1027 lines (1027 with data), 376.4 kB

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "ECG_project.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyO0prtYilJLwoIgWqYim3nF",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/hardikroutray/ECG/blob/main/ECG_project.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "g4s82uBJWlj7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f2a992cd-59ea-41b3-c703-4d5859d75685"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib as plt\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sn\n",
        "%matplotlib inline\n",
        "%pylab inline\n",
        "%config InlineBackend.figure_formats = ['retina']\n",
        "from imutils import paths\n",
        "import time   # time1 = time.time(); print('Time taken: {:.1f} sec'.format(time.time() - time1))\n",
        "import cv2\n",
        "import pickle\n",
        "import warnings\n",
        "warnings.filterwarnings(\"ignore\")\n",
        "import pickle\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Populating the interactive namespace from numpy and matplotlib\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pluEuqpFYD0V"
      },
      "source": [
        "\n",
        "import keras\n",
        "import keras.utils\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, Dropout, Flatten\n",
        "from keras.layers import Conv2D, MaxPooling2D\n",
        "from keras.optimizers import Adam\n",
        "\n",
        "from tensorflow.keras import utils as np_utils\n",
        "\n",
        "from tensorflow.keras.utils import to_categorical\n",
        "from keras.preprocessing import image\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "from tqdm import tqdm\n",
        "from sklearn.metrics import plot_confusion_matrix\n",
        "from sklearn.model_selection import train_test_split\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cwJWpDYHJ0Fs"
      },
      "source": [
        "from tensorflow import keras \n",
        "from tensorflow.keras.models import Model\n",
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Conv1D\n",
        "from tensorflow.keras.layers import Convolution1D, ZeroPadding1D, MaxPooling1D, BatchNormalization, Activation, Dropout, Flatten, Dense"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JSElyJujYOGQ",
        "outputId": "5dd6d0ef-4f92-4050-ee0b-216bcfbab84d"
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount._DEBUG = True\n",
        "drive.mount('/content/MyDrive', force_remount=True)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "unset HISTFILE; export PS1=\"root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: \"\n",
            "bash: cannot set terminal process group (-1): Inappropriate ioctl for device\n",
            "bash: no job control in this shell\n",
            "\u001b[01;34m/content\u001b[00m# root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: umount -f /content/MyDrive || umount /content/MyDrive; pkill -9 -x drive\n",
            "umount: /content/MyDrive: no mount point specified.\n",
            "umount: /content/MyDrive: no mount point specified.\n",
            "root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: pkill -9 -f /opt/google/drive/directoryprefetcher_binary\n",
            "root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: ( while `sleep 0.5`; do if [[ -d \"/content/MyDrive\" && \"$(ls -A /content/MyDrive)\" != \"\" ]]; then echo \"google.colab.drive MOUNTED\"; break; fi; done ) &\n",
            "[1] 158\n",
            "root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: cat /tmp/tmpxk3y3ecb/drive.fifo | head -1 | ( /opt/google/drive/drive --features=fuse_max_background:1000,max_read_qps:1000,max_write_qps:1000,max_operation_batch_size:15,max_parallel_push_task_instances:10,opendir_timeout_ms:120000,virtual_folders_omit_spaces:true --inet_family=IPV4_ONLY --preferences=trusted_root_certs_file_path:/opt/google/drive/roots.pem,mount_point_path:/content/MyDrive --console_auth 2>&1 | grep --line-buffered -E \"(Go to this URL in a browser: https://.*)$|Drive File Stream encountered a problem and has stopped|Authorization failed|The domain policy has disabled Drive File Stream\"; echo \"drive EXITED\"; ) &\n",
            "[2] 161\n",
            "root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.activity.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fexperimentsandconfigs%20https%3a%2f%2fwww.googleapis.com%2fauth%2fphotos.native&response_type=code\n",
            "google.colab.drive MOUNTED\n",
            "fuser -kw \"/root/.config/Google/DriveFS/Logs/timeouts.txt\" ; rm -rf \"/root/.config/Google/DriveFS/Logs/timeouts.txt\"\n",
            "Specified filename /root/.config/Google/DriveFS/Logs/timeouts.txt does not exist.\n",
            "root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: nohup bash -c 'tail -n +0 -F \"/root/.config/Google/DriveFS/Logs/drive_fs.txt\" | python3 /opt/google/drive/drive-filter.py > \"/root/.config/Google/DriveFS/Logs/timeouts.txt\" ' < /dev/null > /dev/null 2>&1 &\n",
            "[3] 291\n",
            "root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: disown -a\n",
            "root@b7c9efda8951-3fa0a08868c44e1badf05dfc7af50d5f: exit\n",
            "Mounted at /content/MyDrive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OneI2FHXYF8H"
      },
      "source": [
        "# Enter the directory\n",
        "!cd /content/MyDrive/MyDrive/ECG/\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DKV8pm3NMi_c"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jALJ2MIEH3ib"
      },
      "source": [
        "# Importing any of these files is fine.\n",
        "They differ by methods of preprocessing of the CSV files"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DlqItrd6XNnX"
      },
      "source": [
        "#Files 1\n",
        "with open('/content/MyDrive/MyDrive/ECG/dataset_dict.pickle', 'rb') as file:\n",
        "    dataset_dict = pickle.load(file)\n",
        "# Sets with truncated max and min to remove strays\n",
        "with open('/content/MyDrive/MyDrive/ECG/dataset_dict_nominmax.pickle', 'rb') as file:\n",
        "    dataset_dict = pickle.load(file)\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zY9lmesoBffF"
      },
      "source": [
        "#Full_no2\n",
        "with open('/content/MyDrive/MyDrive/ECG/dataset_full.pickle', 'rb') as file:\n",
        "    dataset_dict = pickle.load(file)\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NhNlh62VjOfY",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "e46d4ce0-6d61-4164-e455-7a513ac9ba94"
      },
      "source": [
        "dataset_dict.keys()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "dict_keys(['XY', 'label'])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "y12V8VMrkh6F"
      },
      "source": [
        "## Only use for XY, label when we import dataset_full"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tiPhEKAokmtU",
        "outputId": "cf6370c7-4fc1-4983-e213-66043785db48"
      },
      "source": [
        "X_train, X_test, y_train, y_test = train_test_split( dataset_dict['XY'], dataset_dict['label'], random_state=24)\n",
        "print(X_train.shape, y_train.shape, X_test.shape, y_test.shape)\n",
        "\n",
        "x_train1=X_train\n",
        "x_test1=X_test\n",
        "\n",
        "y_train1=y_train\n",
        "y_test1=y_test\n",
        "\n",
        "y_test = to_categorical(y_test1) #[:,1:5] # Since labeling is [1,2,3,4] instead \\\n",
        "# of [0,1,2,3]\n",
        "y_train = to_categorical(y_train1)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "(754, 673, 2) (754,) (252, 673, 2) (252,)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OAKau2s0iv40"
      },
      "source": [
        "# x_train1=dataset_dict['X_train']\n",
        "# x_test1=dataset_dict['X_test']\n",
        "\n",
        "# y_train1=dataset_dict['y_train']\n",
        "# y_test1=dataset_dict['y_test']\n",
        "\n",
        "# y_test = to_categorical(y_test1) #[:,1:5] # Since labeling is [1,2,3,4] instead \\\n",
        "# # of [0,1,2,3]\n",
        "# y_train = to_categorical(y_train1) #[:,1:5] #one-hot encoding"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uv-ZsQniIHqO"
      },
      "source": [
        "Plotting an example to see if the coarse grained reconstruction looks reasonable. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7GqJwWjSlCZ7",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 272
        },
        "outputId": "08b8ae18-3f2e-4790-cbb8-1cc2024e96a4"
      },
      "source": [
        "plt.plot(x_train1[1,:,0],x_train1[1,:,1])\n",
        "# plt.axis([0,400,-50,50])\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 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "image/png": {
              "width": 391,
              "height": 255
            }
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ejmMjREWjbnF"
      },
      "source": [
        "comb_x=np.concatenate([x_train1, x_test1],axis=0)\n",
        "comb_y=np.concatenate([y_train, y_test],axis=0)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vwseJd7gAL2L"
      },
      "source": [
        "v=-1"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "egYjhsPLj25f"
      },
      "source": [
        "x_train, x_test, y_train, y_test = train_test_split(comb_x, comb_y, random_state=150, test_size=0.2, stratify=comb_y)\n",
        "\n",
        "x_train=x_train[:,:v,1]\n",
        "x_test=x_test[:,:v,1]\n",
        "\n",
        "\n",
        "x_train=np.expand_dims(x_train,2)\n",
        "x_test=np.expand_dims(x_test,2)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "whti8wEQOmQU"
      },
      "source": [
        "# x_test.reshape(742,1980,1)\n",
        "print(x_test.shape)\n",
        "\n",
        "y_test.shape"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-c3Ix3bpIc-o"
      },
      "source": [
        "# Model \n",
        "1d CNN <br>\n",
        "https://towardsdatascience.com/understanding-1d-and-3d-convolution-neural-network-keras-9d8f76e29610\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "uUAeR8Q8_q92",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "86dcb04c-99d8-4170-b907-5dd47b25b240"
      },
      "source": [
        "# Earlier (128)\n",
        "\n",
        "num_classes=4\n",
        "\n",
        "model_m = Sequential()\n",
        "input_shape=(x_train.shape[1], 1)\n",
        "model_m.add(Conv1D(128, kernel_size=3,padding = 'same',activation='relu', input_shape=input_shape))\n",
        "\n",
        "model_m.add(BatchNormalization())\n",
        "\n",
        "model_m.add(MaxPooling1D(pool_size=(2)))\n",
        "\n",
        "## CONV2\n",
        "model_m.add(Conv1D(64,kernel_size=3,padding = 'same', activation='relu'))\n",
        "\n",
        "model_m.add(BatchNormalization())\n",
        "\n",
        "model_m.add(MaxPooling1D(pool_size=(2)))\n",
        "## End CONV2\n",
        "\n",
        "model_m.add(Flatten())\n",
        "model_m.add(Dense(64, activation='tanh'))\n",
        "model_m.add(Dropout(0.1))\n",
        "# model_m.add(Dense(32, activation='tanh'))\n",
        "# model_m.add(Dropout(0.2))\n",
        "model_m.add(Dense(16, activation='relu'))\n",
        "model_m.add(Dropout(0.2))\n",
        "model_m.add(Dense(num_classes, activation='softmax'))\n",
        "model_m.summary()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "conv1d (Conv1D)              (None, 672, 128)          512       \n",
            "_________________________________________________________________\n",
            "batch_normalization (BatchNo (None, 672, 128)          512       \n",
            "_________________________________________________________________\n",
            "max_pooling1d (MaxPooling1D) (None, 336, 128)          0         \n",
            "_________________________________________________________________\n",
            "conv1d_1 (Conv1D)            (None, 336, 64)           24640     \n",
            "_________________________________________________________________\n",
            "batch_normalization_1 (Batch (None, 336, 64)           256       \n",
            "_________________________________________________________________\n",
            "max_pooling1d_1 (MaxPooling1 (None, 168, 64)           0         \n",
            "_________________________________________________________________\n",
            "flatten (Flatten)            (None, 10752)             0         \n",
            "_________________________________________________________________\n",
            "dense (Dense)                (None, 64)                688192    \n",
            "_________________________________________________________________\n",
            "dropout (Dropout)            (None, 64)                0         \n",
            "_________________________________________________________________\n",
            "dense_1 (Dense)              (None, 16)                1040      \n",
            "_________________________________________________________________\n",
            "dropout_1 (Dropout)          (None, 16)                0         \n",
            "_________________________________________________________________\n",
            "dense_2 (Dense)              (None, 4)                 68        \n",
            "=================================================================\n",
            "Total params: 715,220\n",
            "Trainable params: 714,836\n",
            "Non-trainable params: 384\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yi63jA2WJsC2",
        "outputId": "f24f8efb-47d6-496b-90bf-7fda13c20854"
      },
      "source": [
        "num_classes=4\n",
        "\n",
        "model_m = Sequential()\n",
        "input_shape=(x_train.shape[1], 1)\n",
        "model_m.add(Conv1D(64, kernel_size=3,padding = 'same',activation='relu', input_shape=input_shape))\n",
        "\n",
        "model_m.add(BatchNormalization())\n",
        "\n",
        "model_m.add(MaxPooling1D(pool_size=(2)))\n",
        "\n",
        "## CONV2\n",
        "model_m.add(Conv1D(32,kernel_size=3,padding = 'same', activation='relu'))\n",
        "\n",
        "model_m.add(BatchNormalization())\n",
        "\n",
        "model_m.add(MaxPooling1D(pool_size=(2)))\n",
        "## End CONV2\n",
        "\n",
        "\n",
        "## CONV2\n",
        "model_m.add(Conv1D(16,kernel_size=3,padding = 'same', activation='relu'))\n",
        "\n",
        "model_m.add(BatchNormalization())\n",
        "\n",
        "model_m.add(MaxPooling1D(pool_size=(2)))\n",
        "## End CONV2\n",
        "\n",
        "model_m.add(Flatten())\n",
        "model_m.add(Dense(32, activation='tanh'))\n",
        "model_m.add(Dropout(0.1))\n",
        "# model_m.add(Dense(32, activation='tanh'))\n",
        "# model_m.add(Dropout(0.2))\n",
        "model_m.add(Dense(16, activation='relu'))\n",
        "model_m.add(Dropout(0.2))\n",
        "model_m.add(Dense(num_classes, activation='softmax'))\n",
        "model_m.summary()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential_15\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "conv1d_30 (Conv1D)           (None, 672, 64)           256       \n",
            "_________________________________________________________________\n",
            "batch_normalization_20 (Batc (None, 672, 64)           256       \n",
