{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":8089,"databundleVersionId":44321,"sourceType":"competition"}],"dockerImageVersionId":30559,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"pip install tensorflow","metadata":{"execution":{"iopub.status.idle":"2023-12-13T14:41:06.302381Z","shell.execute_reply.started":"2023-12-13T14:40:54.482303Z","shell.execute_reply":"2023-12-13T14:41:06.301413Z"},"trusted":true},"execution_count":33,"outputs":[{"name":"stdout","text":"Note: you may need to restart the kernel to use updated packages.\n","output_type":"stream"}]},{"cell_type":"code","source":"import tensorflow as tf\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport datetime\nimport os\nimport random\n\nfrom tqdm import tqdm \n\nfrom skimage.io import imread, imshow\nfrom skimage.transform import resize\nimport matplotlib.pyplot as plt","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-13T14:41:06.304415Z","iopub.execute_input":"2023-12-13T14:41:06.304746Z","iopub.status.idle":"2023-12-13T14:41:06.310561Z","shell.execute_reply.started":"2023-12-13T14:41:06.304716Z","shell.execute_reply":"2023-12-13T14:41:06.309747Z"},"trusted":true},"execution_count":34,"outputs":[]},{"cell_type":"code","source":"# Clear any logs from previous runs\n!rm -rf ./logs/ ","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:41:06.31182Z","iopub.execute_input":"2023-12-13T14:41:06.312182Z","iopub.status.idle":"2023-12-13T14:41:07.345383Z","shell.execute_reply.started":"2023-12-13T14:41:06.312133Z","shell.execute_reply":"2023-12-13T14:41:07.344153Z"},"trusted":true},"execution_count":35,"outputs":[]},{"cell_type":"code","source":"# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\nbase_dir = \"../input/data-science-bowl-2018\"\ntrain_dir = os.path.join(base_dir, \"stage1_train.zip\")\ntest_dir = os.path.join(base_dir, \"stage1_test.zip\")\n\nimport zipfile\nwith zipfile.ZipFile(train_dir,\"r\") as z:\n    z.extractall(\"./stage1_train\")\n\nwith zipfile.ZipFile(test_dir,\"r\") as z:\n    z.extractall(\"./stage1_test\")\n\n# We can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when we create a version using \"Save & Run All\" \n# We can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-13T14:41:07.348801Z","iopub.execute_input":"2023-12-13T14:41:07.349436Z","iopub.status.idle":"2023-12-13T14:41:12.108409Z","shell.execute_reply.started":"2023-12-13T14:41:07.349406Z","shell.execute_reply":"2023-12-13T14:41:12.107636Z"},"trusted":true},"execution_count":36,"outputs":[{"name":"stdout","text":"/kaggle/input/data-science-bowl-2018/stage1_test.zip\n/kaggle/input/data-science-bowl-2018/stage1_sample_submission.csv.zip\n/kaggle/input/data-science-bowl-2018/stage2_sample_submission_final.csv.zip\n/kaggle/input/data-science-bowl-2018/stage1_train.zip\n/kaggle/input/data-science-bowl-2018/stage1_train_labels.csv.zip\n/kaggle/input/data-science-bowl-2018/stage1_solution.csv.zip\n/kaggle/input/data-science-bowl-2018/stage2_test_final.zip\n","output_type":"stream"}]},{"cell_type":"code","source":"seed = 42\nnp.random.seed = seed","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:41:12.109522Z","iopub.execute_input":"2023-12-13T14:41:12.109843Z","iopub.status.idle":"2023-12-13T14:41:12.11405Z","shell.execute_reply.started":"2023-12-13T14:41:12.109818Z","shell.execute_reply":"2023-12-13T14:41:12.113153Z"},"trusted":true},"execution_count":37,"outputs":[]},{"cell_type":"code","source":"IMG_WIDTH = 128\nIMG_HEIGHT = 128\nIMG_CHANNELS = 3","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:41:12.115188Z","iopub.execute_input":"2023-12-13T14:41:12.115707Z","iopub.status.idle":"2023-12-13T14:41:12.12682Z","shell.execute_reply.started":"2023-12-13T14:41:12.115673Z","shell.execute_reply":"2023-12-13T14:41:12.125997Z"},"trusted":true},"execution_count":38,"outputs":[]},{"cell_type":"code","source":"TRAIN_PATH = \"./stage1_train/\"\nTEST_PATH = \"./stage1_test/\"\n\ntrain_ids = next(os.walk(TRAIN_PATH))[1]\ntest_ids = next(os.walk(TEST_PATH))[1]\n\nX_train = np.zeros((len(train_ids), IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS), dtype=np.uint8)\nY_train = np.zeros((len(train_ids), IMG_HEIGHT, IMG_WIDTH, 1), dtype=np.bool)","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:41:12.128087Z","iopub.execute_input":"2023-12-13T14:41:12.128367Z","iopub.status.idle":"2023-12-13T14:41:12.147632Z","shell.execute_reply.started":"2023-12-13T14:41:12.128343Z","shell.execute_reply":"2023-12-13T14:41:12.146423Z"},"trusted":true},"execution_count":39,"outputs":[{"name":"stderr","text":"/tmp/ipykernel_32/617529957.py:8: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.\nDeprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations\n  Y_train = np.zeros((len(train_ids), IMG_HEIGHT, IMG_WIDTH, 1), dtype=np.bool)\n","output_type":"stream"}]},{"cell_type":"code","source":"print('Resizing training images and masks')\nfor n, id_ in tqdm(enumerate(train_ids), total=len(train_ids)):   \n    path = TRAIN_PATH + id_\n    img = imread(path + '/images/' + id_ + '.png')[:,:,:IMG_CHANNELS]  \n    img = resize(img, (IMG_HEIGHT, IMG_WIDTH), mode='constant', preserve_range=True)\n    X_train[n] = img  #Fill empty X_train with values from img\n    mask = np.zeros((IMG_HEIGHT, IMG_WIDTH, 1), dtype=np.bool)\n    for mask_file in next(os.walk(path + '/masks/'))[2]:\n        mask_ = imread(path + '/masks/' + mask_file)\n        mask_ = np.expand_dims(resize(mask_, (IMG_HEIGHT, IMG_WIDTH), mode='constant',  \n                                      preserve_range=True), axis=-1)\n        mask = np.maximum(mask, mask_)  \n            \n    Y_train[n] = mask   ","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:41:12.148874Z","iopub.execute_input":"2023-12-13T14:41:12.149158Z","iopub.status.idle":"2023-12-13T14:45:13.873277Z","shell.execute_reply.started":"2023-12-13T14:41:12.149134Z","shell.execute_reply":"2023-12-13T14:45:13.872172Z"},"trusted":true},"execution_count":40,"outputs":[{"name":"stdout","text":"Resizing training images and masks\n","output_type":"stream"},{"name":"stderr","text":"  0%|          | 0/670 [00:00<?, ?it/s]/tmp/ipykernel_32/118592298.py:7: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.\nDeprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations\n  mask = np.zeros((IMG_HEIGHT, IMG_WIDTH, 1), dtype=np.bool)\n100%|██████████| 670/670 [04:01<00:00,  2.77it/s]\n","output_type":"stream"}]},{"cell_type":"code","source":"# test images\nX_test = np.zeros((len(test_ids), IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS), dtype=np.uint8)\nsizes_test = []\nprint('Resizing test images') \nfor n, id_ in tqdm(enumerate(test_ids), total=len(test_ids)):\n    path = TEST_PATH + id_\n    img = imread(path + '/images/' + id_ + '.png')[:,:,:IMG_CHANNELS]\n    sizes_test.append([img.shape[0], img.shape[1]])\n    img = resize(img, (IMG_HEIGHT, IMG_WIDTH), mode='constant', preserve_range=True)\n    X_test[n] = img\n\nprint('Done!')\n\nimage_x = random.randint(0, len(train_ids))\nimshow(X_train[image_x])\nplt.show()\nimshow(np.squeeze(Y_train[image_x]))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:45:13.874973Z","iopub.execute_input":"2023-12-13T14:45:13.875385Z","iopub.status.idle":"2023-12-13T14:45:15.894204Z","shell.execute_reply.started":"2023-12-13T14:45:13.875346Z","shell.execute_reply":"2023-12-13T14:45:15.893155Z"},"trusted":true},"execution_count":41,"outputs":[{"name":"stdout","text":"Resizing test images\n","output_type":"stream"},{"name":"stderr","text":"100%|██████████| 65/65 [00:01<00:00, 47.41it/s]\n","output_type":"stream"},{"name":"stdout","text":"Done!\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"#Build the model\ninputs = tf.keras.layers.Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS))\ns = tf.keras.layers.Lambda(lambda x: x / 255)(inputs)","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:45:15.897833Z","iopub.execute_input":"2023-12-13T14:45:15.898126Z","iopub.status.idle":"2023-12-13T14:45:15.911078Z","shell.execute_reply.started":"2023-12-13T14:45:15.8981Z","shell.execute_reply":"2023-12-13T14:45:15.910286Z"},"trusted":true},"execution_count":42,"outputs":[]},{"cell_type":"code","source":"#Contraction path\nc1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(s)\nc1 = tf.keras.layers.Dropout(0.1)(c1)\nc1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c1)\np1 = tf.keras.layers.MaxPooling2D((2, 2))(c1)\n\nc2 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p1)\nc2 = tf.keras.layers.Dropout(0.1)(c2)\nc2 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c2)\np2 = tf.keras.layers.MaxPooling2D((2, 2))(c2)\n \nc3 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p2)\nc3 = tf.keras.layers.Dropout(0.2)(c3)\nc3 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c3)\np3 = tf.keras.layers.MaxPooling2D((2, 2))(c3)\n \nc4 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p3)\nc4 = tf.keras.layers.Dropout(0.2)(c4)\nc4 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c4)\np4 = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(c4)\n \nc5 = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p4)\nc5 = tf.keras.layers.Dropout(0.3)(c5)\nc5 = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c5)","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:45:15.912143Z","iopub.execute_input":"2023-12-13T14:45:15.912432Z","iopub.status.idle":"2023-12-13T14:45:16.050225Z","shell.execute_reply.started":"2023-12-13T14:45:15.912408Z","shell.execute_reply":"2023-12-13T14:45:16.049512Z"},"trusted":true},"execution_count":43,"outputs":[]},{"cell_type":"code","source":"#Expansive path \nu6 = tf.keras.layers.Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(c5)\nu6 = tf.keras.layers.concatenate([u6, c4])\nc6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u6)\nc6 = tf.keras.layers.Dropout(0.2)(c6)\nc6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c6)\n \nu7 = tf.keras.layers.Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(c6)\nu7 = tf.keras.layers.concatenate([u7, c3])\nc7 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u7)\nc7 = tf.keras.layers.Dropout(0.2)(c7)\nc7 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c7)\n \nu8 = tf.keras.layers.Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(c7)\nu8 = tf.keras.layers.concatenate([u8, c2])\nc8 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u8)\nc8 = tf.keras.layers.Dropout(0.1)(c8)\nc8 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c8)\n \nu9 = tf.keras.layers.Conv2DTranspose(16, (2, 2), strides=(2, 2), padding='same')(c8)\nu9 = tf.keras.layers.concatenate([u9, c1], axis=3)\nc9 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u9)\nc9 = tf.keras.layers.Dropout(0.1)(c9)\nc9 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c9)\n ","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:45:16.051314Z","iopub.execute_input":"2023-12-13T14:45:16.051599Z","iopub.status.idle":"2023-12-13T14:45:16.228152Z","shell.execute_reply.started":"2023-12-13T14:45:16.051564Z","shell.execute_reply":"2023-12-13T14:45:16.227247Z"},"trusted":true},"execution_count":44,"outputs":[]},{"cell_type":"code","source":"outputs = tf.keras.layers.Conv2D(1, (1, 1), activation='sigmoid')(c9)\n \nmodel = tf.keras.Model(inputs=[inputs], outputs=[outputs])\nmodel.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\nmodel.summary()\n\nlog_dir = \"logs/fit/\" + datetime.datetime.now().strftime(\"%Y%m%d-%H%M%S\")\ntensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:45:16.229286Z","iopub.execute_input":"2023-12-13T14:45:16.229556Z","iopub.status.idle":"2023-12-13T14:45:16.351019Z","shell.execute_reply.started":"2023-12-13T14:45:16.229532Z","shell.execute_reply":"2023-12-13T14:45:16.350158Z"},"trusted":true},"execution_count":45,"outputs":[{"name":"stdout","text":"Model: \"model_1\"\n__________________________________________________________________________________________________\n Layer (type)                   Output Shape         Param #     Connected to                     \n==================================================================================================\n input_2 (InputLayer)           [(None, 128, 128, 3  0           []                               \n                                )]                                                                \n                                                                                                  \n lambda_1 (Lambda)              (None, 128, 128, 3)  0           ['input_2[0][0]']                \n                                                                                                  \n conv2d_19 (Conv2D)             (None, 128, 128, 16  448         ['lambda_1[0][0]']               \n                                )                                                                 \n                                                                                                  \n dropout_9 (Dropout)            (None, 128, 128, 16  0           ['conv2d_19[0][0]']              \n                                )                                                                 \n                                                                                                  \n conv2d_20 (Conv2D)             (None, 128, 128, 16  2320        ['dropout_9[0][0]']              \n                                )                                                                 \n                                                                                                  \n max_pooling2d_4 (MaxPooling2D)  (None, 64, 64, 16)  0           ['conv2d_20[0][0]']              \n                                                                                                  \n conv2d_21 (Conv2D)             (None, 64, 64, 32)   4640        ['max_pooling2d_4[0][0]']        \n                                                                                                  \n dropout_10 (Dropout)           (None, 64, 64, 32)   0           ['conv2d_21[0][0]']              \n                                                                                                  \n conv2d_22 (Conv2D)             (None, 64, 64, 32)   