{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "id": "qWty393oiaBu" }, "outputs": [], "source": [ "import sys, cv2, glob, os, time\n", "import pandas as pd\n", "import numpy as np\n", "import numpy as np # linear algebra\n", "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n", "import matplotlib.pyplot as plt\n", "# Input data files are available in the \"../input/\" directory.\n", "# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n", "\n", "import os\n", "import glob\n", "import cv2\n", "from sklearn.utils import shuffle\n", "# importing all necessary libraries to run the code\n", "import re,string\n", "import numpy as np\n", "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "from nltk.corpus import stopwords\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "import numpy as np\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "from warnings import filterwarnings\n", "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report, roc_auc_score, roc_curve\n", "from tensorflow.keras.models import Sequential\n", "from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D, BatchNormalization,MaxPooling2D,Activation,GlobalAveragePooling2D\n", "from keras import models, Model\n", "from keras import layers\n", "import tensorflow as tf\n", "import os\n", "import os.path\n", "from pathlib import Path\n", "import cv2\n", "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n", "#from keras.utils.np_utils import to_categorical\n", "from sklearn.model_selection import train_test_split\n", "from keras import regularizers\n", "from keras.optimizers import RMSprop,Adam" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "id": "fz44upqpi2dL" }, "outputs": [], "source": [ "from sklearn.metrics import accuracy_score\n", "from sklearn.metrics import classification_report\n", "from sklearn.metrics import confusion_matrix" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "id": "rYSwhXgi0WLj" }, "outputs": [ { "name": "stdout", "output_type": "stream", ] } ], "source": [ "!pip install Augmentor" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "id": "VxnzIwz50WLj" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Initialised with 888 image(s) found.\n", "Output directory set to Original Images (Primary and Secondary Sources)\\Original Images S\\output." ] } ], "source": [ "import Augmentor\n", "from Augmentor import Pipeline\n", "# Create a pipeline for augmentation\n", "p = Pipeline(source_directory='Original Images (Primary and Secondary Sources)\\\\Original Images S\\\\', \n", " output_directory='output')" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Processing : 100%|█| 5000/5000 [00:51<00:00, 97.54 Sample\n" ] } ], "source": [ "#from Augmentor import Pipeline\n", "import uuid\n", "\n", "# Apply standard augmentations\n", "p.rotate(probability=0.5, max_left_rotation=10, max_right_rotation=10)\n", "p.zoom(probability=0.3, min_factor=0.7, max_factor=1.0)\n", "p.flip_left_right(probability=0.4)\n", "p.flip_top_bottom(probability=0.5)\n", "p.random_distortion(probability=0.3, grid_width=2, grid_height=2, magnitude=7)\n", "\n", "# Add additional transformations\n", "p.crop_random(probability=0.5, percentage_area=0.9)\n", "p.skew(probability=0.5, magnitude=0.3)\n", "p.random_contrast(probability=0.5, min_factor=0.7, max_factor=1.3)\n", "\n", "# Define custom save function to generate short UUID filenames\n", "def custom_filename_generator():\n", " short_uuid = str(uuid.uuid4())[:8]\n", " return f\"aug_{short_uuid}\"\n", "\n", "# Apply the custom filename generator for saving images\n", "for operation in p.augmentor_images:\n", " operation.save_function = custom_filename_generator()\n", "\n", "# Sample the images (adjust the sample size as needed)\n", "p.sample(5000)\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "id": "-36JkmwSi2iS" }, "outputs": [], "source": [ "def get_images(directory):\n", " Images = []\n", " Labels = [] # 0 for Building , 1 for forest, 2 for glacier, 3 for mountain, 4 for Sea , 5 for Street\n", "\n", " for labels in os.listdir(directory): #Main Directory where each class label is present as folder name.\n", "\n", " for image_file in os.listdir(directory+labels): #Extracting the file name of the image from Class Label folder\n", " image = cv2.imread(directory+labels+r'/'+image_file) #Reading the image (OpenCV)\n", " image = cv2.resize(image,(150,150)) #Resize the image, Some images are different sizes. (Resizing is very Important)\n", " Images.append(image)\n", " Labels.append(labels)\n", "\n", " return shuffle(Images,Labels,random_state=817328462) #Shuffle the dataset you just prepared.\n", "\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "id": "pgdaDUvU0WLk" }, "outputs": [], "source": [ "# data\n", "X_train, y_train = get_images(\"Original Images (Primary and Secondary Sources)\\\\5k\\\\\") #Extract the images from the folders.\n", "\n", "X_train = np.array(X_train) #converting the list of images to numpy array.\n", "y_train = np.array(y_train)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "colab": { "base_uri": "/" }, "id": "0gF5TePn0WLk", "outputId": "9acf0121-050c-4d48-feb3-df36b9cde5ee" }, "outputs": [ { "data": { "text/plain": [ "Counter({'Alopecia Areata': 293,\n", " 'Acral Lentiginous Melanoma': 268,\n", " 'Alopecia Totalis': 247,\n", " 'Granuloma Annulare': 183,\n", " 'Herpes Zoster': 174,\n", " 'Epidermolytic Hyperkeratosis': 172,\n", " 'Basal Cell Carcinoma': 161,\n", " 'Dariers Disease': 153,\n", " 'Arsenicosis': 151,\n", " 'Bowens Disease': 151,\n", " 'Hemangioma': 148,\n", " 'Androgenetic Alopecia': 142,\n", " 'Fordyce Spots': 134,\n", " 'Drug Eruptions': 130,\n", " 'Malignant Melanoma': 122,\n", " 'Impetigo Contagiosa': 112,\n", " 'Lichen Planus': 112,\n", " 'Oral Lichen Planus': 109,\n", " 'Discoid Lupus Erythematosus': 108,\n", " 'Ecthyma': 101,\n", " 'Hypertrophic Lichen Planus': 93,\n", " 'Nevus of Ota': 91,\n", " 'Molluscum Contagiosum': 88,\n", " 'Drug Reactions': 85,\n", " 'Livedo Reticularis': 85,\n", " 'Trichoepithelioma': 74,\n", " 'Ichthyosis': 74,\n", " 'Seborrheic Keratosis': 69,\n", " 'Lupus Vulgaris': 67,\n", " 'Systemic Lupus Erythematosus': 66,\n", " 'Psoriasis': 66,\n", " 'Chromoblastomycosis': 65,\n", " 'Mole': 61,\n", " 'Pityriasis Versicolor': 59,\n", " 'Linear Scleroderma': 57,\n", " 'Squamous cell carcinoma': 54,\n", " 'Pagets Disease': 53,\n", " 'Nevus Spilus': 52,\n", " 'Vitiligo': 51,\n", " 'Pityriasis Rosea': 51,\n", " 'Pemphigus Vulgaris': 50,\n", " 'Keratoderma': 47,\n", " 'Nevus Sebaceus': 44,\n", " 'Tinea Barbae': 39,\n", " 'Malignant Acanthosis Nigricans': 39,\n", " 'Pityriasis Lichenoides Chronica': 36,\n", " 'Tinea Pedis': 34,\n", " 'Tinea Corporis': 28,\n", " 'Striae Distensae': 28,\n", " 'Tuberculosis Verrucosa Cutis': 23,\n", " 'Tinea Faciei': 19,\n", " 'Pyogenic Granuloma': 19,\n", " 'Verruca': 16,\n", " 'Granulomatous Diseases': 13,\n", " 'Solitary Mastocytosis': 11,\n", " 'Melanoacanthoma': 11,\n", " 'Nevus': 11})" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from collections import Counter\n", "Counter(y_train)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "id": "MivrAWvw0WLl" }, "outputs": [ { "data": { "text/plain": [ "(5000,)" ] "source": [ "from sklearn.model_selection import train_test_split\n", "X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.30, random_state = 42,shuffle=True,stratify =y_train)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "id": "Y3IXgtj3jkcr" }, "outputs": [], "source": [ "n_samples = len(X_train)\n", "X_train = X_train.reshape((n_samples, 150,150,3))\n", "\n", "\n", "n_samples = len(X_test)\n", "X_test = X_test.reshape((n_samples, 150,150,3))\n", "\n", "\n", "#n_samples = len(X_val)\n", "#X_val = X_val.reshape((n_samples,128,128,3))\n", "\n", "from sklearn.preprocessing import LabelEncoder\n", "\n", "target=y_train.tolist()\n", "label_encoder = LabelEncoder()\n", "Y = np.array(label_encoder.fit_transform(y_train))\n", "y_train = pd.get_dummies(Y).values\n", "\n", "from sklearn.preprocessing import LabelEncoder\n", "\n", "target=y_test.tolist()\n", "label_encoder = LabelEncoder()\n", "Y = np.array(label_encoder.fit_transform(y_test))\n", "y_test = pd.get_dummies(Y).values\n", "\n", "\n", "#target=y_val.tolist()\n", "#label_encoder = LabelEncoder()\n", "#Y = np.array(label_encoder.fit_transform(y_val))\n", "#y_val = pd.get_dummies(Y).values" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "id": "oGbJJkwx0WLm" }, "outputs": [], "source": [ "#n_samples = len(val_images)\n", "#X_val = val_images.reshape((n_samples, 224,224,3))\n", "\n", "#from sklearn.preprocessing import LabelEncoder\n", "\n", "#target=y_val.tolist()\n", "#label_encoder = LabelEncoder()\n", "#Y = np.array(label_encoder.fit_transform(y_val))\n", "#y_val = pd.get_dummies(Y).values" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "3ErIr8ey0WLm", "outputId": "a22f3849-d566-4e2f-e37d-1e9acdce7687" }, "outputs": [ { "data": { "text/plain": [ "((3500, 150, 150, 3), (3500, 57), (1500, 150, 150, 3), (1500, 57))" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_train.shape, y_train.shape, X_test.shape,y_test.shape" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "id": "Cot_rV3hjkfK" }, "outputs": [], "source": [ "import tensorflow as tf\n", "from keras.models import Sequential\n", "from keras.layers import Dense,Flatten,Conv2D,MaxPooling2D,Dropout,BatchNormalization,Activation,MaxPool2D\n", "from keras.preprocessing.image import ImageDataGenerator\n", "from tensorflow.keras.models import Sequential\n", "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, BatchNormalization, Dropout\n", "#F1 score\n", "import keras.backend as K\n", "\n", "def f1_score(y_true, y_pred):\n", "\n", " # Count positive samples.\n", " c1 = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))\n", " c2 = K.sum(K.round(K.clip(y_pred, 0, 1)))\n", " c3 = K.sum(K.round(K.clip(y_true, 0, 1)))\n", "\n", " # If there are no true samples, fix the F1 score at 0.\n", "\n", "\n", " # How many selected items are relevant?\n", " precision = c1 / c2\n", "\n", " # How many relevant items are selected?