            "_________________________________________________________________\n",
            "max_pooling1d_30 (MaxPooling (None, 336, 64)           0         \n",
            "_________________________________________________________________\n",
            "conv1d_31 (Conv1D)           (None, 336, 32)           6176      \n",
            "_________________________________________________________________\n",
            "batch_normalization_21 (Batc (None, 336, 32)           128       \n",
            "_________________________________________________________________\n",
            "max_pooling1d_31 (MaxPooling (None, 168, 32)           0         \n",
            "_________________________________________________________________\n",
            "conv1d_32 (Conv1D)           (None, 168, 16)           1552      \n",
            "_________________________________________________________________\n",
            "batch_normalization_22 (Batc (None, 168, 16)           64        \n",
            "_________________________________________________________________\n",
            "max_pooling1d_32 (MaxPooling (None, 84, 16)            0         \n",
            "_________________________________________________________________\n",
            "flatten_15 (Flatten)         (None, 1344)              0         \n",
            "_________________________________________________________________\n",
            "dense_44 (Dense)             (None, 32)                43040     \n",
            "_________________________________________________________________\n",
            "dropout_30 (Dropout)         (None, 32)                0         \n",
            "_________________________________________________________________\n",
            "dense_45 (Dense)             (None, 16)                528       \n",
            "_________________________________________________________________\n",
            "dropout_31 (Dropout)         (None, 16)                0         \n",
            "_________________________________________________________________\n",
            "dense_46 (Dense)             (None, 4)                 68        \n",
            "=================================================================\n",
            "Total params: 52,068\n",
            "Trainable params: 51,844\n",
            "Non-trainable params: 224\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "1hAXD7g5J5B6",
        "outputId": "80a57b99-54b0-41fa-ea3a-951ed3601015"
      },
      "source": [
        "model_m.compile(loss='categorical_crossentropy',\n",
        "                optimizer='adam', metrics=['accuracy'])\n",
        "\n",
        "# Hyper-parameters\n",
        "BATCH_SIZE = 100\n",
        "EPOCHS = 100\n",
        "\n",
        "# Enable validation to use ModelCheckpoint and EarlyStopping callbacks.\n",
        "shape=x_train.shape\n",
        "history = model_m.fit(x_train,\n",
        "                      y_train,\n",
        "                      batch_size=BATCH_SIZE,\n",
        "                      epochs=EPOCHS,\n",
        "                      validation_split=0.1,\n",
        "                      verbose=1)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/100\n",
            "8/8 [==============================] - 4s 412ms/step - loss: 0.0591 - accuracy: 0.9834 - val_loss: 0.8027 - val_accuracy: 0.8395\n",
            "Epoch 2/100\n",
            "8/8 [==============================] - 3s 377ms/step - loss: 0.0785 - accuracy: 0.9723 - val_loss: 0.8312 - val_accuracy: 0.8148\n",
            "Epoch 3/100\n",
            "8/8 [==============================] - 3s 379ms/step - loss: 0.0698 - accuracy: 0.9765 - val_loss: 0.7749 - val_accuracy: 0.8395\n",
            "Epoch 4/100\n",
            "8/8 [==============================] - 3s 385ms/step - loss: 0.0592 - accuracy: 0.9876 - val_loss: 0.6955 - val_accuracy: 0.8395\n",
            "Epoch 5/100\n",
            "8/8 [==============================] - 3s 380ms/step - loss: 0.0561 - accuracy: 0.9889 - val_loss: 0.8705 - val_accuracy: 0.8519\n",
            "Epoch 6/100\n",
            "8/8 [==============================] - 3s 380ms/step - loss: 0.0560 - accuracy: 0.9806 - val_loss: 0.8837 - val_accuracy: 0.8395\n",
            "Epoch 7/100\n",
            "8/8 [==============================] - 3s 379ms/step - loss: 0.0401 - accuracy: 0.9917 - val_loss: 0.7805 - val_accuracy: 0.8519\n",
            "Epoch 8/100\n",
            "8/8 [==============================] - 3s 385ms/step - loss: 0.0475 - accuracy: 0.9862 - val_loss: 0.7021 - val_accuracy: 0.8642\n",
            "Epoch 9/100\n",
            "8/8 [==============================] - 3s 387ms/step - loss: 0.0392 - accuracy: 0.9903 - val_loss: 0.8165 - val_accuracy: 0.8642\n",
            "Epoch 10/100\n",
            "8/8 [==============================] - 3s 383ms/step - loss: 0.0504 - accuracy: 0.9876 - val_loss: 0.7460 - val_accuracy: 0.8642\n",
            "Epoch 11/100\n",
            "8/8 [==============================] - 3s 377ms/step - loss: 0.0304 - accuracy: 0.9945 - val_loss: 0.7533 - val_accuracy: 0.8519\n",
            "Epoch 12/100\n",
            "8/8 [==============================] - 3s 380ms/step - loss: 0.0225 - accuracy: 0.9986 - val_loss: 0.6737 - val_accuracy: 0.8519\n",
            "Epoch 13/100\n",
            "8/8 [==============================] - 3s 381ms/step - loss: 0.0247 - accuracy: 0.9972 - val_loss: 0.6527 - val_accuracy: 0.8642\n",
            "Epoch 14/100\n",
            "8/8 [==============================] - 3s 377ms/step - loss: 0.0277 - accuracy: 0.9945 - val_loss: 0.7631 - val_accuracy: 0.8519\n",
            "Epoch 15/100\n",
            "8/8 [==============================] - 3s 383ms/step - loss: 0.0219 - accuracy: 0.9959 - val_loss: 0.7143 - val_accuracy: 0.8519\n",
            "Epoch 16/100\n",
            "8/8 [==============================] - 3s 379ms/step - loss: 0.0247 - accuracy: 0.9945 - val_loss: 0.8858 - val_accuracy: 0.8642\n",
            "Epoch 17/100\n",
            "8/8 [==============================] - 3s 385ms/step - loss: 0.0394 - accuracy: 0.9862 - val_loss: 0.9010 - val_accuracy: 0.8642\n",
            "Epoch 18/100\n",
            "8/8 [==============================] - 3s 388ms/step - loss: 0.0240 - accuracy: 0.9945 - val_loss: 0.9225 - val_accuracy: 0.8519\n",
            "Epoch 19/100\n",
            "8/8 [==============================] - 3s 382ms/step - loss: 0.0228 - accuracy: 0.9931 - val_loss: 0.9769 - val_accuracy: 0.8519\n",
            "Epoch 20/100\n",
            "8/8 [==============================] - 3s 382ms/step - loss: 0.0342 - accuracy: 0.9862 - val_loss: 0.7760 - val_accuracy: 0.8519\n",
            "Epoch 21/100\n",
            "8/8 [==============================] - 3s 384ms/step - loss: 0.0322 - accuracy: 0.9917 - val_loss: 0.6857 - val_accuracy: 0.8765\n",
            "Epoch 22/100\n",
            "8/8 [==============================] - 3s 380ms/step - loss: 0.0294 - accuracy: 0.9931 - val_loss: 0.6294 - val_accuracy: 0.8519\n",
            "Epoch 23/100\n",
            "8/8 [==============================] - 3s 384ms/step - loss: 0.0279 - accuracy: 0.9945 - val_loss: 0.6308 - val_accuracy: 0.8642\n",
            "Epoch 24/100\n",
            "8/8 [==============================] - 3s 380ms/step - loss: 0.0202 - accuracy: 0.9972 - val_loss: 0.6634 - val_accuracy: 0.8765\n",
            "Epoch 25/100\n",
            "8/8 [==============================] - 3s 382ms/step - loss: 0.0207 - accuracy: 0.9986 - val_loss: 0.5723 - val_accuracy: 0.8642\n",
            "Epoch 26/100\n",
            "8/8 [==============================] - 3s 385ms/step - loss: 0.0236 - accuracy: 0.9959 - val_loss: 0.5092 - val_accuracy: 0.8395\n",
            "Epoch 27/100\n",
            "8/8 [==============================] - 3s 384ms/step - loss: 0.0260 - accuracy: 0.9959 - val_loss: 0.7525 - val_accuracy: 0.8519\n",
            "Epoch 28/100\n",
            "8/8 [==============================] - 3s 384ms/step - loss: 0.0209 - accuracy: 0.9945 - val_loss: 0.8691 - val_accuracy: 0.8642\n",
            "Epoch 29/100\n",
            "8/8 [==============================] - 3s 384ms/step - loss: 0.0160 - accuracy: 0.9972 - val_loss: 0.9122 - val_accuracy: 0.8642\n",
            "Epoch 30/100\n",
            "8/8 [==============================] - 3s 379ms/step - loss: 0.0157 - accuracy: 1.0000 - val_loss: 0.8643 - val_accuracy: 0.8642\n",
            "Epoch 31/100\n",
            "8/8 [==============================] - 3s 383ms/step - loss: 0.0145 - accuracy: 0.9972 - val_loss: 0.7903 - val_accuracy: 0.8765\n",
            "Epoch 32/100\n",
            "8/8 [==============================] - 3s 383ms/step - loss: 0.0146 - accuracy: 0.9959 - val_loss: 0.8005 - val_accuracy: 0.8519\n",
            "Epoch 33/100\n",
            "8/8 [==============================] - 3s 380ms/step - loss: 0.0142 - accuracy: 0.9972 - val_loss: 0.9095 - val_accuracy: 0.8395\n",
            "Epoch 34/100\n",
            "8/8 [==============================] - 3s 382ms/step - loss: 0.0199 - accuracy: 0.9945 - val_loss: 0.9223 - val_accuracy: 0.8642\n",
            "Epoch 35/100\n",
            "8/8 [==============================] - 3s 378ms/step - loss: 0.0258 - accuracy: 0.9903 - val_loss: 0.9137 - val_accuracy: 0.8642\n",
            "Epoch 36/100\n",
            "8/8 [==============================] - 3s 383ms/step - loss: 0.0178 - accuracy: 0.9945 - val_loss: 0.8236 - val_accuracy: 0.8765\n",
            "Epoch 37/100\n",
            "8/8 [==============================] - 3s 383ms/step - loss: 0.0119 - accuracy: 0.9972 - val_loss: 0.9343 - val_accuracy: 0.8765\n",
            "Epoch 38/100\n",
            "8/8 [==============================] - 3s 381ms/step - loss: 0.0106 - accuracy: 0.9986 - val_loss: 0.9537 - val_accuracy: 0.8765\n",
            "Epoch 39/100\n",
            "1/8 [==>...........................] - ETA: 2s - loss: 0.0052 - accuracy: 1.0000"
          ],
          "name": "stdout"
        },
        {
          "output_type": "error",
          "ename": "KeyboardInterrupt",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-18-4186720757cf>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     13\u001b[0m                       \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mEPOCHS\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     14\u001b[0m                       \u001b[0mvalidation_split\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m                       verbose=1)\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m   1181\u001b[0m                 _r=1):\n\u001b[1;32m   1182\u001b[0m               \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_train_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1183\u001b[0;31m               \u001b[0mtmp_logs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1184\u001b[0m               \u001b[0;32mif\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshould_sync\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1185\u001b[0m                 \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masync_wait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    887\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    888\u001b[0m       \u001b[0;32mwith\u001b[0m \u001b[0mOptionalXlaContext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_jit_compile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 889\u001b[0;31m         \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    890\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    891\u001b[0m       \u001b[0mnew_tracing_count\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexperimental_get_tracing_count\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m    915\u001b[0m       \u001b[0;31m# In this case we have created variables on the first call, so we run the\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    916\u001b[0m       \u001b[0;31m# defunned version which is guaranteed to never create variables.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 917\u001b[0;31m       \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateless_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# pylint: disable=not-callable\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    918\u001b[0m     \u001b[0;32melif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stateful_fn\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    919\u001b[0m       \u001b[0;31m# Release the lock early so that multiple threads can perform the call\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   3022\u001b[0m        filtered_flat_args) = self._maybe_define_function(args, kwargs)\n\u001b[1;32m   3023\u001b[0m     return graph_function._call_flat(\n\u001b[0;32m-> 3024\u001b[0;31m         filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access\n\u001b[0m\u001b[1;32m   3025\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3026\u001b[0m   \u001b[0;34m@\u001b[0m\u001b[0mproperty\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_call_flat\u001b[0;34m(self, args, captured_inputs, cancellation_manager)\u001b[0m\n\u001b[1;32m   1959\u001b[0m       \u001b[0;31m# No tape is watching; skip to running the function.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1960\u001b[0m       return self._build_call_outputs(self._inference_function.call(\n\u001b[0;32m-> 1961\u001b[0;31m           ctx, args, cancellation_manager=cancellation_manager))\n\u001b[0m\u001b[1;32m   1962\u001b[0m     forward_backward = self._select_forward_and_backward_functions(\n\u001b[1;32m   1963\u001b[0m         \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36mcall\u001b[0;34m(self, ctx, args, cancellation_manager)\u001b[0m\n\u001b[1;32m    594\u001b[0m               \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    595\u001b[0m               \u001b[0mattrs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattrs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 596\u001b[0;31m               ctx=ctx)\n\u001b[0m\u001b[1;32m    597\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    598\u001b[0m           outputs = execute.execute_with_cancellation(\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py\u001b[0m in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m     58\u001b[0m     \u001b[0mctx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     59\u001b[0m     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,\n\u001b[0;32m---> 60\u001b[0;31m                                         inputs, attrs, num_outputs)\n\u001b[0m\u001b[1;32m     61\u001b[0m   \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     62\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mname\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3qO_taXiGqWG",
        "outputId": "66e5bf4d-525b-43dc-8515-e69da4d8b899"
      },
      "source": [
        "print(history.history.keys())\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "dict_keys(['loss', 'accuracy', 'val_loss', 'val_accuracy'])\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 571
        },
        "id": "RQapulbtF0Y2",
        "outputId": "701a2505-3b6d-4ffc-aec6-678aaec40764"
      },
      "source": [
        "plt.plot(history.history['accuracy'])\n",
        "plt.plot(history.history['val_accuracy'])\n",
        "plt.title('model accuracy')\n",
        "plt.ylabel('accuracy')\n",