9248        ['dropout_10[0][0]']             \n                                                                                                  \n max_pooling2d_5 (MaxPooling2D)  (None, 32, 32, 32)  0           ['conv2d_22[0][0]']              \n                                                                                                  \n conv2d_23 (Conv2D)             (None, 32, 32, 64)   18496       ['max_pooling2d_5[0][0]']        \n                                                                                                  \n dropout_11 (Dropout)           (None, 32, 32, 64)   0           ['conv2d_23[0][0]']              \n                                                                                                  \n conv2d_24 (Conv2D)             (None, 32, 32, 64)   36928       ['dropout_11[0][0]']             \n                                                                                                  \n max_pooling2d_6 (MaxPooling2D)  (None, 16, 16, 64)  0           ['conv2d_24[0][0]']              \n                                                                                                  \n conv2d_25 (Conv2D)             (None, 16, 16, 128)  73856       ['max_pooling2d_6[0][0]']        \n                                                                                                  \n dropout_12 (Dropout)           (None, 16, 16, 128)  0           ['conv2d_25[0][0]']              \n                                                                                                  \n conv2d_26 (Conv2D)             (None, 16, 16, 128)  147584      ['dropout_12[0][0]']             \n                                                                                                  \n max_pooling2d_7 (MaxPooling2D)  (None, 8, 8, 128)   0           ['conv2d_26[0][0]']              \n                                                                                                  \n conv2d_27 (Conv2D)             (None, 8, 8, 256)    295168      ['max_pooling2d_7[0][0]']        \n                                                                                                  \n dropout_13 (Dropout)           (None, 8, 8, 256)    0           ['conv2d_27[0][0]']              \n                                                                                                  \n conv2d_28 (Conv2D)             (None, 8, 8, 256)    590080      ['dropout_13[0][0]']             \n                                                                                                  \n conv2d_transpose_4 (Conv2DTran  (None, 16, 16, 128)  131200     ['conv2d_28[0][0]']              \n spose)                                                                                           \n                                                                                                  \n concatenate_4 (Concatenate)    (None, 16, 16, 256)  0           ['conv2d_transpose_4[0][0]',     \n                                                                  'conv2d_26[0][0]']              \n                                                                                                  \n conv2d_29 (Conv2D)             (None, 16, 16, 128)  295040      ['concatenate_4[0][0]']          \n                                                                                                  \n dropout_14 (Dropout)           (None, 16, 16, 128)  0           ['conv2d_29[0][0]']              \n                                                                                                  \n conv2d_30 (Conv2D)             (None, 16, 16, 128)  147584      ['dropout_14[0][0]']             \n                                                                                                  \n conv2d_transpose_5 (Conv2DTran  (None, 32, 32, 64)  32832       ['conv2d_30[0][0]']              \n spose)                                                                                           \n                                                                                                  \n concatenate_5 (Concatenate)    (None, 32, 32, 128)  0           ['conv2d_transpose_5[0][0]',     \n                                                                  'conv2d_24[0][0]']              \n                                                                                                  \n conv2d_31 (Conv2D)             (None, 32, 32, 64)   73792       ['concatenate_5[0][0]']          \n                                                                                                  \n dropout_15 (Dropout)           (None, 32, 32, 64)   0           ['conv2d_31[0][0]']              \n                                                                                                  \n conv2d_32 (Conv2D)             (None, 32, 32, 64)   36928       ['dropout_15[0][0]']             \n                                                                                                  \n conv2d_transpose_6 (Conv2DTran  (None, 64, 64, 32)  8224        ['conv2d_32[0][0]']              \n spose)                                                                                           \n                                                                                                  \n concatenate_6 (Concatenate)    (None, 64, 64, 64)   0           ['conv2d_transpose_6[0][0]',     \n                                                                  'conv2d_22[0][0]']              \n                                                                                                  \n conv2d_33 (Conv2D)             (None, 64, 64, 32)   18464       ['concatenate_6[0][0]']          \n                                                                                                  \n dropout_16 (Dropout)           (None, 64, 64, 32)   0           ['conv2d_33[0][0]']              \n                                                                                                  \n conv2d_34 (Conv2D)             (None, 64, 64, 32)   9248        ['dropout_16[0][0]']             \n                                                                                                  \n conv2d_transpose_7 (Conv2DTran  (None, 128, 128, 16  2064       ['conv2d_34[0][0]']              \n spose)                         )                                                                 \n                                                                                                  \n concatenate_7 (Concatenate)    (None, 128, 128, 32  0           ['conv2d_transpose_7[0][0]',     \n                                )                                 'conv2d_20[0][0]']              \n                                                                                                  \n conv2d_35 (Conv2D)             (None, 128, 128, 16  4624        ['concatenate_7[0][0]']          \n                                )                                                                 \n                                                                                                  \n dropout_17 (Dropout)           (None, 128, 128, 16  0           ['conv2d_35[0][0]']              \n                                )                                                                 \n                                                                                                  \n conv2d_36 (Conv2D)             (None, 128, 128, 16  2320        ['dropout_17[0][0]']             \n                                )                                                                 \n                                                                                                  \n conv2d_37 (Conv2D)             (None, 128, 128, 1)  17          ['conv2d_36[0][0]']              \n                                                                                                  \n==================================================================================================\nTotal params: 1,941,105\nTrainable params: 1,941,105\nNon-trainable params: 0\n__________________________________________________________________________________________________\n","output_type":"stream"}]},{"cell_type":"code","source":"################################\n#Modelcheckpoint\ncheckpointer = tf.keras.callbacks.ModelCheckpoint('model_for_nuclei.h5', verbose=1, save_best_only=True)\n\ncallbacks = [\n        tf.keras.callbacks.EarlyStopping(patience=2, monitor='val_loss'),\n        tf.keras.callbacks.TensorBoard(log_dir='logs')]\n\nresults = model.fit(X_train, Y_train, validation_split=0.1, batch_size=16, epochs=25, validation_data=(X_train, Y_train), callbacks=[tensorboard_callback])\n\n####################################\n\nidx = random.randint(0, len(X_train))\n\n\npreds_train = model.predict(X_train[:int(X_train.shape[0]*0.9)], verbose=1)\npreds_val = model.predict(X_train[int(X_train.shape[0]*0.9):], verbose=1)\npreds_test = model.predict(X_test, verbose=1)\n\n \npreds_train_t = (preds_train > 0.5).astype(np.uint8)\npreds_val_t = (preds_val > 0.5).astype(np.uint8)\npreds_test_t = (preds_test > 0.5).astype(np.uint8)\n\n\n# Perform a sanity check on some random training samples\nix = random.randint(0, len(preds_train_t))\nimshow(X_train[ix])\nplt.show()\nimshow(np.squeeze(Y_train[ix]))\nplt.show()\nimshow(np.squeeze(preds_train_t[ix]))\nplt.show()\n\n# Perform a sanity check on some random validation samples\nix = random.randint(0, len(preds_val_t))\nimshow(X_train[int(X_train.shape[0]*0.9):][ix])\nplt.show()\nimshow(np.squeeze(Y_train[int(Y_train.shape[0]*0.9):][ix]))\nplt.show()\nimshow(np.squeeze(preds_val_t[ix]))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:46:47.590276Z","iopub.execute_input":"2023-12-13T14:46:47.591065Z","iopub.status.idle":"2023-12-13T14:48:08.937566Z","shell.execute_reply.started":"2023-12-13T14:46:47.59101Z","shell.execute_reply":"2023-12-13T14:48:08.936557Z"},"trusted":true},"execution_count":47,"outputs":[{"name":"stdout","text":"Epoch 1/25\n","output_type":"stream"},{"name":"stderr","text":"2023-12-13 14:46:50.937236: E tensorflow/core/grappler/optimizers/meta_optimizer.cc:954] layout failed: INVALID_ARGUMENT: Size of values 0 does not match size of permutation 4 @ fanin shape inmodel_1/dropout_9/dropout/SelectV2-2-TransposeNHWCToNCHW-LayoutOptimizer\n","output_type":"stream"},{"name":"stdout","text":"42/42 [==============================] - 13s 126ms/step - loss: 0.5503 - accuracy: 0.7492 - val_loss: 0.4224 - val_accuracy: 0.7633\nEpoch 2/25\n42/42 [==============================] - 3s 64ms/step - loss: 0.3217 - accuracy: 0.8147 - val_loss: 0.2557 - val_accuracy: 0.8971\nEpoch 3/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.1979 - accuracy: 0.9250 - val_loss: 0.1529 - val_accuracy: 0.9414\nEpoch 4/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.1475 - accuracy: 0.9429 - val_loss: 0.1286 - val_accuracy: 0.9506\nEpoch 5/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.1312 - accuracy: 0.9504 - val_loss: 0.1170 - val_accuracy: 0.9557\nEpoch 6/25\n42/42 [==============================] - 3s 64ms/step - loss: 0.1270 - accuracy: 0.9521 - val_loss: 0.1160 - val_accuracy: 0.9565\nEpoch 7/25\n42/42 [==============================] - 3s 64ms/step - loss: 0.1128 - accuracy: 0.9573 - val_loss: 0.1048 - val_accuracy: 0.9603\nEpoch 8/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.1076 - accuracy: 0.9599 - val_loss: 0.1002 - val_accuracy: 0.9624\nEpoch 9/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.1051 - accuracy: 0.9605 - val_loss: 0.1028 - val_accuracy: 0.9614\nEpoch 10/25\n42/42 [==============================] - 3s 64ms/step - loss: 0.1029 - accuracy: 0.9611 - val_loss: 0.0965 - val_accuracy: 0.9627\nEpoch 11/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.1033 - accuracy: 0.9606 - val_loss: 0.1045 - val_accuracy: 0.9590\nEpoch 12/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.1025 - accuracy: 0.9608 - val_loss: 0.1074 - val_accuracy: 0.9574\nEpoch 13/25\n42/42 [==============================] - 3s 64ms/step - loss: 0.1019 - accuracy: 0.9608 - val_loss: 0.0930 - val_accuracy: 0.9649\nEpoch 14/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.0947 - accuracy: 0.9632 - val_loss: 0.0889 - val_accuracy: 0.9656\nEpoch 15/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.0936 - accuracy: 0.9641 - val_loss: 0.0924 - val_accuracy: 0.9629\nEpoch 16/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.0928 - accuracy: 0.9640 - val_loss: 0.0874 - val_accuracy: 0.9660\nEpoch 17/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.0897 - accuracy: 0.9651 - val_loss: 0.0840 - val_accuracy: 0.9670\nEpoch 18/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.0898 - accuracy: 0.9648 - val_loss: 0.0895 - val_accuracy: 0.9655\nEpoch 19/25\n42/42 [==============================] - 3s 66ms/step - loss: 0.0889 - accuracy: 0.9651 - val_loss: 0.0845 - val_accuracy: 0.9661\nEpoch 20/25\n42/42 [==============================] - 3s 66ms/step - loss: 0.0866 - accuracy: 0.9661 - val_loss: 0.0827 - val_accuracy: 0.9673\nEpoch 21/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.0859 - accuracy: 0.9662 - val_loss: 0.0848 - val_accuracy: 0.9676\nEpoch 22/25\n42/42 [==============================] - 3s 66ms/step - loss: 0.0880 - accuracy: 0.9650 - val_loss: 0.0806 - val_accuracy: 0.9672\nEpoch 23/25\n42/42 [==============================] - 3s 66ms/step - loss: 0.0828 - accuracy: 0.9674 - val_loss: 0.0775 - val_accuracy: 0.9697\nEpoch 24/25\n42/42 [==============================] - 3s 65ms/step - loss: 0.0819 - accuracy: 0.9678 - val_loss: 0.0780 - val_accuracy: 0.9699\nEpoch 25/25\n42/42 [==============================] - 3s 66ms/step - loss: 0.0813 - accuracy: 0.9679 - val_loss: 0.0756 - val_accuracy: 0.9704\n19/19 [==============================] - 1s 16ms/step\n3/3 [==============================] - 0s 13ms/step\n3/3 [==============================] - 0s 