\n", " recall = c1 / c3\n", "\n", " # Calculate f1_score\n", " f1_score = 2 * (precision * recall) / (precision + recall)\n", " return f1_score" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"model\"\n", "__________________________________________________________________________________________________\n", " Layer (type) Output Shape Param # Connected to \n", "==================================================================================================\n", " input_1 (InputLayer) [(None, 150, 150, 3 0 [] \n", " )] \n", " \n", " rescaling (Rescaling) (None, 150, 150, 3) 0 ['input_1[0][0]'] \n", " \n", " normalization (Normalization) (None, 150, 150, 3) 7 ['rescaling[0][0]'] \n", " \n", " rescaling_1 (Rescaling) (None, 150, 150, 3) 0 ['normalization[0][0]'] \n", " \n", " stem_conv_pad (ZeroPadding2D) (None, 151, 151, 3) 0 ['rescaling_1[0][0]'] \n", " \n", " stem_conv (Conv2D) (None, 75, 75, 32) 864 ['stem_conv_pad[0][0]'] \n", " \n", " stem_bn (BatchNormalization) (None, 75, 75, 32) 128 ['stem_conv[0][0]'] \n", " \n", " stem_activation (Activation) (None, 75, 75, 32) 0 ['stem_bn[0][0]'] \n", " \n", " block1a_dwconv (DepthwiseConv2 (None, 75, 75, 32) 288 ['stem_activation[0][0]'] \n", " D) \n", " \n", " block1a_bn (BatchNormalization (None, 75, 75, 32) 128 ['block1a_dwconv[0][0]'] \n", " ) \n", " \n", " block1a_activation (Activation (None, 75, 75, 32) 0 ['block1a_bn[0][0]'] \n", " ) \n", " \n", " block1a_se_squeeze (GlobalAver (None, 32) 0 ['block1a_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block1a_se_reshape (Reshape) (None, 1, 1, 32) 0 ['block1a_se_squeeze[0][0]'] \n", " \n", " block1a_se_reduce (Conv2D) (None, 1, 1, 8) 264 ['block1a_se_reshape[0][0]'] \n", " \n", " block1a_se_expand (Conv2D) (None, 1, 1, 32) 288 ['block1a_se_reduce[0][0]'] \n", " \n", " block1a_se_excite (Multiply) (None, 75, 75, 32) 0 ['block1a_activation[0][0]', \n", " 'block1a_se_expand[0][0]'] \n", " \n", " block1a_project_conv (Conv2D) (None, 75, 75, 16) 512 ['block1a_se_excite[0][0]'] \n", " \n", " block1a_project_bn (BatchNorma (None, 75, 75, 16) 64 ['block1a_project_conv[0][0]'] \n", " lization) \n", " \n", " block1b_dwconv (DepthwiseConv2 (None, 75, 75, 16) 144 ['block1a_project_bn[0][0]'] \n", " D) \n", " \n", " block1b_bn (BatchNormalization (None, 75, 75, 16) 64 ['block1b_dwconv[0][0]'] \n", " ) \n", " \n", " block1b_activation (Activation (None, 75, 75, 16) 0 ['block1b_bn[0][0]'] \n", " ) \n", " \n", " block1b_se_squeeze (GlobalAver (None, 16) 0 ['block1b_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block1b_se_reshape (Reshape) (None, 1, 1, 16) 0 ['block1b_se_squeeze[0][0]'] \n", " \n", " block1b_se_reduce (Conv2D) (None, 1, 1, 4) 68 ['block1b_se_reshape[0][0]'] \n", " \n", " block1b_se_expand (Conv2D) (None, 1, 1, 16) 80 ['block1b_se_reduce[0][0]'] \n", " \n", " block1b_se_excite (Multiply) (None, 75, 75, 16) 0 ['block1b_activation[0][0]', \n", " 'block1b_se_expand[0][0]'] \n", " \n", " block1b_project_conv (Conv2D) (None, 75, 75, 16) 256 ['block1b_se_excite[0][0]'] \n", " \n", " block1b_project_bn (BatchNorma (None, 75, 75, 16) 64 ['block1b_project_conv[0][0]'] \n", " lization) \n", " \n", " block1b_drop (Dropout) (None, 75, 75, 16) 0 ['block1b_project_bn[0][0]'] \n", " \n", " block1b_add (Add) (None, 75, 75, 16) 0 ['block1b_drop[0][0]', \n", " 'block1a_project_bn[0][0]'] \n", " \n", " block2a_expand_conv (Conv2D) (None, 75, 75, 96) 1536 ['block1b_add[0][0]'] \n", " \n", " block2a_expand_bn (BatchNormal (None, 75, 75, 96) 384 ['block2a_expand_conv[0][0]'] \n", " ization) \n", " \n", " block2a_expand_activation (Act (None, 75, 75, 96) 0 ['block2a_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block2a_dwconv_pad (ZeroPaddin (None, 77, 77, 96) 0 ['block2a_expand_activation[0][0]\n", " g2D) '] \n", " \n", " block2a_dwconv (DepthwiseConv2 (None, 38, 38, 96) 864 ['block2a_dwconv_pad[0][0]'] \n", " D) \n", " \n", " block2a_bn (BatchNormalization (None, 38, 38, 96) 384 ['block2a_dwconv[0][0]'] \n", " ) \n", " \n", " block2a_activation (Activation (None, 38, 38, 96) 0 ['block2a_bn[0][0]'] \n", " ) \n", " \n", " block2a_se_squeeze (GlobalAver (None, 96) 0 ['block2a_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block2a_se_reshape (Reshape) (None, 1, 1, 96) 0 ['block2a_se_squeeze[0][0]'] \n", " \n", " block2a_se_reduce (Conv2D) (None, 1, 1, 4) 388 ['block2a_se_reshape[0][0]'] \n", " \n", " block2a_se_expand (Conv2D) (None, 1, 1, 96) 480 ['block2a_se_reduce[0][0]'] \n", " \n", " block2a_se_excite (Multiply) (None, 38, 38, 96) 0 ['block2a_activation[0][0]', \n", " 'block2a_se_expand[0][0]'] \n", " \n", " block2a_project_conv (Conv2D) (None, 38, 38, 24) 2304 ['block2a_se_excite[0][0]'] \n", " \n", " block2a_project_bn (BatchNorma (None, 38, 38, 24) 96 ['block2a_project_conv[0][0]'] \n", " lization) \n", " \n", " block2b_expand_conv (Conv2D) (None, 38, 38, 144) 3456 ['block2a_project_bn[0][0]'] \n", " \n", " block2b_expand_bn (BatchNormal (None, 38, 38, 144) 576 ['block2b_expand_conv[0][0]'] \n", " ization) \n", " \n", " block2b_expand_activation (Act (None, 38, 38, 144) 0 ['block2b_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block2b_dwconv (DepthwiseConv2 (None, 38, 38, 144) 1296 ['block2b_expand_activation[0][0]\n", " D) '] \n", " \n", " block2b_bn (BatchNormalization (None, 38, 38, 144) 576 ['block2b_dwconv[0][0]'] \n", " ) \n", " \n", " block2b_activation (Activation (None, 38, 38, 144) 0 ['block2b_bn[0][0]'] \n", " ) \n", " \n", " block2b_se_squeeze (GlobalAver (None, 144) 0 ['block2b_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block2b_se_reshape (Reshape) (None, 1, 1, 144) 0 ['block2b_se_squeeze[0][0]'] \n", " \n", " block2b_se_reduce (Conv2D) (None, 1, 1, 6) 870 ['block2b_se_reshape[0][0]'] \n", " \n", " block2b_se_expand (Conv2D) (None, 1, 1, 144) 1008 ['block2b_se_reduce[0][0]'] \n", " \n", " block2b_se_excite (Multiply) (None, 38, 38, 144) 0 ['block2b_activation[0][0]', \n", " 'block2b_se_expand[0][0]'] \n", " \n", " block2b_project_conv (Conv2D) (None, 38, 38, 24) 3456 ['block2b_se_excite[0][0]'] \n", " \n", " block2b_project_bn (BatchNorma (None, 38, 38, 24) 96 ['block2b_project_conv[0][0]'] \n", " lization) \n", " \n", " block2b_drop (Dropout) (None, 38, 38, 24) 0 ['block2b_project_bn[0][0]'] \n", " \n", " block2b_add (Add) (None, 38, 38, 24) 0 ['block2b_drop[0][0]', \n", " 'block2a_project_bn[0][0]'] \n", " \n", " block2c_expand_conv (Conv2D) (None, 38, 38, 144) 3456 ['block2b_add[0][0]'] \n", " \n", " block2c_expand_bn (BatchNormal (None, 38, 38, 144) 576 ['block2c_expand_conv[0][0]'] \n", " ization) \n", " \n", " block2c_expand_activation (Act (None, 38, 38, 144) 0 ['block2c_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block2c_dwconv (DepthwiseConv2 (None, 38, 38, 144) 1296 ['block2c_expand_activation[0][0]\n", " D) '] \n", " \n", " block2c_bn (BatchNormalization (None, 38, 38, 144) 576 ['block2c_dwconv[0][0]'] \n", " ) \n", " \n", " block2c_activation (Activation (None, 38, 38, 144) 0 ['block2c_bn[0][0]'] \n", " ) \n", " \n", " block2c_se_squeeze (GlobalAver (None, 144) 0 ['block2c_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block2c_se_reshape (Reshape) (None, 1, 1, 144) 0 ['block2c_se_squeeze[0][0]'] \n", " \n", " block2c_se_reduce (Conv2D) (None, 1, 1, 6) 870 ['block2c_se_reshape[0][0]'] \n", " \n", " block2c_se_expand (Conv2D) (None, 1, 1, 144) 1008 ['block2c_se_reduce[0][0]'] \n", " \n", " block2c_se_excite (Multiply) (None, 38, 38, 144) 0 ['block2c_activation[0][0]', \n", " 'block2c_se_expand[0][0]'] \n", " \n", " block2c_project_conv (Conv2D) (None, 38, 38, 24) 3456 ['block2c_se_excite[0][0]'] \n", " \n", " block2c_project_bn (BatchNorma (None, 38, 38, 24) 96 ['block2c_project_conv[0][0]'] \n", " lization) \n", " \n", " block2c_drop (Dropout) (None, 38, 38, 24) 0 ['block2c_project_bn[0][0]'] \n", " \n", " block2c_add (Add) (None, 38, 38, 24) 0 ['block2c_drop[0][0]', \n", " 'block2b_add[0][0]'] \n", " \n", " block3a_expand_conv (Conv2D) (None, 38, 38, 144) 3456 ['block2c_add[0][0]'] \n", " \n", " block3a_expand_bn (BatchNormal (None, 38, 38, 144) 576 ['block3a_expand_conv[0][0]'] \n", " ization) \n", " \n", " block3a_expand_activation (Act (None, 38, 38, 144) 0 ['block3a_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block3a_dwconv_pad (ZeroPaddin (None, 41, 41, 144) 0 ['block3a_expand_activation[0][0]\n", " g2D) '] \n", " \n", " block3a_dwconv (DepthwiseConv2 (None, 19, 19, 144) 3600 ['block3a_dwconv_pad[0][0]'] \n", " D) \n", " \n", " block3a_bn (BatchNormalization (None, 19, 19, 144) 576 ['block3a_dwconv[0][0]'] \n", " ) \n", " \n", " block3a_activation (Activation (None, 19, 19, 144) 0 ['block3a_bn[0][0]'] \n", " ) \n", " \n", " block3a_se_squeeze (GlobalAver (None, 144) 0 ['block3a_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block3a_se_reshape (Reshape) (None, 1, 1, 144) 0 ['block3a_se_squeeze[0][0]'] \n", " \n", " block3a_se_reduce (Conv2D) (None, 1, 1, 6) 870 ['block3a_se_reshape[0][0]'] \n", " \n", " block3a_se_expand (Conv2D) (None, 1, 1, 144) 1008 ['block3a_se_reduce[0][0]'] \n", " \n", " block3a_se_excite (Multiply) (None, 19, 19, 144) 0 ['block3a_activation[0][0]', \n", " 'block3a_se_expand[0][0]'] \n", " \n", " block3a_project_conv (Conv2D) (None, 19, 19, 48) 6912 ['block3a_se_excite[0][0]'] \n", " \n", " block3a_project_bn (BatchNorma (None, 19, 19, 48) 192 ['block3a_project_conv[0][0]'] \n", " lization) \n", " \n", " block3b_expand_conv (Conv2D) (None, 19, 19, 288) 13824 ['block3a_project_bn[0][0]'] \n", " \n", " block3b_expand_bn (BatchNormal (None, 19, 19, 288) 1152 ['block3b_expand_conv[0][0]'] \n", " ization) \n", " \n", " block3b_expand_activation (Act (None, 19, 19, 288) 0 ['block3b_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block3b_dwconv (DepthwiseConv2 (None, 19, 19, 288) 7200 ['block3b_expand_activation[0][0]\n", " D) '] \n", " \n", " block3b_bn (BatchNormalization (None, 19, 19, 288) 1152 ['block3b_dwconv[0][0]'] \n", " ) \n", " \n", " block3b_activation (Activation (None, 19, 19, 288) 0 ['block3b_bn[0][0]'] \n", " ) \n", " \n", " block3b_se_squeeze (GlobalAver (None, 288) 0 ['block3b_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block3b_se_reshape (Reshape) (None, 1, 1, 288) 0 ['block3b_se_squeeze[0][0]'] \n", " \n", " block3b_se_reduce (Conv2D) (None, 1, 1, 12) 3468 ['block3b_se_reshape[0][0]'] \n", " \n", " block3b_se_expand (Conv2D) (None, 1, 1, 288) 3744 ['block3b_se_reduce[0][0]'] \n", " \n", " block3b_se_excite (Multiply) (None, 19, 19, 288) 0 ['block3b_activation[0][0]', \n", " 'block3b_se_expand[0][0]'] \n", " \n", " block3b_project_conv (Conv2D) (None, 19, 19, 48) 13824 ['block3b_se_excite[0][0]'] \n", " \n", " block3b_project_bn (BatchNorma (None, 19, 19, 48) 192 ['block3b_project_conv[0][0]'] \n", " lization) \n", " \n", " block3b_drop (Dropout) (None, 19, 19, 48) 0 ['block3b_project_bn[0][0]'] \n", " \n", " block3b_add (Add) (None, 19, 19, 48) 0 ['block3b_drop[0][0]', \n", " 'block3a_project_bn[0][0]'] \n", " \n", " block3c_expand_conv (Conv2D) (None, 19, 19, 288) 13824 ['block3b_add[0][0]'] \n", " \n", " block3c_expand_bn (BatchNormal (None, 19, 19, 288) 1152 ['block3c_expand_conv[0][0]'] \n", " ization) \n", " \n", " block3c_expand_activation (Act (None, 19, 19, 288) 0 ['block3c_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block3c_dwconv (DepthwiseConv2 (None, 19, 19, 288) 7200 ['block3c_expand_activation[0][0]\n", " D) '] \n", " \n", " block3c_bn (BatchNormalization (None, 19, 19, 288) 1152 ['block3c_dwconv[0][0]'] \n", " ) \n", " \n", " block3c_activation (Activation (None, 19, 19, 288) 0 ['block3c_bn[0][0]'] \n", " ) \n", " \n", " block3c_se_squeeze (GlobalAver (None, 288) 0 ['block3c_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block3c_se_reshape (Reshape) (None, 1, 1, 288) 0 ['block3c_se_squeeze[0][0]'] \n", " \n", " block3c_se_reduce (Conv2D) (None, 1, 1, 12) 3468 ['block3c_se_reshape[0][0]'] \n", " \n", " block3c_se_expand (Conv2D) (None, 1, 1, 288) 3744 ['block3c_se_reduce[0][0]'] \n", " \n", " block3c_se_excite (Multiply) (None, 19, 19, 288) 0 ['block3c_activation[0][0]', \n", " 'block3c_se_expand[0][0]'] \n", " \n", " block3c_project_conv (Conv2D) (None, 19, 19, 48) 13824 ['block3c_se_excite[0][0]'] \n", " \n", " block3c_project_bn (BatchNorma (None, 19, 19, 48) 192 ['block3c_project_conv[0][0]'] \n", " lization) \n", " \n", " block3c_drop (Dropout) (None, 19, 19, 48) 0 ['block3c_project_bn[0][0]'] \n", " \n", " block3c_add (Add) (None, 19, 19, 48) 0 ['block3c_drop[0][0]', \n", " 'block3b_add[0][0]'] \n", " \n", " block4a_expand_conv (Conv2D) (None, 19, 19, 288) 13824 ['block3c_add[0][0]'] \n", " \n", " block4a_expand_bn (BatchNormal (None, 19, 19, 288) 1152 ['block4a_expand_conv[0][0]'] \n", " ization) \n", " \n", " block4a_expand_activation (Act (None, 19, 19, 288) 0 ['block4a_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block4a_dwconv_pad (ZeroPaddin (None, 21, 21, 288) 0 ['block4a_expand_activation[0][0]\n", " g2D) '] \n", " \n", " block4a_dwconv (DepthwiseConv2 (None, 10, 10, 288) 2592 ['block4a_dwconv_pad[0][0]'] \n", " D) \n", " \n", " block4a_bn (BatchNormalization (None, 10, 10, 288) 1152 ['block4a_dwconv[0][0]'] \n", " ) \n", " \n", " block4a_activation (Activation (None, 10, 10, 288) 0 ['block4a_bn[0][0]'] \n", " ) \n", " \n", " block4a_se_squeeze (GlobalAver (None, 288) 0 ['block4a_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block4a_se_reshape (Reshape) (None, 1, 1, 288) 0 ['block4a_se_squeeze[0][0]'] \n", " \n", " block4a_se_reduce (Conv2D) (None, 1, 1, 12) 3468 ['block4a_se_reshape[0][0]'] \n", " \n", " block4a_se_expand (Conv2D) (None, 1, 1, 288) 3744 ['block4a_se_reduce[0][0]'] \n", " \n", " block4a_se_excite (Multiply) (None, 10, 10, 288) 0 ['block4a_activation[0][0]', \n", " 'block4a_se_expand[0][0]'] \n", " \n", " block4a_project_conv (Conv2D) (None, 10, 10, 88) 25344 ['block4a_se_excite[0][0]'] \n", " \n", " block4a_project_bn (BatchNorma (None, 10, 10, 88) 352 ['block4a_project_conv[0][0]'] \n", " lization) \n", " \n", " block4b_expand_conv (Conv2D) (None, 10, 10, 528) 46464 ['block4a_project_bn[0][0]'] \n", " \n", " block4b_expand_bn (BatchNormal (None, 10, 10, 528) 2112 ['block4b_expand_conv[0][0]'] \n", " ization) \n", " \n", " block4b_expand_activation (Act (None, 10, 10, 528) 0 ['block4b_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block4b_dwconv (DepthwiseConv2 (None, 10, 10, 528) 4752 ['block4b_expand_activation[0][0]\n", " D) '] \n", " \n", " block4b_bn (BatchNormalization (None, 10, 10, 528) 2112 ['block4b_dwconv[0][0]'] \n", " ) \n", " \n", " block4b_activation (Activation (None, 10, 10, 528) 0 ['block4b_bn[0][0]'] \n", " ) \n", " \n", " block4b_se_squeeze (GlobalAver (None, 528) 0 ['block4b_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block4b_se_reshape (Reshape) (None, 1, 1, 528) 0 ['block4b_se_squeeze[0][0]'] \n", " \n", " block4b_se_reduce (Conv2D) (None, 1, 1, 22) 11638 ['block4b_se_reshape[0][0]'] \n", " \n", " block4b_se_expand (Conv2D) (None, 1, 1, 528) 12144 ['block4b_se_reduce[0][0]'] \n", " \n", " block4b_se_excite (Multiply) (None, 10, 10, 528) 0 ['block4b_activation[0][0]', \n", " 'block4b_se_expand[0][0]'] \n", " \n", " block4b_project_conv (Conv2D) (None, 10, 10, 88) 46464 ['block4b_se_excite[0][0]'] \n", " \n", " block4b_project_bn (BatchNorma (None, 10, 10, 88) 352 ['block4b_project_conv[0][0]'] \n", " lization) \n", " \n", " block4b_drop (Dropout) (None, 10, 10, 88) 0 ['block4b_project_bn[0][0]'] \n", " \n", " block4b_add (Add) (None, 10, 10, 88) 0 ['block4b_drop[0][0]', \n", " 'block4a_project_bn[0][0]'] \n", " \n", " block4c_expand_conv (Conv2D) (None, 10, 10, 528) 46464 ['block4b_add[0][0]'] \n", " \n", " block4c_expand_bn (BatchNormal (None, 10, 10, 528) 2112 ['block4c_expand_conv[0][0]'] \n", " ization) \n", " \n", " block4c_expand_activation (Act (None, 10, 10, 528) 0 ['block4c_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block4c_dwconv (DepthwiseConv2 (None, 10, 10, 528) 4752 ['block4c_expand_activation[0][0]\n", " D) '] \n", " \n", " block4c_bn (BatchNormalization (None, 10, 10, 528) 2112 ['block4c_dwconv[0][0]'] \n", " ) \n", " \n", " block4c_activation (Activation (None, 10, 10, 528) 0 ['block4c_bn[0][0]'] \n", " ) \n", " \n", " block4c_se_squeeze (GlobalAver (None, 528) 0 ['block4c_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block4c_se_reshape (Reshape) (None, 1, 1, 528) 0 ['block4c_se_squeeze[0][0]'] \n", " \n", " block4c_se_reduce (Conv2D) (None, 1, 1, 22) 11638 ['block4c_se_reshape[0][0]'] \n", " \n", " block4c_se_expand (Conv2D) (None, 1, 1, 528) 12144 ['block4c_se_reduce[0][0]'] \n", " \n", " block4c_se_excite (Multiply) (None, 10, 10, 528) 0 ['block4c_activation[0][0]', \n", " 'block4c_se_expand[0][0]'] \n", " \n", " block4c_project_conv (Conv2D) (None, 10, 10, 88) 46464 ['block4c_se_excite[0][0]'] \n", " \n", " block4c_project_bn (BatchNorma (None, 10, 10, 88) 352 ['block4c_project_conv[0][0]'] \n", " lization) \n", " \n", " block4c_drop (Dropout) (None, 10, 10, 88) 0 ['block4c_project_bn[0][0]'] \n", " \n", " block4c_add (Add) (None, 10, 10, 88) 0 ['block4c_drop[0][0]', \n", " 'block4b_add[0][0]'] \n", " \n", " block4d_expand_conv (Conv2D) (None, 10, 10, 528) 46464 ['block4c_add[0][0]'] \n", " \n", " block4d_expand_bn (BatchNormal (None, 10, 10, 528) 2112 ['block4d_expand_conv[0][0]'] \n", " ization) \n", " \n", " block4d_expand_activation (Act (None, 10, 10, 528) 0 ['block4d_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block4d_dwconv (DepthwiseConv2 (None, 10, 10, 528) 4752 ['block4d_expand_activation[0][0]\n", " D) '] \n", " \n", " block4d_bn (BatchNormalization (None, 10, 10, 528) 2112 ['block4d_dwconv[0][0]'] \n", " ) \n", " \n", " block4d_activation (Activation (None, 10, 10, 528) 0 ['block4d_bn[0][0]'] \n", " ) \n", " \n", " block4d_se_squeeze (GlobalAver (None, 528) 0 ['block4d_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block4d_se_reshape (Reshape) (None, 1, 1, 528) 0 ['block4d_se_squeeze[0][0]'] \n", " \n", " block4d_se_reduce (Conv2D) (None, 1, 1, 22) 11638 ['block4d_se_reshape[0][0]'] \n", " \n", " block4d_se_expand (Conv2D) (None, 1, 1, 528) 12144 ['block4d_se_reduce[0][0]'] \n", " \n", " block4d_se_excite (Multiply) (None, 10, 10, 528) 0 ['block4d_activation[0][0]', \n", " 'block4d_se_expand[0][0]'] \n", " \n", " block4d_project_conv (Conv2D) (None, 10, 10, 88) 46464 ['block4d_se_excite[0][0]'] \n", " \n", " block4d_project_bn (BatchNorma (None, 10, 10, 88) 352 ['block4d_project_conv[0][0]'] \n", " lization) \n", " \n", " block4d_drop (Dropout) (None, 10, 10, 88) 0 ['block4d_project_bn[0][0]'] \n", " \n", " block4d_add (Add) (None, 10, 10, 88) 0 ['block4d_drop[0][0]', \n", " 'block4c_add[0][0]'] \n", " \n", " block5a_expand_conv (Conv2D) (None, 10, 10, 528) 46464 ['block4d_add[0][0]'] \n", " \n", " block5a_expand_bn (BatchNormal (None, 10, 10, 528) 2112 ['block5a_expand_conv[0][0]'] \n", " ization) \n", " \n", " block5a_expand_activation (Act (None, 10, 10, 528) 0 ['block5a_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block5a_dwconv (DepthwiseConv2 (None, 10, 10, 528) 13200 ['block5a_expand_activation[0][0]\n", " D) '] \n", " \n", " block5a_bn (BatchNormalization (None, 10, 10, 528) 2112 ['block5a_dwconv[0][0]'] \n", " ) \n", " \n", " block5a_activation (Activation (None, 10, 10, 528) 0 ['block5a_bn[0][0]'] \n", " ) \n", " \n", " block5a_se_squeeze (GlobalAver (None, 528) 0 ['block5a_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block5a_se_reshape (Reshape) (None, 1, 1, 528) 0 ['block5a_se_squeeze[0][0]'] \n", " \n", " block5a_se_reduce (Conv2D) (None, 1, 1, 22) 11638 ['block5a_se_reshape[0][0]'] \n", " \n", " block5a_se_expand (Conv2D) (None, 1, 1, 528) 12144 ['block5a_se_reduce[0][0]'] \n", " \n", " block5a_se_excite (Multiply) (None, 10, 10, 528) 0 ['block5a_activation[0][0]', \n", " 'block5a_se_expand[0][0]'] \n", " \n", " block5a_project_conv (Conv2D) (None, 10, 10, 120) 63360 ['block5a_se_excite[0][0]'] \n", " \n", " block5a_project_bn (BatchNorma (None, 10, 10, 120) 480 ['block5a_project_conv[0][0]'] \n", " lization) \n", " \n", " block5b_expand_conv (Conv2D) (None, 10, 10, 720) 86400 ['block5a_project_bn[0][0]'] \n", " \n", " block5b_expand_bn (BatchNormal (None, 10, 10, 720) 2880 ['block5b_expand_conv[0][0]'] \n", " ization) \n", " \n", " block5b_expand_activation (Act (None, 10, 10, 720) 0 ['block5b_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block5b_dwconv (DepthwiseConv2 (None, 10, 10, 720) 18000 ['block5b_expand_activation[0][0]\n", " D) '] \n", " \n", " block5b_bn (BatchNormalization (None, 10, 10, 720) 2880 ['block5b_dwconv[0][0]'] \n", " ) \n", " \n", " block5b_activation (Activation (None, 10, 10, 720) 0 ['block5b_bn[0][0]'] \n", " ) \n", " \n", " block5b_se_squeeze (GlobalAver (None, 720) 0 ['block5b_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block5b_se_reshape (Reshape) (None, 1, 1, 720) 0 ['block5b_se_squeeze[0][0]'] \n", " \n", " block5b_se_reduce (Conv2D) (None, 1, 1, 30) 21630 ['block5b_se_reshape[0][0]'] \n", " \n", " block5b_se_expand (Conv2D) (None, 1, 1, 720) 22320 ['block5b_se_reduce[0][0]'] \n", " \n", " block5b_se_excite (Multiply) (None, 10, 10, 720) 0 ['block5b_activation[0][0]', \n", " 'block5b_se_expand[0][0]'] \n", " \n", " block5b_project_conv (Conv2D) (None, 10, 10, 120) 86400 ['block5b_se_excite[0][0]'] \n", " \n", " block5b_project_bn (BatchNorma (None, 10, 10, 120) 480 ['block5b_project_conv[0][0]'] \n", " lization) \n", " \n", " block5b_drop (Dropout) (None, 10, 10, 120) 0 ['block5b_project_bn[0][0]'] \n", " \n", " block5b_add (Add) (None, 10, 10, 120) 0 ['block5b_drop[0][0]', \n", " 'block5a_project_bn[0][0]'] \n", " \n", " block5c_expand_conv (Conv2D) (None, 10, 10, 720) 86400 ['block5b_add[0][0]'] \n", " \n", " block5c_expand_bn (BatchNormal (None, 10, 10, 720) 2880 ['block5c_expand_conv[0][0]'] \n", " ization) \n", " \n", " block5c_expand_activation (Act (None, 10, 10, 720) 0 ['block5c_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block5c_dwconv (DepthwiseConv2 (None, 10, 10, 720) 18000 ['block5c_expand_activation[0][0]\n", " D) '] \n", " \n", " block5c_bn (BatchNormalization (None, 10, 10, 720) 2880 ['block5c_dwconv[0][0]'] \n", " ) \n", " \n", " block5c_activation (Activation (None, 10, 10, 720) 0 ['block5c_bn[0][0]'] \n", " ) \n", " \n", " block5c_se_squeeze (GlobalAver (None, 720) 0 ['block5c_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block5c_se_reshape (Reshape) (None, 1, 1, 720) 0 ['block5c_se_squeeze[0][0]'] \n", " \n", " block5c_se_reduce (Conv2D) (None, 1, 1, 30) 21630 ['block5c_se_reshape[0][0]'] \n", " \n", " block5c_se_expand (Conv2D) (None, 1, 1, 720) 22320 ['block5c_se_reduce[0][0]'] \n", " \n", " block5c_se_excite (Multiply) (None, 10, 10, 720) 0 ['block5c_activation[0][0]', \n", " 'block5c_se_expand[0][0]'] \n", " \n", " block5c_project_conv (Conv2D) (None, 10, 10, 120) 86400 ['block5c_se_excite[0][0]'] \n", " \n", " block5c_project_bn (BatchNorma (None, 10, 10, 120) 480 ['block5c_project_conv[0][0]'] \n", " lization) \n", " \n", " block5c_drop (Dropout) (None, 10, 10, 120) 0 ['block5c_project_bn[0][0]'] \n", " \n", " block5c_add (Add) (None, 10, 10, 120) 0 ['block5c_drop[0][0]', \n", " 'block5b_add[0][0]'] \n", " \n", " block5d_expand_conv (Conv2D) (None, 10, 10, 720) 86400 ['block5c_add[0][0]'] \n", " \n", " block5d_expand_bn (BatchNormal (None, 10, 10, 720) 2880 ['block5d_expand_conv[0][0]'] \n", " ization) \n", " \n", " block5d_expand_activation (Act (None, 10, 10, 720) 0 ['block5d_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block5d_dwconv (DepthwiseConv2 (None, 10, 10, 720) 18000 ['block5d_expand_activation[0][0]\n", " D) '] \n", " \n", " block5d_bn (BatchNormalization (None, 10, 10, 720) 2880 ['block5d_dwconv[0][0]'] \n", " ) \n", " \n", " block5d_activation (Activation (None, 10, 10, 720) 0 ['block5d_bn[0][0]'] \n", " ) \n", " \n", " block5d_se_squeeze (GlobalAver (None, 720) 0 ['block5d_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block5d_se_reshape (Reshape) (None, 1, 1, 720) 0 ['block5d_se_squeeze[0][0]'] \n", " \n", " block5d_se_reduce (Conv2D) (None, 1, 1, 30) 21630 ['block5d_se_reshape[0][0]'] \n", " \n", " block5d_se_expand (Conv2D) (None, 1, 1, 720) 22320 ['block5d_se_reduce[0][0]'] \n", " \n", " block5d_se_excite (Multiply) (None, 10, 10, 720) 0 ['block5d_activation[0][0]', \n", " 'block5d_se_expand[0][0]'] \n", " \n", " block5d_project_conv (Conv2D) (None, 10, 10, 120) 86400 ['block5d_se_excite[0][0]'] \n", " \n", " block5d_project_bn (BatchNorma (None, 10, 10, 120) 480 ['block5d_project_conv[0][0]'] \n", " lization) \n", " \n", " block5d_drop (Dropout) (None, 10, 10, 120) 0 ['block5d_project_bn[0][0]'] \n", " \n", " block5d_add (Add) (None, 10, 10, 120) 0 ['block5d_drop[0][0]', \n", " 'block5c_add[0][0]'] \n", " \n", " block6a_expand_conv (Conv2D) (None, 10, 10, 720) 86400 ['block5d_add[0][0]'] \n", " \n", " block6a_expand_bn (BatchNormal (None, 10, 10, 720) 2880 ['block6a_expand_conv[0][0]'] \n", " ization) \n", " \n", " block6a_expand_activation (Act (None, 10, 10, 720) 0 ['block6a_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block6a_dwconv_pad (ZeroPaddin (None, 13, 13, 720) 0 ['block6a_expand_activation[0][0]\n", " g2D) '] \n", " \n", " block6a_dwconv (DepthwiseConv2 (None, 5, 5, 720) 18000 ['block6a_dwconv_pad[0][0]'] \n", " D) \n", " \n", " block6a_bn (BatchNormalization (None, 5, 5, 720) 2880 ['block6a_dwconv[0][0]'] \n", " ) \n", " \n", " block6a_activation (Activation (None, 5, 5, 720) 0 ['block6a_bn[0][0]'] \n", " ) \n", " \n", " block6a_se_squeeze (GlobalAver (None, 720) 0 ['block6a_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block6a_se_reshape (Reshape) (None, 1, 1, 720) 0 ['block6a_se_squeeze[0][0]'] \n", " \n", " block6a_se_reduce (Conv2D) (None, 1, 1, 30) 21630 ['block6a_se_reshape[0][0]'] \n", " \n", " block6a_se_expand (Conv2D) (None, 1, 1, 720) 22320 ['block6a_se_reduce[0][0]'] \n", " \n", " block6a_se_excite (Multiply) (None, 5, 5, 720) 0 ['block6a_activation[0][0]', \n", " 'block6a_se_expand[0][0]'] \n", " \n", " block6a_project_conv (Conv2D) (None, 5, 5, 208) 149760 ['block6a_se_excite[0][0]'] \n", " \n", " block6a_project_bn (BatchNorma (None, 5, 5, 208) 832 ['block6a_project_conv[0][0]'] \n", " lization) \n", " \n", " block6b_expand_conv (Conv2D) (None, 5, 5, 1248) 259584 ['block6a_project_bn[0][0]'] \n", " \n", " block6b_expand_bn (BatchNormal (None, 5, 5, 1248) 4992 ['block6b_expand_conv[0][0]'] \n", " ization) \n", " \n", " block6b_expand_activation (Act (None, 5, 5, 1248) 0 ['block6b_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block6b_dwconv (DepthwiseConv2 (None, 5, 5, 1248) 31200 ['block6b_expand_activation[0][0]\n", " D) '] \n", " \n", " block6b_bn (BatchNormalization (None, 5, 5, 1248) 4992 ['block6b_dwconv[0][0]'] \n", " ) \n", " \n", " block6b_activation (Activation (None, 5, 5, 1248) 0 ['block6b_bn[0][0]'] \n", " ) \n", " \n", " block6b_se_squeeze (GlobalAver (None, 1248) 0 ['block6b_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block6b_se_reshape (Reshape) (None, 1, 1, 1248) 0 ['block6b_se_squeeze[0][0]'] \n", " \n", " block6b_se_reduce (Conv2D) (None, 1, 1, 52) 64948 ['block6b_se_reshape[0][0]'] \n", " \n", " block6b_se_expand (Conv2D) (None, 1, 1, 1248) 66144 ['block6b_se_reduce[0][0]'] \n", " \n", " block6b_se_excite (Multiply) (None, 5, 5, 1248) 0 ['block6b_activation[0][0]', \n", " 'block6b_se_expand[0][0]'] \n", " \n", " block6b_project_conv (Conv2D) (None, 5, 5, 208) 259584 ['block6b_se_excite[0][0]'] \n", " \n", " block6b_project_bn (BatchNorma (None, 5, 5, 208) 832 ['block6b_project_conv[0][0]'] \n", " lization) \n", " \n", " block6b_drop (Dropout) (None, 5, 5, 208) 0 ['block6b_project_bn[0][0]'] \n", " \n", " block6b_add (Add) (None, 5, 5, 208) 0 ['block6b_drop[0][0]', \n", " 'block6a_project_bn[0][0]'] \n", " \n", " block6c_expand_conv (Conv2D) (None, 5, 5, 1248) 259584 ['block6b_add[0][0]'] \n", " \n", " block6c_expand_bn (BatchNormal (None, 5, 5, 1248) 4992 ['block6c_expand_conv[0][0]'] \n", " ization) \n", " \n", " block6c_expand_activation (Act (None, 5, 5, 1248) 0 ['block6c_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block6c_dwconv (DepthwiseConv2 (None, 5, 5, 1248) 31200 ['block6c_expand_activation[0][0]\n", " D) '] \n", " \n", " block6c_bn (BatchNormalization (None, 5, 5, 1248) 4992 ['block6c_dwconv[0][0]'] \n", " ) \n", " \n", " block6c_activation (Activation (None, 5, 5, 1248) 0 ['block6c_bn[0][0]'] \n", " ) \n", " \n", " block6c_se_squeeze (GlobalAver (None, 1248) 0 ['block6c_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block6c_se_reshape (Reshape) (None, 1, 1, 1248) 0 ['block6c_se_squeeze[0][0]'] \n", " \n", " block6c_se_reduce (Conv2D) (None, 1, 1, 52) 64948 ['block6c_se_reshape[0][0]'] \n", " \n", " block6c_se_expand (Conv2D) (None, 1, 1, 1248) 66144 ['block6c_se_reduce[0][0]'] \n", " \n", " block6c_se_excite (Multiply) (None, 5, 5, 1248) 0 ['block6c_activation[0][0]', \n", " 'block6c_se_expand[0][0]'] \n", " \n", " block6c_project_conv (Conv2D) (None, 5, 5, 208) 259584 ['block6c_se_excite[0][0]'] \n", " \n", " block6c_project_bn (BatchNorma (None, 5, 5, 208) 832 ['block6c_project_conv[0][0]'] \n", " lization) \n", " \n", " block6c_drop (Dropout) (None, 5, 5, 208) 0 ['block6c_project_bn[0][0]'] \n", " \n", " block6c_add (Add) (None, 5, 5, 208) 0 ['block6c_drop[0][0]', \n", " 'block6b_add[0][0]'] \n", " \n", " block6d_expand_conv (Conv2D) (None, 5, 5, 1248) 259584 ['block6c_add[0][0]'] \n", " \n", " block6d_expand_bn (BatchNormal (None, 5, 5, 1248) 4992 ['block6d_expand_conv[0][0]'] \n", " ization) \n", " \n", " block6d_expand_activation (Act (None, 5, 5, 1248) 0 ['block6d_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block6d_dwconv (DepthwiseConv2 (None, 5, 5, 1248) 31200 ['block6d_expand_activation[0][0]\n", " D) '] \n", " \n", " block6d_bn (BatchNormalization (None, 5, 5, 1248) 4992 ['block6d_dwconv[0][0]'] \n", " ) \n", " \n", " block6d_activation (Activation (None, 5, 5, 1248) 0 ['block6d_bn[0][0]'] \n", " ) \n", " \n", " block6d_se_squeeze (GlobalAver (None, 1248) 0 ['block6d_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block6d_se_reshape (Reshape) (None, 1, 1, 1248) 0 ['block6d_se_squeeze[0][0]'] \n", " \n", " block6d_se_reduce (Conv2D) (None, 1, 1, 52) 64948 ['block6d_se_reshape[0][0]'] \n", " \n", " block6d_se_expand (Conv2D) (None, 1, 1, 1248) 66144 ['block6d_se_reduce[0][0]'] \n", " \n", " block6d_se_excite (Multiply) (None, 5, 5, 1248) 0 ['block6d_activation[0][0]', \n", " 'block6d_se_expand[0][0]'] \n", " \n", " block6d_project_conv (Conv2D) (None, 5, 5, 208) 259584 ['block6d_se_excite[0][0]'] \n", " \n", " block6d_project_bn (BatchNorma (None, 5, 5, 208) 832 ['block6d_project_conv[0][0]'] \n", " lization) \n", " \n", " block6d_drop (Dropout) (None, 5, 5, 208) 0 ['block6d_project_bn[0][0]'] \n", " \n", " block6d_add (Add) (None, 5, 5, 208) 0 ['block6d_drop[0][0]', \n", " 'block6c_add[0][0]'] \n", " \n", " block6e_expand_conv (Conv2D) (None, 5, 5, 1248) 259584 ['block6d_add[0][0]'] \n", " \n", " block6e_expand_bn (BatchNormal (None, 5, 5, 1248) 4992 ['block6e_expand_conv[0][0]'] \n", " ization) \n", " \n", " block6e_expand_activation (Act (None, 5, 5, 1248) 0 ['block6e_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block6e_dwconv (DepthwiseConv2 (None, 5, 5, 1248) 31200 ['block6e_expand_activation[0][0]\n", " D) '] \n", " \n", " block6e_bn (BatchNormalization (None, 5, 5, 1248) 4992 ['block6e_dwconv[0][0]'] \n", " ) \n", " \n", " block6e_activation (Activation (None, 5, 5, 1248) 0 ['block6e_bn[0][0]'] \n", " ) \n", " \n", " block6e_se_squeeze (GlobalAver (None, 1248) 0 ['block6e_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block6e_se_reshape (Reshape) (None, 1, 1, 1248) 0 ['block6e_se_squeeze[0][0]'] \n", " \n", " block6e_se_reduce (Conv2D) (None, 1, 1, 52) 64948 ['block6e_se_reshape[0][0]'] \n", " \n", " block6e_se_expand (Conv2D) (None, 1, 1, 1248) 66144 ['block6e_se_reduce[0][0]'] \n", " \n", " block6e_se_excite (Multiply) (None, 5, 5, 1248) 0 ['block6e_activation[0][0]', \n", " 'block6e_se_expand[0][0]'] \n", " \n", " block6e_project_conv (Conv2D) (None, 5, 5, 208) 259584 ['block6e_se_excite[0][0]'] \n", " \n", " block6e_project_bn (BatchNorma (None, 5, 5, 208) 832 ['block6e_project_conv[0][0]'] \n", " lization) \n", " \n", " block6e_drop (Dropout) (None, 5, 5, 208) 0 ['block6e_project_bn[0][0]'] \n", " \n", " block6e_add (Add) (None, 5, 5, 208) 0 ['block6e_drop[0][0]', \n", " 'block6d_add[0][0]'] \n", " \n", " block7a_expand_conv (Conv2D) (None, 5, 5, 1248) 259584 ['block6e_add[0][0]'] \n", " \n", " block7a_expand_bn (BatchNormal (None, 5, 5, 1248) 4992 ['block7a_expand_conv[0][0]'] \n", " ization) \n", " \n", " block7a_expand_activation (Act (None, 5, 5, 1248) 0 ['block7a_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block7a_dwconv (DepthwiseConv2 (None, 5, 5, 1248) 11232 ['block7a_expand_activation[0][0]\n", " D) '] \n", " \n", " block7a_bn (BatchNormalization (None, 5, 5, 1248) 4992 ['block7a_dwconv[0][0]'] \n", " ) \n", " \n", " block7a_activation (Activation (None, 5, 5, 1248) 0 ['block7a_bn[0][0]'] \n", " ) \n", " \n", " block7a_se_squeeze (GlobalAver (None, 1248) 0 ['block7a_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block7a_se_reshape (Reshape) (None, 1, 1, 1248) 0 ['block7a_se_squeeze[0][0]'] \n", " \n", " block7a_se_reduce (Conv2D) (None, 1, 1, 52) 64948 ['block7a_se_reshape[0][0]'] \n", " \n", " block7a_se_expand (Conv2D) (None, 1, 1, 1248) 66144 ['block7a_se_reduce[0][0]'] \n", " \n", " block7a_se_excite (Multiply) (None, 5, 5, 1248) 0 ['block7a_activation[0][0]', \n", " 'block7a_se_expand[0][0]'] \n", " \n", " block7a_project_conv (Conv2D) (None, 5, 5, 352) 439296 ['block7a_se_excite[0][0]'] \n", " \n", " block7a_project_bn (BatchNorma (None, 5, 5, 352) 1408 ['block7a_project_conv[0][0]'] \n", " lization) \n", " \n", " block7b_expand_conv (Conv2D) (None, 5, 5, 2112) 743424 ['block7a_project_bn[0][0]'] \n", " \n", " block7b_expand_bn (BatchNormal (None, 5, 5, 2112) 8448 ['block7b_expand_conv[0][0]'] \n", " ization) \n", " \n", " block7b_expand_activation (Act (None, 5, 5, 2112) 0 ['block7b_expand_bn[0][0]'] \n", " ivation) \n", " \n", " block7b_dwconv (DepthwiseConv2 (None, 5, 5, 2112) 19008 ['block7b_expand_activation[0][0]\n", " D) '] \n", " \n", " block7b_bn (BatchNormalization (None, 5, 5, 2112) 8448 ['block7b_dwconv[0][0]'] \n", " ) \n", " \n", " block7b_activation (Activation (None, 5, 5, 2112) 0 ['block7b_bn[0][0]'] \n", " ) \n", " \n", " block7b_se_squeeze (GlobalAver (None, 2112) 0 ['block7b_activation[0][0]'] \n", " agePooling2D) \n", " \n", " block7b_se_reshape (Reshape) (None, 1, 1, 2112) 0 ['block7b_se_squeeze[0][0]'] \n", " \n", " block7b_se_reduce (Conv2D) (None, 1, 1, 88) 185944 ['block7b_se_reshape[0][0]'] \n", " \n", " block7b_se_expand (Conv2D) (None, 1, 1, 2112) 187968 ['block7b_se_reduce[0][0]'] \n", " \n", " block7b_se_excite (Multiply) (None, 5, 5, 2112) 0 ['block7b_activation[0][0]', \n", " 'block7b_se_expand[0][0]'] \n", " \n", " block7b_project_conv (Conv2D) (None, 5, 5, 352) 743424 ['block7b_se_excite[0][0]'] \n", " \n", " block7b_project_bn (BatchNorma (None, 5, 5, 352) 1408 ['block7b_project_conv[0][0]'] \n", " lization) \n", " \n", " block7b_drop (Dropout) (None, 5, 5, 352) 0 ['block7b_project_bn[0][0]'] \n", " \n", " block7b_add (Add) (None, 5, 5, 352) 0 ['block7b_drop[0][0]', \n", " 'block7a_project_bn[0][0]'] \n", " \n", " top_conv (Conv2D) (None, 5, 5, 1408) 495616 ['block7b_add[0][0]'] \n", " \n", " top_bn (BatchNormalization) (None, 5, 5, 1408) 5632 ['top_conv[0][0]'] \n", " \n", " top_activation (Activation) (None, 5, 5, 1408) 0 ['top_bn[0][0]'] \n", " \n", " global_average_pooling2d (Glob (None, 1408) 0 ['top_activation[0][0]'] \n", " alAveragePooling2D) \n", " \n", " dense (Dense) (None, 176) 247984 ['global_average_pooling2d[0][0]'\n", " ] \n", " \n", " dense_1 (Dense) (None, 1408) 249216 ['dense[0][0]'] \n", " \n", " multiply (Multiply) (None, 5, 5, 1408) 0 ['top_activation[0][0]', \n", " 'dense_1[0][0]'] \n", " \n", " conv2d_1 (Conv2D) (None, 5, 5, 48) 67632 ['multiply[0][0]'] \n", " \n", " max_pooling2d (MaxPooling2D) (None, 5, 5, 1408) 0 ['multiply[0][0]'] \n", " \n", " conv2d (Conv2D) (None, 5, 5, 32) 45088 ['multiply[0][0]'] \n", " \n", " conv2d_2 (Conv2D) (None, 5, 5, 64) 27712 ['conv2d_1[0][0]'] \n", " \n", " conv2d_3 (Conv2D) (None, 5, 5, 16) 22544 ['max_pooling2d[0][0]'] \n", " \n", " concatenate (Concatenate) (None, 5, 5, 112) 0 ['conv2d[0][0]', \n", " 'conv2d_2[0][0]', \n", " 'conv2d_3[0][0]'] \n", " \n", " global_average_pooling2d_1 (Gl (None, 112) 0 ['concatenate[0][0]'] \n", " obalAveragePooling2D) \n", " \n", " dense_2 (Dense) (None, 64) 7232 ['global_average_pooling2d_1[0][0\n", " ]'] \n", " \n", " dropout (Dropout) (None, 64) 0 ['dense_2[0][0]'] \n", " \n", " dense_3 (Dense) (None, 57) 3705 ['dropout[0][0]'] \n", " \n", "==================================================================================================\n", "Total params: 8,439,682\n", "Trainable params: 3,498,465\n", "Non-trainable params: 4,941,217\n", "__________________________________________________________________________________________________\n" ] } ], "source": [ "from tensorflow.keras.applications import EfficientNetB2\n", "from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, concatenate, Dense, Dropout, GlobalAveragePooling2D, Flatten, Add, Multiply\n", "from tensorflow.keras.models import Model\n", "import tensorflow.keras.backend as K\n", "\n", "# Function for the Inception module\n", "def inception_module(x, filters):\n", " # 1x1 convolution\n", " path1 = Conv2D(filters[0], (1, 1), activation='relu', padding='same')(x)\n", " # 1x1 followed by 3x3\n", " path2 = Conv2D(filters[1], (1, 1), activation='relu', padding='same')(x)\n", " path2 = Conv2D(filters[2], (3, 3), activation='relu', padding='same')(path2)\n", " # Max pooling followed by 1x1\n", " path3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')(x)\n", " path3 = Conv2D(filters[3], (1, 1), activation='relu', padding='same')(path3)\n", " return concatenate([path1, path2, path3])\n", "\n", "# Attention Layer\n", "def attention_module(x):\n", " attention = GlobalAveragePooling2D()(x)\n", " attention = Dense(K.int_shape(x)[-1] // 8, activation='relu')(attention)\n", " attention = Dense(K.int_shape(x)[-1], activation='sigmoid')(attention)\n", " return Multiply()([x, attention])\n", "\n", "# Input Layer\n", "input_layer = Input(shape=(150, 150, 3))\n", "\n", "# Pretrained EfficientNet-B2 Backbone\n", "base_model = EfficientNetB2(weights='imagenet', include_top=False, input_tensor=input_layer)\n", "for layer in base_model.layers[:-20]: # Freeze most EfficientNet layers\n", " layer.trainable = False\n", "\n", "x = base_model.output\n", "\n", "# Apply Attention Layer after the EfficientNet feature map\n", "x = attention_module(x)\n", "\n", "# Custom Inception Block\n", "x = inception_module(x, [32, 48, 64, 16])\n", "\n", "# Global Average Pooling\n", "x = GlobalAveragePooling2D()(x)\n", "\n", "# Fully Connected Layers\n", "x = Dense(64, activation='relu')(x)\n", "x = Dropout(0.5)(x)\n", "output = Dense(57, activation='softmax')(x) # Adjust number of classes as needed\n", "\n", "# Final Model\n", "model = Model(inputs=input_layer, outputs=output)\n", "\n", "# Compile the Model\n", "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n", "\n", "# Model Summary (optional)\n", "model.summary()\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/100\n", "55/55 [==============================] - 28s 224ms/step - loss: 3.4742 - accuracy: 0.1571 - val_loss: 2.4631 - val_accuracy: 0.4160\n", "Epoch 2/100\n", "55/55 [==============================] - 7s 132ms/step - loss: 2.2203 - accuracy: 0.4529 - val_loss: 1.4557 - val_accuracy: 0.6540\n", "Epoch 3/100\n", "55/55 [==============================] - 7s 133ms/step - loss: 1.4542 - accuracy: 0.6246 - val_loss: 1.0577 - val_accuracy: 0.7367\n", "Epoch 4/100\n", "55/55 [==============================] - 7s 133ms/step - loss: 0.9449 - accuracy: 0.7529 - val_loss: 0.7411 - val_accuracy: 0.8293\n", "Epoch 5/100\n", "55/55 [==============================] - 7s 133ms/step - loss: 0.6935 - accuracy: 0.8174 - val_loss: 0.6116 - val_accuracy: 0.8527\n", "Epoch 6/100\n", "55/55 [==============================] - 7s 133ms/step - loss: 0.5277 - accuracy: 0.8549 - val_loss: 0.5627 - val_accuracy: 0.8700\n", "Epoch 7/100\n", "55/55 [==============================] - 7s 134ms/step - loss: 0.4178 - accuracy: 0.8871 - val_loss: 0.4902 - val_accuracy: 0.8960\n", "Epoch 8/100\n", "55/55 [==============================] - 7s 134ms/step - loss: 0.3174 - accuracy: 0.9183 - val_loss: 0.4124 - val_accuracy: 0.9093\n", "Epoch 9/100\n", "55/55 [==============================] - 7s 135ms/step - loss: 0.2794 - accuracy: 0.9237 - val_loss: 0.3971 - val_accuracy: 0.9167\n", "Epoch 10/100\n", "55/55 [==============================] - 7s 135ms/step - loss: 0.2308 - accuracy: 0.9426 - val_loss: 0.3702 - val_accuracy: 0.9267\n", "Epoch 11/100\n", "55/55 [==============================] - 7s 134ms/step - loss: 0.2476 - accuracy: 0.9306 - val_loss: 0.4888 - val_accuracy: 0.9173\n", "Epoch 12/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.1991 - accuracy: 0.9463 - val_loss: 0.3825 - val_accuracy: 0.9187\n", "Epoch 13/100\n", "55/55 [==============================] - 8s 148ms/step - loss: 0.1605 - accuracy: 0.9546 - val_loss: 0.3082 - val_accuracy: 0.9253\n", "Epoch 14/100\n", "55/55 [==============================] - 8s 144ms/step - loss: 0.1728 - accuracy: 0.9586 - val_loss: 0.3840 - val_accuracy: 0.9340\n", "Epoch 15/100\n", "55/55 [==============================] - 8s 144ms/step - loss: 0.1402 - accuracy: 0.9631 - val_loss: 0.4314 - val_accuracy: 0.9213\n", "Epoch 16/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.1934 - accuracy: 0.9563 - val_loss: 0.4704 - val_accuracy: 0.9067\n", "Epoch 17/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.1637 - accuracy: 0.9626 - val_loss: 0.5324 - val_accuracy: 0.9067\n", "Epoch 18/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.1550 - accuracy: 0.9589 - val_loss: 0.4495 - val_accuracy: 0.9227\n", "Epoch 19/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.1162 - accuracy: 0.9694 - val_loss: 0.4788 - val_accuracy: 0.9233\n", "Epoch 20/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.1079 - accuracy: 0.9700 - val_loss: 0.3941 - val_accuracy: 0.9313\n", "Epoch 21/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.0837 - accuracy: 0.9763 - val_loss: 0.4232 - val_accuracy: 0.9273\n", "Epoch 22/100\n", "55/55 [==============================] - 8s 143ms/step - loss: 0.1038 - accuracy: 0.9729 - val_loss: 0.4535 - val_accuracy: 0.9227\n", "Epoch 23/100\n", "55/55 [==============================] - 8s 147ms/step - loss: 0.0720 - accuracy: 0.9831 - val_loss: 0.3519 - val_accuracy: 0.9387\n", "Epoch 24/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0730 - accuracy: 0.9840 - val_loss: 0.3447 - val_accuracy: 0.9373\n", "Epoch 25/100\n", "55/55 [==============================] - 8s 147ms/step - loss: 0.0704 - accuracy: 0.9820 - val_loss: 0.3520 - val_accuracy: 0.9367\n", "Epoch 26/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.0858 - accuracy: 0.9780 - val_loss: 0.3168 - val_accuracy: 0.9447\n", "Epoch 27/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.0814 - accuracy: 0.9783 - val_loss: 0.3654 - val_accuracy: 0.9353\n", "Epoch 28/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.1088 - accuracy: 0.9766 - val_loss: 0.3850 - val_accuracy: 0.9327\n", "Epoch 29/100\n", "55/55 [==============================] - 8s 144ms/step - loss: 0.0862 - accuracy: 0.9774 - val_loss: 0.3512 - val_accuracy: 0.9433\n", "Epoch 30/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0864 - accuracy: 0.9786 - val_loss: 0.3812 - val_accuracy: 0.9327\n", "Epoch 31/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.1070 - accuracy: 0.9740 - val_loss: 0.4265 - val_accuracy: 0.9260\n", "Epoch 32/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.1112 - accuracy: 0.9800 - val_loss: 0.4568 - val_accuracy: 0.9227\n", "Epoch 33/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0561 - accuracy: 0.9883 - val_loss: 0.4046 - val_accuracy: 0.9273\n", "Epoch 34/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0495 - accuracy: 0.9871 - val_loss: 0.4028 - val_accuracy: 0.9373\n", "Epoch 35/100\n", "55/55 [==============================] - 7s 137ms/step - loss: 0.0559 - accuracy: 0.9857 - val_loss: 0.3919 - val_accuracy: 0.9360\n", "Epoch 36/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0477 - accuracy: 0.9883 - val_loss: 0.3398 - val_accuracy: 0.9507\n", "Epoch 37/100\n", "55/55 [==============================] - 7s 137ms/step - loss: 0.0351 - accuracy: 0.9911 - val_loss: 0.3660 - val_accuracy: 0.9493\n", "Epoch 38/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0738 - accuracy: 0.9831 - val_loss: 0.3566 - val_accuracy: 0.9433\n", "Epoch 39/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0758 - accuracy: 0.9849 - val_loss: 0.3146 - val_accuracy: 0.9433\n", "Epoch 40/100\n", "55/55 [==============================] - 8s 143ms/step - loss: 0.0597 - accuracy: 0.9854 - val_loss: 0.3296 - val_accuracy: 0.9460\n", "Epoch 41/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0400 - accuracy: 0.9894 - val_loss: 0.2783 - val_accuracy: 0.9547\n", "Epoch 42/100\n", "55/55 [==============================] - 8s 137ms/step - loss: 0.0558 - accuracy: 0.9886 - val_loss: 0.3182 - val_accuracy: 0.9447\n", "Epoch 43/100\n", "55/55 [==============================] - 8s 137ms/step - loss: 0.0919 - accuracy: 0.9820 - val_loss: 0.3752 - val_accuracy: 0.9273\n", "Epoch 44/100\n", "55/55 [==============================] - 7s 137ms/step - loss: 0.0878 - accuracy: 0.9817 - val_loss: 0.3818 - val_accuracy: 0.9340\n", "Epoch 45/100\n", "55/55 [==============================] - 7s 137ms/step - loss: 0.0829 - accuracy: 0.9817 - val_loss: 0.4093 - val_accuracy: 0.9313\n", "Epoch 46/100\n", "55/55 [==============================] - 8s 137ms/step - loss: 0.0825 - accuracy: 0.9809 - val_loss: 0.4110 - val_accuracy: 0.9333\n", "Epoch 47/100\n", "55/55 [==============================] - 8s 137ms/step - loss: 0.0701 - accuracy: 0.9837 - val_loss: 0.4390 - val_accuracy: 0.9287\n", "Epoch 48/100\n", "55/55 [==============================] - 8s 137ms/step - loss: 0.0720 - accuracy: 0.9823 - val_loss: 0.4098 - val_accuracy: 0.9400\n", "Epoch 49/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.0372 - accuracy: 0.9911 - val_loss: 0.3869 - val_accuracy: 0.9373\n", "Epoch 50/100\n", "55/55 [==============================] - 8s 146ms/step - loss: 0.0759 - accuracy: 0.9820 - val_loss: 0.4825 - val_accuracy: 0.9333\n", "Epoch 51/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0596 - accuracy: 0.9831 - val_loss: 0.3705 - val_accuracy: 0.9387\n", "Epoch 52/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0850 - accuracy: 0.9840 - val_loss: 0.4160 - val_accuracy: 0.9313\n", "Epoch 53/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0457 - accuracy: 0.9871 - val_loss: 0.3954 - val_accuracy: 0.9373\n", "Epoch 54/100\n", "55/55 [==============================] - 8s 145ms/step - loss: 0.0796 - accuracy: 0.9857 - val_loss: 0.3621 - val_accuracy: 0.9380\n", "Epoch 55/100\n", "55/55 [==============================] - 8s 150ms/step - loss: 0.0738 - accuracy: 0.9831 - val_loss: 0.3940 - val_accuracy: 0.9320\n", "Epoch 56/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0546 - accuracy: 0.9871 - val_loss: 0.4141 - val_accuracy: 0.9347\n", "Epoch 57/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0624 - accuracy: 0.9843 - val_loss: 0.4354 - val_accuracy: 0.9293\n", "Epoch 58/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0625 - accuracy: 0.9880 - val_loss: 0.3647 - val_accuracy: 0.9393\n", "Epoch 59/100\n", "55/55 [==============================] - 8s 143ms/step - loss: 0.0541 - accuracy: 0.9869 - val_loss: 0.4219 - val_accuracy: 0.9293\n", "Epoch 60/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0598 - accuracy: 0.9854 - val_loss: 0.4396 - val_accuracy: 0.9380\n", "Epoch 61/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0474 - accuracy: 0.9886 - val_loss: 0.4071 - val_accuracy: 0.9360\n", "Epoch 62/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0527 - accuracy: 0.9909 - val_loss: 0.4208 - val_accuracy: 0.9347\n", "Epoch 63/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0510 - accuracy: 0.9874 - val_loss: 0.3558 - val_accuracy: 0.9400\n", "Epoch 64/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.0341 - accuracy: 0.9920 - val_loss: 0.3769 - val_accuracy: 0.9433\n", "Epoch 65/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.0284 - accuracy: 0.9923 - val_loss: 0.3935 - val_accuracy: 0.9393\n", "Epoch 66/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.0326 - accuracy: 0.9920 - val_loss: 0.4383 - val_accuracy: 0.9360\n", "Epoch 67/100\n", "55/55 [==============================] - 8s 138ms/step - loss: 0.0297 - accuracy: 0.9920 - val_loss: 0.4025 - val_accuracy: 0.9427\n", "Epoch 68/100\n", "55/55 [==============================] - 8s 142ms/step - loss: 0.0333 - accuracy: 0.9900 - val_loss: 0.4225 - val_accuracy: 0.9407\n", "Epoch 69/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0194 - accuracy: 0.9946 - val_loss: 0.3996 - val_accuracy: 0.9360\n", "Epoch 70/100\n", "55/55 [==============================] - 8s 143ms/step - loss: 0.0253 - accuracy: 0.9923 - val_loss: 0.3572 - val_accuracy: 0.9453\n", "Epoch 71/100\n", "55/55 [==============================] - 8s 142ms/step - loss: 0.0212 - accuracy: 0.9954 - val_loss: 0.3911 - val_accuracy: 0.9427\n", "Epoch 72/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0400 - accuracy: 0.9911 - val_loss: 0.4170 - val_accuracy: 0.9367\n", "Epoch 73/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0754 - accuracy: 0.9809 - val_loss: 0.5475 - val_accuracy: 0.9253\n", "Epoch 74/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0589 - accuracy: 0.9866 - val_loss: 0.4175 - val_accuracy: 0.9400\n", "Epoch 75/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0457 - accuracy: 0.9886 - val_loss: 0.4911 - val_accuracy: 0.9293\n", "Epoch 76/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0685 - accuracy: 0.9877 - val_loss: 0.5789 - val_accuracy: 0.9260\n", "Epoch 77/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.1021 - accuracy: 0.9789 - val_loss: 0.5933 - val_accuracy: 0.9273\n", "Epoch 78/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0667 - accuracy: 0.9869 - val_loss: 0.4928 - val_accuracy: 0.9420\n", "Epoch 79/100\n", "55/55 [==============================] - 8s 139ms/step - loss: 0.0428 - accuracy: 0.9886 - val_loss: 0.4286 - val_accuracy: 0.9440\n", "Epoch 80/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0323 - accuracy: 0.9926 - val_loss: 0.3747 - val_accuracy: 0.9493\n", "Epoch 81/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0264 - accuracy: 0.9931 - val_loss: 0.3829 - val_accuracy: 0.9500\n", "Epoch 82/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0179 - accuracy: 0.9937 - val_loss: 0.4603 - val_accuracy: 0.9447\n", "Epoch 83/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0575 - accuracy: 0.9874 - val_loss: 0.5784 - val_accuracy: 0.9347\n", "Epoch 84/100\n", "55/55 [==============================] - 8s 148ms/step - loss: 0.0572 - accuracy: 0.9877 - val_loss: 0.3911 - val_accuracy: 0.9393\n", "Epoch 85/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0394 - accuracy: 0.9917 - val_loss: 0.5265 - val_accuracy: 0.9267\n", "Epoch 86/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0418 - accuracy: 0.9906 - val_loss: 0.4432 - val_accuracy: 0.9360\n", "Epoch 87/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0716 - accuracy: 0.9857 - val_loss: 0.5681 - val_accuracy: 0.9213\n", "Epoch 88/100\n", "55/55 [==============================] - 8s 149ms/step - loss: 0.0381 - accuracy: 0.9909 - val_loss: 0.3961 - val_accuracy: 0.9453\n", "Epoch 89/100\n", "55/55 [==============================] - 8s 150ms/step - loss: 0.0319 - accuracy: 0.9917 - val_loss: 0.4388 - val_accuracy: 0.9473\n", "Epoch 90/100\n", "55/55 [==============================] - 8s 149ms/step - loss: 0.0656 - accuracy: 0.9849 - val_loss: 0.4923 - val_accuracy: 0.9260\n", "Epoch 91/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0708 - accuracy: 0.9840 - val_loss: 0.4813 - val_accuracy: 0.9267\n", "Epoch 92/100\n", "55/55 [==============================] - 8s 141ms/step - loss: 0.0563 - accuracy: 0.9883 - val_loss: 0.3747 - val_accuracy: 0.9407\n", "Epoch 93/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0558 - accuracy: 0.9889 - val_loss: 0.3798 - val_accuracy: 0.9400\n", "Epoch 94/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0366 - accuracy: 0.9914 - val_loss: 0.5211 - val_accuracy: 0.9293\n", "Epoch 95/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0530 - accuracy: 0.9863 - val_loss: 0.3665 - val_accuracy: 0.9440\n", "Epoch 96/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0321 - accuracy: 0.9914 - val_loss: 0.3982 - val_accuracy: 0.9433\n", "Epoch 97/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0510 - accuracy: 0.9894 - val_loss: 0.6117 - val_accuracy: 0.9267\n", "Epoch 98/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0527 - accuracy: 0.9894 - val_loss: 0.4230 - val_accuracy: 0.9327\n", "Epoch 99/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0645 - accuracy: 0.9871 - val_loss: 0.4123 - val_accuracy: 0.9307\n", "Epoch 100/100\n", "55/55 [==============================] - 8s 140ms/step - loss: 0.0447 - accuracy: 0.9900 - val_loss: 0.4148 - val_accuracy: 0.9407\n" ] } ], "source": [ "hist = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=100, batch_size=64, verbose=1)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 14, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 329 }, "id": "Sozc1DC-jcCt", "outputId": "f07be3ef-949b-430f-d948-e24c7782d4e1" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "47/47 [==============================] - 5s 43ms/step\n", " precision recall f1-score support\n", "\n", " 0 0.9753 0.9875 0.9814 80\n", " 1 0.9775 0.9886 0.9831 88\n", " 2 0.9610 1.0000 0.9801 74\n", " 3 1.0000 1.0000 1.0000 43\n", " 4 0.9778 0.9778 0.9778 45\n", " 5 0.8571 1.0000 0.9231 48\n", " 6 0.8431 0.9556 0.8958 45\n", " 7 1.0000 0.8500 0.9189 20\n", " 8 0.9783 0.9783 0.9783 46\n", " 9 0.8387 0.8125 0.8254 32\n", " 10 0.9211 0.8974 0.9091 39\n", " 11 0.9167 0.8462 0.8800 26\n", " 12 0.9655 0.9333 0.9492 30\n", " 13 0.9796 0.9231 0.9505 52\n", " 14 0.9524 1.0000 0.9756 40\n", " 15 0.8125 0.9455 0.8739 55\n", " 16 1.0000 1.0000 1.0000 4\n", " 17 0.9778 1.0000 0.9888 44\n", " 18 0.9455 1.0000 0.9720 52\n", " 19 0.9655 1.0000 0.9825 28\n", " 20 0.9167 1.0000 0.9565 22\n", " 21 0.9643 0.7941 0.8710 34\n", " 22 1.0000 0.9286 0.9630 14\n", " 23 0.9118 0.9118 0.9118 34\n", " 24 0.7727 1.0000 0.8718 17\n", " 25 0.9583 0.8846 0.9200 26\n", " 26 1.0000 0.9000 0.9474 20\n", " 27 1.0000 1.0000 1.0000 12\n", " 28 0.8974 0.9459 0.9211 37\n", " 29 1.0000 1.0000 1.0000 3\n", " 30 1.0000 0.8333 0.9091 18\n", " 31 0.8846 0.8846 0.8846 26\n", " 32 1.0000 1.0000 1.0000 3\n", " 33 1.0000 1.0000 1.0000 13\n", " 34 1.0000 1.0000 1.0000 16\n", " 35 0.9310 1.0000 0.9643 27\n", " 36 0.9429 1.0000 0.9706 33\n", " 37 0.9286 0.8125 0.8667 16\n", " 38 0.9286 0.8667 0.8966 15\n", " 39 1.0000 0.5455 0.7059 11\n", " 40 0.9333 0.9333 0.9333 15\n", " 41 0.9474 1.0000 0.9730 18\n", " 42 0.9048 0.9500 0.9268 20\n", " 43 1.0000 0.6667 0.8000 6\n", " 44 0.9545 1.0000 0.9767 21\n", " 45 1.0000 1.0000 1.0000 3\n", " 46 1.0000 0.7500 0.8571 16\n", " 47 1.0000 1.0000 1.0000 8\n", " 48 0.9412 0.8000 0.8649 20\n", " 49 1.0000 0.6667 0.8000 12\n", " 50 1.0000 0.7500 0.8571 8\n", " 51 1.0000 0.3333 0.5000 6\n", " 52 1.0000 1.0000 1.0000 10\n", " 53 1.0000 1.0000 1.0000 22\n", " 54 0.7778 1.0000 0.8750 7\n", " 55 1.0000 1.0000 1.0000 5\n", " 56 1.0000 0.9333 0.9655 15\n", "\n", " accuracy 0.9407 1500\n", " macro avg 0.9534 0.9156 0.9269 1500\n", "weighted avg 0.9443 0.9407 0.9391 1500\n", "\n", "[[79 0 1 ... 0 0 0]\n", " [ 0 87 1 ... 0 0 0]\n", " [ 0 0 74 ... 0 0 0]\n", " ...\n", " [ 0 0 0 ... 7 0 0]\n", " [ 0 0 0 ... 0 5 0]\n", " [ 0 0 1 ... 0 0 14]]\n" ] }, { "data": { "text/plain": [ "
" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" }, { "data": { "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "predict=model.predict(X_test)\n", "classes=np.argmax(predict,axis=1)\n", "rounded_labels=np.argmax(y_test, axis=1)\n", "print(classification_report(rounded_labels,classes,digits=4))\n", "cnf_matrix=confusion_matrix(rounded_labels,classes)\n", "print(cnf_matrix)\n", "plt.figure(figsize=(12, 8))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['Solarize_Light2', '_classic_test_patch', '_mpl-gallery', '_mpl-gallery-nogrid', 'bmh', 'classic', 'dark_background', 'fast', 'fivethirtyeight', 'ggplot', 'grayscale', 'seaborn-v0_8', 'seaborn-v0_8-bright', 'seaborn-v0_8-colorblind', 'seaborn-v0_8-dark', 'seaborn-v0_8-dark-palette', 'seaborn-v0_8-darkgrid', 'seaborn-v0_8-deep', 'seaborn-v0_8-muted', 'seaborn-v0_8-notebook', 'seaborn-v0_8-paper', 'seaborn-v0_8-pastel', 'seaborn-v0_8-poster', 'seaborn-v0_8-talk', 'seaborn-v0_8-ticks', 'seaborn-v0_8-white', 'seaborn-v0_8-whitegrid', 'tableau-colorblind10']\n" ] } ], "source": [ "import matplotlib.pyplot as plt\n", "print(plt.style.available)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAxYAAAHqCAYAAACZcdjsAAAAP3RFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMS5wb3N0MSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8kixA/AAAACXBIWXMAAA9hAAAPYQGoP6dpAACtF0lEQVR4nOzdeXgTVdsG8HuS7nSBQktZyg4tSwuIoiiIC+6gAi4gCKLip4iK+Kq4UUAU3HHHVzY3EISKu6gIiIAvKlQqlLJDEQqFQlso3ZLz/REznDRLM22WTnL/rqsX7WQmOSe5mcwzM2dGEUIIEBERERER1YHB3w0gIiIiIiL9Y2FBRERERER1xsKCiIiIiIjqjIUFERERERHVGQsLIiIiIiKqMxYWRERERERUZywsiIiIiIiozlhYEBERERFRnbGwICIiIiKiOmNhQUQUYO644w4oigJFUTBlyhR/N4eCyJw5c9TsDRgwoNbPU1VVpT6Poig4ePCgB1tJRN7CwoKIfGrBggU2GwzWn7CwMLRo0QJDhgzB6tWr/d3MoLJv3z6Hn0n1H1mbNm1sHlu/fr3N4/LnnJSU5NV2OWsjAOzduxcGg8FmnhUrVjh8PXmj2PqzZcsWu/m++OILu/l+/fVX9fGnn35and6hQwebZVu2bGm3bEhICBo3bow+ffpg5syZKC0tdev9qb7xrSgKJk6caDdfRUUFkpKSbOa7++673XoNIiItWFgQUb1QWVmJQ4cO4fPPP8ell16KN998099NIg2eeuopfzfBoQ8++ABCCJtpCxYscHv5t956y27aG2+8Uddm2TCZTCgsLMRvv/2GJ554AldddRXMZnOtnmv+/Pk4ffq0zbTFixfjyJEjnmgqEZFLLCyIyK/Wrl2LtWvXYuHChejUqZM6/dFHH8XRo0drXP7UqVPebF5QeuONN9TPRf5xZfXq1fjxxx892o5mzZrZtaFHjx7q49dcc43LNgoh8OGHH9o97/Lly1FUVORWGz755BOcOHFC/Xvr1q34+eefa9ehasaOHYu1a9fip59+wujRo9Xpv/76K3777bdaPefJkyfx8ccf20xjkU5EvsLCgoj8qm/fvujbty+GDx+O2bNnq9PLy8vV02vk02ouueQS/P7777jiiisQGxuL5ORkdZmSkhI8++yzOOeccxATE4Pw8HC0a9cOY8eOxc6dO21ed/Xq1epztmnTBgcOHMBtt92Gxo0bIyoqChdffDHWrVtn196Kigq8/vrr6NOnD+Li4hAWFobk5GTcdttt+PPPP+3m//jjj9GvXz80atRIPeUlLS0Nd9xxh93GY2lpKV588UX07t0bsbGxCA8PR8eOHTFx4kQUFBTYPXdBQQHuuusuNGnSBA0aNMAll1yCDRs2aPsAHEhLS1M/F/mnJlqOWmzcuBHDhw9HcnIywsLC0KhRIwwYMABffvmlOk94eLhdG+Li4tTHExMTXbbxl19+wd69ewEArVq1wmWXXQYAKCsrw+LFi122LyoqCkajEaWlpZg7d6463Xq0IjY21u2+OtOqVSv07dsXl19+OWbNmmXz2KFDhzQ/n7VN8lGWDRs24Pfff7d53BGz2Yx58+ahf//+iI+PR1hYGJo1a4bBgwdj1apVdvNXVVVh6tSpaN26NSIiIpCeno6PPvqoxjYuWrQIV1xxBZo0aYKwsDA0b94ct912G/7++2+t3SWi+kgQEfnQ/PnzBQD1R7Zp0yabxxYvXmy3TIsWLURkZKT6d1xcnBBCiMOHD4uOHTvaLC//REVFiR9//FF9rVWrVqmPNWzYUDRv3txumbCwMLF69Wp1mVOnTokLLrjA6WuEhISIDz74QJ1/3rx5TucFIGbMmKHOW1BQILp16+Z03hYtWog9e/bYtKVLly5284WHh9tMz8jIqPEz2bt3r81zrFq1qsZlWrdurc4vvyeZmZl2n1nTpk1tln377beFwWBw2tcnnnjC6ev2799fnW/06NEu23jHHXeo806aNMmmTX369LGb//3337d5v4cMGSIAiLZt2wqTySQKCwtFVFSUACAeeughmzavXbtWfZ6nnnpKnd6+fXub12jRooX62LPPPiuEEKK8vFy8++676nRFUURubq7LvgkhRGVlpU0bHnzwQbvPcNiwYQKAaNasmbjlllvUx++66y6b5xk0aJDTz0NRFDFz5kyb177tttscztuzZ0/198svv1yd32QyiVtvvdXpa0RERIhvvvnGad/y8vJqfD+IyP94xIKI6oWDBw9i8uTJNtPk016s/vnnH8THx+P999/HDz/8gGnTpgEAxo0bpx6VaNq0KebNm4fly5ere7FLS0sxYsQIu/PPAcvpI3FxcViyZAkWL16snpJVUVGBe+65Rz1H/5lnnlGPMkRHR+P111/H119/jRtvvBGAZS/uPffcg7y8PADAsmXL1NeYMmUKVq5cic8//xyvvvoqrr76akRGRqqP33///epe2x49emDRokX47rvvMHToULXf8ukyL7/8MrZt2wYACAsLw8yZM/H1119j4MCB6vTauvTSS+0GBVv76MjIkSORmpqqvkeuxgds3boVDzzwAMxmMwwGA5566in88MMPeO+999CoUSMAwIwZM+p8utHp06exdOlS9e8RI0ZgyJAh6nu+YcMG7Nixw+VzjB8/HoBlAPg333yDOXPmoLS0FAaDAePGjatT+wDLe6UoCsLDw3HfffcBsHyWL7zwgs1pge667rrr0LZtWwCW058OHTqkZvCee+5BaGiow+XeeOMNfPXVVwCA0NBQTJ8+Hd9++y3GjBkDwHJK2RNPPIFNmzYBAFauXImFCxeqy//f//0fvv32WzzxxBPIyspy+Bpvv/22epQoISEB7777Ln788Uc8+eSTACxHkUaOHOn2KWpEVE/5u7IhouBS/YiFsx95b7S8jKIo4q+//rJ5zsLCQps94MuWLVMfKygosDnCsWTJEiGE7RELAOLvv/9Wl/njjz9sHtu0aZMwm82icePG6rRXXnlFnb+8vNzmiMeLL74ohLDdq7to0SJRUFDg8D05ceKEMBqN6rwLFy4Ua9euFWvXrhWrVq0SoaGh6mPbt28XQgiboxsPP/yw+lwVFRU2e8Vrc8TC0c8NN9xgs4x8xOLdd98VS5YsUf/+6KOPnB6xeOSRR9TpAwYMUPu5du1aceedd6qPDRs2zGFb3T1i8cEHH6jzde/eXZ0u77V/8sknbZapfsRCfp8vu+wy0aZNGwFADBw40G6Pem2OWDj6iYmJEdOmTXP1camqt+HHH38UL730kgAgjEajGD16tAAgQkNDxaFDh8SIESMcHrFIS0tzmCUhhM0RiAcffFAIIcS9996rTjvvvPNs5rce5UG1Ixbdu3dXp0+aNMnmc09PT1cfmzNnjsO+8YgFkT7wiAUR1SsJCQmYMmUK3n//fYePd+jQAenp6TbTdu7cabOXXD7XvkmTJkhJSVH/3r59u91zNmrUCF27dlX/7tWrl83RhJ07d6KgoADHjx93+BphYWHo3bu33WuMHTsWRqMRADB8+HAkJCQgPj4el1xyCV5++WX1sqI7duyAyWRSl7/tttvQr18/9OvXD5deeikqKyvVx6xHNXbt2qVO69Onj/p7aGioTVtqw9Hg7RkzZrhc5qabbkLPnj0BWI7OVFVVOZxPPpry008/qf3s168f5s2bpz5W13Pu5Ss/jRgxwuHvH330UY1XX7Ietfj555+xb98+AMADDzxQp7ZZWQdvr1q1Ci+//DLCw8NRUlKCyZMn24w30uKuu+5CVFQUTCYTPvjgAwCWz6ZZs2ZOl5H/T1Qfp3LRRRfZzecse9Xnl+Xk5Ki/z5w50+Zzly/py7EWRPoW4u8GEFFws17JJzQ0FAkJCWjbtq3D+xFYudpAqm8uueQS/PHHH1iwYAH++OMP5Obm4tixY1izZg3WrFmDdevW4fPPP9f0nL64CpZ18LYWiqJg+vTpuO6667B7926bIqE26tLP/fv329wL5bHHHsNjjz1mN19eXh5WrlyJK664wulzjRw5EpMmTcLJkycBACkpKbjiiitsCsHasg7eBixZycnJUQeKL1y4EPfee6/m52zUqBFGjBhhU5h7qhDyBV7ljUjfeMSCiPzKejWf888/H+3atXNZVABw+HjHjh1hMJxdnclXczp+/Dhyc3PVv61jAWQnTpyw2aO6adMmnDlzRv27Q4cOSEhIQOPGjR2+RmVlpXrlHfk1hBDo0aMHZs2ahV9//RUFBQXYtWsXoqOjAVhutFZaWopOnTqpRzYAIDc3F0IIu59Tp06p4yzat2+vzi9fXaqqqsqmLb507bXXqhvKzq5O1blzZ/X34cOHO+ynEKJOe64//PBDu3tXOGPdq+9MgwYNcOedd6p/jx8/vsaM1pbc5sLCwlo/j1xI9OrVy+6oQnXy/4nqV0KTb3xonc9Z9qrP7+w15s6d6/AzLysrw7vvvuuyrURUv/GIBRHpXqNGjXDDDTeoe//vv/9+FBUVIT4+Hq+88opaJCQkJODaa691+Bw333wzMjIyAMBmEHnHjh3Rs2dPKIqCUaNG4bXXXgMAZGRkIDQ0FO3atcPcuXPxzz//ALBcInXYsGEAgIcffhi7d+/GlVdeieTkZMTFxWHTpk3qKVBCCJSXl6NRo0YYMmQIPvvsMwCWDfRHH30UHTp0wMmTJ7F//3788ssv2L59u3o6yk033YStW7cCsAyMTUpKQteuXbFgwQIcPHiwTu9ndnY2QkLsvx569uyJBg0auFz2ueeeQ//+/Z0+fscdd2DWrFkwm81YtGgRYmJiMHDgQISHh+PgwYPYtm0bvvzySzz55JO44447atV+uVi4++670atXL5vHDx48iOeeew4A8Pnnn6O4uNjlpVgnTJiAmJgYALAZQF9XBw4cwK+//oqqqir8+eefNvef6NKlS62fNy0tDW+88QaOHz+Oyy+/vMb577jjDjzyyCMALJeqbdKkCXr27ImlS5eqA7at+Qcs2XvvvfcAWC4bPG7cOFx//fX49ddfnR6Bu+uuu/DQQw8BsLyf+fn5OPfcc1FRUYEDBw7gjz/+wJdffomsrCy0bNmy1n0nIj/z7ZAOIgp2ri43684y/fv3dziPO5eb/eGHH9T55cHb8fHxNoORrT+hoaFi5cqV6jJaLzf7f//3fy4H6l5//fXqvEePHnV5uVkAonXr1ur8JSUlIjU11W4eo9Eo2rdv7/HB2wDE5s2b1WWqD96WXXnllTbLVb/c7FtvveXycrMAxPz58x22tabB27/88ov6uMFgEPn5+XbzVFVViSZNmqjzvf/++0IIx4O3nfHW4G38O4C7+gUK3GmDfDllR5wN3q7pcrMA7C436+zSsSkpKQ4Hb1dVVdkMnHf2Yx2kzcHbRPrEU6GIKCAkJSXhjz/+wNSpU9GjRw9ERUUhLCwMbdq0wV133YXNmzc7PZc+JiYG69evx8iRIxEfH4+IiAj07dsXP/30k3pTNcByWsyaNWvw2muv4fzzz0dMTAxCQkLQvHlzDBs2DBs2bFD36gKWU33uvvtupKWloXHjxjAajWjQoAF69uyJadOm2dykLSEhARs3bsTLL7+MCy64AHFxcQgNDUXz5s1xwQUX4KmnnrK5fG10dDTWrFmDO+64A/Hx8YiMjESfPn3w/fffax4f4WnWowHO3H///fjtt98wYsQItGrVCmFhYYiNjUVKSgpuvvlmfPjhhxgyZEitXls+WtG3b180bdrUbh6j0Yjrr79e/Vse6O0vkZGR6NSpE+655x5s2rTJ7gIF3hQSEoLly5djzpw5uPjiixEXF4eQkBAkJibihhtuwM8//4zHH3/cZpmPPvoIkydPVm9wmJqairfffhv/+c9/HL6G0WjE4sWL8emnn+Kqq65CQkICQkJCkJCQgO7du+O+++7Dd999p6sxVERkTxHCzRNRiYgCyOrVq3HppZcCAFq3bq1e8YeIiIhqh0csiIiIiIiozlhYEBERERFRnbGwICIiIiKiOuMYCyIiIiIiqjMesSAiIiIiojpjYUFERERERHUWdHfeNpvNOHToEGJiYqAoir+bQ0RERERUbwkhUFJSgubNm8NgcH1MIugKi0OHDiE5OdnfzSAiIiIi0o28vDy0bNnS5TxBV1jExMQAsLw5sbGxXnsdk8mErVu3omvXrjAajV57HdIH5oFkzAPJmAeSMQ8kqw95KC4uRnJysroN7UrQFRbW059iY2O9XlhER0cjNjaWKwZiHsgG80Ay5oFkzAPJ6lMe3BlCwMHbRERERERUZywsiIiIiIiozoLuBnnFxcWIi4tDUVGRV0+FEkLAbDbDYDDw6lPEPJAN5oFkzAPJmAeS1Yc8aNl25hELL6qoqPB3E6geYR5IxjyQjHkgGfNAMj3lgYWFl5jNZuTm5sJsNvu7KVQPMA8kYx5IxjyQjHkgmd7ywMKCiIiIiIjqjIUFERERERHVGQsLL/L39YapfmEeSMY8kIx5IBnzQDI95YFXhSIiIiIiIod0c1WoX375BYMGDULz5s2hKAqWL19e4zKrV6/GOeecg/DwcHTo0AELFizwejtrQwiB4uJiBFndRk4wDyRjHkjGPJCMeSCZ3vLg18Li9OnT6N69O95++2235t+7dy+uu+46XHrppcjKysKECRNw9913Y8WKFV5uqXZmsxl79uzRzSh+8i7mgWTMA8mYB5IxDyTTWx5C/Pni11xzDa655hq35589ezbatm2LV155BQDQuXNn/Prrr3jttddw1VVXeauZRERERERUA10N3t6wYQMGDBhgM+2qq67Chg0b/NQiIiIiIiIC/HzEQqv8/Hw0bdrUZlrTpk1RXFyMM2fOIDIy0m6Z8vJylJeXq38XFxcDAEwmE0wmEwBAURQYDAaYzWabc9is063z1TTdert163OHhYXBZDLBYLDUb9UPYzmbbjQa1Vu4V59evY3OpnujT+60nX1y3HaTyYSIiAi7efXcJ2fT2Sf3+mRdPwRSn9xpO/tk33ZrHqzPEQh9cjb988+BZ581YMcOBZ06CTzzjBmDB7tu++efK3j2WQNycwU6dQImT7YsU1/6JLfdE58TAJv1gzt9WrbMjGnTDNixA+jUCZgyRcHgwfWnT4H4OfmqT/L3hb/6pGV8h64Ki9qYMWMGpk6dajd969atiI6OBgDEx8ejVatWOHjwIAoLC9V5kpKSkJSUhH379qGkpESdnpycjMaNG2Pnzp0oKytTp7dr1w6xsbHYtm2b+sFs27YNKSkpCAsLQ3Z2tk0b0tLSUFFRgdzcXHWa0WhEWloaSkpKsGfPHnV6REQEUlNTceLECeTl5anTY2Ji0L59exw9ehT5+fnqdG/2CQD7VIs+paamIj8/P6D6FIifky/6lJubC5PJhG3btgVMnwLxc/J1n4xGo1fXET/9FIsnnqjAvn3haN26HP/3f/kYNy4J33wThiefrMD+/WenT5jQChUVFXjnnXy8914S9u8PR5s25ZgxIxIDBlj6tHJlnPpYaiowceJpdO++2+nntHJlHP7zn7ZQFAEhgOxs4OabjXj55b0AgLlzW2LvXgNat67C2LGHcPnlRdIygBAK/v5bqMuMHds44LL399+d8NJLUdi+PfXfz+IfXH55EVJSUpx+TkuWVOG228L/fV8t79HQocBHH51Bt247NPfJ+rkeOBCBlBRg3LjjOP/8f+qUPWefk6vs+epzWrkyzmH23PucFLXd1s/JW9nLy8vz23pP0/gOUU8AEJ9//rnLefr16yceeughm2nz5s0TsbGxTpcpKysTRUVF6k9eXp4AIAoLC0VVVZWoqqoSJpNJCCGEyWRSp8nT5WmuppvNZnV6RUWFOHr0qKioqBBms1mYzWaH8zuaLoRwOr16G51N90af3Gk7++S47RUVFeLYsWOisrIyYPoUiJ+Ts+mffWYS6elChIebRVqaWXz2Wd36JK8f5LZ/9lmVSEszq6+zdKn+P6dA7JOns2fNg8lkcrtPWjO5dKlZAEIoiu2/t97qePq0aWbx3HOOH1u61CwWLKiq9pgQgBCffVZl85mnpwvx2WeWtqelmdX5z/5Y5rP+Lv+7eLHzZaKjzeK118zizTeFTb4++0y/673PPrN9T63vw8CBJnHVVY4/iylTzCIszCy9d0L9PLp3196n6m2QP1drG9PTzSIiQtjkrqbsOcqqs0z6ch1h31+zTX9df07Cbhmz2bKOc5RJR9Nr6lP19eeyZf5Z7508eVIAEEVFRaImuiosHnvsMdGtWzebacOHDxdXXXWV269TVFTk9ptTF1VVVWLz5s1qQCi4MQ+et2yZEOnpQkREWP5dtsy9x9x9vg8