        "plt.xlabel('epoch')\n",
        "plt.legend(['train', 'validation'], loc='upper left')\n",
        "plt.show()\n",
        "# \"Loss\"\n",
        "plt.plot(history.history['loss'])\n",
        "plt.plot(history.history['val_loss'])\n",
        "plt.title('model loss')\n",
        "plt.ylabel('loss')\n",
        "plt.xlabel('epoch')\n",
        "plt.legend(['train', 'validation'], loc='upper left')\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAwoAAAIqCAYAAACE472jAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAWJQAAFiUBSVIk8AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdeXwV1f3/8de52feVEPawB1DZrAqoIFgXqPvW1qLU9tva2lZtba2tVmhd++vXb63dqwWs1VqxirjgguCGVgUUBcIe1kDISsie3PP7Y+bebDchQJKbm7yfj8c8JnPmzMxnLgHmc88yxlqLiIiIiIhIY55gByAiIiIiIt2PEgUREREREWlBiYKIiIiIiLSgREFERERERFpQoiAiIiIiIi0oURARERERkRaUKIiIiIiISAtKFEREREREpAUlCiIiIiIi0oISBRERERERaUGJgoiIiIiItKBEQUREREREWlCiICIiIiIiLShREBHpoYwx1l2yOvCcq9xzzuuoc4qISPekREFERERERFpQoiAiIiIiIi0oURARERERkRaUKIiIiIiISAtKFERE2mCMyXUH784wxvQzxvzZGLPHGFNpjNlkjLnVGONpVP8qY8w7xpgSY8xhY8xLxpiTjnKNicaYJ9zzVhtjCowxrxpjrjjKcR5jzPeNMZ+68Rwyxiwzxkxp5731Mcbcb4z5zBhzxBhTboz53BhzrzEmtX2fUPsYY6Lcz+ZxN94CY0yVMWaXMeafxpjJ7TjHGPfz32KMqXA/48+MMb9r7XhjTJoxZoExZo1bv8I9/l/GmEub1Z3v/lkvaiOGRW6d+c3KZ7jlue72hcaYV4wx+cYYrzHmlkZ1zzbGPGyM+a8xZr8xpsatt9wYc2U7Pod23ZMx5u9uTEuOcr4Fbr3VR7u2iPQy1lotWrRo0dLKAuQCFvg6kOf+XArUuT9b4BG37gPudh1wuNH+YmBkK+f/FlDfrG7jc/8DCAtwXDjwfKN6te6xvp8vb7QvK8DxZwKFjepUA5WNtncDowMct8rdP+8YP8cvNTq3Fyhqdr1aYG4bx3+/2edypNH9WmBVgGPOAgqa3WNh4/M0qz/fLV/URhyL3Drzm5XPcMtzgR81uk/fn+ctbr34RvFY9/ektFnZX9q4frvvCZjaqE5aK+fz0PA7/s1g/33TokVL91rUoiAi0j7/B+wExltrk4BE4C53303GmJ8BPwRuAZKstYnAycBmIBm4t/kJjTFTgT/hPKwtAQZZa1Pc+nfiPLx9DbgjQDy3A5fgPIz+2L1mCjAMeAP4e2s3YowZAiwDUt3rjwRigDg35teAQcB/jDFh7fhs2uMI8DvgbCDeWptqrY0BhgC/xUl8/mqMGRwg3qvcY8NwPqex1tp4937TcD6jNc2OGQ686O7/BJgJxFpr04AE4DzgPx10b431BR4E/gj0c2OMd+MG589rCXAZzsN7ovv7lAJ8D+dz+pZ7z00c6z1Za1cDG4FI4NpW4p2J82dQDjx9/LctIj1SsDMVLVq0aOnOCw3fthYByQH2r6Dh291fBNh/lruvCohs5dh3CdxqcJ+7vwxIbFQeR0OLxfwAx0UBGxrFldVs/xNu+f2t3HMk8Klb58pm+1ZxHC0K7ficH3PPe3ez8ghgr7vvyWM437/dYzYDCe08Zj4n3qJwTHEGOP9c9xwrO+iebnWPWdfK/iePds9atGjpvYtaFERE2ufP1tqSAOVvuOsa4KEA+9/DSRKigBG+QncMwDnu5v3W2voAxz7oHhsPzG5Ufh7ON8jVOC0dTVhrq4HfBLoJY0wscBXON9uB4sVaW0PDN+BfDFSnEyxz19Oalc8CBuB0z/pxe05kjInH+cYenOStrEMibL//dwLH+j6HMxq35pzAPT2O87s5wRgzsfEOY0xyo3O22gIlIr2XEgURkfb5rJXyfHeda6090nyntdaL06ccnO4lPhMBg/Nt7luBTmytLaWhS82kRrt8P3/i1gkk4DmByTgtBgb4zBhzINAC3ObWH9TKeY6ZMSbVGHOXMWa1MabQGFPnDqK1wHNutf7NDjvDXX9qrd3XzkuditOVyQLLTzzyY1KJ0xrTKmNMuDHmG+7g5Tx3ALvvcyh2q0XT9PfluO7JWluIM5YFnHE2jX3Fvc5Wa+3b7T2niPQe4cEOQEQkROS1Ul5/lP2N60Q0KuvjrksDJRiN7G1Wv/HP+9s4rrWH6n7u2uD0pz+a2HbUOSpjzFjgzWbXLKNhQHMkzoNxXLNDffV3H8PlfMeUtpFIdZZCNzkMyG0ZeBVnoLFPJXAIp5UHGuKPoyHJPJF7ehS4GviqMeY2t8UI4AZ3vfAYzycivYRaFEREgiuqi6/n+3e/1Fpr2rHM6KDrLsR52F0LXIDTxz7RWtvXWpuJ0x0KnAQmlAXqQtbYXThJQgFwPdDXWhtrrc1wP4cBjep21GfxBs5A/DTgYgB3yt5T3XgXd9B1RKSHUaIgIhIch9x1jDGmTxv1Bjar3/jn5t10Gmtt30F3nWiMSWo7xI7hzmR0Gs5D6cXW2lcDtKK01rrhi3fIMVzSd0zSMd5jnbuObqPOiX5mvoTo+9bax621+c32H+1zONZ7wlpraRiD4Ot+5GtNeNVa21bLlIj0YkoURESCYx1OlxtoGNTchPtA6HuR2NpGu3w/TzDGJLZy/umtlH+M80BscL7Z7wr+ZKeNcQbntlL+gbs+xRgzoJU6zTW+xwvbeQyAb7D6wEA7jTGGhj+P4+U797pW9rf2ORzvPfksxEnUznenx/2aW65BzCLSKiUKIiJBYK0tAla6m7ebRm93buR2nG+3jwAvNyp/DWd61Cjg5uYHGWMicV76Fei6ZcCz7uYvjTEJrcXoDrqNP8qttIevT31fY0xGgOucDHy1lWNX4Iy3CKOdswm5rRW+wdEL2rrHZnwD1r9gjOkXYP+1nPjgbt9ncXLzHe5n/fNAB53APfmO3we8gvM5/hNnnMsh4IVjOY+I9C5KFEREgucunAGsk4B/GWMGgvPA6L7A7aduvQestYd9B1lry4Ffu5t3G2N+aIyJcY/NwnmgbOuB9qc474UYBaw2xlxgjIlwjzfGmJHGmB8COTj92E/UJpxB2QZ42hgzwr1WhDHmcuB1nGSoBWttLQ1Jz1eMMf82xmT79rszKf2PMeZ3zQ79Gc5g6VHA28aYc3zJmDEmxhgzxxjzcrNj3sMZIB4JPGWMGerWjzXGfBv4Gw2zEh2v1931Q8aY6W4rBcaYL+AkRWltHHs899TYo+7aNwXtE+7nKyISWLBf5KBFixYt3Xmh4YVrM1rZP8/dv+p4zgF8G6dLiMVJGopwupj4Xt71BIFfxhaOM+2lr14tzkOs7+fLG+3LCnD8F3C+qffVqcEZYFvdqMwC05sdt4rjeOEaznz99Y3Oe7jRtXbhdIWxONPMBjr+h82OL2t0vwE/f5wuXY3rVLn36P982xFnqft5WpyXwi2i7ReuBYy/Ub1hON/k+85fiZMkWaAC5x0Zbf25HfM9Nfud2d/o2JOC/fdLixYt3XtRi4KISBBZa/+C89D+JM4Uq/E4D6evA1dZa79mA7yMzVpbB1wB/ABYj/OgWA+8hPNw/5+jXPcjIBune9NqnIfVZJyH1Y+B37nnae19DMfEWvscMNO9rzKcqWJ34bwYbiIN08C2dvxDbr2FOIlXBM7D7nrgYZw3EDc/ZiUwGufFdZ/jfEbRwHbgKdwZgALEeR5Ot7AynK46nwDfsNZ+45huOvB97MAZ2P0Ezjs4wnDGRvwT+IK19rWjHH/M99To2DoaXuj2kbX28xO6GRHp8Yy19ui1REREJOQZY7YAI4HvWGv/HOx4RKR7U6IgIiLSCxhjZuG8U6Ec6G8bjXsREQlEXY9ERER6OGNMOg2zRv1dSYKItIdaFERERHooY8xvgKuBTJxxHQXAONvyRW8iIi2oRUFERKTnSseZKrcS5/0bM5UkiEh7qUVBRERERERaUIuCiIiIiIi0oERBRERERERaUKIgIiIiIiItKFEQEREREZEWlCiIiIiIiEgL4cEOoKcyxuwEEoHcIIciIiIiIj1bFnDYWju0I0+qRKHzJMbExKSOGTMmNdiBiIiIiEjPtWnTJiorKzv8vEoUOk/umDFjUtesWRPsOERERESkB5s8eTJr167N7ejzaoyCiIiIiIi0oERBRERERERaUKIgIiIiIiItKFEQEREREZEWlCiIiIiIiEgLIZcoGGOuNMY8Yox5xxhz2BhjjTFPHOe5Bhpj/m6M2W+MqTbG5BpjfmuMSenouEVEREREQkkoTo96JzAeOALsBbKP5yTGmOHAaiADWArkAKcBNwMXGGOmWWsLOyRiEREREZEQE4qJwq04CcI2YDqw8jjP80ecJOEH1tpHfIXGmIfca9wL3HhiobaP1+ulqKiIsrIyqqursdZ2xWVFjsoYQ1RUFAkJCaSmpuLxhFwjpIiIiBynkPtf31q70lq71Z7A07TbmnAekAv8odnuu4FyYK4xJu64A20nr9fLnj17OHToEFVVVUoSpFux1lJVVcWhQ4fYs2cPXq832CGJiIhIFwnFFoWOcI67fs1a2+TJx1pbZox5DyeROANY0ZmBFBUVUVFRQXh4OJmZmcTFxelbW+k2vF4v5eXlHDhwgIqKCoqKikhPTw92WCIiItIFemuiMNpdb2ll/1acRGEUR0kUjDFrWtnVrrETZWVlAGRmZpKQkNCeQ0S6jMfj8f9e7t27l7KyMiUKIiIivURv/eo6yV2XtrLfV57c2YFUV1cDEBfX6b2cRI6b7/fT9/sqIiIiPV9vbVHoMNbayYHK3ZaGSe04HkDdjaRbM8YAaAyNiIhIL9Jbn059LQZJrez3lZd0QSwi3Z4vURAREZHeo7cmCpvd9ahW9o90162NYRARERER6dF6a6Lge/fCecaYJp+BMSYBmAZUAB90dWAiIiIi0rGsteo+exx69BgFY0wEMByotdZu95Vba7cbY17DmdnoJuCRRoctAOKAv1hry7syXula8+fPZ8GCBaxcuZIZM2YEOxwREZF2q633cqSqLthhdAgL1NR5qaytp6q23r92Fi+VNfVU1dVTWVNPdZ277a/n9ddtON5LdW2zOnX1eIwhOSaC5NgIUmIjSY6NJCXW2XZ+9m1HkhLnqxNBVHhYsD+ioAm5RMEYcylwqbuZ6a6nGGMWuT8XWGtvc38eAGwCdgFZzU71XWA18DtjzCy33uk471jYAvy8M+KX1uXm5jJ06FCuv/56Fi1aFOxwRES6varaeuq9lriokPvvXI5DRU0dK3MO8fJnebyZk09lbX2wQwop9dZSWF5DYXkNzrt12yc2MsyfNDQkFU2TDd/+FDfhSIwJ7xHj+0LxX5YJwPXNyoa5CzhJwW0chduqcCrwS+ACYDaQBzwMLLDWFndYxNItfe973+PLX/4ygwcPDnYoIiLtUlPnZd3uYlZvL+T97YWs21NMbb3ljGGpXDFpIBee3I94JQ09ipKD4KuoqaeippJ9JZXtPmbbvRcSHqZEoctZa+cD89tZNxdo9U/JWrsH+HpHxCWhJz09XS8PE5Furd5r+XxfKau3F7J6ewEf5RZRVettUe+DHUV8sKOIXyzdwAUnZXLFpIFMGZ5GmCc0HlS8XkvOgTIqa+v8XUCSYiJCJv6O5ksOXvpsPytzDrWaHCREh/eYzygyzENMZBjR4WFER4YRHd6wHRMZRnSEh+iIMKIjwoiJcLZjIsKI8m83lPvrNTpPVHgY9V5LSUUNJZW1FJfXUFxRS0lF43XLspKKWuq8xza2ITE6nPCwnjEMOOQSBemZfOMFABYvXszixYv9+xYuXEhWVhbnnHMOd999N7Nnz2bBggW8//77FBcXs3PnTrKysli5ciVPPfUU7777Lnv37qW2tpbhw4dz1VVXcfvttxMdHR3wms3HKBhjmD59OkuWLOFnP/sZy5Yto6ioiBEjRnDbbbfx9a8rtxSRzmGtZWv+Ed7bVsDq7YV8sKOQsqP0QzcGfGM0K2vreW7dPp5bt49+SdFcOnEAV0wayIiM+C6I/tiUVdXy7tYCVuTks2pzPgVHaprsNwYSoyMa+ow371ceF7jLR0xkaPYnr6ip482cfH/LQaCEEGBkRjyzT+7HnFP6MapvQhdHGdrCPIaMxGgyEqOPXtllraWsuo6S8lqK3SSjpKKmRaJR7CYVxRU1JEZHdOJddC0lCtItzJgxg5KSEh5++GHGjx/PpZde6t83YcIESkqcV1q8//773H///Zx55pnccMMNFBQUEBkZCcCDDz5ITk4OU6dOZc6cOVRVVfHee+8xf/58Vq1axRtvvEFYWPv+AykpKWHatGlERkZy5ZVXUl1dzTPPPMMNN9yAx+Ph+uub934TETl21lr2FFXy3vYCtztRQYsH5uaGpMUydXgaU4anM2VYGl5reX7dPp5du5ctB4/46+WVVvGnVdv506rtjB+UzBWTBnDRKf1JiYvs7NtqVW5BOSty8lmZk89/dxZSW9/6N7XWQmllLaWVtVBY0e5rRIV7miYPcU0TjbT4SIakxTEsPY7k2OB9FtCQHLy0Po+Vm5UcdEfGGBKjI0iMjmBwWmyww+lyShSkW5gxYwZZWVk8/PDDTJgwgfnz5zfZv2rVKgBee+01/vznP/Ptb3+7xTn++Mc/MnTo0BaDh+666y7uuecelixZwjXXXNOueD799FO+8Y1v8Je//MWfXNxyyy2ccsopPPjgg0oUROS4HTxcxfvbC/2tBkfr95yREMW0EelMGZ7G1OFpDExp+bDy7enD+dbZw9iw/zBL1uzlhU/3U1TekHB8uqeET/eU8KsXNzIruy+XTxrAOdkZRHRy94jaei8f5RaxMiefFTn57DjU+gDStLhIBqbE+LuFHD7OGX2q67wcOFzFgcNVR62bEhvB0PQ4hqbHM6xPHEPT48hKiyMrPZbYyM55RCqvbmg5OFpyMOeUfsw5uR8jlRxIkChR6OayfvpSsENot9wH5nT6NSZMmBAwSQAYNmxYwPJbb72Ve+65h1dffbXdiUJsbCwPPfRQkxaIsWPHMm3aNN5++22OHDlCfHz3a8oXCTU1dV4Oug91+0sqOVBaRXiYh/EDkzhpQBLREaHZjaSxkooaPthRyGo3OdjexsMyQHJsBFOGOUnB1BHpDEuPa9fsKcYYThrgfG4/mz2Gt7Yc4tk1e1mRc9D/zX1tvWX5hgMs33CA1LhILh7fnysnD2Rc/8QOm6Gl8Eg1qzYf4s3N+by9+RBl1a0/8I/rn8is7AxmjunLKQOS8DTqb19X76W0sjZA945GXT7Km3b5KKmopaY+8IN3IMUVtRTvLmHt7pIW+/olRbtJhLMM6+MkEYNSY485wWpvcjCqr9tyoORAugklChJSTjvttFb3lZeX8/DDD/Pcc8+xZcsWysrKmrxcZd++fe2+zsiRI0lMTGxRPmjQIACKi4uVKIgchS8JyCutIq/USQJ8P+e5Pxccqaa1dyBFhBnG9ktk4uAUJg1JYdLgZAYkx3TrKQdr673sOFTOxrxSNuw7zPs7CtmYd7jVewSIiwzjtKGpTB3utBqM7ZfY5IH5eESGe/ji2L58cWxfistreHH9fpas3cenexoeiIvKa1i0OpdFq3MZ1TeeKyYN5NKJA+h7DP23wek+lXOgjDdz8lmx6SDr9pS0er/RER7OHNGHWWMyOGd0BplJrV8rPMxDWnwUafFRxxRLRU19k+SheVJx8HAVOwvKyS0sb/WBHfD/jq7eXtikPMxjGJwa2zSJSI8jKz2OzMRo/59deXUdK3LyedntVlRdp+RAQo8SBQkpmZmZActra2uZOXMmH374ISeddBLXXHMNffr0ISLCGVC0YMECqqur232d5OTkgOXh4c5fmfp6TU8nvVvzJCCvtIoDpW6rwOGjJwHtUVtv+XRvKZ/uLWXR6lzA6YYzaXAKEwcnM2lICicHsdWhtKKWjXmH2eQuG/MOs/XgkaN+ox0Z5mHykBS3xSCNUwYmd2oXoJS4SOZOyWLulCy25Zfx7Np9PLd2X5OuOVsOHuH+V3J4cHkOZ47swxWTBnDe2MxWBwZX1dazensBKzbl82ZOPnmlrXfzGZAc4yQG2RlMGZbWqX9exhjiosKJiwpnYErbdb1eywE3aWi+7C6qoL6VmW7qvdZfr7noCA9ZaXGkx0fxUW5Rm8nBnJP7M+eUTEZkKDmQ7kuJQjfXFd15Qklr3yQuXbqUDz/8kHnz5rFw4cIm+/Ly8vwzKolI+1lr2VtcyYb9zoPw5gNl7C+tZH+JkwR0BGOgT3wU/ZJj6JcYTWZSNGVVdazbXcyOAA9i+WXV/q4zAOEew7j+TqvDxMHJTBqcwsCUjm118Hotu4sqmiQEm/LK2j2nepjHcMrAJCcxGJ7O5CEpQUtuRmQkcPsF2dx23mje317Is2v3svzzA/7pN70W3t5yiLe3HCIhKpzZJ/fjiskD+UJWCnmlVbyZ4yQGq7cXtPptvMfApMEpzByTwazsvozqG98tW4E8HkP/5Bj6J8cwbUTTqbJr673sKaogt7CcHYeaJhFtJUVVtV5yDpQBZS32je6b4A5IVnIgoUOJgnQbvvEAx/Nt/bZt2wC4/PLLW+x76623TiwwkV6gqraeLQfL2Ljf9w15GZvyDrfZv/xojHFaADKTYuif5CQB/ZKi6ZcU46yTY8hIiGr12/Ti8ho+2VPC2t3FrN1dzCe7SyivafrvQ523cauDU9YnIYpJbtIwcXAKpwxsf6tDZU09OQec+9+YV8qmvDJy8g63uG5bBiTHMKZfAmP6JTJ+YDKnDUvtdtMlhnkMZ45M58yR6fzq0jpe+SyPZ9fu5YMdRf46ZdV1PP3xHp7+eA8psREUV9S2er7E6HCmj85gVnYG00f1CerMSh0hIszDsD7xDOsTz8zspvsqaurILXCSiJ0FvkTiCDsLylt8RkoOJNQpUZBuIyUlBWMMu3fvPuZjs7KyAGd2pIsuushfvmPHDm6//faOClGkR8gvq3ITgjL/N+Q7Dh3hWN4p5DGQkRDo4d/ZzkxqOwloj5S4SM7JdrqsgNPlY2t+GWt3NSQPgWbROVRWzasbDvLqhoOA0+owtn9iQ5clt9Xh4OFq//37uhDtLChvd3epyDAPI/vGM7ZfImP8S0LQp9w8VvFR4Vx16iCuOnUQe4sreG6tM9VqbqMpSQMlCSMy4pnl/vlMHpLS6TModRexkeGM7Z/I2P4tx7GVVNSws6CcA6VVjOwbr+RAQp4SBek24uPjOf3003nnnXe49tprGTVqFGFhYVx88cVHPfaiiy5ixIgRPPTQQ3z22WdMnDiR3bt38+KLLzJnzpzjSj5EQp1vYG3TLjOHjzpPf2MpsRGNHoITGZoeS7+kGPqcYBJwPMI8huzMRLIzE/nq6YMB58Fs3e4S1u0uZu3uEj7ZU8KRZq0gdV7L+r2lrG/U6hAd4WlzIGtzaXGRjO3fkAyM7ZfEsD5xPe7heGBKLN+fNZLvzRzB2t3FPLt2H8s+3U9ZVR2RYR5OH5bKzOwMZmZnMCQtLtjhdjvJsZFMHBxaiaJIW5QoSLfyj3/8g1tvvZXly5fz1FNPYa1l4MCB/haD1sTFxfHmm2/y05/+lFWrVvHOO+8wbNgw7rrrLn74wx/y9NNPd80NiARJaWWtPyHwJQVbDh6hppXBlM0ZA0PT4hjTL9F9IHa6zmQmRnfL/uU+ybGBWx3W7S5h7S6n1SHQdKRt9a8f1ie+UUKQyNh+ifRJiOrWn0NHM8YweUgqk4ek8osvjWVXYQUDUmKIj9Jjg0hvYuyJTEkhrTLGrJk0adKkNWvWtFlv06ZNAIwZM6YrwhI5bvpd7V6cufmLWO2+0Xdb/pGjH+SKjQwjOzOh0TfkiWRnJnTaC6aCraSihnV7Sli3q5h1e0r4ZHcJZdV1xEeF+xMiX/ehUX0TWp3pR0Sku5o8eTJr165da62d3JHn7Zn/K4iI9DDl1XV8lFvE6u2FrN5ewIb9bc/N79M/KbpJQjC2XyKDU2NPeJ7+UJIcG8k5o515+8FpdSipqCElNrJXfQ4iIsdKiYKISDdUXVfPut0lrN7mtBh8sqeEujZGG0eEGUZmNLQSjA3RgbVdIcxjjuklXiIivZUSBRHplapq68k5UEZcZBiZSdEkBHn6yrp6L5/vP+x0JdpW2ObLmsDpS3/KwGSmjQj+3PwiItIzKVEQkV7jQKMXRr23rcD/kilwpojs58713z8pxlknO9N89nOnAO3IZMLrtWzJL2P1tkJWby/kvzsKj/rOguzMBKYOT2faiDS+MLT7zc0vIiI9ixIFEemxvF7L+n2lvLnpICty8tmw/3CrdY9U17E1/whb2xgUHCiZ8L047GjJhLWWXYUV/jEG728vpLC87WlKh6bHMWV4GlOHpzFlWJq6y4iISJdSoiAiPUpZVS3vbi1gRU4+qzbnt/nOgMGpsXgM5JVWtdnNx6e9yUTDS8icFon9JZW8v72QfSWVbZ4/MzGaqW5XoqnD0+ifHHPUmERERDqLEgURCXm5BeWsyMnnzZyDfLiziNr6wIN+wz3GfWFUX2ZmZzA03XlhlLWW4opa8korySupIu9wFQd8P5dWOeXHkExsyz/SrulKU2IjmDo8nSnD05g2Ip2stNheNVe/iIh0b0oURCTk1NZ7+Si3iJU5+azIyWdHgBdq+aTFOS/kmpWdwZkj0wN2DTLGkBoXSWpcJOP6JwU8j7WWkopa9pdWcqC0iv2lbjJRWkVeSRUHDlexv6SyzWQiPiqc04emut2J0snOTND0nCIi0m0pURCRkFBUXsOqzU5i8PaWQ5RVtT7wd1z/RGa5b+sdPzC5Qx7GjTGkxEWS0o5konErxIHSKmKjwjhjWBqnDEgiPMxzwrGIiIh0BSUKItItWWvJOVDGmzn5rNh0kHV7Slp9wVh0hIczR/RhZnYG52T3oV9ScPr2N04mxvZPDEoMIiIiHUWJgoh0K2VVtfxp1XaeX7eP/aVVrdYbkBzDzOwMZo7JYMqwNL1DQEREpIMpURCRbsFay3Pr9nH/KzkcKqtusd9jYNLgFGaOyWBWdl9G9Y3XwF8REZFOpERBRILu832l3FR6LKwAACAASURBVP3CBtbsKm5SnhgdzvTRzkDk6aP6kBIXGaQIRUREeh+NqpNeIysri6ysrCZlixYtwhjDokWL2n2eefPmYYwhNze3Q+NrLlC8PU1xeQ0/f+4zLvr9u02ShIyEKP7vmvGsueuLPPKViVw6cYCSBBERkS6mFgWRIJkxYwZvvfUWtrURuj1Yvdfy1Ie7+c1rmympqPWXR4QZbjhzKN+fOZL4KP3zJCIiEkz6n1h6tcsuu4wzzjiDfv36BTuUFlasWBHsEDrFml1F/GLpBjbsP9yk/KyR6cy/eBzD+8QHKTIRERFpTImC9GpJSUkkJQWeEz/Yhg8fHuwQOlR+WRUPvJLDf9bua1I+MCWGu740lvPG9tXgZBERkW5EYxSkW/jggw8wxnDZZZe1WmfMmDFERUVRVFRETU0Nv//975k9ezZDhgwhKiqK1NRUzj33XF555ZV2X7etMQpvvPEGZ511FnFxcaSmpnLppZeSk5PT5rmuuOIKhg0bRkxMDImJiUybNo0nnniiSb3c3FyMMbz11luAM/e+b5kxY4a/XmtjFKqrq3nggQc4+eSTiY2NJTExkbPOOot///vfLer6rjVv3jxyc3P58pe/THp6OtHR0Zx66qm8+OKL7fugTkBtvZdH39nBzN+81SRJiAr3cOu5o3jjh9M5f1ymkgQREZFuRi0K0i2cccYZjB49mpdffpnCwkLS0tKa7P/www/JycnhiiuuIDU1lQMHDnDzzTczdepUvvjFL9KnTx/y8vJYtmwZs2fP5m9/+xvf/OY3jzueJUuWcM011xAZGck111xDv379ePfdd5kyZQqnnHJKwGO+853vMG7cOM4++2z69etHYWEhL7/8MnPnzmXz5s386le/AiA5OZm7776bRYsWsWvXLu6++27/OY42eLmmpobzzz+ft956i+zsbG666SYqKir88X7yySfcd999LY7btWsXp512GsOGDWPu3LkUFRXx9NNPc8kll/DGG29wzjnnHPdn1Zb3thVw9wsb2JZ/pEn5BeMy+fmcMQxKje2U64qIiEgHsNZq6YQFWDNp0iR7NBs3brQbN248ar3e4L777rOAfeSRR1rs++53v2sB+8ILL1hrra2qqrJ79uxpUa+kpMSOGzfOpqSk2IqKiib7hgwZYocMGdKkbOHChRawCxcu9JeVlZXZ1NRUGx4ebj/66KMm9W+55RYLWMDu3Lmzyb5t27a1iKe6utrOnDnThoeH27179zbZN336dOv8FQwsULy+z+jCCy+0tbW1/vKDBw/aIUOGWMC+9957/vKdO3f6450/f36Tcy1fvtx/rvY4lt/VvcUV9jtPfGyH3P5ik2Xmb1bat7fkt+scIiIi0j6TJk2ywBrbwc+zalHo7uZ3z/7zAc0vPaHD586dy5133snixYv53ve+5y+vqanhX//6FxkZGVx44YUAREVFMXDgwBbnSEpK4oYbbuBHP/oRH330EWefffYxx7F06VKKioq47rrrOPXUU5vsmz9/PgsXLqS0tOW9BhpTEBkZyU033cSbb77JihUruO666445nsb+/ve/Y4zhoYceIjy84a9vRkYGd911F9/85jd59NFHmTp1apPjhgwZwp133tmk7Pzzz2fw4MF8+OGHJxRTY1W19fzt7R38YdU2qmq9/vK4yDBuPnck86YOJTJcPR5FRERCgf7Hlm5j4MCBzJo1i48//piNGzf6y5ctW0ZRURHXXnttk4fjDRs2MG/ePP+YAF8//x/96EcA7Nu3r8U12mPt2rUATJ8+vcW+pKQkJkyYEPC43bt3c9NNN5GdnU1sbKw/niuuuOKE4vEpKytj27Zt9O/fn+zs7Bb7Z86cCcC6deta7JswYQJhYWEtygcNGkRxcXGL8mNlreWNjQc57//e5n9f39IkSbhs4gBW3jaDb509XEmCiIhICFGLgnQr8+bN4/XXX2fx4sU8+OCDACxevBiA66+/3l/vgw8+YObMmdTV1TFr1iwuvvhiEhMT8Xg8fPLJJyxdupTq6urjisHXWtC3b9+A+zMzM1uU7dixg9NOO43i4mLOOusszjvvPJKSkggLCyM3N5fFixcfdzzN42ptKldfeUlJSYt9ycnJAY8JDw/H6/UG3NdeOwvKWbBsA6s2H2pSPrZfIgsuGccXslJP6PwiIiISHEoUursT7M4Tai677DISExN54oknuO+++ygsLOSVV15h/PjxjB8/3l/vnnvuobKykpUrVzaZKQjg/vvvZ+nSpccdg2+61IMHDwbcf+DAgRZlDz30EIWFhSxcuJB58+Y12ffUU0/5k50T4Ysr0PUB8vLymtTrbOXVdfx+5TYee2cnNfUNyUZSTAS3nT+ar542mDCPZjISEREJVeoHIN1KTEwMV199Nfv37+eNN97gySefpK6urklrAsC2bdtITU1tkSQA/mlHj9ekSZNaPU9paSmffPJJi/Jt27YB+LsZtSceX1eg+vr6dsWVkJDA8OHD2bdvH1u3bm2xf+XKlU3i7yzWWl74dD+z/vct/rRquz9JMAa+evpgVt42g7lnDFGSICIiEuKUKEi34/tG/vHHH+fxxx8nPDyca6+9tkmdrKwsioqKWL9+fZPyxx57jFdfffWErn/JJZeQkpLCk08+yccff9xk3/z58wMOZPZNa7pq1aom5a+++iqPPvpowOv4poDdvXt3u2O74YYbsNby4x//uEmCUVBQ4J9+9YYbbmj3+Rqz1lLvtdTU1VNRU0dZVS0lFTUUHKnm4OEqauu97Cmq4OLfv8cPnlrHgcNV/mMnDU7mhZvO5L7LTiY1LvK4ri8iIiLdi7oeSbczbdo0RowYwTPPPENtbS0XXXQRGRkZTerccsstvPrqq5x55plcffXVJCUl8fHHH/Puu+9y5ZVXsmTJkuO+fnx8PH/961+55pprOOuss5q8R+Hzzz/n7LPP5u23325yzHe/+10WLlzIVVddxZVXXkn//v35/PPPWb58OVdffTVPP/10i+vMmjWLZ555hssvv5zZs2cTExPDkCFDmDt3bqux3XbbbbzyyissXbqU8ePHM3v2bCoqKnjmmWfIz8/nJz/5CWeeeSbWWuq8lupaJ5moqfdSVF5DvddLnddJCOq9lkp3/8a8w9R7/VP7BlRXbymuqOWzfQ2JUnp8FHdcmM1lEwfgUQuCiIhIj6IWBemWrr/+empra/0/N3fBBRewbNkyxo4dy9NPP81jjz1GVFQUK1euZM6cOSd8/SuvvJLly5czefJk/v3vf/PnP/+Z1NRU3n//fYYOHdqi/imnnMLKlSuZOnUqL730En/60584fPgw//nPf7jxxhsDXuOb3/wmd9xxB6Wlpfz617/mrrvu4rHHHmszrsjISF5//XXuvfdeAB555BEWL17MyJEj+fNji7jh1jvZsK+Uz/aVsinvMDsKygEor6pjb3EFeaVVHCqrpqi8htLKWrxeJzGoq/e2mSQ0F+YxfOPMobx523SumDxQSYKIiEgPZI7l4UDazxizZtKkSZPWrFnTZr1NmzYBMGbMmK4IS3qgmrp69hRVUl5Td8Ln8hhDmMdZwpusPRzas52y6joqYzMZ1z+JzKToDoheRERETtTkyZNZu3btWmvt5I48r7oeiYQoay0lFbXsL6mkPkDC7zzke5o89Af+uaFOWy0Dxfs9pMRGMnVM4GljRUREpGdRoiASgurqvewrqaS0stZfZjBkJEaRFhdJmMd52ZuIiIjI8VKiIBJiyqpq2VtcSW2jdxdEhXsYlBJLbJT+SouIiEjH0FOFSIjwei0HDldRcKTpG55T4yLplxSj9xaIiIhIh1KiIBICKmvq2VNcQVVtw7sTwj0eBqbEkBgTEcTIREREpKdSoiDSjVlrKThSw4HDVU2mL02IjmBgSgwRYZrhWERERDqHEgWRbqqmzsve4gqOVDdMe+