13ms/step\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAd4AAAHVCAYAAABfWZoAAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAD05UlEQVR4nOz9eawt6XXeB68a93TmO192N7tJtkVK1EyJbkkwPDTCKLYhQUQSfmAQWhaiICHtUASimIFIQIzsjoXA5keDlizDkClAihP9YSWIEQYBjdiIRU20pZih1KQkit3s7jvfM+2ppvf7o+WzfmvdgWRyecjjbz0XF6i9d1Xtt96h6uxnrfU8WUopSSAQCAQCgVNB/rVuQCAQCAQC//+EePAGAoFAIHCKiAdvIBAIBAKniHjwBgKBQCBwiogHbyAQCAQCp4h48AYCgUAgcIqIB28gEAgEAqeIePAGAoFAIHCKiAdvIBAIBAKniHjwBgKBQCBwiviaPng/+tGPypNPPinj8Vje+ta3ym/8xm98LZsTCAQCgcBXHdnXSqv5f/gf/gf5j//j/1h+9md/Vt761rfKhz/8YfnlX/5lef755+XixYsPPXYYBnn55Zdlc3NTsiw7pRYHAoFAIHB/pJTk6OhIrl69Knn+JX7Tpq8Rvvu7vzu9+93vPnnd9326evVqeu65577ksS+++GISkfgf/+N//I//8f/r6v+LL774JZ9hpXwN0DSNfOpTn5L3v//9J+/leS7PPvusfPKTn7xn//V6Lev1+uR1+uMf6f/fn/sFmUymUsuW2X91e3Wyvby+ONlu77Zmv+FQz9m1Sc8/FCfbmVS2LQNelN3J5uzChtlv68n6ZHvj6vhkOx91Zr+7+9qGL/6utnv9uYOT7WZt/3oq33DuZPs1b9w+2b50tTf7bc90eCswA4MjCYZerz1v9bv6Zm53XOmB3VLP3WCXyUYSIt9G/+GvwEHsfpVov2QYplW7NPu1g15jUY30/U777vbC9tfLv62Dtv/JO9rug4XZb+i0DQVPkQazX9tqGzpcxmzPzsMnv0XH6cr36vzYuajzYVrYMWtE50PfaB9nrr+yQtvaV3q+UsZmv1KnoRRJ53XXan+l3E6IbtA25IWer3DzpmS35Nq+vrdtHTD3CgxuO9i1Jdo8SeiWvtH2FIP7JVHoOW7c1Lev/+pts1t1W2fpHPMrLdZmv/N7OqemV2Yn2xe/de9ke3S1NsekSudRL3p8ltt502faLyXnVPL7mY7VY9y1D6L92g967ht3dWyvvWCP6XAvyTOdQ2Vrx2yyrQNw4bIOzMit7wLztzrUPs5KOw/rPZ3/CU0qcQ1Nsm2tsB7XvQ5aquy8Kc3E1PZVve3XDvN/tWzxvrY737D38UmubeCduxL76Dw4PJDFYiF/6f/zDtnc3JQvha/Jg/fWrVvS971cunTJvH/p0iX5vd/7vXv2f+655+Qnf/In73n/8rkLMp3NpCrthR5VOvH2RR8e66kdiOoSbuJYFHmmC27o7EQ7uqUPgu6uLrjRwk60vNc21RUegJV9kNzupyfb6Ysvn2z3N3SfcslHm0jR6jW1Y6Xlx5fcw38TN5GJTs7SD/uAOxEW8DDYP1RyTP4BC3iJbh1N3AOiRJtK3CjE/gEiiefW6532E7Mbb5NViQWIm7MdZZF5h/7D06Kp7Ln7EosRf1Tl7saYmvvTSDs758zrS4/pH0VXn9Bx2tjVG0ApK3NMQlv7lX5PU9r+ynCzyQod5yq387AaaduznOOu5xvcg1J6XRc9HoZ1XpjdioQ2DHq+NtkHEzFkeu7B71fhj98Fzocb+mD/TpGs0nPUBdp3yd6cjw51rY4xv6rM9v/mROfr3lT7dW97R48/P+UhUowwK/EXW3JhMD4oh4T55R6o5jD0ce/m4YAfCPNOP1v/kd4fun99yxwzP9K2rnv93pnYtpav0f5LW9onmxfsXEEXyQRrP9W2j0a7eD3omA0FjsnsHC+xbHv8odiN7H0uH2FSdPjDwj14s07X92qu9+G21DbUW9vmmBIP8jbTc9duyYzHpcznr669Lyf8eSaymt///vfLwcHByf8XX3zxa92kQCAQCAT+H+Fr8ov3/PnzUhSFXL9+3bx//fp1uXz58j37j0YjGY1G97wfCAQCgcBZw9fkF29d1/Kd3/md8olPfOLkvWEY5BOf+IQ888wzX4smBQKBQCBwKvia/OIVEXnf+94n73rXu+Qtb3mLfPd3f7d8+MMflvl8Lj/8wz/8ZZ9jkFIGKaVLNm46X2k853hfAwXrYxfjRYhvsq1dUW/p3yPZ2sW1jjVOsEBCQuuSNKpXlOdPSDAqpzZIdYRY7vK6JlQd72tMI+tsu/NOE0fS8xqP3rls/47a3tM2TEaIJbt4YYmkhq4YsC0WuV5HVel15IiDDIVLqmD8EHEtH+NlclSBOGyWuWtHW4der2+NuMrqyJ57ua/bDePUnR0LxtA6xJvyzC6TLWQBlZt6vXsXbMxy+6LutzHRdldIuhlae31Nq/NovtK+W7S2Df0SSU+InU+37fm28Lqo9ZoqJI24FCcZcr2OhNyH3vUD47UFMvb6zMUsMQV6ZE3x3CIieab9VbCPsE/T2bEdEBOvas2ruPQ6OxbzV5AoeIuJmratS+zGJLGEudsONumwR1y9ZhwwszkSK8G1J+31zLWhwBUnHMO1KSIiA5IGb+l+r3zm8GR7+fk75pAO96nlGsmcuWUUsyPty3LEGKhNICxQ+VmNkJQ6tedDXpMUwnWrfVT09obDfK8e8fvRQ2Ldgv4fkksI4MtSX9S1jsUo8/kv9090y1w8WvJBJPPZJQ/G1+zB+x/+h/+h3Lx5Uz74wQ/KtWvX5Nu+7dvk4x//+D0JV4FAIBAI/NuEr9mDV0TkPe95j7znPe/5WjYhEAgEAoFTxdf0wfv/Fm3WSpu10h1bqubOtf2T7dsvKBXV7lsqoK6VDukv6/bWm5SDzmeWiMsqpUmWrVIc6zuW7h4V+N6x0sH5FUuBLVFzl46VvmjWR3qMS4svBqW2jq7fPdne/8Mds9/8Kb2OzZnyNkVhKTBBOYqpzXSiZl2h06UFHTZCCZJ0voRCqa0M9a9ZYccsL7RfmI1fJks/dY32axLt8x50XXNkz52WqNcFVTm42pQWtBLpvrq3tBLLXicjfTE755bTBcQyatBUvfZJ42izu3M9x+0/0rmxesWeejhUurPMdI6OX2PHbPUN+tnuDq53pv1dFq4uElRgAWq+Sbasrcd+KcO4JHu+lEjtgkat7VzJMI8KlhYh9JMW9pgcZUdlrWtm+rgNeew9rSUo56egTjfdPMR8m13WsSi3UKOa3BwnRWr60u5XgxLt8Fnryk8SKUuWbLm5gkuX6y/qHF/9vsav+sN9c0yF8siiRU11b8uq5pjk4z/UPpo/Yft1axPXhPtD0btrQiiCzHDBsIQLI2SgoRPqxLvchvUE9eA5prir+JEW/TqgDK0oH/wYxO3elBV2vq6+/4qY5rNRThQIBAKBwL8tiAdvIBAIBAKniDNNNa/WneRFJ3ev2d/4L/6RUhR3/1Dpp+zA0sEbyEYsD5QOnl7cOdmeXbaUyZwZh43SO+vDI7PfslH6o8MxfWdVttrbSq+s1pAnQ8Zt3lmKj1TX+kgpohuvWAnEK7eU6jyHnLWRp8rAp+Sgz7Pe0uIZsgSN2g746b6wbU2g1EockrnMVxJ0CVnDbjcj4bYGNUxJxWrsqOEakoOkrCqXtg3qLXcZz0SPVZNANY/OW/qphuJPBtWnBnTmvLFjceuavn7ld5B5ed1m0hZQl2pB08tdV+++r9ns2eO6PXtK2zrbdbQZlICQ/Cmlmw8Nspo5ULl4xTPIgYJWnXd2P0NQo4/zSvuxdtmkDPckhCHKqaW7L7xR+6V+EiGFHUudMuM2QZ4oVcjIdwpeeWL4g+Np+6tGyIgVA2Xm1zdkW8FfpsHero+Odfv2C8jWv633gaxx4RR8cYJy2DBYqvkY4ZnRbYTUvmhVo/YvIfsZ11s73rWs9RzjsfbrGOGeLnfkMBl33HsaFwKjYmTOYR/sWshXpIpxjxkhlOHO3ULmFiJbZltEpBsK6QZfBvJgxC/eQCAQCAROEfHgDQQCgUDgFBEP3kAgEAgEThFnOsb74p21jJeF3HjexopufFaDH+0r6hVWr+x+tPyrEGuoX9KYYLljY0UF9qNqzrqx8dVmTSce/d7MWbC1PAfKLga49aTexoAqnCNfqkrN8W1rhXb0ssZ4m8cQp5lY55CKalCYEVmy8bQ0MN6EIIdR67HBjx7x5BZWYcnFmXPEmBJKMsrOxslKlEK1mL51p/H7TWswIrPH9Hq7m+hLZ9vWrPFdR4gZu5heNdb2DWOoPO06RxZUE+X4rhYOKusj24bbX9C5u/y8loqxPSIiNcV6EMryZQ4dQpjHiDHOYZ24+aY9HiIXTV4DLTJdOZ4pr0CpmVNsyqCsNUbIsW7tfj3KUTIoda1RirI6tGth/Yq+Hp+D2tvYxvdmF1EiyLKc0s7DDkFCqqv1COyXpbsnQAKP6zs516E1XHBY/ubLk0zvU+1tsGM7IH7b3db7QL/C+05+rkdJX6I6WLIx3m6t6+lgoX15cNuO2fSL2r5lT5cz+2ipkE8xlLqdc225+P2Az1pz3+3dfihFhBNc4cSlGsz/AQknNca8cH1sSuYqPT5v7DwchoUMg30GPAzxizcQCAQCgVNEPHgDgUAgEDhFnGmq+aXPLqQeiRz/9qF5v39JZX6Kuf78H5yyCEXeV/taDjR/Qc0KNp60ZukZaJKUg/a8hwbS1+sjlOHcdPRarhTPAEqNZRy5o+4KUf4wAx3WHtpyqf2XlQ6Z39X9RruWqqmq++fJZ46KJSXdoIQosU7ICZ0PkJLJEmggZ5IgRkAe1Lf725D0XYk6gnGu4zSZ2tKb7ddqfw03tfxhddPSRdKA6hxB2caVDmQwPNi6pGVoW+dtqdgmSo2M2D1CB4sD2w/HL+p86GGU0TeWOu1hap8hRNFPbH91a2388jrWAsqWlgtnfvDdytXvbunxm+5ukYHioxNC7hSuOLakjaVwNCioZhlIy+rx/dKuhbTmmtE+yltLnZLj7tHW5NSlhkHbnmOcBpgIZLVtN+8Jg6GavQkHwi649Sax/VWgFKcyym0u9AOjktEE5TqYAk3hQluDnoOVM13vJjnGcOigiuXMYOYv6+u6xRwd7H5jNGqFOYqojaTchpU6hARGcExoPC2+xD0QcyVz9+QS99FlifFEF7W5K0XEfSX1FbZdydwf//tyEb94A4FAIBA4RcSDNxAIBAKBU8SZpprvfnYpVSWSXrGek9kC2WWke5zv5QCKbr1SvmFxR6nmprU2hcUGFHrgP1lnNtOxFcPjaNsOLA1aQq1l6JT+SKCY8syq61QZMy+13c3KUla3ryv1fPtlmEBsW/qpgYB/WZMucpQaus98Avq3c6pF9OCtMtDqTki/y6B6g2MyZxBBD4ZBmB2JnZzB7NY5KFy9Xq/vaGyn/wTfVVJtyVGi+UT3u/C0+pOeu2Kzmqeg8Jeg8pYYpv1DS201dxCWWIMedf26QNboBKco5pbeXCHT0lCsUKHKDg/MMes1Moq/Ta+puGr7AQndUpBKdyGdAiGGvntwKCNrYURgvJ91n41du4ZbULvTXWQeV7Zf6a3LZGMvpG98CJBZXVBUv7DzhkGAAfGsfrDrLIHTHIHS7nw/4HVCyCobLBU7hT9vuashj4SqhdrR/rnxC4GiW+bXOrL6QWn3azsPD6/p/axbMFvc3rMme/Db3tnVY5D6X7ns7hIUfKLKoDNOEfivr9EnlfMGnyJLesB8ZbZ+5gwrCtwHGEboc9sPQ27n1ZdC/OINBAKBQOAUEQ/eQCAQCAROEWeaah5eOZah6KVe28LlNT1XQVsWnlgy1LNSB6tjPV+7tFTN5LzSFRvnlN5ZbNgsvgx8Wws6uPbZgxScAKXZVchcvsfnUcmtCt6uQ3Ns9lq8cutk+4/+UI/ZuGj/3noNhOIzePPKPZrf8DFFv65wfYMXWTA0NMT3XcZnmYEmRLpl67xwOyHNrmNWl7o9re20LjZQ+P5avb7xOUfDIQO0phdoaTui3EQm80UVn2BmqYhIBi9iZpMeI/l8/6bLfL2jlNyEA1DZedNSYAX0ZrO2/Z8j/LDGRGp7bURx5LKaQd3dmJ/X/b5j1+x36XXavs2Rtm/kxOm7BiEGXFMqXFtJ7zOsAeGJ/JwV6R9tglqssBYKS8vmyLZPyIrNHCVaYkqkpH2UQwBi5MQhqO3fCzOm7dhmifQkM97t2DKrv6Nvtadi0Y4x6O/RGHT3ylHz+K6cntO2G6TAG/UUwjfO1GMxR0b9kV5f4YxKyktKf5e7/F5Widg28A2urN5latNPN1/p2M6nLkSEmIUVOtF9MkdjD8gk52dZ5sxIhsr4An8pxC/eQCAQCAROEfHgDQQCgUDgFBEP3kAgEAgEThFnOsYr7bHI0N2jUJIhNT5BQcUrEDFyYATNV3pMcuUZ48eU219CeH10wamuQEQ7g8B6PnXm8oj9VQOCfyVVfFyMEccwQFE5aa5uX2O+t35ft79wdWb227ioHbOL2pTKlU30OfoFpTeZaZ/9Wy5HSUUG1XIbpRFJGLN1omGCi38h+Jch1pPDhHvs4sw0tc+2EKvbttdX1lDKGRD3rm08p55qnLGaId7uxNtblIwsUbp2cFuv6eAPrOpaNmf5AkooMntuVLLJgDKTZm37iypSTQtFMCgB9YU9dwHzgv7/0na/4MzSiw3Ety8ivlXYOdBgfQ4oTWGZkYhIVkOFCqfIYCoxuHOnCjOJB7n9csaTYQCf+1sg8ywwl7NKt9veH4M5jjUiLl6YIybbCde9i/PTmCJjqYvdL9UwdkEOwJQmHjObe8IuarBuq6lT6BvB9AKlXWtXTjSghKjF7Su/afu/fgX5ADCzmG6gTKu28fscfVnw3uGSXtZUmUMjupXNeVlWWKsY265lvN3GphGClm5gCZLLIZBM8nvuag9G/OINBAKBQOAUEQ/eQCAQCAROEWeaah5JIbUU4utecpToFFRIclRsDrkj43HLtP2VPWbU6neVkO6ZbFnVom6OrkUbqg2bct4cQwj/AGUOuKbG0RoDqJZS4DPqhLtTUqqlf/mlk+27v2up0zuv03PM9vQ68tqJ3VNVHXTbiL6lbkq1VMQBTZyc9yaF8EuypclR8zif8fKkio9Xu4LjRD7Va5o6OpLMeoGyqvHY0nA5aD2WiGRO7L4FtUhx//ZllKm87LxrSVeT5nK0bNnAW7SjEYi99p5hCfydnfeY772jyCudAwlzcvVZS93dfo1S4ee2NHxRzzyFDHq/YHmfXQupMor5J5u8osHT3RjbjD7Ozqyj4bWDwswdtdjxHChxqzC/8mTLFxPKpziaVXKxLdQdNeY3jytNwfkTzpEcxZrBgGRjrPt1KA9MG071bq79ssK8SRftOmOJYHtDr6pZWuW9tNTrWEIBbzi04zTZ135dHUExEPM4G1tafGa8t41k3QORQ2FMGqvIhoiFjNDnvF/4UAZV60rji24bkbLchMG+FOIXbyAQCAQCp4h48AYCgUAgcIo401RzPqklL0eSH1jqZ4m/JwbQzl7sviKXB5H+FtRiZhkYWS2hbrTQD2dOTWVA9jIpsDRzSjJQGiJTQdoiOSpw3SuNs86ZqeeUckA7lmul1JqXLF10fBNU8etAnWZO0Qht6joIyIOq6WrbD6TDOBYU7BdxYvUwhchdxi3DCBmo5gJ0fJY7f9MKCj+NXt9QWYovldr2YopM9JFTNwI7SSODlVNJz5EFmUB9NvMHZ7QmKC61HWWUXL92NFDQ8+V2iptwisnir5iV7ryk8bqDqcH4yFKBnEfdm/Tck6kNuww04chhuuD8VwfQ6R3blJHOt20lozxA4L5wYvdUsGcoKXeUYQE/VuO9Daqzc+OcUXAfay45qnmAh3IOP2tx2fAF5jiV2gbnyz3GutvYwn5XtY+7lQtl3IJRwArbU9uG+RrzcA1qeGHvtYL9Ev22j2wYYX0Xfrygu1tk1496O2YNsvppvpI5xTNWpHBO1e7m3SGcOKAsAG9LkRw1j/tP16J6wK/HP85r/nIRv3gDgUAgEDhFxIM3EAgEAoFTRDx4A4FAIBA4RZzpGG91YSJVNRG5a1PX80QHDsS/fEkG4icl1E+mV7dPtmcXrMrTMIdB9FzjDiPXlQMqUIZe4wYujCHLkiU2+r6pqEk2ttZDjSuxvMLFZEvj0MISKdtf3TFirwgJ9c7RPEeJR7+EEhMCbTMfk0XQkX7fg3d4Man4SO8vbblH1ut+Dfo80cXIKQuxNEtQXpPcmNUsHaATSe9cR1pcSE8zcdtfDcyyB7oJwfDdL8AB8eiOZQ6tPffAyUKVp9KdsUWMHfHeGnkHgyu9SVBDK+jK4+LHNeKwHFvvplVlzHdAiZWL8xthJpyjGBjXdzFxlOplcIdJzqi8ZP+n+5ehiYjkVIJD/UmTM6bucimwtipcROudbvC6QGnK4MpQSlxTQTN4F98uoKa1eR7xy9dpfx9fc45ZcEcbHWq8dulyDdql9sMKilTd0uUxdNqvJSZi37g47BrqUBiaouW92oJDYwzp3X3uQUU+WW7jtUWp9/IM90Yqq3lHtipXNa2uQHzbjW2RZ14s7aGIX7yBQCAQCJwi4sEbCAQCgcAp4kxTzVeemshoNJXb+5YmmbwC6hS54iNXYlBB/HsKQ/PL36qG33vnLdWcfUHVe1YDOJOZpSNrUGpr0jPJpfdTaQWlOHlDIwRziKVTSN86GrsANZxD4acq3QlrbXsHem21doL0EOBf3IEJPUTZR5uODkPjC6oHZbbkJyXl5ll21LXub8OEUhww5qQCc9cRGcZpKLXUInMmEDSFoOJZ5ajYstM2LLGEymTnISrPDMVHU4ksc+ULI+0XCvh7829ptQ01+iuVtq0MF5DZpcF642gzGndMOSd9qRgUqrLZprbBMfMsc2s5e124gXEY0vZsXePmLunuAf1fuBI8xnEa3BNKxy2S9V3l7DvMXVdOJANL5rRErXBrvUQ5UNeTTrbn4/S1oRp77R0MIma7CJNgoMvChmpSCSUyhLmOj53a2xLH8RSujKZEh1VQ5po4yrbkPEL4yLTO9Stf5pgPjaP6B1D9A8Z92dlGrBvst8J9CSVz9cSVl+H2PIZqXuXW46IcJL/XheeBiF+8gUAgEAicIuLBGwgEAoHAKeJMU82vecNIJpORjBeWUrgG6qyBL+7IibdPd5VGvvD6CyfbV79Zac+tyqo8dTA1GJCpt+yskP5Ar1hkEWcHPtsSHrBozxIKOFljs5ArUIEQkJLcia1TvWc0AnW6Y5WFGhg3LEAvZ2v7vesFKLVjeIHCu7N3VBQZGapx5b2nrPSa1lQg8pmhyKJsQaN2oJozR3NloOSYOdvlLlscNFWeIUPWqRt1oL1o9tA5irvo4fsKY4WJRjJksWOPyfdBSYOOrFyq8AAKktnYsuEU1KAateDlggb1PqLjEnQpsv3zsf07fbat82iK/SqX2U6FsRp9lJyhQxJmgXNsBe87YwWaaEB1qvXeqFSrQhu63F5Tge/N6P3MSgnPKOIULSZY6bLrEw5MCD10LgM7MUN8hVCEU65iCIo0Z72n95HN0h7TbYKyLTRduf/9fbNf3/E4jJ/Lmq/p6YsM+OmG3W9jE6GREdT/zPp2GevsF2a2u3tHgirfstFrunlobwRzqHa1d9QHm1n825ddxvRl/d6tPXgK564qYxhJ7kILD0P84g0EAoFA4BQRD95AIBAIBE4R8eANBAKBQOAUcaZjvJNzY5lOx/Lab7Nxn509mC4jtlPu2NKN7V0Ntm2e3zrZnu3sn2wXTtElR7nGrNb40nBg27A4hpvGIWJKS+ecg/KIaotxMlXP6p3B/bBArAiBnsxb00w1Vtdf0PMNT9kYbw6nmuPbGtPu5/Z78wZlCqgXaBH/WvU2zjyiUTxiXJkzQe8RR81MTNUF1MzLBxma23HOGB9FKcnD3EQYc/Yx0J4lGoy3uxIDutZsoJxr9wlt3+plG0dvl5hTUMVK3v2KMjl0V3HyUhXGqT+E+s+K5WXuGMybYqbtKV9j+3UH82iEsrjkYucFzdwTS7Esco4N9muYq5BcrBtuMnQQ8qbxjImX7EoXN+1xfq78imVLbj5wfiQTjza7STmw3Annc+VqSEuRxR2UVXWuHJKx9C2oYo0RZ3Z5LaOljm0+UVWmKrOjUUJ5qkQct3TyTJw7k4l+13TPXtNEqzWNSmCB2HSWuXst479QHczdHOhbXUMHyD258TmzmzSfvn6yvboDRTC4Qx1ftPevu9+g7Tv3bfqMuLLnXLJSJ+tkS7cehvjFGwgEAoHAKSIevIFAIBAInCLONNU8znIZZ4WMnrSlPBtXUN4CdZxhZo2RJ6SNc6VaikrT8QurrSIdDKxzmEdXC0uvVXf03LfXEPO/7agfpslD9HxvS7cP201zzOoIBt1Q65lMLU2ycQH9cgUG5Bcszdse3jnZPr4NY/djR/3AZHq0p7TX1iHosNqpxYAirakc5lTE+gTFJnxt4yjD3NCYoOtAU2WlozpRX0SjgJFTmiEV3qEMh+L7r77WtrLMpM5tW1e49mIEqhk03PINlr69dRtlNChXK1wUoUKTqEhVFLatA/qvHuk1tei7csf+/T25oOO8cVnnze7T22a/jceUqlwjXFG4spAcMvY9+rh04QaGTagcRiUm18XSDg+gKkt7TRnoSasAZffr3bw8+Z6cbbXXVyKclaHEzZeXDAI6nqVTrqzq+La27/gFupbY751O9bgZSnkmld4Hxu7+xXEagzauSntvzNGXOZXHKnuvHSOEMt3Qc2y6sF4BKrzGRwxz1b7rsbZ6yFh1gw3XLRd6jusv6PUe/18HZr/s83qPX0MRb2A50i07Zsd3oIS1wjh/u73XTiYiCxs1eijiF28gEAgEAqeIePAGAoFAIHCKONNU8yCDDNJLtWlpkjFUmhK8G6uxy0akP2kGRSootVQuNbFC5qXAO1WmljYrRkpr5AegN6/Z8w0L9XgsoLA0Yhbmtr2+FqYGGWjU8a6lP8qr8HadgracWyp2eVdVXHpkTGcrS1OVMBiYtPAvBr08jO2UamdKTxaGS/J0JLN0lUrqXGZogYxnk7lKitCNGWnawmSkOqqZlCYzq52yEKWLElSQ2syOU0rw7wSVN0ZS+eaTto/nN+EXfITMy5VrK19AIalt7RzvoL5U7yI8cEHnyvkn7byZXtbXk/NKLe5ubJj9DAOPzPt8sNcEC2XpMBiT3lKsHdZWb9TL4PPq6MialC3Gb53ZNkyQUZwhW3bwoQzQwR2+rIM5bOXo22Fg/9EAwCueaVt7hDn6xl7U6kj3W1zXOdC6OXA00tc7pQ7GeSjJedH/CjRvhYzn2bb9DbYLNbt+gXBd6+6HEz3hxjnd3tq1lRNbuD+WMFWh8cY9LD/o7gF92brleHSobdr/jJrYrF88NvtlCx2bAs+F1On9cFi5sYAZSYJxzV3ZMfulpyeyWNw/THE/xC/eQCAQCAROEfHgDQQCgUDgFHGmqWYpcpGikNxxFCVEuFmbbgk1kSKnBywE/FEIPfh0UnxVie8dO0p0htS9+bZSjv2289QsdL8KmbQ0WRg7Qe5uhsxEUEzFnu2HFpmEx6jKb+4cmf3mh9q+AexMtnY+xyUFK3b0eAiW1GtLt2ZrPXc31mstXRF81jGDUbCfK1RHJmyPvxspnlDfQyFDnMN4fD5ElALnHjnqlJ7Ay4xjZv+OLUFDUwygrZAJumXn1/Yb0fZGZ+ziBdtf5Ry0OIYps/bRsnNFz3HudRDDuKRU4OZ521+zCUIZI2YU2/mwAudXwvu0qW3YJYd5QdHgs9JeE/01EkU3MtKRTjwBr3uEiEat89nFONEYoXd0cNHCY5he3ghf5MkL5KMN4N+Hwo2ZmfMwWHFU8+IW9jrQNVc6GvQYVQflXLeRvC7br7frscZ9aYps9q0rdo7njd4IRmMYKzR2jk8n+vr8FdDOj1mqebKr+xUzbGMtdF4AiOEofOYFWppOw3rDbf2sd2JFPdYxPaxz3HdT6apYGngov6Tbd/+Vo5WHVpYra6jzMMQv3kAgEAgEThHx4A0EAoFA4BQRD95AIBAIBE4RZzrGm1czyauZlGLjCaMSBs8wNHfhHBPwyzKN97YoUchdjLFAmUKGmF7m4oojKLHXMJ8eX3Xxx2MIrGM4CsQghs1dcwxj0AJz8jRzcVME//KFxkhWC6fOclfjOe0hrmlt27ocax+VW3qOLaTpS2vb0CL+xfKRyg1GhvhhQrBvSDauWDDGB3WjAaUaXWWj+TQJzzHmLlwlGfq/Siw3sG0YEMcrEL/0ZTRjiMu3jE1j1VVuCe5d0bZuou7o7kV77uK2Xu8I+83O2zhZjbKh/Byub6rbzt9echpvoLubxpW1HcNQY3l/1S8REXrN1zVKRDZcYgTiePQDKDFXaGIvYmP+Ax3qXUnZgGsyngSuCVmuccGCcWGU7aXe3m8GqmJlGmPMXCyYQv8yIF74io1F3v5DLW2s4F3QuxBiNtc5sYbZRreJfJUrTnVthjgs8k2Gy7ZUjGNRIwfAr4XRRNuwi3Ki6pz93nJLX1dTmCRArS/P7WAwJM58Dp9LMUCBcIX12LW2XwcsPN4veuQkDG49JpTJdTCOWFyzqlj5aC2rdiFfLuIXbyAQCAQCp4hH/uB97rnn5Lu+67tkc3NTLl68KD/4gz8ozz//vNlntVrJu9/9bjl37pxsbGzI29/+drl+/foDzhgIBAKBwL89eORU8z/7Z/9M3v3ud8t3fdd3Sdd18l//1/+1/Dv/zr8jn/nMZ2Q2e7XW4cd+7Mfkn/yTfyK//Mu/LNvb2/Ke97xHfuiHfkj+xb/4F1/Rd43LRsZVJeU9YvdKr1GIvXDemwMUkgZQyoURLfdC7vq6G1jaYhWyC3i2zuCJWlyxNFW2UtolpyoMvDY7L9IPJZ8O177MneoKlKcamBAsO0vzrtf6ejkHn9XYfp2Al1s0Sis18BbtxFKdFKSnjW3m6KKeIvSgbLNkr52OABnUxgxz7SjfrsQ0h4lAeU/5AuhIUItrp1yVcL0sEfFVR23BOYUmwENWnKlBPYZa1SUYMOzYMRshDFBTyczR7BnNZyFoX6K/vQ/qQDoXJWXdwvGyqOrYPyAd7D2nYSaC8qlUVW4/hlr0/YTB9R63AxWuqFaVW1q8p2cu1lM52NKUHopGuTm37pPldq3bMAlKi5KjRHGPWKO8bH7HUax3db8WYaG0thNs4wLvbaBisU9jL082NvVCJlCTGs650A/KFPsWql+DXQtZxZCazr2RU/IrUXZUo/YyxxrMnSwZTTMqGES07h7TY970MF1Yru011aDJuwqUNOjk3t1vWixqlu0VC3vuxa1G1p2d9w/DI3/wfvzjHzev/+E//Idy8eJF+dSnPiV/6k/9KTk4OJB/8A/+gfzSL/2S/Nk/+2dFROTnf/7n5U1vepP82q/9mvzJP/knH3WTAoFAIBD4usFXPcZ7cPBqEHpvb09ERD71qU9J27by7LPPnuzzxje+UZ544gn55Cc/ed9zrNdrOTw8NP8DgUAgEDiL+KpmNQ/DIO9973vle7/3e+XNb36ziIhcu3ZN6rqWnZ0ds++lS5fk2rVr9z3Pc889Jz/5kz95z/u55FJILiNp73PUv9kHGbKONpaBnpOge0BZ9Y6+zXulUyrRLLbcidOvQJtU8AbNL1g/y2wNQ4cVKSxQZY4KbEHlLaBAf7S2vNIKVPEc2cbJqYwPyP6jELhLYDR0j4BuZfbhcE82qZ6vBX2bufAAM0PpmZv7jGJkhtIXt0BWus+OrKhcBRrVT/4cY01KreucKD7Vr+D3vM7s90JAzdKWnK+OjqwKnV8UX9pxKkjVBo5jFrhYirUokGWLedRQ6L+x5+6Q9ku1pKK1abUr+AULDR162w8rjCenMj2KRUSyEmEEyC8NyHxtnUHBGHMyh+pUZ20kjFEGs89Ll3ncIis2YTxLjHNyqdAJNK/x2XVtYGZ1gtJX4RTUanhxJ9wSynN2rjz2LRq2GqBuN0e6/sHLrioAkYh6E4YVTkEtB307YP53mVs1MAYZYcLT8EVEJGPGOsIrvKLarYWEsRnk/h7YIiKjQvebwIBh31ct4L7XGgMGjLkzfDZmHayC8eYt60by7sHPIY+v6i/ed7/73fLpT39a/tE/+kf/r87z/ve/Xw4ODk7+v/jii4+ohYFAIBAInC6+ar943/Oe98j/8r/8L/LP//k/l8cee+zk/cuXL0vTNLK/v29+9V6/fl0uX75833ONRiMZjbzSciAQCAQCZw+P/BdvSkne8573yD/+x/9Y/uk//afy1FNPmc+/8zu/U6qqkk984hMn7z3//PPywgsvyDPPPPOomxMIBAKBwNcVHvkv3ne/+93yS7/0S/I//U