTYxmxI6q1qLOfHFzTPPPBPUTzrppBbtd/r06UG9T58+QX3ChAkt2m9bIeagM6tG3DGzoO686eAeeuihoO3qq68O6oceemhWXrx4cdC2zz77BPX169dn5VWrVgVt3bqFl5jz58/PynfddVfZvrcX4g5aG8P/AAAAAKAAbqoAAAAAoAAW/wWAVrR58+agftVVVwX1W2+9NSvHw2WWLVsW1Hv16lV22zxxzlRc94flHH/88UHbZz7zmax8yimnVHxMFDNihBSltmSGD5eiUVhArrzhf9/+9reDtr/97W9B/Z577im73379+gV1P39z27ZtQZsfvyRp06ZNWfnee+8N2k4//fSyxwQ6Cp5UAQBQZeVuqJpqAwDUBm6qAAAAAKAAhv8BQEFf+9rXsvIvf/nLoG3t2rVB3Z+uOB4eM3DgwKDuD5fp3bt30BZPX+xPdRzvNx4K9M4772TlP/7xj0GbP/TnmGOOCdoee+wxAah98TIKvpkzZwb1OO4MHbprlvF4mYc47gwaNCgrd+/ePWiL487cuXOz8ssvvxy0MfwPnQFPqgAAAACgAG6qAAAAAKAAbqoAAAAAoAByqgCgmeK8qSuvvDIrjxgxImiLc6H8qY3jnIOtW7cGdX8q9HhadH8/UphDEU9tHPP31adPn6Ctrq4uK8dTLX/4wx8O6n/4wx9yjwOg9qxfvz6oDxkyJKj7eaA7duwI2vzczbg93m+8re+NN96orLNAB8KTKgAAAAAogJsqAAAAACiAmyoAAAAAKICcKgBopm9961tBvV+/flk5znWK13VZvHhx2f0OGDAgqPu5T926heE6zl/YvHlzVh48eHBuH/x9+WtWSWGe1/Dhw4O2eJ2q5cuXZ+U4LwNA7ViyZEnZtji2xDHMF+dr+mtT+fmYpfbjx8mlS5eW7yzQQfGkCgAAAAAK4KYKAAAAAApg+B8ANNOaNWuCuj91cDxNejzc71/+5V+y8oUXXhi0HX744UHdn4590aJFQVvfvn2D+pgxY7JyPNQnntrY39eoUaPKbrtu3bqgbdOmTUF93rx5WZnhf0DtmjVrVtm2Hj16BHX/PI+H9MVDBf0p1ePYlzcduz90GOgseFIFAAAAAAVwUwUAAAAABXBTBQAAAAAFkFMFAM0UT0PuT30e5xXEfvjDH2bl/v37B21xDsLGjRuz8oknnhi0PfLII2WPsf/++wf1l19+OaivXbs2K//kJz8J2vzp4ocOHRq0xVOzT5kyJStPmjSpbH8AVNfMmTOzcpxD5ccvKYw7/lINUuN8Un/5hngK9TgW+nHTzxcFOgueVAEAAABAAdxUAQAAAEABDP+rMfHwmt1223Xfm7fKuRQ+Wo+nUH711VeD+vjx41vaRaBL2rJlS9k2/9yMhwbGPvnJT2blu+++O3fbVatWZeV4uN9ll10W1Pv165eVf/vb3wZtK1euDOoLFy7Myuecc07Q5g//i+NRPJ3yjBkzyvYdQO149tlns7J/XSGFw/2k8DyPh/vFyz74MWDgwIFBW3wd4h9nzz33rKTbQIfCkyoAAAAAKICbKgAAAAAogJsqAAAAACiAnKoWiqcKjev+mOU333wzaHvyySeD+qmnnpqVi0wzGo9f9k2ePDmof+1rX2vxcYCu6K233irb5p/vmzZtyt3PokWLKj7m7bffXrbt/PPPD+q9evXKynEu1MSJE4P622+/nZX79OlTcX9ica4mgNo0e/bsrNy9e/egLc6xWr9+fVYeOXJk0PbUU08FdT+fNF4SIq5v27YtKw8aNKiSbgMdCk+qAAAAAKAAbqoAAAAAoABuqgAAAACgAHKqWkk8Jtn3+OOPB/Wnn346qPu5Gl/84hdb3IelS5dm5fvvvz9o69u3b4v3C0BatmxZRdv5eQNS4/wF/3yPcw5iJ5xwQtm2D37wg0F9/vz5WTnOV7jvvvuC+oknnpiV43wrP8cq7l9dXV1QX7x4cdn+Aagd/npT8Xmcl1P10Y9+tOJjxLGvvr6+7LZ56/4BHRVPqgAAAACgAG6qAAAAAKAAhv+1UDxlcbdu4Uf57LPPZmV/KlNJGj58eFD3pyU+66yzgraBAwdm5c2bNwdtY8aMCeorVqzIymvXrg3aRo0aJQAtFy+N4IuXVPDFQ2D8IXPxsJt4P3PmzMnK8TII8+bNK3vM/fffP6i//PLLQf3111/Pyj/72c+CNn/KZD/+SI2Xbcj7TADUjiVLlmTl5izdct555+W2+zFh5cqVQduQIUPK/t7GjRsr7gPQUfCkCgAAAAAK4KYKAAAAAArgpgoAAAAACiCnqhn86YXjHKoNGzYE9TvuuCMrx3kIcW7UunXrsnKcU+HX47YXX3wxqI8ePTorx7kQcQ4YgObJm1Ldn6I4nlY4rvtTln/jG9/I3faBBx7IyjNnzgza4vPfz6OMc6jifKxzzjknK8+YMUPlxFOqO+eC+tatW8v+LoDasWnTpqwcL7GSd33w3ve+N3e/xxxzTFZ+8skng7Y4nvkGDx6cu1+gI+JJFQAAAAAUwE0VAAAAABTATRUAAAAAFNApc6r83KM4ByAvRyDeNh5n7OdNxK655pqg7q9F1bNnz6Bt4cKFQd3PsYrXsPLHJMf9i9ea8HO31qxZE7S98847Qd3PAWvOmhVAV/X222+XbfPXm4pzH+O8gv79+2flH/7wh7nH9LeNY8NLL71U9vdGjBgR1JcvXx7U45hUTlPr8eVtmxcvAdSOODfSP8/jnPBYQ0NDVp4yZUrQlrd+nx/bgM6CJ1UAAAAAUAA3VQAAAABQQIcd/pc3xC+u+/xhOrHmDF+59dZbg/rixYuD+mGHHZaV4+E/q1evDuqDBg3KyvE0o/6wnfXr1wdtedOVxo/dN27cGNRfffXVrHzooYeW3Q+ARN6U6r4ePXoE9fe9731B/fHHH8/K/jIIUuOY4w/bjeOTPzV7LI4N8dBBf7/xfgYMGJCV4+nW/VgVW7BgQVDfe++9y24LoHria6QtW7YE9eacu34Mi2NU3rUY0BnxpAoAAAAACuCmCgAAAAAK4KYKAAAAAArosDlVeWN1/WnT4ynU45wFfz9NTQF8/fXXZ+VXXnklaNtzzz2D+ooVK7JynN+0adOmoD5q1KisvG7durL9q6+vD9r8qdjj4zQ1lvn+++/PyuRUAU2LcyF9/nnrn8+SdMEFFwT1++67LyvH53QsL5blic//OMfKz6mKp0n/6Ec/mpXjnKo88bTt5FQBtSk+5/0lViTpwAMPrHhfp512Wla+8sorg7bmxCygM+BJFQAAAAAUwE0VAAAAABTATRUAAAAAFFCzOVVNjcX1cwbinCV/Laq8dalib731VlCfPHlyUPdzocaPHx+0xWtI+TkLfn6VJHXv3j2o++8lXk/KF7+X3XffvWx77969yx5Dkv72t7+VPQ6AxuLz2OfHhmHDhgVtAwcOLPt7cSyIc5/887Y5sSw+3/PWj/FjlSQdddRRZfcb96Fnz55ZmfwJoGOI40F8DTVu3LiK9zVx4sSsHK93lbeWZnyNAnQGPKkCAAAAgAK4qQIAAACAAqo+/M9/DO1PaV5kqItv2bJlQX3BggVBfc6cOVn57bffDtp69OgR1Pv165eV4+mV165dG9S3bt2alePhNfHU7X6f4sflAwYMKNufvEf4vXr1yt22T58+WXnWrFkCkM8/5/1hb1K4vEE8rGX27Nll9xlPbezHjVhTyyT44uE88e/69TiWVbpcRXyceEp1ALVj9OjRWTmeQj2+3tpjjz0q3m8cw3wM/0NXw5MqAAAAACiAmyoAAAAAKICbKgAAAAAooOo5VXF+0U5LliwJ6gsXLgzq/pjgeHywP73x/Pnzg7Z4ynJ/PHDfvn2Dtjh/YM2aNSWPEe8nPk6c3xRPhe5PQzpy5Migzc/VivseT9XsT+u+cuXKoM3PoZKkxYsXl90WQGOVThm+7777BvXXXnut7LZx/lJ8jLylI/LE+41zG/wYFO83nhI+r3/+78b5qwBqh39ez5s3L2iL48Mrr7xS8X7jXG9fXr5V3vIxQEfFkyoAAAAAKICbKgAAAAAogJsqAAAAACig6jlVvr/85S9Z+a233gra4rG5/vj9eA0mP08r/r04b8rPQ/LzjKTGuQb+elNxPlOca+DvN+5fvD6Dn+/kr0slNS9Pwe9TvO5EnAPm53HljXsGkPDXkMo7Z+KcqkcffbTstnnruEhhDIpjTN5afnHsiuvlclmlcD0bvyzlr0XlxzwAtWXSpElZOV47L87znjFjRqscM16jM++YQGfAkyoAAAAAKICbKgAAAAAooKrjvtauXasHHnggq1933XVZeb/99gu2jaca94fxxcNi/Ck+46F38TAYfz/+kDip8fCadevWld1PPLzOn9I47kM8zNCfPv6ll14K2vw+xfuJ+cMI42nme/bsWXbbvCmUAST8pRHyhs/FcePll18O6t27d8/KTZ3TzeHvK55SPa7nDV+cO3duVh4xYkTQFscu/70wRTJQu44//visfMMNNwRt8bTozz33XIuOEce+vOHNecOXgY6Kf9UAAAAAUAA3VQAAAABQADdVAAAAAFBAVXOqevfuHUzz+dRTT2XlF154Idh2ypQpZffjj+uXwjypQYMGBW1xvX///lk5zqmK86ZWrFiRlefMmRO0xfkEa9euzcpxPsPMmTOD+iGHHJKVGxoagrYHH3wwK8fTk+aNSY5zJvbYY4+g3q9fv6zs54oBKM0/p/Jyofyp1yVp5cqVQb2+vj4rx/mgzRHHlTxxDlhersPdd9+dleN4NH369KDux6BVq1ZV3B8A7evYY4/NynGOdRwfWppn7V9XSI2voXxFYh9Qq3hSBQAAAAAFcFMFAAAAAAVUdfhfXV2dBgwYkNUvu+yystuuX78+qD/99NNZOR6K98QTT2TlBQsWBG3PP/98UPenHo8fVcfDa/yhLvEwwoMPPjiov//978/Kp512WtAWP3rPc8YZZ2Tl119/PWgbPHhwUPcfvftDIKXGwwH91cwnTJhQcX+Arso//zdv3lx2u3gK9XjYrn/uxUMF42E4ecNn4ja/3tTQwLyhN37M9IcmS9Idd9wR1P3jxO8FQO0YM2ZMVo6H6cUxyo9v8+bNC9rGjRtX9hhxKkZeTGjN5SSAWsGTKgAAAAAogJsqAAAAACiAmyoAAAAAKKCqOVXN0adPn6B+0kknlSxL0r/+67+2S5/awz333FPtLgBQmAuVl5MUTy0e51/5+4lzqGJ+Hle8hEKcN+XX47a8/Ct/WQlJevLJJ7NyU/mW/nE2bdqUuy2A2hDnUMVLLPjLyzQnp2rkyJFBPc5pHzhwYFYmpwqdEU+qAAAAAKAAbqoAAAAAoABuqgAAAACggA6TUwUA1eSvwVJfXx+0+evofeUrXwna/vKXvwR1P/cozpPKk5dDJeWvaRXngPnHXbNmTdB24oknZuXTTz89aPvOd74T1P2csDhPA0D15K27edZZZwVtt9xyS1D348WUKVOCNn8NzlgcF/P65OdXAZ0FT6oAAAAAoABuqgAAAACgAIb/AUAFNmzYkJXjqdD9oYFbt24N2oYOHRrUX3311awcT0+cN1V7c+QN/ZHC/sZTwA8bNiwrDxkyJPc4/jDChQsXNrufANpGXgw488wzg7Zf//rXQb1Hjx5Z+c477wzaLr/88rLHjKdJzxuy7C8tAXQWPKkCAAAAgAK4qQIAAACAAripAgAAAIACyKkCgAocd9xxWfnJJ58M2nr27JmVJ0yYELS98sorbduxNjRv3ryg3rdv36DuT6M+adKkdukTgKblLaNw6qmnBm3x9Ob+ed2cZR8OOuigoP7CCy8EdT9Ovv322xXvF+goeFIFAAAAAAVwUwUAAAAABXBTBQAAAAAFkFMFABXwc4Y2bdoUtPnrujQnB6HWxWtu+bkWkrRly5as3Lt373bpE4CmxWvp5RkzZkxQf+qpp7Lyxo0bg7YnnngiqB977LFZOV6navPmzUHdjxfLly+vuH9AR9F5/voDAAAAQBVwUwUAAAAABTD8DwAqMGrUqKx82GGHBW3+VMFNDYPbtm1bVo6H6JhZkS62SHxMv0/77LNP0PahD30oqK9evTorH3PMMW3QOwAt4ZyreNvPfOYzQX2//fbLyueee27Q5g/3i51//vlBfc2aNUG9T58+Wfk973lPxf0DOgpuqgAAaIFLLrmkbNsVV1zRjj0BAFQbw/8AAAAAoABuqgAAAACggKoO/5s2bdpy59zCavYBJY1pehOg42mPmOPnDXQljzzySJFfJ+ag0+rI1zo33nhjm+z35ptvbpP9NhNxB62qqjdVZja0mscH0LUQcwC0N+IO0DUw/A8AAAAACuCmCgAAAAAK4KYKAAAAAArgpgoAAAAACnBm1vRGTh+RdJek/c30cgXbL5B0pJmWR6+vN1PFU2M1d/uc/Vwg6QEzvVWi7e8kXS5pf0mTzDTVa/u6pE9L2i7pi2a6P339FEk/kVQn6VozXZG+frOkgyXda6ZvpK99U9IsM/2+TN8Ok3SRmT7tvfZ7SSPMdHQF7+1ESV810+kl3vORZrqoqX20ZPuc/QyQ9Pdm+llaHyrpJjOdUmS/4THcMklNzaQ0RAr//bVwm66wr9Y63phaSch2TtslvaBkMp7Zkv7RTBtztv+rkvNoarn41YZ9fZ+k/5TUQ9I0SZ820zbntJ+kGyQdLulSM/1nuv1QJfF4gKRv7owtzuluSf9SKs6l7RdLWmmm/3NON0o6QdIaSTskfd5MT+b08QKl8cE5XS5p/c7+tAXndJGkjWa6vq2O0VwVxJ2OHANqdV+VbFMTccc5DZb0UFodoeS6YVlan2SmLVXpWKpWrnUkTZH0pfTlAyTNSY/7ZzOVX027DbXFdUpraaW405FjQC3uq3zMMbMmfyT7nWSPS/adCrdfINmQEq+vr+T3W7p9zn7+KtmRZdr2l2zfeBvJDpBspmS7SzZWstckq0t/XpNsnGQ90m0OkOwQya5Nf/dByfpLNlKyPzTRt9slm+jVB0j2hmSzJRtXwXs7UbJ7S7x+gWQ/bcZn1Kztc/bTINms6LUbJDuuNf5fVt4PTW2NbbrCvlrzeLXy48cOyW6W7CtNbJ+d/+XiVyv1y0m2m1ffLT3fJ6T170r26bQ8TLJ3SfZ9yb7q/c4XJfuEZPWS/TV97cOSXZ5z3G6SPS9Zt7R+o2Rnp+WTJXu+iX5n8UGyy/3+tMFn1C19b89V+99R8/rdcWNAre6rI8WcsN+Nz5Gd51479qEuqtfUtU76Wrlrxbrmvt8Cn9POmNju1ymt0//aO2+7yr5K/TQ5/M859ZH0biXfYpzrvX6ic/qrc7rDOb3snG52Ti763V7O6T7n9JkS+/035/Ssc3reOX0n5/j/7ZxedE4Ppd8myDkd6pyeSn/3Luc0sNzrzulsSUdKutk5zXBOvfz9m2m2meaUOPSZkn5rpnfMNF/SXEmT0p+5ZppnyTdPv0233Sqpl3PaTVJ3Jd+8fFfSt3PeW19Jh5hppvfyRyX9Id2v/3nf6Jyudk5POKd56fuK9/cu5/Scc9o7en2oc7oz/byfdU7HlenSnun/01ed29Vv5/QV5zQr/bm4idevkLR3+ln/KH3t95L+odznALSxxyXtk8ase3e+6Jx+mj6BKavUv3HndIVz+ry3zeXO6atpuVFcc04NzmmOc/o/SbMk7ekdYrCkLWZ6Ja0/KOljkmSmpWZ6Vkls8W2VVC9pd0nbnVM3SRdLujLnrbxP0nQzbSvR9pikfdK+LnBOQ9LykekTvLzPp1TM3c85PeNt0+CcXkjLRzinR53TNOd0v3Mamb7+V+d0lXOaKulLljxVXOCcJuUdH6hl6d/ta5zT05KuzLl2+atzOjItD3HJ03I5pwOd0zPp39PnndP49PVPeK//wjnVpa+vd04/dk4zJR3j96UGr3XibYK+l4m9Dc5plvc7X3XJk3M5py86p5fSz+m36Wu9ndP16Wf1nHM6M339Aud0j3N6WLueLnKdgsIqyak6U8lj2VckrXBOR3hthyn5Y36ApHFScLHeR8nNwa1m+pW/Q+d0sqTxSk7aQyUd4ZyOL3Hs3pKmmulASY9q10n7f5K+ZqZDlAzxKfu6me6QNFXSP5jpUDNtquA9S9IoSW949UXpayVfN9NsJY/6p6fvex9Ju5lpes4xjpR2BYjUeZJuTX/Oi9pGKrnBPV3JzUvGOR0r6RpJZ5rptej3fiLpv830LiUXbNeW6c+ktP0QSX+XXlQdIelTko6SdLSkzzinw8q9LukSSa+ln/W/pfudKuk9OZ8D0CbSG45TlcSD5v5uuX/jv5P0cW/Tj0v6XRNxbbykn5npQLNgKMdySd12XlBJOlvhTVcptyiJyw9K+oGkf1UydKXs8EYlsXlambYPqwWfT6pUzH1ZUg/nNDbd5hwln093Sf8j6WwzHSHpeknf9/bVw0xHmunHaZ24gc5gtKRjzfQVlb92Kedzkn5ipkOVXC8sck77Kzmnjktf365dNwO9JT1tpolmmlJh/6p1rRPL+i5pk0rH3jyXSDos/Ww/l752qaSHzTRJ0nsl/cg59U7bDlcSi05I68QbFFbJ4r/nKbkol5JvKs7Trj/Oz5hpkSQ5pxmSGqTsRL5b0pVmKrVs9snpz3NpvY+Si47Hou12KLmAkaTfSJrsnPpLGmCmR9PXfy3p9nKvV/D+Wo1Z8BTnD5IudE6XSpoo6cH45lLJTdIy73eGK/kcppjJnNNW53SQWRaMfm+mHZJeSrfdaX9Jv5R0spXOp3i/pAPcrueI/ZxTHzOtj7Z70Ewr0r5MVnIDZ5LuMtMG7/X3SHJlXr+nxPGXStqjxOtt6ZettE1X2FdrHq9W9EpjkpQ8qbpO0rHN3Me7VeLfuJmudk7DnNMekoZKWmWmN5zTl1Q6rr0uaaGZnooPkJ7n50r6b+e0u6QHlFwklWWmNZI+lPZpoJKLibOc068kDZT0Y2ucHzVSSW6Z70cuyYNYJu3K6axUEzH3NiUXflek/z1H0r6SDpL0YBqL6iS97e3ydwotlbRfc/tVRR05BtTqvjpSzCnndjNtb+E1ypOSLnVOoyVNNtOrzukkSUdIejY9j3opOVekJHbc2dpvIFb0WqcMv+8lY69KX1/s9LySEUm/l7K8rpMlneHSkQSSekraKy0/aKaV3u9X4zqlNdTiedtV9tVI7k2VcxqkZNjIwc7JlPwRNOeyJxDveJtvj/b3N0mnOKdbzBTPhuEk/dBMv2hmf5ueVaP1vKnwG+PR6WvKeV2SlD5inqbkompvM308Hepyc/Rt8iYlJ/lOH1dyUTQ/DZb9lNzEXpq2+5+3P9Ty7XQ/h0klb6p2k3S0mTaXfKe7xJ9va33ePaWKnxC2CjNr8qSoZJuusK/WPF4N2ZR+i5txTtsUPp3vqZa7XclTpRHadTNQMq45pwYpuTgoJb0Bek+67cmSJjSjH99S8rTnPCVfaN0habKkD0bbxbFGkv4tfZLv8z+jIp/P75R82TVZkqUXgwdLetEsHJbkiT+jdo8bRXTkGFCr++pgMaecsue+p+R5Z6Zb0qGDH5L0J+d0oZI482szfb3Efjab5X8pU0I1rnVKqaTveTH8Q5KOV/Lk/dI03jhJH4uHPTqno9TB481OtXjedpV9ldLU8L+zlQwrGWOmBjPtKWm+KntEepmkVZL+t0Tb/ZL+ySX5WnJOo5zTsDL925k79PdKnuCskbTKuawP50t6tNzraXmdpL4V9Nl3j6RzndPu6TCW8ZKekfSspPHOaaxz6qEk7yn79iQd4rIzv6GXdt2Y1CmZ3cs3W2kuQ+o8Saekn3WDkm+jzlXTVisJKD90yWyAsQckfcHr46EltpGkDzinQS7JO/uIkhvjxyV9xDnVp4/Nz0pfK/d6qc96gpp+9A+0tYVKntju7pJZKk9qYvty/8al5KbhXCXxaee3zZXGtcDObdInVV9TMoy3SS7Jrxhtpr8qybHaoSTe9CqxeRxrylkgZUO8P5a3YV7MTYcgb1dy07fzpnOOpKHOJTdVzqm7czow5xDEDXQaTVyjLNCu8y7Ll3ZO4yTNM9PVSkb/HKIkB+hsL24Mck5jCnStGtc6TSkXe5dIGuacBqfx8vS0L7tJ2tNMjyiJof2V3OjdL+kLLs33b2IIIfEGhTU1/O88Sf8RvXZn+no8VKOUL0m63jldaab/t/NFMz2Qjgt+Mn0is17SJ7TrEfZOGyRNSoeoLFUyhESS/lHSNc6pXtI8JWNv816/MX19k6Rj/Lwq53SWknH+QyX90TnNMNMHzfSic7pN0ktKvh35/M5vUVwy3e/9SoLH9WZ60evz55V8i7TROT0vqd4lSdp/MtNq/82Z6WXn1PinZXIAACAASURBVN8lSZyDJY2Rdg0RMtN857Qm/VYll5mWOKfTJd3nnP4pav6ipP9N+9NNyTDLz8X7UBJI71TyjdRvLJ1y1SXTL+9MPL/WLBnelPP631ySTHpfmlf1Xkl/bOo9AG0pHaJ3m5I/nPO1a5heue2nl/s3nsaHvpLeNEuGsOXEtaa+ff239NzdTdLPzfSwJDmnEUrG+feTtMMlydoHmGlt+nvf166n2LcqGfJyiZIvtGL3SbqpiX5I0nckXeec/l3Kn6QiVS7mSsnfiB9JGitJZtrikgl2rk6HQnWTdJUUxE/fcUqmgAY6i3Lny39Kus05fVbh38qPSzrfOW2VtFjSD8y0Mr0meiC9mdiq5Lojd5mRWrnWMdO6pj6kvNjrnL6bvv6mlC3xUyfpN2lccZKuNtPqNI5dJen59LOaL4XLz3i4TkFxLZ02kJ/W+ZHsy5L9c7X70cbv8THJBrbPsXSKkm/E50q6pMw21yu5SZ+Vs589JT2i5A/Ni5K+VGa7nkoC/Mx0u7LLDigJ/M9JajQFvrfNAiUJzDNUZlpPJesT3aHkD8psSceU2GbfdB87f9ZKurjEdl9O+z1LyYV5zxLbfCltf7HUPvjpGD+S3SXZ+Gr3o8K+HibZTdXuR+X9bb+405yYk26fG3cqiTnpdrlxp9KYk25L3OliP7V+rdOe1ymt01+uddJtaupap+r/MLr6j2Q9JTu/2v1ow/c3VLKPtM+xVCfpNSUzUfZIT/4DSmx3vJKZf/ICzUhJh6flvpJeKbMvJ6lPWu4u6WlJR5fZ51eUzNzWVKDJXSNJSYLzP6flHpIGVPC5LFayYJ3/+igl39z1Suu3Sbog2uagNMjUK3my8BdJ+1T73xU/zf9J16g5vtr9qLCvH5Csodr9qKyv7Rt3mhNz0m1y404lMSfdruK4Uy7mpG3EnS74U8vXOu15ndI6/eVaJ+dzqeq1TiVTqqMNmWmzWUXDcjokMy2zMiust4F0XQ2bZ2b+uhpRn+wxKZj1pxEze9vMpqfldUq+JRlVYjszs52zKHZPfxpN8OGcG60k763cdPYVcc71VxIor0uPv8XMVuf/lk6S9JqZlRoe0k1SL+dcNyXBJJ7oZH9JT5vZRjPbpiQH4KNF3gOqw0xzzBrNsFqTzPSgWbJWTwfQrnGn0pgjVTXu5MUcibjT5dTytU47X6e0Bq51Sqv6tQ43VehMyq23UYhzrkHJzIpPl2mvc87NUPKY/UEzK7XdVZL+n5LJBPKYpAecc9Occ58t0T5WydS0NzjnnnPOXeuc611iO9+5Sh53hwcye1PJWP7XlcwgucbMHog2myXpPc65wc65ekmnqel1lICupN3jToUxR6os7jQVc6Tmx52SMUci7gCtgGud0qp+rcNNFZDDOddHyeQdF5vZ2lLbmNl2MztUyQQfk5xzB0X7OF3SUjMrt/iq791mdriSBWs/75yLF8XupuRx/s/N7DAlk7lcktP/HpLOUIn1UJxzA5V8uzVWyfocvZ1zn4je22wlk9U8IOnPSsYsN3fKXgDN0FTcaSrmpPuoNO40FXOkZsSdvJiTthN3gBrDtU7rxBxuqtCZ5K230WzOue5KgszNZja5qe3TR9OPKEkg9R0n6Qzn3AIlj+nf55z7TZl9vJn+d6mku5Q85vctkrTI+4boDiWBp5xTJU03syUl2t4vab6ZLTOzrUrWN2q0QK6ZXWdmR5jZ8UqWSXgl53hAV1O1uJMTc6QK404FMUdqXtzJizkScQcoimudxmriWoebKnQm6boabmz6rUWwrkZzOOeckrG8s83sv3K2G+qcG5CWe0n6gHZN8ypJMrOvm9loM2tI+/SwmX2ixL56O+f67iwrWQ1+VrSvxZLecM7tm750kpJZe8o5T2WG4Sh5FH60c64+fb8nKRlPHfcrXQ/F7aVkjPEtOccDupp2jTuVxBypsrhTScxJ99WcuJMXcyTiDlAU1zqN1cS1TlPrVAEdhpltc85F62pYozVwnHO3SjpR0hDn3CJJ3zaz66LNjlOyOOML6RhiSfqGmf0p2m6kpF875+qUfElxm5nd28K3MFzSXck5r26SbjGzP5fY7guSbk6Dabw2UCYNVh+QdGGpdjN72jl3h6TpStYneU5SqZXE73TODVa6HkoFyaJAl1GFuFONmCNVEHeaijkScQcoimudUC1d6zizkpMGAQAAAAAqwPA/AAAAACiAmyoAAAAAKICbKgAAAAAogJsqAAAAACiAmyoAAAAAKICbKgAAAAAogJsqAAAAACiAmyoAAAAAKICbKgAAAAAogJsqAAAAACiAmyoAAAAAKKBbtTsANNeQIUOsoaGh2b83c6a0bVv59m7dpIkTW96vrm7atGnLzWxotfsBtIWWxh20LeIOOrO2uN7hWqeYvJjDTRU6nIaGBk2dOrXZv+dcfvu2bVILdouUc25htfsAtJWWxh20LeIOOrO2uN7hWqeYvJjD8D8AAAAAKICbKgAAAAAogJsqAAAAACiAmyoAAAAAKKCqE1XUwmxK27zpUZYtWxa01dXVBfXddit/Dxpvm8fMgnq3brv+N/Tt2zdoc03NrtAGmE0JnVUtxJw8GzZsCOo7duwoWW5KvG337t2Dep8+fVrQu7ZDzEFnVmtxZ86cOUE9vs7w6/H1So8ePYK6375169agLe+aKd7v+PHjc3rcNog7aG1VvamqhdmU/BupX/ziF0HbgAEDgnqvXr3K7qd///5B3Q9K27dvD9q2bNkS1IcNG5aVTzzxxKAtDmDtgdmU0Fk1J+bENyb+BUJ8QeAr8kXIk08+GdQ3btyYleO4EccV3zvvvBPUhw4NrxuOP/74lnaxTRBz0JnVwrWOL77OiL8U3n333bPy5s2bg7b45tBvX7JkSdAWf0nsx6w4fv3pT3/K73QbIO6gtTH8DwAAAAAK4KYKAAAAAAro8ov/3n777Vn5e9/7XtA2cODAoD5y5MisPH/+/KBt1KhRQX3ChAlZefbs2UFbz549g/r73//+rBw/Pj///PPL9h1A24mH8bV0yN+6deuC+sMPP5yVp0+fHrTdd999QX3fffcte4z169cH9RUrVmTlwYMHB23xEJ7vf//7WfnDH/5w0HbGGWdk5b322ksAOr61a9dm5RdffDFoi4cH+zZt2hTUX3vttaDuX8/EOVT19fVB3R/CnHdMoKPiSRUAAAAAFMBNFQAAAAAU0OWH//mz/8Wz2uRNBzpixIigHs9k4w/FWbNmTdDWr1+/oP7mm29m5f322y+/wwDaRd7wv7zhfr/85S+Dejx9sT+rYHy+n3POOUF9xowZWdmfkUsKl4OQwqGC8axbvXv3Dup+3Fu4MJwA68tf/nLZ37viiiuC+h577CEAtc8fAhzHr/j6xZ91OJ6BOE6L8H/XH2IoNb6G8q+x8mZTBjoqnlQBAAAAQAHcVAEAAABAAdxUAQAAAEABXT6nys99iqf4jKcOHTRoUFaOp0mOcxhWr16dleOpmPPGHR988MGVdBtAG4vP27w8qp/97GdZeeXKlUHb2LFjg3r37t2zcpzLMGzYsKB+wgknZOXJkycHbXFep5/7EOcyxHHFn7p9/PjxQVv//v2zcpxv9c1vfjOoX3/99QJQ++68886s7F/3SNLo0aODuh+X/BxQqXFup98eT78e5336+eVvvfVW0DZt2rSsfMQRRzR+A0AHwJMqAAAAACiAmyoAAAAAKICbKgAAAAAooMvnVI0ZMyYrz5w5M2irq6srW4/Xb4nXcvDHJMe5D6tWrQrqeevWAKiOvJyqN954I2jz6+PGjQva1q9fX/YYcRxZsmRJUN97771LliXp1VdfDep+zudRRx0VtD322GNB3V9fyl+/RpI2btyYleO1ZBYvXhzUb7rppqx8/vnnB23NyUkD0LauvfbarDxy5MigLc7l9ONQt27hZWIc++rr67NyfM3Us2fPoO7va+nSpUHbM888k5XJqUJHxZMqAAAAACiAmyoAAAAAKKDLD//zh6TE0w7HQ3P84SzxdOt5Q/omTJiQ2wd/WE/8qB1AdcTTkvvmzp0b1P1hL/E0wn369Anq77zzTlaOp1SPt/WXZjj11FODtilTpgR1f6he3Ie47g9J3rBhQ9DmLxexZcuWoC2eTvm5557LyvHwP4b7AbVjzpw5WfnII48M2uKp0Ldu3ZqV4ynV4xjlx4g4zvjLM8T1OL7GU6wDHRFPqgAAAACgAG6qAAAAAKAAbqoAAAAAoIAun8Djj+vdc889g7YDDjggqPs5ArfffnvQtnLlyqD+4osvZuXjjz8+aIunCx01alRWjnMY/OlKAdQG//yWwqmD/ZwpqfHU4v45HecrxFMSr127NivH0yCffPLJZX833s8+++xTtk/xNOl+XkQ83XrMnwYZQO14++23g7qfvxlPoR5Pb+5fF8XLxcRTqvuxL8638nOzpDC2xNOtx/maQEfEkyoAAAAAKICbKgAAAAAooMsP/9t///2z8kMPPVS2TQofTx944IFB26RJk4L6Zz/72ay81157BW2jR48O6gMHDszK/rTIAGrTokWLgnq/fv2ycjz8LzZ8+PCsvHHjxqAtnpK4e/fuWTkechgvAeEv67DHHnsEbfF0xf5U7UuWLAna/OnW42OOHTs2qA8ePDgrx0OX42FDANpPPKw3L5UgHqLsX4csX748aIunY581a1ZWXr9+fdAWDwf0hyDGQ5Tj4YBAR8STKgAAAAAogJsqAAAAACiAmyoAAAAAKKDL51T5OQ29e/cO2uIxyX7uUyzOhfDzKuJpk+Oxw9267frfEE9hzDSjQG2Ic498fi6Bn68kSYccckhQ9/Ok/ByDUvy8gzgWxMfxc5riHIl4amN/uuV4v/5+4mPE/Nj2/PPPB21x7gWA9vPKK68EdT/uxNc6MX/5mHhq9tdeey2oH3bYYVl5zpw5QduYMWOCup9n6V/3SFzroHPgSRUAAAAAFMBNFQAAAAAUwE0VAABoZMQIybnyP97s+wDQ5XX5nCp/bHG8Zsxuu4X3nP5aL3EO1aGHHhrU/THJmzZtCtri9Vz8vAp/3DOA2jFv3rysHK+/4udCbtiwIWjzY4EkrVy5MivHuU5xTqUvzs2M13nxj7N06dLcPvjHifvgx8H4fcZrcPl5EfPnzw/ayKnq+HLSCCtqR/W8/PLLQd1fpyqOUXEs8XMphw4dmnuco48+OivPmDEjaIvjjh8/4jbWtUNnwJMqAAAAACiAmyoAAAAAKKDLD//r1atXVo6H+8VDX/La/GlFY/GwQv+YUjiVKMP/gNr0xhtvZOV4WYR4aJ5v4cKFQb2hoSErx0Ne4inW/WHGffv2DdriWOEfJ+5PPH2x3//4mP5SEvHUy/Ex/Xo8nTKA6pk7d25Q79+/f1aOUxDi89pPdbjgggtyj/NP//RPWfmaa64J2vLiYjzkMK4DHRFPqgAAAACgAG6qAAAAAKAAbqoAAAAAoIAun1Plj+ONxxXHU3769bx8KynMm4qnLI7zFPw+MK4YqE1+nkGcf9mvX7+sHE87vm7duqDu/268NEN8/vvt8THj4/j5C3H+1apVq4K6n1MVL/ngv5dly5YFbX5eRnzMmTNnCkBtWLt2bVD3r0nia5v4GsWvX3zxxbnHede73lV2v3nLQPi55HEb0FHxpAoAAAAACuCmCgAAAAAK4KYKAAAAAAro8jlVQ4YMycpNjQf213aI16mJ+TkNZha0xb87atSorBznTQCoDevXr8/K8fpSAwcOzMrxulRnnnlm2f3EMSfO6/TzpuIcqjgPwl+LKm7bvHlzUPePG8ej/fbbLyvffffdQVscn/z+xrlZAKonXpvOzwOP40587o4YMSIrjxs3ruJj+tdTUuNrqEGDBmXlFStW5PYB6Ii4ggcAAACAAripAgAAAIACuvzwv5EjR2Zlf3if1HjY3saNG7NyPLwm5k+FHE+h7k9ZLDV+RA6g9vhD6PzpiaXGQ218BxxwQFB//PHHs3JTSzP4w+1Wr14dtPlDDuNt42GEcf/i2OabMGFCVo6H5MS/50+LvGbNmrL7BNC+Bg8eHNTj5Rt8/pBkSTrllFNadEx/2KDUeJp0f3jgypUrgzaug9AZ8KQKAAAAAArgpgoAAAAACuCmCgAAAAAK6PI5VfX19SXLUuN8B3/MbzweOObnUcVTIft5CFLjsc8Aqi/OQfDzKLdv3x60+blGcT7THnvsUXbbmJ+3KYW5UBs2bAja4rjhT5McT5kcTwHvi9/LPvvsU7Y/8bb+ZxLnZcT1pvLHALSe+HxbtWpVVo5j29y5c4P6j3/847L7jXOf/FzOsWPHBm2LFi0K6kOHDs3KcSyJtwU6Ip5UAQAAAEAB3FQBAAAAQAHcVAEAAABAAV0+p8pfRyFeTyoeO+yPQ/bHBpcyfvz4rByv9RKvceWvfwOgNixfvjyo+7lQcc6Snx8Q51TF+Qt+PV4/Kl4rz8+LiHM+4zjix5lhw4YFbfF6Mf57idv8HDA/X6IUf72u+DNZvHhxUPdztQC0rTh327/OiPMd4zzPeG09X5wL5ceIAw88MGibP39+UO/bt29WXrZsWdAWr7sHdEQ8qQIAAACAAripAgAAAIACuvzwP188TCeeNt1vb+pRtf/4/I033gja1q5dG9T9ITQAasPq1auDun/+9+zZs+y2e+21V9DmD3mRwqnRhw8fXvYYUjgEOR6mFw8b9of/xdvGwwz9oYPr1q0L2vyhQXH/4v36Q4HiIURLly4N6gz/A9rPwQcfHNSffvrprBzHDj9dQZJGjBhRdr95Q4JPO+20oH711VcHdX+Jhnh48KBBg8ruF+goeFIFAAAAAAVwUwUAAAAABXBTBQAAAAAFkFPlWbFiRVCPxxnfd999WfnCCy/M3dfhhx+elZ955pmgbdSoUUE9nrodQPXFU4T705vH0xXPmTMnK++3335lf09qnN/ki6cr9nOf4v7EffBzM+OciXi//r7i3FF/aYk4LyPOv/JzS+P+xdM2A2g/55xzTlC/4YYbsnIcg+I874cffjgrn3zyyUFbnDvpi2PfnnvuGdT9fKx4P3FsAToinlQBAAAAQAHcVAEAAABAAdxUAQAAAEAB5FR5Hn300aA+d+7coO7nVN100025+zrooIOycpyz8NOf/jSoT5w4MSsfccQRlXUWQJuKcyz9PAR/TShJWrNmTVb2z2dJWrZsWVD38xfiPCQ/h0qS3nnnnaxcX19ftj9SmK8Q9y/O2+zevXtWjteeev3117Py3nvvHbQ98cQTQd0/TpxPEedpAGg/8Xntn/NxvmO8rX99E+dU5eWEDhkyJKjHa1EtXLiwbB/itf+AjognVQAAAABQADdVAAAAAFBAlx/+50/rGU87HA//86dYb+pRtf+I3B8aJDWeYn3btm2VdRZAu5k+fXpQ94e6xcPrlixZkpX9acYlaerUqUHdH8bnD9krVfdjUo8ePYK2OG7428axLJ5+3a/Hw3lmzpyZlfv16xe0+dO2S+HnsHHjxqAtft9nn322AFSHP9wujl/x9Ux8jdJS8dIO06ZNy8rxUOe4T0BHxJMqAAAAACigyz+pAgCgJS655JKybVdccUU79gQAUG08qQIAAACAArr8kyp/SuMtW7YEbfEY3zgvIY+/r3jscJxjFbcDqL7evXsHdT8/4M033wza1q1bl5XjKdX9HCVJGjBgQFaO85Bifs6nP7261Dhvyp8WuU+fPkFbnI/lbxtP675gwYKsfMYZZwRtn/70p4P6xz/+8awcT/k+cuRIAagNxx13XFa+5ZZbgrZBgwYF9ThetFRDQ0NQX7VqVVZuKp4BHRFPqgAAAACgAG6qAAAAAKCALj/8zxc/8l67dm1Qj4cD5fFXL4+nLI6H+40YMaLi/QJoH5/61KfKtvnTE0vSvHnzsvLee+8dtE2ePDmo+1Oux/vZsWNHUPeHCi5fvjxoi4cr+8MT4+nW47o/dfuwYcOCtqeeeiorX3jhhUHbsmXLgro/zLCpZSYAVM9FF12Ule+4446gLV7KYfXq1VnZj22SNG7cuIqP2bdv36DuD5OOY128FAXQEfGkCgAAAAAK4KYKAAAAAArgpgoAAAAACiCnytOrV6+g7ucoSM3LGfDzs/xpkaXGY4lba/pSAO0jnrL8kEMOycp+3oAkrVixIqj70xc3lV/pT7ke7yeOK34ciXMk4umL82KOf8wZM2YEbaeddlrZ3wNQu0aNGpWV/VxNqXFup5+v+cwzzwRtzcmpiuOMn9sZx6Q4RxToiHhSBQAAAAAFcFMFAAAAAAVwUwUAAAAABZBT5Vm8eHFQ3759e1CPc6Hy+DkXcX5DvN84lwtA7fFzmOJYUFdXl5WnTJkStMXr1Pnq6+uDerzfuXPnZuWmchn8+BXvJ84P9dfci+OPn3vx2GOPBW1xTpX/mTjncvsHoP3EOZf++fmBD3wgaLvzzjuDup8Ldffddwdt5557bsV9iHNP33rrrbL9a871FVCreFIFAAAAAAVwUwUAAAAABTD8zzN8+PCgvnTp0qDuD/FpysCBA7NyU9MbDxs2rOL9AqgOf/hMXiyYM2dOUI+nL/bP/3hoYPy7Y8eOzcr+kD1JevPNN8vuNx5Ks2nTpqDuD72Jpz326/GQ6Jj/meQNNwLQvvKGKMfDeO+4446g7g8JXrRoUYv70L9//6DuT5vuXyNJ0sqVK1t8HKBW8KQKAAAAAArgpgoAAAAACuCmCgAAAAAKIKfKc+qppwb1qVOnBvXm5FT17ds3K8fjiuPpjceMGVPxfgFUX7wsgh8bFi5cGLTFOZQTJkwo+XuStN9++wX1QYMGZeWXXnopaItzlrZu3ZqV41wtPx5JYUzy8xzi/m7cuLFsmyTtvvvuWZmcKqB2xLncvne/+91B3V9GQZJWr16dleO8ypkzZwb1iRMnlj1Ov379grofT7p37x60xbmnQEfEkyoAAAAAKICbKgAAAAAogJsqAAAAACiAnCpPz549g3qc+9ScnCpfvEZMnKcwevToFu0XQHXk5Qv94Ac/COo/+tGPgvp9992Xlf3cBSlcl0oKc6PiOBKvb7dq1aqsvHbt2rJtUpgnEecyDBkyJCtfdNFFQZufQxXLy+EA0L6ak9O41157BfUZM2Zk5Tj36cEHHwzqeTlV69atC+pxDPMtWbKkyX4CtY6/ggAAAABQADdVAAAAAFAAw/88n/zkJ4P6lClTgno85XqlzjjjjNz2gw8+uEX7BVAdeUPdevXqFdQvu+yystu+/vrrQT2eNt0fEhMP6duxY0fZ/cZDduK6P9znuOOOC9r69OlTdr8AOp9LL700qI8YMSIrx7HjhBNOqHi/55xzTlAfPnx4Vo6HHZ900kkV7xeoVTypAgAAAIACuKkCAAAAgAK4qQIAAACAApyZVe/gzi2TtLBqHUA5Y8xsaLU7Uc6RRx5pU6dObfbvVTLDbBVPhw7POTfNzI6sdj/yEHNqVk3HHKl03LnkkkvKbn/FFVe0dZfaXEeImcQdFNAh404lmjp3q33edmR5MaeqE1XU+j9mAJ0LMQdAeyPuAF0Dw/8AAAAAoABuqgAAAACgAG6qAAAAAKAAbqoAAAAAoIA2n/3POQ2W9FBaHSFpu6RlaX2Smba0aQea4Jz+TtLlkvZP+zPVa/u6pE8r6fMXzXR/+vopkn4iqU7StWa6In39ZkkHS7rXTN9IX/umpFlm+n2Z4x8m6SJJUyR9KX35AElz0uP+2Uzlp5hqQ85pqKSbzHRKNY5fToUzKQ2RtLwVtukK+2qt49X8TErN4ZwulfT3Ss7DHZIuNNPTzmmBpCPNws/COZ0h6YCd8SBqO1HSFjM9UeZYJ0q6SlJ3ScvNdIJz2lfS77zNxkm6zExXOaf/kHSqpBlm+mS6j09IGmKmq8ocY6SkX5npdOdUL+lXkg6R5CStlnSKkv/H95rpoBK//11Jj5npLyXaLpD0gJneSuu/lfQtM71aqi8dUQVxpyPHgFrdVyXb1ETc4VqHa5220EpxpyPHgFrcV/mYY2bt9iPZ5ZJ9NXqtWzv3oS6q7y/ZvpL9VbIjvdcPkGymZLtLNlay1ySrS39ek2ycZD3SbQ6Q7BDJrk1/90HJ+ks2UrI/NNGf2yWbGL22QLIhTfW9jT+nbul/b5DsuPb8f9Q6/dfU1timK+yrNY/XWX4kO0ayJyXbPa0PkWyPtFzy/MzZV7dSsc9rHyDZS5LtldaHldimTrLFko1JY8uD6evXSnawZL0ke0iy7jn9+JFkZ6blr0v2X17bvmmsa5BsVjM/q7oS8fMEyX5V7f+P7ftvpuPGgFrdV0eNOVzrlOwP1zpt0v/aO2+7yr5K/VRl+J9zutE5XeOcnpZ0pXM61Dk95Zyed053OaeB6XZ/dU5HpuUh6TfEck4HOqdnnNOM9HfGp69/wnv9F86pLn19vXP6sXOaKekYvy9mmm2mOSW6eaak35rpHTPNlzRX0qT0Z66Z5lnyzdNv0223SurlnHZT8m3zdknflfTtnM+hr6RDzDQzZ5ug787pK85pVvpzcbpNg3Oa5f3OV53T5Wn5i87ppfRz+m36Wm/ndH36WT3nnM5MX7/AOd3jnB7Wrm/cfi/pH8r1D+ikRip5YvSOJJlpuaVPYVJfcE7TndMLzmk/KTt/fpqW/Rh3m6TPSfpyGpveEx3r7yVNNtPr6bGWlujPSZJeM9NCJU/NujsnJ6leSez5qqT/MdPWnPf0MUl/9t7fmzsbzDRn53uVVOecfuWcXnRODzinXt57OjstL3BO/+Gcpks6T9KRkm5O318vSY9Ler9z1V22A6gmrnWyz4FrHXQJ1cypGi3pWDN9RdL/SfqamQ6R9IJyTs7U5yT9xEyHKvljvsg57S/pHEnHpa9v164TpLekp8000UxTKuzfKElvePVF6WslXzfTbCWP+qdL+oOkfSTtZqbpOcc4UtoVIMrI+i5pk6RPSTpK0tGSKn25hAAAIABJREFUPpM+Us9ziaTD0s/2c+lrl0p62EyTJL1X0o+cU++07XBJZ5vphLQ+VWp0EQh0dg9I2tM5veKcfuZcdj7stNxMh0v6uZIbmlJ2xriPSrpG0n+b6VAzPR5tN0HSwPTCappzyXC+yLmSbpUkM62T9CdJz0l6W9IaSUdZmWE3kuScxkpa5d04XS/pa87pSef0vZ0Xa6nxkv7XTAcqGRb4sTK7XWGmw830GyVx4h/S97fJTDuUXJxNLNcnoIvgWodrHXQR1fwW8XYzbXdO/SUNMNOj6eu/lnR7E7/7pKRLndNoJd/wvuqcTpJ0hKRnXbKSdC8p+8Z3u6Q7W/sNxMySb1MkyTn9QdKFLsnLmCjpQTP9KvqVkdo15rocv+/vlnSXmTakx5isJAjck/P7zyv5Bvn3UnbRdbKkM5zLLgZ7StorLT9oppXe7y+VtEcTfaxFv2ylbbrCvlrzeJ2CmdY7pyOUnF/vlfQ753SJmW5MN5mc/neapI+W2c3tZtpeweG6KYldJymJW086p6fM9IokOaceks6Q9HWvf1dKujJtv1bSZc7pn5Wc28+b6XvRMYJYY6YZzmlcuv37lcTNY5RczMw30wzv/TWU6ffvyry+087YMa2J7TqLjhwDanVfnSHmcK3DtU5bqsXztqvsq5FqPqnaUME227Srjz13vmimW5RcZGyS9Cfn9D4lyda/Tr8pPdRM+5olj4Ulba7w4sb3pqQ9vfro9LVyr2fSR8zTJPWRtLeZPi7pbJckh/s2+e+rjEr67n9Oivb5IUn/q+RbmWfT4ThO0se8z2qv9NsnqfH/l55pPzsUM2vypKhkm66wr9Y8Xmdipu1m+quZvq0kwdp/YrPzic92lf9yqpIYJyXfAN9vpg2WTH7xmMInPKdKmm6mJfEvpt/eOiXJ3n+Xxpq9oydPUolYY6b1Zppspn+V9BtJp0XvTSr2/jpk7GipjhwDanVfnSTmcK3DtU6bqcXztqvsq5SqT6lupjWSVnl5BudL2Tc5C5R8IyMpGcsvSek3rPPMdLWku5XMYPWQkpN5WLrNIOc0pkDX7pF0rnPaPR06M17SM5KelTTeOY1Nv0E+V963J86pu6SLlXyL3EvSzukV6yT1iI4xW8mj80o9Lukjzqk+fYR9VvraEknDnNNg57S7pNPTvuwmaU8zPSLpa5L6Kwl+9yvJCXHpdnmP1Seo6cf2QKfinPaNbkwOVdMzTuZZJ6lvmba7Jb3bOXVLL0aOkrI//FKSs3Rrmd/9d0nfUpLbUJe+tkNqdFHzirwnTs7pOC+fo4eSWbha+/0RO4AU1zpc66Dzq5Uk4n+UdE16QTFPyVhaSfpPSbc5p89K+qO3/cclne+ctkpaLOkHZlrpkik9H0hPsK2SPq8mLhSc01mS/kfSUEl/dE4zzPRBM73onG6T9JKSb0c+v/NbFOd0kZKTtU7S9WZ60dvl55V8i7TROT0vqd45vSDpT2Za7R/bTC87p/7OqW+aJ5HLTNOd041KAp6UTHH6XNqn76avvynp5bS9TtJv0mEHTtLVZlrtnP5dyfTNz6ef1XylwamE9yr87IGuoI+k/3FOA5Sc/3MlfbbA/v4g6Y70m90v+HlVZprtnP6sZPjKDiXn9SwpSbSW9AFJF8Y7dE4fkTTVdk1jPiONNc/HCeFm2uCcXnNO+5hprqS9Jf08vdjYTck5fqfU4ouzG5XE8E1KEuT7SdpkpsUt3B/QGXGtw7UOOrOWThvIT+v8SPZlyf652v3I6d9jkg2sdj8q769OUTIUaq6kS8psc72S8dNlp45WMuzhESV/aF6U9KUy2/VUEuBnptt9J2efdUomF7g3Z5sFShKYZ6jMtJ6SBki6Q8kflNmSjimxzb7pPnb+rJV0cYntvpz2e5aSpyE9S2zzpbT9xVL74Kdj/Eh2lmTfa6djfVmyT1f7PbffZ9t+cac5MSfdPjfuVBJz0u1y406lMSfdlrjTxX641mnt/nKtk25TU9c6Vf+H0dV/JOsp2fnV7keZvg2V7CPV7kfl/VWdpNeULJLaIz35Dyix3fFKxl3nBZqRkg5Py32VDJ8qtS8nqU9a7i7paUlHl9nnVyTdUkGgyV0DSUmC8z+n5R6SBlTwuSxWsmCd//ooJd/c9Urrt0m6INrmoDTI1Ct5sv0XSftU+/81Py37aa+LGsk+1d7r8lTvM23fuNOcmJNukxt3Kok56XYVx51yMSdtI+50wR+udVqzv1zr5HwuVb3WqXpOVVdnps1muqna/SjFTMssZ5rmGpSuq2HzzMxfVyNgZo9Jwaw/jZjZ22Y2PS2vU/ItyagS25mZrU+r3dMfi7dzzo1Wkkh7bbPeUeP99FcSKK9Lj7/FzFbn/9bONY6s1PCQbpJ6Oee6KQkmb0Xt+0t62sw2mtk2JTkA5Wa7Q40zK/bvrxnHucFM29rjWDWgXeNOpTFHqmrcyYs5EnGny+Fap1VxrVNa1a91uKlCZ1JuvY1CnHMNkg5T8s1MqfY659wMJY/ZHzSzUttdJen/KcmZyWOSHnDOTXPOlcrhGatkatobnHPPOeeudc71LrGdL1vjKDiQ2ZtKxvK/rnS9IzN7INpslqT3OOcGO+fqlcwQt6cA7NTucafCmCNVFneaijlS8+NOyZgjEXeAVsC1TmlVv9bhpgrI4ZzroySB/2IzW1tqGzPbbmaHKplydpJz7qBoH6dLWmpmlazX824zO1zJNNqfd84dH7V3U/I4/+dmdpiSaWEvyen/zjWOGq2H4pwbqOTbrbFK1ufo7Zz7RPTeZkv6DyWL4f5ZyZjl5k7ZC6AZmoo7TcWcdB+Vxp2mYo7UjLiTF3PSduIOUGO41mmdmMNNFTqTJtfVaA7nXHclQeZmM5vc1Pbpo+lHlCSQ+o6TdIZzboGSx/Tvc879psw+3kz/u1TSXUoe8/sWSVrkfUN0h5LAU066xpE1WuNIyaKv881smZltVbKg7bEl+nSdmR1hZsdLWqVkzDWARNXiTk7MkSqMOxXEHKl5cScv5kjEHaAornUaq4lrHW6q0Jmk62q4sem3FsG6Gs3hnHNKxvLONrP/ytluqHNuQFrupWT665f9bczs62Y22swa0j49bGafKLGv3s65vjvLSlaDnxXta7GkN5xz+6YvnaRk1p5y8tY4el3S0c65+vT9nqRwfaSd/UrXQ3F7KRljfEvO8YCupl3jTiUxR6os7lQSc9J9NSfu5MUcibgDFMW1TmM1ca1TK+tUAYWZ2TbnXLSuhr0Yb+ecu1XSiZKGOOcWSfq2mV0XbXacksUZX0jHEEvSN8zsT9F2IyX92jlXp+RLitvM7N4WvoXhku5Kznl1k3SLmf25xHZfkHRzGkz9tU4CabAqucaRJJnZ0865OyRNV7I+yXOSSq0kfqdzbrDS9VAqSBYFuowqxJ1qxBypgrjTVMyRiDtAUVzrhGrpWseZlZw0CAAAAABQAYb/AQAAAEAB3FQBAAAAQAHcVAEAAABAAdxUAQAAAEAB3FQBAAAAQAHcVAEAAABAAdxUAQAAAEAB3FQBAAAAQAHcVAEAAABAAdxUAQAAAEAB3FQBAAAAQAHdqt0BoLmGDBliDQ0N1e5GRWbOlLZtK93WrZs0cWL79qctTZs2bbmZDa12P4C20JHiTmvJi19SbcQw4g46s84UdzpCPKlEXszhpgodTkNDg6ZOnVrtblTEufJt27ZJHeRtVMQ5t7DafQDaSkeKO60lL35JtRHDiDvozDpT3OkI8aQSeTGH4X8AAAAAUAA3VQAAAABQADdVAAAAAFAAN1UAAAAAUEBVJ6qo9VlNtm/fHtTr6uqy8jvvvBO0bYumNHFeRp6LsvN69erVWl1sE8ymhM6q1mNObMWKFVl5w4YNQZuZBXU/PvXs2TNoGzJkSBv0rvUQc9CZdbS401UQd9DaqnpTVY1ZTeILkf/P3n3H21GV+x//PKmkENILzSSkAQmQAoZehAiKiBVBKZaLyk8hiAhXQSwXARuiCIjCRUGqFAMiIITmNbSE9AIJBAhppCckpK7fH7MyWWudvXdOMic57ft+vc4ra80zZ2b2hv2cmT3rWZNe8ISWLl0a9Tt06JC3Z82aFcUWLVoU9cMTnJYtW0axQYMGVe9ga4lmU5KGqjZyzqZNm6J+mIPCPFHKX/7yl7w9ZsyYKJZ+kRPmpwEDBkSxr3zlK2X3sS05sdLvbsvvpZRzpCFrSDO4NSTKO1LTNPxPRERERESkAF1UiYiIiIiIFNDgH/5bqS4K4uEr6TC99evXR/2wFmrNmjVRrH379mV/t3nz5lHsv/7rv6L+z3/+85LHLiL1X5Mm1f/uauLEiVH/7LPPztuHHnpoxe2Geebaa68tux2I82A6bG9bhvQVGfInIiLSkOhOlYiIiIiISAG6qBIRERERESmgwQ//29rsWvfcc0/e/uEPfxjF0qE49913X96++OKLo9irr74a9Z988sm8ffzxx0ex8847L+qHs3g1axb/J6mp2bVEpG6YPn163l6wYEEU69q1a9R/8cUX8/YVV1wRxZYvXx71w+HJf/rTn6LYc889F/X//e9/5+1LLrkkirVo0aLssYuIiEhpulMlIiIiIiJSgC6qRERERERECtBFlYiIiIiISAENvqZqa8Iapt133z2KXXbZZVH/Yx/7WN5+7LHHotibb75Zdh833HBD1O/Zs2e1j091VCL1y9ixY6P+Qw89FPXnzp2btw8//PAotmzZsqjfsWPHvN2/f/8otnDhwqgf1lQdeOCBUWzdunVRv127dnk7faTD0Ucfnbf33XffKNa5c2dERESkKt2pEhERERERKUAXVSIiIiIiIgXookpERERERKSAeltTVen5TWH9wLhx46JYWrPwwQcf5O2ZM2dGscmTJ0f9Rx99NG+3b98+ivXo0SPqv/baa2WPfcaMGVF/7dq1eTut61q/fn3e7tatWxRr0kTXxCJ1Qfisp4985CNRLK1DCmujBg4cGMVmz54d9W+//fa8PXTo0CjWr1+/qB/mkVGjRkWxj370o1E/rJV64YUXolj4jL00duqpp0b9vn37IiIiIrpTJSIiIiIiUoguqkRERERERAqot8P/Kk01PnXq1Lz98ssvR7F0WuJwCM1BBx0Uxd59992ov2rVqrydTpM8ePDgqL9o0aK8vWbNmijWpk2bqL948eK8/frrr0exFi1a5O3mzZtHMU1vLFI7Jk2aFPXD4XbXXHNNFEsfoRA+xqF3794V1126dGne/vKXvxzF3njjjai/evXqvD1+/Pgo9uEPf7jsuumQ4z322KPsdn79619H/RtvvBERERHRnSoREREREZFCdFElIiIiIiJSgC6qRERERERECqi3NVWVhHUIffr0iWJhXRRAly5d8vaKFSuiWKdOnaJ+WMP0yiuvRLGXXnop6odTJb/33ntRbOXKlVG/Q4cOZfcZTpue1maJSO0YO3Zs1H/sscfy9q233hrF/v73v0f98DMeTm0OMH369Kj/8MMP5+00P6XTry9YsCBvp7WZ6eMYwsc6pLVZHTt2zNv77bdfFPv4xz+OiIiIVKU7VSIiIiIiIgXookpERERERKSABjH8Lx3SFw6v69GjRxQLpz4GGDRoUN7+4IMPKu6nbdu2eXvdunVRLB2aF05/vnHjxiiWTgffunXrkm2Ipz4O2yJSe0aPHh31e/XqlbfTRzPstttuUT/MI+EwYYC33nor6of567jjjotis2bNivrr16/P2+mU7+njF8KhgunQwHA7qTlz5kT98NEResSDiIg0ZrpTJSIiIiIiUoAuqkRERERERArQRZWIiIiIiEgBDaKmatmyZVF/7dq1ebt79+5RLKwlgHi68zZt2kSxpk2bRv1ddtklb7dr1y6KhTVUAM65vJ1Ok57WWGzatKlkG+LarbTWIXydAC1btkREdrx0evN33nknbw8bNiyKpXWdYe1m+/bto1j4OAiI80rfvn2j2PLly6N+WI8ZTpkOVR/jEO43zGsARx99dN6+//77o1g6VfvixYvztmqqRESkMdOdKhERERERkQJ0USUiIiIiIlKALqpEREREREQKaJA1VS1atMjbac1Chw4don5Yl5TGwroogCZNtlyDps+0atWqVdQP6xTSddNnWoW1EGnN14YNG/J2+lrSuo4uXbogIjtepVqoRx99NIqln8vw85/WfM6ePbtsP41Nnz496nfs2DFvv/HGG1Hsa1/7WtSfO3du3h4/fnwUe/bZZ/P2f/7znyiWPkcvresUERFprHSnSkREREREpABdVImIiIiIiBTQIIb/pcPpwuF/6bTo6bqLFi3K2+kwnXC4H4CZlT2GZs3it3Ljxo15O50mPZ36PPzddHrjdLuhdF0R2TmGDh0a9c8+++y8nQ6ZS4fiLVmyJG/PmzcviqVTqq9atSpvp8Oc02nSw5wTTnUOMGfOnKgfTo2+evXqKBbmxHR6+HTYYzjkUEREpDHTnSoREREREZECdFElIiIiIiJSgC6qRERERERECmgQNVXplOVhHVVad5ROWR7WMKT1Amldwrp16/J2WuuU1m6FdV1pbVZaY9WuXbu8HU5nDDB48OC8ndZ0pVO+i8iOM2nSpLx91113RbHTTz89b6ef7/CxCAC77bZb3m7btm3ZGMQ5J2wDrF+/vuyxdurUqeJ2w/yV5qcwd5144olRbP78+VH/6aefzttnnnlm2eMRkR0rPV9JaznD2sm33347ig0cODDq33zzzXk7/VzvvvvuUT/MLeljaVJhbkzzTiXpuU6l+naR2qQ7VSIiIiIiIgXookpERERERKQAXVSJiIiIiIgU0CBqqtJag9atW+ftdCzuihUron737t3zdvocmHTcbjgGOK2pSusowt9t3rx5FEtrLEJ/+9vfon6/fv3ydjqWOa0lE5Ed5/3338/baW3RbbfdlrcfffTRKHbFFVdE/fAz3a1btyiW1km9++67efvQQw+NYmlNQteuXfN2+vyovn37ll03fTbWpz71qbw9bdq0KDZhwoSoP2TIkLytmiqR8srVQG+tPih8/lxauz169Oi8/bvf/S6KzZo1K+qH+SusmwTYZ599on5Ye3700UdHseuvvz7qP/nkk3l71KhRUWz48OFRv1IdVXgelx6faqikvtCdKhERERERkQJ0USUiIiIiIlJAgxj+t3bt2qgfTuuZ3nKfPn161A+nXG/ZsmUUW7NmTdQPb8On0lh4mzsdGphOoxx68MEHo/5FF12Ut9Nb4qtWrSq7HRGpWfvtt1/evuqqq6LYiBEj8naXLl2i2P333x/1wymI99xzzyiWDo+5884783bv3r2jWDq8Z968eXn7+eefj2LpVMfvvPNO3l65ciXlfOxjH4v6xx57bNQP3xMRqZ5tmVo8HPI3bty4KPab3/wmb/fv3z+KnXbaaVF/6NCheTt9fEw6ZHnMmDF5+49//GMU23XXXaN+OIQ5HDoM0KtXr6h/6aWX5u1TTjkliqXnNyL1ke5UiYiIiIiIFKCLKhERERERkQJ0USUiIiIiIlJAg6ipSqfbbNeuXd5O661mz54d9cPxwem66ZTl4dTo6TjotJ9OfRoKp3yHuO4rnOId4imVDzjggCiW1mqJyI7z+uuv5+3XXnstioWf94ULF0ax9BEKYf1lWreZ5o2w9mnKlClRLK0PDfNXWkuaTtX+9ttv5+0lS5ZEsf333z9vp1O+h+8BwMSJE/N2mp9EZIvwPKXS+UElYV0UwOLFi/N2+hiFbXH22WdX7IfefPPNqP8///M/eXv8+PFRLK37DmtR0+306NEjb6c5Kc1nYQ5Nz4Mq5b7jjjsOkR1Jd6pEREREREQK0EWViIiIiIhIAbqoEhERERERKaDe1lSF9U7pM6LC502tWLGi4nZWr16dt9u0aRPFmjWL356wpiqtUUiFdRRpzVf6PIawbmru3LlRbM6cOWX3oZoqkZ0nrCcKn28HcT649957o9jVV18d9cOapfR5MelnOqy/POOMM6LYq6++GvXDY0rrFU466aSof+ihh+bttH7hwgsvLLuPMF9CnBOXLVsWxdLXJtJYrVu3LvpbHtZkpjXWrVq1ivphvfbIkSOjWFhH+Z///CeKpZ/H8JwpPX9Jz6FeeumlvD1//vwoFtasAwwYMCBvn3DCCVGsb9++UT98Lt9DDz0UxcJn66XPwgrzDMR5Mq1ZTXNo+D4cfPDBiOxIulMlIiIiIiJSgC6qRERERERECqi3w//S29Wh8PZ0OvVxKrzVHg4bLLWPcHrQdErU9JZzeMs+jaW3q/fYY4+8vbUpjEPpsMLweLd3ylYRKW3s2LF5O52+OJzaeMaMGVEsHUY8evTovN2/f/8olk5B/Oyzz+btwYMHR7E0t4XDXMLjATjqqKOi/pgxY/J2Ohx57733ztvp8L8wVwEsWrQob7/33ntRTMP/RDJNmzalbdu2eT8cihc+3gCqDvkPzyUGDRoUxW655Zay+0wfERN+ztNSh65du0b9z3/+83m7V69eUSyc+ryIr3/961E/LNVIc2Z6zhRKp1BP+yHlJNnRdKdKRERERESkAF1UiYiIiIiIFKCLKhERERERkQLqbU1VKBxzDPEUpePGjav4u2FN1Zo1a6JYWpcUTuu5tZqlcExwenyVxvyG466han1GqFKtlmqqRGpWOA358OHDo9jkyZPz9hFHHBHFOnToEPUnTZqUt9etWxfF0s90mCvSGs90KuawpildN61JCKdUTmuqwhyUPpIirelYuXJl3k7rMkQk07Rp06ie52Mf+1gtHk3dlE7VLlIf6U6ViIiIiIhIAbqoEhERERERKUAXVSIiIiIiIgXU25qqsCYgrUMIn9+0ZMmSitvZdddd8/b7778fxdJ6h7BOIa1DqPQchbS+Ka3dCmu1OnXqFMXC15nallotESlm/PjxebtPnz5lY+mznObNmxf133333bydPvMlrFGC+Bk26fNr3nzzzagfxlevXh3FFixYUHa7ac7p169f3k5z4J577hn133rrrby9dOnSKLbbbrshIiLSWOhOlYiIiIiISAG6qBIRERERESmg3g7/C4elpMP/wunM06F2qXCIyvz586NYOrxu1apVeXvt2rUV1w2HIKZD+NLjDacSTYfMhMN0UuHrLLVdEak5jzzySN5Oh9ped911efujH/1oFBs6dGjUD3PFkCFDotg777wT9Q855JC8vf/++0ex9PMe5o50OPKBBx4Y9cNh0emU7+HU7N/5zneiWPqIh3Ao4/e///0o1rNnT0RERBoL3akSEREREREpQBdVIiIiIiIiBeiiSkREREREpIB6W1MV1jSE9UupdDrjvn37Rv3wd9Opz9OapbCfxsLp1tPjS6X1V6F999036k+fPr3suqqpEtl5fvnLX+btQw89NIqF9Zb77LNPFFu2bFnUD2ssd9lllyjWvn37qN+9e/e8nU7Vnn7e586dm7dXrFgRxdIcuddee+XtDz74IIqF9apf+9rXotgRRxxR9hjSmIiISGOiO1UiIiIiIiIF6KJKRERERESkgAY//C+dknzPPfcsu510mvR0SF84PXs69CY9hjCexipN8962bduyx5AeTzpcMZ1GWURqzhtvvJG302F74Wezf//+Ueypp56K+g888EDeHjduXBQLh/AB3HbbbXl76dKlUSydfn3atGl5Ox3Sl253/PjxeXvx4sVRbMSIEXk7nF4dYMGCBVE/HCqYDnPs0qULIiIijYXuVImIiIiIiBSgiyoREREREZECdFElIiIiIiJSQL2tqQqFUxSn0vqlPn36RP2wLqlly5ZRLK2FCtdNY2FtQSqtfaqkTZs2UT88/tWrV0exdEr1SscgIsW8//77eTutNQr7w4YNi2JDhgyJ+uFjHdJpyCdMmBD1w9qtL3zhC1FsypQpZfeT1l+eccYZUT88xiVLlkSxE088sew+wqnjIX5PKtWKioiINHS6UyUiIiIiIlKALqpEREREREQK0EWViIiIiIhIAfW2pip8DkulmqXZs2dH/cMOOyzqv/nmm3l73rx5UaxVq1ZRv0OHDnk7reNKaxjCZ0al61aqAUv3uXz58rL7SGuqRGTHWblyZd5OnxE1c+bMvN26deso9vjjj0f98HOcPltu/vz5UX+//fYrezzpfgYNGpS3w2dqAbRv3z7qd+3aNW+nz54K82D63Lz0uX/he5I+G0tERKQx0Z0qERERERGRAnRRJSIiIiIiUkC9HT8WDpsJpx2GeHhNOiQlne7YOZe3W7RoUXY7EE89nA6L2bRpU9QPpxoOh8gANGkSX8uGx5hOv9y9e/e8nQ456t+/f9SvNKxQRIoJh9cNHz48ir322mt5u3nz5lFsxYoVUT/MM+HwXoAxY8ZE/c6dO+ftJ598Moql05v37t07b7/44otR7IQTToj6YS5Jh0j369cvbx999NFRbOrUqVG/Xbt2eXufffZBRESksdKdKhERERERkQJ0USUiIiIiIlKALqpEREREREQKqLc1VWZWsg0wd+7cvL1u3boo9tnPfnbHHlgJnTp1qva6ac1XWDcxevToKBbWeEBcxyUiNWvvvffO20899VQUC6caT2smJ06cGPV33333vL169eooltY3dezYsezxpNOxr1mzpmQbqtZ1hvtNazXDOtOWLVtGsXT69T322CNvh4+cEBERaWx0p0pERERERKQAXVSJiIiIiIgUoIsqERERERGRAuptTdVbb72Vt9NnvSxbtixvX3755TvtmHaECy64IG/36tUris2fPz/qh8/KUn2DSM0Kaxh/97vfRbGXXnqp7O+dddZZUf+FF17I202bNo1i6bOnwnrMWbNmRbH0eVhhnVRaq5XWeYW1pmmuGDBgQN5O68HSfs+ePfN2WtsqIiLSmOhOlYiIiIiISAG6qBIRERERESmg3g7/a9u2bd5ev359FGvXrl3ePuaYY6q9zXAqYagbw1k+85nRKr7oAAAgAElEQVTP5O0WLVpEsY0bN+7swxFptJo125IuP/3pT0ex7t27l/29gQMHVuyHvvKVr0T9oUOH5u00z4VTs0M8FK9Hjx5RbL/99iu77ic+8YmyxxPuH6oOI9xrr73ydl3IlyIiIrVFd6pEREREREQK0EWViIiIiIhIAbqoEhERERERKaBWa6rGjh27yMze2vqaspN9qLYPQGRH2Bk556qrrtqRm2+olHOkwdK5Tp2lvCM1qlYvqpxzXWpz/