oxhn5J0aTGRXbpYGVNoywiItL7KFEIMmMM1lq8Xi8ej74dFkdJRQ37Siqp9zY8oMdEhDEoNZboiLAuj8eXKGgmJRERkd5DiUKQRUVFUVVVRXl5OQkJCcEOR4Ks3utlf0kVxRU1/jID9EmIJiMxCk+QHtTLy503PEdFRQXl+iIiItL1lCgEWUJCAlVVVRw4cACAuLg4jNEc+L3Rkeo69hZVUNNo2tPIMA+DUmOJC8K0p9ZarLWUl5f7fz+VzIqIiPQeShSCLDU1lfLycioqKti7d2+ww5EgsDgvUKurbzoOIMxj8IYZdpd0j6QxNjaW1NTUYIchIiIiXUSJQpB5PB4GDRpEUVERZWVlVFdXa+BoL1JdW8/u4goqaxpaEcI9hgEpMSRFBn/aU2MMUVFRJCQkkJqaqnE0IiIivUhIJgrGmIHAL4ELgDQgD3geWGCtLT6G81wBfB+YCEQCO4AngP+11ta0dWxH8ng8pKenk56e3lWXlCCz1vL4+7u47+VNVNc1JAlnjkjnN1eNJzMpOojRiYiIiIRgomCMGQ6sBjKApUAOcBpwM3CBMWaatbawHee5D7gDOAI8CxQBZwH3AbOMMRdaa2s75y6kN8s/XMWPl6znrS2H/GWR4R5+ekE286Zm4dEblkVERKQbCLlEAfgjTpLwA2vtI75CY8xDwK3AvcCNbZ3AGDMJJ0koASZba3e45cY9/404LQ0PdcYNSO+1/PMD3PGf9RRXNOSg2ZkJPPzliYzO1EBhERER6T5CqsOx25pwHpAL/KHZ7ruBcmCuMSbuKKe61F0/6ksSAKwzOOBn7uZNJxywiKu8uo7bl6znxifW+JMEY+BbZw9j6femKUkQERGRbifUWhTOcdevWWu9jXdYa8uMMe/hJBJnACvaOE+mu97RfIe1ttgYUwwMM8YMtdbu7IC4pRf7745CfrxkPbuLKvxl/ZKi+d+rxjN1hMaliIiISPcUaonCaHe9pZX9W3EShVG0nSgUuOuhzXcYY5KBlEbXazNRMMasaWVXdlvHSc9XUVPHr5dvZtHq3CblF43vzz2XnERSbPBnNRIRERFpTaglCknuurSV/b7y5KOc5yWcMQr/Y4z5o7U2F/xjFO5tVC8lwLEiR/XBjkJ+0qwVISE6nF9dchKXThwQxMhERERE2ifUEoUOYa19zxjzGPANYL0xpvGsR6fgzKSUDXhbP4v/XJMDlbstDZM6LGgJCa21IszMzuC+y07WtKciIiISMkItUfC1GCS1st9XXtKOc/0P8KG7vhrnBbkfADOAO3EShfzjDVR6n9ZaEe6+aBxXTBqA02AlIiIiEhpCLVHY7K5HtbJ/pLtubQyDnzvD0V/dpQljzMk4rQlrjyNG6WXKq+v49fIcFr+/q0m5WhFEREQklIVaorDSXZ9njPE0nvnIGJMATAMqcFoGjosxZgYwGFhmrW1tLIQIAO9vL+Qnz37KnqJKf1mi24pwuVoRREREJISFVKJgrd1ujHkNZ2ajm4BHGu1eAMQBf7HWlvsKjTHZ7rE5jc9ljEm01h5uVjYEeBSowel+JBJQeXUdDy7P4fFmrQizsjO47/KT6ZuoVgQREREJbSGVKLi+C6wGfmeMmQVsAk7HecfCFuDnzepvctfNv9p9zE0M1uIMZB4KXAxEAHOttes7J3wJda21Isy/eByXTVQrgoiIiPQMIZcouK0KpwK/BC4AZgN5wMPAAmttcTtP9SLwLeAqIAE4CCwBHrDWbmrrQOmd1IogIiIivUnIJQoA1to9wNfbWTfg17vW2sXA4o6MS3qu1dsLuP3Z9WpFEBERkV4jJBMFka5SXl3HA6/k8I8PmrYinDvGmdEoQ60IIiIi0kMpURBpxertBfxkyXr2Fje0IiTFRDD/4rFcOkGtCCIiItKzKVEQaaa8uo77X9nEEx/sblJ+7pi+3HfZSWpFEBERkV5BiYJII6u3FfCTZ1u2Iiy4eByXTOivVgQRERHpNZQoiABHqut4QK0IIiIiIn5KFKTXW72tgB8vWc++ErUiiIiIiPgoUZBeK7+sigdf2cyza/c2Kf/i2L7ce9lJZCSoFUFERER6LyUK0uvU1ntZvDqX376xlSPVdf7y5FinFeHi8WpFEBEREVGiIL3Ke9sKuPuFDWzLP9Kk/MKTMllwyTi1IoiIiIi4lChIr7CvpJJ7X9rIy58daFI+vE8c8y8ex1kj+wQpMhEREZHuSYmC9GhVtfX87e0d/GHVNqpqvf7yuMgwbjl3FNdPzSIy3BPECEVERES6JyUK0iNZa1mxKZ9fvriR3UUVTfZdPnEAP70wW1OeioiIiLRBiYL0ODsLylmwbAOrNh9qUj62XyK/vGQcp2alBikyERERkdChREF6jPLqOn6/chuPvbOTmvqGbkZJMRHcdv5ovnraYMI8ms1IREREpD2UKEjIs9aybH0e9720iQOHq/zlxsBXThvMbeeNJjUuMogRioiIiIQeJQoS0nIOHObupRv4786iJuWTBifzy0tO4qQBSUGKTERERCS0KVGQkFRaWcv/vb6Ff3ywi3qv9Zenx0dxx4XZXDZxAB51MxIRERE5bkoUJKR4vZYla/by4PIcCstr/OXhHsO8qVn84NyRJEZHBDFCERERkZ5BiYKEjE/2lHD3Cxv4dE9Jk/JpI9KYf9E4RvZNCFJkIiIiIj2PEgXp9gqPVPPr5Zt5+uM9TcoHJMdw55wxXHBSJsaom5GIiIhIR1KiIN1WXb2XJz7YxUOvb+FwVZ2/PDLcw41nD+M7M0YQExkWxAhFREREei4lCtIteb2Wbyz+mLe2NH1p2rlj+vKLL41lcFpskCITERER6R2UKEi39Pwn+5okCUPT4/jFRWM5Z3RGEKMSERER6T2UKEi3U1FTx6+Xb/Zvf+W0wcy/eCxR4epmJCIiItJVPMEOQKS5v7290/+G5T4JUdw5Z4ySBBEREZEupkRBupWDh6v481vb/du3nTeKuCg1fImIiIh0NSUK0q385tXNVNbWAzCmXyJXTh4U5IhEREREeiclCtJtfL6vlCVr9/q375wzhjCP3o8gIiIiEgxKFKRbsNZyz0sbsdbZPndMBtNGpAc3KBEREZFeTImCdAuvbzzIBzuKAAj3GO6YPSbIEYmIiIj0bkoUJOhq6rzc/0qOf/trZwxheJ/4IEYkIiIiIkoUJOie+GAXOwvKAUiMDufmWSODHJGIiIiIKFGQoCqpqOHhFVv92z+YNZKUuMggRiQiIiIioERBguzhFVsprawFICstluumZAU3IBEREREBlChIEO04dIR/vL/Lv/3TC8cQGa5fSREREZHuQE9lEjT3v5JDndeZD/W0oamcP65vkCMSERERER8lChIUq7cX8PrGg/7tu+aMxRi9XE1ERESku1CiIF2u3mu558VN/u3LJw3g5IFJQYxIRERERJpToiBd7tm1e9mYdxiA6AgPPzk/O8gRiYiIiEhzShSkS5VX1/GbVzf7t7999nAyk6KDGJGIiIiIBKJEQbrUX97eQX5ZNQAZCVF8e/qwIEckIiIiIoEoUZAuk1dayV/f3u7f/vH5o4mNDA9iRCIiIiLSGiUK0mX+36ubqar1AjCufyJXTBoY5IhEREREpDVKFKRLrN9bwn/W7vNv3zlnLB6PpkMVERER6a6UKEins7bpdKjnje3LlOFpQYxIRERERI5GiYJ0ulc3HODD3CIAwj2GO2aPCXJEIiIiInI0ShSkU1XX1XP/Kzn+7eumZDE0PS6IEYmIiIhIe2jKGelU/3h/F7sKKwBIiongB7NGBDkiERGRTlBZAluWw4bnYc9/YdQFcNFvITwq2JFJ4XZYdjPsfr9rrheVCLfv7JprdTIlCtJpispreHjFVv/2zbNGkhwbGcSIREREOlBlMeS8DBuXwvY3wVvbsO/TJ6GiAK7+B0ToxaJBU7ANFn8JyvK67pre+q67VidToiCd5uE3tlBWVQfAsPQ45k4ZEuSIRERETlBFEeS8BBufhx2rwFvXet2tr8HT18I1/1SyEAyHtsDii+DIgWBHErKUKEin2JZ/hCf+u9u/fcfsMUSEaUiMiIiEoPJCyFnmtBzseAtsK98Y95sA4y6FikJY/YhTtu0N+NdX4MtPQkRM18Xc2x3a7CYJB53tiFj4yr9gyNTgxhVilChIp7j/5U3Uey0AU4alce6YjCBHJCIicgyOHHKSgw3PQ+67rScHAybD2EucJSXLKbMWIuLgrQec7e1vwlNushAZ2yXh92r5OU6SUJ7vbEfEwbXPQNa04MYVgpQoSId7d2sBK3Kcv5zGwM/njMEYvVxNRES6ubKDsOkFp+Vg13tgvYHrDfwCjL0Uxl4MyYNb7jcGzrnDWa+63ynbsRKe+rLzrbaShc5zcKOTJFQUONuR8U6SoJaE4xKSiYIxZiDwS+ACIA3IA54HFlhri4/hPGcCPwbGA5lAPvA58Dtr7fKOjrs3qPda7nlpo3/7ykkDOWlAUhAjEhERacPhPNi0zBlzsGs1YAPXG3R6Q3KQNLB9557xUzBhsPIeZ3vnW/Dk1fDVpyFSU4V3uIMb3CSh0NmOjIevPQuDzwhuXCEs5BIFY8xwYDWQASwFcoDTgJuBC4wx06y1he04z3eAPwLlwHPAXmAgcDlwoTHmTmvtvZ1zFz3XMx/vIedAGQCxkWHcdv7oIEckIiLSTOm+huRg9wcETg4MDJ7idiu6GBL7H9+1pv/YaVl481fOdu478M+r4dp/K1noSAc+g8UXQ6XzglciE9wk4fTgxhXiQi5RwHm4zwB+YK19xFdojHkIuBW4F7ixrRMYYyKA+4EqYLK1dnOjffcB64CfG2N+Y62t7vhb6JmOVNfxm9e2+LdvnD6cvoma5UFERLqB0r1Ol6KNS533HARkYMg0Z0By9pcgsV/HXPvs28ATBm/Md7Z3vQtPXOl0iYmK75hr9GZ56+Hxi53pasF5j8HX/gODvhDcuHqAkEoU3NaE84Bc4A/Ndt8NfAuYa4z5kbW2vI1TpQJJwPrGSQKAtXaTMWYLcDIQDyhRaKc/r9pOwRHn48pMjOZ/zhoW5IhERKRXK97ljDnY8Dzs+zhwHeOBrDOdloPsiyChb+fEcuatzrVe/4WzvXs1/NOXLCR0zjV7g/2fwOOXQFWJsx2VBHOfg4GTgxtXDxFSiQJwjrt+zdqmI4ystWXGmPdwEokzgBVtnCcfOASMMsaMtNb63wpmjBkFjAQ+aU8XJnHsK6nkb+/s8G//5ILRxESGBTEiERHplYp2NrQc7F8buI4Jg6FnOWMOsr8E8X26JrZpNzvXfu3nzvbu9+GJK+DaJRCd2DUx9CT717lJQqmzHZ0Ec5+HAZOCG1cPEmqJgq/D+5ZW9m/FSRRG0UaiYK21xpibgCeANcaY54D9wADgMmAD8OX2BGSMWdPKruz2HN9T/Hp5DtV1Tu528oAkLp0wIMgRiYhIr1G43U0Onoe8TwPX8YTD0Oluy8GXIC6ta2P0mfo9p2Xh1Tuc7T3/hScud/rTR2vyj3bbtwYevwyqfUlCMly3FPpPCG5cPUyoJQq+v0Glrez3lScf7UTW2meMMfuBp4DrGu06CCwEdgQ8UFpYt7uYpZ/s92/f9aWxeDyaDlVERDpRwTbY+JyTIBz4LHAdTwQMm+GMORg9G2JTuzLC1k35rpMsLL/d2d77EfzjMqdffcxRH2Fk78fO51V92NmOSXGShH7jgxtXDxRqiUKHMcZ8Dfgb8B/gV8AuYAhwF/B7YDpw9dHOY60N2AnObWno8W1f1lrueWmTf/vCkzI5bWg3+YdYRER6lkObncRgw/OQvyFwnbBIGD7TaTkYfaHzENkdnXGjM8D55duc7X1rnIffuc8pWWjLng+d7lr+JCEVrn8BMk8Oblw9VKglCr4Wg9ba5nzlJW2dxB2H8HdgPTC30XiHHGPMXJwuTlcZY2ZYa1edWMg928ufHWDNLmeWgYgww08v7FU9rkREpLPlb3ISg41L4dCmwHXComDELGfMwegLQqcLz2n/40yd+tKPnO39a50+99c9330TnGDa/V8nSahxpmEnNg2uewEyTwpuXD1YqCUKvhmKRrWyf6S7bm0Mg895QATwVoBB0V5jzNvAZHdZdXyh9nxVtfU8sLzhH+15U7MYkqY5oUVE5ARY67w4yzcguWBz4Hrh0TDiXCc5GHV+6A4G/sI3nW5IL97qbOe5s/jMfb77dJXqDna978wSVXPE2Y5Nh+uXQd+xwY2rhwu1RGGluz7PGONp/JBvjEkApgEVwAdHOU+Uu25tmgNfec3xBtobLFqdy56iSgBSYiP43syRRzlCREQ6VFUpHNwY7Cg6Rn2N8+bijUuhcFvgOuExMPKLzpiDkef1nGlFT73BSRaW3exs533qvBfguheULIDzxuwnroRad+b7uD5OkpAxJrhx9QIhlShYa7cbY17DaRG4CXik0e4FQBzwl8bvUDDGZLvH5jSq+467vtJ9qdr6RvUnAFfivKbxzU65kR6g4Eg1f3iz4R/yW84dRVJMRBAjEhHpRbz18N+/wIpfQl1lsKPpXBGxTovB2Euc5KCnvs148jxn6tQXvg/YhjcNX7c0eDM0dQe57zpvsvYnCRlukqCuzl0hpBIF13eB1cDvjDGzgE3A6TjvWNgC/LxZfV/fGP80PNbaD40xC4GvAx+506PuArKAS4FI4LfW2lZGSslv39hCWXUdAMP7xPHV0wcHOSIRkV6iYCssvamNtwv3AJHxbnJwqdO9KDI22BF1jUlznZaFpTcBFg5+BosvcgbrxqUHO7qut/NtePIaqK1wtuP7wvUvQp/WeqBLRwu5RMFtVTgV+CVwATAbyAMeBhZYa4vbeapvAG8D84DzgQTgMPAu8Ddr7b86OPQeY/uhIzz5393+7Z/PGUNEmCeIEYmI9ALeenj/97DyPqiraihPHgwJ/YMXV0dKyYIxFzkDkyNigh1NcEy81kkWnv8OYJ3ZnRZf5HRD6qoXw3UHO1bBk19uaDGLz4R5L0K6ujl3GdhnuwAAIABJREFUpZBLFACstXtwWgPaUzfghP7WWgsschc5Bq9vPIjXOj9PG5HGOaMzghuQiEhPl58DS7/rTKHp4wmHs34EZ90G4ZHBi0063oSvuMnCjWC9kL8RFn/J6XIT3wv+z92+Ep76ckNCnNDPaUlIHxHcuHohfQ0sx2znIf8QEL44pi/G6OVqIiKdor4W3v4N/OWspklC5inwPyvhnJ8pSeipxl8Dl/3VSRgADuXAoi9B2cHgxtXZtq1omiQkDoB5LylJCJKQbFGQ4NpZ0JAoDO0TH8RIRER6sAOfO60IeZ82lHkiYMbtMO0WCNMEEj3eKVc571n4z7fA1jtTxS6a43TBScgMdnQdb+sb8K+vQn21s504EOYtg9RhwY2rF1OLghyzHY0ShWHpPXT2CRGRYKmrgVUPwF9nNE0S+k+CG9+Bs3+sJKE3OflKuOJRZ0YkgMKtTrJweH9w4+poW16Df32lIUlIGuQkREoSgkqJghyTw1W1FBxx/hJHhnnon9xLB5uJiHSG/Z/A386BVfeDt9YpC4uCcxfAN17XvPG91UmXw5V/d8algPOeiUVzoHRfcOPqKJuXw9PXOu/SAEga7HQ3Sh0a3LhEXY/k2OQ2ak0YkhZLmEfjE0RETlhdNbz1a3j3/5wuJj4DvwCX/FHTQYrzkjnjgSVfB28dFO2AP06B2JRgR3biSvc69wTOLF7zXnLWEnRKFOSYNBmfoG5HIiInbt8aeP4mOLSpoSw8BmbdBaffCJ6w4MUm3cvYi+GqxfDMPKfFqbrUWXqKlCxndqPkQcGORFzqeiTHZMehxgOZlSiIiBy32ip4/Rfw6LlNk4TBU+E778GUm5QkSEtjvgTX/ANie9gL2PpNcFsSlCR0J2pRkGOigcwiIh1g93+dt+8Wbm0oi4h1xiJ84Zvg0fd4/5+9+w6zq6r3P/7+plfSQ+iBQAi9d+kKiAVUVKRjRVHQH3qvigiK9er1CghWioJ0IaEJoQqCiPSWECAJvYSEhJCemfX7Y5/hnJnMJDOZPbPnnHm/nmeec/bae/b+hsOZOZ9Ze62lldj0g/D/noZ3amSMQo9e2eBlp1vvcgwKapMZb7373vMNRzo1qiS1ydKFcMeP4P7zgFRuH7snfPQcB2+q9Xr1dUYgdTiDglotpdRosTXHKEhSG8y8F677ajYItUGfQfCBH8IOx9uLIKnLMSio1WbNX8KCpdlsHIP79mLkIFcDlaRVWvIu3P4DeOAPjdvH7QcfOdt7siV1WQYFtdr0txoPZA7vJZSklZv+D7juazD3hXJb3yFw4I9hu6O8J1tSl2ZQUKs5NaoktdKS+dmMRg9e0Lh9kwPhI7+GNdYupi5JagODglptRqMZjxzILEnNeu52uP5kmPdSua3fEDjo57DN4fYiSKoaBgW1mmsoSNJKLJoLk0+FRy5p3L7ph+DDv4LBY4qpS5JWk0FBrVY5NaprKEhShWm3wPVfh/mvltv6D4eDfwFbfsJeBElVyaCgVlleV8+Lcxa+tz3WoCBJsHAO3PwdePzyxu2bHwoH/xIGjSqmLknKQa5BISJ6p5SW5XlOdQ2vzF3EsrpscaDRg/syqK8ZU1I3N/VGuOEb8O4b5bYBI+FD/wtbHFpcXZKUk7w/7b0SERcCf0wpPZfzuVWg6c54JEmZBbPh79+CJ//WuH3Lw+CD/wMDRxRTlyTlLO9lIHsA3wKeiYhbI+ITEdEz52uoAJUrMm/kQGZJ3dVT18K5OzcOCYPWhMMvhcPONyRIqil59yisDRwGfBHYH9gPeDMiLiDrZZiZ8/XUSVxDQVK39u4suOkUeHpS4/ZtPgMH/gQGDC+mLknqQLn2KKSUlqaULk0p7QNMAH5NFka+AzwXETdFxCERkXdPhjpY46DgGgqSuomU4Imrs16EypAweG044kr42O8MCZJqVod9YE8pTUspnQKsAxwF3AMcBFwDvBgRZ0SES1NWCXsUJHU781+Hy4+Ev30OFs0pt293NJx4P4w/sLjaJKkTdPhf9lNKS4EbgWuBV4Egu0Xp+8CMiPh1RPTt6Dq0+hYvq+OVuYsA6BGw/vABBVckSR0oJXj0sqwX4Zkby+1D1oOjroFDfpOttCxJNa5D57iMiF2BLwGfAvoB7wBnAxcA2wP/D/ga0Bf4ckfWotU3c3a5N2G94QPo08s7xyTVqHmvwA1fh2cnN27f8bPwgR9C38HF1CVJBcg9KETEYOBosoCwJVkPwiPAecClKaVFpUMfj4iLgZvJBkAbFLqoyhmPvO1IUk1KCR65GG45FZa8U24fugF89BzYaO/iapOkguS94Nr5ZL0HA4AlwMXAeSmlB5o7PqVUFxF3kc2OpC7KNRQk1bS5L8L1J8PzdzRu3/lLsP/3oa8TOEjqnvLuUTgeeB74HXBhSmnOKo4HuAv4Yc51KEeVA5k3MihIqhX19fDQhXDr92Hpu+X24RvBIefCBrsXV5skdQF5B4WDUkqTV31YWUrpXuDenOtQjpwaVVLNmTMDrvsazLynojFgtxNh31Ohj5M2SFKuQaGtIUHVoVFQcFVmSdXuiauzkLBsYblt5PisF2G9nYurS5K6mFynr4mI/SPigpbWR4iItUv798nzuuo4cxcuZc6CpQD07dWDtdboV3BFktQO774JE79cDgnRA/b4OnzpHkOCJDWR961HXwMmpJRebW5nSunViNgNGEI2NkFdXNOF1nr0iAKrkaR2evwKqMv++MHQDeCTF8I6OxRbkyR1UXlPiL89cN8qjvknsGPO11UHcUVmSTUjJXjkr+Xtvb5lSJCklcg7KIwmW315Zd4oHacqYFCQVDNefRhmTcme9x4AWxxabD2S1MXlHRTmAeut4pj1gAWrOEZdhGsoSKoZlb0Jmx/qKsuStAp5B4UHgEMjYkxzO0uDnA8tHacqULkq80bOeCSpWi1bDE9eXd7e7sjiapGkKpF3UDgHGAzcExEfjYi+ABHRNyIOAe4GBgFn53xddYCUkmsoSKoNU2+AxfOy58PGwgZ7FFqOJFWD3NdRiIgzgdOAa4EUEW8Dw4AofZ2ZUro5z+uqY7zxzhIWLasDYEj/3gwb0LvgiiRpNT1acdvRtkdCOIObJK1K3j0KpJROBw4CbgLmkE2FOge4ETiwtF9VYPpb7773fMORAwl/sUqqRvNehufvLG0EbPOZQsuRpGqR9zoKwHsrNLtKc5WrvO1oIwcyS6pWj10GpOz5RnvD0FXNuSFJgg7oUVDtqBzI7IxHkqpSSvDopeXtbY8qrhZJqjIGBbWo0dSozngkqRq9+C+YMz173ncIbPbhYuuRpCqSe1CIiLUi4tyIeC4iFkVEXTNfy/O+rvLnYmuSql7l2glbfhx69y+uFkmqMrmOUYiIdcjWSFgTeAroC7wALAE2Kl3vUbKF2dSFLaur58U5C9/bHjvCoCCpyix5F566try9nbcdSVJb5N2j8H1gDHBQSmmbUtuFKaUJZEHhFqA/8PGcr6ucvTRnIXX12eC/MWv0Y2DfDhn3Lkkd5+lJsKzUMzpyU1hnh2LrkaQqk3dQOBC4OaV0W9MdKaWXgU+SBYUf5Hxd5azRjEeOT5BUjSoHMW/n2gmS1FZ5B4UxZLccNagjCwYApJTeBW4FDsn5usqZ4xMkVbU5M+CFf2bPoyds/eli65GkKpR3UHgH6FOx/TawTpNj5gGjcr6ucjbdoCCpmlX2Jmz8fhg8prhaJKlK5R0UXgAqV7J5DNgvIgYAREQP4ADg5Zyvq5xVrqHgrUeSqkp9fWmRtZLtjiyuFkmqYnkHhduBfSOid2n7z8DawH0R8QvgXmAL4Iqcr6ucNb71aFCBlUhSG834B8x7KXvefziM/2Cx9UhSlcp7KpvzyW43Ggm8llK6JCJ2AL4GbF065nLgxzlfVzlasGQ5r7+zGIBePYJ1hznvuKQq8mjF2glbfwp69Wn5WElSi3INCimlZ4GfN2n7RkT8hGx61JkppTfyvKbyN3N2uTdh/eED6N3TBbwlVYlFc2HK9eXtbb3tSJJWV94Lrh0DvJFSuqWyPaU0C5iV57XUcZzxSFLVeuoaWJ71iDJmK1hr65UfL0lqUd5/Kr4AOCjnc64gItaNiAsi4tWIWBIRMyPi1xExrJXfv09EpFZ8rbfqs9WeyoHMBgVJVeWRituOtnUlZklqj7zHKLxO/uGjkYgYB9wHjAYmAVOBnYGTgYMiYo+U0uxVnGYmLS/6thXZytFPppReyqXoKtOoR8EZjyRVi1nPwCsPZs979IatPllsPZJU5fIOCjeTzXrUI6VUn/O5G5xHFhJOSimd09AYEb8CvkE2UPqElZ0gpTQTOKO5fRHRMKfeH3OotSq5hoKkqvTIJeXnm34QBo4orhZJqgF5//X/VGAwcH5EjMz53A29CQeQ9Qic22T36cAC4OiIWK1Pt6WaPwYsAv6y+pVWr5QS02e9+972Rk6NKqka1C2Hxytm3t7O244kqb3y7lG4jGzl5WOAwyNiJtntSKnJcSmltP9qnH/f0uPkpj0WKaX5EXEvWZDYlWxNh7Y6FugL/CWlNLc13xARD7Wwa8JqXL9wby9cxjuLlwPQv3dP1lyjb8EVSVIrPHcbvFuaVG/QGBi3Or9iJEmV8g4K+1Q87wtsWvpqqmlwaK2Gc01rYf+zZEFhPKsXFL5Qevz9anxvTZjxVrk3YcORA4mIAquRpFZ6tOK2o20+DT3z/vUmSd1P3usodPSE+0NKj/Na2N/QPrStJ46IvcmCyJMppfta+30ppR1aON9DwPZtraNo02c5kFlSlVkwG565ubztbEeSlAtX0ir7YunxD4VWUbDKGY82ciCzpGrwxFVQvyx7vu5OMGp8sfVIUo2otqDQ0GMwpIX9De2tGl/QICKGA58gG8R88eqVVhtcbE1S1am87ciVmCUpN3mvzLxXa49NKd29Gpd4pvTY0p+LNik9tjSGoSUNg5j/3NpBzLXKoCCpqrz2OLz+RPa8Vz/Y8uPF1iNJNSTv0V530fqByj1X4/x3lh4PaLpWQ0QMBvYAFgL3t/G8DYOYu/VtR/X1yaAgqbo8WrES82YfgX4tdThLktoq76DwQ5oPCkOBnYDdgeuBh1fn5Cml5yNiMtnMRicC51Ts/gEwEPh9Sum9T7sRMaH0vVObO2dE7AlsRhsHMdei195ZzJLlWfYaPrAPQwf0KbgiSVqJ5Uvh8SvL2952JEm5ynvWozNWtj8ijiP7cH9qOy7zFeA+4OyI2B+YAuxCtsbCtGbOPaXh8i2cz0HMJTNm2ZsgqYpM+zssmpM9H7IebLh3sfVIUo3p1MHMKaWLyG4L+kk7zvE8sCNwEVlAOAUYB5wF7JpSmt3ac0XEMOAwHMQMrLiGgiR1aY9U3Ha0zWegR7XNzyFJXVsRK9I8SnlMwGpJKb0EHN/KY1tcMSyl9DbQvz211JLpjk+QVC3mvw7P3Vre3vaI4mqRpBpVxJ9f1qOYgKJVcA0FSVXjscuhYT6LDd4Hwzcsth5JqkGdFhQiomdEfJ7sVp8HO+u6ar1GMx65KrOkriqlxrMdbecgZknqCHmvozB9JddZs/S4FPhuntdV+y1dXs9Lcxa+tz12hEFBUhf18oPwVmm5nD6DYPNDiq1HkmpU3rcA9aD56VGXAU8ADwDnpJSmNHOMCvTinIXUl165dYb2p1/v1VnmQpI6QeVKzFscCn38w4YkdYS8p0cdm+f51HlcaE1SVVi6EJ68pry97VHF1SJJNc655AQ4NaqkKjH1BljyTvZ8+DhYf9di65GkGpZrUIiI/hGxfkQ0u6RvRPQt7e+X53XVfvYoSKoKlYOYtz0CosUZsCVJ7ZR3j8L3gWeAQS3sHwhMxcHMXc70Wc54JKmLm/sSTP9HaSOyRdYkSR0m76DwQeC2lNKc5naW2m8DPpzzddVO011DQVJX99hlvDdfxrh9Ycg6hZYjSbUu76AwFpi2imOmlY5TFzF/8TJmzV8CQO+ewbrDBhRckSQ1UV/f5LYj106QpI6Wd1DoDdSv4pgEOEahC5n5Vnn9hA1GDKRnD+/5ldTFvHgfvD0ze95vCEywY1qSOlreQWE6sPcqjtkHeCHn66odpjvjkVTd3nga/vMnmP960ZV0nEcqehO2PAx6+/cmSepoeQeF64AdIuK/mtsZEd8Gtgcm5nxdtcMMxydI1WvKDfD7veDGU+A3O8PDF0Nqbt3LKrZkPjxd8WtjO287kqTOkPfKzL8EjgR+GhGfAiYDrwDrAAcC2wIvAv+T83XVDk6NKlWpp6+Dq4+H+uXZ9pJ5cN1X4alr4SNnwdD1iq0vL09NhGWlWyRHbQZrb19sPZLUTeS9MvPbEbEPcCmwK1nvQQIabnq/DzgqpfR2ntdV+xgUpCr01ES4+rOQ6koNwXszAj1/O5y3GxzwQ9jh+Opfa6ByEPN2R1b/v0eSqkTuKzOnlGamlHYHdgS+CpxWetwxpfS+lNLMvK+p1ZdSYoZrKEjV5clrGoeEERvD1x6CXU/kvb/LLJ0PN3wD/vLR8iDgajT7eXjxX9nz6Albf7rYeiSpG8n71qP3pJQeBh7uqPMrH2+9u5T5S7LbFgb17cWoQX0LrkjSSj1xNVzzxYqQsAkcdwMMHgMH/QQ2PwQmnQizn832z7gbztsd3n8G7PR56JH734c6VmVvwvgDYdDo4mqRpG4m198YEdE/ItaPiD4t7O9b2u90FV1E09uOwi59qet6/Cq45gvlkDByPBx3YxYSGqy/C5xwD+xxMkTpR/yyBfD3b8GfP5z9hb5a1NfBo5eVt107QZI6Vd5/Wvo+8AwwqIX9A4GpwHdzvq5W0wynRpWqw2NXwLVfhFRaqmbUhFJIWHPFY3v3hw/8ED53W3Zcgxfuhd/uAf86L/sQ3tVNvxPmv5o9HzAy61GQJHWavIPCB4HbUkpzmttZar8NcKWcLmK6A5mlru/Ry+DaL1WEhM3g2BtWfRvOujvAl+6GPb+Z3d8PsHwR3PIduPCD8NazHVt3e1WunbD1p6Fn7+JqkaRuKO+gMBaYtopjppWOUxdQOZB5IwcyS13PI3+FiV/mvRmNRm+RjUkYNKp139+rL+x/GnzhDlhzy3L7S//Oehf++WuoW5572e226G2YemN527UTJKnT5R0UegP1qzgmAY5R6CKcGlXqwh6+OBuY3BAS1twSjr0eBo5s+7nW3ha+cCfs8x3oUZrHom4J3HY6nP8BeHNKbmXn4sm/ZfUBrLUtrLlFsfVIUjeUd1CYDuy9imP2AV7I+bpaDXX1iRdmL3xve6xBQeo6HrooWzytISSM2aoUEkas/jl79YF9vg1f/AestU25/dWHs9Wd7/4l1C1rT9X5qbztaLujiqtDkrqxvIPCdcAOEfFfze2MiG+TLcI2MefrajW8OncRS+uyDqCRg/qyRj/v/5W6hAcvgOtPLm+P2RqOuQ4GDM/n/GO2hM/fDvudBj1Lk9TVLYU7zoQ/7Q+vP5nPdVbXm1Oy8AJZfVt+oth6JKmbyjso/BJ4CfhpRDwYET+JiBNLjw8BPwZeBP4n5+tqNVQOZN7I3gSpa/jPn7KF0hqstS0cm2NIaNCzN+z1zWyw89rbl9tfewz+sDfc9TNYvjTfa7bWI5eUn296cP7/dklSq+QaFFJKb5PdWvRvsp6DbwNnlx63A/4F7Fs6TgWbMcupUaUu5YE/wo2nlLfX3h6OmQT9h3XcNUdvBp+7NZtOtWdpwcX65XDXT+GP+8Krj3bctZtTtwwev6K87W1HklSY3JfoTCnNTCntDuwIfBU4rfS4Y0rpfSmlmXlfU6un0UBmZzySinX/7+Cmb5a319kRjr4W+g/t+Gv37JUt0HbCP2HdncvtbzwJf9wPbj8Tli/p+DoAnr0VFszKng9eC8bt1znXlSStoFdHnTil9DDwcEedX+3nGgpSF/Gv87K1DRqsuxMc9TfoN6Rz6xg1Hj57M/z7d6VwsChbBfqeX2ZTlR5ybrY2Q0d6tGIQ8zaHQ4+eHXs9SVKLOiQoRMRawP7AOkDfZg5JKaUzO+Laar0ZjlGQinffb2DyqeXt9XaBI6+GfmsUU0+PnrDbiTD+ILjua9lqzgCzpsD5789CTHTgh/eXHyg/39bbjiSpSLkHhYj4AdmYhMpzB+/N8ffec4NCgRYvq+OVuYsAiID1RwwouCKpG7r3LLj1++Xt9XaFo66GvoOLq6nBiHHZ6s//+RPcdgYsW5CtDP3Svzvn+uvtAiM37pxrSZKalesYhYg4kmxMwj3AYWSh4M/AEcAfyRZjuxzwptOCvThnIakU3dYd1p++vezelzrVP/+vcUhYf/euExIa9OgBu3wRvnIfbLhX5157z2+u+hhJUofKu0fhy8DLwEEppeURATAzpXQ5cHlEXAvcCFyW83XVRtNnVY5PGFRgJVI3dPcvszULGmzwPjjiCujbRd+Lw8Zm6zjMmgoL53TC9TaAIet2/HUkSSuVd1