//k2xubp7Ebbe3t2Uymcj29rb8yI/8iLzvfe+Tvb092drakr/yV/6KPPPMM195RnM1EakmJn4gItIjxpQhntA5/p5xn5LxIexXiC85oeE63oVDhohIgVhpCbPn0czZx6z0JGvs1yAO5UyCZH6ssYTbB7p9fMu2YX1bY3LtXY31dce2HKJukGZPFZ7k4mQIbmaI5TZ08GhsnKPptXQmQRWod65PjJnQ7SVLLkUffdFBlaxHXL7O3HzIoN5Es3pXJlQjhtMjXuPLHAQlC+aT5OYK4u89lcjwPVVmr4/lFSXmXuZyDTpTb0OlLxePTvwumImjtKXsnZvQinMP517Yv9PXB4ivdizJsP2QVnqNneh8WJT2e8eVtmk0QhwQY165fAeGBZmCkLlYJOO1A/py5WK8RokMYzGw7wZXpoJp1GIsqszmXDAXokNpUNbb841RfphdRImOu3VkO5sn2/M1cj2+qLknoxft/GI8dONPoP+dfFkxu7/qWu3WY0I+BVXhUmfnazvXa6zRfwMU1FaVDZxiKIzaWNm7OD/W42xTP6tG9nwt7ps58l8yPC/Gpb2Hplr7mAHyLHP5Qnkj4tbow/DIH7w/8zM/IyIif/pP/2nz/s///M/LX/pLf0lERP723/7bkue5vP3tb5f1ei1ve9vb5O/+3b/7qJsSCAQCgcDXHR75gze5jLP7YTwey0c/+lH56Ec/+qi/PhAIBAKBr2ucbZOEPJM8z2TIPG0Jug4G8F3pqAAcN8CIvUNqflk743qktSfSLk4VCyyjoZqnlS+j0ddrUBVz6G3f3rf0zt0vqpH9wUtKJ69etjRJe3tf27pCmUPj6DqoIOWgHSuX3p+DbqN3QQ+6fDh0KmIrqPpQxcrRt6RuqDIkySkLocynNSVIaHdm210atSscU47Nfhko1j5xPtixZcQiQ/kI1aBe/QJcE+ZkzlKG3C5BGjUM+KK8d/EGtIGlSuJKUxKutxn0enuWSDkjdkGZ0GIOw5G7lhJdQckqzfWY1pUT1SiFIh0pK1eWs8Qc3YYaEX0xXOhnRAMMozzmSpXwVSwNan0kCeevTPipwx5uLPhjY2Dpk90v5z2mV1o9HbpyIsz/fA/qUms7r699WvtrcaDjVBzquYvKzq/lNVz747jPTex+wwihKYRnKl+SiWvMUXp2dORKgw61rQXNMRAiGrvwE40aGnDNnuatMTbTbS0rLKb2ftjf0ptqwvnM8PW2HyagwhmbrGtbtjfaySU5g5iHIUwSAoFAIBA4RcSDNxAIBAKBU8SZppqbdSNlWcl6YtWgoMEtPYSrq95lu46gWAKKqKQyzeAzVXWzQwZj67MoS2TxIfOvd1QzKdvFWs9x64bSRa/8/r45Zv/z6gXZvqxeusu7R2a/HjRh1oGydepSOaZBXUABqra10yNQsyX7qwX109u/5QYmUIPiTpXPOmU2NTJxPbWFjMYBfGuLYxo3FhX+vqyNGpGbDwmC9JxDLmu+wH5iVItstmVDcwbMFWaHO5Eto3zEb6Wa16vnGGE/HefKsV09witNB+p0iUz2YzcnkXHbIxu+9yYJc33dwle66q0vaTbmOtM51Dk1rhE6o0I2PLPPe/dbIUO4IQPN3jsjA3pdM4KSucx9Kn+tmE6dM8xi14VZ0shkTt47mApqGdeP2w/9OoaCV5Nsfy1ehicsSh8KZra7eZPmGM9Gr8OrRtG0pEY/FIMLjTBUhj7ujpyKE19TRQxmK4VTqWPm/hgfrV0e0RQ35ek5hAou2nGav4I5uuR3gdJ2/TXDV42RVT7ZtVRz/UQlhfMvfxjiF28gEAgEAqeIePAGAoFAIHCKiAdvIBAIBAKniDMd4+3alXRNITJYSRcqreQwXC+c4gxNq4cSaeiIkQy95+0R6+FHLg44QuCnQ/xk8O4XiGstDjQ29sq/vnGyfePTN8wxixv7evyRxvfaxsa1Bhg85wgmd66tLLehGflkvGv225tqP2+NNTazWWnfVS5GMqA0JSGGXYxdXJHtQce2zsVIEBs2LjMZr9VOa5pbDwyqtjYm2zJGaMzXnQIO5pfJB3Ax3hrzK0GhKpUMIDv3K4xTMq5DI7cfnJQKHOP+lmZfrtA+E+M9sO02qmQ9YllOQq2nyhnmezs4RaqCpSCUKHMlZShpYVXHgP7KnRF7RxUwo35mY3ADxpbKYeLGdhDG+RlzhouYK9laYB52vcZQh2Tb0DEGWiDuvWn7KxVY0yjV8w5oFcqTMtznBlHXIi+mRjctzq8297Fu5CFgMApXeZa4tpBrUPqKK7gVNThmjPyQyqldDRnvWczNsOfuUPI52tN70ewxu+PtP1A72XKN9chrdfcOQY7E7JL26/Zr7TOneGqQahkx3kAgEAgEvi4RD95AIBAIBE4RZ5pqTs0gqRxk6JxoOdLfEygUTxEJS1hAyy5ZBeJoDb4uKajuSliKXKnYvCN1bU94DJrq7k2lam4+f+tk+84Xr5tj+sX+yXZHU/veCZhDAYeUY5cstdWDPxqhnGg6tTzVNtLzty7o9Y02SXtaNagRjRWo3OMUiKyJANSpSkdJg7bMUZpSYCr7MqEO155IgyavBkX6SZE7CtmYgZMOdrTxCrvVRoWKZhO2DUbJCvOzcJRoAg3XgtLMnWITafICNG2JkqjBqWIZ83WaAzjacoSxqCbaR8u1pVjLDVCVm7pdbdnzlWM9X19QKQom6K4EieU/hvp2HCtVrUy1oDO1H6CkxGHnPabxRhSg7RcomZv3Ts0O8y2HClVe23tHuYO2r9H/K6fGhXleko4fowxnYvthsof+H+m2V4Pi/Bpwv1iLVYPK8dttABXufAykYFkg2p1jPPvCr3Wl7bNuhPfdY6tWCng80fON91wIZUvvbf0hwxe6T+nmeLGl7Z5c0e3NNzgjkAulpIUroXoI4hdvIBAIBAKniHjwBgKBQCBwijjTVHOTdVJmrTQuIy9Hlhv9TpNYCmyMTMUW1Erp6D8iK0lfQD3IcSt5q3xdAxWYNtns1DVovcO7aniwOFAVqn5hs5VbqFBRbakYHLUCqrkDzZ4cvZaBBiqQgV06mnd6XvtvckXpnXpG5Sun8oQZxvNVztdzEGaNIlvTmQgkZB0WNCgwf0PaY2r0y7gF3efGucmY0Yrs7sH+fbrGHChAm3mlohVfol9bcFulO4ZJvwmUdubGrMuhRIYs9ZHL3KeyluB8Q637eQUpdKskZMFOx64qoKIEkW5OXeprDQp5Snp5x67HogT9LaSNSYl6+hbKYfTWENvW3CRTI/Qgnr4FXbrSKoNjZHSvXGjrCJnHB/t67sNDs5v0d7HOYCox2bRtGGNsqq0c77uKAaiFcZinM+3X8Xnbhtlr9bN6CjU1p+o3YE6x+iN3t8YGfdkwFuGtaZF5P8J9oIQ6Xu8qImg4kWMAMzdda3wtqebZOXs/3ML9a32o958cJiHe/GDz8oYef1VDW1uX7H283ezv5akfgvjFGwgEAoHAKSIevIFAIBAInCLiwRsIBAKBwCnibMd4i0GKYjBOGiJW7ahAfCj3pUFWekrfpwNR7WJFJWKTK40HFM5AuUGsra/03L1z4FjONX67OIJSS4M4bm9jvAxfZfweF/ygclJPF53MxWHRMRDAkbqyf5cV2yghuohyqRrqMxPXX3v6XQNMpZ2JkSl3YtgzOfeYgvE1uO0I2lq6ABPHmeU1nesvOsaMGEt0ZWj5A1xmCjfBasyJkso7ON/ahYVYIlKh9KxzNkbsvoFuU25+DVDe4UF05TElaSLSY04lKFfVY1f2QnUpzLV6ZPebbaF9O4jRjx4cVyxx7ZmZK25shUpfiEuKj537oOMft8G/D6W6fqFr8C7eP5ybI+TuF3S/m7+n2+1Nm8cwRZw4Q2z67oZVQSo3tE1bl3WdXTy/afYbPYYcB4QzyxHix5dtH88uoZQN4cyhcPU/KPfrUTbZil8LeEHnotxee49SI1RcSYsxyzMXw2ZOAkvrMpejAgenKfJ2ruzZeG0LtanDDo5EUJyabdq5e+6N2v+7T2u8d3bZ1sLNZSml+D58MOIXbyAQCAQCp4h48AYCgUAgcIo401Rz0SYp2ySSOcWmTFO9M1BR9WD361AOlIw7Nr7DK+VAfJ0qVIVzIB9wPgrap8Yqv/THShetF/pZhzKatnRKUwNKScgkOiUmin8bbXpPw3Gb9T9TOz0qmD9PoFxV1qoIMxpb2nK8gbEAJV24Mo6E0p4GJUnJ0U8cpqJA+Q/KFfrcUkw9ztejViZzpTcV2rQWvaYEc3MRp9YDJs/TcAIVpBZ0cAkar3ClSiwbahASKJwyGsuQOlBcjZsrhZnM2EQ1xNhWRkiDc2cw965c6KECQ5rQX2Vt50AF+q6v71+CJGKpelKYLIUTF9LJUN+S4wKTq3sZWKrCUJIrV8sHXYOk3Odzvabrn7fjfPe3lXtePa/m9OWxnTcN1hPvCf2NhdmP4YGjG0ovT77Fdtj267G9o9Qn58p4y3UySojWFdeZHbMM5ZU1jB+8NhPvKwMMD5pjS7uOcc+qKi1FbE1JoKOQQUNzXQyO0s0QWqxHel/auWhp9vaNeu0XJzrpmxYhpnP2mHNP6vmmV3TC11Or0NfOW2nzL/9xGr94A4FAIBA4RcSDNxAIBAKBU8SZppo3+l6mfS+jtaV0Eui2nD//S5cRCSqJ4ugVMqEbJ+ZP5rkoqLDkaDimB69Aia5c5hukq3KoKtUjpe5kMuURkiB2T3vS3Kn1UA3e0MlOwasHNS/or3xk95Pz2G8XmZNj3c/78U6ofgU66x6VGvpgQgUsB4UpIlIge7YtmPkKNSKvIINM5nxg9rQzU+ALUMA+i5IUPsXfkzMyMNeLETBhCDe/ctG5nJB2muVu3sC7NEM2cOvamtMwBLz4qESmvZtfJrt0ptv1yM6vAucQCP2nmW1rX0MhCVUBjjU2YYU8sY+ZrezagHmTTPatC1GAOi3Qryl3Gd0IKwy4Pxy+rNt3fsemNa8+d6zn29f1PPT2vtRh3fHeU3R2zIZK19my0es72j42+3VPbes5Luo8nG7q8bW4MNUDsvUz56GcGRU3ZLnnlmI1JiG4ps5502ZYxtUGsrtxT/brJ3vAi9zdv2h0wZDfaMPGUHafxNrfon83+mHXZo7PNqDQN4EPt5fwypp7Qp4PQ/ziDQQCgUDgFBEP3kAgEAgEThFnmmqebBQynRYyai1NMiBLravox2uP78yfHXqOEUUM7E4yCDIQQW/67NQESpP+Cbnzii1B7W7P9Jg7EDdfDxs8RI6Y5Hl8W7/TZwCDjqSgQOYyZEfw4qQQ+2TbUjWTbeWL6hnoLJhS1OnBWaeSMQPVUoakYumbnImj65ChzK6sQLdm3kQZVOWAjN3C0YwDaNocoYeULL2WYPDQZ/c3TBARSaDTE5YaDSFKZxaR0fwA+3WDo7vxvQPOXTihDZpMkL5teD63MEY4dzZWqq3YcPQaxDryGfxbXcZnMtSu0qVeRKVGFutAbhGbbW77mNmuzOB21q4mh56UdOH8sROEFeZo4PFtjPk1K2jTH+o9IYMHrx+zEsoR9A5unVFGTgGglX7X8b5dj4dzzWTewTk2Kj1+7K5vjd9aa2SR3+NpgO0ue3BohJnoE5holK4iYgRRjxwUcF7q3CiTz0THHMd9hWtORCQ3GdnIri/tvWO6o9/bbSilXOFeVJZ2Uk5zmrfgGlwWeCFJCpeV/TDEL95AIBAIBE4R8eANBAKBQOAUEQ/eQCAQCAROEWc6xpsXI8nLsSRX9cLSIJap1PcIpdNonPFQfEfyaeOIH0PFyndkQnFKh1hFKlzsA8LzW7uqjLJ3HmUNLnbQdhp3S0soYbkQQ0roB8QnhsLG4MZTjSHvXtw52d5+3Tmz3/aefu8I5U5ZiThSbxuBMLOkTL83JaeBg1hnYeK9LqZXsCwE7yM+WIhTMkv3H+fBjRo9DhhDFRcLprp8jz5O3qHbxMYUHcouVm5OVqixKTCHMtcPiQpcmKOZizP3xkQAphmI91ZOmauAulQ9ae/7vohVocpHKOdyy6xE/7H0afDqUjBSt8b1nA82vscSlIJr1RlbyIA1g/WYO2OLFZwfeO7+SK+hmdtjOsz5MSbl4Ncj1Nly5iqIzyNR8JNkh0n6JdTLkIvCeGjrrq99kKn9PV4R988NyNz5Ekr68i3kyTxur2mMPi+nyF3AfMhdyRxj0CWV31xMvCm5ZhCHdQp2zAQqUOZYIMelHvxY8H7DMkeXT5OyewxdHob4xRsIBAKBwCkiHryBQCAQCJwizjbVnKav/i+suhHTw1uoQa1dqnhFE4EHlC8MruylhufkANqzG3xXgnICleF7vIKX5DlQzcMB6NLOtqE5hOLWoabFd409OSm1GrTneNOWJ52/evlk++I36vbm661PqEDsvkTpTQ0aKPe0uCl7uX/px6vHgTZD2VFyCldUjKHHMIepd+YH/PMyVaCNHWXVQhGH88Gba1ANylpeWJDiNrweqdd7aHFcO0o3uty2lUpDRvDH0d2kxDJ6zVJ0fuyMFfCygKh+W1lqOEdZWv6QNUOfaIYEcrdmaIYwwjkM7ZwcFVjoCDSk9u9ZjzTHgEGB69eBqmegKjOUFqXezweUMeF7K0fLTireY/TcVo9KpB04/9nHbl7zFtHrMauK1+CUq9D2qtGOHQ2WxybN21KdLbP0LUNxNVSj0nlb+pSzpIxmHaC+OxceKDr93qzQdnuTl6Jn+9g25yee3z/UQoOc3pVaFgglLbGWxu7cXTbc4+/9MMQv3kAgEAgEThHx4A0EAoFA4BRxpqlmyV79Xzth+B5cRtkqhdKXnt5UaqDq9ZglFUocFSWgPEibda4nC2QZlqRZMpclDSq139bMy51LENgfXPbnCu0Gc7o8spR721JVRr/n/BO7Zr/HXn/pZPvS6zWTefuCpanGY+0L0mgZqTHn2FmBiuqZtZhshixVrSagiht3vhx0aQH6luo6vVcConj5QMrR9leJNnBKZV4QHfQYwxp9ZvurRFZyjmxJCvgnl3nJ7xrQR5VTuGJGd4c+KgYviq+vB/RRBZUhn9FK84OyIC3rs7bpkcqscudDK2wDVbtsv2bM4qayE+k/lyrMoWFCqsnod+0TnM+zgxzPAmGgySaOHzv1pgNkFKN9ydG8LfqygiLY1NPdLQwKMBaVU4PKClwj53XP+5cPPdA4RbdXTvGM6mprzsnBqUYx6xdj0d6jEsgseqx1o2znMrCpUvaACgYRkYJ+5xi/zBlEMBu6p4oe5nFyPuEMj0Gg7x5zDRka61jzJRC/eAOBQCAQOEXEgzcQCAQCgVNEPHgDgUAgEDhFnOkY71C0MhSt9K58YXiQcXbjlHfwkgbRqYAxuDNn7o3aFdVdvDMF2gDHmcqVNKUa6lczKAZd0H3OuRgQPMdlp9I4xtFNG2NYIVY9vqBlR5fecMHsd+mqlg3tXoDr0My2lfHuHPG4ns1zykIF+si6Jz3YD6XBWAyZdxBC3AbXRy/x3jnYULGM6jidK1Wqepa9oDTCGW+b0hTGm5wRds/jEEcq0Z7WLUEqng3MNXDybDQdZ0nM2qn/5IOatteiymEQTpJhZtswIAa6YszMh+VRzzIMKB9JNrZGZ6yEGGHr4rWjjKUl+mWMx0npHZJQcoLxy3MXD2WcGdfUeKcbKIeNJtrn24/rPWFycW6Omd/SgiCW9XgnnzVc0xKcyCZbrkSHv4em2q+7j9vyvumetnWK+8q0Razc/bQa0D7GL3uXJ7NGX65aKGE1rr86rNVWz9F29nwZFPpmMx0LKp5lle0v3m8y5MkMPg6LtvMyBrcWBswvliTxPp6cs1mW6xznFQ2unChPleRu3j8M8Ys3EAgEAoFTRDx4A4FAIBA4RZxpqllSKZJKKbxaD+hJ0qArR21VUKkxhuGg+7yj9gAKhUolvtIiJVLNOLejmkcTUp8wexallar8wWU9mxtqwj0/b6nOpoLSyuWreswVa5JwfhP7bcBUonZ/l7FMARwW6VFPy7akKqlg5GjepVEd0uutHmJSkaiEBYqocBQfJ3kaxvd9/9Xz6TsNyis80czxLPr7mzuIiAygx6jgRXa6cipbpuShQPjDcYZU6OlNeYw3BwCtbQT8KXzvKL6kc6rtEXZxY0bDdoHpxcr1Q9trP6wWKO9zNXg7oHYrGKeXKKXKHSXKOUW3lM71F707ChoAuBIwlrrkKMGbIRyz+cTCHLP8/B09N+lkx82Twq/BzO9edOVvWzpH8x3t/3NXbX9tXUa52RShkYIlafaYHn2UwXWhaW2/3jnW1/N9pdLXc3uPyY5hHgHThvWBndcV4mO7j23p+6/Tfp3s+HWL8EAiRb6ybUgs4YIymqOke4Ru2Cs5Ss+8cQdL2Qbc5OvOjlkmhWRfwe/Y+MUbCAQCgcApIh68gUAgEAicIs401Zy6UlJXSidWkNtkhuL9zlGQI4py09eTdKajAqkmZLadWs/wIBraZcNlSC8dgYbOpvr+wlF8aaJUTb2jtNTGVecTiuuot0Bdb9vsyBnEzdmVdeHoOqi1rEHBWH9M59cp96dlvUJMDlqJdGIjlhYvcb5BNLu0IN3q2tDmpKSZhWyzHnl9NWjC3Hl0JpNBjW03v6iM1oHSpM+uz8in92yOude5WAazPK1JhTPUwHZBVhbzrnX0WtkyWxwKUk6Zp8QYUi1s5aoHjm4qNXv7RdhKrGy/Lp7UPnr8qlKsOTJ7SydiP6BN9LXtswevW0H/V07pawCHz/DTbFvPt/2UPeb27+2cbDeN0qBFb9swHelxm7i+c6+fmv1GW1B52sX9Yc/212QXawtGFx3GNnPrjCYcHM+DQ3v/eukLurZuvaTjNxyZ3WSy1Bm2OND317fstW/CeWN4TNtQYsyufLO9L9U1KWR9P3PqWZQs4zLJk30u8DaV435t7xcunEKVOaqD+aqM1BtFuy+F+MUbCAQCgcApIh68gUAgEAicIuLBGwgEAoHAKeJMx3jnbSapyaTq7WWMqXzUo4zDXe0aMbkxYno0HS96y+UnxJhSh1jd3J0c5RVlhc9caKBF7C+VULhCfHXqYq1tD1cdlgd0tvClR/lICeWYkXdSwn4d4iqDr5GS+yvE0JGIsUMRkQFB0AyBGp+2XyJw2iEmO2S+PAaOP4j/JpS2lL3tr5JqNiZG7ErFMpsRcHJu707EmBDKk+41CdfzT1HPklgmlHysCCU/hcaoMu/6hHnd0uDbl9vwenPGqHBNjW1D3yCu22vM8sj9nZ6ggtTCMWvlSklufk7jgKvPauwws1U5ko63T7Y3J3odOyVivGMbtysyvIYJfTHYspcSY91CSa4bvFqSHjfmsNfaR+cfs7HI5hv1Qu6gX9uF7dfplq7brTfo9uQJe00bG1i3O3p/qDc27PnQFwn1SXRYGtz9a8Cc7HudD/uv2MF4+Xe0RGr/97ScKK3sWhhP9PwLlCDJoVP8q/R6S0zlrfMooXytM64/r8dQvM+7E5kIbeL9y8e3dbspeC/jDcLmlNDZrBh4H3c5F8UgWREx3kAgEAgEvi4RD95AIBAIBE4RZ5pq/qMvJhlPknzDyKaXVxvMPVcaYezMxPNOqYwaFGlHus473IPyaw6Vylh90SmZgOIZLqDcY9OZJXf43lKPmYL+zUtLYRagSXqj+OSNstEPNVL4XUlGxaajH7yZOPPxmYJfQhw8OUWXDvRmw3IbLzJuaF8IyHfOLB00U4broEIWaX4RkRwxhnWpc6B2pWIZaN4ef5MW/u9TUFg0AMgdHdyi/0uoN5VG3ciLsuu51/je0o0tTekz8HDJlccUoD4HlF3QBF2c8P16rfTy4bF+z/6hK/+5o/utjvR8y6Uds9VnlcbsryttmfeO5n0R3/W4vl+hDGdS2vlVYy0kXF/hSsBIGZZDjWNsWxuYjtT4bIJSv3N7lmouv1Gp6w3w08drRyFvKVV84Qk9386e2U3qTb0vFTM1N9monQg/Q2oMI7DczXm3JJQ4Lee6feeLVg3q+Pd1nBYvaZ1Qv3aqZDXuX5z+bk4VI+2jJUwS+gYqg04Vq99FCV6lfZ4584MM95yEi8/9fQCfGUU99BFDDa9+Btoe9+TMm+IkERe5eijiF28gEAgEAqeIr/qD97/9b/9bybJM3vve9568t1qt5N3vfrecO3dONjY25O1vf7tcv379q92UQCAQCAS+5viqUs2/+Zu/KX/v7/09+ZZv+Rbz/o/92I/JP/kn/0R++Zd/Wba3t+U973mP/NAP/ZD8i3/xL76i87/wL2/KqJ7LnvMTnTyJbFBQR6X4rDPNYGtII4DC6VxWbYJJwvJYaZbj60uzX9Ey8xW+uGNHGzNzuAOtQfpjbNtA04TaeGpa6o5sbpGRonV+qWhDiWzQ3P1d1uBlSZUWNDa5rFqeoQNNnDuPYSQyGyUmP0V7ZuMamhZqVy4bu0oYG7SvcHR3x++C2Dqzd0VEOtK5uKYqt3OgT8g+R5Y051TKbBZlhoxbq0Jl96PyV+L5xMJQ2SZ7E4YQLqQwX2kbDq7rWrjzebvf4Qv6enWsxxy2th/yO5gfyIot/Nhe13Oc+6KeY3um63k6cR7K+Iz+q4M4yhB9Sd9UlwAvFebeutT2Vbj0zZFdP9njyhWP4K27dreb6UTnw+Ym1LNGlpLOJphTI46Zo5rBIzOh1pgGOGOYBvQr/Crk6I4zfoDa2LCC4pyLlKU11gYyxDsXxlnmOn+POh3bO6024sKxHbPNNQxNRrxAt24z3rtRkeIMQ3KjPKXjxMqVorBtoC90Z5Tu7NxdZ5msfQXGQ/BV+8V7fHws73znO+Xv//2/L7u7uyfvHxwcyD/4B/9A/tbf+lvyZ//sn5Xv/M7vlJ//+Z+XX/3VX5Vf+7Vf+2o1JxAIBAKBrwt81R687373u+XP//k/L88++6x5/1Of+pS0bWvef+Mb3yhPPPGEfPKTn7zvudbrtRweHpr/gUAgEAicRXxVqOZ/9I/+kfzLf/kv5Td/8zfv+ezatWtS17Xs7OyY9y9duiTXrl277/mee+45+cmf/Ml73t//3E2py4ncfP058/5rriiNMELma1c5P14W0uNvkIp/j2SWZuxbUA/7eP/IZgWSXi6RYbmR2y4/zlQgfbHAdyG7bjJyYhMU8cD5HANjhLwLZOzWYinDDgYFBbKsDf8rIgW9Lpn4bahO29YBFF8q9Hvv8a6kwAT6vPNGDcwixvkKk6XoKHIKd4ACWzvzCZP1y+xp21JDURthfmeSUMM3NIP7RF+SCnRZ2/iykqYE3hwAVFmJayqSnYdIoJYGFGSGY3qXvN4s9DpWr6jgxfHvWyH9o1cgwADecrk6MPuNGGLAdw1ekOM2xBiu67pYXYYZw0Xb1h7UMz2ZB2+SQG9XdrIb3ArzsBkYbsB8qO2YTbY1W3kE6ttFKGSMRVPCn1YKJ9oAutNk1Q62/+n/zOzlRBEJF/rhNR13GDNH8zZLhNsgFJR7f1+E3hJMULw5AxP+myMIjnxWXRf+6JzNFt+8otc+meE63NjWMH5Ivfbl4O5fHdZ7Qr8mzMPWeZ+3oOozCDVlybl0p8mrRglfJh75L94XX3xR/ov/4r+QX/zFX5TxePylD/gy8P73v18ODg5O/r/44ouP5LyBQCAQCJw2HvmD91Of+pTcuHFDvuM7vkPKspSyLOWf/bN/Jh/5yEekLEu5dOmSNE0j+/v75rjr16/L5cuX73vO0WgkW1tb5n8gEAgEAmcRj5xq/nN/7s/Jv/7X/9q898M//MPyxje+Uf6r/+q/kscff1yqqpJPfOIT8va3v11ERJ5//nl54YUX5JlnnnnUzQkEAoFA4OsKj/zBu7m5KW9+85vNe7PZTM6dO3fy/o/8yI/I+973Ptnb25OtrS35K3/lr8gzzzwjf/JP/smv6LvS3X1JxUruvGLjE8drmISPNT5RutjAGHGuFrGnHCo1U1eCtIKBcjHSwMXG1InTI3A2hmKNVLbLm2Pdb/EC2oO4WO9EwbfO43toaiAWLEdJxhzAguVE1vzApeMj1kPjgYQ4bO8CzTxHSlSasrGUCiVcbYnYrbt29nKB+FKJ8qS1Nz/AOWrEv3Inok7zdMaZnc686VcqQ/XiTdVxfsSFM1Nq4WPiLJdC3oEzVWf8KmPMvrDXbkwYmBtAYwsXm2oOdb/FTX3/6LaNH6+PdC2sFxq3Wy1tjDdDSUbFWLcfp6WGpnqoKg0IVJduflnVLoytI/My64Kux7jVUKArypw5CciXcDkSRYn4MUqQvAEG8ywKtNtVAUqPdVK0D/7eDPN1EJYLMsbrDFbQJI67v8fkzFHBvM5yr56l+zW5zoHC3TtGuF4q5Q139N69+IM5D5Hu27RMq1f/DMkL2wauxw55O4MvJ0JX5IydI09mcGVQplSSXelyM2RoX/3/ZeJrIhn5t//235Y8z+Xtb3+7rNdredvb3iZ/9+/+3a9FUwKBQCAQOFWcyoP3//g//g/zejwey0c/+lH56Ec/ehpfHwgEAoHA1w3OtEnCsFpJnydZ3LIUxXyh9MDuNqlm760LCgVUDenR1qXjrylUvoOSjguWeqhZQrGpxzSF7fIkquLSHShNcnwHVFRuU9fHMy21KOATmjnOqgCdyEtvfSVPRkoNbUuW0ukL1oKQQqZikKOaDbUFpR1Pm4H2HTAuLBERERmRsqVqF0XxXUihQPtyUMiejqT/MP2BxalsDfDs7FD2Vd6Tq4hwAbbZnsKVqw2JpWIMFTRuP5RA4LPKMWUd+oLlEPSy6F09UTeHOhvMDxYLe/LFGuUtDdSqWrtfgtwR6brcldYxrMByrrJkeMDRt6Cuaa17DzVvaF/MtWRLdJqKNC0U8Nasy7LrDOyyaV/vDB1yzPkCklm9ozdzcKI55nVy5WpNxfsUlLAwuMU9JUig/WGIMt50JTq4twlU/Xzop1+j/GqFdrdOwQ5jPcH5aHIxcqGfPCl1XUEFzvmwmHsWbwPJGWUYaj3ndVB9y53b3L+wW2Fp5bJ49f+XizBJCAQCgUDgFBEP3kAgEAgEThFnmmqWvhFJmaSjY/P2Cn6g9KTNHI/Qgi4gMdKC2iqd/EzRKw26gYzibtPRlmvQjINSVlXn6I9cKZS216zR5R29pv3cKrpUuzpsWzUE5MeOaqYHKeiUtc+2JM3+ENUbfmbUpUAN506UncLkJskweRoItBfMBvrBXlPG7GyaISSGDbwaFGg9UlGOSi8w1mDhjLnDq+cHXQfh+t75PQ+YVR2oT4YvvDcyk5IrZoyKDTeUQnqf4+L+lkZoowDl26Ldmc/G7FVNiEpTyVGiPQTuud/EZXczozhL7GNrDlAzrECqEjTlPUm1oCc5HTJHy3ZsoBG7d2EEzInSGIuoTK3PXu8KCO6D2h95qhPfS+o1c2PbcQkVzFx2WfgY9zJRJQ3+2O63VY3+qqf6vduXpma/9rXIFD6EItXCnm+1jznFMJCj8Eus28R7YKVtGD+2wUOML7EgBJC5bOWeWdxIS8/cvYgZ3lZhD+pnmQu7lFwn98+MF3nVH7t3Ia6HIX7xBgKBQCBwiogHbyAQCAQCp4h48AYCgUAgcIo40zHevigkzwvJOhfbbBDbRHw1Hzx/r9uMgSacL/P2JYi7TSZ6vvWeK184RptG2p7BlxjQwRrlOgOktFav2Bj2HOVJsx2UL9RO5QnX1zOenZzxNhWuEBbxJT+mNIUxNLyfezUi9FdJtRhnvk5z8swEYu0UpdNTz8Yy5pn7mCwNw4v7vi9iXZaoWFMlu1+PeNoA15rU2f1WDUzVEV/NEStdujZUFfIBELN33usmNJmJxsL63MZrOb1yxqopquXiWiyPKRBmG41tWxfIn0iIh7Jc5NWvur97VSpsbHNAPUYqEasb8X17DOP5DKk6rzCTU0Bz897NL5qn58x3wLVW3tUqPaAcz5erZcw3wWe97dcC8eie/eViyzb/hOsH/eVKtqh2Nau0XOfcOeeQ9JiWaDYH2ufNXRsLllbzAXq6BNX2fD1yHDrE9rcu6/nOPWlzWeqJXgdM4aRwOQntQNcgxGtd//dy/9I67uddraoO900kfnTp3vwX+87DEb94A4FAIBA4RcSDNxAIBAKBU8SZppqzspIsr2WyYemnyQgm31SBKe3lUlh8IN3WgLZ0ciRVSRUklFOgLEhEZFlD1aoExVE6KgOUWjXR9o1mUDpaOFrjLqitQ6j67