yLSuCjniMjOprwj0jho+J+IiIiIiEgBuqgSEREREREpQBdVIiIiIiIiBdTpiyozuptxtxmzzBhrxqNm9NuO7bQ347wK8VvNWGjG5GR5RzP+Zcbr/t8OfrmZ8VszZpox0Ywhfnl/f5wTzTjUL2tmxpNmtK6w/9+YcZRvNzfjar/PcWaMMeOkbX3Nflsjw/364+iwPdsSaQzM+IEZU/xneLwZH/bLZ5vRucT6p5hxaZltHWPGYWViA/xne60Z301iJ5oxw+eXS4Plvcx40S+/x4wWfvm3zZjs8+PmZUeYcW2F19nKjGfNaGpGE5/PJpsxyYyXzejl11tV5ve/YcZZZWKnmrFf0P+lGceVOxaRhqZcHqmB7T5jxrDtWceMb/nc4cJcVu58xsfO9ucir5txtl/W0ozHfL44L1j35vB3S+z/VDN+6Nv9/XGON2OaGTdv2ztRdh/HmPFIddcx42QzflIT+xaBWp6oohIzDHgQ+LNzfMEvOxDoBry2jZtrD5wH3FAmfhtwPfCXZPmlwFPOcbU/ubkUuAQ4Cejrfz4M3Oj//TpwATAbuA74DPBN4A7nWF3mdXYChjvHSL/op0APYKBzrDWjG3D0Nr7ezUYCd0C+79vJ3ocrt3N7dUI1Z1LqDCyqgXV26LbM6sRx1dT+6vVMSv6LkJOBIf6z1xmyi5RynGMUMKrEtpoBxwCrgP+U+NUlwPnAqcnvNQV+D5wAzAFeNmOUc0wFrgGudY67zbgJ+CpZ7vkicADwfeCj/oThcuD0Cof+FeAB59hoxunA7sABzrHJjD2B97fyum8qtdy/7lOBR4CpfvHvgD8Coytts66rRt6p9XxSG9sqkMNqap06lXe2J4/sJP9H9rl8Jlle8nzGjI7AFcAwwAFjzRgFHAn8G/iZ3+YN/tysqXOMq7D/7wGn+PZvyXLZ3wHMGFT41W2ffwA/NePqcudota2G8o7ySc1uq3zOcc7VyR9wx4F7rkzMwP0C3GRwk8Cd5pe3BfcUuHF++Sf98rvBrQE3HtwvymyzJ7jJybIZ4Hr4dg9wM3z7D+BOT9cDdw24EeD6+X22B/cEuCYVXue54H7k263BLQbXrsy6p/vXNRncNcHyG8G9Am4KuB/7ZeeDW+fXf9ov65C+xob6A7xSE+s0hm3V5P7q8w+4T4N7uExsNrgfB7llgF9+Drjrffs2cDeBexHcA+Dmg3vX550jy2z3R+C+G/QPBfd40P9v/2PgFoFrlq7n99cS3M/AnQjuTHAjt/Ja/wOup29/B9zvyqy3CtyV4CaAewFct/S4wT0D7jc+B/0A3BJwb/rXvY9fZyy47rX933jH/v9Tf3NAXd1Wfcw5W8kjPwT3sv8bfjM488uf8ecPL4F7bXO+ANfKn0tMA/eg/6wP87Eqf/eDbQ2rcHyzwXUO+uXOZ04H94d0PXAn+VzTEtwLPjYK3O4V9tlv83mI708EN7TEej3BPe/z7Dhwh/nlx/jX9Tdw08H9NXjvTvTLxoH7LbhH/PJDwI0B96rPd/2DbT0S7PNacJ+v7f9vtv//t7r3uW0s2yr1U5eH/w0ExpaJfRo4CDgQOB74hRk9gA+ATznHEOBY4Ff+jtelwCznOMg5Lt6GY+jmHPN8ez7ZXTKAPYB3gvXm+GW/J/u2+M9k3+JcDvzMOTZV2MfhwevsA7ztHCvSlczYneyb6uP8az/YLP+W+wfOMYzs2+qjzTjAOX4LzAWOdY5jAZxjKdDS3x0TkdgTwF5mvGbGDWZV7hAv8rnlRoiH7AX2BA5zjk8DN5F9G3uQczxfzWMol1s6AcucY0OyHLK77C8Ae5N9c/xlslxUkh8i2Ns5ZvtF9wKf8ENxfmXG4GD1NsALznEg8BzwX2U228I5hjnHlWR37i72r3uWj48jy3UiDV2lPHK9cxzsHAOBVmR3tDZr5hyHkI0wucIv+yaw2jn29cuGButX+bu/ncdbLueUW/4voCdZzvmtGacA45xjboV9HA7RXaxrgdFm/NOMC81o75cvBE7wefY0sjtamw0me2/2A3oDh5uxC9ld8E+QvTfdg/WnA0c6x2Dgh2TnZKW8Qnb3TaSwunxRVckRwF3OsdE5FgDPAgcDBvzMjInAk2QJoFv5zVSfczjAbWWdt53jGOc4lGzI3Z7ANDNu9zUQperBegDvVeMQDgaecY73/InVXyGrwwI+b8Y44FVgf9hSz1DCQrKhPiIScI5VZH+YzyX7TN5jxjnBKg/4f8eSnVSUcp9zbNxRx1iKc9zuHIOd40vAhWQnIieZ8TczrjWrkuc7A8uC358D9Af+G9gEPGXGR3x4HeQ1CpVe9z1bOUzlHWkUtpJHjvV1kZPIviDdP/jVUvnlKLIh/DjHRGBisP62/N2vMc6xwTnO8Bcr95Fd6PzKjF/7nHNKiV+LznOc43+Bff3vHwO8YEZLoDnwR//+3Ef8ml5yjjn+S+rxZO/RAOBN53jdn6PdEay/G3CfZbXy1xK/1yHlJqkxdfmiagrxtzLV8UWgCzDUOQ4CFgC7FDiGBf4OGP7fhX75u8BewXp7+mWhK4HLyOom/kQ2nvgKqloTHONMYG8z2lX3AH1B+XeBjzjHAWRjhCu95l38Phu66hS+Vrc4tqFvqyb3V6/5L2qecY4rgG+R1UVuttb/u5Hy9agVa5GqoVxuWQy09zVL4fKcv5t9iHM8BFxE9k3vMsgvkDYLcw4AzrHWOf7p7+T/jC21Xuv9yQoUe92NIe/U5xxQV7dVL3NOqTzi76rcAHzWOQaR3WEJP4fVyS/Adv3dr6RczqnOec55ZLXow4HlZDnnohL7KJVz5jrHrc7xSWAD2eikC8nO2w4kq+UKa9HWBu2tvkdk9elP+7uCn0j3H6jvuakufm4by7aqqMsXVaPJhqqdu3mBGQeYcSTwPHCaZTNXdSH7Nuclsm8mFjrHejOOZUsx2Upg1+04hlGQzXjj//17sPwsP2vOcGB5MEwQf7t/rnO8DrQm+/Z3k2+nppEN+8NlhZK3ANfZllm8upjxOf/6jjajsy9mP53sDl07shOa5X5Si3CmwOh1+6GQ3SEf9tNgOee2+qGozjqNYVs1ub/6zM9I1TdYdBCwtQlRKtmevPMy0Neymf5aAF8ARvkLm6eBz/r1wny02U/JhrlANrTIUSLv+GHATf1JHmYM8Rdk+LtaB1Dzr7sfxLOrNjT1OQfU1W3Vx5xTIY9sPqlfZEZbtnyWK3kOOMNvdyDkQ/wq/d3fVuXOZx4HRpjRwbJZg0f4Zfjj6UA2fPEvbDnPcWS5J5Wf5/jfPdGM5r7dnWx487tk53Dz/N2oM4GmWzn26UBPM/bx/XBynt3YchF4ToVt1OvcVBc/t41lW6XU2YsqfxLxKeB4y6ZUnwJcRVbb9CDZbfAJZBdf33OO+WRD4ob5W8dnkX3gcI7FwP9ZNgXoL9J9mXEXMAbob8YcM77qQ1cDJ5jxOlnt1tV++aPAG2R3lv4I0bSiRnaH6qd+0c1kMwH+A/hliZf6D7Lb35tdRnabfKq/bf0IsMInuUvJTqwmAGOd4+/OMYHs9v904E6ymorNbgYeM+Np3x9KVh+xARFJtQX+bMZUP4R4P+BHBbb3MPApX6sUjdm37HERc4DvAJf5vNPOfza/RXbyMg241zmm+F+7BPiOGTPJTkJuCbY3GMBtmX3rTmASWS3DYyWO7QmyYdQAXYGHfb6ZSPat8fUFXvfdwMVmvGrGPv7kqQ9Z7YJIQ1cyjzjHMrLzhclkn++Xq7GtG4G2ZkwDfoKvv97K3/2SzDjf55w9gYlm/MmHSp7POMcSsvOYl/3PT/yyzX4IXOkvgB4nq0uaRDbLcOo5YLA/P4LsAm2yGRP8717sz+FuAM72ywew9VlIPyAbZvkPPxRyYRD+OXCVGa9S+a7WsWTnYSKF+dlTpDaZ8W/gZJ90d+R+riP71vupHbkfEanbLHuezIXOceZO2NenyKaXvnxH70tE6iZ//vGwczxZ28eymb/Ld6dzVYZIi2yXOnunqpG5iGzmrh1tckO/oDKzE81shpnNNLMyD2W1W81soZmVveVvZnuZ2dNmNtXMppjZBWXW28XMXjKzCX69H1fYZlMze9XMyj6c0Mxmm9kkMxtvZiW/2Tez9mb2NzObbmbTzOzQEuv099vY/LPCzEaWWO9Cf9yTzewuM6sy7tzMLvDxKaW2IfWPv6P1tB9KvKM1A361E/ZTa3Zm3tmWnOPXr5h3qpNz/HoV8051c45fV3mn8fkZpUsgatPelK4Bq/N0rpOvU7fOdbZ3Lnb96Keu/ZCNv55FNt1qC7JhkvuVWO8oYAhQ9pldZLMVDfHtXckeOF1qWwa09e3mwIvA8DLb/A7ZUI1HKux3NtC5XNyv82fga77dAmhfjfdlPvChZPkewJtAK9+/FzgnWWcg2XCV1mQnx08CfWr7v7V+9FNXfnZ23tmWnOPXqZh3qpNz/HrVzjvlco6PKe/oRz8FfnSuU/F9qdVzHd2pkobkEGCmc+4N59w6stqOT6YrOeeeg2hseBXOuXnOuXG+vZKsvmWPEus559wq323uf6qMqTWzPYGPQz6OfbuY2W5kifIWv/91zrmtDRv9CDDLOVdq8oFmQCsza0aWTNJnjewLvOicW+2c20A2Ocqni7wGkQZmp+ad6uYcqNW8UynngPKOSBE61ymt1s91dFElDUm5hxUWYmY9yR48+GKZeFMzG09WJPsv51yp9X5DNq1+pQdBQ5aknjCzsWZ2bol4L7KJTP7X317/k5m12co2vwDcVWVHzr1LNnnK28A8YLlz7olktcnAkWbWycxaAx8jnmZXpLHb6XmnmjkHqpd3tpZzYNvzTsmcA8o7IjVA5zql1fq5ji6qRCows7bA/cBI59yKUus45zY65w4im1XpEDMbmGzjZGChc25sNXZ5hHNuCNkUuf/PzI5K4s3Ibuff6JwbTDY7Usnx1H7fLYBTyB6kmMY6kH271Yvs4YdtzOxLyWubBlxDNlvcY2QPXdypD7cVaWy2lne2lnP8Nqqbd7aWc2Ab8k6lnOPjyjsidYzOdWom5+iiShqS6jyssNrMrDlZkvmrc+6Bra3vb00/DZyYhA4HTjGz2WS36Y8zszsowX+jgnNuIdmjAw5JVpkDzAm+IfobWeIp5yRgnHNuQYnY8cCbzrn3nHPrgQeAw0oc0y3OuaHOuaOApWRjrkUkU2t5p0LOgWrmnWrkHNi2vFMp54DyjkhROtepqk6c6+iiShoS/+BU6+W/tfgC2YMNt5mZGdlY3mnOuV9XWK+LmbX37VbACfjno23mnPtv59yezrme/phGO+e+VGJbbcxs181t/LM8km3NB94xs/5+0UeAqRVeyumUGYZDdit8uJm19q/3I2TjqdPj6ur/3ZtsjPGdFfYn0tjs1LxTnZwD1cs71ck5flvbkncq5RxQ3hEpSuc6VdWJc51KD0QTqVeccxvMbPODU5sCtzrnpqTrmdldZA9c7mxmc4ArnHO3JKsdTvZE90l+DDHA951zjybr9QD+bGZNyb6kuNc5V3Ya0a3oBjyYfeZpBtzpnCv14NZvA3/1yfQN4MulNuaT1QnA10vFnXMvmtnfgHFkD3x9leyB0an7zawTsB74f9UoFhVpNGoh79RGzoFq5J2t5RxQ3hEpSuc6sbp0rqOH/4qIiIiIiBSg4X8iIiIiIiIF6KJKRERERESkAF1UiYiIiIiIFKCLKhERERERkQJ0USUiIiIiIlKALqpEREREREQK0EWViIiIiIhIAbqoEhERERERKUAXVSIiIiIiIgXookpERERERKQAXVSJiIiIiIgU0Ky2D0BkW3Xu3Nn17Nmztg+jTpowATZsKB9v1gwOPHDH7Hvs2LGLnHNddszWRWpXfck7tZkDaoPyjjRk9SXvVEdDyU2Vco4uqqTe6dmzJ6+88kptH0adZFY5vmED7Ki3zsze2jFbFql99SXv1GYOqA3KO9KQ1Ze8Ux0NJTdVyjka/iciIiIiIlKALqpEREREREQK0EWViIiIiIhIAbqoEhERERERKaBWJ6poSLOaNCSaTUkaqrqec955552ov2bNmrzdsWPHKLZp06aob0EV8NKlS6NYt27dov5uu+1W6DhrmnKONGR1Pe80Vso7UtNq9aKqIc1q0pBoNiVpqOp6zrngggui/qRJk/L2mWeeGcVWrVoV9Zs125LOH3jggYrbPfnkk6t1POmFW5MmO2Zwg3KONGR1Pe80Vso7UtM0/E9ERERERKQAXVSJiIiIiIgUoIf/iojsRM8880zevuGGG6JYy5Yto/6SJUvy9vnnnx/FmjZtGvVbt26dt4cPHx7F7r333qg/atSovH311VdHsbB2a0cN9xMREWlo9BdTRERERESkAF1UiYiIiIiIFKDhfyIiNWjGjBlR/5prron6r732Wt4+4IADoti0adOifqtWrfJ2586do9iiRYui/sCBA/N2OqV6ODMgxMMMR44cGcX69OmTt7/xjW9Esa5duyIiIiJV6U6ViIiIiIhIAbqoEhERERERKUAXVSIiIiIiIgWopkpEpBo2btyYt9PpzG+88ca8/cILL0SxNm3aRP1DDjkkb7dt2zaKffDBB1F/+vTpeTusr4Kq9U3h8b388stR7Ktf/WrU79ChQ95esWJFFJs3b17e/vrXvx7FbrrppqjfrVu3vL1p06YopunYRUSkMdFfPRERERERkQJ0USUiIiIiIlKALqpEREREREQKUE2ViEg1pHVUoUmTJuXt7t27V/y98JlR6fOkTjnllKg/derUvB3WOgH86le/ivo/+clP8vaIESMqHkNYu9W6deso1q5du7yd1kndeeedUf/CCy/M26qhEhGRxkx/BUVERERERArQRZWIiIiIiEgBGv4nIrKN0mF74XC6Ll26VFx3w4YNeXvXXXeNYu+9917UP+aYY/L2ggULoti9994b9Xv16pW3BwwYEMXef//9qL9u3bq8vX79+igWTt2eDmWcM2dO1K80zbyIiEhjojtVIiIiIiIiBeiiSkREREREpABdVImIiIiIiBSgmioRkW305ptvlo2F9VUAa9eujfph7VHbtm2j2Ntvvx31V6xYkbd79OgRxcIaKoD58+fn7dmzZ0extHarW7duedvMolhYJ7Vy5coolr625cuX5+2OHTsiIiLSWOlOlYiIiIiISAG6qBIRERERESlAw/9ERLbRu+++G/XDYXHhMDyoOi15OKRv2rRpUWzZsmVRf968eXk7nOq81Lqvvvpq3u7cuXMUS6dYf+edd/J2ONwPYNWqVWWPPTV9+vS8fdhhh1VcV0REpCHTnSoREREREZECdFElIiIiIiJSgC6qREREREREClBNVcA5V7HfpEnNXIM+99xzUf+oo46qke1ui/fffz9vt2nTZqfvX6Q+S2uqWrZsmbfDzxbAhg0bon6nTp3y9ltvvRXFli5dGvV32WWXkvsA6Nq1a9Tfd99983bz5s3LbgfiGrB+/fpFsSeffDJvp1O+p7VaU6ZMyduqqRJpfMLzpLAGFGD33XeP+mFu/PWvfx3FvvWtb+Xt9JykRYsWZfef1oSGj6wQ2dl0p0pERERERKQAXVSJiIiIiIgUoIsqERERERGRAlRTFTCziv1Kzj///Kj/9ttv5+0jjzwyij311FNRv1evXnl7r732qvY+01qNZs3K/+f8xS9+EfXvu+++vD169Ohq71NE4pokiJ/tNHPmzCi2Zs2aqN+zZ8+8HdZXQdVaqMWLF+fttN5q9erVUX/lypV5u3fv3hW3G9YdLF++PIqNGTMmbw8cODCKjRgxIuqnr1VE6r+wTio9D3rjjTei/siRI/P2N77xjSg2bty4qH/BBRfk7XvuuSeK/eMf/8jbd955ZxQ7+eSTo35Yu9W6desodu6550b9MMemdfIiNU13qkRERERERArQRZWIiIiIiEgBDX7436ZNm6J+kSF+4W3vgw8+OIqdccYZUX/IkCF5O53iMx3y8+1vfztvP/TQQ9U+nkrD/W6//faof/fdd0f9cLjS9OnTq71PEYEVK1ZE/XCq4PCzBfHw3jS+zz77RLF02vSXXnopb7/33ntRbL/99iu73fXr10exdAhiOGQmPb5bbrklb//gBz+IYumQw3T6eBGp/yqdF6VDi0eNGlV23QceeCDqn3DCCXk7fBwDwNq1a/N2Wgbx7LPPRv30ERGhSudFIjua7lSJiIiIiIgUoIsqERERERGRAnRRJSIiIiIiUkC9GXyaToUZjvmtFGvSpPJ147p16/L2/Pnzo9jgwYOjfjh16CWXXBLFDjjggKg/e/bsvJ3WHey7775R/8knn8zbHTp0iGLf//738/app54axdJpkv/973/n7RtuuKHiugceeGDe3mOPPRCR6gs/3xDXQqU1lF/84hej/tVXX523089lmq/C2q1wenWAhQsXRv0JEybk7TQftWjRIuqHj2MIp2KHeMr3dLritF5MUxSLNC7pI1hmzZqVt/fee+8odtttt0X98NwnrR9v06ZN3k5rusIp1AGOOOKIkvsHePjhh6P+l770pby9ceNGRHYk3akSEREREREpQBdVIiIiIiIiBeiiSkREREREpIB6U1NV6bkJlWLPP/98xe1eccUVeTutLQqf1wLxM6/mzJkTxcLnyaTSZ8SkdQgf//jH8/Zuu+0WxW688ca8feutt0axXXfdNeovWrQob6djmw899NCo/+KLL+bt9Jk7IlJZOsa/c+fOeXvZsmVRLP389+3bN2+HtU1Q9ZlxYc1nmhvSuq65c+fm7cMPPzyKpb/71ltv5e00j4TP40vrrdLnw4Q1VukzrNJ6LJHGrFz9YXr+kq4Xnnek9ZqVpLklfHbd1rYT1mBeddVVUSzMDxDnhO7du0exP/zhD1E/fL5nmh+OO+64vN2xY8coFtaLQ/zMvrRG/f7774/6YU2VnmElO5ruVImIiIiIiBSgiyoREREREZECGsS90JkzZ0b9cPjNXXfdFcXS4TWXX3553k6nPk+nWA/j6a31dFhMOHVnePse4IMPPoj6a9euzduf+9znotgpp5ySt2fMmBHF0qlE99prr7x9/PHHR7F0+M8999yTt9PplkWkqnAoXtiGeCr0dFhLpWnJ06GCH/rQh6J+GE+nUE+nNw8fAZHmmHTdcD/p8N+2bdvm7XQYTjjEGOLhPmm+7N27NyKSqVSmUN31Kj3CIP29dKjbtgx9C6dCT4cZDxo0KOqH50WdOnWKYj169Ij6YdnEeeedF8UWLFiQtwcMGBDF0vOZdu3a5e2vfOUrUSzNk3fccUfeDocCiuwIulMlIiIiIiJSgC6qRERERERECtBFlYiIiIiISAG1WlO1du1aXn/99bx/99135+2uXbtG66Y1AuFUv+FUoRDXARx77LFRLJzSE+Kp0MO6CIjH7UI8DWlYMwWwZMmSqB/WF6TTEqdTLIc1VWksrG/o379/FDviiCOifocOHcoez0MPPRT1w7HPU6ZMQUQqC2s3W7ZsGcXCHLR8+fIoltYVhLUNaW1mq1aton64rcWLF0exNLe99tpreTutfUqFdV7p9MrhMaXTraf98JjSPCciW1Sqh6pkW6ZRD6W55aabbsrbr776ahQLHwkBcM455+TtcKpzgDvvvDPqT506NW+n52KHHXZY2eP7/e9/H/UvvPDCsseXnouFj4xIHx+T9l955ZWyxyBS03SnSkREREREpABdVImIiIiIiBSgiyoREREREZECarWmauHChdx44415f8KECXk7rVlIhXUJ6TOY3nvvvbyd1jektVpt2rTJ22+++WYUmzx5ctQPn7GQPl8mrYUKa8DS+qtU+FrTmophw4bl7ZdffjmKXX/99VE/rAnbf//9o1j6DItw3T59+lQ8PhGJP/OVaqoOOOCAKBY+ywniPBLWTELV50mF+0w/w+l2w/rUtLYhrecIn02V1l506dIlb6d1ppVqPtNcKyJbVPc5Vanw/CGtrwprpcO8AlXrksLccvbZZ0exZ599Nurvu+++efuNN96IYuH5FcTnOun5VSXp+xE+Xyo9Z1q9enXUD5+jNWLEiCiW5tSwxurtt9+u9vGJbA/dqRIRERERESlAF1UiIiIiIiIF1Orwvw4dOvDZz34274dTob/zzjvRukuXLo364fS9c+fOjWLhcMDZs2eXjUE85O/999+PYuEQQ4iHwqTbCacoBhg0aFDeTqc+TqdGfuCBB/L2E088QXWlUxint8hD4TBHgBYtWuTtdMiRiFQVDk+pNBV6OiwvHYoXDpfp1q1bFAsfrwBxDkrXHT16dNQPpzbu3bt3FAsft5AeQzrkOBxiFOYJqDpkJ3xt6dBAESmt0vTqmzZtivqVplQfP3583k4fO9O8efOof/HFF+ftwYMHR7H0/GDatGl5OxwODFWHFYav5Y477ohi3/jGN8oeeyrMJW+99VYU69evX9QPh1g/+OCDUezMM8+M+gcddFDenjRpUrWPR2R76E6ViIiIiIhIAbqoEhERERERKUAXVSIiIiIiIgXUak1Vq1atoqm/P/ShD+XtHj16VPzdcMrNdCxxOAVoWAcB8M9//jPqn3POOXk7nQq5U6dOUT+tL6gpn/jEJ/L2Y489FsUOPPDAvJ1Ob5yOtQ6nEk3HbKf1YvPmzcvblWqxRCSzaNGivL3rrrtGsbAeoFevXlEsrE+AuIYxraFK67HC2tK0ZgrGvhkAACAASURBVCmsQYW4NiqtkUjrpsKasEqPr0jrwdJ1wzyT5mER2SL8rFR6zEpayx0+/mDWrFlRLKw9Cuu4Ia6xBLjkkkvy9r333lt2HwB77bVX3k7Pg55++umof/DBB+ft9Hwrrfs87rjjKCc811mwYEEUO+2006J+eM500kknRbEzzjgj6oe158pRsqPpTpWIiIiIiEgBuqgSEREREREpQBdVIiIiIiIiBdRqTVXTpk2j5z2F43qfeuqpaN30uTDhMxjat28fxQYOHJi303qhb33rW1E/fJ7LunXrolhYQwFVnwsVSusdwn5a35SOmd5jjz3ydlqz8Pzzz+ftcMwxVK13CGus0jHb6fsQ1nWkY6ZFpKrwM73LLruUjXXu3DmKpXUGYc4L6yABli1bFvXDXJHWRab1V0uWLMnbae3A/Pnzo36YMyvltTTvpv3w+NL8KSJbhM94S88BKgnPH/7+979HsRkzZuTt9DMfPsMKYPLkyXk7fVbme++9F/VHjRqVt0eOHBnFnnnmmaj/4x//OG+neeanP/1p1A9rqpYvXx7FunbtSjnpdkPp8aXC52qldfMiNU13qkRERERERArQRZWIiIiIiEgBtTr8LxVO4xm2S5k5c2beTofevf7663k7HU6TTkse3j5Ppzdu165d1A+HHIa38qHqMJ5wuuN0mF46HDC8td2lS5ey+9y0aVPF7SxdupRy0imgw+PbZ599yv6eiFSVfqbDYXHpELkpU6ZE/TAHpfkozVdhnunQoUPFYwhzRTqFejqsOBwqnA7bC/NRODy6lHAYkx7NIFLa+++/z5gxY/L+TTfdlLfDofhQdWhgmCPSWPh3PR1mnJZFhI9ReeGFF6JY+qiZ9FwolA47TofxhdJhhh/+8IfzdnredsIJJ+TtNNfdfffdUf+CCy7I23379o1iQ4YMifrhtPPXXXdd2WMVqQm6UyUiIiIiIlKALqpEREREREQK0EWViIiIiIhIAXWqpmpb9OnTp1rrDRo0aAcfiYg0BmF9U1i/BHFN5bRp06LYYYcdFvUHDBiQt9OpgsNaJ4inOk7rKdLHJoT9tN4qrXsI6zFbtGgRxcLazUqPbYB4avm0lkxEMq1atYqm8/7a176Wt9PpzNPa6LD2KK1DCqdRT2PpZ/Wyyy7L22l9dlo/Hj5mJZySHKrWal100UV5O60Jr1R/deWVV0axOXPm5O0ePXpEsbR+PIyn9aNt2rSJ+mG+VY6SHU13qkRERERERArQRZWIiIiIiEgB9Xb4n4jIzhQOQUmH4oVDA8PHFQB885vfjPpvvPFG3h43blwUS4fPTJo0KW9PnTo1iqX7CYf/pcNu0uGKc+fOzdtnnXVWFBs+fHjeTocNhseTSqeHF5FMkyZNomFpRx55ZC0eTd2QTuMu0hDor6CIiIiIiEgBuqgSEREREREpQBdVIiIiIiIiBaimSkSkGsK6qVRYz3TEEUdU3E7v3r1Ltks5+uijy8bSaZHXrl2bt9NphrdXWuNV6T1Ij0dERKQx0Z0qERERERGRAnRRJSIiIiIiUoAuqkRERERERApQTZWISDW0bNkyb1eqLUqfCZUK66+aNm0axcJnYW1tP+lzoba3jqrSPnfdddcolh5vWEe1bt267dq/iIhIQ6A7VSIiIiIiIgXookpERERERKQADf8TEamGRYsW5e3169dHsXBYXLNm259W0+F+4dC8SkMBi0inQg9fSzr8L5y2PY1vbdijiIhIQ6Y7VSIiIiIiIgXookpERERERKQAXVSJiIiIiIgUoJoqEZFqCKdCT+uHNmzYkLd79OhRY/vcljqqSvVXlaZNr1RTlU7TntaSha87rb8SERFpTHSnSkREREREpABdVImIiIiIiBSgiyoREREREZECVFMlIlINTZps+Q5q5cqVUWzZsmV5O6y9KiWsYQrrl4qqVH+1vc+4Sp+5lb62sLasTZs227UPERGRhkB3qkRERERERArQRZWIiIiIiEgBGv4nIlINX/7yl/P22LFjo1g4/G/o0KEVt5MOqatt4bDGVDo9fNoPX0v79u1r9sBERETqEd2pEhERERERKUAXVSIiIiIiIgXookpERERERKSAWh3cP3bs2EVm9lZtHoOU9KHaPgCRHWFn5JwzzzxzR26+zvr5z39e5NeVc6TB0rlOnaW8IzWqVi+qnHNdanP/ItK4KOeIyM6mvCPSOGj4n4iIiIiISAG6qBIRERERESlAF1UiIiIiIiIF7JCLKjN+YMYUMyaaMd6MD9fw9o8x45Ea2tYAM8aYsdaM7yaxE82YYcZMMy4Nlvcy40W//B4zWvjl3zZjshmPBsuOMOPaCvtvZcazZjQ1o4kZv/XbmGTGy2b0qonXGezvHDOuL/D7vzTjuJo8JpG6wozuZtxtxiwzxvrPcr/t2E57M86rEL/VjIVmTE6WdzTjX2a87v/t4Jebzw0zfV4d4pf398c50YxD/bJmZjxpRusK+/+NGUf5dnMzrvb7HOfz4Unb+pr9tkaG+/XH0WF7tiVSX+2ocyAznjFj2PasY8a3fP5wZnQOlpfMLT52ts8Lr5txtl/W0ozH/HnKecG6N4e/W2L/p5rxQ9/u749zvBnTzLh5296JsvvY6rlhuI4ZJ5vxk5rYtwjsgIkq/B/2k4EhzrHWf3hb1PR+tpcZzZxjQ7BoCXA+cGqyXlPg98AJwBzgZTNGOcdU4BrgWue424ybgK8CNwJfBA4Avg981H9wLwdOr3BIXwEecI6NZpwO7A4c4BybzNgTeL/4q64Z/j35HfBHYHRtHUc1Z1LqDCyqgXUa3LbMdtj+6vVMSmYY8CDwZ+f4gl92INANeG0bN9ceOA+4oUz8NuB64C/J8kuBp5zjav9FzqXAJcBJQF//82GyfPNh4OvABcBs4DrgM8A3gTucY3WZ19kJGO4cI/2inwI9gIE+Z3cDjt7G17vZSOAOyPd9O9n7cOV2bq/OqEbeqc85oE4c13auU6fyTh0+B/o/4BHgmWR5ydxiRkfgCmAY4ICxZowCjgT+DfzMb/MGnyebOse4Cvv/HnCKb/+W7Bzq7wBmDCr86rbPP4CfmnF1uXxZ22oo7yg31ey2yucc51yN/oD7NLiHy8Rmg/sxuHHgJoEb4Je3AXcruJfAvQruk355T3DP+/XHgTvMLz8G3CO+fbD/nX3ADQX3LLix4B4H18Ov8wy434B7BdxFZY7tR+C+G/QPBfd40P9v/2PgFoFrlq4H7kVwLcH9DNyJ4M4EN3Ir79d/wPX07e+A+12Z9VaBuxLcBHAvgOvml3cBdz+4l/3P4X75IeDG+PfmP+D6++XngLvetz/u1+kMboRvjwN3H7i2wX+za/zyL/hlY8F1r+n/d2r2/0NeqYl1GsO2anJ/9fkH3HHgnisTM3C/ADfZ567T/PK24J4Kctrm3HU3uDXgxoP7RZlt9gQ3OVk2I8hbPcDN8O0/gDs9Xc9/NkeA6+f32R7cE+CaVHid54L7kW+3BrcYXLsy657uX9dkcNcEy2/0+XQKuB/7ZeeDW+fXf9ov65C+xob6U59zQF3dVn3MOVQ+B/qh/zs9GdzN4Mwvf8Z/ll8C9xq4I/3yVv5zPQ3cg/4cY5iPVfkMBtsaVuH4ZoPrHPTL5ZbTwf0hXQ/cSf4cpyW4F3xsFLjdK+yz3+ac4PsTwQ0tsV6lc75nwP0N3HRwfw3euxP9snHgfsuWc8Ny50D5+aPvXwvu87X9/832//9W9z63jWVbpX52xPC/J4C9zHjNjBvMqnzjucg5hpB9G7J5uN0PgNHOcQhwLPALM9oAC4ET/PqnkX27kTPjMOAm4JPA22R3UT7rHEOBW4m/HW3hHMOc41fVfB17AO8E/Tl+WSdgmdtyt2vzcsi+eX4B2JvsG5wvk93tKskPEeztHLP9onuBT/hb4r8yY3CwehvgBec4EHgO+C+//Dqyb3wOJvuW+k9++XTgSOcYDPyQ7FulcN+fIvsW/GN+0WXA8f69fgX4TrD6YucY4hx3+/444PByr0uknhoIjC0T+zRwEHAgcDxZjuoBfAB8yn9ujgV+5e94XQrMco6DnOPibTiGbs4xz7fnk90lg/L56Pdkd8b/TPYZvxz4mXNsqrCPw4PX2Qd42zlWpCuZsTvZXfnj/Gs/2Cy/o/8D5xhGdmf+aDMOcI7fAnOBY53jWADnWAq09HfHRBqDSudA1zvHwc4xEGhFdkdrs2b+HGgk2R0iyO46r3aOff2yocH6VT6D23m85XJLueX/AnqSnev81oxTgHHOMbfCPg6H6C7WtcBoM/5pxoVmtPfLK53zDSZ7b/YDegOHm7EL2ciZT5C9N92D9SueAwVeIbv7JlJYjQ//c45VZgwl+5/0WOAeMy51jtv8Kg/4f8eSnagAjABOsS01TbuQXZjMBa434yBgI0S1DfsCNwMjnGOuGQPJTor+5W8fNoX85ATgnhp7kWU4x+1kw13wY4d/C5xkxllkyemi5GSnM7As+P05ZvQnO4k5DnjKjM85x1PAOsjHCo8lG5YI2QnefsEt03ZmtAV2A/5sRl/AAc2D/R5Hdkt/hHOsMONkskT1f347LYAxwfrpe7eQbJiiSGNxBHCXc2wEFpjxLHAw8E/gZ74+aRPZSUe38pupPudwZritrPM2cAyAGX2APYFpZtxO9jm+3LkqQxd7AO9V4xAOBp5xLlvXjL8CRwEPAZ8341yyvyE9yPLHxDLb2ZwvFldjnyL12lbOgY4143tAa6AjMAV42P9qeG7U07ePwl9YOMdEs+gzti2fwRrjv1A+A7J6TOBx4JNm/JrsvO0vzjEq+bUo5zjH/5rxOHAi2ZfiX/dDCJtT/pzvJeeY4/c7nuw9WgW86Ryv++V3AOf69SudA4V0PiM1Zoc8/NefeDwDPGPGJOBsyC+q1vp/Nwb7N+AzzjEj3I4ZPwIWkH073ITsW+HN5pFdfA0mu/gyYIpzWbF2Cdtam/QusFfQ39MvWwy0D2qzNi8Pj3t34BDn+Ik/+TqO7E7QR8i+5dlsjX8NOedYS3ai9k8zFpDVej0FrHcuP8EK37smZPUR4XuDZZNRPO0cnzKjJ/E46llk3/T0I/uWxoB/OVe29it973bxx16XVafwtbrFsQ19WzW5v/psCvDZbfydLwJdgKHOsd6M2SSf6W20wIwezjHP3wlb6JeXy0ehK8nyzPlkd6xnk307+8VkvTDvzAT2NqNdqbtVpVg2ec53gYOdY6kZt1H5NdeHfFET6nMOqKvbqpc5p9Q5kBl3k9VYDnOOd/z5Tfi5KXVuVNJ2fAYrKZdb3sV/YRMsfyb53fPI6kKHA8vJ7i6NhioXVWvILnJy/s7WrcCtlk3YM5DsjlO5c761QXur7xFZrWi5c6BQfc9PdfFz21i2VUWND//zs7r0DRYdBGxtUoHHgW/7YTMEw952A+b5uztnkt192mwZ8HHgKjOOAWYAXWzLDFjNzdi/wEt5Gehr2Ux/LYAvAKP8hc3TbDn5OhuyYsvAT8luN0N2i9+RfYsdzcblh8Y09bewMWOIvyDDjCZkt/W39t49AXx7c8d/wwPZe7f5pOuc5HfeIhsq+Bf/Hr1Adiu9j99GG6s841k/iGctq2ucc1v9UFRnncawrZrcXz03mmyo2uZvOjHjADOOBJ4HTrNsls4uZN8gv0T2OVvoL6iOZUsB60pg1+04hlFkOQXi3DIKOMuymbqGA8uDYYL4IUZz/Te2rcnyTZWc400jG/aHy4qzbwGusy0zlnYx43P+9R1tRmfLJqk5HXgWaEf2RctyP6lFOFNg9Lp9Tu8O+RDnBqs+54C6uq36mHMqnANtvuhZ5EeTVOcLnOfYcldoIORD/Cp9BrdVudzyODDCjA6WzeA5wi/DH08HsuGLf2FLznFk5zypPOf43z3R3+XCjO5kZRXvUvmcr5TpQE8z9vH98IvhSudAoTp/PlNJXfzcNpZtlbIjaqrakt1ynepvVe8H/Ggrv/NTsluzE82Y4vuQfatzthkTgAEkd0ycYwHZh/r3ZHesPgtc49cfDxy2tYO1bArlOWQ1RJeZMcd/a7sB+BZZEpkG3OscU/yvXQJ8x4yZZMnglmB7g/2xbR4/fCcwiWxM8WMlDuEJsqFFAF2Bh/23NhOBDbDV6c/PB4ZZNhXqVOAbfvnPyS44X6XENzrOMZ3sG+z7yBL0OcBd/r/ZGLL3uwqfCPuQ3eESaTD8FyafAo63bEr1KcBVZLVND5J9JieQXXx9zznmA38l+/xNAs4i+yOPcywmG0472YxfpPsy4y6yz1l/n3O+6kNXAyeY8TrZ0N6r/fJHgTfI7iz9EaKpjI3sDtXmvHkzWa3lP4Bflnip/yD+BvoysqE5U33ueQRY4U+sLiX7EmkCMNY5/u4cE4BX/Wu9k6x+dLObgcfMeNr3h5LVgoYzroo0ZCXPgZxjGdlndzLZecXL1djWjUBbM6YBP8HXQm7lM1iSGef7c509yc61Ntdfl8wtzrGELKe87H9+4pdt9kPgSn8B9DjZcMdJ+BKIxHPA4M1fnJNdoE3252qPAxf7fFrxnC/lR+icC/zDjHFsubMPWzkHChxLlhNFCvOzp0htsey5Dhc6x5m1fSzVYdkEF0Oc4/LaPhYR2T5m/Bs42Z/o7cj9XEd2h/+pHbkfEanbfC542DmerO1j2czf5bvTOT5S28ciDcMOefivVJ+/o/W0H15THzSDas+guNOZ2YlmNsPMZprZpWXWudXMFppZ2Vv+ZraXmT1tZlPNbIqZXVBmvV3M7CUzm+DX+3GFbTY1s1fNrOzDCc1stplNMrPxZlbybqCZtTezv5nZdDObZmZV6gjNrL/fxuafFWY2ssR6F/rjnmxmd5lZlXH5ZnaBj08ptQ2ply4iKyrf0SY3hguqnZl3tiXn+PUr5p3q5By/XsW8U92c49dV3ml8fkbp4ci1aW+yXFjv6FwnX6dunets71zs+tFPXfshG3+9eRKOFmRDlvYrsd5RwBCg7PNzyGYrGuLbu5I9/LXUtgzwz/SiOfAiMLzMNr9DNlTjkQr7nQ10Lhf36/wZ+JpvtwDaV+N9mQ98KFm+B/Am0Mr37wXOSdYZSDZcpTXZBfWTQJ/a/m+tH/3UlZ+dnXe2Jef4dSrmnerkHL9etfNOuZzjY8o7+tFPgR+d61R8X2r1XEd3qqQhOQSY6Zx7wzm3DribbLrWiHPuOYjGhlfhnJvnnBvn2yvJ6ur2KLGec86t8t3m/qfKmFoz25NsYpU/pbFtYWa7kSXKW/z+1znntjaE6yPALOdcqUlPmgGtzKwZWTJJnzWyL/Cic261c24D2UQFn0ZENtupeae6OQdqNe9UyjmgvCNShM51Sqv1cx1dVElDUu5hhYWYWU+yiVBeLBNvambjyYpk/+WcK7Xeb4DvQcWHskKWpJ4ws7Fmdm6JeC+ySQX+199e/5OZtdnKNr8A3FVlR869SzaRwdtkjyhY7px7IlltMnCkmXUys9ZkD4veCxHZbKfnnWrmHKhe3tlazoFtzzslcw4o74jUAJ3rlFbr5zq6qBKpwMzaAvcDI51zJZ/j45zb6Jw7iP/f3p3H21XVdx///DLPZCTEQAbAMBhCxMhQBIrKYOtLiqVqWqpi+6gVtFgfWxSHRwSUolTAShERfTQqFEGDRFAwFESJkBAyQEISCJgBQsCEzCHJr3+sfU/WXvecfc/Nvrnn5Ob7fr3uK2vttc7e6xw5P/c6ew1hVaXjzWxico53AmvcfXYdl3yLux9HWCL3QjM7NSnvQXicf4O7v5GwOlLV8dTZtXsB7yKs8piWDSH8ujWesPlhfzM7P3lvTwFXEVapvIewqubOOt6HiOyhtuJOWzEnO0e9caetmAPtiDtFMScrV9wRaTK61+mYmKNOlXQl9WyQWjcz60kIMtPc/Y626mePpmcSdomPnQy8y8yWEx7Tv9XMfljjHCuzf9cQlvE+PqmyAlgR/UJ0OyHw1PIOYI67v1il7O3As+7+kru/BtxBlW0I3P1md3+Tu58K/Ikw5lpEgobFnYKYA3XGnTpiDrQv7hTFHFDcESlL9zqtNcW9jjpV0pVkGzbb+OxXi/fRemf3upiZEcbyPuXu1xTUG2Fmg7N0X+AMsr2KWrj7Z9z9YHcfl7XpN+5+fpVz9TezgS1psr08knO9APzRzI7IDr0NeLLgrUylxjAcwqPwE82sX/Z+30YYT52268Ds3zGEMcY/KrieyP6mU+NOPTEH6os79cSc7FztiTtFMQcUd0TK0r1Oa01xr1O0IZrIPsXdd5hZy4bN3YHvuvvCtJ6Z/Ziw+elwM1sBfNHdb06qnUzY0X1+NoYY4LPuPiOpNwr4vpl1J/xIcZu711xGtA0jgTvDd54ewI/cvdqG0R8HpmXB9Bnggmony4LVGcBHqpW7+ywzux2YQ9ho+nHC5q2pn5rZMOA14MI6JouK7DcaEHcaEXOgjrjTVswBxR2RsnSvk9dM9zra/FdERERERKQEDf8TEREREREpQZ0qERERERGREtSpEhERERERKUGdKhERERERkRLUqRIRERERESlBnSoREREREZES1KkSEREREREpQZ0qERERERGREtSpEhERERERKUGdKhERERERkRLUqRIRERERESmhR6MbINJew4cP93HjxjW6GR3niSdgx47a5T16wLHHdl579tDs2bPXuvuIRrdDZG9ohrjTRUJFh1Lcka6sGeJOPfan2FQUc9Spkn3OuHHjeOyxxxrdjI5jVly+YwfsA+/XzJ5rdBtE9pZmiDtdJFR0KMUd6cqaIe7UY3+KTUUxR8P/RERERERESlCnSkREREREpAR1qkREREREREpQp0pERERERKSEhi5Usa+sarK/0WpK0lU1e8zZtm1bLt+7d+8OOe+WLVty+b59+3bIeTuKYo50Zc0ed1Jr166tpHcULekGdOu2+7f5Xr165coGDx7csQ3rYIo70tEa2qnaV1Y12d9oNSXpqpot5uzcuTOXX758eS5/2GGH7dG5unfvniubP39+Lj9x4sRK2tpatqkTKOZIV9ZscactN910UyW9bt26XFnayRowYEAlffDBB+fKzj333L3Quo6juCMdTcP/RERERERESlCnSkREREREpARt/isi0iCvvfZaLv/HP/4xly8a/ufuuXw65C+2atWqXP6YY46pt4ki0kDx97xoqG4aD9Jhej179qyk02HHPXrkbwXjuZxtDQ+Oy9O5m2effXYu/8tf/rLmeeL2pu0R2VfoSZWIiIiIiEgJ6lSJiIiIiIiUoGesIiIN0qdPn1z+O9/5Ti4fL0k8efLkXFnRsJyf//znufy1116by5911lntaqeINEbR8L9du3ZV0vHS5pAf7pe66KKLcvl064ZRo0ZV0uky6Vu3bs3lt2/fXkkPHDgwVzZ37tyabUjFQ/7S4YlFQ5tFmomeVImIiIiIiJSgTpWIiIiIiEgJ6lSJiIiIiIiUoDlVIiINki6p/tBDD+Xyjz76aCU9adKkXNkFF1yQy1922WWVdDrvYeLEiaXaKSKNEc+VSuNF0bypGTNm5PJf+9rXKully5blyoYOHZrLx3O3Ro8enStLt2eI5z+lc77SZd7juVqf/vSnc2UXX3xxJa05VLKv0pMqERERERGREtSpEhERERERKUGdKhERERERkRI0p0pEpEHSOREHHXRQLr9jx45KetGiRbmyCy+8MJeP97waMmRIrmzEiBGl2ikijRHvRVU0h2rq1Km5/G233ZbLDxgwoJLu169friydC7Vx48ZKevXq1YXt27JlSyXdt2/fXFm639S2bdsq6UsvvTRXdvXVV1fS119/fa7svPPOy+XjuBjvbyXSaHpSJSIiIiIiUoI6VSIiIiIiIiXouamISJNIh8+sXLmykh44cGCubPDgwbl87969K+l0SfX+/ft3VBNFpEnMnDmzkv7Zz36WKxs7dmwuHy/HHg+fq2b79u2V9PLly3NlRx99dC4fD+lbt25driwekpzm05gUt+9DH/pQrmzy5Mm5/OGHH15Jp8u2p0MZRTqTnlSJiIiIiIiUoE6ViIiIiIhICepUiYiIiIiIlKA5VSIiTSKdr7Bs2bJKumg55bQ8nVM1evTomq/TnASR5tWtW+3fvm+88cZKunv37rmydN5UvLx5+p2Pl22HfCxJ486qVaty+XguZ1uxJC5P2xdfJ33Pn/zkJ3P5u+66q+Y1RBpJT6pERERERERKUKdKRERERESkBA3/ExHpRPEQmHToSrrMcI8eu0N0W0NrRo4cWUm//PLLNa8pIvum9Hv829/+tpLu169frixeohzy8SI9T1o3HtKXDitMhwpu2rSpkk63hEivUxSH4uGAgwYNypU9+OCDufz8+fMr6WOOOabmOUU6m55UiYiIiIiIlKBOlYiIiIiISAnqVImIiIiIiJSgOVUiIp2oaAngpUuX5vJFyylv27Ytl9+wYUMlPWzYsFzZc889t0ftEZHmceutt+byr7zySiWdzkNK5z7F3/MDDjggV7Z58+ZcPp5jFS/FDq3nfcbXSWNSnz59arahaH5VW3Oxvv71r1fS3/ve92qeR6Sz6UmViIiIiIhICepUiYiIiIiIlKBOlYiIiIiISAmaU1XgW9/6Vi6/YMGCmmVF2tpfRkQEYObMmbn8mDFjKumePXvmytI5E7E0xixatKgDWicijfS73/0ul4/3kEr3mkr16tWrkt6yZUuuLH1tHGvi/aMABg8eXPMa6b1OOh8rniNadF+UXjPdK+uhhx6q2QaRRtKTKhERERERkRLUqRIRERERESmhqYb/xY+k+/btW3fd+LF2W9LHyLFf/OIXufyqVaty+QMPPLCSfv/7358ru+KKK3L5Qw45pJJua7hf+og8VtReEdm3LVmyJJcfMWJELt+7d++ar02XRY7jTBpzVq9evadNFJEmMWfOnFy+aDhdel8Ux4StW7fmytKlz+Phd23FgFWPqgAAHotJREFUkri8rXux7du316wbXzN9L2kc7NevX+F1RBpFT6pERERERERKUKdKRERERESkBHWqRERERERESmiqOVXxPKWLLrooV3baaafl8m3NudoT6TLpxx9/fC4fjwE++OCDc2W33nprLh/Pvzr33HNzZQMHDszl43lT6fyqdGxxvbRsu0jzS+dIxHMOIP89Llr2GPLzJOK5FgArVqwo1U4Rabxly5bl8vG9Q3qvkG65EMeEHj3yt37pEubxudK6aWyJ41J6nlT82qK66X1Q2oaNGzcWXkekUfSkSkREREREpAR1qkREREREREpQp0pERERERKSEhs6p2rVrF5s2bark43H/06dPz9XdvHlzLj9x4sRKeujQobmyeA+DdFzx888/n8vfcsstlfRBBx2UKxs+fHguf9ddd1XS55xzTq5s3bp1ufyMGTMq6UWLFuXKDj300Fz+jDPOqKTHjh3LnorHIReNpwbtfyXSDGbNmpXLp9/T+DudzplI68bl6ZzKUaNG5fJLly6tpA8//PB2tFhEGuXFF1/M5eN7lHTOZdGcpTR2pPEizqfnSe8t4rrpedO68TzQtL3tmQe+fPnySvrVV1/NlQ0aNKju84h0ND2pEhERERERKUGdKhERERERkRIaOvxvy5YtLFiwoGpZPCwQYNq0abn8pEmTKul4qfM0Hw9zAZg/f34uHy9hfMopp+TK0uWOzzrrrEo6HmJYrQ1nn312Jb1mzZpc2dNPP53L//73v6+kjzrqqFzZG97whkp6ypQpubIRI0bk8vGQPg3vE2l+CxcuzOXT4TNxXEmXEU6Hy8TDdNKydKjNyy+/XElr+J/IviEdAhz//3zRdgyQH0pcNNwvlQ7hS6dFxFMz0mka6X1Ieq5a7Suql1q8eHEu/+Y3v7nu14p0ND2pEhERERERKUGdKhERERERkRLUqRIRERERESmhoXOqdu7cmVuK/JVXXqmke/TIN239+vW5/J133llJDxkyJFcWzx8YOHBgruykk07K5SdMmFBJp/MZ4mXbAdauXVtJp2OH02Xd4/eSzr8aM2ZMzXy6POhDDz1UST/66KO5svS8gwcPrqTTpdkPPPDAXP7II4+spHv37o2IdL54aWBoPTcznieVLm2cxsh0TkWt8wAsWbKkkj7hhBPqaquIdL6VK1fWLIvnQqXzrTpKet50vlMcW9K5m+k9VZH4tWkcLHpvzz77bC6vOVXSSHpSJSIiIiIiUoI6VSIiIiIiIiWoUyUiIiIiIlJCQ+dUdevWjf79+1fy8f5NF1xwQa7uuHHjcvl4ztLWrVtzZfHcoj59+uTK0rrz5s2r2b4BAwbk8vEcpnT+wgsvvJDLx2OCBw0alCtLXxvPo0r3gEjnasXS9xLvh7Vq1aqabQe4/PLLK+nzzz+/5jVEZO95/vnnc/kjjjgil0/nKMTSvWXiOVbpvId0bkO6X5+INKd0H6Za2vrO76l0r6l4j7u0PL3fStsU59P2xXOz0jlVRftWrV69umaZSGfTkyoREREREZES1KkSEREREREpoaHD/9atW8f06dMr+VGjRlXS6fC1dKnxQw89tJJOlyiPHyOn59m2bVsuv3PnzsL2xeJl3Xv27JkrS5csLxr+l4qH5o0cObJm+9Jhg+mj9jiffl7p5xAPHbrmmmsK2yciHSf+TqdDeNMhMUXLpKdDYuLvdBrn0iE86XBlEWlOzzzzTF310i0W0mXI4/iQxpmiuql0C5Y4nqUxqT1tiPPp9YuG/7300ks1y0Q6m55UiYiIiIiIlKBOlYiIiIiISAnqVImIiIiIiJTQ0DlV27ZtY+nSpZX8YYcdVklPnDgxV3fBggW5/IoVKyrpouXDi8bipuXp/IU0H4/zTccVp+N64/K+ffvmytL5WLG1a9fWbN+GDRtyZemcr7g8XQ4+nbuxZMmSmucRkb3nueeeq1mWbn2wadOmSjqNG0XzF9K5DOn8y3QpdxFpTvFWKUXSeUjpfPF0XmW90lhSFHfSNhS1Kb2HiudUpVtJFN0zxdvriDSanlSJiIiIiIiUoE6ViIiIiIhICepUiYiIiIiIlNDQOVXdunXLzSF45JFHKum29mSKyzdv3pwri/eFGj58eK5s48aNuXzRPlXpGOR4H4h0T4h0z4V4n6pUOj44nv+Ujp+O31u691Q6Tyoeh5y2L967K33tl770pVzZBz7wgZptF5FyFi1aVLMsjSPxdzqNKWndOJal8yDSeLBy5cr6GisiDbVs2bKaZXEMSO9XtmzZkssXzUsqks6het3rXpfLv/zyy5V0ek+SzqmK41B6jzdkyJCq54TWbY/Po32qpJnoSZWIiIiIiEgJ6lSJiIiIiIiU0NDhf2PGjOH666/P5VsMHTo0Vzddajx+dJwOi4mHzKXLbQ4cODCXj4fFpcNp0iEz8WPw9NF6+pg7blP6mLvoOkVl6WcyePDgXD4eIpnWPeKII3L5M844g1o0/E9k72nP0Lt02G6saGnjdEniND6l2zOISHOK733Se5L4e57Gg7RuOiS4qCzOp/ckq1evzuWLtq0pup9Zv359ruz000+vpO++++5cWRoH4+GA6VBBkUbSkyoREREREZES1KkSEREREREpQZ0qERERERGREho6p6p79+65ZTSvvPLKBrZGRGTvi+czFc2RgPx8hXReQTqXIZ03FUvnNhTN1RKR5hHHi3Rp8Xj++NixY3Nl6fzxWbNmVdKjR4/OlW3bti2XL4olRWWpNEbFcSjd3iYW3xdC63lTcdws2hZHpLPpSZWIiIiIiEgJ6lSJiIiIiIiU0NDhfyIi+5t4SfV0OE86XCYe2tLWsJt4aE063C89bzzcJx1ymLZJRBonHv7Xt2/fXFm8ZczkyZNzZenQ4kceeaSSTpdQL4otad2iocPpeYry6XnjIX8TJkzIld133325/PDhwyvpoiXdRTqbnlSJiIiIiIiUoE6ViIiIiIhICepUiYiIiIiIlKA5VSIinejVV1+tpHv37p0rS+cZxLp3715YN56vkM6pSvOxeF4GwMiRI2vWFZHOFc+rLJrvePrpp+fyCxcurFm3KB6k0nlR6VLt8bLuZbZqGDZsWCUdz5mC1nOq4vYXxUyRzqYnVSIiIiIiIiWoUyUiIiIiIlKCOlUiIiIiIiIlaE6ViEgn2rhxYyXdnj2h0rkDaT6ec9XWeeO9qdatW5cr05wqkeYRz7uM51elzjnnnFx+7ty5Neume9Olez3Fc5bSsjTubN++verrqtWN98dL9erVq5I+9dRTc2Vf+cpXcvl4ntegQYNqnlOks+lJlYiIiIiISAnqVImIiIiIiJSg4X8iIp1o69atlXT//v1zZenwnjifDsNJly+Ohwmly6/HQ3QAxo8fX7U9ItJc4mFxqQEDBlTS6TLkmzZtyuXjIXNpLEnzRTZs2JDLx0P+0viVLsee5mPxML50q4k01sXtLRoSKdLZ9KRKRERERESkBHWqRERERERESlCnSkREREREpATNqRIR6UQPP/xwJT1w4MDCun379q2ahtZzLeJl1NO5C+nSxvE8qsWLF+fKjj322MI2iUjnieddxtsxQPF8yHRbhXieUrr0eZqP52SmsSSdfxWXp3XT8/bosfuWs0+fPrmyV199tWq6mvi9DBs2rLCuSGfSkyoREREREZES1KkSEREREREpQZ0qERERERGREjSnSkSkE330ox+tpL/yla/kytL9pOI9YVavXp0rGzp0aC7/2muvVdLpfKt07tbmzZsr6SFDhtTTbBFpgBkzZlTSa9euzZVt2bKl5uuWLl1a9zWK9sdL52PG86IgP48q3R8v3V8qPVds3rx5lfTnP//5ul8n0kz0pEpERERERKQEdapERERERERK0PA/EZFOdNlll1XSxxxzTK7sySefzOXj4T0TJkzIlU2ePDmXj4f09evXL1eWLps+derUdrRYRJrB8OHD666bDgGOlzBPl1tP8/FQ4nToXboUetFQwVRcNx2SfOSRRxa+VmRfoCdVIiIiIiIiJahTJSIiIiIiUoI6VSIiIiIiIiVYI5eqNLOXgOca1gCpZay7j2h0I2qZMmWKP/bYY41uRseJlqStaR9YUtbMZrv7lEa3o4hiTtNq6pgDzRF3ukio6FCKO1KC4k4H2Z9iU1HMaehCFc3+H7OIdC2KOSLS2RR3RPYPGv4nIiIiIiJSgjpVIiIiIiIiJahTJSIiIiIiUsLe71SZXYrZQszmYTYXsxM66LwPYFY8ObVWHbOLMFuKmWM2PDpumF2Xlc3D7Lio7AOYLcn+PpAd643ZPZgtwOxjUd1v517b+vp/hdkXsvQRWTvnYvYUZt+u7wNoh3o+q9qv7YXZg5hpo2jpUszYacZcMxaa8YQZnzLrnB+azPib7Lq7zJiSlH3GjKVmLDbjrOj42dmxpWZcEh2fZsY8M66Mjn3OjL8quP4bzbg5S3/QjJfMeNyMJWbca8afdew7zl17hBn37K3zi+xrzDjIjJ+YscyM2WbMMGNC269sdZ7BZnysoPy7ZqwxY0FyfKgZv86+/782Y0h23My4Los588w4Ljt+RNbOeWaclB3rYcZ9ZvRrfeXKdb5hxqlZuqcZX82uOceM35vxjva+5+xcF8fXzdoxZE/OJVLG3r1RNjsJeCdwHO7bsg5MrzZe1RkeBn4BPJAcfwfw+uzvBOAG4ATMhgJfBKYADszGbDpwCvBb4MrsnN/C7FigO+5zCq7/r8C7svR1wH/g/nMAzI4p++Y6jFkP3Ldjdj/wXmBao5sEMHv27LVm1tZKSsOBtR1QpznOVX1pnY5qV0e1fWwd52gmW9yZDGDGgcCPgEGE73qFGT3c2dHB114AvBu4MbnW0cD7gDcArwPui26u/hM4A1gBPGrGdEIM3+LOpOxm6ACgH3CCO5cXXP+zkCu/1Z2LsjacDtxhxunuPJW0r/Rn4c5LZqw242R3Hi5zrs5UR9xpinhSJVQ0Rbv2Yp19Le7kmGHAncD33XlfduxYYCTwdDtPNxj4GPCtGuXfA74J/P/k+CXA/e58NfvB5hLg36h1TwQfAf4ZWA5cC/w18E/AD93ZXON9DgNOdOfi7NCXgVHARHe2mTESOK2d77fFxcAPoXLtHxA+hyv28HxNo4PiTlPEgC4Um2rHHHffe3/wboe7apR9weFRhwUO3/ZseXeHBxyucviDw9MOp2TH+zr8xOEphzsdZjlMycpucHjMYaHDl6JrPFCpU70Nyx2GR/kbHaZG+cUOoxymOtzYqh68w+FKh94Oj2Rl0x1eV3DNCQ4zo/w8hzdVqfdBhzsc7nFY4vDvUdmZDr93mOPw3w4D6vhMpzh0c/iew+UO3R2uzurPc/hIVvfPHR7K3sfT2bFjHWbs1f9WOvgPeKwj6uwP5+rI6+1Lf+Abk/yh4C+DG/gHwaeD/wb8f8D7g38X/A/gj4Ofk73mDdmxueDzwF+f1b0b/AnwBeDvLWjDA+BTovxnwD8T5e8FPyn7uzetB34U+DTwbtm5BoDfBH5cwTUHgi+O8h8E/2ZS5zLw/4ja+A3wx8A/Bf6m7DOZnbVvVFbvE+BPZp/DT7Jjp2WfzdzscxuYHT8H/FuN/m+gY/972ndjQLOeq6vFnOrv0d8K/mCNMgO/Oosj81tiSfY9vx98Tna8JR79BHxL9n27usY5x4EvSI4tjr7Ho1riA/iN4FPTeuBXgZ8JPiG75mDwX4F3K3ifHwb/f1m6XxZrB9WoOzV7XwvAr4qO35DFoYXgX8qOfQJ8e1Z/ZnZsSPoeu+pfM35v95dzVfvb20O6fgV8AbOngfuAW3H/n6zsm7hfBoDZDwhPtO7Kynrgfjxmf0H41fjthF9BNuN+FGaTgPhJ0KW4v4JZd+B+zCbhPm8P2jsa+GOUX5Edq3X8v4G/Bx4BrsbsXcAc3FcVXOPkpO3/AfwGs98RPq9bcF+XlU0G3ghsAxZjdj2wBfgc8HbcN2H2b8C/AJfR1mcanjQtwP0KzD4MrMf9zZj1Bh7G7FdZ3eOAibg/m+UXAG8ueE8i+zx3njGjO3Bgdug4YJI7r2RD637jzofMGAz8wYz7gI8C17ozzYxeQHfgL4BV7vwlQPb0qF6jCfGkRUusgdYx6AR3njLjJUJM+QFwONDNnaIn5VMgP/ynijmEX6Nb9HJnihk9gf8BzvHwxOm9hF+DP0T4dXu8h1+dB2ev+7/Ahe48bMYAYGt2/DEofJImsr+YCMyuUfZuwn3AsYRfzx8140HgJeBcd141YzjwSPbk+hLCk5/J7WzDSHdWZ+kXCE/JoPa9z38Snnb1JsSJzwNXurOr4BonA7dn6cOB5915Na1kxuuAq4A3AX8CfmXGX7nzM+DSLB53B+43Y5I715nxL8Dp7uHpgjt/MqO3GcPcebmdn4XIHtu78wfcNxK+GB8mBIFbMftgVno6ZrMwmw+8lTDcpcUd2b+zgXFZ+lTC412yDlPcaXoPZnOAx7PzHN3Rb6Uq9x24/y3ubyR0sC4Gvo7ZNZjdnnWyUqMIn0XLOW4Bjspe/+fAI1knB+B+3NfjvhV4kvDI8UTC+3sYs7nAB9j9KLLoM72Rlg5VcCbw/uwcs4BhhEf8AH+IOlTgvhPYjtnA9n1AIvu0X7vzSpY+E7jEjLmEYcN9gDHA74HPmvFvwFh3tgDzgTPMuMqMU9xZvzcb6c7F7kx25+uEITWfN+NSM24z4/9UeUk+BlWXDtS4Nfv3CMJN4K+zz+JzwMFZ2TxgmhnnQ2WI4MPANWZ8Ahjsu4cOriEMbxSR2t4C/Nidne68SPhB482E7+eVZswj/GA9mt0doVLcccDbqPO8O3/uzkmEIXcHA0+Z8QMzbq0xH6yeuAPh/T3gzktZvJhGuP8DeI8Z9d7rKcZIp9v7k7Ldd+L+AO5fBC4C/hqzPoQxv+fhfgxwE+EmpcW27N+dtDXvy2w84dfQt+E+Cbg7OVd7rAQOifIHZ8dqHY99jPDLzYnAesIcpE9VucaWVu1zX4X7d3E/h3AzMjEr2RbVavksDPg17pOzv6Nx/4c6PtPfETpdLccM+Hh0nvG4tzyp2lSl3b3Z/SvzvqCeBT/qXRSkq5+rI6+3zzLjUML3bE12KP4eGPDXWedlsjtj3HnKnR8R5kduAWaY8VZ3niY85ZoPXG7GF9rRjD2OQWacQ/ghagBwmDvvAc6rMnG8dQxq7Y2Qm0/V8lkYsDD6HI5x58ys7C8Jv2AfR/hFvYc7XwX+EegLPGzGkVndPlk7upJ9OQY067m6dMzJLCT8+NwefweMAN6UPZV6kT2/7wF40YxRANm/LTGwnnufKwg/rnwC+A5hzvgXq1wjjjtLgTFmDKq3gWZU7vXcqederyvGmGqa8Xu7v5yrlb3bqQor270+OjIZeI7dX4S1mA0AzqvjbA8Cf5uddyIwKTs+iPB/+OsxGwl7tnpMZjrh6Y1hFjpH7quBe4EzMRuC2RDCr9b3Vl4Vjr2T0KnqB+wi/NLTt8o1niI8+m557dmY9czSBxGeGKVBK/YIcDJmh2ev6Y/ZBNr+TG8GZgC3ZSv53Qv8U3TtCZj1r3pFs2HAWtxfK2hXU3H3Nr8U9dTZH87VkdfbV5kxAvgv4JvZL7Wpe4GPZ5PKMeON2b+HAs+4cx3wc2BSNnxlszs/BK4mdDLqNR14XzZ0ZTzh6fEfgEeB15sxPhtm+L6sbkv7exKelP87Ie60vIfutF4cKB+DEmacRhhdcFOV4sXAiGjFr55mvMHCqomHuDOTMMH9AGCAGYe5M9+dq7L30NKpmkDbQxD3KftyDGjWc3XlmBP5DdDbjA+3HDBjkhmnAA8B7zWjexajTiXEgwOANe68li0s0zJaZQOwJyNKphNGvZD9+/Po+PuzVQBPBNZHwwRbYsUqd5aw+95nV5ZOVeKOh8UsbgauzeJZy6qgf5O9v9PMGJ4N85tKeEJXudfLFrWI7/Vy7zuL0wcRFtLo0prxe7u/nKuavT2nagBwPWaDCU9glgIfxn0dZjcR/k/1BcL/2bblBuAWzJ4ifDnDGGT3JzB7HFhEGPvb9mpSZp8g/JpyEDAPsxm4/yOh0/EXWTs3Axdk13gFsy9H7bwM91eiM34BuAL3XZjdC1xI+JX6v6pc/UHCEEHLZsSdCVyLWctToE/j/kKN1d7A/aVsCOWPo2GCn8P96TY/U/drMDuAMPfi7whDK+dgZoTH8rWWYD6d8KuQSFfSNxvC1pMQn34AXFOj7peBbwDzsg7Es4QfUt4D/L0ZrxG+d1cShq9cbcYu4DXCfNAcM84Frif82ny3GXPdOcudhWbcRhjuu4MwH2ln9pqLCJ277sB33VkYnfJCwuphm7MhQf3MmA/McGddVA93FplxgBkD3dmQHX6vGW8h3Aw9S3gql1v5L3vtdjPOA67L5or1yD6Xp4EfZscMuM6ddWZ8Obvp20X4Rf6X2akUU0QIw+2yePCNbBjxVkJn4GLC6sInAU8Qfij5V3deMGMacFf2HX+McP+DOy+b8bCFJdN/6c6n42uZ8WPCNIPhZqwAvujOzcBXgdvM+AfCD9/vyV5S/Z6ISsflc4RRORB+3Z9GiAmtYh7h+/4RwtMsstdeDjxpxlZCh+kL7qzOViCcSYgld7uHTp4Zte71vg3cY8Yqd04nPPl7xDt+1VaRQpatdCGdyexa4C7c72t0U+pidgdwCe7tXd5VRJqQGZ8ENrhXbnA6+/oPEha7+FMjri8inc+M3wLvTH/o2QvXuRaY7s79e/M6IqlO2ehSWrmS6o/Hm49ZL+Bn+0qHyszONrPFZrbUzC6pUee7ZrbGzGoOPzKzQ8xsppk9aWYLzeyfa9TrY2Z/MLMnsnpfKjhndzN73Mx+UVBnuZnNN7O5ZvZYjTqDzex2M1tkZk9Z2A8urXNEdo6Wv1fN7OIq9T6ZtXuBmf3Yds+5i+v8c1a+sNo5ZJ90A/k5m50mG8Z0TVfqUHVm3GlPzMnqF8ademJOVq8w7tQbc7K6ijv7p08RFvjZ2xZ09Q6V7nUqdZrrXmdP12LXn/6a7Y8wLGoZcChhHskTwNFV6p1KmOdScx8LwkpFx2XpgYThTdXOZWT7hBGGkc0CTqxxzn8hbDD7i4LrLifeO616ne8D/5ilewGD6/hcXgDGJsdHE4Z69c3ytwEfTOpMJAwp7UcY1nEfcHij/7fWn/6a5a+z4057Yk5WpzDu1BNzsnp1x51aMScrU9zRn/5K/Olep/Bzaei9jp5USVdyPLDU3Z9x9+3AT4Bz0kru/iDwSno8qbPa3edk6Q2EeXyjq9RzD1sHQAg0PamyHK2ZHUxYHa3UcCsLc+JOJUzyxd23++59zWp5G7DM3avtyt4D6Gth8ZJ+QLrH2lHALHff7O47CBOG313mPYh0MZ0ad+qNOdDQuFMUc0BxR6QM3etU1/B7HXWqpCuptVFhKWY2jrDE9Kwa5d0t7Pe1Bvi1u1er9w3C4ihFmyNCCFK/MrPZFjZoTo0nLCpyS/Z4/TtWa9XG3d4H/LjVhdxXAl8DngdWA+t997L6LRYAp5jZMDPrR5i0fAgi0qLT406dMQfqizttxRxof9ypGnNAcUekA+hep7qG3+uoUyVSwMLy9D8FLnb3Vru/A7j7TnefTNjD43gLS/7H53gnsMbdZ9dxybe4+3GE5WIvNLNTk/IehMf5N3jYdHoTUHU8dXbtXoR9lP67StkQwq9b4wmbJPY3s/OT9/YUYXf7XwH3AHMJezmJyF7SVtxpK+Zk56g37rQVc6Adcaco5mTlijsiTUb3Oh0Tc9Spkq6kno0K62ZhD6+fAtPc/Y626mePpmcCZydFJwPvMrPlhMf0bzWzH9Y4x8rs3zXAnYTH/LEVwIroF6LbKd4H6R3AHHd/sUrZ24Fn3f0lD3uQ3QH8WZU23ezub3L3U4E/EcZci0jQsLhTEHOgzrhTR8yB9sWdopgDijsiZelep7WmuNdRp0q6kmyDVBuf/WqR2yC1PczMCGN5n3L3WnsXYWYjLOzDhpn1Bc4g2zOkhbt/xt0PdvdxWZt+4+7nVzlXfzMb2JIm7GG2IDnXC8AfzeyI7NDbCHsa1TKVGsNwCI/CTzSzftn7fRu03pvIzA7M/h1DGGP8o4LriexvOjXu1BNzoL64U0/Myc7VnrhTFHNAcUekLN3rtNYU9zp7e/NfkU7j7jvMLNkg1Rem9cws2gDRsg0Q/eak2snA3wPzszHEAJ919xlJvVHA982sO+FHitvcveYyom0YCdwZvvP0AH7k7vdUqfdxYFoWTJ8h2pAxlgWrMwgbLrbi7rPM7HZgDmGj2ccJmyimfmpmwwgb2V5Yx2RRkf1GA+JOI2IO1BF32oo5oLgjUpbudfKa6V5Hm/+KiIiIiIiUoOF/IiIiIiIiJahTJSIiIiIiUoI6VSIiIiIiIiWoUyUiIiIiIlKCOlUiIiIiIiIlqFMlIiIiIiJSgjpVIiIiIiIiJfwvbvRl6yuAGeUAAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 864x720 with 30 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j2KlSAkwx2DX",
        "colab_type": "text"
      },
      "source": [
        "# Congrats on Solving Your First Project in ML!\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "---\n",
        "###### Credits: https://www.tensorflow.org/tutorials/keras/classification"
      ]
    }
  ]
}