DYCrgspbS8ou29P1WnlG6JiFuAbwHX53xttYHjE6SC/OMXcOePyttj98xCQp8u/j6MyKZSlSR1G3lPj9obmF2xvQhoOm3Hk8A2OV9XbTTjLddQkDrdXT9rHBI23AuOuLLrhwRJUreUd4/Ca8BaFdsvAls3OWZtYDkq1AynRpU6T0rZAmb/+Hm5baN94PDLoI8TCUiSuqa8exQeAbas2L4D2DMijo6IgRHxIbJBzo/kfF21kUFB6iQpwZ0/bhwSxu0Hn7nckCBJ6tLyDgo3AFtGxIal7Z8B84CLgHeA68hmQvpeztdVG8xbtIy33l0KQJ9ePVh7aP+CK5Jq1LLF2dSid/+i3Lbx+7OehN6+7yRJXVuutx6llC4iCwUN2y9FxE7AKcA4YCZwXkrpiTyvq7aZWdGbMHbEAHr2iAKrkWrMskXw3G3w1ESYdjMsLY8HYpMD4FMXQ+9+xdUnSVIrdcjKzJVSSjOAr3b0ddR63nYk5WzpQnh2Mjw9Cabdki1O1tT4g+BTf4FezS1WL0lS19PhQUFdz/S3XENBarcl75bCwUR49lZYtrD544ZvBNscAXucZEiQJFUVg0I35BoK0mpaMj/rMXh6Ijx7Gyxf1PxxIzaBLQ6FzQ+BNbfM1iCQJKnKGBS6oco1FDYaZVCQVmrxO9lYg6cmZmMP6pY0f9zITUvh4NBsYTLDgSSpyhkUupmUEjNmOUZBWqlFc8vh4PnboW5p88eN3jzrNdj8UBg9oXNrlCSpgxkUupk35y9hwdI6ANbo14vhA/sUXJHURSx6G6belA1Ifv4OqF/W/HFrbpkFg80PgVHjO7dGSZI6kUGhm5le2ZswahDh7RHqzhbOgak3ZmMOpt8F9S0sGj9mq1I4OBRGbtypJUqSVBSDQjfjQGaJbLXke34Jd/2s5XCw1rbZmIPNPgojxnVufZIkdQEGhW6mciCz4xPULaUEt/8Q/vmrFfetvX15tqJhYzu9NEmSuhKDQjfjYmvq1lKC206He88qt625JWxzeBYOhq5fXG2SJHUxBoVuZrpBQd1VSjD5e/Cv35TbXC1ZkqQWGRS6keV19bw4u7x6rEFB3UZKcMupcP+55bZND4ZPXmRIkCSpBQaFbuTltxexvD4BsOYafRnY15df3UBKcPN34N+/LbdN+DAcdiH0cnpgSZJa4ifFbsTxCep2UoK//xc88Idy22YfyUJCz97F1SVJUhXoUXQBqyMi1o2ICyLi1YhYEhEzI+LXETFsNc61fURcGhEvl871RkT8IyKO6Yjai9R4fMKgAiuROkF9Pdz0zcYhYfNDDAmSJLVS1fUoRMQ44D5gNDAJmArsDJwMHBQRe6SUZrfyXF8FzgLeBm4EXgGGA1sCBwN/yf0fUKDKqVFdQ0E1rb4ebjoFHryg3LbFx+DjfzQkSJLUSlUXFIDzyELCSSmlcxoaI+JXwDeAHwMnrOokEXEAcDZwK3BYSml+k/0192nCW4/ULdTXww1fh4f/XG7b8hPwsT9Az2r8kSdJUjGq6tajUm/CAcBM4Nwmu08HFgBHR0RrPgX/AlgEHNE0JACklJa1r9quZ8asiqAwyqCgGlRfD9ef1DgkbPVJQ4IkSauh2n5z7lt6nJxSqq/ckVKaHxH3kgWJXYHbWzpJRGwJbA1MBOZExL7ADkACHgXubHr+ardoaR2vzlsMQM8ewXrDBhRckZSz+jq47iR49JJy29aHw6HnQY+exdUlSVKVqragsGnpcVoL+58lCwrjWUlQAHYqPb4J3AXs1WT/ExHx8ZTSc6sqKCIeamHXhFV9b2eaObvcm7DesP706VVVnUnSytXXwaSvwmOXltu2OQIO+Y0hQZKk1VRtnxaHlB7ntbC/oX3oKs4zuvT4OWAs8KHSuccDlwBbATdGRM1Msu74BNWs+jqY+JXGIWHbowwJkiS1U7X1KOSlISD1BA5PKf2rtP1OaVrUCcCOwCeAy1Z2opTSDs21l3oats+n3Pab4dSoqkV1y2HiCfDEVeW27Y6Gj5wNPart7yCSJHUt1fabtKHHYEgL+xva567iPA37X68ICQCklBLZtKuQTbtaE6Y7kFm1pm45XPvFxiFh+2MNCZIk5aTaehSeKT2Ob2H/JqXHlsYwND1PS4Hi7dJj/1bW1eW5hoJqSt1yuObz8NS15bYdPwsH/68hQZKknFTbb9Q7S48HRESj2iNiMLAHsBC4fxXnuZ9sKtWxLUylumXpcUY7au1SHKOgmlG3DP722cYhYafPw4d+ZUiQJClHVfVbNaX0PDCZbADyiU12/wAYCFycUnrvU3FETIiIRjMQpZQWAucD/YAfRURUHL8VcBywHLg6/39F53t7wVLeXpgtC9Gvdw/GrNGv4Iqk1VS3DK4+Hp6eVG7b+Ytw8C+h/DaWJEk5qLZbjwC+AtwHnB0R+wNTgF3I1liYBpza5PgppcemnyJOI5sW9evAbqU1GNYEPk4WIL5eCiZVb0bF1KhjRwykRw8/UKkpyvvAAAAgAElEQVQKLV+ahYSpN5TbdvkyHPRTQ4IkSR2gqnoU4L1ehR2Bi8gCwinAOOAsYNeU0uxWnucdYE/gJ8Bw4KvAh4F/AgemlM7KvfiCVK7IvJEDmVWNli+Fq45tHBJ2PdGQIElSB6rGHgVSSi8Bx7fy2BY/RaSU3iXrgWjaC1FTHJ+gqrZ8CVx5DEy7udy221fhgB8ZEiRJ6kBVGRTUNq6hoKq1bDFceTQ8O7nctsfJ8P4fGBIkSepgBoVuYLo9CqpGyxbDFUfCc7eV2973Ddj/dEOCJEmdwKBQ4+rrEzMrgoJrKKgqLFsElx8Bz99Rbtvzm7Df9wwJkiR1EoNCjXtj/mIWLasDYOiA3gwb2KfgiqRVeOc1uOYLMPOectte/wX7fteQIElSJzIo1LjKGY+87UhdWkrw6KVwy3dg8bxy+z7fgX2+XVxdkiR1UwaFGuf4BFWFeS/D9V+H525t3L7f92CvbxVTkyRJ3ZxBocZVzng0bpQzHqmLSQke/jPc8j1YOr/cPmwsfPQ3sOGehZUmSVJ3Z1Coca6hoC7r7Rfg+pNg+l0VjQG7nAD7nwZ9/P9VkqQiGRRqnEFBXU59PTx4Ptx2Bix9t9w+fBwcci5ssFthpUmSpDKDQg1bVlfPi3MWvrc9doRBQQWbMx2uO6nxjEbRA3Y7EfY9FXr3L642SZLUiEGhhr04ZyF19QmAtYf0o3+fngVXpG6rvh4e+D3c/kNYVg6vjNwUDj0P1t2xuNokSVKzDAo1rNHUqKPsTah5b8+EpyfBmlvAhntDz95FV5R56zmYdCK8dH+5LXrCHifD3v8NvfsVV5skSWqRQaGGOT6hG3n1UfjLIbB4brbdbyhM+DBsfghstA/0KmChvfo6+Ne5cOePYfnicvvozbOxCOts3/k1SZKkVjMo1LDGayg4NWrNeuVhuPjQxouULZ4Lj16SffUdAhMOhs0PhXH7Qq++HV/TrGdg4lfglQfLbT16wZ6nwJ7fLCa4SJKkNjEo1LAZb5VnlNnIHoXa9MpD8JePwZJSSOg3BPquAfNeKh+zZB48dln21XcN2PSDWU/DuP3zv+2nbjncdzbc9TOoW1JuH7MVHHIerLV1vteTJEkdxqBQw7z1qMa9/CBc/DFY8k623W8oHDMJ1tom62V4+tpszMLcF8vfs+QdePyK7KvPIBh/EGxxKGz8/vbPOPTGU1kvwmuPltt69M7GIbzv611nzIQkSWoVg0KNWrBkOW+8k/1Ft1ePYN1hTjtZU156AC7+eHk14/7D4Jjryn+xX3eH7OsDZ8Krj2SB4emJ2YDnBkvfhSevzr56D4TxB2Y9DZscAH0GtL6WumVwz6/g7l9A/bJy+9rbZWMR1tyi3f9cSZLU+QwKNaqyN2H9EQPo1bNHgdUoVy/+Gy75REVIGA7HXpfd3tNURDZoeJ3t4f1nwOuPw1MTs9AwZ3r5uGUL4Klrsq/eA2CTD2RjGjY5APquZHzLa49nvQhvPFFu69kX9v0O7PY16OmPGEmSqpW/xWtUZVBwfEINeeFf8NfDyisaDxgBx17fur/aR2S3Ja21Dez/fXjjyayn4amJMPvZ8nHLFpZ6ICZBr/6wyfuz0DD+QOg7ODtm+dKsB+Gfv4L65eXvXXenrBdh1Kb5/ZslSVIhDAo1yvEJNeiF++CSw7K//gMMGFkKCZu3/VwRWQ/EmK2yFZHfnJL1Mjw9CWZNLR+3fBFMuT776tk3G8uw8X7wn/PhzafLx/XqB/udBrt+GXq4sJ8kSbXAoFCjZjg1am2Z+U/466fKIWHg6CwkjJ7Q/nNHZGFjzc1h3+/Cm1PLYxoqw0DdEnjmxuyr0vq7wUd/AyM3bn8tkiSpyzAo1Kjp9ijUjhl3w6Wfzm4JAhi0Jhx7A4wa3zHXGz0h+9rnv2HWNJgyCZ6a1HgcAmRjGd5/Buz0BejhGBhJkmqNQaEGpZSYMatiDYVRBoWqNf0uuPTw7BYggEFj4LgbYOQmnXP9UeNh1Ldgr2/B7OezXoZpk2HQqGxGpeEbdk4dkiSp0xkUatCcBUt5Z3E2wHRAn56MHtwJK/Eqf8/fCZcdDssXZ9uD18p6Eoq6xWfEuNLKyqcUc31JktSpvF+gBjUdyBwRBVaj1fLc7U1Cwtpw3I2OA5AkSZ3GHoUa5PiEKvfsbXD5EdngYYA11oXjrofhGxVblyRJ6lYMCjXINRSq2LTJcMWRULc02x6yXja7kWMBJElSJ/PWoxo0Y1ZFj4IDmavHMzc3CQnrZwOXDQmSJKkA9ijUINdQqEJTb4Irj4H6Zdn20PWzgcvDNii2LkmS1G0ZFGpMfX1ixuyKoDDCHoUub8oNcNVxFSFhg2zg8tD1Ci1LkiR1bwaFGvPqvEUsXV4PwIiBfRgyoHfBFWmlnr4Orj4e6rPpbBm2YXa70ZB1i61LkiR1ewaFGtN0alR1YU9NhKs/C6ku2x6+UXa70ZB1iq1LkiQJBzPXHINClXjymsYhYcTG2e1GhgRJktRF2KNQY6Y741HX98TVcM0XK0LCJtntRoPHFFuXJElSBYNCjXENhS7u8avg2i9CysaRMHJ8drvR4DWLrUuSJKkJbz2qMU6N2oU9dkXjkDBqQna7kSFBkiR1QfYo1Jjjdh/Lc7PeZcasBWwwYkDR5ajBo5fBxC8DKdsetVm24vKgUYWWJUmS1BKDQo357PtcxbfLee72xiFh9BZw7HUwcGShZUmSJK2MQUHqSO+8Ctd8gfdCwppbwjHXwcARhZYlSZK0Ko5RkDpK3bJsCtSFs7PtQWPg6GsNCZIkqSoYFKSOcseZ8OK/sufRAw67AAaNLrYmSZKkVjIoSB3hmb/DvWeVt/c7DcbuUVw9kiRJbWRQkPL29gtw7Qnl7U0OgD2+Xlw9kiRJq8GgIOVp+VK46jhYPDfbXmNd+NjvoYdvNUmSVF389CLl6dbT4NWHs+c9esEnL4QBw4utSZIkaTUYFKS8PD0J/v278vYHfgjr7VxcPZIkSe1gUJDyMPt5mPTV8vaED8OuXymuHkmSpHYyKEjttWwxXHUsLHkn2x66ARxyLkQUW5ckSVI7GBSk9rr52/D6E9nznn3gU3+G/kOLrUmSJKmdDApSezx+JTx0YXn7wJ/A2tsVV48kSVJODArS6pr1DFxfsT7CFh+HnT5fXD2SJEk5MihIq2PpArjyWFi2INsesTF89GzHJUiSpJphUJBWx03fgllTsue9+sEn/wx9BxdbkyRJUo6qMihExLoRcUFEvBoRSyJiZkT8OiKGteEcd0VEWslXv478N6iKPXIJPPrX8vbBv4QxWxZXjyRJUgfoVXQBbRUR44D7gNHAJGAqsDNwMnBQROyRUprdhlP+oIX25e0qVLXp9SfhxlPK29t8BrY7qrh6JEmSOkjVBQXgPLKQcFJK6ZyGxoj4FfAN4MfACa09WUrpjLwLVI1aMj9bL2H54mx71AT40P86LkGSJNWkqrr1qNSbcAAwEzi3ye7TgQXA0RExsJNLU61LCa4/GWY/l233HgCf+gv08X81SZJUm6qtR2Hf0uPklFJ95Y6U0vyIuJcsSOwK3N6aE0bEp4ENgaXAFOCOlNKS/EpWTXjwfHjyb+XtD/8aRm1aXD2SJEkdrNqCQsMns2kt7H+WLCiMp5VBAbi8yfabEXFiSunq1nxzRDzUwq4Jrby+urpXH4Gbv1Pe3uE42ObThZUjSZLUGarq1iNgSOlxXgv7G9qHtuJck4CPAOsC/ck+2P+09L1XRMRB7ahTtWLRXLjqOKhbmm2P2QoO+nmhJUmSJHWGautRyE1K6f+aND0DfDciXgXOIQsNN7fiPDs0117qadi+vXWqQCnBpBPh7ZnZdp/B2XoJvZ05V5Ik1b5q61Fo6DEY0sL+hva57bjGn8imRt02IlxBqzu7/7cw9Yby9iHnwIhxxdUjSZLUiaotKDxTehzfwv5NSo8tjWFYpZTSYmB+adMpbbqrl/4Dt55W3t75S7DFx4qrR5IkqZNVW1C4s/R4QEQ0qr301/89gIXA/at7gYjYFBhGFhbeWt3zqIotnJONS6gvrbm39vZwwJmFliRJktTZqioopJSeByYDY4ETm+z+AVkPwMUppQUNjRExISIazUAUERtGxPCm54+IUcCFpc3LU0quztzd1NfDtV+Cd17OtvsNgU9eBL36FlqWJElSZ6vGwcxfAe4Dzo6I/cnWPtiFbI2FacCpTY6fUnqsXD53b+B3EfFPYDowB1gfOJhsnMODwH911D9AXdi9v4ZnJ5e3D/0dDNuguHokSZIKUnVBIaX0fETsCPwQOIjsw/1rwFnAD1JKb7fiNA+RrZ+wA7AdsAbZrUZPAFcCv08pLe2A8tWVzbwX7vhReXv3r8GEg4urR5IkqUBVFxQAUkovAce38thopu0J4Licy1I1e3cWXP1ZSHXZ9nq7wP6nF1uTJElSgapqjILUIerr4JrPw7uvZ9v9h8NhF0LP3sXWJUmSVCCDgnT3L2D6XaWNgI//EYasU2RFkiRJhTMoqHt79la462fl7b2+CZu8v7h6JEmSugiDgrqv526HK44CUrY9dk/Y5zuFliRJktRVVOVgZqndnr0NLj8C6pZk22usC584H3r0LLYuSZKkLsIeBXU/0ybD5Z8ph4Qh68FxN8DgNYutS5IkqQsxKKh7eeZmuOJIqCstkzFk/SwkDN+w2LokSZK6GG89Uvcx9Sa48hioX5ZtD10fjr3BlZclSZKaYVBQ9zDlBrjquIqQsAEcdyMMXa/QsiRJkroqg4Jq39PXwdXHQ/3ybHvYhtntRkPWLbYuSZKkLswxCmq7lODJv8F//gRLFxZdzco9NbHUk1AKCcM3ynoSDAmSJEkrZVBQ2z38F7j6s3DjKfC7PWDmvUVX1Lwnr8nqTHXZ9oiNSyHBVZclSZJWxaCgtlkwG247vbw9ZzpcdDDc9C1Y8m5xdTX1xNXwt89XhIRNsoHLa6xdbF2SJElVwqCgtrntdFj09ortD/wBfrs7TP9H59fU1ONXwTVfKIeEkeOzMQlrrFVsXZIkSVXEoKDWe+kBeOTi8vZHzoJNDihvz30B/vJRuOEbsGR+59cH8NgVcO0XIdVn26MmZLcbDR5TTD2SJElVyqCg1qlbDjf+v/L2ph+CHY6DI66EQ38H/YaU9z14AZy3Gzx3e+fW+OhlcO2XKkLCZtntRoNGd24dkiRJNcCgoNZ58Hx4/Ynsea/+8MGfZc8jYNvPwIkPZOGhwbyX4JKPw6QTYdHcjq/vkb/CxC8DKdsevUV2u9GgUR1/bUmSpBpkUNCqzX8D7vhReXuvb2arGlcaPAYO/yt84nzoP7zc/sglWe/CtFs6rr6HL84CSUNIWHNLOPZ6GDiy464pSZJU4wwKWrVbT4Ml72TPR2wMu3+t+eMiYKvD4MR/w+aHlNvnvwqXfgquPQEWzsm3tocuguu+ynshYcxWpZAwIt/rSJIkdTMGBa3cjHvg8SvK2wf/Enr1Xfn3DBoNn/oLfPLPMKDir/qPXQbn7QpTb8yntgcvgOtPLm+P2RqOuQ4GDG/5eyRJktQqBgW1rG4Z3PTN8vYWH4Nx+7b++7c4NBu7sOVh5bZ334DLj8gWQlswe/Vr+8+fstmVGqy1LRwzyZAgSZKUE4OCWnb/eTBrava8zyA48CdtP8fAEXDY+XD4pTBozXL7k3+Dc3eGpya2/ZwP/DFbFbrB2tvDMRMNCZIkSTkyKKh5816Bu35e3t7n2+1b1XjCh+Ar98M2nym3LXwLrjoWrjwG3p3VuvPc/7vGvRzr7AhHXwv9h61+bZIkSVqBQUHNu+U7sGxB9nzUZrDLCe0/54Dh8LHfZWsvDK4IHU9PynoXnrgaUmr5+/91Htz83+XtdXeCo6+B/kPbX5skSZIaMShoRc/dnn14b/Ch/4WevfM7//gD4cT7Ybujy22L5sDfPgeXHwnzX1/xe+77TRZeGqy3Cxx1TeOF3iRJkpQbg4IaW74EbvpWeXvrw2HsHvlfp98QOOQ32Yf9IeuV25+5MetdePTScu/CvWfB5FPLx6y3Kxz1N+i3Rv51SZIkCTAoqKl7z4Y5z2fP+w6BA87s2OttvD98+T7Y8bPltsXzslWWL/0U3H4m3Pr98r71d4ejroa+gzu2LkmSpG7OoKCyt2fCPb8sb+9/WrYmQkfrtwZ8+P+yNRCGblBuf3Zy43o2eB8ceZUhQZIkqRMYFFT292/D8sXZ87W2afxX/s6w0d5Z78LOX1px39g94cgroe+gzq1JkiSpmzIoKDP1Jpj299JGwId+BT16dn4dfQfBwf8Dx/8dho/L2jb+QDZTUp+BnV+PJElSN9Wr6ALUBSxdCH+vmHZ0+2Ng3R2Lqwdgg93hqw/CvJdg6PoQUWw9kiRJ3YxBQXDP/8K8F7Pn/YfD+88ospqyHj1g2AarPk6SJEm589aj7u6t5+C+s8vb7z8jWxhNkiRJ3ZpBoTtLCW76JtQtzbbX3anxImiSJEnqtgwK3dnTE2H6ndnz6JGtwNzD/yUkSZJkUOi+lsyHm79b3t7p89mUqJIkSRIGhe7rHz+H+a9mzweOhn1PLbYeSZIkdSkGhe7ozSlw/2/L2wecCf2HFlePJEmSuhyDQneTEtx4CtQvz7Y32AO2/nSxNUmSJKnLMSh0N49fCS/cmz3v0QsO/qWLmUmSJGkFBoXuZNFcmPy98vauX4Y1Ny+uHkmSJHVZBoXu5M4fw4I3s+eD14a9v11sPZIkSeqyDArdxauPwn/+VN4+6CfQd1Bx9UiSJKlLMyh0B/X12QDmVJ9tb7QvbH5osTVJkiSpSzModAePXAyvPJg979nHAcySJElaJYNCrVs4B247o7y9+0kwcuPCypEkSVJ1MCjUutvOgEVzsudD1oc9Tym0HEmSJFUHg0Ite/lBePgv5e0P/hz6DCiuHkmSJFUNg0Ktqq+DG/8fkLLt8QfBhIMLLUmSJEnVw6BQqx68AF57LHveq1/WmyBJkiS1kkGhFr37Jtx+Znl7z1Ng2NjCypEkSVL1MSjUosmnwZJ52fPh47KZjiRJkqQ2MCjUmpn3wuOXl7cP/gX07ldcPZIkSapKVRkUImLdiLggIl6NiCURMTMifh0Rw9pxzr0ioi4iUkT8KM96O03dsmwF5gabHwIb719cPZIkSapavYouoK0iYhxwHzAamARMBXYGTgYOiog9Ukqz23jOwcCfgYXAoHwr7kTzX4NUnz3vPRAO/Gmx9UiSJKlqVV1QAM4jCwknpZTOaWiMiF8B3wB+DJzQxnOeBQwBflr6/uo0dH044Z9w/3nQuz8MWafoiiRJklSlqurWo1JvwgHATODcJrtPBxYAR0fEwDac8xDgeOAk4NV8Ki1Qrz7wvq/DLl8quhJJkiRVsaoKCsC+pcfJKTXcY5NJKc0H7gUGALu25mQRMRr4IzAxpXRJnoVKkiRJ1azabj3atPQ4rYX9z5L1OIwHbm/F+f5IFpbaeqvSeyLioRZ2TVjdc0qSJElFq7agMKT0OK+F/Q3tQ1d1ooj4LPBR4NMppTdyqE2SJEmqGdUWFHIREWOBXwNXpZSubM+5Uko7tHCNh4Dt23NuSZIkqSjVNkahocdgSAv7G9rnruI8FwCLgK/kUZQkSZJUa6otKDxTehzfwv5NSo8tjWFosD3ZFKuzSguspYhIwIWl/aeW2ia2r1xJkiSpOlXbrUd3lh4PiIgelTMflRZN24Ns0bT7V3Gev5DNjtTUJsBewKPAQ8Aj7a5YkiRJqkJVFRRSSs9HxGSymY1OBM6p2P0DYCDw+5TSgobGiJhQ+t6pFec5qbnzR8RxZEHhxpTS93L/B0iSJElVoqqCQslXgPuAsyNif2AKsAvZGgvTgFObHD+l9BidVqEkSZJU5aptjAIppeeBHYGLyALCKcA44Cxg15TS7OKqkyRJkmpDNfYokFJ6CTi+lce2uichpXQRWQCRJEmSurWq61GQJEmS1PEMCpIkSZJWYFCQJEmStAKDgiRJkqQVGBQkSZIkrSBSSkXXUJMiYnb//v2Hb7bZZkWXIkmSpBo2ZcoUFi1aNCelNCLP8xoUOkhEzADWAGYWcPkJpcepKz1KtcjXvnvyde++fO27L1/77qu5134s8E5KacM8L2RQqEER8RBASmmHomtR5/K175583bsvX/vuy9e+++rM194xCpIkSZJWYFCQJEmStAKDgiRJkqQVGBQkSZIkrcCgIEmSJGkFznokSZIkaQX2KEiSJElagUFBkiRJ0goMCpIkSZJWYFCQJEmStAKDgiRJkqQVGBQkSZIkrcCgIEmSJGkFBoUaEhHrRsQFEfFqRCyJiJkR8euIGFZ0beo4pdc5tfD1etH1qX0i4rCIOCci7omId0qv6yWr+J7dI+KmiJgTEYsi4vGI+HpE9OysutV+bXntI2LsSn4OpIi4vLPr1+qJiBER8fmIuDYiniu9h+dFxD8j4nMR0exnN9/31a+tr31nvO97tfcE6hoiYhxwHzAamARMBXYGTgYOiog9UkqzCyxRHWse8Otm2t/t7EKUu+8B25C9li8DE1Z2cEQcAvwNWAxcAcwBPgL8H7AH8MmOLFa5atNrX/IYMLGZ9idzrEsd65PAb4HXgDuBF4E1gY8DfwI+GBGfTBUr5vq+rxltfu1LOux978rMNSIibgEOAE5KKZ1T0f4r4BvA71NKJxRVnzpORMwESCmNLbYSdYSI2JfsQ+JzwN5kvzz+mlI6qplj1ygdNwTYI6X0YKm9H3AHsBvwmZSSf12uAm187ccCM4A/p5SO67wqlbeI2A8YCNyYUqqvaB8DPACsBxyWUvpbqd33fY1Yjdd+LB38vvfWoxpQ6k04AJgJnNtk9+nAAuDoiBjYyaVJaqeU0p0ppWeb+QtScw4DRgGXN3xYKJ1jMdlfpwG+3AFlqgO08bVXjUgp3ZFSur7yg2Kp/XXgd6XNfSp2+b6vEavx2nc4bz2qDfuWHic38z/X/Ii4lyxI7Arc3tnFqVP0jYijgPXJguHjwN0ppbpiy1In26/0eHMz++4GFgK7R0TflNKSzitLnWjtiPgSMAKYDfwrpfR4wTUpP8tKj8sr2nzfdw/NvfYNOux9b1CoDZuWHqe1sP9ZsqAwHoNCrRoDXNykbUZEHJ9S+kcRBakQLf4sSCktj4gZwBbARsCUzixMneYDpa/3RMRdwLEppRcLqUi5iIhewDGlzcpQ4Pu+xq3ktW/QYe97bz2qDUNKj/Na2N/QPrQTalHnuxDYnywsDAS2An4PjAX+HhHbFFeaOpk/C7qvhcCZwA7AsNJXw7iGfYDbvf206v0M2BK4KaV0S0W77/va19Jr3+Hve4OCVOVSSj8o3df4RkppYUrpydLA9V8B/YEziq1QUkdLKb2ZUvp+SunhlNLc0tfdZL3J/wY2Bj5fbJVaXRFxEnAK2YyGRxdcjjrRyl77znjfGxRqQ8NfC4a0sL+hfW4n1KKuo2Hg016FVqHO5M8CNZJSWk42rSL4s6AqRcRXgbOAp4F9U0pzmhzi+75GteK1b1ae73uDQm14pvQ4voX9m5QeWxrDoNo0q/To7QbdR4s/C0r3uG5INhBuemcWpcL5s6BKRcTXgXPI5sPftzT7TVO+72tQK1/7lcnlfW9QqA13lh4PaGbVvsFki60sBO7v7MJUqF1Lj/5y6D7uKD0e1My+vYABwH3OfNLt+LOgCkXEf5MtmPYo2QfFN1s41Pd9jWnDa78yubzvDQo1IKX0PDCZbPDqiU12/4AsTV6cUlrQyaWpg0XEZs0NVCotwvKb0uYlnVmTCnU18BZweETs2NBYWnjpR6XN3xZRmDpWRGzf9A9Fpfb9yRbdBH8WVI2IOI1sAOtDwP4ppbdWcrjv+xrSlte+M973rsxcI0qLrt0HjAYmkU2BtgvZGgvTgN1TSrOLq1AdISLOIBvkdDfwAjAfGAd8COgH3AR8LKW0tKga1T4RcShwaGlzDHAg2V+I7im1vZVS+maT468GFgOXA3OAj5JNoXg18CkX8KoObXntS1MhbkL2e+Dl0v6tKc+xf1pKqeFDo7qwiDgWuAioI7v1pLnZjGamlC6q+B7f9zWgra99Z7zvDQo1JCLWA35I1v04AngNuBb4QUrp7SJrU8eIiL2BE4DtKE+POpesu/Jisp4k3+RVrBQGT1/JIS+klMY2+Z49gFOB3cgC43PABcDZLsJXPdry2kfE54CPkU2hOBLoDbwB/Av4TUrpnpZOoq6lFa87wD9SSvs0+T7f91Wura99Z7zvDQqSJEmSVuAYBUmSJEkrMChIkiRJWoFBQZIkSdIKDAqSJEmSVmBQkCRJkrQCg4IkSZKkFRgUJEmSJK3AoCBJkiRpBQYFSZIkSSswKEiSJElagUFBkiRJ0goMCpKkmhURd0VEKroOSapGBgVJkiRJKzAoSJIkSVqBQUGSJEnSCgwKkqRViohdIuLqiHg9IpZGxEsR8fuIWLvJcXdFRIqIvhHxo4iYERFLIuL5iDg9Ivq0cP79I+LmiJhTOn5aRPwsIoa0cPzwiPhxRDwZEQsjYl5EPFb6noHNHN8rIr4bEc+Wzv9SRPy8pXokSRApOcZLktSyiPgs8AdgCXAd8BKwCfBR4A1g15TSi6Vj7wL2Lh23E3A1sAw4BBgH3AB8NFX88omILwG/BRYAVwFvAvsAuwBPA3uklOZWHL8hcCewAfAQ8A+yP3yNB94PbJpSmtmknquAPYG/A+8AB5f+DRellI7P5T+UJNUYg4IkqUURMR54EngR2Dul9ErFvv2BycB1KaWPldruIvtg/iywS0rp7VJ7P7IP97sCx6SULi61bwBMIwshO6eUplac/zzgy8AfU0pfrGi/D9gN+G5K6adN6h0JvJtSWtyknoeBD6SU5pTaBwKPARsC66SUXm/3fyxJqjHeeiRJWpkvA72BkytDAkBK6XaynoOPRMTgJt93ZkNIKB27GPhOaRSj7K0AAALjSURBVPOzFccdBfQBflMZEkpOBeYDR0dEX4CI2IEsJDwK/LxpsSmltxpCQhP/3RASSsctAP5K9ntwx+b+4ZLU3fUqugBJUpe2W+lx74jYqZn9o4GeZLf9PFTR/o9mjv0nUAdsV9G2fenxjqYHp5TejohHgL2ACWQ9ALuWdt+SUqpv7T8CeLCZtpdKj8PacB5J6jYMCpKklRlRevzWKo4b1GT7jaYHpJSWR8RbZOGiQcNg5ddaOG9D+9Amj680c2yLKsc4VFheeuzZlnNJUndhUJAkrcy80uOQlNI7bfi+NcnGNbwnInoBI8kGEzc9/xjgqWbOs1aT4xo+8K/ThlokSavBMQqSpJW5v/S4Zxu/b+9m2t5H9tf7RyraGp7v0/TgiBgKbAssBqY0qefAiPB3mCR1IH/ISpJW5jdk05v+X2kGpEYiok9ENBciTouIYRXH9QMaZii6sOK4S0rn/1pEbNzkHGcCawCXpJSWAKSUHgLuIwsQ/91MPSNK15IktZO3HkmSWpRSmlpaR+EC4KmIuJlsOtPewPr/v707RokrjMIw/J3WJbgMNxBsrAXBRpdgEYikE6yGQLDUDWhj+vSuQEilRcCpbKyt/xT/BGROsJlAijxPdYuZy53uvtw592Q+aXjJHDZ+62H1+fU9Ct+TXL85/7KqPia5THJfVd9W5/uQOUj9mB4Ex0nukiyq6mB1XJl7EfZW17Lc/NcD/N+EAgDvGmPcVNWPJJ+S7GbejL8mec5cqHb7h68dJjlLcpRkO3P4+DzJl7G2wGeMcVVVP5OcJjlIspX5RqKvSRbrg8hjjKeq2knyOcl+kpPMvyctk1xkLmwDYEMWrgHw1/xecDbGqH99LQBsxowCAADQCAUAAKARCgAAQGNGAQAAaDxRAAAAGqEAAAA0QgEAAGiEAgAA0AgFAACgEQoAAEAjFAAAgEYoAAAAjVAAAAAaoQAAADRCAQAAaIQCAADQCAUAAKD5BZG3RiRZ3B03AAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "image/png": {
              "width": 389,
              "height": 277
            },