Drh7pLp84oht2UvpvwAVIu3da6SqdfQ70V5UpZb2pKsMUX/xZVV9Sh9yqAYlDvamHS3ZNrHLLW417he3zFUkiuXoul4MlSUvSaSSg2oqPXCtvXwUOdHt0YZzVKJ0N6du4UqWQn1oH7bUnyzEpQ0vnZwpU8c+J40KtSu/NytJ/rZdFOPme3a9XO8BPUJ0fiqt6GMvuWcQr9O7X7FntKTkwtKO5bboE6dyUjBUqrEEJNXz2IJFyhMRzVzTdMEvTOGAmIBynyE4exLO8dNJAP9lZduzZgddbNz5ZAVwjNFxrHVOVkPbq1jfjDUtrVt50Czp69HuGcdFXZ+TQ5ZrgaqeMPR7DBY2djTcb/8jXoN21fNIZJGKCNDnzuxNxPe6rD6fVlhjntMT2OEFh3hSsB6usEgjJM7lcAyWeOYL4X4xRsIBAKBwCkiHryBQCAQCJwizjTVvLmxKXUxlt0nbDbcDN6NRQWlFqeUU4GO6sBKNC0y2RylMIYKfUElJ9+TG1TUofejUzchTzgCTTJCuyvLYYzP6XY2wd9OhcusBnWaI/MvOfqWAvKVoWxd1i/+TqMCEemZ1vVXTTOFghmazv+Tnpo0P3AZtwXoah5D/9De/T25Ajc1gPsenOB+RU9TUOatVyCCqcC60c+W+zaXdnmDmaHwCT2GeYXL7i5nGPcLoJovOdWi3a2T7c2RtqGu7DVlD1BpqpnJWbjs9S34UYNenl62/bCVlP7OoMCVL+3YrsB2Mjt4dsnSm+dfr+fYfhI0KlThXMK0NJgP1K3PnboRIxs2c9VdOzjNwbCMOhZdZlWZqpIewzQ48ApqoDczKrp5M4X7b4tbj6SXGSpjuKhy9HRPNS6E0SZbNly3fVFp/1vwuK3d+bINvaYaNHTp5iGX+xZUss5d0b7bmDolOZ6PphfOOCUVDGVQMdCp6DHsAmWtFbPDj+wxE9yfs837953Iq/PN39ofhvjFGwgEAoHAKSIevIFAIBAInCLiwRsIBAKBwCniTMd4t5+eyaiayN43uhT3XcRZUNYjrtTFGHabTRpJ23R8OtoM5e7Jduf3Q6lLTiN2p7pSIIYwOq/nWL8MpRwrAiP163TY2i1tz11n/j1CLKRCrnvmnIGMoTz+FutyXw6BdHockyFW2vkphfhLThckF1szLUfMuXb9xSoRCpaZCozezodjKJa1kMApvHpWrW0vc409zZKN1SXUk7RLbdDqjo3xNi9rjPfoFmJKRyidciUPowlUto7gdLO0ccUZTOm7HY33bm+58hiUpZUIcnEsBjdk+Vg7c7yjx8xWdj50kLXqEWfODu01VQs4cKH0ZucpO7HPv1b7fHJJv5dLOOvcvIEz1hjX12YPVnnqEHsd3DyUHubyWD/NMRTYWnvu2TbK+1ACUzr3qwHzJlWmzs62AfM/0RzeqSq1WBslyoR6xtudYxZLXmqs4WFiJ8EUMd7ZWt3CknOhL7FfvcS63TS7SQ21vd3z2L6sxw+bTrmKORdYq61z9OoG5t2gdNPlZnS4L/S4jtUR9rntSgyhTjiptd1d75S5uiPpuy//d2z84g0EAoFA4BQRD95AIBAIBE4RZ5pqfs13bsp4PJULlxz9UT2gJKa3f2eQxemhzlKAoigGS/H1oI9y0EVl4yiKxJIk7ebe1UOwvIUUTPkmlCg4MfnDDaVM5teV3lw52nIL1RrnQEFOpj5lHvQmnNhrR0mThs4M7QVVJrEwwvw0rPam3ihpqXuWbtjzlaB92177q0FbD1YLc8yta3ru5U3Qfa0d2wnKW2bK3ko/cRQ+3Ng7qFAt71hab3FN23r3lhpdHIOK7R0dltfgvW5r+2a37BzYu6rn2Lis7Vu/xtJ1W6KU2GbN/sc87uxYDCyX2QCVu+lKdMCktqAS+5WlWLNjPf+o0s92Llu6busCSks2db7OWArkSmpGov26Ao/a+Ko9MMpZptRp7k3tURNSIXKwPMK1rxw9jfWZsbTFKVJx/lP9apJsvzagyXm1VWcvyjCboNlNpZ9bkQltKLGG28qN2Z5yxTsrnQ+ZK+/LEFJjGKCe2mua7OrYTs/pd9V7utAY3nm1rXqBC1NC5MqEUC6YGE50ZjBlq+dbzRH2uoNyz7nt4wPQ2HOawWR2rbdZJuulu1k9BPGLNxAIBAKBU0Q8eAOBQCAQOEWcaar56mMbMp1OZWvDUlYlqVlkG/eD3a8FZVGZjEOca7DUXZNArfRKaWZeuRsUcgtatXf7JVCxic2+qBTM3Tt2mG7+7uHJ9vHzd0+2O5sALFMI6x+/YeNk+9Kb7N9bJaifEvnFpbgT0kyBmZegswpnwFAyA5h0mOuHAhef51ShcgYRpJWgTHMbnPQfvbA0x7z42/p6+IL23cSFB8rLSq/lF3VsL1yxNNzjjymFVSygQHRkr/34ULnKwzu63+0Dfb9tnAEDMsnHCEu01yxttr6u41mf0/1Gb7BU2RverNv5RYwzKMems/NruUZmO7LAq8quhUkPMX7IRvWbLvv2op5jXIL63rHGDxPQm1NkmFdIu24dLdsyfEGv5dZR+FRkA4XZu/NlmIcDsoYzzOPcHbNc6WcjKM7JxM6bnNJGRknLKVfx/JjvfeG8qUm/Yi2UUJpKLlxkvYg1tOIV9WYC1bS9PW1bb8MzAgOLGtnZeWHXVr2BjHWoXcmMZiROKS/dP5zlRMmM9wrrI1Lmw4TIZF5iPNcwM3Ghn8Mv4nvnmEOFvTfme60sli608BDEL95AIBAIBE4R8eANBAKBQOAUEQ/eQCAQCAROEWc6xjuejmQ8HUs9cYbaiIXQeEKcWwhLVUqk8Gdw78m8GwdjsqwJuEd8BnHKjPEAV+cAVaUGcZrrMFF/6V9ZRaTF790+2V69dP1k22XCy3SkccDmuqpsSWYdp/e+A8HlDSrEuHg0XreIhaESS0a9K5fCFCuhEpS5qTcw7vYAY2sRkVY0zrhqtT37tzR2+8V/ecscc/c3tI/SXahJOWWh/KU7J9s1yiuy12yb/cZ/6vzJ9h6UocSbr6P7Vmu9piPEhWVtS58yxvdQmjJtN8x+K9TLLG/qXJkc2LlyYxelGyjRGaHUZZjbNqxvQ0HtGK43jfs7PUOsG+M3KmxsLUF6aoK4596OzbmYbOJ8xnAdeQfJxtb6ATkXKPHIcjt3W5SCDDBBbzsX54fjWIOytnzQfs1sUFEGo4yGz3qf96FtmGxA+W1kS37Y9ha/jQqvoIZ+ycxchrqeWz891h1Lg0auvC9DrkE72jnZrncPzH5DqecbY5xrp7KVVTq2OXI9asaC3f15MCVgUBNMbr5yCFG6aTMuRNYc6zWUzNCP8yMxWPyR3i+4LobWuRPtLGXZ2HY9DPGLNxAIBAKBU0Q8eAOBQCAQOEWcaap5ndVSZLUkp3hCcsVk3HvqB+oqfSKlAxrOKwuhxKZDSrnLnjdG8QXKY7Jk6bUOhsy353qSL35WS2Be/q0X7MlvKiXaL2DK7kT/B7QvgyHE5gVbxrH8Bn09Q9r/kFlaL4GGYxkU6Xjn0yB9rhRdD5UbUnoiIgMoVlI/ufvbcI3zzxs95voLSgMtf8dSzd3L+9puULudowzzI7yGYfuqtf06f60um62ntQSmGFtarwKFmENRp0C/No6SK2gCAOqtK+2YjaCeRDGh7KVDs9/BZ5Wi3ryg5SObU5RdHFiKrLuhfNv6WOdnMzh6DeVOBajErLQG91NQi+OJzv/R2Crpj0qUqJUcC9Cyrr9ylEINOL4r3X4tTON7jIWbXyVV2GDmnu/oPtnC3m8GlDStwPQX7eD2Q+lNDYODkV1nC1DhOej83NcLYj9JDOOwv+xYsGwyx/zPkg8R6Wekg1Nt+6tBGVIBlbNRbudKm1g2tMI29nHlizRpyXm/8OVXuOO3uL+m3oUlGr1HzI9BRM9xTfs2VNPintwc0zTDhlNGbSOdU8J7GOIXbyAQCAQCp4h48AYCgUAgcIo401Sz5EkkT9IV9u+HDNQWk/U6lxGZgaJIxuNRKYO+sJmvLSiPCllyyYmtt8ZLEnSMV2IalFK+e1cbe+N3lU5eXXPU6RIi70z9G5xyCmilBgLe88O52W3ZQJ0FlNDYKRo1oI96ZChTuJ4erSIiZT6/736S++xuUFGg/fvc9he/92Ct43nj9/dPtpeuvwZkG6YOma+eXsMcMNSpU6TJDykar1nW5YbLkN3R7fEOTCpWJNhsH5MeayDRs3ShjA0ospGG817L1R/tn2wfPaHUbn8ZKmSHdiz6fZ0Py1t67XMXHqhBBzNLt/RZv8gQL0kF+lIAzI8EGpuKTVlhw0U5clcHU3HgsmqNxv79v0dEpMFno0LPnTbgu+zjKXArGGHddy7+NAJV3zfaD+09DDLnG5Tf3H2O3rpUv8pAfRfiM6ER/qB3bebuS+hns19pKeSqgUoc+qEYu0xtrLUSvrgtwn997ilkBdWq1m7e1OjXHJUFuasymCMKs3oJnU4Fu8aeezzWuVuMdD5Uztt98ngp5frLf5zGL95AIBAIBE4R8eANBAKBQOAUcaap5kp6qbJeimQphWQoRFA/7mph22vE1/tcaSDjJysiLOYvQJdmnd2PjExG71NH1+U9Cr4PNZu0uamF6t3KZsu1yG4sh4dlVsMTuIVg/8r21xFedzSLyO3fZRQZp+BIyphR6bJJ8bLmsGTO/xOiARmyeZNTRO/Qf4dH2i/zl7S/1nNrkpCQKWxF3h1lBbquotBAenA2aV0hpDC21z7d1deztVLXu4NmGmd3bRblmnTpUr+38sIrFNlfo/9z26/Dvp5j+VkYahSgyNe2v5oDPd8xxDnWKytJ0JX6Xe0eKOTMegeXNWhVqNYk169DoftRcJ+bg8usxvKRvL+/qIuIdXDl9uBEVDJmB4NuZViqdJnVXQvBiskDvMBFJEdGMCMCnrkuqOxTYQ4M9ga2ZngLbaoxOZhJLSIygMbuWXnh73PoB2YXi7snZKBp2yXWY2UvqmZTcb9mpUTlvYPZf9z0YarEtcqwmZ2vyyWqL1pkdx/h5IWj0ukrvKdhtJH7yTr7xpFUy6CaA4FAIBD4ukQ8eAOBQCAQOEXEgzcQCAQCgVPEmY7xSp+JdJkRCxcRSYj1sHyk6Wys9AixgbyjSpBy+XVl44AVYno145SlE8hmnIsxod7GlKi6xdhOQmr+IF5BCjG5xNioU/BiiQHinNWRM4he6DWVLk5MlFBcWjPGiHhQ7dSzBHFhmk+0Li7PV8ao3I3twFjPAv2wYizMHrNGmVXPPnExJQrDV5gD4w1rULCxrSpSkxkF6e1ymuxpO7ahQCRQQ3O68DKHElnf6HbpRP8bxBx7jG23dDFexJ2n149PttcXtA3jwvZXc6xx5/kBjnFqPX0B8wOYYxS1nYezLSMfd7K5dGVHVJEaoVQpo0KWU5IbkANA5aPCr5mM8VWcw8UBTdkL46M4vqudYfuR9ldJkwSn3tQjH4Px47L0t2HE+RHT9uYMJUupYGDSsTTPlxgaswiTdGF2S7iX5IjFl84EZdkhP2Sh9TqdUxNsMSfKxHWm87Ur3XzItF8HlKGVaWb2E1z7gH41sXIR2YSy1sEUCn0H6EfXXSXWFsvicpdQk09ryTN38EMQv3gDgUAgEDhFxIM3EAgEAoFTxJmmmvt5L33qJe36EhalfReg7vaPLK10dKyqSt0RSm9KpTWm5y2tsXNBKYo0VrphJpZaKaG41EMVpissHUHlnHKk5yDFPXclASXoMArvJKfyZMTb8VnmUuYn9f3pseT8eEegtftBaZcex+S9bcMCqkMlKM3ccToUzmmFqjlmN1P2MEUfjcbwWC2tEUUOapFKYd6AoahAZ23o9vYTO2a/7dfpnKi3MB9yO79mvSpFHeHaDw+Vvk2+HxAaKdH/uaP4ZAW6ukU4ZbAhj6JXmnwCWjBrlDYeMtvu9VIpvtVC91s4+SzS/j3aWm9YmndvqX3Ugioe9d5sAPONcxy1JINTDKISUwbqleYjIiIZwkqsNRqcslOdPYDahYJdNrHlUtkM5Wpoazmx86tDqCYf0zTDhZ9AWfYoGUq5LT1roOJWJO6n1+oiOlIiFNRgP8+SFgP7D37DgyspSwhFQJFq3dgvzhDKKztdP1QH29qy/ToeoayT5hXOLIJhmCVuiMmpbO3ugo6/ot915zbmw76dDxMYzcxG8BHeco/OWqT68pnm+MUbCAQCgcBpIh68gUAgEAicIs401Xy430m77sRZlUrKlCY5uK108o3r1hzg4BWlHZuboG2g/rPxxLY5pnvjpZPty7op05ntysF4YkJs3SlX0Vxhc0+pkZ1L+v7RS/YC87Wej9Trwv0ZVULofzRTemfyxJbZb2cPdDAVmxy7mUA1MyFyAN3XO3qamZc9MifXjl4rDK16f4UfERFY3MoWMhPPXdFr6jft9WVQq+o6pZhypyw03tQ+2nxKaeK97zxv9tt5Uvcbz0D5OvWfBtmlM1DupHb7pVNBWpGSg4KXGwsKpTFDfOyywCsoFRU0BYE6mz85M/x7Zq22dj9ms9OItju2Y9svtb8SKMPSZf1S+MuI9idmpVt6umBWP2nj1p6bxgYDqOaidvMQv0UyKCQxLFGN7bzJzt9f8cxLyWWg2Yv8wftxXvbwrh0GS7HWguoNKskxozvzYwbVtY6Uu1Opwz2wQIVFao7MfsyuP4SC1627lnddHcLbeKX09BSht93HrMHKlUs61rMSNL33HWdXFnq/zl0lQGKG/2O6vbij+x3vWyo9VeiXmR6z8aSlxZfbgxRfwdM0fvEGAoFAIHCKiAdvIBAIBAKniHjwBgKBQCBwijjTMd7ueJCuG+TwZVs6sI/YxfE1La84eOHA7Hf4CsqJEJMYkIZ+fOScbqAkM5Pdk+36qv0bZow4UIFYVpm7OA3Mlbd3dThe8yf2tJ0v22MO4KwxoPxkVPiY5c7J9qWnLpxsv/Y7bNx6to04F9rqSy2Mw0viZyhfcIbaFeKeA+LbpXduYd0DYmsp2VjKkOtYj6EadekNcMC5uWuOaf5AY0rdEVR9nLH49uOI636r9n/1eqtclU81FlUgRpUmNv5Yo95mI9Pv3d3Sth5u2HK1ttAYWosSol58vBBzAPG9rHSqPhwbBKEKGHyXnT13WSJuirHwFU0D5kBNE3RnJt6zSohG9pWdXx3ciQaU8pSodRm5HIKObk4oqVm39poO7ui82dhhHNcpYbHqiB8h72Ds1K6aGnMUJW5D48rxEA/NEavundJaz3lpJN1sDJTKdD3WVoEcgs6pXWU5cw3g0NO78isognW93n96L+3UQQ3qhu53+7ftfutXdF73cDSaoJMPv8Fen3yb3qcu4d5YjV15JfJrxohNV650s0EuA1JeZPUk5sORi4kjcabchMrgBXtfWpdHsi5DuSoQCAQCga9LxIM3EAgEAoFTxJmmmlf7rWSjRo6OrFrPrTtKDx+9rPTy8tqh2e8YSlZppefIQF+tGksfVBCG35mAuphaenNyXv+mqWnc7MohxhCN34L60sU/oVzI6u6eOeb6hu7XgOLbnFmaZPecUqSPf4PSeOffYKnTqkbZRK70e+/riXqWzvAzLXkonLH4AJowR1t7ZyY+UEUHtLPbTQooY9Wgqc6/BtTdW2z5zxIKQsvroFtdKcnGFShS1aAMb9k5cAC1neocKLDaln2VZBohND++qN873rT0Wj/WsaGRt6fmeypcQYlsNLZ/S/N1+bh+1waosnLfjnM31fZNJ3p9K0edrsA953AGryb2fNUYAvkwBMicOUMiTUsFooGGI7YNA0MUmBvDyhllXNf+2sD6LsZOYQnmAAm8c4v+r3JLM3ZwFhmh5Ce/h+bVdZJwH3AVhlIyXIP107ryK+6XGFJAn/h5Q7OHBOp7cOp45Lg7mMssXWPna93v4AX9rP09e69d3UYIBUprS9Ql9q4M7Uap+9Vv1Pvr7IJVpptCSWyCUtLk5lc5MCyh/bqFcrDJt9pzL2/pdoVr78b2nnDncCnLpQ1LPgzxizcQCAQCgVPEV+XB+9JLL8l/9B/9R3Lu3DmZTCbyzd/8zfJbv/VbJ5+nlOSDH/ygXLlyRSaTiTz77LPyuc997qvRlEAgEAgEvq7wyKnmu3fvyvd+7/fKn/kzf0b+1//1f5ULFy7I5z73OdndVargp3/6p+UjH/mIfOxjH5OnnnpKPvCBD8jb3vY2+cxnPiPj8fghZ7e48ftHMqo6KUaWfjq+pTTH4fUbun1sKek1koWtKDgyNA+ckP5LmiE7uajdt/WYpRk3tndOtiv6ODrVlRIU5KxSauUCqMDRW3Z4iFx8UpWZmJW5MbP9MN1QOmu8o/1abThDB2ZbJlJRzneUgvTIzqaAuXFtEJEeaj0laK7c0dhrvMxgwJA7X9UMdHVZ6/du4vpWr7NUYNsgK7Mg1Wl2k6ZQKjb/I/i8vuJ8aG8ohVW/Scd953F7whpZ1zVCFsMC5g5OuSrV2obswQJE0oKiowhSVdn5Wu/q+XZA122e1zmQNZYi67e1L9fn4EPrskRnyHad4lq3LzsKH2GXGajvVNnbT44wTknFJmTzZu6WVYqu6c4oPjmKFQbSqxvad+Ndt98mM8mZAaxj2+Uu/oGx6JANXLgKhg6qUTxDNVjzg4T530JhrMzsPGS4h16w9Czuk13rPbLKe4aLHIXcIwTWrPXa550NjdxFNcjyJaWTG+/53ei9bbXWcBYLMY5v2Iz8yR+gImUHWfhWmE7qXNvUgvYv7e3QeXFjDVYYjYt2/eS72A/J7Pu5vb7btwdZubX8MDzyB+/f/Jt/Ux5//HH5+Z//+ZP3nnrqqZPtlJJ8+MMflp/4iZ+QH/iBHxARkV/4hV+QS5cuya/8yq/IO97xjkfdpEAgEAgEvm7wyKnm//l//p/lLW95i/z7//6/LxcvXpRv//Zvl7//9//+yeef//zn5dq1a/Lss8+evLe9vS1vfetb5ZOf/OR9z7ler+Xw8ND8DwQCgUDgLOKRP3j/8A//UH7mZ35Gnn76afnf/rf/Tf6z/+w/k7/6V/+qfOxjHxMRkWvXromIyKVLl8xxly5dOvnM47nnnpPt7e2T/48//vijbnYgEAgEAqeCR041D8Mgb3nLW+Rv/I2/ISIi3/7t3y6f/vSn5Wd/9mflXe961/+jc77//e+X973vfSevDw8P5fHHH5ebX9yXuljLRm2VZNoFnFIONe7QrVy6N8o1GDvqEM/pG8vlL6Fktb6l8b1ubuM5a5hH04Vl4uJDdFIqkO4+HmlZSfYae33ji7qdlxoXq0vbhhGuIy8R67EhOGO8nRDbsepUIj0dUBAeqvAiOedtvqJSjjc0z6BQRZeZYW7b0CJOTJcYqkaVh7YfhkOUEdzRYxqnWkQXo/mhxpdSYV2t1ktVuNpEDDSdt/GvQneTKdSNKsS4xs4ZKFXooxrtK+1+oxrqYx3KIaY2zryJEqktxHsrKPw0YzdvtjWIti3aJ9Mdu37aXq9puoFSpSs2Vlch5luhFK6q7DVlcJMpMHcLxPkzp/LUYD5kOcq8xk41CspH2TFi/q2bA5zXWMM8d+HVrhhHRcyy85U8GOueMdnS7piwajLU0/W9zV0QrBO2e0AZ1ODa0BWI7YuOZ0r2UdCgNGu+0Dbs79t1e+tzKDV6Sed1u7T3zdSirQMbi7at3di+ouO0/ALuCZfcveMyzo0claL36xvlTqaUSrdLVwI2QSkczJekP3JlVTfnsl7ZHKKH4ZH/4r1y5Yp84zd+o3nvTW96k7zwwgsiInL58mUREbl+/brZ5/r16yefeYxGI9na2jL/A4FAIBA4i3jkD97v/d7vleeff96899nPflZe+9rXisiriVaXL1+WT3ziEyefHx4eyq//+q/LM88886ibEwgEAoHA1xUeOdX8Yz/2Y/I93/M98jf+xt+Q/+A/+A/kN37jN+Tnfu7n5Od+7udE5FVh7/e+973yUz/1U/L000+flBNdvXpVfvAHf/Ar+q58vpS8SNIsXAkLqLzUgZZw2d4sPyCtOkCkPHN0K2kga5rteSWYd8OwunNUbIZzDCgjKNGGwpW9bNQsjwHNmzkxf9BUJeiU4h4KWb9gCVo87+01sUwh0bg+Z1mCF8jX861RO5B3fjCgCgNaqmstzSsoW+kqLbXoW+3v7sDSXIvr+rq5jtBDZ6k7o+0P1igl+/fpCCYaS9DYq7mjtlAaV8y0fTtPQpXsFV9Koq/zGuYa510btpTHbtDWzfO2HO8iSohKAW12W/dp184MfowSpCnKMy7YNjQMZUxBpZ+zpXXjbZhKjLQNdW6/t0SpXeoR+kFYInehmg7rMUd7ypE999Zjeg5GprqJvwWCdsT0L2BykTkjkAHGAT1V11xMJ0PJToXzpd5T7gnH4L6UbL/ynpVy3i/QX87oRNDHLKnpvfkESsxuI4x2+w/t2jr6rO7X3MJnyYYveCvJWFaIKVUM7r50qH3ZIEQ0NPaGmNDPVe8VuBQDQgcD79egpEvvZp/u30erhaW722tLaddfvnLVI3/wftd3fZf843/8j+X973+/fOhDH5KnnnpKPvzhD8s73/nOk31+/Md/XObzufzoj/6o7O/vy/d93/fJxz/+8a+ohjcQCAQCgbOIr4pW81/4C39B/sJf+AsP/DzLMvnQhz4kH/rQh74aXx8IBAKBwNctzrRJQtfkkue58QwVEelbpTx6wzS7jFtQRr2Q/tDtkVPXmW7or/KtPaUMqw1LW1bIAB6BdildVuYadNtQMtNOj6kcXZQhA7Ey8kv23AW+y6jmlA+mxZkpOWT22quMGc8QbwdF3jjKPcO5+TVDb6kaWetx66UaW7SVpevGeN2AZu/nyh8e71vKZ3mk33WALOluZf2ZKbo1glh+5fqrg2j/UY9s3rnNPs9noD6R6HvuST2mHJ8zxxw+pudukE06u+DGAtRu2+hn011LR0529Dq6OTLoOS7eR3QDCmUTbXjuVLHgdyBFifm+Yds6Bu3LY3LvgIFwSEd/Wcw1L+afMY140LWZFXbNFJugE5FVm7ns+hy3RIZJSOVmXtEN5+u5Np3q2mD8c7GWfCwJ9GYNQwevXsYKggYZ4Z3wfuMMK9B2+mNLb+fuaqX9cnwTpgafsaGR7qYq+WUtzFLGdt12CGFVCAtNGt6DbT8MCGHVUDzLR3a/MbLjGbrL3TiVhk7Xvmv5vS7riex3ogd2Y3fs7y6kb8IkIRAIBAKBr0vEgzcQCAQCgVPEmaaax2mQURqkzF0mLagD+lFOXHF0jmzjVMGUAEL1GztWDODSY0rdnXtSqa3JtvO4NYYAyJ7OPf2h26T/VszWdH8fZaDbMtLLPmOaycagyjpHSVegUEbou85RWzwqBxXLpEyf3J2D7s5BX61aJ3oCqnkFGrrasP1fwMeUFF8Lb+X1LXvuJSjWdqU0XLe0Be+st88QOSgmVmi+hXDHAk4bR3ctvVlCmGJc6zmKidJwO4/Zc28gfMFM0MLN8QGZnP2g1zsbeeMBPf+AbNcBjPTSDfSAsSA919W2rVxO1F8oxjbsMq5xvgoiGblta4l2JHjX9qCDk8/SxTykYYjkbix4jQXXpqUti0z7cmAYCP1d9j5TGF+Lr2lymyxaJAj7YE1XzqCA96wBnrI0T3i1ragsAL1McxNvKkGvcYrlZJ2lxYUJyne1re1tu1+CUEbCWs8Ke8+aQMCkXSF8cQCBEPczMMcx9RV4Tm/bayqqB9yAXOVEjvtFV3FsHxxGYB+buecMMFKe7rm3PwzxizcQCAQCgVNEPHgDgUAgEDhFxIM3EAgEAoFTxJmO8U4mlYyKSqTwsSJ9PYH4fuX+zpghxpTPNOg13tMY7/YTu+aYq69TcfrtJ3W7mNl4Tt8yTsPyDJtyblSkECydsvTAtZtKLT1MFjIZuf00DjFAEL10saJMtO1Uq8pyXw4BtR0TR0IMzoU5ihYqWzCcaFt77rbTz3LECLORL0tAHBCKS/0RVJTuuHZDeadFG/relV8hRt7B5L3pbIlOrhUUsrwNVSwX21xjOEaIE+eIc44rV0qyqXOPccDalV8tGYtHPLMsXYwXY53BTJylXZkr45CWcUBcg4vJ5sb0goYcNmZcjFgSA5P23sc2Ec/k/EKZUJ67khPmTyAwmTkFowrrxBh3+N8eaDpzFxh3dRFek0tRsHzHxwGh/DZCCWTmFw3Go80Zu3VlhbiQLGGdpPvv88eN0t1wgf3SKfThsw7rpB/sPMygDJg1aKs3g6l1DWVU+sJupSvbm13UNbN5Bfk0Nu1DbFgWa92VUnUYatyepWKsW3wuBTsZJxi5Mq29Woa1nxkPRvziDQQCgUDgFBEP3kAgEAgEThFnmmqudzekLieSOkcrraGSkilF0biSjPFYL390aedke+tJtR089wZLM84eV55jcllpwa3SlrCkOeg68CmZEwLPQWV0VNJCWwungEONdlJtmXeBQI0HWZx0T5kQPDXxvY6pkRKUstWAgXdq5xRwcL0D6NtWnMg4UvETxiXL7H40e1ij/mBNh4Mj2wbByxa0v/cEJhWYo9ypPj42+/WgdhfXtIxsPbXhhmET3wW6m1R6mrrrK6gOpudrk6Wxe5gpkNZrHM07QRlNhmvvSz1+7EIPCSYQLAdLTvQ/oTypZVlO6WhGSIJRuC13VD8NRIpCr5d7eVqWLUqgCdvCzoG+1z2pTkWfXRGRHnQ6KdEE7+7OmTtUGMIO4Zj8HgoZRgaJYSB7Gx4wv6oWSlpufedY3wVLkNCGJrNKUzRdsEpYtq29iUWAai7tbzWjiNfjuxaOusYcYxingipZMbJ2r5s7+nq2p+ts6krmJggrZLj/5OJNOHBPRQllyjg/nT+2KU3V++TEWSNPL04kX0U5USAQCAQCX5eIB28gEAgEAqeIs001bxcyqgpJK0spNAuIpUOpZVI4wf1z+nrzSRWr33mdUsjnn7KcQn1RKY8KNoalSx9MyEItiwdTEBR9Jw1E319eg4gVHO/xvd5nl1nNGVW6nNp6PiAbkVmijmpmtqXx1AQN5zMvE3jeBtfUN3a/1QjqWSUpcmds0VDJBxQ8jnHeDjIpQd1NdGxbRwX2yMokJeoSsEWW+mG9D1WfQ3tNwxpeyw36H+fu3NhSTWjeKXW339qL6lekS/X92czu1yLGQI+DKu2dbBdiPY+7igYFUGzyJiP4u53scuMyj0kB02u2qjytd/9zM7Dhh4Lp2SaDO9l+yEDf5okhE3tP4Lhn2f0zmb3nqwnxkHJ3YZJEIwO0z9n7miqBDNc0uH5dIyxRCilWDYf5W09iuAghgNyF4Wpc8cYYobup3a/FXEkt1oIzESiXrJYA5VvruphdsunKO1c1zLe5i/UzcfaxaEOJuda5ezJNF+z9FZne8uAM8xo09KS282v3wkyWy3tumA9E/OINBAKBQOAUEQ/eQCAQCAROEfHgDQQCgUDgFHGmY7wbrxvJeDSW7NjGadYNjJYRqxjvTsx+O5dVeWrnST1H/fimbl+0Md4pFIhqlt64gGiPuIONLThlFKa44zOEPKV1sYo14oIlSmBKF19do5TKfK1rq4lE0VXEK78gNpwNjE3zWm0Ujs5HlKnpGlvmkDNugzhg29lrGvfc1rHpp9qeHTfO6z2UvYy0fXf2bUxpfXB4sp1wfZ1bJkkeEJ9rHxyzLBBr7TOda60Tu1kv9dw3Xla1sZdesXHY9RwuPyjxuHDVlsfsYP6OUN40gWPQtHbleIj9sR9aH8JCSQwdwkZufrV0RcJ8Tbk/oba1xJwyfexL4QqWvSCvwpVI0ZwoY16Eq8DjXO4qzGXMtW6wcUA6AxnzdR9fpVoV1kKeuTI0rieMU+rs76SEWDXXDEufehcXLukgxPvNyN7nOD+2zun37FyybWiP4RZ2E0pYTmmN6TXVSM+xcV7vteef3uMhsvkElOlmKHFz63GF+1SDscmTuxexbAiJEbwHD4Vbwz3KpRC/T1YkUGbnR5Iv7DU/DPGLNxAIBAKBU0Q8eAOBQCAQOEWcaap5940zmUymkh1ZdaketEvZKoWy/VpLLZ67oqVBkz0YAOzCtHzsSm8MRUEqw6Wuo75iADXs1aBI95QoMSDF5+m1OgO1RaNmR/EVCf0ChZ7GGTYnKEDlUEQSJ4pfJNLLoI1RcjK4EoocRPaAkofWlx3loPBRrjHxYvel7reGmfUUojflazfFgGpQx7q9etGp+oDWpqjV4JSKirG2YTbVPppN7H7TCah5iKpTaH5+zV7fnS+oOs61//vOyfbdF26Z/Y6OFyfbZaXtWT62Y/Y7fEzneHFJt3cu6lhcdiVzu+AFaaReiVNnA3XKUpfelfII6L8a4vupslQgQxmk+HJDj7pTs1Rp0L7rMntNCfQ+r8Iro4kxamBIB+GKwa51mqd3VKbz5SygKikAlRzfbczqeX2u/C1vsQYrtBvnGwrbxz1KfjLcL/ra0t0zrKce9XSrN7t+PafHHb6AssIXrdrbhDVvG/q9u69Rennzcfc7cAthjk6/ZzV38QGqUJU6TiNXV9hPEJ5hKRvuc4OLDwxU/kJfTtwc35tWskh2/T8M8Ys3EAgEAoFTRDx4A4FAIBA4RZxpqnlvlMt0lMuw5X7iT1SFqgJFsXXV0ikbOzBJgKdvX0PpyP1t0oPaHZhV6D1NmbEJZqRwSkU0SchB/VDlxovTG1UftMGrRhWgjZmt17thp9gOszez3u7X5UrllWwDKJ3KZXI2BdL/IMxfO+WXCZSnZoNmJVelzVDuQeEzoZWZkq1TwJmM9Ji9Q2QXV3fMfsfoo9WcabB2zOoNvabz53R766pNdRztKOU91DB3ONTtw+ctJTf/I81kbl7QLOvujt1vta99WWR6Hf3Bgd3vBeUMa3hO94/Dfzq/ZI4Zvx5qVcxGvccXGv1Cwf5k6dsMFHKFMElyJgkDjBEYGiFFm7tzU6koZTpXCicH1ZmMZ2Ssu/BMjmvMMoYsdFxyl2mf4CW96mlC4MIuI/gKV9rWzIV+GD5iKCq5jFtBFu0C/VLD5MKbsjTwQK7QR61bj+VMB34Ev+6twVLXORKRNy/BnOGinSv5CnMFHtSTbe3jzGUK95jyXacvjgd77jHidwVu8d3U3bvRzxlCERXCJNXgTDMQLmAYjQYmr35Yvfr/y0T84g0EAoFA4BQRD95AIBAIBE4R8eANBAKBQOAUcaZjvGk2ljSdSDWy3PreFPw9ygiqTVt2VCNeaMKZCKWk/h75mZNNU/6T2VjKkLFMSN/PXdlRW2pMYYV4E8KSxlFERCSDbEqWsfTDxl+M0xBN3l02Pp2Vcly8N+hmLVRhyi4Yk7LH5ChzyGZQURpdNvsVsM6hkXfn+v/4FpxqjuGiQ/Ul5+RDF6lziAXPShvPmc9QamTcVNz5au3znV3dnl11ZUc7KDNBfK49QHnGi0tzzPLmkW7PNa7Vru0cGHo9jsbifedUzo71s82JHrOGE9PxJRtHby/qOkk7+n5ypvH8q50qVJnLNaD7S2disq40BSVqKYfCFWK8TjTKGMAz1yBzqkX5gLWKuTtyMVDmT1hRMpZLudjtkmVyGu/NKjsf0orrTI/ZcOVqAyyFWqyndWH7n65IGSTQ2kzbULnSpwT5sQ5XWGa2BC8f6T2mQqx0Y8cOQIm8DYpfzd01rZFbUfVwj6Ma1NKee92iFJH3qMHfQ3Hf3NL+qn3xGW7Ew0rnRzXW97fHLgcHJUId1LiWbiLevZHJchHuRIFAIBAIfF0iHryBQCAQCJwizjTVXNaVVHUl5dhSVhWoLlYLpNxSREmUThlohgy1ktzxsjQiIB1WOPqjR9mQSWP3XBk4boj6SIu/ibxJdZGUSuLpMlf2wnIPa8bg1FkwDRLaOjhqsWpRhpGzhEhpmyZz9FqFMocMZT6lHbMGBvc37qK/9h2tdF2/q2hh/r0DEfsjV3Iy03Ge7On2xlVLM+5u6/ceQyWocELzea5UWT0CtbXp5hcqDlJBVSXdb39u23DnjipSzQ9RWrSw5URVC0oTdKmr0JG20+tYVtqgBSjow88fmWMOv0XL8bZ3tL96H/LIGW6AebsrmeuTUtkljdhRnvbqdYB2RIgBS9MYjoiIDAlqRCi7651qVG4oZCg+iUUP1acCdHCCKta6W9hjUCLFsIQvv1phnfRUu8pdHQ2o7LIx7g5mt45hr+7+5W+D2D7mb62MJWCuJ3LcG2vIbKWpU4VjqGuEcyzstRcNyv3WuOetQNMf28fREv1AlS4fKhtNce0dqX4X9spZ0oeyUBispNfYuVuA9k+Y1+3c3kP3PzeX1coamTwM8Ys3EAgEAoFTRDx4A4FAIBA4RZxtqrnopCw7GVWe2sLfEy3pCiuK30GhKgdlUsBTNu8tJdqCsqVqTu/pWyhPkXZ2DJjkMCjokAVZMkvaUUykz7Nej0ku2zJRyJsKLIWlN6mYxQzU5Lx16e3Zs02km5Kj5pFpWmA7d5mvx0juXf4BqPRrzrB2Dg9YZCgLzA8yJ6JeQUWn3NJxGp+zWe7thu63xSxKpyxUkkOmIM/I7tcj27JARmRZM7PUtrVZ6BztaNbrVMRy0Kps3toJ6a8YGmmUCpuskV08t/2QVqCNQWGWtVMRS9pWZiT7QoBcdL+eJiPu2jNk4Vf0AWbmsTdC5QCAg6yculFPFSnztS7rly4mCB8VHbJgW7eIIe+VYY14JTkGYbguxNHnXPo0Gcl6lzWL8EyiDy0k3UoX+ulhMgKxOKPcJ2Kpet6zitLea8uRzp2mBzXvnixUHOvnut3cRnhnbkNbgvPxPu6GTKZYd32jc7Sr7flK9BHV45hN3Vy282YENTVEbeTopr03ti830jb2vYchfvEGAoFAIHCKiAdvIBAIBAKniHjwBgKBQCBwijjTMd5UZpLKTIrSxScQE0oDP3OuIpnGAOhmwvBlW7o0e8S8BjoVebUexBNKBL068fFaPX+F0ghjdpTbOHNuFKT0Gvy5ByrYINbjVbYYl82MW5LZTfr8/sosCf2dZTauUiAeym9tnbrU8i7iI4eIay1tOUTeol9R8sByg7Z1/XCg31xe0O1xZV2MylrPsSxYpuLcY0yYC/FjF08r0a8DYpbTmb6/5WJKRy9pv8yXUGJq3ZiJxrI49zo3D41JOAzNheUnTvmtrjgPkavgS8WMMxZzA1wpDx1fsB4zN18zo6CGOYUcidKps9W4hbVYw7lzJ+IQcl4nV4JnjNATy470/VVpxyzhdZkzj8HeO6oCORw1Yt0+bso4PerD1mvnNHSA/l8hPr6F+8OOjctDdE0yxKaT+w1Wsv/QnszlEJT9/edUtrbX1BxrnH95Q+fD/AZKEed2rdO9KjGu7koyF7W+niEvpZnaEryxoBQKqmkzxL0z/1MUJWCoKJPVNTvH6264RzXuYYhfvIFAIBAInCLiwRsIBAKBwCniTFPNeeolT/091FYJQ2KW9fg09JIfsZQHylCZO2gA3cZyiMwbag9UyoEalDfohmpNxZIH5vA7Q+0Wn3Us17mHxlZKJ+v5N5YzqUb/rUnfDo4KBBWegeIecK1ZZqdUBiUgqmI1C3tNzXXt83xfz92vbP83aPvQaHsm27pfPXPUHZTIqgr97cp/6ExhSNXBK4KhFAFqXm3lShEgIF+BHptO9HvOf4M11O5WGyfbLIs7eOWGbQOaPiyVNit6Z+SNPq/hEr65pRTk5tUNc0y1AyUzCMsXTgUpYQ6UmZ67c8pVHdpQgrrLXb8OoGIHhmrA/2Vura9pTs5xEYtkbnUoMfRqdmbKQz0O6lt1YRWK2O4cZTlFYUNEBfarqWbnogMdShgHUZWstHJKWAcoZ1zpSXbgVpBVrvxqhBAKjR9cuRoVwcQoATqzDtwD+wbmDgs7Ast9PW59Q9cFy3LauTUM6XqWkeFe5u61DZreYH4MpS2Ty9H22WO4D+yhHKxy64cGHwhhtXdtaWrfDDI0QTUHAoFAIPB1iXjwBgKBQCBwijjTVHM/VNIP1T0KS2IyUvUSB8fp0CM1hyFAa5TmLRXIbOUcqcdGLUscDQ2qrBJLr1GtZ0xxc3zP4DIJK4q4QF1nqBxnhb+rupw0sc1OFSM0D/qqs99L1aEM2ak5qG/HAhmv377T4/sjS9VUC9KY6GPL1sl4CopurB0x2tVzTye2ETX8mTcugBIdu+mPl2CDpU2Wfjo60vOvbumOGzPXr2hTgYzpEpT01kWX/fnmrZPtVIPy/deW5j28oRmbpHn7xs7XHjTh5q6e+/ybd062L3zrnjlmcwvZ3szcT35+IVsfRgGDo4NTYniG5h9O7S2xYgD7gdJuC0f7Y21UzEIe7FgMOY0M+D1mN6P21mItZMjg9lnuRjwL1HzlqgBGRnAf4QG3ztpB1wbNWyqXsT5mqASM8nQXTatsG1pjDENvZGcXQeUv+n+7+1fZa1sLmEd0Tt3reKltP4BM3fxQDTrapV1n7QCDFWa2u3DdEvfx/jbu6U7RsMZ637g0xn54RrhMdIjPGU9zWdn9ulUjXeuUtx6C+MUbCAQCgcApIh68gUAgEAicIs421SyF9FJI2du/H/oBWYEmq9ZlHpPO6kmVQZzAqX2XzOxk5vJg6e4OKgtoglSZ3a9k1nR2/+zn3Imjk0BJEERvfdo2aOgW2dilO1+DTMwV6MSusdQWmaC+0z6GZoAUtaV3Nkr0P4rqG2dkQBGPNQr7iw27384btM/rLfDQSGAsnMBBDoGIBgoCmdtvyEnr4WJdGGG+0H6Zv6LjmcTS58OeNqre1O+dzpSSI/0oIrKBbOP+tWhCd8Hsl5DK2SE0MrZWsTIC9XnuDdsn25e+68rJ9u5rrcjCFLQ4RSR6d7vgLBqYhe9CI+y/FufwlGEOSn/IKe6A9exFXRIpaZgDODrYisvofoNjz5drPW4BKrZb3z9kIiIyxqknyOofi+3XEe43HeZX78xNctxjOtGM82psww3ji7o9FKCDt2naYA6RHP1iTRwc1cxwAa6pc+I0FDoxVKynXVHF0GD9LGF+0PfeJIFjCKMZJ6LS0scZhgfFXdtfS6zB7hh93IAiH2xsCzonUsE/mgIoIiKpTZJaNzkfgvjFGwgEAoHAKSIevIFAIBAInCLiwRsIBAKBwCniTMd4yyxJmSVZS+3e1+0MjgeFU9RhyU6XVECbKfzJGbsLDM0XUFVazF2MpNV09XqkbdjatEGlEYcAKjoF40GFi2Ej9lRkLHOwbaVZ/QhxpLZwqfA43xpx3dt37X6HNzTGsTrU/Rjj3d60KkjNnvbxqGR5hr0mXuOAuE/hlIXKWse6Qoy3gyLP2k1rlrNkjbZh7OLy9ALv0ZeDmzcNSp/aAz3H8dyeb/2ixqwmG1C9uQR1o23bDwXE7icwkujP23hh/gTiZIeI5e+Y3eT8Yxpn3vtGLRPae0LHaTZxeQymhAilGuJzJFDigbyBIffxVc55lODZphozBHmA8UPmYnAZ4vLMaShd6SDV4zrEIpdLO2bXoEh07Y6e7+AGchXm9tyzHY2vvuYJbV/9mF2PY/TLAAUvH7geEBtOJXJPCtv/Y5jDdChRq7EgW1ffx/E0hiidnQMsP+T9cHBKcj3KhgaUGKbOfi9NDliu2bJE0T2NiuTK806+x64ZDnULtaveq+Md45qOtM/7NeLtvV1nAwwYigrX7koHs5Tdo6j1MMQv3kAgEAgEThHx4A0EAoFA4BRxpqnmJKUkKcX/wE/5/UsMxJUvlIbmhXg7lGSWrnTgCGLfL70EmvElm7reITV+tqcU32ufsqLlu5e09SVUZnJc1eA8bgeKwQ9KjZSemgG9TO/T3NHnHXwkj0GdHvyB9bO8+bn9k+31TaXkcpRpdduWqmleo1Tn5uNKb04rK2BeQMx9XKqyTe76vz1GackFbfccFPl834nJH2u7s0bbt2FZcZmd1+3JptKeufPZ7BlWONLPVkdmN1keaZnCADGoYQUR+6mjrCj6TxrVid3vPYWykDlos027GnafVrWqnYv6XWN2f2UpORqLDOZvc+9nzfI30odeXUq3c1CsvZuHLcwBsgeUc1W1bUPV6XjmkDnrvKEDjE9anO/mkaWaP/e8zuvrn76rx39h/2S7XNr+mk8x5994VdvzPVfMfvnT2v8bHHa3bhPqDyv0XetUo/JKJ3BWkbqmuYALbXXa9g6UdHI0doPSmAzzvVvYfm0xP3p6Pw92bGlkw9BURS/izJlKUEXPeN049T8TYiOlba99tYTpyD5UrOag311FUzHG3Cs1fFjt2GdJtltK1nz5j9P4xRsIBAKBwCnikT94+76XD3zgA/LUU0/JZDKR17/+9fLf/Df/jdFUTSnJBz/4Qbly5YpMJhN59tln5XOf+9yjbkogEAgEAl93eORU89/8m39TfuZnfkY+9rGPyTd90zfJb/3Wb8kP//APy/b2tvzVv/pXRUTkp3/6p+UjH/mIfOxjH5OnnnpKPvCBD8jb3vY2+cxnPiPj8fhLfIOi+eOs5m2nZCIJovFMecsspUNtckMvI+PtizctZXL795SLmH/h5sn28Q3rJdmCIt3Y04zpjdYK0k8n4CB3dLOGGHzROyoQVFQOKqnNXYYsFb1A660cN3/c6n5HL+l13P3MTbPfrc8dnGx3h+pJWoD6SdOZOSbdJE2FDx63bZ0gM328RSF9Sxc1oMp6eH7evaPbN/5v65e6QDZ23ek1TC5Z+nbrTcq/Xn0Sfp1OXaqHOk62Rna3k0FKa23H0MGcgbTsoaXzO4x1MUEbppbCr6/q+crH9f3ygl0/Wxd1PGYICZQ04XCJ+wxzrEknl/b6zPyC20DuFOJa/NHNjNaFU5zrkIWaQ/mIHrf9yN6yRvScht9t5cw1avhezzu9jpdftmN77ddun2wvn39RzwdTD5+9usT3HoGWfcVl7k/r15xsb7wW2by18wRGJn9nutxR+Lif5TCFaKh8Vdh7Y6KKGPqOpg0iIt0aVRW39Xz9sW1rprc247ed13ZSTSb62dZUxzBb6XbTOB9nrCejQDjYNtAIJ8f9fuX6f7zWMTy+pWtzfqDXvu3vtejXEhnOOxedUcPTtSydccLD8MgfvL/6q78qP/ADPyB//s//eRERefLJJ+W//+//e/mN3/gNEXn11+6HP/xh+Ymf+An5gR/4ARER+YVf+AW5dOmS/Mqv/Iq84x3veNRNCgQCgUDg6waPnGr+nu/5HvnEJz4hn/3sZ0VE5Hd+53fk//w//0/5/u//fhER+fznPy/Xrl2TZ5999uSY7e1teetb3yqf/OQn73vO9Xoth4eH5n8gEAgEAmcRj/wX71/7a39NDg8P5Y1vfKMURSF938tf/+t/Xd75zneKiMi1a9dEROTSpUvmuEuXLp185vHcc8/JT/7kTz7qpgYCgUAgcOp45A/e//F//B/lF3/xF+WXfumX5Ju+6Zvkt3/7t+W9732vXL16Vd71rnf9Pzrn+9//fnnf+9538vrw8FAef/xxqbOVjLJC2tzGtYpMg4ksoxm8Vg7iXG2j/PxNEy+0NSKL39s/2W5u62fzAxurY9VDmmts4WjDxpnnVzX2NNpCrAIlHp1ze8mNyfeD4wq9U+85eX+ww04lpsWLd06291+0zMLhjf2T7WGlfVzRwWlhv7ODI9EWlInGrjymhLrXCDGzfMeVBsFt584LGqM6+oxurz+7z0PkCPFoKlKNb2+Z/Vh6sYVSo40dG3titHU1gnKPMzQvEOcvEf+iGc3hvlO7mmu/zna1X2sX18p7bdNoQ/tyY9PFQGEG3q90u0OsbjS1Y5ZhOeWIN2ZOwauGWlWOMqjWz69eXx9B+ejojr321SuIJTZQ/dpEycrYlalgflWVNnzDlVWVWHcHrX7vy39gczMWf3DjZHu4o/OmRGy6cwWMHUpxjqB8lT3/ktnv7mu0fYvLGhyd1ba/cgTdOTJZ4a49Y2mPzoEe67FzKk8s+8qxFuhwJSLS4dTrO3h/YdtajaFeVum1jzfs927vIoaMW2WJNbdc2PWzXuk4rblfZ+ch3aKYT+BdshYoFdpYQuEKeRpd7xzG6FhW6hzftJVi0nQjWSy+hjHe//K//C/lr/21v3YSq/3mb/5m+cIXviDPPfecvOtd75LLly+LiMj169flyhVt/fXr1+Xbvu3b7nvO0Wgko9Hovp8FAoFAIHCW8MhjvIvFQnKfXVsUMvzxX3FPPfWUXL58WT7xiU+cfH54eCi//uu/Ls8888yjbk4gEAgEAl9XeOS/eP/iX/yL8tf/+l+XJ554Qr7pm75J/tW/+lfyt/7W35K//Jf/soi8alrw3ve+V37qp35Knn766ZNyoqtXr8oP/uAPfkXflbJSUlZK5tS1c8M2gBbKnSg+KLG7YJz2ryvdd/iio5pvKk+SjvV8ZWNphhpfWzQo5bl2YPZrrivdWb2GJQbYduU/2XB/OiXzLuEo0Un4rHBqUGkBBa59lEsdOsWsFcoPGpQs4GuPBkvVrAftr2yk37t7x8pGbVwFvTzTdrdOUWe5r987/wMdmwMoDh3uW/rwqIWCVNLP1o4aHoOe3HwtQgCblpLegMJVBrOIAy/KDjWtkkYeUNRZu2MSqOYO5UTNwtJrozlVnrTvarcWEgzc0z6Ox7VnMyekX7JcDaVivStnQalXj3nYD/Z8i0b7/Oi6zqE7z9u1Nf+cXnuPPirP6/c2ThVrUHEpGU/3T7Znl+z8mu5pgOD2UufQ/qdvmf06hIxqlDRRpcuHfhi+aEDnt05BbfmKhm6Wh1q6Nt1w9C2pbGNq4MsFoQKGz9g+bwwjGFuGVrwRSAZz+Bb3ueTUmfIc4aMa59iy/T9Aoa+A2t5oqnOjObDXNz/SeT1foWzP1UMuwSEPUJlLub2mBjQ7lboKyIOVpbs+hL1YjlpP7LNkcm5LhvGX/zv2kT94/87f+TvygQ98QP7z//w/lxs3bsjVq1flP/1P/1P54Ac/eLLPj//4j8t8Ppcf/dEflf39ffm+7/s++fjHP/4V1fAGAoFAIHAW8cgfvJubm/LhD39YPvzhDz9wnyzL5EMf+pB86EMfetRfHwgEAoHA1zXOtElCMWRSDJnJzhOx4toDFFlSbymilqo8yHTsD5DSd+wyCUG/Fsjq9GaSpHY70HrDkaUWl2Ce18jWI2nhKaYc9FPCZ07kSXooLhlPU/HZkVC/gjh9vrZUcwUlGfoGZAMF7e31rUDvLNbKaLSdpWqqHVBJu3qO1U2XmXhNqanFF3T7+K525HyxMMeseyhIQeVscNmRRzegboRzt3vW0GEE/9XqEjr9hqVOqULFbOUa9NUk2T7OJzpfqfG+3LcUfnZD59v0SaXuhtb2Vwfv2H6h11RDtStNnMwTs+HRvlzsuZscVCxUqDqn4LWcw8ziD7Ufjj9ts+b3v6g0b4Ns3OIaslZbN8mXeu4JCLO1My05vqB9dIAqg/aPLNWcQX0oQxu4ZgbnEZ0y3m+olOd8jpGVnMETO8ss08fscZ67d0pMVHDqCh0LqpJJbuduzyxdXkbvqxF0e8Byyh3VX+AeWo1B3+56v1rt/7ZCW3ewHu/a/prgXjs+0nPXd+25V5mu7+MWmfGVq0aYwYhlD+dD1nxW2LUw0LQE6zYbXCVNcSiFY/UfhjBJCAQCgUDgFBEP3kAgEAgEThHx4A0EAoFA4BRxpmO8WcokS5nkreX8W5guZ0itz5Mvh9D4Qg4VmBzvs4xAROizLB3imZ0LPXUoJclzjSklsTGEOeLJyx5p9kiFH5xSDmO8Df50Kl15TMPQa8XYk7smli5N4IrkYlmS2djwybnRvN45t2RQ4elYapS72CaUbboNtO+6cwFBKcj8SGOC3Vrjl0NnY7xZDwcbKPT0nY2bLhFTWt7Qz5a3rSpZNkF5EeZUnluRlxrlQNkhYtprqEbNXGCogLE7uqhzFkJrqHFlB3rMcmLbMJ/r945n2pf7iD9Oe18Khz7PdG4MLsab9RrnGmBwv3YqW80h4vxf0M+Or9myr9UB3Zx0HrUInXtzc7qKpRolaUvXX0famYtOt9uVbUMacB/A75IMsdE8ecN2HUO6im24OOfuE9pfI4ReV879qsJYWxUr+zuJ1V1U6CtylppZdJyvMJ6vku2vEjH7AnMlubYOlR5X1ToHitq6afW4n+UFHMw2cX3btg3VsfbfCOtnsuUcy+6qCthyrR2bxj6PRNfGxSfgHgd1vLpy8XuoImYY59LlyfTVIH11//vj/RC/eAOBQCAQOEXEgzcQCAQCgVPE2aaas0KyTOUo/w16ECzM6PfKTgl0QVYhzR6yU6Nk6UjSQk2rn/WO5q2gKjOwm50MVb+GoUO/d7Jdo3Rg6Sg+CgMllDysVpa+7Ra6YzUDbeYokRrXO95VGrXcvmH2yw70OgawOB1KKHJX8pBlpK5B2zixlHwKE/MJypYu2raO7+j5WT6yhHmCEyiTEh3WQ+Wpd6U867VSyscH2u75bVcasQ1hfgq7t/Z8011QsaBOs0wbWM0sNUzFpt6oXblSOOx3hDnU3HVG3oXud3elakLr55Vi3d2yY7Z7Sdu9tQEqMXMUPqi3jvS0K9Nqj7Vfl1AVWy0cHdxp23OqpGHNpWRpxgT1OYZkkguL0AMgx/qpxFKiHecRvrcG5d67+0g20uvdPq806vlv2jX77T6tn5Uj7ePOl/dhjqZM7zHe5GWMkhaGxHrQpcndGyv0V8/7Um7Lr6jmBO8JY7IgIjJCSWWB+ZqP7JoZof9KjFM+g3rWll24wzFMQrZ0PmxuOxOOubkZ6ebIni9BTGvnoo77eE/bOq59qSWeEbinJ0fiZymZsOaXQvziDQQCgUDgFBEP3kAgEAgEThFnmmousk6KrJMsWQpMlnpZq40J9rd/Z1SgSapS9ythpjsuLWWyHis12C2hYuXbQKeGjGYFTugcAvXlCOpSoOtS6ShyZA5TtSs5VRkex6zTwvmlTiu9xs0LSofNXrNn9uvuQG0HmbArqCWVYttQob8mu9t67vMuUxs+qxUsIIdde+31ee3LyXnNYJzMtT1NZ89NOrIvSD85OhKhg/mBtmF122a+zqD61CN7My+c0tcEFOkFbdMaamW5yzAfmJGKOEnvQh4FFMb270IJaG2v6Rher3deuK3fC8GmxfaMh8jizaA0v137eGtqadkSqj7MeLctFVm38ATGIYPzgG2QfT6A1staqAw5urUkbYylNbhwA9s3muh17J23yk6LY/2sgnIbk8WLDXvM+IJ+eOUN+tlj33HB7LcJo4YMfHfmssolB32eMYP6wYpzdO5l9nmW2ftXwexl0tMuuZ60bLWL+5K7zSWElhKzfl06dT4GBUyPZ3g1p8apQWG6tfCc7vbsPXSy0msccI/3/sW0ba+3kWG+hTVcuzYkhKZymlI4D+vhgUUf90X84g0EAoFA4BQRD95AIBAIBE4R8eANBAKBQOAUcaZjvOuhlnKo74mbdmuNMq0ZS8ntflOE15jiXm4jbrFtVWqqO4hFwslkWFjOv0Acdlzq+cZTGwiYXtTz1zXVqnCu3MYBaTouiEFMKhvYKnG9ba3fU4h3TdH9ts9pcKd58rzZr4JDTsJ3lVAm8n28g5KaS09r/Gv3NTZeOJpAGQjlEFVlz1ci2FZCGWh8S79ntbSxVkl6vRlKVprBBbbQ6ZhCMj+ybdhroMKzg2CWDf3J+g7iWohlrdZ6/GjuYt0jKPmUeh3dYINr3Ur3a39fG9uVNl54CEm15mWoXTX6vV21aY5ZHWtJ2fTCEyfbG29w7jiIHxZQqypdyU+GmF7C2DaZUyCCAl3ea3kLY6Apt+sxQzzULAu/1lG+tnEZSlNPWcP2+UKvvbmu/bqHkpOt19vchwnKr/Yu6vdu7jmFK87lBmu1dzkJOAxL0yhkiYgklMOxwqnosL6dkhzV+pKgfMvlv4zGyDXgbeCui5uWKBfE+72zSuM9poB6VgWVQSdAKIK4eo4Yb20rn2RAX2Yo18xL21aWUZZTvb6SimeuHFIwl1kxmg8+kyH98f8vD/GLNxAIBAKBU0Q8eAOBQCAQOEWcaaq5TCJlykzZhYhI20CUHUbgg1MWWlGQnoYJIE0mtiJAukOlKDZQDlHmtg3dsVKD9GbIL1labwslO2Wh52ihbkSTcRGRDHRIAUonFY7uLihMrnRY7szqR6DZtzdA+b7BlpmMunMn27Op1sQc7kO9xhlJn38cSj7fqEo+mxfsfuMCxuygFvvBUmVUYpJNfO8OyozElQSstF9HqAxae6UvlL0UpP9cuQdVgqZU9TlvubL+Rag03dD5sDrU99cr2w9boCcrmBqsXfnC8kA/Wy2UQl47sfuhhfFAAyUm9OvS0YL1LSh9QRWoHqzKFqvXEj6re8sF1qDlBtD7jSu/GEBX1wNUkEAfFm6tGwORAopzO3ad7T2la30HClJbb7BUc4+QTHes7dmZocxozx4Df3QZ19193xcREay7DBdfDJ4Ohpl7TSMDV3pmjtHtElx1cjJunLusZMsdNZ+jHqja0O3B3eeyEc4H4/nelWHSbKMEBVxgzJJ7HA0lSiB5tbVrQ0sFLt3sC3ffRClhjvblBalm2+yBfY5rSI6az1MpefryH6fxizcQCAQCgVNEPHgDgUAgEDhFnGmqeVW1kleNbDnFpgxZzvk+1FkOLI/QZkrDtRRiX+n2eOzotW9AFt4uRLyvWbquPVD6YqoMrZx7s82I3LkEmgOM0wC624tvU6h8QLvvyVambj38hntHkxQQUh+P9Rz5eUupjd6gDdyAj+zOSs83qix1unFZudjJVT1mPHV/84FmbOClOj+y2YNzZCWvQW0N50CrOyWmqkP7kLE7PrA+uz38eKVClvvEZ8hiNyiPbbzG0mvLl3XuLK+rqWyOa81cBvaQ4CcKf1+fbLkCVXkIT+fUWmoxp6KRocp0n3Jq18/kkk6c2RYy1gu7X4FwCBnf5DKrc2T1j2AoMCrtRa1B/9XIJi1ptOE9aUE9j2fImr9qqebNN+tn22/QObDjwgMFqF2qOU2wRgbHR9L3pCqY4e8MUXCLWNJIwqmNjSf0tQXt72j2Dn3B8BE9un2VQQ6qn17ZZWbnTQfatEUoot50VR5QejLVCJ7mxSUOhhbH/U8smKHMcc+cRNSAtZohUz53+zFMUSFlesBicBpiknAdVObqB3uPybIj891fCvGLNxAIBAKBU0Q8eAOBQCAQOEWcaapZsiSSJem9Xy1k2vsWfrXH9nITRN4TMuM6ZnK6LN2ty/p6eBIUxR1L1VQoxJ9e1v1mr7X0bQ3GYgAt1ICmqgpHgJBCQRbrPXaQSFvMYZIgLvuuQ2ZhmZNfc0rnV5HZuaEZyjOKjzj6sJgqpVOMIOjh6O5moWO2ug0DgDvWoGABo4YlQgIZKPKytGNWwvM2QxX86K4V8chuaeZxjs6cnLNjVsJ4o57AR9juJlt/Qing5q5SnSOYcOSV62OIcHQwDWicd+0BMrIXjfZR1TnaEhRkhTlVg/Ld3LUN335CG5FP9ZiVo5pHAtF4KDgUhZ1fsy3t/52r2ieHN+04yQrfu9T5QNqycucextq+ncs7J9sXX2+p5u0nQTVfhLmGC3lk+C1SQnyEyeKDqx5gTKdA6KdPlsamN/W4hMjP2t2GkeVcIFu890bTWO89hEXKhKzy1mUA00QA/rl9Zu8xfaLpArKQa9tfdQVxGgil5C5Tmz2WQzQjB5/fOmqeQhsZvdNd3CXh/pWjU5yukiRQ1yXPh/a4bpC+Y7gHZhHuXttluXTZl/87Nn7xBgKBQCBwiogHbyAQCAQCp4h48AYCgUAgcIo42zHeIZNsyGSonGIThbKRMp93lsBvkf69pmb5GjE4K4Ik9EmuLiLW95jdcdTBnHlCcW57vsyUe0D0HGoqfebigIipZigPGJy6UYv09w6x2yLZEhZOggLna20llRSVtikhOJ0hHb+pbIwxIY6UQcGoO7ax2+N9HYD5y/rZ4TW73+pA92sRgyswMLUzbB9BBD3bQznLeXuB9RUdnBrnnl6wYzveROkSjC1qJ1VUPKHXmw8a85c7MBdwca014rp39nW+Lo6cyhbiuqlDvw62/3vEsiooepWV9lHhVIbyYygVzRlItOeuMC8zzKLRYNtab+n3bj2ubT137EwqSozHMWKWMBeoRzYuPNrRY84/rnV7u2+wY7txSV9PppgPtV0zWYN7QocyLcZG3ZhliDsXgrF1uSctlJMq3AeSi/PnFeKKeN/7rFcoAWLcOWt0bQ65L7/Ssal7xpKd+YRovgO8MCQb2fPxnlPhPuDV9gTx6Q45Kj3uwdngVckYP9b3U257gqVPfeL90M9X9BcVvFDn1YtdC8kkzuC5IFadLR/ye+LaD0P84g0EAoFA4BQRD95AIBAIBE4RZ5pqftUkQSRPliZJSOkfQC8UjgbtqHgFAfkCpRq1K6kpZ0r/TUZKPYwntnyBfqItqW9HG1OMXEhTQR2n6Cwll4FqJlHWO+WUDmLk/Asr7+1+KSNVBo/hZOm6klS4YV9RguGurwW7v16COj20bZjDK3b/C7p9dMNSOqtDlB2B8ism2l9bTn0/B7U42YWY/5bt1/ElnUdj8GsTp1xVw5whG6GkzHmf1hM9384bQIe12nlVZ+nIY1DKd19SI4r+85ZyTwPLw1DCMthwyhJzfMRZ0CE8cGT7a30NtCBKu+QpR3ai+zKWfjgqcAx6cnZJadA972Fd69ii2kbymfZXsWFjNVs7+tnmno7txkU7d8fwl5Xi/jSjiEgH5a8G4YYB1+DvNyUpeCp4eeYRqlYN5o2MbH9lPVT0EKop3e26N0pKWAv5/de9iMgwsKSPPrZ2Huaoq6GXLkt3RGwJo5n/g123A1pCmrfHGi4HpwgGon2FEMqydeEZ3K87xMc6R11vVNqmCe7jUyjg5YWjp03YhDS2XWdZyu8pc3oY4hdvIBAIBAKniHjwBgKBQCBwijjTVLMMSWRIUrpsXsmVlhtAmSxySy12oGd60LkU6Kk3Lf1RgD7MoNI0lHa/YUCmHJV3fIYy0vUKqMVMcbxjYCQNyJimao6j+DKo3uRQs8ky55UJvqiCRE8hPvsZqlGgMAe0J3fqOi2y/7pGt+dz29Y7t/S4w1eUZzy+YSnW9QJetmTrJtrWbO5MEpD1mENJK9+z/TDdURpzo2BWrb2mAuNOeqltraFDh+7LoCBVTpQeTc7gQ0A9M3t2yCy92cH4wVrwevMJ3WywFphNP1q5bH9QwFT6Kns3d9EPVB0acpcOjxBPMdOxmGzZ711hqAt05XgL2a0XnZLcee3LbZg9TKYu8xhhl8TsVkf1dyhvmDd6jkOESWRu18X2FMpHe6Qt7djWoD7p0U3q+9UPdbPEvawv/FzRzRxrndOhdFJMJcJKzNjtxNO8ujZGoIaLbOz2wz0w6aD5jO5ED3FcPG+bK3f/oj/z8VyPf+EVux7vvqD3lfEhzCzWtq3lFOGo12obHntS59TFLftILDN4Sfdcj/bcXb6SLvd55w9G/OINBAKBQOAUEQ/eQCAQCAROEfHgDQQCgUDgFHGmY7xDyl797+JkfD2wPODYxn0ahGoS1KrqCbplbI8pkI5fIciSOXPsAjG9hHhAXto4QFHCVadhWQjKPVyqf1FQ+QVuOy7UbVybsNnkrhwC8b4G15E5FReEFaVhgKljqYUrS0CAemj1e1fzQ7Pf6lCVcub7Gtea37Ux3mXL12gr3HvypTNYx3UMcMqpL9vpX0HJqti8vyLPqyeBuhHm0NGBc3g5RFwd5RDVtp5vtOFLu1AWgmsaN85c3pigI64orpwrpyrP/R1ZfAlFhjlfbGq8PHfzMJncCrTPnc/kKCB2uz60+7UHeh3HUD5aj3W/iy6XYgyRsmKG/IvKzgEaxQ9wcOrWNl67j2n54sv6XQ3K3bI7++aYw8vaR+tv2jnZTk45aXOi/bV5Xq916qcXygJbSuclt8BNfgjiq+jw1t1vcsR4qXpXOGcdvuyN6p2PBUOtispV3qmHpTZ0R0tUrrKx2wa5Bzdu6Gdf/E27X/l7OmgV+vz42K8tOHpdVne17Lsv6vFv2THHnEdOSGaUqyxyGSS/R1vswYhfvIFAIBAInCLiwRsIBAKBwCniTFPNRXr1f+Z+4Q+9XtYaJQHdylFld0EdsFTiqh4/9I7GnoNOIcXqlFpILfZU0nJU4BjUDY2bqXWfHL1D0+oBFM7aK+rkbNOD/8aikowRFs8spZMn0uzoB9B/nRNHNxUooHr69cLs1y5QqoTSjaaxbehbKjbpydtS3y8LOxbtXF/3h2jDsS3/GXqlsRvQ067Yw5ho3IFpw/EXj81+6TqpLu3X2WVQ385cI0fpWUnVqdq2YgS1nb4AHZbstSeMbV3C0AHhlPFl24adN6ihQ3UZ4+mq0DIK3FPVbHA7IjwwHClluzywbT24qX20vqvvL+9ou7dcSGeNsc5hspAc1TzDgmpblqnYm8cLL+o17f+mUpjFHVyDW4+tXpLkjV57t7DXd3RJ+/nxt6rSXTFyM8w0HZ+5fiWlXFDNrtDrK1yYJE8wGTFfZNvA9c2wRDE4BTWUuQ05wg3JPlr4vZ0pLUL/u3vo4q6uzxe/oMcsPn3X7LeD/m9H2kfru3Oz30A1wNXRyfa81jYcPm77eO9JjWUwJJO7h86/UVH8chG/eAOBQCAQOEXEgzcQCAQCgVPEmaaahz/+7z0Uuwxekj0yj9eWdklL0ME8voPQ9txRp8fIiFzhe50Bw4AMvQxZxJlY6ro3quoQmkeWaOWGyWTPgbbpcpv5OjBDFiowpdQP3C8H3+0TE+ltXIL2armfy3wdQHXRgCE5CmxYgkKGJ+oquTgCBopn6JFpnFrbD12rNGhag3ZeWRp7eYS5gn5Y944yPNJrvPOiUm+LP7RUc38LoQzQvGvQkbLhlJi29Xsnu3qFsyt2DszuIuu9YQqq8w6GyccMBhFbV5TqPP8NVunrwpv1s8m5+4vvi1jKMFGQ3na/dCtQeejz47Xt1zu3YQ4AH+bRXT33XUfzjkXbWk2VmhxPrHpWT5F9mGjsOxWqu58DZf6i0pEtMsxT7RS3Wv1sdUfpzdwpfa0PVBlt5yndLs/be8IU12iqAsSGRhLoXK5hI9bvMqYT1lMyov8WnFIlQgo+VMb7FLOxk6eacRyNYhKur3f35yOaqryAbOzbzoBhrGPdQz2uaO3YDsx6R7gu3UW2880jc8wS1POMGeLOkKYtc2nLL/93bPziDQQCgUDgFBEP3kAgEAgEThHx4A0EAoFA4BRxpmO8fdZLl/Wy6VLhR0hxZ1yx72wMocHfHSNEOdKxHtO1ztEIhusZSwecw0saI1ZXMn3+wUbSVLrp2B7xJTqI5zDu6iI1Cf1C9ZnM2R2VCFckpMkPXgkrZzyZn2jMZShcP6A8pqh0ulXJxiILtJ1p+bWLFXVQYqoYj8ZULlysparQXygz8S5NCeVF8yOUPxzbWPAByoQO/kBLTpavHJj9OpRIZQXKk9CxpTds39TX412NvW49YQdjudbxZOlT7cZ2dAVG8a/dONneQMnc3uM2xrt5CepeI6gWufXDEhT2+LqzsbXlAs5TCz3mwFaFSHdHY+TtAq4wK23r4dTGxDfP6bVPj/VaJ52dhw3ck/aPtQ13X7LX1L+iseXVHM5ALaXfbIwx34eqVY32jF2cGVN5/4X9k+2dJ8+Z/bIRHIR4H+jd+u4Re6VaGNZp6RI1BihXFYxT+pJMvNFTGc2V0Qz4jEp5vqQvsTwPczTh/tW09tzzNdqwr3k7ZW/X44CSwwXGqczttU9qtJVxa8yV/o5zV8NlDFgLrmBOylyk9MvjIYhfvIFAIBAInCLiwRsIBAKBwCniTFPNkueS5blRfBKxSkoZynyaytJ1zRhUGRSuRqAuBicyPhToMrDQuVhFl6zQcoERFKUKJ3RO5akBVM0ASrV05RmDaRKutbTD2WN4k1EZsufrKLiPkpHBazYZA2tQYKCN+8Gl8KOMYF1qn2S1paLqSsmbokRZyD3XxPIkbXcNCnm26Qzuz6v6zAisXunGNqG0pIGw1v51e013Pq8lB8cvKr3cz61SjoASy1FStoDK1tYrE3PI6qpex3iEbWcAvzPSPh/Oab/OHGdYP677bV1VSnm0o+/PRra/xjUUykALdvco87A8TN/NBjthW6ytBiVDq5edctiRriGaljDa0y7tvOnWSueCmTTbIiKHMCB54TP64d1/Zfnu7oYOPDX7j0Evp9a2YQK1Npb+DRO70FqUJh5/EQYaR5bezKaUsHPxHiCBPi9AIfe4d2SupKmA+QrpaW9QkKHkMEO4yN8SBqhNGbWrwRcoseEIwaA+MHMqdcMC1w4zizbZ+cVqv4TStc5RzTXKi3if63u91v6unZNUvSs2oGJV2lBZlSZSeROLhyB+8QYCgUAgcIqIB28gEAgEAqeIM00156mVPLWSxFKB9KsdQRloNnXelPA4Tb1SVi1UhqZTJ0w+Bu+FdODKibIXEK4fhFmBljKkEUEmoLihQtUVNrM69Tyfvt/f44FJUW+YRfi/t6jikpPusdfOTMcG585Ac3kqqkQWZIXM3lHt6E1QzSOoDg29pW8yqA5VuN56otsb513m62VQzeeVbs1GbiygnNMhi3Lxks1W3n/pth6yr1RU6TJpS1BPHeZkcwTK8aZVu5rdUQqrhVevz9Dcg3lBjazkqafANnWuTJBlSyWtDUcND6AZhw5qRJlTDDKhEXzgYhlDr+uzO0ZWubVkFmn1uAptqkB9zxx9W88QoihggNHZ+XUIpa/b/9fNk+315142+1VYWzQn6Va4ht73F9Yj9jNhKRGZJKXSS4FHt1MEKxCaohFLl1katKm0fdMHCPT3XsyfftuJylW2rUPJjGkc7zLbM8zL3Kjy2f5vMae6Qq8j5/fmlmouYYgygHJfuv4v0Uc1DGmyzoZ+EtZdGmt4huPUu8zxJajrNWj6sdi2dn0v3UPCAh7xizcQCAQCgVPEV/zg/ef//J/LX/yLf1GuXr0qWZbJr/zKr5jPU0rywQ9+UK5cuSKTyUSeffZZ+dznPmf2uXPnjrzzne+Ura0t2dnZkR/5kR+R42P7l38gEAgEAv824iummufzuXzrt36r/OW//Jflh37oh+75/Kd/+qflIx/5iHzsYx+Tp556Sj7wgQ/I2972NvnMZz4j4/Gr9Mo73/lOeeWVV+R//9//d2nbVn74h39YfvRHf1R+6Zd+6StrTFaJZJXkjmIt4W9Zn1dKZ/fQ0gizXGmhJQQwSvh6jseW5h0zMxoCDMmZMSZUUw+GDrb0R0GRC1A/aYC3qFgKI+X3FzcfHGVImpe0UuE8hgvQRSyI97OjRIYrBQmo2ZA5gZAMpgklqLHRxNK8U1CGm1vInnZ0Xb7Sz8YMKezofqMrzngAVPP4nM6HbGLHrN8HrbeAScK+pVibY2Q/N0qbJeeXSko/gx9pARMIUtoiIovrer7JAlmiG3ZsxyNkzZ/T65uMNsx+G8jcpp8os12TnQ7SFKC4ObaZ25EC/hBMGDLb1iqnYQgoOkexlgipUOd/OtWxnZ2z86GGiUNdIfPYUc3rOQRRbt052e6dSQKzeQus4TEyjXsn6pJR6AEptsuVW2fIUqc5xlDb/Trw9sZ4wAnz51iDJTOrQcWucnfujOIVCGc584MSi59Ubu7NTUx1A4U7bFtrGDwUoGR5z+tRCSIi0kKMJ6vgI+yyh6uFjmEx1nHP3X2uR2Z6jrmcEE5p1q7yZakVDOsWwjKV7Yd8yCQfXLnIQ/AVP3i///u/X77/+7//vp+llOTDH/6w/MRP/IT8wA/8gIiI/MIv/IJcunRJfuVXfkXe8Y53yO/+7u/Kxz/+cfnN3/xNectb3iIiIn/n7/wd+ff+vX9P/rv/7r+Tq1evfqVNCgQCgUDgzOCRxng///nPy7Vr1+TZZ589eW97e1ve+ta3yic/+UkREfnkJz8pOzs7Jw9dEZFnn31W8jyXX//1X7/vedfrtRweHpr/gUAgEAicRTzSB++1a9dEROTSpUvm/UuXLp18du3aNbl48aL5vCxL2dvbO9nH47nnnpPt7e2T/48//vijbHYgEAgEAqeGM1FO9P73v1/e9773nbw+PDyUxx9/XFrJpZFc+tzFJxArmm1qqUX+GqckU+sv5xFCbT3icXVp4wT5DgX39f2UWwUioyLFFH4XB+gRI+lgJs5vLV1Mo0NoLLHMxIn+M45RIsayzF35lYnvQNjdfS/DNgViRRkizYMrexkQexoh1X80s3HY6qIamk8RAx3fdYYOUEGCGJTUMHmfXrbi9NNLGtcd7bLMy/ZXc4wYEOaAkwozcWyaiffOpJ2GGAmNZRy9dTGl/jYUemCEULZO5alCDsAmYoxOvR3dLzmuN8c4JR+aKlDG0eoxrSuXKPF3e9kyLmlPN0Wp2GQbschNF1+F8XmLuWxK+GY+nwPKQgwMJ7sfjdhrlta58j5jIl/oZ5swm6jG9tyLF1AqdqhJoveWCSFeO7BUxpcBYo5zbblaPVZtsc8L1P+4W6MMWLf3kSLTj3D7oml84RICaE4ihX7Zyk2qAmWBXDMN71G5nbwjNH7Mj2p3H0dpTw6jBW8Gg9QFqbGm+0HLvLqFfSS2MEjpIGfX17ZsT/Ls3s5+CB7pL97Lly+LiMj169fN+9evXz/57PLly3Ljxg3zedd1cufOnZN9PEajkWxtbZn/gUAgEAicRTzSB+9TTz0lly9flk984hMn7x0eHsqv//qvyzPPPCMiIs8884zs7+/Lpz71qZN9/uk//acyDIO89a1vfZTNCQQCgUDg6w5fMdV8fHwsv//7v3/y+vOf/7z89m//tuzt7ckTTzwh733ve+Wnfuqn5Omnnz4pJ7p69ar84A/+oIiIvOlNb5J/99/9d+U/+U/+E/nZn/1ZadtW3vOe98g73vGOrzijuUillKmUUjz9AVoIJgmya8tCilovPz/W/dqk+9XOoSBtQYEFIvFeNIpp+3V//zIOEZEBKe8ZuFym4xeWsTK+uFSTuqcRoD66hNKnwpXRoH2kovz3UuEqw7lrUGWtKyNgW9meYsPuN6MvbVLaedhypQMt+qUgbQk6+ZJTDNpFacSmbjeOjmwOUaoET19vIjAB7zWADu5c2VeBeVSCbh1DZavw9BREsuZQwpo56q4B3TaaQXmssvRtLwiBjLSPs5xC9RZZz/lFZTVn8AFKMzXoy7Ur+Sl1zWxf0Um1er1dW0t81+ouSsWwTitH31acyth2LKNANE2m29onrZuHU4z7ESsH+Rtl2/oXp7FSlRvwDq6dd/AYTN1kptfhPafvafwfo88svclyGXo891zD7n7TIwzHtZ5cmCTjvQ3X7r3BS94TEOfoSzsPBUYEA+c8Qm2u+kdymnVAlaye2B0XoKhb0MH+V+UY90BSzcsDXaf9dNMcs7dG+AMKicveju2QDzLk/ob5YHzFD97f+q3fkj/zZ/7Myet/E3t917veJf/wH/5D+fEf/3GZz+fyoz/6o7K/vy/f933fJx//+MdPanhFRH7xF39R3vOe98if+3N/TvI8l7e//e3ykY985CttSiAQCAQCZw5f8YP3T//pP33PX0dElmXyoQ99SD70oQ89cJ+9vb2vXCwjEAgEAoF/C3AmspofhGm2lmlWSlG4zERkRFJZJa9stmtR6eVvIq25R6Zp7/iKDEpAPaiQzGXz5vCM7CF6vm7tflkLMXjS2jW+x3nSCjJue5PO6LL4QLYwG7EWS7mvkHWdkPnaOdHyEeisCtRnSxUrp240ImXOLPCp7YfiAig6ZAz2S2dsgf6jik4Ob+V6yxkwzJDJjGzqbOlCFOj/Atmzsx17vp0FMuVz7ctuZfsL3Sp5BaMGqHTljhBbH2sbBqavi6UZe4j81PAtHc1dBjyU1lKpczxjBn1m1wX9dBOViRwpvQTtf/wK9lvYaxrVStFNIax17nX2mg7BTlYZFYgQ1sidkhkyaROMSrLK7ldChaqa6VhsbLgMf1LSUKSiL3HRWIq8x1dNdujZ6lTvzmk/bz2mHVGNfPYzKGSkLnuL2wF0MFP8iwEmBC5TWKhmZ/xe3DqDcl6PdODM3TsazImBYY17KGkqXOF93FPyyrZhA77am1AsO9qw9/slVN1WB8jobq1Heom50qN6I1sgK3ppleQkwzUZKtmu9ZQqScn19UMQJgmBQCAQCJwi4sEbCAQCgcApIh68gUAgEAicIs50jDf1paS+vOevhy5juQZiH5nl5TMo4rSVppHnayq/uNgHSipMJYgLBhdQhaH6TOuMpDt81xaUbTKUUPTOYeT/1963x9h1VeevfZ73NXfuzNie8cSPOJA2gQQa4iY1VCoolkhApA9aROQWt0Ug2kRNitSaFqUgVSGRqCoVioJaqfQPAgGkEGjUh0ycEiIZvxLT5kHiEP9sJ874NZ7nfZzH3r8/3Mz+1rIzdQq+w9jrk0a6d+655+yzzj7n3POttb7PZKCsBTmgPBTKVQU44kCutSeMyjGPZ6AFphTtNoWDvEiIzibQjiSUbaDjhxzkyeJYlOMPQlsVtAuEPE1DZYbtV6AihvlZ4ShFdZ9LDKGdIuRiUBRC/jhK/XJxi6uSDYI6Th3yyb02z38VBWwAlM1CSK4VooeigHyT6/p1m4APNm1CYDvY1sPzjwTOLe05aOcy0J7R5JeBDFpESjCndyLHOHPaL5f9xO97pStaflb4eVMf8f83TeFiNOqXmwVnphLaqoImj1cEKlIG8rihyAVXYK7UoaXMCZesEszXA2i3GRz3rUAu4d+hCqhnYZ5a5CKbb4bc8qjP8ZYitxlCMtfCCRCLuYLlHRG8wZoSinjOn0C1LrLnVjIjIiqgNwvbywzxseJ7B3PKlbzeJA/gugljjWFSNcSFPIf41cd9UUPtML9+NaEVtA3bLYTTLKa7TQL7B2121SZ3SIogzxzCHArkTce4M3/nCX3iVSgUCoWij9Abr0KhUCgUfcSypppNmZMpcrKWq43kUDaOVHF4lkaP/wyNFUwC1GLM6TADFFYFSvAlDYcUTOnAqJl46wYyYmGMSjTQ0iF+HxmggVCJphSD6BlUswHKUNBAESgQFUAJhWftFOwTrNsCtSU6mqgAWjVEUwLB80aoRlOFdrAGP2ZJz38GnV0UYctVKNuE/KByoEGLjhgs9DkwAwXDW05qA/54VFf618LvgDq5n0dFxx/3fB7G0xbHDNlqVJcSXQ4282NC9bPA8rFm0BJz+mW/3Wge2rI2cEp0EiSbsuOoFMZTNTQDbT7TsFzC4+oG/b5j61+zInZqFcwpoCMNGDWkK/hXImjNqiZwzETroK35dVcv85+1X+HzsDjp97EBLWCNlqeG80zMySGYNz0f18Z6TluuvNqvozaABiZ8DqCiVAktKqW4flmYr9US2tBAcq4Q1w48pUMD+y7SVGxE2GpkZZsWUMjQ3mSFUwa+ReUqS+duDyQiiqDlsDrir/HNIR4vdxrnpR9DlPJ5XYVrYAoxSkGJrrmaXzvq0FYYozJgJFpYqXeWstti0CdehUKhUCj6CL3xKhQKhULRRyxrqjkLQ4qjkIxQ3knRSxXoOpIVt1C9WRgwRgBFKicqim3gKY8CqLegFDQcCGqXBiltTsPFQGOGQJcWcGiM8Ou0QJ06oNVTQTMWQE2hoLqxnFYKUQEHDCdMwMeaYVUfVDqG7Peb8C+GMWFlNSVCLQk9kIFeMwVfrgDqH0OJvqCyuhsrfUuo7E3nhAIR0LyoU++E0HwcgwnHCFBRMY9XAN6evUk4ZlC1WulxqrMNKkGoStazogrcAY2J/r4im2JyEMU/MeuXg0rQwvFUzcxPfDloMXHab0aoINUgJRBWgFZPeVwDMHeNYNhhlc/rKsxzC5XDBtSNqtyfgBIwxwhBkaqMBG0JpgSNtX7cM0dFBTz57bagyroCxhvJrEhRgBxXDufC8Ju4fenQajiGMcZf0Leo9gavCyFd5YDmtaDalcBplktTFufjhZ67qIZHRBRZTKOhnzgfK1ZQOxirk2YWoPRUQhrH4TVYxAGr1JsNqFwe5teE3oTfbl7AdUn4JmNqysA1IYDq6XQFV1MzmPYCRb0o5svFrkfx+Rc16xOvQqFQKBT9hN54FQqFQqHoI/TGq1AoFApFH7Gsc7yOwv/54+S6ZU4YkAcxQtUHEEBuB4WdcpECCiEXXEBeNxJ52MBhGw3k2USLjglxfH4dGeSWA/GdwmH+CxSyhMpWCapdOeRxS6HqU0MDccyJlyLnAklVzPFiu5NU2QoxVw3tDzIfYnE5PAARXxAFwkpw7MH2LXQ8ISLK0bQaVL/I8fmAIj9VyLebEZ7bNHBsU1CuMjXRegbtYZhTyjM45h2eu41yyPnC3E2EuhFV/GcdUOqqhqKloQtqaNCuEcf+dWeKK27lR30u2E758Rji+ei84eNfBfWrRBxcgy1l0KoX1uQ89J/Fsd9WDippCe/QoQjybpSgAxcfQwItcxbaUcbfwVXJulf6/GEyDPsHSmv5cR7jcB62AwpstbU8DxhV4XvolGP4+gKYv6ggRUJxLsZ5De0xJdQDBOKaV8B7V4ILmJHHDHKgcF2RT2oltD2GIOdkRb7W4nUB5qEBF6SA+FhRKSqGc6uxgo+iMwy1MaA+V4o5gO+iqv9OfY2fA9E4nw9pDVoloe5A6iUWZUZByWtsFoM+8SoUCoVC0UfojVehUCgUij5iWVPNJizIhAWVRtK8QEGWSLWJ1hQseQcmxAJtaUpOf1ikDIEmzC2n6+IUVH2AMpHm8gXQYwG07yBb6gJBYZSgZlOCybtQwAlDpHT8OqTCSg9ooAKMERJBn8cYJKBpuyHW6fMx5KgGhcb1RlLIoNLkkH4S+wTKWo6ZcHsEwtS7AFODEsZdCFY2hLGmVVC2qTfYcg5axQI4zkEqVMlKT5e6OVAjAqUcqvNBmMLPXQuKZ0lDtIA1/PqSFFvPhAkHCMUH0HLSLvyxzE4J8xBstUAnEGEEYuf92LvkN5SIeIHvA9UzGLdQKgqgvcimnlNOkR6NRbzAhcPAuRULdbYClkN2mlby/qRoFcwVODfDHC+VfNwGthWCIURcF/MQ0wAwjwt5XQJq3sB8DcW1iKV4oIXOAnUdiRakGNJFqKjnRPrJGH9tw1ZLJ9XsYEpg92FhxK0Fr2EOU4EQY0GLJ3B7Kmo+5o1VPD2Tr4frNaQlenN8rtThelaHNsCBX/BzoHaZbEPzr1NUFBPprDaF1CHZmvb60CdehUKhUCj6CL3xKhQKhULRRyxrqtlRSY5KMhGvtiyhOtIALVSIClmK0LwAKoXR/KDHf5vMnwaaA6gMK2i4Eio7ywGgULiYDQWg4oJVvxFIEAWC2uoA1ZkXqEi1SGUi+lQG3KgyBtWhwPjx5GK7Cfrzwss08FSUlRQy0DsOqXRBRRVIOTms1OZxTQhpcaiSBgbMWVFZ3YOK7gzXTXy5BJWYoIJRLIjFpMjsulR6MoOhQ9WPIQXB/qDg1F0GdKSBKtFwiMc1rkNlNVCiTiijlUDn5hC7NhghuFPc9LgKFc8WxOCNE0L6YBZgUCA/5zRcOQ80o/XnqpUKY6CMhapMIeyDI/4dpH0DmP89QblnMGG7cNmzwvjBQsU5WPNSDikrJ75TSZDmhQ/ENSGIwNAEDnsmKGRUkqvDvke5UJcCOhiV27gTgkjVAI2NmaTY8WPmsBLdYbWyWA6qlwusahYpJzhVKYR1RKzjQ8wHiGUKaZJymF87qnANTIGSLuaESQLM5cpqv450zF//UuH3XME0HGynIyj8uSygdnb+z7H6xKtQKBQKRR+hN16FQqFQKPoIvfEqFAqFQtFHLOscb+lKKl1JjUIoBpE32LaQLymMXA5VlaAtAXJFtsvzDuUMfL8D7SJSMKjj8zGZFwKiWsCVUSrQ5mAxPwcrzKW5eQfaOOYhxyvjALnJGJIsoouDclBBQkWjNBFtR6DcEsaQD3XYKsDXXUDON4IcrxEBiyC/E4BjUykq9F1w7hYpVMrB3C8RUYm5b0hshalwlKpgngw2LGoI4orvR0FHFqwZICLKwR2lB4baNcjVdRM+vypoLwQ5wajJ96nahPWBIlIY8YDNpmBqD7n4EGoXChHjGqhxYS6yELnzCJxqQvjIiMsKTCmqYH5c5B+xoyXC+gQUUxPqTRZrOCBf3hM71QUXqC7kprOMHzMz5TeW9WC5AlqGhJNPO/Hvw4p/bfipTmii1oVzOOvwOCQQlxbMyYEmbzuqrfTBrGGLDtSAODEfShw7dgHKiwKcyNi2JC8e2AKEp10sajOwdTNgdR/wWijJVcBZKYP8f6PGWzdp1O9jr+Hb0GzBx5Cm4GQFudwkhWtoLI4tvG3DZSDv8GvC9PQsddrzdL7QJ16FQqFQKPoIvfEqFAqFQtFHLGuq2VFClhIqpboU0CRdoJDLXPCgQDkR0JYlUBRWfKfoAsUwBSo3UgUJ2lYioDpLUXKeA5eHguZoatDpcPpj9oQfa/s0ql3x5VJQUkpD3zLiYk4/BbMg2I6tJA3RTgQqLiGo8qRgWG2kSQK2JaAIuqCaS6DcA6CYnFAgMkipgQmEBQrahXxaO6CuwxRUboTSTAZ0NbY0kRHpBlAEi5HKS/ixzeD04m1poHzV43GISzARAEP5YEC0UAyAmH8FUwCCkh707zsznmrrWk+LOdECloL5twOK1bb5fHCgmBVCP1eFC1dRc72n/0wdBPxFXgI2RREosjGjE9HiVsJnnQyo5rZQFjrt3/egmy6fFyYC0/4cKjpgiAKnfZDJ6w18Bm1ytsIpUUyB2Ck/BypCmK5IoT1pEI7ZBt4eMwoG7gm0lxnCljlxYYL0gDF+X2UboEE6GBXnQh7/GPqn0ITGWqG0ButLMQ5wbrZF2x5eNyuYKkvFPIz8/KpW/bzJRcsi+jZUIrjGw1g7GY/XzEl/DDsTcK2e5LRypz1DnW6bzhf6xKtQKBQKRR+hN16FQqFQKPqIZU01l1Sc+RPVa/NQ3dhpg2h2h9MpOVDUKBKezwOFmXNao9H1605yT0MEgtoyQIfEVU8DVYTqDZKd6MdbAKXabXPKaua4p2d6EyCkbzh12msBDVcDPqvkNFAE+4H68XlPKMmAP28FKnix0DE6ywMTKG5cMODrDpBKAr/hWJhKICVWMCUtoIGEGlStApXtWOAszJZx3wOgTq3l1aSMzU1guZRTgSXkH0qg44FlpHbOactW7KnmoYbfbmOQxzUGOjgBxaySD5WqoNZWm/ZjnQNzhkJUoFqgOgmMEEpRdRoHnn9trfTRS6/gprlmg3/fhfMiFP6rlEF1KhxDHJ2NBDUM1GkGp0nvtFjuVR/0LlQud+d4XLNZ37aQg7qXnQNaticqq5lqGs5rrhCHil4hULRBRVyGoWo+gvh3RCqpdyXQ0DUf4wZULpdGzF00VsDK/bPOW+gygOOeR8JPHCrdIzBfCWWbB2wL/dNLuALGVswHOPBIfVuRzkqQ/gY1tEBUzRtYIfp3d0t/nOZP8WrlyRf8vOn8xC8XzPCxdl2Pupmotl4E+sSrUCgUCkUfoTdehUKhUCj6iGVNNQdlSkGZ0nzOd2NmytMFs0d99VlX+I7awtMIRd1TNdmsp3DirqjiAyGEuIn0iRCQh+rZdAjEzCv8t07JGtVBRL3w+zQvqh67U57GmTnmtxNForkdKmnLQagqbPLl0O807qF6u/DWhSriClQ4o29pGfH9Y++AGpb9+uihyyqXz6piBQEMg9QWmAEEIsYDUGEOVchB76xB+OVgHSIMTFDAwXGedZwCm5j11NOxl0H05EU/J80cp7a6K/36wmuGFl4Lq1+q1PwYIjAUcAk/F7AKtb7Sr2TlNQN+DIKaJxBymTnu1xdN8njVwbvWbAABk2aFLTcHZgHBlP+/0NGnvAdVxDlS3H6ZqMop0RDi0GmD3/AkX65zEijbUz7+nSlOGeZznk4sodo/b0OlsDBydgbnCphcWOFzDFRqDehk6V0bw/EkoFVlU0YAZsshzMkc6GVpnBJD0LFCvJRUMzMB8HPUiGtR5vyFIIj9diORIiJI6/XgPEMTFFNKAwysfgahlJCnMiL0T0eP7oDvE+6RgdL27owf64lXQO2IiE686D+bP+R3PurweZOZLvUKbjayGPSJV6FQKBSKPkJvvAqFQqFQ9BF641UoFAqFoo9Y1jleco7IOZqb578f5g77XNGpFzxn3xE5Xswl2gqq4/jvpMEA+04HlM+bLcgXCrWeBHLB1RaUwp/l442l/+dWiElEQjQHVawOtEhJA/L4uH/taqCos0aYCLT8ZzGoRiWlyBmXPoeREeR7caccPxbYIoX5nMDysVqW/4V9ciIRGGA+B5TDLKg3CbWeEnO+kH50Fb5uNLwvWZsEj0MX3me53/dDR3iO58geUIf6yemF19Up/3+b8zG0T/jc0ysQkygdZcs16tCWAy1qQvyHupB3S4d8XBNocSPDx20xl78aFJ86Qvi+6t/PQbw6h8X6QA2qjrnITORhZ8DEIQdTA8hTujrPo9Mqn3fL5kG56jhv5Qkgl15CDci8uCZkoGTluth7BvEWQTYwXzGPK/Or2AWD9RhxyONaSbGNzO9TvIq3q4WJXy6AtqocNiQN7vH8DCDfK9KhlEF7X4m1EF1RJ5P6a2WewEUw4reWAjeAqlhoVCOeAw3M6wyuHc7xdZewjgByy0a0qxWgSjUPLZpTp/z/T77C43XyFb9cecLPm1C4t5SmoJ5QUFwM+sSrUCgUCkUfoTdehUKhUCj6iGVNNXddlwIbkj3F/98+MO1fA/3Xnuc0AqOCwPQTWBuKKkLtCrxP5yY9DZ00ha9qE6hdaL0xQrmqgN8+IbSj5ECpxjVBRdU85ZSGnv7I2ny5NpTJh0D3BcKowa1C31hopVrJFqMAWlVMhAYFMNazuHT04PX/LQW9FqKaDShkWWFkYMFgoAAGDK2WXSFakIC2RI/iNOZtCUhhBQZUaGJO8aXQTnISWruO7j7Blpvbe8R/Zx5aZSI/IVIRB9vx42s/7enpYwnPZbRWtBZeVxrQUibUy6oQmCIBGpSp/0hTCRgT7rtg0tqg3jNxwO9f/uw0Ww6NRmZAYSkp+LmVnQJaDxTj0Lu5IE7NFzG0acFxsUKwHv19u6gcNsd3quz460UA9HkCRhmRaP/BuRtHoJyUCuOBCA0wfBzCKj9nkpZfLl3rj0XzCj5XkhjmK9sUtL2YOn5AARxE9AFxIqUTAbU+C2p9ufBDRtGtBNWlpG8venFDexlGPw5Eigj9nzENJ+aANZh+AoWxkserBIOb3rQ/zrPHgIL+fyIFdgLmFKjMJTKdZXIiEi1Ui0CfeBUKhUKh6CP0xqtQKBQKRR+xrKnmsu2oJEdzp3kV5dxx/8jfnvL/z4X3qQHxb1egmoqnfnpNTt1N10BCqO2rUweGuVrPwJinBkMUco/4GNAMIYHxpFCJW1YH2XeGVoMX5BTQeIIu6kGVZ9n1NF42xQ975IAmXAEU0SinyqIKVEviTzYQJs9DTvGhopRBX1shgYMmCV0goEThK6FOfwZ0WAYUYXFSVHejAesw0NgNQYvDISwTVLvii2E17oljvqpz+kVONZtpf5xQrz2zPt6myqvmQ6DWLVT5Tj93mi0397bhhdfDo54OjkR5KqpsoY8wOfDztVzcHYXwTQgKUqLAvAepjKkX/PjywzNsuRCkp9qRj1cScaqf2n59DhTjmBia8BsOQB0KPbCNoC0L7B5o+7nSEd66eQ/oREw9AK1bEemPClSIV0f9JKqO8+XSur8m4OjqQs1ucLVfRx08eNNBvk8R0J0OPawDqHYW86FEfhnU8SQtG5ZYYQ6xa/BJEMAxNKB4Fgl/3whiWcJnGdDEuVB+g9VRxK5tgg6G42EMVknzY+tAoa075+M1fQTSQEf5dSkCehq7KKIal5JzNUNWpLgWgz7xKhQKhULRR+iNV6FQKBSKPkJvvAqFQqFQ9BHLOsebZwXlUU7ZrFAWynwOx0AJuMmEigsojVhmSO65/I60UIH38aDPb9QbQnUF+H5UpCJRjp/AkDDHEUAuK67zfEIVcq8FtGTkEc+vVtqQAy19W8FZalCQ4gvQikcYpAcp5Lyq5873ulC08oBClYUEbehEKwnExTqfZ8lF3qQHebxuxw98/gTkaV7iZf2x9etLLwe1nst4btPEuE8+z2ZCHv8eKHhNnYLc8gx3NokIFaWgzQQNswPeqoTKXCUqkc3Ns8VyMLUPLCoQSUcWUKtyfluYx81knxDk4xy2IwkXo86sn2/t0z6PXpzmjkvgy85ydS7mx8lBzt7B+ViJ0N1LuIDRudWXrIhrkeM548dddLtiOZhHcNxj57ebVHhrV/Myf24NvLXpX18hcrxDvlYjgNx5TZQaRA1QyUqh3dAK5Sp4bipAkcpCfUguTOMDuObF6CAkVLYKOGgGcsmReFZD9asSHY1EyxU3r8flYO5ZYcEVQJ4Zrh2lky2L/r11qFgmrveQC87n4boJ7UR2np/DeI8weC0L+RjCSkRhfv63U33iVSgUCoWij9Abr0KhUCgUfcSyppqDwFAQBOSEaHkI6j0OFIgKYc5cFp5GiKCdKIPWA9Pm5eUG+kKSln9dNIRLAgrwA40aC8F9A2MtoWzfhv7QSFH26gCoRo36fcjbnDbrHAPjANg/I8wPElSkAlWseEBQ3GDeneBvNqBHmWs5ETdNwJ4aoWwToToRUJptYYAxfcLvbxto3vYEpBcOcYopcZ5a7LY93ReLNpoUqGaq+n3NHKdiT4N5+txPoJVNmNqb3M8dg+o6aOQtWigCVEECqiwWtFkQoTC/p72KglNgLvDjQ9Uvg8bnIv1RIK1X+PEhDUtE1J0HEfsOmCl0uUFB1vPbrWG7VMnXF+DcgRSDxbRLLtWBoKUmAKOAHj9vC+iFKmDdoXz2MJgiQqU2//3KKI/x8NX+3B/4Rd8eVhvl508CKaMQDnsYCqofzvcY6FsXCrUkEOo3cGzR0KFnectWDOpSmEkSgmcU4VyBMURCNcpAW1oJLVxlyOMfYvoCUjAYSUN8PpSsBQnaxgLRJoRSg0BDh8KwJYD1hxkc5xLUz8R1qQdpmBAMIsxpnvoJSiJbqHKVQqFQKBQ/l9Abr0KhUCgUfcSyppopKomigsyA8GesQnUkVstKf0ZUT4KfICVU+JmcUw+ofhKBH2a1yWklUwf6LwI1nID/1inRhxYUpLCS0IhK4VoCPsKw3WJFlS1XrAaPVKjsNYI6rY7Afox5aqq5kldRxuDpGwGthNV+BYmqU4PViOgFKuKK/p9Qqd2bEqpkP/ExmnvFU5rd01CtOSWUmICOHMg87dxL+LHIhj1V1Kj66sZuweN66pBfrjjkFZvSjqiSBlo0x2r4yNORkTDNQCIvhErQKBUUcsV/rwPTOJ/ldHeAFa5A9dfB1zYSJhzoU42i+uT4/hVzoHjW9jHuiO6BAmhfVNLKS74cescGQKOiZ2sR8bFyxbkufIdTnWj8kACVi562REQG3mOVdbXh50BjQ4t9Z+AXfPpiEOjlcICfPzWQYjLgx1sG4jKM5xNQrFakEQjiZYG+jSB9YXqcEkVOOYLKbytF/7FCF66HVlQrJ/ge5pcxPK4WYl6gL3eB1dN8qCUarICsnDR0CCEOOVwrped3GMD8qOBrUMoT1d1lz78PIDVp5/l1qSgcZSU/9xaDPvEqFAqFQtFHvOEb7+OPP04f+MAHaHx8nIwx9PDDDy98luc5bdu2ja699lqq1+s0Pj5OH/nIR+jo0aNsHZOTk7RlyxZqNpvUarXoox/9KM3NzZFCoVAoFBc73vCNd35+nt7+9rfTl770pbM+a7fb9OSTT9Ldd99NTz75JD300EP0/PPP06233sqW27JlCz3zzDO0fft2euSRR+jxxx+nj3/84//3vVAoFAqFYpngDed4b7nlFrrlllvO+dng4CBt376d/e/v//7v6YYbbqDDhw/TunXr6LnnnqN///d/pz179tDGjRuJiOiLX/wive9976O/+Zu/ofHx8fMeSxzFFEcJJRVRjt+EFoMU3C9KsbuFz1E5yMGh+I8VdfYGjMurkCeLB0VbSAq5FPgoEvlVtHzBzIWF7USOOx9R7PMLKZTchytE68AG/1kHcs6BFS1Sw35btSH/nWpDtHtAnqWHziEGc+oi/4KKQZBTtwnPV6FAFRpbhx2Rlz/pc1ado2CcPuPzK1a0NFUhz2lgPmSzwlQdTNGzzMehl/Hluq/6/G8TVNKKkOf0OpATLSBf5bCVx4p8O+TBkxjUklKRb4fX7Um/73OHeO4JW1gSmEZ2CNouQnFegJwaczcSikElHFsLrUZdHi7WYuacH2shHHESPPECv60UlKZCy88zrMcIIK8bS0UwTEXG/rNKwvc9jME4vgTFsxU+eK0r+HlWGYOcKjhepaJNKAZXnhLaCiORN+1Ce56FdsbcCqUvuDaF2FZl/PgCy/OOZeTHVzrMZ/NrQhtO8AJqSiKRY0f3sRJb5qSCGtSEhGzOg+pUICYOrgK2Y8U1Blv1iLUW8bliI8g7Q9tkZcDvU5rwvHAP8tYObMqs5QnpMutSZn+O2ommp6fJGEOtVouIiHbu3EmtVmvhpktEtHnzZgqCgHbt2nXOdfR6PZqZmWF/CoVCoVAsR1zQG2+326Vt27bRbbfdRs3mGQ3TiYkJWrVqFVsuiiIaHh6miYmJc67n3nvvpcHBwYW/tWvXXshhKxQKhUJxwXDB2onyPKcPfehD5Jyj+++//6da11/8xV/QJz/5yYX3MzMztHbtWopjojgmCoXCUh3K+Ls1T4HFPf47owtUBJKqEXAcUSQo5Cq0C7TA1KAlFKmA6QoYjSraIbDdBlpLOqAYlFpufpCiAlfsxxO1+LpTOLyuCZRhVyq6+AHmGbQgnRYtBtDmYyr4GtYlVLEcrBvjUArKioASwxaKXKj19FJoNQJqxwEdLNgisrCOdg7LzXM6zM34Y4HrC0phjg1GDb3UU5MuEpQ0ATODTgG5b0GyJacto9SrINXqfhI1pal6DCmUExDLE2KfOnCcRvx8yCCOJuXfSZqo/AY0sThkISh9pXBwIxI0IyZRoBXECuWwLlCnMbaX5a8jsE+8TQhRxuJ8xHQDpo+EUTx4Y1Al8ce2ebk/Lq31PPVTb4J5CKxaeMFTgWJv0ALjSk7hG6DTg8LPvVK0uhi4yOSoiBdASocPgUJslYRWrFyctwW2adUg9RPyVEYZ+PlbgBFIafmtJQWDBwdtNyW2q4nv4JF1SEO7Ra4xKMgmpkYALVyDqR/3qhFQtlvJz8cOUO5daNkqe5xW7llDuaCfF8MFufG+dtM9dOgQ7dixY+Fpl4hobGyMjh8/zpYvioImJydpbGzsnOtL05TSND3nZwqFQqFQLCf8zKnm1266Bw4coO9973s0MjLCPt+0aRNNTU3Rvn37Fv63Y8cOstbSjTfe+LMejkKhUCgUP1d4w0+8c3Nz9OKLLy68P3jwIO3fv5+Gh4dp9erV9Nu//dv05JNP0iOPPEJlWS7kbYeHhylJErr66qvp5ptvpo997GP05S9/mfI8pzvuuIM+/OEPv6GKZiIiFzhygaNYeOEODPmn486Ir4JFUXEiIgvcTw68UABcZVrh36mCMk1l1P+oqDSEoQAoqKAQe06coshBtLzd9d+ZOeHHbUSxXKPqVXTSFSCoHgo6EujgrO0pnW5XUDVAPRvwUo2E7wONepopB3WwdgVobKGuk4CgeVqDmISyAhDGjtRuxOm1sgFVyVWgQSHekeXzoYSUQgYexe1pvu420LKt0o8vEXRkY4U/bWahUtI6rhLkoFo1gHSB6/rXVlQUO4iXAeON5tXDbLlq4sfUOQ4UmFBBiiFlgQX1UChMhajaDmAelXWoVBVKXylU8FahSrQe8TF0wLvUAsUqeVCH3rq4H5CWcKJSFc8tE+J84OvOgZbF1EoiL4FwqKtD/jxrvnXlwuvamOgeQJMRSH/EorK3gP0LYYBOeuaGWMELaa9CpH4gQWbAa7mI4RwW9G0I18ASrkV5VxgUwGkcpJ5aL0iqQfmxoplCaHh6BpWxSnvu45kL6SrIprAnxOIsYwtUWoPxCIWrFOZUOuS3O7jOK8mNtfkYAqhqPjoJqclpMcHmHJHsmlkEb/jGu3fvXnrPe96z8P613OvWrVvps5/9LH33u98lIqJf+qVfYt977LHH6N3vfjcRET3wwAN0xx130E033URBENAHP/hB+sIXvvBGh6JQKBQKxbLDG77xvvvd72a6uhKLffYahoeH6Wtf+9ob3bRCoVAoFMsey9okITSWwsBSMxKFV1Cllo8BDRRzGjSFysfqPJgIACXRGOSN+K03+UrH6rinnKqC7g6ASs2gSjGTYgxAAc++6l9PHQQaSXjS5iv9+obfAhTrIF+uh03w00DtnuSN/bYH9AxQLd1IVFtiM38bKHKg7HtCpL8CXqojl3vKShSLkwXqNGKmCyJe8/59b8bHKOghZcXpMAPHGT1ye7OcVrLzvggwIDCfiDltVhuCimKgikuxXRRGCEAQIgCxiVhUbYcRVJPWoQJ1BZ+HXZhHZQ98RoUJRxtMPfJZEOQAUYsoFnR+z48hAj2JOOTzIRjx8z8aAR/nl/n65rtAM0IVvxFjDeFyFGE6ZcxTgYmYk7aHwgwokM+PbRu4U4MV2FU+huqAn0cDcK4Pw+ua0LOJgNLEzEghvLct+RiVMXoti/jjuQFV7pRzWd0YTCaKHHyXIY1gY35tLCB1ZnJfdV8KGjuErzk4TqEQ+zBI26PPsfBzMEBRByAsk4OARiSKgjFVw8U0Fqlsh+/Y4PVp42odqspX+7nmROV4VPHHrHrcp5KmTnBq/vTJgLIiIDpA5wU1SVAoFAqFoo/QG69CoVAoFH2E3ngVCoVCoegjlnWO11BEhiKqxvz3QwH5pmLe8/emwvMYFlpTejmYEiSQu23y1oH6Wm963RiB7wijckxKBGC+btq85aSY9Ydg/mUYz4tgHs5TjBT0oGwfFI1QoJ2IKD8Fxs2noI2gI1R9IDfZg+K4oseXm58AEwFo+bFggs7cE4ioAmL8EawvmxWi/2DGHsDvwVAo6oRT/nWKuSyHbQ3sKxSC5JIBdZ0wFznGNrQlQEo8rAiz9Nh/WBnwx681yOfKPORRoTuJImidqiY8YRhCbpNafrtZyduvyja0gsBnrsuT5/Mdn4tqZH58Blo60iaPg0EzBMiZJSIXHA/5/GO6yu9HzMNAds6PqYCDE4Xi2MLbCKbHijV+3Y3RFv8Oirp1oK5CzF3Koe0uAfP1AT7Y2iq/4eG3+nbBWgsMIUIeLwdqaDmaOIhcJOZDHdSAFPIqbCH+cG2T+VpCMwXIm4aQ/89FGGzuz1U8T3LRAob5UBx3LPbJQkI6BjMXK2ozsKbAwvzKMT8bivwqtDuFFscjWqQgf5zBdnPRBhiCYlmEuekBX0MwPMbPxyT1Y6iP+M8GV8yy5YaOE3UzQ/QDOi/oE69CoVAoFH2E3ngVCoVCoegjljXVbCkmSzEVonY9afrS//o4UFuDvAS8mPFUxFyAKjyefqoh9UdEjSFPN1RqSF3wMTjgh20PDAByHnJgoak3CTRJF1p+hMiTKcFHE1qfsA2EiCg/CS0nU34l3XnpIuBpl/kZaCWZEV6eQKnZDEXefRyrdU7VRE0/1tkpKNuf4cYP1WH4HiiP1SLe+tSAVp72IFBbSIGJeEWpj1Ed2ilq4mdnALRvCWpCkWhhGRj0Gxi/2s+VE3XO62XPwRuIa4itRQmfX6bl39tBH9fp0zxevUlII8wART7Hd952/TGMQRkoaXh6jYQPapIAJQqfVRyfNzUQz28ADdep8X2qQItUYeEz0X5F4KGLakkxnHMj68W60XwC9fuz16eaHZgahK06W8ysgpYrUCgz4CcrDYcttNF0MfwiTRJX/TGrghqXTI2gL20EPTZV4WGdwURH+tWAz3go/L8ttjYyj1u+nIH5H0BbTo94/FNQngqgrdMIqjmH9aOqVYBtRqWYD0BJo183CYUr1k6EqTIxrzFTwkwzKtAGNcSvzwMp0OwNv6/1FUKpcGVInY7wgF4E+sSrUCgUCkUfoTdehUKhUCj6iOVNNZuSrCkpDgWlgGLuI1B5OcRV/4NprwRTw0rOmqfhajFfdwRi8DFQkFHJaWxb+nV3gIpFJSEiohKKnEOsvERaRFRt14Y9zREDlevanI4sgF4uoAq2M8PHaoB6bs/4bTVSTlsGJQ4KXgMVVW3xqloL1Yj5UaSuOV3UBeWcpAHrq3F6bWStp7qKeb+t+ZeA+m5zyqox7qnKgbV+fQ0haj60GpS1qn6uBEK5qt4CivsaGN8IX19e+IM7e9j/PwFfY1kxXcI65jp+u3PPCHONac+rxmB6EYhq3gjotiz1czIY83GMmkKhrAJUOHw/JD7WBlDSHZiT7ZEBtlxzFmjGDlThx3yfwsSvY+WoN4VYdZlXFGuNcWq4msCcgvJgI6RrkSnGwmNKBCU6CB7DCVSfE8yBXBgKtH28upCCSR2fDxbilYdwHQlkNS/MZfL7GyTcCzcFAwQH9KuJ/bqjglPIDuhvtCUupfkBvA3wOmd4KimANALGNSyF9zlWRoNhRQh+vNbyawdSyOg97IQilQHKHWdyKOaAA1MJNCepAfVdiO4UvMxFkNbr1fm5kCc5kTBYWAz6xKtQKBQKRR+hN16FQqFQKPoIvfEqFAqFQtFHLOscbzbXo8iGlAlbCzS4L8BtIhLOEwVWf0OqBxVTZIU79bxiSRc4/TDn+VU0IWpDj8H0MZ5zmYfcXzEH+RfIR8SxyH00fU6iHfg8Yn6aq2J1Zv1Yp077/8+J5dDJxUHZ/2xXtEjBTsXg7pFWfSB7Md+/suPHgIo6wv+dLOTTsJ2IqqLVpQatSyv862wSck2paI1YBcdpPcSYd0ZQPuC/17E+RjYXLTrQuuRCaBGp8+02r/L5MLMCWjdgqnTbfP86HZ/HKw9495hsls8v24G2L1Dmqjj+WzrGcwPa5Oql3/lKKpS5YEhJB1tJRL4Q2laiqh93/TJ+0gzBeVLJoE1ogOdr4yF/PFevAYew9aAQ1xTqczFMJIttdjwvz0zkC/hM5EADSN9CpwzlBpTCOvw7XXB96vWgHSzlueAQcvEFyHQlsWiPgaE6mGs4BiIiB/UTzI6VKVrx70Ql5FTRBqng8cJpmcA5mMVCNSr1n6XQulSIWhZUlMrAfSwsQa3PiHYc2HfWziWszWLM+YIiW2D5vhsYXxeCjM5JoeVxKCEnXkIG2UWiByyyZ/7OE/rEq1AoFApFH7Esn3hf+3XX6Zx5CghFZSI+8eb4xCuq3Ap4kslAHzWKUeyAbzsEEQnUEQ4L/kSSsydeeJKSv5bhR3EBTf8G/DULw3/hteFJNILN5h3xxNvzH3bhh1xXPJ2zJ174NWrEL0YHv2JRTMPlsE8ZHyv+CMQnXtHbTjH46ZYYIyefCH0Va7cH3rpwLFGPloiom4EoQgcqX4mPNYBSzhK0dG0pRAjgV3oOfspdeWy7EH/wzMUf1T3hz8z2o4D5WXIxEwtUjEUtavHEi7a0EVTNd7p+rrTbgiEAz+Mcnsy6ovK1Dfv02rlIRNTNePVtr+jAa9AezkUFfObPz04Pqn47UGWd8niFaIALTzTO8CeXEKkriKt84sUq/BCeigp84u3y7/SgqhmPZ1nKsUJVM1T55os+8fr5mguRC/7EC9uCkysQQu8RXLMszP9SPPHiA2tuYbuiwwKvhwU8XYeLPPEa91M+8Ybn+cTrFnvixesAPvEKb2TYbGlfR9CDiNrteer8T1eJE/eZc8G481nq5wwvv/wyrV27dqmHoVAoFAoFw5EjR2jNmjWLLrMsb7zWWjp69Cg552jdunV05MgRajab//sXL1LMzMzQ2rVrNQ4aByLSOLwGjcMZaBzO4ELHwTlHs7OzND4+TkGweBZ3WVLNQRDQmjVraGbmTPFJs9m8pCfUa9A4nIHG4Qw0DmegcTgDjcMZXMg4DA4O/u8LkRZXKRQKhULRV+iNV6FQKBSKPmJZ33jTNKXPfOYzlIo+xEsNGocz0DicgcbhDDQOZ6BxOIOfpzgsy+IqhUKhUCiWK5b1E69CoVAoFMsNeuNVKBQKhaKP0BuvQqFQKBR9hN54FQqFQqHoI/TGq1AoFApFH7Fsb7xf+tKX6PLLL6dKpUI33ngj7d69e6mHdEFx77330i//8i/TwMAArVq1in7jN36Dnn/+ebZMt9ul22+/nUZGRqjRaNAHP/hBOnbs2BKNuD+47777yBhDd91118L/LpU4vPLKK/S7v/u7NDIyQtVqla699lrau3fvwufOOfqrv/orWr16NVWrVdq8eTMdOHBgCUf8s0dZlnT33XfThg0bqFqt0pve9Cb667/+ayZUfzHG4fHHH6cPfOADND4+TsYYevjhh9nn57PPk5OTtGXLFmo2m9RqteijH/0ozc3N9XEvfnosFoc8z2nbtm107bXXUr1ep/HxcfrIRz5CR48eZetYkji4ZYgHH3zQJUni/umf/sk988wz7mMf+5hrtVru2LFjSz20C4b3vve97itf+Yp7+umn3f79+9373vc+t27dOjc3N7ewzCc+8Qm3du1a9+ijj7q9e/e6X/mVX3HvfOc7l3DUFxa7d+92l19+uXvb297m7rzzzoX/XwpxmJycdOvXr3e///u/73bt2uVeeukl9x//8R/uxRdfXFjmvvvuc4ODg+7hhx92P/rRj9ytt97qNmzY4DqdzhKO/GeLe+65x42MjLhHHnnEHTx40H3rW99yjUbD/d3f/d3CMhdjHP71X//VffrTn3YPPfSQIyL37W9/m31+Pvt88803u7e//e3uhz/8ofvBD37g3vzmN7vbbrutz3vy02GxOExNTbnNmze7b3zjG+7HP/6x27lzp7vhhhvc9ddfz9axFHFYljfeG264wd1+++0L78uydOPj4+7ee+9dwlH1F8ePH3dE5L7//e87585MsjiO3be+9a2FZZ577jlHRG7nzp1LNcwLhtnZWXfllVe67du3u1/7tV9buPFeKnHYtm2b+9Vf/dXX/dxa68bGxtznP//5hf9NTU25NE3d17/+9X4MsS94//vf7/7wD/+Q/e+3fuu33JYtW5xzl0Yc5A3nfPb52WefdUTk9uzZs7DMv/3bvzljjHvllVf6NvafJc71A0Ri9+7djojcoUOHnHNLF4dlRzVnWUb79u2jzZs3L/wvCALavHkz7dy5cwlH1l9MT08TEdHw8DAREe3bt4/yPGdxueqqq2jdunUXZVxuv/12ev/738/2l+jSicN3v/td2rhxI/3O7/wOrVq1iq677jr6x3/8x4XPDx48SBMTEywOg4ODdOONN15UcXjnO99Jjz76KL3wwgtERPSjH/2InnjiCbrllluI6NKJA+J89nnnzp3UarVo48aNC8ts3ryZgiCgXbt29X3M/cL09DQZY6jVahHR0sVh2bkTnTx5ksqypNHRUfb/0dFR+vGPf7xEo+ovrLV011130bve9S665ppriIhoYmKCkiRZmFCvYXR0lCYmJpZglBcODz74ID355JO0Z8+esz67VOLw0ksv0f3330+f/OQn6S//8i9pz5499Cd/8ieUJAlt3bp1YV/PdZ5cTHH41Kc+RTMzM3TVVVdRGIZUliXdc889tGXLFiKiSyYOiPPZ54mJCVq1ahX7PIoiGh4evmjj0u12adu2bXTbbbctuBMtVRyW3Y1XceZp7+mnn6YnnnhiqYfSdxw5coTuvPNO2r59O1UqlaUezpLBWksbN26kz33uc0REdN1119HTTz9NX/7yl2nr1q1LPLr+4Zvf/CY98MAD9LWvfY3e+ta30v79++muu+6i8fHxSyoOisWR5zl96EMfIucc3X///Us9nOVX1bxixQoKw/CsKtVjx47R2NjYEo2qf7jjjjvokUceoccee4zWrFmz8P+xsTHKsoympqbY8hdbXPbt20fHjx+nd7zjHRRFEUVRRN///vfpC1/4AkVRRKOjo5dEHFavXk1vectb2P+uvvpqOnz4MBHRwr5e7OfJn/3Zn9GnPvUp+vCHP0zXXnst/d7v/R796Z/+Kd17771EdOnEAXE++zw2NkbHjx9nnxdFQZOTkxddXF676R46dIi2b9/OvHiXKg7L7sabJAldf/319Oijjy78z1pLjz76KG3atGkJR3Zh4ZyjO+64g7797W/Tjh07aMOGDezz66+/nuI4ZnF5/vnn6fDhwxdVXG666Sb67//+b9q/f//C38aNG2nLli0Lry+FOLzrXe86q53shRdeoPXr1xMR0YYNG2hsbIzFYWZmhnbt2nVRxaHdblMQ8MtYGIZkrSWiSycOiPPZ502bNtHU1BTt27dvYZkdO3aQtZZuvPHGvo/5QuG1m+6BAwfoe9/7Ho2MjLDPlywOF6xs6wLiwQcfdGmaun/+5392zz77rPv4xz/uWq2Wm5iYWOqhXTD80R/9kRscHHT/+Z//6V599dWFv3a7vbDMJz7xCbdu3Tq3Y8cOt3fvXrdp0ya3adOmJRx1f4BVzc5dGnHYvXu3i6LI3XPPPe7AgQPugQcecLVazX31q19dWOa+++5zrVbLfec733H/9V//5X7913992bfRSGzdutVddtllC+1EDz30kFuxYoX78z//84VlLsY4zM7Ouqeeeso99dRTjojc3/7t37qnnnpqoVr3fPb55ptvdtddd53btWuXe+KJJ9yVV1657NqJFotDlmXu1ltvdWvWrHH79+9n181er7ewjqWIw7K88Trn3Be/+EW3bt06lySJu+GGG9wPf/jDpR7SBQURnfPvK1/5ysIynU7H/fEf/7EbGhpytVrN/eZv/qZ79dVXl27QfYK88V4qcfiXf/kXd80117g0Td1VV13l/uEf/oF9bq11d999txsdHXVpmrqbbrrJPf/880s02guDmZkZd+edd7p169a5SqXirrjiCvfpT3+aXVgvxjg89thj57webN261Tl3fvt86tQpd9ttt7lGo+Gazab7gz/4Azc7O7sEe/N/x2JxOHjw4OteNx977LGFdSxFHNSPV6FQKBSKPmLZ5XgVCoVCoVjO0BuvQqFQKBR9hN54FQqFQqHoI/TGq1AoFApFH6E3XoVCoVAo+gi98SoUCoVC0UfojVehUCgUij5Cb7wKhUKhUPQReuNVKBQKhaKP0BuvQqFQKBR9hN54FQqFQqHoI/4/Mxlt3TUHBakAAAAASUVORK5CYII="},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}},{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/skimage/io/_plugins/matplotlib_plugin.py:149: UserWarning: Low image data range; displaying image with stretched contrast.\n  lo, hi, cmap = _get_display_range(image)\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 2 Axes>","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 2 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"%tensorboard --logdir logs/fit","metadata":{"execution":{"iopub.status.busy":"2023-12-13T14:49:18.024249Z","iopub.execute_input":"2023-12-13T14:49:18.025277Z","iopub.status.idle":"2023-12-13T14:49:18.037654Z","shell.execute_reply.started":"2023-12-13T14:49:18.025233Z","shell.execute_reply":"2023-12-13T14:49:18.03665Z"},"trusted":true},"execution_count":49,"outputs":[{"output_type":"display_data","data":{"text/plain":"Reusing TensorBoard on port 6006 (pid 1145), started 0:00:57 ago. (Use '!kill 1145' to kill it.)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"\n      <iframe id=\"tensorboard-frame-1990a18e77fc90e2\" width=\"100%\" height=\"800\" frameborder=\"0\">\n      </iframe>\n      <script>\n        (function() {\n          const frame = document.getElementById(\"tensorboard-frame-1990a18e77fc90e2\");\n          const url = new URL(\"/\", window.location);\n          const port = 6006;\n          if (port) {\n            url.port = port;\n          }\n          frame.src = url;\n        })();\n      </script>\n    "},"metadata":{}}]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}