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAwsAAAIqCAYAAABrIdadAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAWJQAAFiUBSVIk8AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdd3xUVf7/8ddJJQmp9JoAioAICFZAxa5gQUVxC4roura1rOu6RX/irnWLq+uuZXcVEOvq6pfFAooCIrqiYEMBRQlNQCGkkF7O749zJzOTTCBAksnMvJ+Px33ce88t85khJPczpxlrLSIiIiIiIg3FhTsAERERERFpn5QsiIiIiIhISEoWREREREQkJCULIiIiIiISkpIFEREREREJScmCiIiIiIiEpGRBRERERERCUrIgIiIiIiIhKVkQEREREZGQlCyIiIiIiEhIShZERERERCQkJQsiIiIiIhKSkgUREREREQlJyYKIiLQ4Y4z1lrwWvOci755T9/K66d51M1sqFhGRWKFkQUREREREQlKyICIiIiIiISlZEBERERGRkJQsiIiIiIhISEoWRETaKWNMvtcxd5wxpocx5hFjzEZjTLkxZpUx5gZjTFzA+ecbY5YYYwqNMcXGmFeMMUP38BqHGmOe9O5baYzZboyZb4w5bw/XxRljfmaM+cSL53tjzFxjzNHNfG9djDF3G2M+M8bsMsaUGmNWGmPuNMbkNO8Tahnee7nUGLPYGFNgjKkwxqwzxvzDGHPAbq7rZ4x52BjzpfcZlBlj1nsdsX9tjOkc4nWmGmMWGmN2GGOqvc/tc2PM48aY01r/3YqI7J2EcAcgIiJ71A94BugOFAOJwCDgPqA/8DNjzD3AzUAtUAakA+OB0caYI6y1XzW8qTHmcuBh/F8cFQJZwCnAKcaYJ4Gp1traBtclAC8AZ3tFNbi/J2cApxljJu/uzRhjxgJzAF9SUAXUAQd7yxRjzMnW2jV7/mj2jzEmFXgJ954BqnGfXx7wEy+WC621cxpcNxJYhPucfdeVAn295TjgI2BewGWzgR8G7BcBGUBnYIi3BJ4vIhJ2qlkQEWn//gKsA4ZbazNxD5i3eseuNsb8Bvg5cD2Qaa3NAA4B1uAe/u9seENjzGj8icILQB9rbbZ3/i2ABX4M/DpEPDfjEoU64CbvNbNxicsC4PGm3ogxJheYi0sUHgYOBFKANC/m14E+wIvGmPhmfDb76z5colAJXAGkW2uzgINwyUAH4GljzMAG1/0Jlyi8D4y01iZ5n0EacDhwPy4ZAMAYcywuUagFbgAyvNfpAPQEpgLvtM5bFBHZD9ZaLVq0aNHSDhcgH/fQXgBkhTj+pnfcAv8vxPFjvGMVQFIT174DxIe49i7veAnuwdZXnoar3bDA9BDXJQOfB8SV1+D4k1753U285yTgE++cSQ2OLfLKp+7l5zjdu25mg/I83MO7BX4a4rpUYK13/IkGx8q88iObGcMvvfNfC/fPlRYtWrTszaKaBRGR9u8Ra21hiPIF3roK9w15Q0txiUIyUN/23usTcLy3e7dt0MzIc693bUdccyafU3DfqFfiajyCWGsrcd+6N+I1+TkfVyMRKl6stVW4mg6Ak0Od04LOwdWsbAX+FSKWMuAP3u65DWo6ir11j2a+lu/8roH9TERE2jv9whIRaf8+a6L8O2+db63d1fCgtbYO2O7tZgccOhQwuG+6F4e6sbW2CFju7Y4MOOTb/tg7J5SQ9wRG4WoODPCZMWZrqAX4hXd+nybu01J872VJEwkTwFveOg3XNMnnVW/9hDHmHmPMUcaYxN281pu4pG4ksMgY82NjTM99DVxEpK0oWRARaf+2NFFeu4fjgecEPsh28dZFoZKMAJsanB+4/e1urtvcRLnvW3gDdNvNkuGdl7qb12gJvvfSVLzg/wwCzwfXV+NdXC3LzcB7QLEx5i1jzJXGmJTAm1jXwfxKoBzXPGw2sNkbdelhY8yh+/dWRERah5IFEZHYldzGr+f7m1NkrTXNWMa1UVwd9vYCa+0OYCyuqdRfcSMfJeGadz0ErDTG9G5wzeO4ka2ux40GtQPXb+IKYLnXUV1EpF1RsiAiEnu+99YpxpguuznP97D7fUCZb3t3TWiaOrbNW2cYYzJ3H2Kb8L2Xvrs5J/CBP/BzwDoLrLXXWWtH4oZA/SmuQ3p/Qvfp2GatfcBaOxFXU3EEbuhWA/zeGDNsn9+NiEgrULIgIhJ7PsL1VwB/R+cg3sP8KG93RcAh3/YIY0wGoR3XRPmHuDkZDNAeJiDzvZcjvc7XoZzgrUtxQ9E2yVq701r7D8BXQ9DU5+A731prP8B1+t6E+5s8tjmBi4i0FSULIiIxxlpbACz0dm9uYnSem3HNc3bh78wLbh6EYlwTpusaXmSMSQJubOJ1S4D/eLu/M8akhzrPu0+CMabjHt7K/noRNzJTJ+DyEDGk4vomALzo6wTtzcS8u0lNy711fTMv73MJybtvdcNrRETaAyULIiKx6Vbcg/JI4Flf+3pjTEev7fyvvPPusdb6hv3EWluKfzjR24wxP/d15jXG5OGa1OxuFKNf4ZrpDATeNcac5htFyDgHGmN+DqwGDmuRd9oEa+164B/e7j3GmMuNMcleLAOBV3BDzpYBdwRcmgGsNcb81hhziG9IVS+JOBH/JHjzA665yxjzgjFmojd0Ld413Ywxf8X1ZbDAGy3/TkVE9t3uvhkREZEoZa191xhzFa4z7vnAJGNMIe5B2DefwFPAPSEuvxc3S/HZwJ+Be40xu3CzP9cAk/HXIDR83XxjzGnA/wFDgdeAamNMMW5kocBv4G2IW7S0G4EBuI7KjwJ/M8aU4t4LuPkkfmit/bLBdbm4BOIOXPwlQCb+z+4b3KzaPgnAed6C934N7j373GKtXdlC70tEpEWoZkFEJEZZax/FPfQ/jRt+tSNQhPt2+3xr7Y9DzT9gra3BPfReC3yKSxBqcd/EH2etfXEPr/sBMAjX1OldXFOnLNw3+B/iRhc6zlrb1HwNLcabeO104DJgiRdDKrAeN1HbIdbaOQ0uKwbOAO4HluE6Pqfj+jV8APwWGGGtDRx29S+4z2sO8CUuUUgGNgLPAcdaa+9qhbcoIrJfjLVt8cWNiIiIiIhEGtUsiIiIiIhISEoWREREREQkJCULIiIiIiISkpIFEREREREJScmCiIiIiIiEpGRBRERERERCUrIgIiIiIiIhKVkQEREREZGQlCyIiIiIiEhIShZERERERCSkhHAHEK2MMeuADCA/zKGIiIiISHTLA4qttf1a+sZKFlpPRkpKSs7gwYNzwh2IiIiIiESvVatWUV5e3ir3VrLQevIHDx6cs3z58nDHISIiIiJRbNSoUaxYsSK/Ne6tPgsiIiIiIhKSkgUREREREQlJyYKIiIiIiISkZEFEREREREJSsiAiIiIiIiEpWRARERERkZCULIiIiIiISEiaZ6EdqKuro6CggJKSEiorK7HWhjskEQCMMSQnJ5Oenk5OTg5xcfp+QUREJJYoWQizuro6Nm7cSFlZWbhDEWnEWktFRQUVFRWUlpbSp08fJQwiIiIxRMlCmBUUFFBWVkZCQgLdu3cnLS1ND2PSbtTV1VFaWsrWrVspKyujoKCAzp07hzssERERaSN6Kg2zkpISALp37056eroSBWlX4uLiSE9Pp3v37oD/51VERERig55Mw6yyshKAtLS0MEci0jTfz6fv51VERERig5KFMPN1ZlaNgrRnxhgAdb4XERGJMXpCFZE98iULIiIiEluULIiIiIiISEhKFqR9U7MXERERkbDR0KnSMqwFWwe2FurqvO06f5mt88prg4+FKrN1UOeVYQEDJi54iQvcj2/+sYBzpt/+e27/3e9YuHAh48aNC/MHKCIiItL+KFmQ3bN1UFsFNVVuXVsFNZVuXVfjf7Bn/2sA8jd+S7+jzuDi889k5v23BwbhJRS1+/0aQXZtdesdX8P23pCdB/H6LyEiIiLioyejWGdtQBLgSwgq/dt11eGOsNVcc8lkLjz7VPr26g5VJVC0EXL6hTssERERkXZDyUK0sxZqq/0JQWAi4FtaSqimP3FNlYVoHrQr2d2nQyZ0G+qdYwDboGlTiGZL9U2amjiv0bE6Oufk0Dkn2x9/RSGU74SU7JBvT0RERCTWqINztCndDoUbYPta2PYFbPkEvvscdnwFheuhZCuUF0DVruYnCnGJkNQRUnKgY3fI6gudDoCuQ9xDffdh0GME9BgO3Q+BbkOg6yDoMtCdl9MfsnMhqw9k9oL0HtCxK6R1htQcSMli+j330e+ggwGYNftJTEISJj4eExfHzFlPsGjJO5jEZKbfeQ/LPv6cCedeSE7PfpjUHPK/K4G0Liz88Asu/8VtDDn6ZDL6HkxKz8EMPfYsbv/bU1Sk93UxdRsC3YdCj2FM/8f/YXqNZNGKL/3vtWgTxhjGjRvH9u3bufzyy+nRowfJyckcfPDBzJgxoxX+0URERETaJ9UsRJvyQtekZm/EJUJ8EiQkuXV8EiQke9uJ7lv/VjZu3DgKCwt54IEHGD58OBMnTqw/NmLECAoLCwF47733uPvuuxk7dizTpk1j+/btJCUlAXDvvfeyevVqRo8ezYQJE6ioqGDp0qVMnz6dRYsWsWDBAuLj4xu/eGpn9xnUVbt+GEBhYSFjxowhKSmJSZMmUVlZyfPPP8+0adOIi4vj4osvbvXPRERERCTclCxEm4QkaFhhEJcQkAT4EoJkf1k7mD163Lhx5OXl8cADDzBixAimT58edHzRokUAvP766zzyyCP89Kc/bXSPhx56iH79+jWaQOzWW2/ljjvu4IUXXmDy5MmNXzwu3tWWFHxdX/TJJ59w6aWX8uijj9YnGNdffz3Dhg3j3nvvVbIgIiIiMUHJQjuX96tXwh1Cs+XfM6HVX2PEiBEhEwWA/v37hyy/4YYbuOOOO5g/f37oZAGgQwakdoKyHQCkpnTgvj/eG1QTMWTIEMaMGcPbb7/Nrl276Nix4/69GREREZF2LvxfKYvshSOOOKLJY6Wlpdx1110cfvjhZGZmEhcXhzGGTp06AbB58+bd3zyjp2uOBBzYry8ZtrjRKX369AFg586d+/gORERERCKHahYkonTv3j1keXV1NSeccALLli1j6NChTJ48mS5dupCY6B7+b7/9diorK3d/87gE1xwJyMpM90ZHKoSUrPpTEhLcf5na2hae80FERESkHVKy0M61RdOeSNKwP4LPnDlzWLZsGVOnTm00YtGWLVu4/fbbQ17XSIeM4P2ijW4kKE3WJiIiIjFIzZCk3fD1D9iXb+3Xrl0LwLnnntvo2OLFi/chGi8pqauBok37cL2IiIhI5FOyIO1GdnY2xhg2bNiw19fm5eUB/lGTfL755htuvvnmvQ8mIdm/XbHTNUcSERERiTFqWyHtRseOHTnyyCNZsmQJP/rRjxg4cCDx8fGcddZZe7z2zDPP5IADDuC+++7js88+49BDD2XDhg28/PLLTJgwYe8TkLgENwldeYHb9zVHEhEREYkhShakXZk9ezY33HAD8+bN45lnnsFaS+/evetrDpqSlpbGW2+9xa9+9SsWLVrEkiVL6N+/P7feeis///nPee655/Y+mMxeUFnin6ytWM2RREREJLYYa224Y4hKxpjlI0eOHLl8+fLdnrdq1SoABg8e3BZhyd6qKIKCb/z72f2CRkeKJfpZFRERaZ9GjRrFihUrVlhrR7X0vdVnQWR3OmS65kg+RRuhtiZ88YiIiIi0ISULInuS2at+sjY1RxIREZFYEnHJgjFmkjHmQWPMEmNMsTHGGmOe3Mt7dDLGXGaMeckYs9YYU26MKTLGvGOMudQYE3Gfi7SiuATI6uPfL98J5UXhi0dERESkjURiB+dbgOHALmATMGgf7nE+8DCwBVgIbAC6AecC/wJON8acb9WhQ3w6ZEJKtksUAIo2QNJgTdYmIiIiUS0Sv0G/ARgIZABX7uM9vgTOAnpba39krf21tXYaLvHYCJyHSxxE/DJ6u1oG8JojbQ5vPCIiIiKtLOKSBWvtQmvtV/vzrb+19i1r7VxrbV2D8q3AI97uuP0IU6JRfAJk9vXvlxe40ZJEREREolTEJQttoNpba8gbaSzFa47kU7jR1TKIiIiIRCE1uA5gjEkALvJ25zXzmqYmUtiXvhQSCTJ6e5O11bgJ24o2Q3ZuuKMSERERaXGqWQh2DzAUeNVaOz/cwUg7FZ8AmYGjI6k5koiIiEQn1Sx4jDHXAjcCq4Epzb2uqZnyvBqHkS0TnbQ7KVlQng0V3uhIhRuha5q/A7SIiIhIFFDNAmCMuQZ4APgCON5aWxDmkCQSZAaOjuQ1RxIRERGJIjGfLBhjrgceBFbiEoWtYQ5JIoWaI4mIiEiUi+lkwRhzM/AX4GNcovBdmEOSSJOSBR2y/PsaHUlERESiSFQnC8aYRGPMIGPMgBDHbsV1aF4OnGit3d7mAUqbysvLIy8vL6hs5syZGGOYOXNms+8zdepUjDHk5+e7gsw+wc2RWmiytlDxioiIiLSliOuNaYyZCEz0drt766ONMTO97e3W2l94272AVcB6IC/gHhcDvwNqgSXAtcaYhi+Vb62d2bBQpBFfc6Sd69x+WQF0yIYOGbu9bNy4cSxevJj9mF9QREREpFVFXLIAjAAublDW31vAJQa/YPf6eet44PomzlkMzNyH+CSCnHPOORx11FH06NFj/26UkgXlWVBR6PYLN0DXQfs1OtKbb765fzGJiIiI7KeISxastdOB6c08Nx9oVGWwN/eQ6JaZmUlmZmYL3aw3VO3yT9ZW/C1k9d3n2w0Y0Kj1nIiIiEibiuo+CxI5/ve//2GM4ZxzzmnynMGDB5OcnExBQQFVVVX87W9/Y/z48eTm5pKcnExOTg4nnXQSr732WrNfd3d9FhYsWMAxxxxDWloaOTk5TJw4kdWrVzd9r9lPcd4Vv6H/0WeSMuBoMvoMYczRR/Hkk08GnZefn48xhsWLFwNgjKlfxo0bV39eU30WKisrueeeezjkkENITU0lIyODY445hn//+9+NzvW91tSpU8nPz+fCCy+kc+fOdOjQgcMOO4yXX365eR+UiIiIxKSIq1mQ6HTUUUdx0EEH8eqrr7Jjxw46deoUdHzZsmWsXr2a8847j5ycHLZu3cp1113H6NGjOfnkk+nSpQtbtmxh7ty5jB8/nn/+859cdtll+xzPCy+8wOTJk0lKSmLy5Mn06NGDd955h6OPPpphw4aFvObKK6/k4IMP5tjRR9GjcwY7dhby6ltLmTJlCmvWrOH3v/89AFlZWdx2223MnDmT9evXc9ttt9XfY08dmquqqjj11FNZvHgxgwYN4uqrr6asrKw+3o8//pi77rqr0XXr16/niCOOoH///kyZMoWCggKee+45zj77bBYsWMDxxx+/z5+ViIiIRDFrrZZWWIDlI0eOtHvyxRdf2C+++GKP58WCu+66ywL2wQcfbHTsqquusoD973//a621tqKiwm7cuLHReYWFhfbggw+22dnZtqysLOhYbm6uzc3NDSqbMWOGBeyMGTPqy0pKSmxOTo5NSEiwH3zwQdD5119/vQUsYNetWxd0bO3atW6jpsrabz+xdvMKW7nufXvCsaNtQkKC3bRpU9D5xx13nHX/BUMLFa/vMzr99NNtdXV1ffm2bdtsbm6uBezSpUvry9etW1cf7/Tp04PuNW/evPp7NYd+VkVERNqnkSNHWmC5bYVnWtUstHfTW6g9fVuYvn8Tkk2ZMoVbbrmFWbNmcc0119SXV1VV8eyzz9K1a1dOP/10AJKTk+ndu3eje2RmZjJt2jRuvPFGPvjgA4499ti9jmPOnDkUFBRw0UUXcdhhhwUdmz59OjNmzKCoqPF7re9jEJ8IWX1gZz5JSYlcPeUc3nr7Xd58800uuuiivY4n0OOPP44xhvvuu4+EBP9/365du3Lrrbdy2WWX8a9//YvRo0cHXZebm8stt9wSVHbqqafSt29fli1btl8xiYiISPRSnwVpN3r37s2JJ57Ihx9+yBdffFFfPnfuXAoKCvjRj34U9ID8+eefM3XqVPr3709KSkp9u/8bb7wRgM2b922+gxUrVgBw3HHHNTqWmZnJiBEjQl63YcMGrr76agYNGkRqp16YXiMxvUZy3k9ucvFs2rhP8fiUlJSwdu1aevbsyaBBgxodP+GEEwD46KOPGh0bMWIE8fHxjcr79OnDzp079ysuERERiV6qWZB2ZerUqbzxxhvMmjWLe++9F4BZs2YBcPHF/hFz//e//3HCCSdQU1PDiSeeyFlnnUVGRgZxcXF8/PHHzJkzh8rKyn2KwVdr0K1bt5DHu3fv3qjsm2++4YgjjmDnzp0cc8wxnHLKKWSmdyS+Yif5Gzcz6/m5VBbv37x/vriaGubVV15YWNjoWFZWVqMygISEBOrq6vYrLhEREYleShbau/1s2hNpzjnnHDIyMnjyySe566672LFjB6+99hrDhw9n+PDh9efdcccdlJeXs3DhwqARhADuvvtu5syZs88x+IZS3bZtW8jjW7dubVR23333sWPHDmbMmMHUqVP9B8oKeGbmo8x6fi5Ul0FF8R4na9tTXKFeH2DLli1B54mIiIjsLzVDknYlJSWFCy64gG+//ZYFCxbw9NNPU1NTE1SrALB27VpycnIaJQpA/ZCk+2rkyJFN3qeoqIiPP/64UfnatWsBOO+884IPpGSz+IPP/PuFG6C2BqC+WVBtbW2z4kpPT2fAgAFs3ryZr776qtHxhQsXBsUvIiIisr+ULEi74/tm/oknnuCJJ54gISGBH/3oR0Hn5OXlUVBQwKeffhpU/thjjzF//vz9ev2zzz6b7Oxsnn76aT788MOgY9OnTw/Zudk35OmiRYuCyue//jr/mh0w/0FdNRSuB2vrh4fdsGFDs2ObNm0a1lpuuummoCRj+/bt9UOzTps2rdn3ExEREdkdNUOSdmfMmDEccMABPP/881RXV3PmmWfStWvXoHOuv/565s+fz9ixY7ngggvIzMzkww8/5J133mHSpEm88MIL+/z6HTt25B//+AeTJ0/mmGOOCZpnYeXKlRx77LG8/fbbQddcddVVzJgxg/PPP59JkybRs2dPVq5cybx587jgggt47rnn/CdXFkPpdk488USef/55zj33XMaPH09KSgq5ublMmTKlydh+8Ytf8NprrzFnzhyGDx/O+PHjKSsr4/nnn+e7777jl7/8JWPHjt3n9y4iIiISSDUL0i5dfPHFVFdX1283dNpppzF37lyGDBnCc889x2OPPUZycjILFy5kwoQJ+/36kyZNYt68eYwaNYp///vfPPLII+Tk5PDee+/Rr1+/RucPGzaMhQsXMnr0aF555RUefvhhiouLefHFF7niiivcSYlp/guKN3PZRT/k17/+NUVFRfzhD3/g1ltv5bHHHtttXElJSbzxxhvceeedADz44IPMmjWLAw88kKeffrq+U7iIiIhISzDWTSAmLcwYs3zkyJEjly9fvtvzVq1aBcDgwYPbIiwJJ1sH338JNeVuPz4ZuhwEcY2HNG2P9LMqIiLSPo0aNYoVK1assNaOaul7q2ZBpK2YOMjOc2uA2koo2hTWkERERER2R8mCSFtK7ACZATNPlxdAWUH44hERERHZDSULIm0tJQdSsv37RRuhZt8mkBMRERFpTUoWokxFdS1FZVV8V1xBTa1m5m2XjIHMPhCf5PZtHezMd2sRERGRdkTJQpTZtLOc9QVlbC2uoKK6eZN9SRjExbv+Cxi3X10GxVvCGZGIiIhII0oWokxygv+ftLJG31S3a0lpkNHDv1/6HVQUhy8eERERkQaULESZpIBkoUrJQvuX1hWS0/37heuhtjp88TRBQyyLiIjEJiULYWaMa4ZSV9cyD/aqWYgwxkBWLsR5k6nX1cDO9dDOHs59yYLv51VERERig5KFMEtOTgagtLS0Re6XpGQh8sQnuoTBp6oEdn0XvnhC8P18+n5eRUREJDYoWQiz9HTXBGXr1q2UlJRQV1e3X00+AmsWqmr3717ShjpkQMeu/v2SLVDVMgnkvrLWUldXR0lJCVu3bgX8P68iIiISGxLCHUCsy8nJobS0lLKyMjZtapnZfGuqa8HLEVYVxanpSMSwUIN/CNXtayChg2uq1A6kpqaSk5MT7jBERESkDSlZCLO4uDj69OlDQUEBJSUlVFZW7ndtwLeF5ZRWumFT+3VOI72D/pkjg3HL9rVgvWFvU7K9IVbDFJExJCcnk56eTk5ODnFxqowUERGJJXqKbAfi4uLo3LkznTt3bpH7PbbyE15Y7mopfn92d6Ycmtci95U2svJreOFy//5Zf4ORU8IXj4iIiMQsfU0Yhfp1Tqvfzt9RFsZIZJ8MPQ8ODUgOXvslfL8mfPGIiIhIzFKyEIXyOgUkC9vD20lW9tHp90LngW67ugxemAbVFeGNSURERGKOkoUolNc5tX573Q4lCxEpKQ0mzYB4b6jSbSvhjVvDG5OIiIjEHCULUSg3oGZhY0EZNbWabyEidR8Kp97p31/2D1j9SvjiERERkZijZCEKdUxOoEu6+0a6utbybaGar0Sswy+DQWf49+dcDUWbwxePiIiIxBQlC1GqX0DtgpoiRTBj4KwHIaOX2y/fCS/+BOpqwxuXiIiIxAQlC1EqsN+COjlHuNQcOO9fYLz/ruuXwtt/DG9MIiIiEhOULESpvIDhU9cpWYh8uaPhuJv9+4vvhfyl4YtHREREYoKShSgV2AwpX82QosOxN0HuGLdt61xzpLKC8MYkIiIiUU3JQpQKrFlQM6QoERcP5/4TUrLdfvFmmHMNWBveuERERCRqKVmIUoETs23cWU61hk+NDpm94Oy/+/fXvAIf/Ct88YiIiEhUU7IQpVKS4ume0QGA2jrLpp3lYY5IWsygCXDE5f79+b+FrZ+FLx4RERGJWkoWophGRIpiJ/8euh3itmsr4YVpUKV/YxEREWlZShaiWD+NiBS9EjvApMch0UsIt38Jr928+2tERERE9pKShSiWpxGRoluXgXD6H/z7H82Glf8JXzwiIiISdZQsRLGgEZF2lB0ElhcAACAASURBVIUxEmk1h/4Yhp7n3597PezMD1s4IiIiEl2ULESxfho+NfoZA2f8BbJy3X5lMTw3BYq3hDcuERERiQpKFqJY35xUjHHbm3aWUVWj4VOjUodMmDQD4hLc/tZP4ZGx8PVb4Y1LREREIp6ShSjWITGenpkpANRZ2LhTTZGiVu9RMP5PYLz/0mXbYfa58NadUFcb3thEREQkYilZiHK5nTR8asw47BK46L/QsZtXYOHtP8ATZ0PJ1rCGJiIiIpFJyUKUy9PwqbGl3zFwxTvQ7zh/Wf4SeOQY+GZR2MISERGRyKRkIcr10/CpsadjV5jyEoz7DeB1Win9Dp6YCIvuUbMkERERaTYlC1EuaPjU7eqzEDPi4mHczXDRHEjr6hVaWHQ3zD4Hdn0X1vBEREQkMihZiHL9Ovv7LKgZUgzqf5xrlpR3jL9s3WI3WtK6JeGLS0RERCKCkoUo1ycnlTivJcq3ReVUVKsJSsxJ7+ZqGI67mfpmSbu2wRNnweI/Qp2G1BUREZHQIi5ZMMZMMsY8aIxZYowpNsZYY8yT+3iv3saYx40x3xpjKo0x+caY+40x2S0dd7gkJ8TTM8sNn2otbCxQU6SYFBcPx/8GprwIqZ1dma2DhXfAk+fCru/DG5+IiIi0SxGXLAC3ANcAI4DN+3oTY8wAYDlwCbAM+AvwDXAd8J4xptP+h9o+9NOISOIz4ATXLCl3jL/sm4Xw6DGQvzR8cYmIiEi7FInJwg3AQCADuHI/7vMQ0BW41lo70Vr7K2vtCbik4SDgzv2OtJ3I04hIEiijh5uP4Zhf+MtKtsCsM2DJn9UsSUREROpFXLJgrV1orf3KWmv39R5ercIpQD7w9waHbwNKgSnGmDSiQPBcC2qGJEB8Apx4K/z4P5DqVaLZOnjzd/D0+VC6I7zxiYiISLsQcclCCzneW79urQ36GtVaWwIsBVKBo9o6sNYQOCKSZnGWIAecBD9dAn2P9petXeBGS9rwv/DFJSIiIu1CrCYLB3nrL5s4/pW3HrinGxljlodagEEtEWhLUDMk2a3MXnDxyzD2Bn9ZybcwYzy8c7+aJYmIiMSwWE0WMr11URPHfeVZbRBLq+uTk0q8N37qlqIKDZ8qjcUnwEnT4YfPQ4o3GJithQW3wTMXQllBOKMTERGRMInVZKHFWGtHhVqA1eGOzScxPo7e2Sn1++t3qN+CNGHgKW60pN5H+Mu+mg+PHAMbl4UvLhEREQmLWE0WfDUHmU0c95UXtkEsbSKwKZKGT5XdyuwNl7wKo6/1lxVvghmnw7sPugk7REREJCbEarKwxls31SfhQG/dVJ+GiJPXKaCTs/otyJ7EJ8Ipv4cfPAsdvNZ4dTXw+i3wzA/ULElERCRGxGqysNBbn2KMCfoMjDHpwBigDIia4WACh0/ViEjSbAedDlcsgV6H+cu+fA0ePQ62fR6+uERERKRNRHWyYIxJNMYM8uZVqGet/Rp4HcgDrm5w2e1AGjDbWhs1T9V5msVZ9lVWX7jkNTgq4L9K0QbXLEnDq4qIiES1hHAHsLeMMROBid5ud299tDFmpre93Vrrm5q2F7AKWI9LDAJdBbwL/NUYc6J33pG4ORi+BH7bGvGHSz8Nnyr7IyEJTrsLckfDS1dAVQlUFMETE+GCWTDw1HBHKCIiIq0gEmsWRgAXe4vvCaV/QNmk5tzEq104DJiJSxJuBAYADwBHWWujagrb3tkpJHjDp24rrqSsqibMEUlEGnwGXPIKpHVx+zXlrg/DJ8+GNy4RERFpFRGXLFhrp1trzW6WvIBz8xuWNbjXRmvtJdbaHtbaJGttrrX2emvtzrZ6P20lIT6OPjmBMzlr+FTZRz2Gw7T5kJXr9m0tvPRTeO/v4Y1LREREWlzEJQuy7zQikrSYTgPg0teh68H+svm/gQXTNbSqiIhIFFGyEEPUyVlaVHp31ySpz1H+snf+Av/9GdSqmZuIiEg0ULIQQ/pp+FRpaSnZMOUlGHiav+yj2fD8xVBdEb64REREpEUoWYgheRoRSVpDUipMfhKG/8BftvpleGoSVBSHLy4RERHZb0oWYki/oGZI6uAsLSg+Ec5+CI6+xl+WvwRmToBd34UvLhEREdkvShZiSM+sFJLi3T/59l2VlFRUhzkiiSpxcXDKHXDS7f6yrZ/C46fCzvywhSUiIiL7TslCDImPM/TJSanfX79DtQvSwoyBsdfDWX8D4/16KfgGHjsFtq4Mb2wiIiKy15QsxJigTs7qtyCtZeQUuGA2xCe7/V3bYMZ4WP9eeOMSERGRvaJkIcYEdXLWiEjSmgafAVNehOQMt19ZBLMnwpp54Y1LREREmk3JQozJVSdnaUt5Y2Hqy5DWxe3XVMCzP4SPnwlvXCIiItIsShZiTD8NnyptrcdwmDYfsnLdvq2F/7sC3n0wvHGJiIjIHilZiDF5nVPrt9UMSdpMpwFw6evQbai/7PVb4I3bwNrwxSUiIiK7pWQhxvTMTCEpwf2z7yitoljDp0pbSe8OU1+Bvkf7y5beD/+9BmprwheXiIiINEnJQoyJizPk5qh2QcIkJQumvAQDT/eXffQk/PsiqC4PX1wiIiISkpKFGJQX1MlZyYK0scQUmPwkDP+hv2zNK/DkeVBRFL64REREpBElCzEoaK4FjYgk4RCfABMfgtE/85etXwozJ8Cu78IXl4iIiARRshCD8jQikrQHxsApd8DJv/OXbf3MzfZcsC58cYmIiOyr6grY8XW4o2hRCeEOQNpe4IhIaoYkYTfmOkjtBP/9Gdg62LkOHj8VfvwidB+65+tFRETamrVQshW2rXTLVm+9/Sv3N+2mr8IdYYtRshCDgpohqWZB2oNDfwwp2fD8JVBbCbu2wYzxMPY6yB0DPQ+FhORwRykiIrGophK+X+MlBp+7WvBtK6FsR+jzS79zTWo7dm3bOFuJkoUY1C29Ax0S46iorqOwrJrCsiqyUpPCHZbEukET3EhJz1wIlcVQWQRvek2UEjpAr1Fu2NXco6HPkZCcHt54RUQk+pRsa1Bb8DlsXwN1ezHEd3Y/96WXkgWJVHFxhrxOaazeWgK4pkiH9lWyIO1A3hg3F8NTk9wvWp+aCtcBev1SWAKYOOh+CPQd7ZKHvqOhY5ewhS0iIhGmpgq2f+mSgW2f+ZsRlX7f/HskdYRuB3vLUPd3qesQSO7YenGHgZKFGBWYLKzfUcahfbPDHJGIp8cwuHoZrH4Z1r8HG96Fgm+Cz7F1sOUTt7z/sCvrdIBX8zDarbPzXCdqEZFoUVPlal4ritzaxENmb9eMU7/v/KyFql1QvhPKC6Gi0G0XbvCaEa2E71dD3V5MTJuV65KBbkNdctB9KGTlQVz0jxWkZCFGaa4FaddSslw/hkN/7PZLtsKG9/zJw9aVgA2+Zsdat3w02+2n9whOHroOiYlf6iLSTtXWeE0si6Gi2P/QXxFQVlHY4HhAYlBRDDVNTF6ZmAZZfSCzj7fuDZl9/WXp3SEuvm3fb0uorvA/6Jd768D9kMe88r1pNhQoMdX9veg+NLi2oENGy763CKJkIUb1CxgRSZ2cpd1L7w4Hn+MWcH88Ny6D9e+6JGLzcqitCr6mZAt8/qJbADpkQp+j/M2Weh4KCWp+JyItaNf3rlZ07QLXwTXwwb9qV+u9bnWp+6b8+9Whj8clQEbP4AQiMKnI7A2JHVo2JmuhqrRx8tMoYSqGyhL/g35gQlBT0bIxNZTZ119L4EsMsvMiM7FqRUoWYlTQXAuqWZBI0yETDjzZLeC+ffp2hT952PA+VJUEX1NRBF/Ndwt4naYPg4MnwqhL3ERxIiJ7q2QrrJoLX8xx/apsXeu9lomD5Az3LXeHTKithqJNe05E6mpcE5zCDbC+iXPSugYkEH0gq69XK9HNjQYUWBtS6XvAb5gE+MqK3HZrfhZ7kpgKHbJcTXVKtttO6+zvX9DtYHdM9kh/HWNUw2ZI1lqM2jtKpErs4Job5Y52+3W1rqOar9nS+vfcUHaBaipg/Ttu+ehJOOtB119CRGRPijb5E4QN/6NRs8iQTPCDvm87aJ0ZvN2wLCmtcd8Ea9238EUboXCji61oo0sMfGVl2/ccXul3btm8fF8+kdYRl+B/0E/Jdg/3gdu7O6bhtluMkoUY1TU9mdSkeMqqaimuqGFnWTU5aWqSIVEiLh56DHfLUVe4P6YF3/hrHta/6yZ/89nyMfxjHIy5Fo67GRJTwha6iLRTO/Phi//Cqv/Cpg+aOMm4PlJDzoIeI4ITg6SOrdNvyhhIzXFLj+Ghz6kud0lEYAJRn1RshOLNYGtbPraElAYJUXrAdqbbD0yOGj70h0qOpM0pWYhRxhhyO6Wxaksx4GoXlCxI1DIGOg1wy8gprqx4i6tRePuPbiI4Wwvv/MV9U3jmA9Dv2PDGLCLht+Nr9zvhiznuS4VQTJybPHLI2TD4TNfHqr1JTIHOB7ollNoa18+rYa1E0SY3jHViWoiH/Ya1IoHHvUQgPrFt36e0CiULMaxf59T6ZCF/eymjcjV8qsSQjB5w3E2uz8Lc61xbY3A1ELPOhJEXwcm/c99uiUjs+H6NP0HYtjL0OSYe+h/nEoSDJkT+PC/xCa6/QlYf4OhwRyPtjJKFGBbUyVkjIkms6nwgXPwyfPQEvP7/XMc8gBVPwJp5MP6P7oFAVeEi0claN/b+F3NcE6MmRxRKhAHHewnCeNfsRyQGKFmIYZprQcQTFwejpsKBp8JrN7mOi+A6+z1/sfvmcMKf3NCDIhL5rHWTOvpqEAq+Dn1efDIccJJLEAaeqtFzJCYpWYhh/TqrZkEkSEYPmPyk68T46k2wa6srX/MK5C+Bk6a7YVY1uZtIZNr+FayY5RKEwg2hz0lIgYGnwOCzXIKQnN62MYq0M0oWYljwXAtlGj5VxGfIWa6D84LbYPlMV1ZZDK/8HD57Hs78K3QZGNYQRWQvVFfAkj+7QQzqqhsfT+roEoMhZ7uahKS0xueIxCglCzGsc8ckOiYnsKuyhl2VNWzfVUWXdI1LLAK45gZnPgCHXABzr4Uda135hvfgkTFw7E0w5nrNAi3S3uW/4wYx8P0f9knOcH0PhpwNA05o+RmMRaKE6tJjmDGGvM6p9ftqiiQSQt4YuGIpHPMLN0EQQG0VLLwTHj0WNjY13rqIhFVZAcy5BmZOCE4Ueh8BP/w33LQWzn0UBo1XoiCyG0oWYlxgUyR1chZpQmIHOPFWuHwx9BzpL/9+FTx2Mrx2M1SWhC8+EfGzFj57Af5+BHw021+enAET/gzT5rsmR5rhV6RZlCzEuKBOzkoWRHav+1C4bAGcejck+mrlLLz/CPz9KPhyfljDE4l5O9fDU+fDfy6F0u/95YPPhKvfh8Mv0wAFIntJ/2NiXGDNwvodZWGMRCRCxMXD0VfBVf+DASf6y4s3wdMXwAuXwq7vm75eRFpebQ28+zd46ChY+4a/PL0nTH7KjXKmoY9F9omShRinuRZE9lF2Lvz4P3DuPyElYHKmlS/A3w+Hj592zSFEpHV9+zH86wR4/bdQ7fvSy8ARl7vahMFnhDU8kUinZCHGNZxrwerhRqT5jIFhF8A1H8Cwyf7y8p3wf1fC7IlQsC588YlEs6pSmP9b+OfxboI1n65D4NI33OzrHTLCF59IlNDQqTEuOzWR9A4JlFTUUFZVy/cllXTN0KgQInslrTOc+w+XOMy9AYq8yZ6+WQQPHQ1jroWc/q6fQ1IqJKZ569TgMg3DKtI8Xy2AlwP+r4GbbXnczTD6WohPDF9sIlFGyUKMM8bQr3Man24qAlxTJCULIvvogJPgqvdg4V3w/sNg66CmHBbf27zr4xICEomU4KQiKS0gsUhtnHgkZ0DuGOjYpXXfo0g47foO5v3aNfcL1O9YOON+6DQgPHGJRDElC0JeJ3+ykL+jlCP7dwpzRCIRLLkjnHYXDD0P/vsz+O7z5l9bVwOVRW7ZFyYeDjzZNYk6SGPHSxSxFj56El6/BSoK/eUp2XDqXTD8B65ZoIi0OCUL0qCTs0ZEEmkRvUfBTxe7B5xvP3IdL6vLXTvr6jKoKoPqUm9d7rbravbvNW0tfDnPLcmZcPDZ7iGqz1EaLlIi1/a18PL1kL8kuHzYZJcopHUOT1wiMULJgtAvcBZnjYgk0nLiE+GwS4BLmnd+TVVAAlEWIqkILCsLTjx2fAUb3/ffq7IIVjzhlqxc92A1/EI105DIUVMFSx+At/8ItZX+8qxcOOMvcMCJTV8rIi1GyYIEzbWQv0PJgkjYJCS5JSV7364vWAef/hs+eQZ2BozCVLge3v6DW3of7pKGg8+F1Jym7yUSThveh7nXuVnSfUw8jL4GjvuV66cjIm1CyYI0Gj61rs4SF6e2nyIRJ6efGw3muF/Cpg9c0rDyP1AR0Adi0wduee1XMPBU10zpwFM0EpO0DxVFsOB2+PBxIGAo756Hwpl/hR7DwhaaSKxSsiBkpSaRlZpIYVk1FdV1bCupoEdmSrjDEpF9ZQz0OcItp90DX86HT56Fr16Hump3Tl01rH7ZLSnZrkP2sAuh92HqKCptz1pYNRde+yWUbPGXJ6bBibe6Cdbi4sMXn0gMU7IggGuK9HGZG2Fi3fZSJQsi0SIhGYac5ZbSHfD5iy5x2Pyh/5zynfDBv9ySM8A1Uxp2AWTnhS1siSFbPnGTqzXswHzgqTDhz5DVJzxxiQigGZzFE9QUSSMiiUSntE5wxE/gJ2/CNR/CMb+AzL7B5xR8DQvvhAeGw4zxsHxWcDMmkZZS/C3831Xw6HHBiUJaV5g0A374nBIFkXYgIpMFY0xvY8zjxphvjTGVxph8Y8z9xpi96hVojBlrjJnjXV9hjNlgjHnVGHNaa8XeXqmTs0iM6Xyga95x3Scw9RU4dAokpQefs34pzL0W/jQQnp/qmjPVVoclXIkiVaWw8G54cBR8/BT1fRNMPBx+GVyzDIaeq+ZwIu1ExDVDMsYMAN4FugJzgNXAEcB1wGnGmDHW2h3NuM+VwENAKfASsAnoDZwLnG6MucVae2frvIv2Jy9g+NR1Gj5VJHbExUHeWLeM/yOsedU1U1r7ppu3AaCmAj5/yS2pneGQSW4o1p6H6oFOmq+u1nW6f/P3sGtr8LGBp8HJv4MuB4UnNhFpUsQlC7gH/K7AtdbaB32Fxpj7gBuAO4ErdncDY0wicDdQAYyy1q4JOHYX8BHwW2PMn6y1lU3cJqoENkNar5oFkdiUmOI6Og89D3Z9B5+94B7utn7qP6dsO7z/iFs6HwTDJ8MhF6i5iOzeN4tg/i2w7bPg8m6HwKl3QP9xYQhKRJojopohebUKpwD5wN8bHL4NV0swxRiTxu7lAJnAl4GJAoC1dhXwJZACdGyBsCNCXlCyUEZdnd3N2SIS9Tp2haOvgiuWwJXvwZjrIL1n8Dnb18Cbv4P7h8LMM2DFbKgoDk+80j59/yU8PRmeODs4UejYHc7+u5vlvP+4cEUnIs0QaTULx3vr1621dYEHrLUlxpiluGTiKODN3dznO+B7YKAx5kBr7Ve+A8aYgcCBwMfNbM60vIlDg/Z0bXuS0SGRTmlJ7CitorKmji3FFfTK0ohIIgJ0G+KaiJx4G6x7Gz59Dr74r5tZ2id/iVte/QUcNN7N3zDgBIiPtD8z0iJKt8Oie9x8Cb7mbAAJKS7xHP0zSI6Z7+NEIlqk/Rb3NWb8sonjX+GShYHsJlmw1lpjzNXAk8ByY8xLwLdAL+Ac4HPgwpYKOlLkdkplR2kVAPnbS5UsiEiwuHgYcLxbJvwZVr/i+jd8sxB839/UVLjhWT9/EdK6wNBJrqlSjxHq3xALqitg2aPw9p+gMrCWycCIH8IJt0BGzyYvF5H2J9KShUxv3dQ4fr7yrD3dyFr7vDHmW+AZ4KKAQ9uAGcA3zQnIWjsqVLlX4zCyOfdoL/I6p7Fig3+uhTEHdA5zRCLSbiWlubkYhl0AJVvhs+fhk+eCm5qUfg/vP+wW9W+Ibta6BHHBdCjcEHws7xg49U7oMTwsoYnI/omoPgstyRjzY2ABsAQYDKR66zeBvwHPhi+68OgXOHyqRkQSkeZK7+6alVz5Dlz5Loy+FtJ7BJ9T37/hENe/4aMn1b8hWmxcBo+dAi9MC04UOh0AFz4DF89VoiASwSKtZsFXc5DZxHFfeeHubuL1S3gc+BSYEtD/YbUxZgquudP5xphx1tpF+xdy5Ajs5Ky5FkRkn3Q7GE75PZw03fVv+ORZWDU3oH+D9fdveOVGGDQBhl2o/g2RaGc+LLjd1SgESsmBcb+Gwy6B+MSwhCYiLSfSfjP7Ri4a2MTxA711U30afE4BEoHFITpK1xlj3gZGecuifQs18gQOn6q5FkRkvwT2b6i6D1a9DJ8+64bQDOzfsPI/bqnv33Ch+xZa/Rvar4oiWPJn+N/DUFvlL49PgiN/6mYGT9lja2ARiRCRliws9NanGGPiAh/0jTHpwBigDPjfHu6T7K27NHHcV17VxPGoFFizsLGgnNo6S3yc/mCLyH5KSnP9FYZPhuItsPIFV+OwbaX/nMD+DV0Gu46wgyYoaWhPaqth+UxYdDeUNRgscMhEV5uU0y8MgYlIa4qoPgvW2q+B14E84OoGh28H0oDZ1tr6r8WNMYOMMQ2HMV3irScZY4YFHjDGjAAm4eaff6vlom//OiYn0Lmjy6Oqauv4trA8zBGJSNTJ6OH1b1gKVyx12x27B5/z/Sp47kfw1Pmw4+vwxCl+1sKaefDwaDc0bmCi0OswmDYfLpilREEkSkVazQLAVcC7wF+NMScCq4AjcXMwfAn8tsH5q7x1/ddT1tplxpgZwCXAB97QqetxSchEIAm431r7eSu+j3apX+dUtu9yk1av215Kn5zUMEckIlGr+1DofgecdDusW+xGUwrs37D2DXhoMYy5HsbeAEn6fdTm1r8Lb90B65cGl2f2hZNuc7N9q/ZHJKpFVM0C1NcuHAbMxCUJNwIDgAeAo5ozkZrnUlyy8B5wqnefk4F3gB9Ya29o2cgjQ14ndXIWkTYWF+86OJ/7KNywEg67lPrvd2qr4O0/wENHwupX3bfc0vo2LYfZ58CM04MThaR019zomg/gkElKFERiQCTWLGCt3Yh70G/OuSF/k1lrLS7hmNligUWBPHVyFpFwSs2BM+6DkVPcaEmbl7vywg3w7A/gwFPh9Hsgp39444xWWz+DhXfBmleDy+MSYOTFbpSjjk119xORaBSRyYK0nsARkTTXgoiETc9D4dIF8NFsN9FXeYEr/2q+G1FprNc0KVEzzbeI79e4jsufvxRcbuJg+A/g2JvUJ0EkRkVcMyRpXcHNkMrCGImIxLy4OBh1MfxsOYy6BH/TpEpYfC/8/UhY81pYQ4x4BevgpSvgoaMaJwpDz4Orl8HEh5QoiMQw1SxIkLzO/g6EGwvKqKmtIyFeOaWIhFFqDpx5P4y8yDVN+naFKy9cD89cCANPg9Pu0QPt3ijaBG//0c2kXVcTfGzQGa65Ufeh4YlNRNoVPQVKkNSkBLpluOFTa+osmzV8qoi0F71GwmVvwpkPQEq2v/zLea6WYdE9UK3fWbtVsg1euxn+eqibMyEwUTjgJPjJW3DhU0oURKSekgVpJLApkjo5i0i7EhcHo6bCz1a4dWDTpEV3u+Y0X84PY4DtVFkBvPH/4IHh8P4jwTMv546FS+bBj/8DvUaFL0YRaZeULEgj6uQsIu1eao6rYbjsTdcZ2mdnPjx9ATzzA7cd6yqK3OhG9w+DpQ9ATUDNS6/D4KI5MPVlyD06fDGKSLumPgvSSK46OYtIpOg9yiUMK2bBgtuhotCVr3kVvn4LjrkRRl8LiR3CG2dbq9wFyx6FpX/1fyY+3Q+BE26FA0/RPAkiskdKFqSRfgGdnNUMSUTavbh4OGwaDD4b3pwOK55w5TUVsPBO+PhpGP9HOPDksIbZJqrL4cPHYcl9ULY9+FiXQXD8b2DQma45l4hIMyhZkEYCJ2bTLM4iEjHSOsFZD8KhF8GrN8KWT1z5znXw1CQ3ys+pd0F2bnjjbA01VfDRE/D2n6BkS/Cx7H4uSRh6nkusRET2gpIFaSQ3x58sbNpZTnVtHYkaPlVEIkWfw+EnC2H5DHjzd67dPsDql2Htm3Cs1zQpIXn396mrg+oyt1TtgqpSqPK2q8u8/V1eWSlUl3plAQsW4pMhPtG9XtB2klua3E7yzg/YTvCOBW5//RYsuheKNgTHn9kHjvulm1QtPrFVPmoRiX5KFqSRlKR4emR2YEtRBbV1lo0FZfTv0jHcYYmINF9cPBx+GQyZ6GaA/mi2K68ph7fucE2Teh/e+OG+/oG/zG1Hoo7d3IzLIy/ac0IkIrIHShYkpLxOaWwpqgBcUyQlCyISkdI6w9l/80/otvVTV17wjVuiSWonGHsDHHYpJKXu+XwRkWZQsiAh5XVO471vdgCwbrtGRBKRCNfnCLh8kev8+9bv/U2T9iQx1S1Jaf4lMRWSOnr73nbDc5LSIDHNTQNRWw01lW5dW9lgu8rNedBwu/4aryxo23eOt52UCiN+CEdeAcnprfghikgsUrIgIQWOiKS5FkQkKsTFwxE/gYPPde3862qCH/iDEgEvSVCHYBGJcUoWJKS8ThoRSUSiVFonGHZ+uKMQEYkIGuJGQgqcxVlzLYiIiIjEJiULElKfnNT6iT2/LSynsqY2vAGJiIiISJtTsiAhdUiMp2dmCgB1FjYWqJOziIiISKxRsiBNCmyKlK8RkURERERijpIFaVJe4IhI6uQsIiIiEnOULEiTAkdEUidnERERkdjTJkOnGmMGAacDZcCz1tpmzoYj4aThU0VERERiW4vWLBhj/p8xZosxJieg7CTgI+BPwEPACmNMp5Z8XWkdeeqzICIiIhLTWroZ0unAamttQUDZ3YAFbgMeBvoB17Xw60or6JuTSpxv+NSiciqqNXyqiIiISCxp4ICfmgAAIABJREFU6WQhD1jl2zHG9AJGAQ9Za++w1l4DvAVMbOHXlVaQlBBHr2w3fKq1sEHDp4qIiIjElJZOFrKBwFqFMbhahZcDypYDfVv4daWVqJOziIiISOxq6WThe6BXwP7xQDXwfkBZUiu8rrSS4LkWlCyIiIiIxJKWHg3pY+AsY8xQoAKYDLxjrS0POCcP2NLCryutRCMiiYiIiMSulv6G/w9AJvAJsMbb/rPvoDEmHtc06cMWfl1pJYE1C2qGJCIiIhJbWrRmwVq7xBhzBvATXF+Fp6y1rwWcMhrYDLzUkq8rrUfDp4qIiIjErhaflM1aOw+Y18SxJcChLf2a0np6Z6cQH2eorbNs/f/t3Xl8XHW9//H3Z7LvSdOm+166SMvSFlooBcuOiCCyKAIKchVFQOV69XfdQLzXuwkKLhdRFotXBFQ2RUDKVnZaLLa0lO5rkiZp9mSyfX9/nJPJJJ0sTSaZzOT1fDzyOJnvOXPmEw6Tzjvf8/1+qxvV0NSqjNSkWJcFAACAITBkA43NrMDMsno/EsNJSlJAk/3pUyXGLQAAAIwk0V7B+TQz+y8zKwhrKzKzFyWVSaows9ui+ZoYfNOYEQkAAGBEinbPwvWSLnTOHQxr+x9JyyVtlVQu6UYzuyTKr4tB1HlGJMYtAAAAjBTRDgtHS1rd/sDMMiRdJOlZ59xsSXMk7ZZ0bZRfF4OItRYAAABGpmiHhSJJ+8IeL5GULuk+SXLO1chbzXlOlF8Xgyj8NqTtjFkAAAAYMaIdFoKSMsIeL5c3hepLYW3VkkZF+XUxiKYVZoa+p2cBAABg5Ih2WNgu6dSwx5+Q9IFzbm9Y22R5g50RJybmZyg5YJKk0pqg6oItMa4IAAAAQyHaYeF+SQvM7A0ze1nSAkn/1+WYo+St7ow4kZwU0JRRYb0L3IoEAAAwIkQ7LPxC0oOSFktaJm98wn+27zSz+fICxAtRfl0MMlZyBgAAGHmiuoKzc65Z0mVmdq330NV0OaRY3grOO6L5uhh8nadPpWcBAABgJIhqWGjnnKvupr1MjFeIS9NHd9yGtJ1BzgAAACPCoIQFM8uUdKG8XoR8SVWS1kr6k3OOT5pxiFWcAQAARp6ohwUz+4i8gc6jJFnYLifpdjO7yjn3ZLRfF4OL25AAAABGnqiGBTNbKOmPkpIk/VbSKkn7JY2XN6XqpyQ9YmbLnHNrovnaGFwT8jOUmhRQU2ubymqbVNPYrJz0lFiXBQAAgEEU7dmQviWvB2G5c+5K59x9zrmn/e2Vkk7y9/9rlF8XgywpYJrSaXE2ZkQCAABIdNEOC8slPeycez3STufcG5Ie8Y9DnAm/FWk7tyIBAAAkvGiHhTxJu3s5Zpek3Ci/LoZA+IxIDHIGAABIfNEOC/skHd/LMYvljWNAnOk0IxI9CwAAAAkv2mHhL5JONbNvmllS+A4zC5jZTZJO94/rNzObZGb3mNk+Mwua2Q4z+7GZFfTjXAvN7P/MbI9/rhIze9HMrhxIjYloeiHTpwIAAIwk0Z469VZJF0j6N0lfMLOX5fUijJM3uHmavFWcf9DfFzCzmZJelVQk6TFJm+T1Ztwo6Wx/pqXyPp7ry5J+IumgpD9L2itvytf5kj4i6Tf9rTMRde5ZYIAzAABAootqWHDOFZvZMkl3STpD0tQuhzwr6Vrn3EBuQ/q5vKBwg3PuzvZGM7tN0lflBZVrezuJmZ0p6Q6/poucczVd9jMvaBfjctOVlhxQsKVNFXVNqmpoVl4G/5kAAAASVbRvQ5Jzbodz7ixJkyV9TNIV/nayc+4s59z2/p7b71U4U9IOST/rsvt7kuokXWFmWerdf0tqkHRZ16Dg/xzN/a0zUQUCpqmFDHIGAAAYKaK+gnM759xeebf1RNMKf/uMc66ty+vVmNkr8sLEUknPdXcSM5sv6ShJj0qqMLMVkhbJWwPi75Ke73p+eKYVZmlzSa0kb5Dz0ZPzY1wRAAAABsuAwoKZ3dPPpzrn3Of68bw5/nZzN/s/kBcWZquHsCDpOH9bKukFSSd32f8PM7vQObelt4LMrLuVqOf29tx4ND1s3MJ2ehYAAAAS2kB7Fj7bz+c5Sf0JC3n+tqqb/e3tvf25u8jffk5e78e5klZLGivpu5Iul/RnM1vgnGvqR50Jq9MgZ8ICAABAQhtoWJgelSqGXvtYjSRJn3TOveY/rvanTJ0rbz2IT0j6XU8ncs4titTu9zgsjE65w0fnVZyZEQkAACCRDSgsOOd2RquQPmrvOcjrZn97e2Uv52nfXxwWFCR590eZ2WPywsLx6iUsjDTT6VkAAAAYMaI+G9Ige9/fzu5m/xH+trsxDV3P012oOOhvM/pY14gxNjdNGSneentVDc06WMddWgAAAIkq3sLC8/72TDPrVLuZ5UhaJqle0uu9nOd1edOsTutmmtX5/rbf07wmKrPO06duL6d3AQAAIFHFVVhwzm2V9Iy8laCv67L7FklZklY650KfYM1srpl1mpnIOVcv6deS0iX9wMws7PgF8gZut0h6JPo/RfzjViQAAICRYdDWWRhEX5L0qqQ7zOw0SRslLZG3BsNmSd/qcvxGf2td2r8jb8rUr0g6wV+jYaykC+WFiK/44QRdMCMSAADAyBBXPQtSqHdhsaT75IWEmyTNlPQTSUudc+V9PE+1pOWS/l3SKElflvRReVOonuWc+0nUi08Q08NmRHpnd29jyQEAABCv4rFnQc653ZKu6uOxXXsUwvfVyuuJ6NobgR4snFoQ+v7lD8r0/PulWjGnqIdnAAAAIB7FXc8CYm9WUbYuXjQp9Pjmxzeosbk1hhUBAABgMBAW0C/fOGeuctO9jqmd5fW6+6VtMa4IAAAA0UZYQL+Mzk7T18+aE3r80+e3aHcFKzoDAAAkEsIC+u2yJVN15IRcSVKwpU3ff/K9GFcEAACAaCIsoN+SAqZbL5gfevzseyVatakkhhUBAAAgmggLGJCFUwp06eLJocc3P/4eg50BAAASBGEBA/YvZ89RXkaKJGlXRb3uepHBzgAAAImAsIABK+wy2PnnL2zRrnIGOwMAAMQ7wgKi4lPHT9GCiXmS2gc7b4hxRQAAABgowgKion2ws/nrZf9tY6n+9h6DnQEAAOIZYQFRc8zkfH3yuI7Bzrc8ycrOAAAA8YywgKj6+llzlZ/pDXbeXdGgX7ywNcYVAQAAoL8IC4iqUVmpnQY7/+LFrQx2BgAAiFOEBUTdJ4+boqMmeYOdm1radMsTDHYGAACIR4QFRF1SwHTr+R2DnZ/bxGBnAACAeERYwKA4enK+PnnclNDjm59gsDMAAEC8ISxg0PzLWXNCg533HGzQzxnsDAAAEFcICxg0BVmp+sbZc0OP//fFrdpRVhfDigAAAHA4CAsYVJcunqyjJ+dL8gY73/zEBjnnYlwVAAAA+oKwgEEVCJhuPf/I0GDnF94/oGcZ7AwAABAXCAsYdEdNytdlx3cMdr7liffU0MRgZwAAgOGOsIAh8fWz5qjAH+y8t7JBP39hS4wrAgAAQG8ICxgS+Zmp+uY5HYOd73pxm7Yz2BkAAGBYIyxgyFy8aLKOaR/s3Nqm7z3OYGcAAIDhjLCAIRPosrLzS5sP6OkNDHYGAAAYrggLGFILJuXp00s6Bjvf+uR7qm9qiWFFAAAA6A5hAUPun8+co1FZqZK8wc4/e57BzgAAAMMRYQFDLj8zVd8MW9n57pe2a9uB2hhWBAAAgEgIC4iJixZN0rFTGOwMAAAwnBEWEBPtg50D/mDnlz8o09MbimNbFAAAADohLCBm5k/M0+VLp4Yef/8JBjsDAAAMJ4QFxNRNZ8xRoT/YeV9Vo366isHOAAAAwwVhATGVl5nSaWXnu1/epq0MdgYAABgWCAuIuU8snKRFUwskSc2tTjcz2BkAAGBYICwg5gIB0/fPP7LTYOen1jPYGQAAINYICxgWjpyQpytPmBZ6fOuT76kuyGBnAACAWCIsYNj46hmzNTrbG+y8v6pRdzLYGQAAIKYICxg28jJS9M1z5oUe/+rlbdpSWhPDigAAAEY2wgKGlQuPnajF/mDnljbHys4AAAAxRFjAsOINdu5Y2fmVLeX68z/2x7YoAACAEYqwgGHnQxNyOw12vvnx97S7oj52BQEAAIxQhAUMS187c7ZGZ6dJkspqg7rynjdVXhuMcVUAAAAjC2EBw1Jueoru/NSxSk3y/hfdXlanq+57S7VMpwoAADBkCAsYtk6YWaiffPIYmT9+4d09Vbp25Ro1tbTFtjAAAIARgrCAYe2cBeP1gwvmhx6v3lKmmx5ep7Y2ZkgCAAAYbIQFDHufXjJVXz19dujxE+v26ftPvseUqgAAAIOMsIC4cMNps3TlCVNDj+97dYd+/sLWGFYEAACQ+AgLiAtmpu+dd6TOXTA+1PbfT7+vB9/cFcOqAAAAEhthAXEjKWC67dKjdeLMwlDbv/7pH3p6Q3EMqwIAAEhchAXElbTkJN11xSLNn5grSWpz0vW/e0dvbCuPcWUAAACJJy7DgplNMrN7zGyfmQXNbIeZ/djMCgZwzpPNrNXMnJn9IJr1Irpy0lN072eP19TCTElSU0ubrvnN29q4vzrGlQEAACSWuAsLZjZT0hpJV0l6U9LtkrZJulHSa2ZW2MPTuztnjqT7JdVHsVQMojE5aVp59ZLQKs81jS36zD1vancFlxAAACBa4i4sSPq5pCJJNzjnLnDOfdM5d6q80DBH0r/145w/kZQn6YfRKxODbUphpu6/+jjlpCVLkkprgrrynjdVVhuMcWUAAACJIa7Cgt+rcKakHZJ+1mX39yTVSbrCzLIO45zny+uluEHSvuhUiqFy5IQ8/fLKxUpN9v5X3l5Wp6vve0u1wZYYVwYAABD/4iosSFrhb59xzrWF73DO1Uh6RVKmpKV9OZmZFUm6W9KjzrkHolkohs4JMwt1xyePUcC8x+/uqdK1K9eoqaWt5ycCAACgR/EWFub4283d7P/A387uZn9Xd8v7b3BtfwsyszWRviTN7e85cfjOnj9et14wP/R49ZYy3fTwOrW1scozAABAf8VbWMjzt1Xd7G9vz+/tRGZ2taSPSfqSc64kCrUhxj69ZKq+enpHTnxi3T59/8n35ByBAQAAoD+SY11ALJjZNEk/lvSwc+6hgZzLObeom9dYI2nhQM6Nw3fDabNUXhfUb17bKUm679UdGp2dqi+fekSMKwMAAIg/8daz0N5zkNfN/vb2yl7Oc4+kBklfikZRGD7MTN8770idu2B8qO1/ntmsB9/cFcOqAAAA4lO8hYX3/W13YxLa/3zc3ZiGdgvlTb96wF+EzZmZk3Svv/9bftujAysXsZAUMN126dFaNqtjyY1//dM/9PSG4hhWBQAAEH/i7Tak5/3tmWYWCJ8RyV9YbZm8hdVe7+U8v5E3a1JXR0g6WdLf5S389s6AK0ZMpCUn6X8vX6RP3f261u+tVpuTrv/dO1p59fFaMuOw1+0DAAAYkeKqZ8E5t1XSM5KmSbquy+5bJGVJWumcq2tvNLO5ZtZpZiLn3A3OuWu6fqmjZ+HPflvXtRwQR3LSU3TvZ4/X1EIvFza1tOma37ytjfurY1wZAABAfIirsOD7kqRSSXeY2aNm9kMzWyXpq/JuP/pWl+M3+l8YgcbkpGnl1Us0JidNklTT2KIr73lTuyvqY1wZAADA8Bd3YcHvXVgs6T5JSyTdJGmmpJ9IWuqcK49ddRiOphRm6v6rjldOmnfX3YGaoK68502V1QZjXBkAAMDwFndhQZKcc7udc1c558Y751Kdc1Odc19xzh2McKw556yP573PP/7b0a8asfShCbm6+zOLlZrs/S+/vaxOV937lmqDLTGuDAAAYPiKy7AA9MfSGYW645PHKOBHx3/srdK1K9co2NIa28IAAACGKcICRpSz54/XDy5YEHq8ekuZbnpondraWOUZAACgK8ICRpzLlkzR187oWKrjyXf365YnNhAYAAAAuiAsYES6/tRZuvKEqaHH97+2Uxff9RrTqgIAAIQhLGBEMjN977wjde6C8aG2NTsP6qN3rtYPnnyPgc8AAAAiLGAESwqYbr/0GF23YqZSkrxRz61tTr9avV2n/+hFPfWP/XKOW5MAAMDIRVjAiJaaHNDXz5qrp25crqUzRoXai6sb9cXfrtXV972lXeUs4AYAAEYmwgIgaVZRjn73T0t1+6VHa3R2aqj9+fcP6IzbX9Sdz33AFKsAAGDEISwAPjPTx4+dpOe+9mFdvnSKzF+PIdjSph89u1nn/ORlvbqlLLZFAgAADCHCAtBFXmaKfnDBAv3pS8s0f2JuqH3bgTpd9qs3dOOD76i0pjGGFQIAAAwNwgLQjWMm5+ux607Szed9SDlpyaH2x/6+T6f96EX95rUdamVtBgAAkMAIC0APkgKmzy6bruduOkXnHT0h1F7T2KLvPrZBH//5K3p3T2UMKwQAABg8hAWgD4py03Xnp47Vys8dr+mjs0Lt7+6p0vk/e0XffWy9qhubY1ghAABA9BEWgMOw/IgxeurG5frq6bOVmuy9fZyTfvPaTp36Py/qsb/vZW0GAACQMAgLwGFKT0nSjacfoWe+crJOnj0m1F5WG9SND/5dl//6DW09UBvDCgEAAKKDsAD007TRWbr/quP0s8sWamxuWqj9lS3lOufHL+tHz7yvxmbWZgAAAPGLsAAMgJnp3KPG629fO0VXL5uugL82Q1Nrm+5ctUVn3v6Snn+/NLZFAgAA9BNhAYiCnPQUffe8D+mJ60/SsVPyQ+27Kup11b1v6YsPrNH+qoYYVggAAHD4CAtAFB05IU9/uPZE/fvHFygvIyXU/tT6Yp3+oxf14Ju7GAANAADiBmEBiLJAwHTZkil67qZT9ImFk0LtdU2t+uYf/6GbHlqn+qaWGFYIAADQN4QFYJCMzk7Tjy45Wr///FLNKsoOtf/xnb06/6ev6IOSmhhWBwAA0DvCAjDIlswo1BNfPkmXLO7oZfigtFYf++kr+uPaPTGsDAAAoGeEBWAIZKQm6b8uOlr/c/HRSk/x3nYNza362kPr9I1H3mWKVQAAMCwRFoAhdNGiSXrsupM0c0xWqO33b+/WBT97RdtYyA0AAAwzhAVgiM0Zl6PHv3ySLjhmQqhtU3GNzrtztZ5Yty+GlQEAAHRGWABiICstWbdfeox+eOECpSZ7b8O6plZd/7t39O1H/8FtSQAAYFggLAAxYmb61PFT9KcvnahphZmh9gde36WL/vdV7Syvi2F1AAAAhAUg5o6ckKcnrj9J5y4YH2pbv7daH71jtf66fn8MKwMAACMdYQEYBnLSU/TTy47V988/UilJJkmqCbbo2gfW6pYnNqippS3GFQIAgJGIsAAME2amK0+Ypj988URNKsgItd/7yg5dfNdr2nOwPobVAQCAkYiwAAwzR03K15+vX64zPjQ21LZud6XOvWO1nttYEsPKAADASENYAIahvMwU/fKKRfr2ufOUHPBuS6pqaNbn7n9bP/zLRjW3clsSAAAYfIQFYJgyM12zfIZ+/4UTNCEvPdR+10vb9Klfvq79VQ0xrA4AAIwEhAVgmFs0tUB/vmG5VswZE2p7e+dBnXvHar24+UAMKwMAAImOsADEgYKsVP36M8fpX86eoyT/tqSKuiZ99t439aNn3ldrm4txhQAAIBERFoA4EQiYvvThWfq/a5aoKCdNkuScdOeqLfr0r15XaXVjjCsEAACJhrAAxJklMwr1lxuX66RZo0Ntr2+r0EfuWK1Xt5TFsDIAAJBoCAtAHBqdnab7rz5eXz19tsy7K0lltUFd/us39J1H1+vtHRVq49YkAAAwQMmxLgBA/yQFTDeefoQWTyvQjQ++o7LaJrU5aeXrO7Xy9Z0ak5Oms44cq3Pmj9eS6aOUnMTfBgAAwOEhLABxbtms0frLDct1/e/e0RvbK0LtB2qCeuD1XXrg9V3Kz0zRGfPG6pwF47Rs1milJSfFsGIAABAvCAtAAijKTdfv/mmpXt5Spr+u369nNpSovK4ptL+yvlkPr9mjh9fsUXZask6dW6Rz5o/TKXPGKDOVXwMAACAyPiUACSIQMJ0ye4xOmT1GP7jA6a0dFfrr+mL9dX2xisNmSqoNtujxdfv0+Lp9Sk8J6JTZY3TO/PE6dV6RctNTYvgTAACA4YawACSgpIBp6YxCLZ1RqO9+9ENat6dSf11frKfWF2tXRX3ouMbmNj29oURPbyhRSpJp2azROmf+OJ3xoXEalZUaw58AAAAMB+YcM6YMBjNbs3DhwoVr1qyJdSlAiHNOG/fX6K/r9+up9cX6oLQ24nEBk5ZML9Q5C8bprCPHaWxu+hBXCgAA+mrRokVau3btWufcomifm7AwSAgLiAdbSmv19IZiPbV+v9bvre72uIVT8nXO/PE6e/44TR6VOYQVAgCA3gxmWOA2JGAEm1WUrVlFs3TdilnaXVHvB4dirdl5sNNxa3dVau2uSv3bXzbqyAm5+uhRE/TJ4yargFuVAABIaIQFAJKkyaMydc3yGbpm+QyVVDfqGT84vLG9Qq1hC7xt2FetDfuqdcdzH+jS4ybrcydNp7cBAIAERVgAcIixuem64oRpuuKEaaqoa9Lf3ivRU+v3a/WWMjW3esGhoblV9726Qytf36mPLBivL5w8Q/Mn5sW4cgAAEE2EBQA9GpWVqkuOm6xLjpus6sZmPbOhRL9evV0b93tjHFrbnJ5Yt09PrNunE2cW6gunzNTJR4yWmcW4cgAAMFCEBQB9lpueoosWTdInFk7Uyx+U6ZcvbdPqLWWh/a9uLderW8s1d1yOPn/yDJ139ASlJAViWDEAABiIuPxX3Mwmmdk9ZrbPzIJmtsPMfmxmBX18fpaZfdrM/s/MNplZnZnVmNnbZnaTmTFqE+iBmenk2WP0wDVL9OT1J+ljR09QUqCjJ2FTcY2+9tA6nfJfz+tXL29TbbAlhtUCAID+irupU81spqRXJRVJekzSJknHS1oh6X1Jy5xz5b2c42xJT0mqkPS8pC2SCiR9TNI4//ynOecauz1J73UydSpGlN0V9fr16u36/Vu71dDc2mlfTnqyLl86VVedOE1FrNkAAEBUsc5CGDN7WtKZkm5wzt0Z1n6bpK9Kuss5d20v5zhG0pGSHnbONYW150h6QdJCSf/snPvRAOokLGBEOljXpAde36n7X9uhstqmTvtSkwK64NgJ+vzJMzSrKCc2BQIAkGAICz6/V2GLpB2SZjrn2sL25UjaL8kkFTnn6vr5GpdJ+q2kJ51z5w2gVsICRrTG5lb9ce1e3f3yNm0vO/TtePq8In3hlJlaPLWAwdAAAAwAi7J1WOFvnwkPCpLknKsxs1fk9ToslfRcP1+j2d/26SZrM+suDczt5+sDCSE9JUmXLZmiS4+brGffK9FdL23VO7sqQ/v/trFUf9tYqmOn5OsLJ8/QGR8a12ncAwAAiL14G+A8x99u7mb/B/529gBe42p/+9cBnAOALylgOnv+OP3xiyfq4WtP0Onzxnba/86uSl37wFqdftuL+u0bO9XYZbwDAACInXjrWWhf8amqm/3t7fn9ObmZfVnS2ZL+Lumevjynu+4ev8dhYX/qABKRmem4aaN03LRR2lJao7tf2q4/vbNXTa1eJ+H2sjp960/rddszm/WZE6fpiqVTVZDFxGQAAMRSvPUsDBozu1DSjyUVS/qEc665l6cA6KdZRTn6z4uO0upvrNAXPzxTOekdf7cor2vSbc9u1on/sUrfeORdrdlZoXgaWwUAQCKJt56F9p6DvG72t7dXdrM/IjO7QNKDkkolrXDObetfeQAOR1Fuur5x9lxdt2KWHnxzl369erv2V3kzFjc0t+r3b+/W79/erZljsnTJ4sm6cOEkjclJi3HVAACMHPHWs/C+v+1uTMIR/ra7MQ2HMLOLJT0sqUTSKc6593t5CoAoy05L1jXLZ+ilf1mh2y89WnPHdZ5WdeuBOv3wqU1a+sPn9E+/eVvPvleilta2bs4GAACiJd56Fp73t2eaWSDC1KnLJNVLer0vJzOzT0u6X9Je0aMAxFxKUkAfP3aSLjhmotbuOqiH3tqjJ9/dp7omb9Bza5vTs++V6Nn3SjQmJ00XLpyoSxZP1swx2TGuHACAxBRXPQvOua2SnpE0TdJ1XXbfIilL0srwNRbMbK6ZHTKNqZl9RtJvJO2SdDJBARg+zEyLpo7Sf150lN781un6r4uO0nHTCjodc6AmqLte3KbTfvSiLvrFq3rord2qC/ZpxmMAANBHcbUomxRamO1VSUWSHpO0UdISeWswbJZ0onOuPOx4J0nOOQtrWyHpb/LC0j2Sdkd4qUrn3I8HUCeLsgFRtu1ArR56e4/+sHaPDtQED9mfmZqkjx41XpcsnqxFLPYGABghWMG5CzObLOn78qY5LZS3cvOfJN3inDvY5dhIYeGzku7t5WV2OuemDaBGwgIwSFpa2/Ti5gP6/Vu7tWpTqVraDv09NiM0KHqiinLSY1AlAABDg7AQhwgLwNA4UBPUo+/s1e/f3q0tpbWH7E8KmFbMKdIliydpxdwipSTF1d2XAAD0ajDDQrwNcAaATsbkpOmfTp6ha5ZP1zu7K/XQW7v1xLrOg6L/trFEf9tYotHZafrEwom6ePFkzSpiUDQAAL2hZ2GQ0LMAxE59U4v+8o9iPfT2br25vSLiMQun5OvS4ybrIwvGKyc9ZYgrBAAgeuhZAIDDkJmarIsWTdJFiyZpe1mdHn57tx5Zs0elYYOi1+6q1Npdlfr2o+u1ZHqhTp1bpNPmFWlqYVYMKwcAYHihZ2GQ0LMADC8trW166YMDeuitPfrbxpKIg6IlaeaYLJ02b6xOnVukRVMLGOMAABj26FkAgAFKTgro1LljdercsSqr9QZF/3HtXr23v7rTcVsP1GnrgW365UvblJOerFNmj9Fp84r04dlFKsgTsDAvAAAcH0lEQVRKjVH1AADEBmEBwIgzOjtN1yyfoWuWz9D+qgY9v+mAVm0q0eotZWpsDi0Mr5rGFj357n49+e5+BUxaOKVAp84r0mlzx2r22GzWcQAAJDxuQxok3IYExJ/G5la9trVcz20q0aqNpdpX1djtsRPzM3Tq3CKdOq9IJ8woVHpK0hBWCgBAB25DAoAhkJ6SpBVzi7RibpHc+U6bimu0alOpnttYond2Vyr8byt7Kxu08vWdWvn6TmWkJGnZrNE6bV6RTp1bpLG5LAIHAEgMhAUAiMDMNG98ruaNz9V1K2apvDaoFzcf0HObSvXS+wdUE2wJHdvQ3Bpay0GS5k/M9cdHFOmoiXkKBLhdCQAQnwgLANAHhdlpunDhJF24cJKaW9v01o4KrdpYqlWbSrWtrK7Tsev3Vmv93mrd8dwHGp2dphNnFmpqYaYm5mdoYkGGJuRnaGJ+BrcuAQCGPcICABymlKSATpw5WifOHK1vf/RD2l5Wp1WbSrVqU4ne2FbRaVrWstqgHl+3L+J5RmenhgLERD9ATCzoCBV5GSwWBwCILcICAAzQ9NFZ+txJ0/W5k6arurFZqz8o03MbS/X8+6WqqGvq9nlltU0qq23Suj1VEffnpCV3BImwHomJBRmalJ+h0dlp3OIEABhUhAUAiKLc9BR9ZMF4fWTBeLW2Ob27p1Kbimu092CD9lb6XwcbVFzdqNZuFoZrVxNs0abiGm0qrom4PzU5oAl56V6QyMtQbkaKslKTlJWWrKy0ZGX720PbkpSZmqwkggYAoBeEBQAYJEkB07FTCnTslIJD9rW0tqmkJuiHiPpQmNhzsCNQBFvaIpy1Q1NLm3aU12tHeX2/6stISfIDhB8mUr0g0VPQmDMuR/PG5/br9QAA8YewAAAxkJwUCI1TkEYdst85p/K6plCI2NclSOytbFBVQ/OAamhoblVDc6vKag/vefPG5+riRZN0/jETVJidNqAaAADDG2EBAIYhM9Po7DSNzk7T0ZPzIx5TG2wJ9UwUVwVVG2xWXbBVdcEW1TW1qLb9e/9xXbBVtf7j+qbWfte2cX+1vv/ke/rhUxt16twiXbxosk6ZM0YpSYF+nxMAMDwRFgAgTrXfFjRnXM5hP7etzam+2QsTtcEW1YcFCS9oHNpWVtuklzYfCN0e1dzq9PSGEj29oUSjs9P08WMn6OLFkzV77OHXAwAYnggLADACBQKmbH8cwtjDeF51Y7OeXLdfj6zZrbW7KkPtZbVB3f3ydt398nYdNSlPFy+apPOOnqD8zNToFw8AGDKEBQBAn+Wmp+iyJVN02ZIp2lJaqz+s3aM/rt2jkupg6Jh391Tp3T1VuvXJjTrjyLG6eNEkLT9iDLMvAUAcMud6nroP/WNmaxYuXLhwzZo1sS4FAAZVS2ubXt5SpkfW7NGzG0rU1HroLE5jc70VsC9aNEkzx2THoEoASFyLFi3S2rVr1zrnFkX73PQsAAAGJDkpoBVzirRiTpEq65v0+Lp9emTNHr0btthcSXVQv3hhq37xwlYtnJKvixdP1kePGq+c9MFfpbq+qUX7Khu1v6pB+6satb+yUeV1QY3NTdesomzNKsrW1FGZSmaANgAcgp6FQULPAoCRblNxtR55e48e/fteldUeupJ1ekpAZx85ThcvnqwTZhT2azXqhqbWjhBQ1aj9lQ3aV9WoYr9tX2WDqhtbej1PSpJpWmGWZhVla+aY7FCImDkmWxmpSYddFwAMpcHsWSAsDBLCAgB4mlvb9ML7B/Tw27u1alOpWiKsXD0xP0OfWDRJFy2cpCmFmZKkxuZWFVc1al9Vg4r9MLCvssFv83oKKusHttZEX0zMzwiFh9DXmGwVZDF4G8DwQFiIQ4QFADhUeW1Qj/59nx5+e7c2FddEPGbmmCwdrG9WRd2hvRH9kZoU0Li8dI3LS9eEvHSNz8/QqMxU7a1s0JbSWm0prVVxdeNhn7cwK1Uzw8JDe5AYn5cuMwZzAxg6jFkAACSEwuw0fe6k6bp62TRt2FetR9Z4tymF9xBsPVDX5/OlJJnG5qZrQl6GxuWla3x+x/cT8jI0Pj9dozJTe73FqaaxWVsP1IXCw9YDtdpaWqudFfVqjdATIknldU0q316hN7dXdGrPSk3STP8WpqmFmRqXm66x/te4vHQVZKYQJgDEDcICAGDImZnmT8zT/Il5+n8fmatVG0v18Jo9euH9UrV/Nk8KmMblpmt8e69AfobG56X7X14QGJ2V1q+xDl3lpKfomMn5OqbLatnBllbtLK8PhYj2r21ltWpsPnTWJ0mqa2oNTR8bSWpSQEW5aV1CRFrH9/6WsRIAhgPCAgAgptKSk3TOgvE6Z8F4ldcGta+yUUW5aRqdnRbztRnSkpM0e2zOIatSt7W5TrcxbSmt1ZYD3raqoedxFE2tbdpzsEF7Djb0eFxuerLG5XUEirGHBIz0Q/4btbY5NbW0qbG5VcGWNgVb/G2z931jc1hbS6vf3mVfWFvQP1dzq9OorFRNKsjQpIJMTSrI0ORRXq9JrK8RgMFFWAAADBuF2WkqzE6LdRm9CgRMk0dlavKoTK2YWxRqd86prLYpdCvTvsoGFVc3qqS6USXVQZVUNaom2PvsTJJU3dii6sZabS6p7b4Ok/IyUtTc6hRs8T7UD6XkgGl8from5XcEiPBAMZYwAcQ9wgIAAFFiZhqTk6YxOWk6YWZhxGPqgi0qqW5UcXWjSquDYWGiUcVVXqgorWns0wf/NicdHIIZobrT0ua0u6JBuysi95KkJJkm5Gd4AcIPFJNGZWhyQaYmFWSqKCc6t5EBGDyEBQAAhlBWWrJmjMnWjB5Wsm5rczpY39SpV6K4qlGlNV6gKK4OqrS6UeVdZowyk9KSA0pPSVJackBpyf42xfs+PSWsrX1/SuDQ56R07E9PCSgpEFBpTaP2HGzQ7or60G1UZbXBHn/W5lanneX12lleL6n8kP2pSQFNyE/XpIJMTR6VoXG5GSrMTtXo7FSvlynL2+amJzMoHIgRwgIAAMNMIGChW7KOnJDX7XHBllbVNLaEPtinJNmQfqhuaGrV3soG7T7YHiA6gsSeivpDwkxXTa1t2lFerx3l9T0el5JkGpWVqsKsND9MdAQJb9vx/ejstKgODm9tc6pralFdsEW1jS2qDXpfdcEW1QZbVdvYrLom7zrUhe3LzUjRxPwM76vA247PT1daMgPXEV8ICwAAxKm05CSlZcfuw2dGalJofYlI6ptatLc9PBys1+4ugaKva2k0tzpvzEd1zz0Z7TJTk7xwkZ2m0V3CRG56iuqbWg75gF/rh4G6ps6hoL6ptc//PfqiKCdNEwsyvNuzwoJEe1tuekpUXw8YKMICAAAYFJmpyTpibI6O6DKbVLu6YEtHkKioV2lNUBV1TSqrbVJ5XVDltU0qrw2q7jA/sNc3taq+qfcZp2KhtCao0pqg3tlVGXF/TnqyJvrjPCbmewEiPFBEa7pgoK8ICwAAICay0pI1Z1yO5oyLHCbaNTS1qrzOCxLltU0qqw16i+LVeoGirK5JFaFw0aSm1shrYPRXZmqSstOSlZ2e7G3TkpWVlqwcf9u1PTM1SRV1Tdpb2aB9lQ3ae7BBeysbVFLdqG7W+AupaWzRpuKablc4T00OaEJeutcTkZeholxvjY6inDSNyfGm2B2Tk8btTogawgIAABjWMlKTNCnVm0GpN8451QRbQr0SZbVNfsjwAkZ1Y7P/4T9F2WlJHR/80/0P/u1f/uOs1OSoTf/a3Nqm4qpG7Q0LEKGt/9XU0nPQaWrp2ziP/MwUjc1JV5EfHtoDRZEfKIr8fekphAr0jLAAAAAShpkpNz1Fuekpmj46K9bldJKSFAitzxFJ+zodHSGiXvsqvVmovLZ6VTf2bZ2OyvpmVdY36/2SyD0U7XLSk8OChBcqxuSkqSg3XWP9bVFOmrLS4vcjY2ubC93Olu0Hw7TkADNs9VH8XnkAAIAEEr5OxzGT8yMeU9PYrH2VjdpbWa/9Vd5aHaU13lS63niIRh2oCfZ6u1PH+VpU0+itPt6TrNQkFbUHCb/Gohw/ZOR2fJ+fmTJkH8KbWtp0oDb8Zw/qQHXHWiXtbeW1h/73SA5Yp9vHctNTOh6ne7eYhb5PTwmFjE7705OVkZKU8KGDsAAAABAnctJTNGdcSo/jPFrbnMrrgn6QCAsUNe0fpL0P1aU1QbX0MVXUNbVqe1mdtpfV9XhcalIgFHjag8SY7HQ/UHTc/lSYlarkpEDEczQ0tXZ82A/74F9S7QWh9raBLEjY0uZCvS8DkRSwUOAIDxP/c/HRGh0Hq9H3BWEBAAAggSQFzP9Lf7qk7tfpaF/8r/0v8B0fxg/963xvYynaNbW2hcZf9CRg0qisjl6KYEurH2KCqgn27VarwzEqK1VZaUmqC7aqprG5Tyuk90Vrm1NVQ7OqGjqHjkAC9TYQFgAAAEag8MX/5o3v/jjnnKobWsLCQ3hvhRcuDtQe3gf9NieV1Qa9VcD397N+k0Znd74NqignTWO6jMEYnZ2m1OTOvRjBltbQeho1jR3rbNQEm/1t2HobYY/b97c/L9hNiMpKS5yB44QFAAAAdMvMlJeZorzMlG7XzGhX39Ti9U50uYWo/fv2fT0tyJeSZBqT3TG4ulMYCPu+MDut3zNVtS9oWDjAW4WaWtpCC/tVN3YEiUSaupawAAAAgKjITE3W1MJkTS3seSaq5tY2ldV6IeJATVCpyYFQEMjPSImbhedSkwNKTU5VQVZqrEsZNIQFAAAADKmUpIDG52VofF5GrEtBLyIPQwcAAAAw4hEWAAAAAEREWAAAAAAQEWEBAAAAQESEBQAAAAARERYAAAAARBSXYcHMJpnZPWa2z8yCZrbDzH5sZgWHeZ5R/vN2+OfZ55930mDVDgAAAMSLuFtnwcxmSnpVUpGkxyRtknS8pBslnW1my5xz5X04T6F/ntmSVkl6UNJcSVdJOtfMTnDObRucnwIAAAAY/uKxZ+Hn8oLCDc65C5xz33TOnSrpdklzJP1bH8/z7/KCwm3OudP881wgL3QU+a8DAAAAjFhxFRb8XoUzJe2Q9LMuu78nqU7SFWbW4xrjZpYt6Qr/+Ju77P6ppJ2SzjKzGQOvGgAAAIhPcRUWJK3wt88459rCdzjnaiS9IilT0tJezrNUUoakV/znhZ+nTdLTXV4PAAAAGHHibczCHH+7uZv9H8jreZgt6bkBnkf+eXpkZmu62TW3t+cCAAAAw1m89Szk+duqbva3t+cP0XkAAACAhBVvPQvDjnNuUaR2v8dh4RCXAwAAAERNvPUstP/FP6+b/e3tlUN0HgAAACBhxVtYeN/fdjeW4Ah/291YhGifBwAAAEhY5pyLdQ195k+dukXe1Kkzw2dEMrMcSfslmaQi51xdD+fJllQqqU3S+PAZkcwsIGmrpGn+a/RrYTYzK8/IyBg1b968/jwdAAAA6JONGzeqoaGhwjlXGO1zx9WYBefcVjN7Rt6MR9dJujNs9y2SsiTdFR4UzGyu/9xNYeepNbOVkj4vb52Fm8LO82V5QeHpAa7gXN3Q0KC1a9fuGMA5+qt9JqZNPR6FRMS1H5m47iMX137k4tqPXJGu/TRJ1YPxYnHVsyCFehdelbfK8mOSNkpaIm9NhM2STnTOlYcd7yTJOWddzlPon2e2pFWS3pQ0T9L58nodTnTObR3sn2cwtE/n2t3gayQurv3IxHUfubj2IxfXfuQa6msfb2MW5H+AXyzpPnkh4SZJMyX9RNLS8KDQy3nKJZ0g6Q5Js/zzLJF0r6RF8RoUAAAAgGiJq9uQ2jnndku6qo/HWg/7KiTd6H8BAAAACBN3PQsAAAAAhgZhAQAAAEBEhAUAAAAAEcXdbEgAAAAAhgY9CwAAAAAiIiwAAAAAiIiwAAAAACAiwgIAAACAiAgLAAAAACIiLAAAAACIiLAAAAAAICLCQgIxs0lmdo+Z7TOzoJntMLMfm1lBrGvD4PGvs+vmqzjW9WFgzOwiM7vTzF42s2r/uj7Qy3NONLO/mFmFmTWY2btm9hUzSxqqujFwh3PtzWxaD78HnJk9ONT1o3/MrNDMrjGzP5nZFv89XGVmq83sc2YW8bMb7/v4d7jXfqje98nROAliz8xmSnpVUpGkxyRtknS8pBslnW1my5xz5TEsEYOrStKPI7TXDnUhiLpvSzpa3rXcI2luTweb2fmS/iCpUdLvJVVIOk/S7ZKWSbp4MItFVB3Wtfetk/RohPb1UawLg+tiSb+QtF/S85J2SRor6UJJv5J0jpld7MJW1eV9nzAO+9r7BvV9zwrOCcLMnpZ0pqQbnHN3hrXfJumrku5yzl0bq/oweMxshyQ556bFthIMBjNbIe+D4hZJp8j7B+S3zrnLIxyb6x+XJ2mZc+5tvz1d0ipJJ0j6lHOOvzLHgcO89tMkbZd0v3Pus0NXJaLNzE6VlCXpz865trD2cZLelDRZ0kXOuT/47bzvE0Q/rv00DcH7ntuQEoDfq3CmpB2SftZl9/ck1Um6wsyyhrg0AAPknHveOfdBhL8kRXKRpDGSHmz/wOCfo1HeX6kl6YuDUCYGwWFeeyQI59wq59wT4R8W/fZiSf/rP/xw2C7e9wmiH9d+SHAbUmJY4W+fifA/WI2ZvSIvTCyV9NxQF4chkWZml0uaIi8cvivpJedca2zLwhA71d/+NcK+lyTVSzrRzNKcc8GhKwtDaIKZfUFSoaRySa85596NcU2InmZ/2xLWxvt+ZIh07dsN6vuesJAY5vjbzd3s/0BeWJgtwkKiGidpZZe27WZ2lXPuxVgUhJjo9neBc67FzLZLOlLSDEkbh7IwDJkz/K8QM3tB0mecc7tiUhGiwsySJV3pPwwPBrzvE1wP177doL7vuQ0pMeT526pu9re35w9BLRh690o6TV5gyJK0QNJdkqZJesrMjo5daRhi/C4Yueol3SppkaQC/6t9nMOHJT3Hrahx7z8kzZf0F+fc02HtvO8TX3fXfkje94QFIM45527x73Mscc7VO+fW+4PZb5OUIenm2FYIYLA550qdc991zq11zlX6Xy/J61V+Q9IsSdfEtkr0l5ndIOkmeTMdXhHjcjCEerr2Q/W+Jywkhva/GuR1s7+9vXIIasHw0T4Y6uSYVoGhxO8CdOKca5E35aLE74K4ZGZflvQTSe9JWuGcq+hyCO/7BNWHax9RtN/3hIXE8L6/nd3N/iP8bXdjGpCYDvhbbj0YObr9XeDf8zpd3uC4bUNZFGKO3wVxysy+IulOefPlr/BnxemK930C6uO170nU3veEhcTwvL89M8LqfjnyFmSpl/T6UBeGmFrqb/kHYuRY5W/PjrDvZEmZkl5lRpQRh98FccjMviFvUbW/y/uwWNrNobzvE8xhXPueRO19T1hIAM65rZKekTeg9bouu2+RlypXOufqhrg0DDIzmxdp8JK/UMtP/YcPDGVNiKlHJJVJ+qSZLW5v9Bdn+oH/8BexKAyDy8wWdv1jkd9+mryFOSV+F8QNM/uOvEGtaySd5pwr6+Fw3vcJ5HCu/VC971nBOUH4C7O9KqlI0mPypkdbIm8Nhs2STnTOlceuQgwGM7tZ3sCnlyTtlFQjaaakcyWlS/qLpI8755piVSMGxswukHSB/3CcpLPk/aXoZb+tzDn3z12Of0RSo6QHJVVI+pi86RUfkXQJi3zFh8O59v40iUfI+3dgj7//KHXMwf8d51z7B0cMY2b2GUn3SWqVdxtKpFmOdjjn7gt7Du/7BHC4136o3veEhQRiZpMlfV9eV2ShpP2S/iTpFufcwVjWhsFhZqdIulbSseqYOrVSXtflSnk9SrzJ45gfCL/XwyE7nXPTujxnmaRvSTpBXmjcIukeSXewUF/8OJxrb2afk/RxedMrjpaUIqlE0muSfuqce7m7k2B46cN1l6QXnXMf7vI83vdx7nCv/VC97wkLAAAAACJizAIAAACAiAgLAAAAACIiLAAAAACIiLAAAAAAICLCAgAAAICICAsAAAAAIiIsAAAAAIiIsAAAAAAgIsICAAAAgIgICwAAAAAiIiwAAAAAiIiwAABIWGb2gpm5WNcBAPGKsAAAAAAgIsICAAAAgIgICwAAAAAiIiwAAHplZkvM7BEzKzazJjPbbWZ3mdmELse9YGbOzNLM7Admtt3Mgma21cy+Z2ap3Zz/NDP7q5lV+MdvNrP/MLO8bo4fZWb/ZmbrzazezKrMbJ3/nKwIxyeb2b+a2Qf++Xeb2X92Vw8AwGPOMe4LANA9M7ta0i8lBSU9Lmm3pCMkfUxSiaSlzrld/rEvSDrFP+44SY9IapZ0vqSZkp6U9DEX9o+PmX1B0i8k1Ul6WFKppA9LWiLpPUnLnHOVYcdPl/S8pKmS1kh6Ud4fv2ZLOl3SHOfcji71PCxpuaSnJFVL+oj/M9znnLsqKv+hACABERYAAN0ys9mS1kvaJekU59zesH2nSXpG0uPOuY/7bS/I+3D+gaQlzrmDfnu6vA/4SyVd6Zxb6bdPlbRZXhA53jm3Kez8P5f0RUl3O+c+H9b+qqQTJP2rc+6HXeodLanWOdfYpZ61ks5wzlX47VmS1kmaLmmic654wP+xACABcRsSAKAnX5SUIunG8KAgSc655+T1IJxnZjldnndre1Dwj22U9P/8h1eHHXe5pFRJPw0PCr5vSaqRdIWZpUmSmS2SFxT+Luk/uxbrnCtrDwpdfKM9KPjH1Un6rbx/BxdH+sEBAFJyrAsAAAxrJ/jbU8zsuAj7iyQlybsFaE1Y+4sRjl0tqVXSsWFtC/3tqq4HO+cOmtk7kk6WNFdeT8BSf/fTzrm2vv4Qkt6O0Lbb3xYcxnkAYEQhLAAAelLob7/ey3HZXR6XdD3AOddiZmXyAka79gHM+7s5b3t7fpft3gjHdit8zEOYFn+bdDjnAoCRhLAAAOhJlb/Nc85VH8bzxsob5xBiZsmSRssbYNz1/OMkbYhwnvFdjmv/0D/xMGoBAPQTYxYAAD153d8uP8znnRKh7SR5f8V/J6yt/fsPdz3YzPIlHSOpUdLGLvWcZWb8GwYAg4xftACAnvxU3tSnt/szI3ViZqlmFilIfMfMCsKOS5fUPnPRvWHHPeCf/3ozm9XlHLdKypX0gHMuKEnOuTWSXpUXIr4RoZ5C/7UAAFHAbUgAgG455zb56yzcI2mDmf1V3lSnKZKmyOtxOCBvAHK4jf7xXddZ+LOklWHn32FmX5H0M0lrzewh/3ynyBtcvUmHhoLLJb0g6d/N7BP+9yZv3YQz/Vp2DPynBwAQFgAAPXLOPWBm6yTdJGmFvA/kdZL2yVt07fcRnnaJpO9I+rSkCfIGJN8s6T9clwV+nHM/N7Mtkv5Z0ickZcqbqei/Jf1718HJzrntZrZQ0r9IukDSl+XdqrRD0o/kLeoGAIgCFmUDAERN+yJozjmLdS0AgIFjzAIAAACAiAgLAAAAACIiLAAAAACIiDELAAAAACKiZwEAAABARIQFAAAAABERFgAAAABERFgAAAAAEBFhAQAAAEBEhAUAAAAAEREWAAAAAEREWAAAAAAQEWEBAAAAQESEBQAAAAARERYAAAAARERYAAAAABARYQEAAABARP8fDcZuuLGCQqkAAAAASUVORK5CYII=\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "image/png": {
              "width": 389,
              "height": 277
            },
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OZNS-3wQOR0g",
        "outputId": "3727f59b-eb4d-444c-ad65-607c33801806"
      },
      "source": [
        "model_m.save(\"model_93\")\n",
        "sh=x_test\n",
        "score = model_m.evaluate(x_test, y_test, verbose=0)\n",
        "print('Test loss:', score[0])\n",
        "print('Test accuracy:', score[1])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Assets written to: model_93/assets\n",
            "Test loss: 0.4121353328227997\n",
            "Test accuracy: 0.9306930899620056\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5YVe7K1KWDek"
      },
      "source": [
        "# 0.85 when two 64 conv used"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "W9QJ3T1UTsqg"
      },
      "source": [
        "import sklearn.metrics as metrics\n",
        "\n",
        "y_test_pred = model_m.predict(x_test)  \n",
        "y_test_pred_labels = np.argmax(y_test_pred, axis=1)  # only necessary if output has one-hot-encoding, shape=(n_samples)\n",
        "# print(y_test_pred_labels)\n",
        "y_test_labels = np.argmax(y_test, axis=1)\n",
        "# print(y_test_labels)\n",
        "confusion_matrix = metrics.confusion_matrix(y_true=y_test_labels, y_pred=y_test_pred_labels)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 341
        },
        "id": "Yckg6V0OP7hI",
        "outputId": "efe0a77a-b55e-4b07-d2bf-77eb058a96f7"
      },
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sn\n",
        "\n",
        "fig, ax = plt.subplots()\n",
        "\n",
        "text_labels=['Covid','MI','Abnormal','Normal']\n",
        "df_cm = pd.DataFrame(confusion_matrix, range(num_classes), range(num_classes))\n",
        "# plt.figure(figsize=(10,7))\n",
        "sn.set(font_scale=1.4) # for label size\n",
        "sn.heatmap(df_cm, annot=True, annot_kws={\"size\": 16}, fmt='g') # font size\n",
        "\n",
        "ax.set_xticklabels( text_labels, rotation = 45)\n",
        "ax.set_yticklabels(text_labels,rotation = 45)\n",
        "\n",
        "plt.xlabel(\"Output Class\")\n",
        "plt.ylabel(\"Target Class\")\n",
        "\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": [],
            "image/png": {
              "width": 431,
              "height": 324
            }
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "r44F6KcvzXvl",
        "outputId": "a3b5dc67-74b0-4f68-eb06-2fecac065e9c"
      },
      "source": [
        "from sklearn.metrics import classification_report\n",
        "\n",
        "y_pred = model_m.predict(x_test, batch_size=100, verbose=1)\n",
        "y_pred_bool = np.argmax(y_pred, axis=1)\n",
        "\n",
        "y_test_b = np.argmax(y_test, axis=1)\n",
        "\n",
        "print(classification_report(y_test_b, y_pred_bool, target_names=text_labels))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "3/3 [==============================] - 0s 43ms/step\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "       Covid       0.98      0.96      0.97        50\n",
            "          MI       0.94      1.00      0.97        48\n",
            "    Abnormal       0.95      0.74      0.83        47\n",
            "      Normal       0.88      1.00      0.93        57\n",
            "\n",
            "    accuracy                           0.93       202\n",
            "   macro avg       0.94      0.93      0.93       202\n",
            "weighted avg       0.93      0.93      0.93       202\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "f26xlOInxU51"
      },
      "source": [
        "plt.figure()\n",
        "plt.step(recall['micro'], precision['micro'], where='post')\n",
        "\n",
        "plt.xlabel('Recall')\n",
        "plt.ylabel('Precision')\n",
        "plt.ylim([0.0, 1.05])\n",
        "plt.xlim([0.0, 1.0])\n",
        "plt.title(\n",
        "    'Average precision score, micro-averaged over all classes: AP={0:0.2f}'\n",
        "    .format(average_precision[\"micro\"]))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "awKhL4mloL6v"
      },
      "source": [
        ""
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "qgAV_fmLxY12"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FJGc4GmWKRBf"
      },
      "source": [
        "![image.png](data:image/png;base64,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)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5rL-ow3sKSC_"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}