/FGL1aiHGjBF2X9iAe8/pjKM8LFsmqn1Z2b5ObfrkbzX1ydOv5cn3xxMZcjeTztYP1ZeZP1+IX38VYvFi5+9r9WUWLxbi55+FaNLk7HzVs6zlx7LBKkRysuPHo6Kcty0iQttrpaZqW6au+fL2OsXZ83XrJsSoUUJER2v/LNq1c/54SIgQCxe636d584Ro1cr5Z16b/8/Vl7H+JCYKYTQ6f63acvaey9O7dhVixgwh3n/f8v9Caxs6dXK+zHvvOX6PJkzQvn4/+97ZFj3+WPdr2Xb2a2FRUlIiNm/eLDZv3iwAiFdffVVs3rxZ7N+/XwghxKRJk8Ttt9+uzr9nzx4RFRUlHn30UZGTkyPefvttYTQaxffff+/2a7KwIH9gHjzL2ZfVO++4/vJztPKuqrJ8oTpaxtUXenp6zW109gWXlmYWYWEmdQ+UEI6/0AEhwsOFaN/e88WNt+XnW/rtaGO2LhsOjni6KPPEBpT139deE2LOHNeZrJ6HigohXnrJef46dXKc0dBQ9/Jb15+IiLOv5e4GcPfujvPg6ic0VPsy7uSr+kb9a68J8dFHjj+jW289u3PBE3l47DEhnn5a2/rG1U9YmBAGg/vvjbXdCxdqe23r/x1H8zdrJsSOHbbva+fOZ//W2r+QkNoXco7e1+rrT3ff1/HjLUVIRIQQKSlCDBtm+dvVe5SUpD2rztodFla7fHuDbgqLVatWCQB2P6NHjxZCCDF69GjRv39/u2V69OghwsLCRLt27cT8+fM1vSYLC/IHT+bB03vV9MZsFqJNG8cr6latnH+RRUY633iJiND+5acoQjz8sPPiwdEXxejR1r/t90A52nvnzpeSL7mzN7BbNyEGD7Z8KTr6YgQsG0Jbt2p/neqPde5s2VBLTHT8/qSmCnHxxc43rpy9TpcujtvdsqUQv/8uxKJF4t9TO84uV5sNqNatbfNgPZ2lpo12LRv1NWXIWe4SElzvze3QQdtrRUQ4/3+RnOy8AHVVsIWEOH9/nFmwwPEyiYmeLWBc5SEqyv3XUhTLe92xo/vvkTvtTk3V3letR5xqyqqz9UNcnOPP3NH6plMny9Geyy6zHL3xRFGtKEI0aKB9me7dta/HXRVsrpbxNd0UFv7gy8Ji165dLCxICOG5PDj7kh0+XIgbbnC8EnrlFSE+/li/BYf8JdKxo2XD1dWXWG2+/Jz9GI2WjUlXK/3qn0Xv3s6LGFdfSG3bOn7c1d5I68Za587aCs3aFKfOsld9b2719jl77wwGy8arvHFeWmo5Bc3R69x6qxCDBmn7/LRs1MgbL+Hh2j6/ml7L1bJaN4SMRsuGppblDAbnp2I89pjj6ZmZzj9zV481b+76KNWyZWc3Urt3r/l1nC0jhPMNMnlvuWUsgOUowc03a/+MXP2EhAhRWWm/zvrrL/ePIlR/Pkv/bXc81OY9euEF522IiHCecesyjl6nNkePHK0DaiqInK1zw8Kcryet/ze0vt9Tpjjur6t+WosyR++Rs1MEHX0WtSnYeMSiHvJVYUHkDbXZK+poxQTUbSOzNjxxaLumfnXpUrsvv7g47XtMXb23Wn8iIix7wZ19WTk7pci6x7v6T3q6EOec4/ixRx913NZhw4S4807Hj02YULv3dcgQ998764+jz6K2OXf2Je9qGespO1qXc1ZENWokREyMtrwoihANGzpvX232/Fv/PznaQHc2vTaP1bQB7Or/urPX0bp+qF4safkcq//dtq3lSKiz57roIiGWLj17BMvR5yb/JCXVfISmNp+FI65ORXS0g6amNjj7bEeNcv7+VD89r6aC6IMPar9zKDracX/Dw7X9v1i61PnRlPBw15+Fq1PgnL0Pzj4n6+mxWv8veQMLCxd8VViYTCZx+PBhdfQ9BTdnedCysb1zp/ND/1p/FMXyeued53jF9f77Qsye7fgxV6eQOOtTbc5ZF8L5xuzZPXv2K1xnr+VoL1hNG2rOvvyWLavdHuqaBitq/bJyVli4+txrc9pXkybav+zDwhz3adEix6cuWX9qs6fX+r5Wf38WLbKcG62lv65O2Rkzxnn7XG1Aufr8PJXJumzUe1ptigRPvparItjZ/8Gzp6XV/PnJP7ff7vwxrXmwvk+e2n6ozRGn2haArooYTxREzj47eX2zdKnjPrnaqNfSBnePFmgt4Gv6nNLTrVdYM/ulqBCChYVLHGNB/lCbqwBZmc2WQcnVr7Yir+zatrUMUHP0mKsVsdYNOFd7yQcMEOLCCx0/5mgDCrBs7B8+bFuMdO1qKWyEcL4xGx7u+T2pntob2LWr86v2nP2Csz/VoSaO2ufJ075c/RgMzr/sXR3id8ZZuxXF+dWLXGW8NntZHe2FdqfIq+0GlOtMOs5Dbffi+2qjvr5ylq/QUOf/N62fh7uf3/PPW06tSktz/P+ieXNLYVubow+eHpPnqSMgNb2Oq/Wrp56rpg3+2hyV83Z/3O2zL/JQWywsXGBhQf5QPQ+lpZbTdhx9ITVtKsT331vONe/c2fmGm6MvRUePOdsr2rx57TYyte7tVhTtywDOB8S6u9fIEV9+kbr6gktPt1wFqK57oJy9P926Oc6XsyMW1g332gyi9fTeQF/tZa3Lc3lyg8OTeSCL2m581oazIqYuA2z1uv3g6fWr1r37nlZfivT6kAcWFi6wsCBvcTXo1Xo5yZQUs7j+eiHi42t3yseVV1oGYntiT/2yZc5PE4mNPXtlDk8UCbVZrlu3+nNqhzO1/eLx1PqhNhvhtR2s66q/nt4b6Mu9rLV5Lk9vcPD7wrN8ud7wxiWVmQfX6ssGv6/UhzywsHDBl2Ms9u/fzzEWQcLZF9nll1u/bKrfWVb7xrY39tTXZsPU2RGQTp0sV8tw9Jiz85eHDnX+HtQ0SE7PPLl+qM1GuK823Gvb7mDD7wvP82WOPV3EMA8kqw950LLtrAghBIJIcXEx4uLiUFRUhNjYWH83hwJE9+5AdrZlk9gdigJcfDGwZo3ldyHO/jtxIvD664DJZL9cRARw5oxn256ZCUybBuTmAikpQEYGMHiw88eEAIYOtW93ZmbNjzl6HUfvnaIA6elAVpZn+0pE5Gmu1qFEgUDTtrPXy5x6hkcsgouWqy7VdrmyMu2DaGvaG++rOxbXlif3eNf30528gesHkjEPJGMeSFYf8sAjFi746oiFyWRCdnY20tLSYDQavfY65FxmpuO958uWAUOG1H25U6eAhx8G9u0Djh51vNc9JASoqtK+N95ZGzIzA3NPWLDt8eP6gWTMA8mYB5LVhzxo2XY2+KhNRF6VmWk5pSYyEujSxbJhOnXq2Q1y4Oy/jz/u+rmcLTdxIjBvnuV1wsOBxo2BOXOAn34CevU6WwAAZ5d/+GHrdPHvdAEhLO1zZcgQSyGTnm45/Sk9PXCLCsDS36wsy2leWVmB208iIqJAFuLvBhDV1ZIlwK23nv07J8ey9zs01PGYh127gH79gL59gW+/tewlb97cUig8+SSwY4fj5fbvB+66y356eLhlvMTAgY73up9/vqVY2b7djNRUBVOmuLfhPGSI6yMrRERERPUJT4XyErPZjKNHjyIxMREGAw8MeUJmpmUDfccOoFUr4KKLgIICS3FgNtvPHxYGVFa6P6AaALp1AwwGbQOxU1MtxYwrzAPJnOUhMycTU9dMxY5jO9CpSSdk9M/AkM6sLgMd1w8kYx5IVh/yoGXbmYUF6UL1MQfusI5vqD5OoUUL4J9/HC8TGgrMnQuMGmW/nMHguIDxxpWayPf8vVGfmZOJoUuGqn8rUCAgsOyWZSwuiIjIbzjGoh4wmUzYvXs3TI6uGUqaVR/3IHM0lklRgK5dHY9TOHDAUkA4YjAAt9/ueLlu3c6OoZBfJyWl5vYzD/WbdaM++0g2ykxlyD6SjaFLhiIzJ1N9vPvs7oicHonus7ur02ureh6OnDqCu7+822YeAQEFCqatmVan16L6j+sHssrMyUT6u+kIfzYc6e+m26xrPL0eIn3Q2/qBRyy8pD6M4tcr6ylPublAy5bAiy8CI0YAZWX284aFAQsXAjfdpO0KSrW5d0JdrtTEPNRv3Wd3R/aRbAjYrg6jw6LRo2kP/Jr3qzqtrkcSMnMyMWX1FOQey0Wnxp3Qs1lPLN++HCUVJQ7nNygG7J+wHy1jW2p+LdIHrh8IOLuDw7qOsRrQdgDKqso8uh6qL/x9pFgP6sP6gUcsSLesG+/Z2UB5ObB7t+Xvpk0dHy3o3NnyuNYrKFlv9Fb9Kk6urtYUqFdq4l4wIKcgx66oAIBTFadsvsyBs0cSMlbXcGkvB6wbDn8f/RsV5gr8XfA3PtrykdOiAgDMwoyu73TF/d/cj+7vBvfnRIEr2NZDNv19tzteWf8K7v36XgCwWxf9tPcnh+shAPi/r/4Pvx38Dcu2Lau371/1z3ZR9iJsPboVT/z0BIYuGYotR7Y4PFLsb8GWSU/hEQsvqQ8Vpr/Jg607dbJstNd0laP0dEtRUV3r1parMnnyvg6+vHdCfc1D9T1kntgLprc9UCt2rcA1n1zjsLCoyZXtrsTek3uRV5Rn11fr+5B7LBetG7bGdR2vwydbPsHR0qMOn+uKdlfgxz0/2n0WjgTK3kqy8NX6wdP/Nz31fM721L921Wu4/7z78dWOr3S1TrFy9v4466+n1Kf1Q/WxYzVRoCC9aTqy7s3yXqPc4Oy7cenNSzG0y1Cffs/Vh+0HDt52wZdXhTpx4gQaNWoUlFd1qM3N6YSwjH1wdBphRATwySf6vYlafcyDEALtXm+HfUX7bKbXZcWutwHIX+/4GkOXDEWFqcJmurXdHw/+GM/+8ix2HN/h9gZAcmwyACCvOM/tdoQZw1D+dDkyczIxbc005B7PRUrjFDzS5xH8vO9nLMhaYLdMffkCBvRXTHpLbd8HT64fqrdh8sWTkdY0DW/+70289ftb6nzyhpKiKJrb7ez/+qKhixBmDNP0fB3f7IhdhbscPmZUjDCJs18Ketn54ax4OKfZOdh6dCvKTeVuPY8CBR0bd4QBBuQez3V7PeTO+sEX74Oz00xdiQiJwJmnandFFFfFnJa+ump3ZEgkzlSdbZ83v+cyczIxdfVU9Tsh4xL/rFtZWLjAq0L5htYxDNabyb3+uv1j7typOpi4WkG6u1K9ucvN+G7Xd1ift97ha4QYQlD6ZClCjU5GuTtQVlWG5FeTcezMMZvp/tgAdudL5POcz3Hr0ltRaa4EAFzQ4gKUVpZiR+EOywq8fwYGdx7sdM+Vp/Y2uvP+hD0bprZTVpcvYE+p6ahXbTZePL2MPzYk3d3Y8GTbarMn3Lrh7m67q8xVWL59OUYvH43SytIan9/V8xWVFeHpn5+2KXjc1SG+A3aM34HPt3+u6f3zxlFaR2qzQW1QDDALs13bMm/JhIBw2O7x543HO3+8A7Owv2RhuDEcZU87GJwI370PEdMjHBZRBsWAhKgEHD191O496t60u0d2bFldlHwR1uWt09RXZ+12xhvfc776jNzBwsIFX54KtXPnTnTs2LFenfriKxERljES1YWGAhUV9tOfegp4/vmzf3vylKf6wFN5cLbivLXrrYgLj8N/N/3XbiU04fwJmPW/WZo3hNObpmN4t+FY9PeiGr+0s49kY0TmCGQfdXAeGyyFStlTZTAavP9/wdXKGACmrpmKnIIcmw31Yd2G4aPBHyHE4PieodWPJGT0z8DwZcM1ffEAzjfiMm/JxODOzgPubCMlvWk6/rr3L01t8LTu73bHlqNb7KZHhkTigpYXYNW+VZq+GD/J/gQjM0eqf7uzjLPPfML5E1BWVYbZf87W9HzW56zrHs6aNjactXve9fNwR487XG40V2/fnT3uxPNrn3d6qp1WLWJa4KvhX2FX4S5MXzsducdyER8ZjypzFQpKCzQ/X2x4LF6/2rLn6LUNryHnmGVcU5W5yuH8ChTERcShqKzI6XorOTYZecV5mvKV/m663XrKGxuFznYGWF+vep+sbZjcfzKmrp6K7ce2I7VJKqZcMkVdNzhaDw3uPNjp+sGgGPB/vf4P6w6sw47jZzOU3jQdF8+/GIdPHdb8Pmj9f9FoZiOcLD/ptK+OCuH/9PkPXrryJafP6Uzb19ti38l9bs3rqq+HSw6j7ettHa7fI0MiUVZV5jCTEcYInHnaczt6Or/dGduPbXe73d7EwsIFjrHwPpMJaNQIKHEyHnX8eODVV89e8vW554Cnnz77+P33A7/+qu2Up/p+Koan8uDoS7EuWsS0wD8l/7hVdDjaQM89lovGkY1xtPSo0w0Eq9QmqQCAfSf2efUz6vpOV2wr2GY3vfopFVb9W/fHylErNRc9rjYkBYTTx1xtODjjbE/0NR2uwTe3fQOl+pUNpOW8ebSg4HQBkl5Jcri31JX2jdrjucuew/O/Po8dx3agY+OOGNhpIPae3IvFfy92mMWO8R2x44EddtOFEOjwZgfsObFHUxs6N+mMbffb5wTQvqewqKwIjV9s7DBf1tPcHLbBwYaDVURIBMqq7Pc2T7poEuIi4vDEyifc3llgUAxIjErEkdNHPHKUzdNCDCGoMlc5LLinrJmiac+/qw2vM5VnED0jWvPefa2+2/kdrlt4ncPioXNCZ0y7ZBpu+uwmpzsYtH5feHLMhqujoFpPdf1+1/e45pNrbKZV76u1WNpWsE0txBpFNMKW+7ZouhLeJ1s+wcjPR9Y8oyTUEIqKZ2z3dP5T/A8u+/Ay7Dhuu65xJ5MJUQk48p8jdV4fCyEwZ9Mc3PP1PQ6fxx9HqllYuMDCwvvKy4GrrgLWrHE+T+fOlvtP7NhhewTj7beBceO0vV59P69fvrxoSpMUTLlkSq3aJYRA6LOhDjdeaiPUEIrSp0rxZe6XNnvBbku7DZ/+/Sk25292uFxUaBRKK0sdfom1im2FA8UHavyC89ZntHTbUtz82c2alqntXn9nG5+uTluo7YaD9fWqfwEDlgGuEy6YYDf/0q1LcfNS+/dizvVz0DC8Iab9Ms3mC25Qp0GYs2kOxn07zq0N6rX712LYsmE4VHJI2xtXB1e1vwoXt7oYi7ctVvegA7Db8+quXs164XjpcRw+dRjtG7XHTV1vQlx4HKb/Mh0nyk7YzOtsg3XFrhW4+6u7cbD4oMPXUKDghQEvYGKfiWrxWlpZihfXvYipa6bWqt1aONs7bP23VVwr5BXladogjQmLwYQLJuDZX561e77Wca1xoOiApufr3KQzpl823eHeeGf/z1IapyD3eK7D53O04XW64jSu//R6/Lz3Z4fLGBUjMm/NxPUp17vdbke+zP0SN392s9NxW9U3qKv3F6jd9oP8fB3iOyAxKhE/73PcV1dax7XGvgn77KYLIdB6Vmu7sWPO/l+UVpai2zvdsPfkXgCWo0sFpQV2fZWff/iy4Vi8dTEA4PK2l+OH23+AQal5zNFbG9/CA9894PAxBYpauDrK5H3n3oeXr3wZUaFR2H9yPy778DJ1J0VCVAIaRzXGvpP7XGZS9uKAF/HoRY/avY67p4zmHstFqDEUpypOOe0Pj1jUMywsfEMIYOxYYNUq4NAhy5GHCy+03NXaWkhUP91p1Cjggw+0vc7+k/vRfXZ3FJUX2UyvLwNbPXWOpBACj/74KF7Z8IrdYwoUtGnYBpWmShwssd+4cXXY3dn7U2WuQuRzkTUehZA1iWqCvIfz8O3Ob22+MG/pegumrJ5id1qAAgVpTdM8cipPwekC3P/t/fhs22eal63rQEFnGwee3nCQzd88H3d+eScAy/u49Jalap6Ky4sxb/M8PPbjY05PxXDEAAPMcHzkoUVMC2wcuxG/HfwNU1dPxbZj2+yyUT3jC4csxOTVk7G7cLemjUxnR5a0UqCgWUwzGGDAPyX/eGRPvQIFGf0z0DiqMWb/MRvbj223a6uzorpjfEcoioK9JywbWq4+m5iwGJyqOKW5za7O0Xe2MeusCB7TYww++OsDh3v3rf9ntDzf85c9j2dWPePws63p/6Cz/0spb6XY7VkGgHYN22H3Q7vVv0vKSzBw0UD8sv8XdZqzzyk+Mh6nK04jpUmK5qOqy7Ytw7Blw9T/GxcmX4hT5afsxm3VxFPbD85Ox1KgYGT6SHy05SOH78O0S6bh6YufVve87zy+E+O+HYef9vzk8HUcHe2Z9NMkvLDuBQDAJW0uwc+jfna6J9/qxJkTSJ+drhbpL1/xMh658BGn8wshMP2X6Zi8erJd/+TsPXbhY3hx/YtOP/MWMS0QYgjB/qL96rR2jdrh51E/o3XD1g5fW85kk6gmNjsWPrzxQ9ze/XabdnZ6q5PDCxTEhMXgwuQLsWL3Cqf91HrqrDewsHDBV4WFEAIlJSWIiYmp8T9ToHJ02K9F8RBceaXlNCktN6er/nwdGndAapNUfL3ja4enCwCePbRdWx3e6IDdJ3bbTY8KjcLECyYizBiGz7Z9hp3Hd7o8NPrsmmdtVp5a9pJXX6nW9bx+Z1xtHLgaCPfqla8ioUECXlr/Uq1O2ckpyIFZmJ1u4Lnak+qvAtQT64fJqybj2V+eBXB2r1xcRBxOV5y2uWKJt3VL7IYJF0zAm/970+29zc6KmFBDKD4e8jFuXXqr3TIJUQlOz+23njak5f+FpwoYq/Sm6Rh37ji8+8e7yD2ei47xHdGmYRt8veNrp/+HqrepptMtFCho2qApKs2VOH7muN1zWY9MOCtondFy7r675+F78vlcvY6zPcdDUodgZ+FO7Di+A0bFiNIqy0DzuPA4TOo7CZ/+/Slyj+eifaP2aBDWABv/2ejwNRYOWYjhacNrvDjAw98/jAPFB9TlRqSNwIIbFzgdt+WKp7Yfanq/rZ/T9mPbERUaZXOUrmFEQ5ypPIOGEQ1x/MxxlzuZ4sLjcPTRowgzhgGwjLk757/noMpchTBjGLbcuwUpTVLcavOqvatw+YeXq20OM4YhtUmq/fii1VOxtWCrzf/hp/o9hZ5JPfHsL886XBfJmbyg5QX48K8Pna4r/zvwvxjba6xbbQaA6b9MxzOrngFgKfBbx7XGoZJDaBLVxK5ocVfbhm3x8pUvq5+R9X3wdVEBsLBwiVeF8rzMTGDyZGDnTiA19d+bzHV2vqd+xDlDHN5FOyICOONke6g255CGGEKw4a4NOLf5ubXvnAbyF09yXDKiw6Kdnk7kiLOjGa//9jomrJig/n3fufdhfd56TXvJXe09d9UfR59hs+hmyD+Vr2njQEuR4s5RnQVZCzDmizF206PDovHfgf9FmDHM7sulptOT9EYIgUs/uBRr9rs451ADBQpiw2Ptjv7VpKZTyRxlz9lGc/UNHnmZgZ0GosHzDZxeHeuTIZ9oOnrkbPB9qCEU0y+bjsd/etwuK864yv/6vPW49INL7U6NAYCUxil4/vLnNZ0C5M6pdp7iqg21eR1PP5/1Oa0bXmHGMJc3m2wQ2gCr71ht950ghECr11o5POILWDbw9p7ca9fuQZ0G4WTZSaw9sNZumc9u+gw3db2pVn3yFC3vtxACL61/CY//9LjT52sS1QTHSo85/P8wqNMgfHbzZwg1huKieRfht4O/AQCm9J+CjEu03Uz0xk9vxBe5X6h/W19v/HnjUW4qx/ub3rdbZnT6aCwYvEDT62w/th093+tpt3OyNsWuEAIPfPcA3v79bU1tcKU+XPXPioWFC748FWrbtm3o0qVLQJ8KZb1fhZX1tKbkGWnIK//bZl7rqS949y9Nl6IFLIOW/z76t8Mv9+s7XY8vd3zpcGUXZghDs5hmOHLqiFdvCOXJwXNRoVF45uJnEBUahZfWv2RziPWVK1/BxD4T6/T8Wmg51cHVxoGzLzhXkqKTsHDIQhw6dQgvrnsR249tR+PIxmgU2cjh4GwA6JLQBVvHbdXUH38UFZ5aPzgbzB8fEY9n+j+Dh1c8rOnIjbPz8G/pcgs+2/aZw8+sNl9+td3A9OQeb3f35spZOa/FeWj7eluHe29rc8TOuoyzPNT2VDtP8vTreLPdZmHGK+tfwWM/Pebw8U6NOyF3vONxGZHTI1Fm8swR7roeCfXk9oPW97vNrDYO964nRCVg70N7sWL3CvX5mkc3R15xnlrs90jqgSOnjqhjnppHN8eeh/YgPCRcU5u1XqSkLu93Tf83tTCZTWj8YmOHO2fCDGGoMFfYrfPm3zAfz/3yHHaf2O10XVQftidZWLjAMRaes3Mn0LcvcLT61Q3brAZGXwYo9tFSoGBm+414/PZznV5SVt54bx/fHr2a9cKHWz502AZHNxZr36g9TGYTth+3v0xbbcY3WDm71Kur86GdXV50zqA5uO+b+zSdAw+gXg1I98TpFilNUpD+brrHTkmpT3t4XPHU+sHZxlBtzoGvaVCpN05j8dRRtNrs8fZlcVPTMsHwfeFL4dPDHR4hcrV+cHZU1dnVuWpSl3WRP/NQ0zqlup/3/oxBiwY5vadJbb6zalPk1fb99vR6zVWh4uyoak3rovqwfmBh4QILi9rJzASmTrVcArZxY6BBA0thAQDonAn0nwo0yQUqooGo4y6fy6AY0KPBVdj6zwGUN9iNiNOd8GB6Bl64Q9uef1f/+curytHslWZuX9nFHc6u1+9KuDEcC4cudHh5Ua1jGOrLgHRPq82NpBzR0/vjqfWDp8+Bd8Ubp7HUhif3ePvqfdDDhkMg8eQ9RTJvycQzq57BtoJtds/XrlE7hBhCsOP4Do9tmAL+3X6ozXu3dv9aXLLgErtxU54+mtg8pjkMigEHiw96dAeHJ9dr3lgn14f1AwsLF1hYaFf9dCcbnTOBW4cCQnF6hMLdU1+6JHTB7sLdLm86puU/v7O9HrUZ1O3qUq8KFMtzmpyfp+koD85WaO9c+w4e/P5Bzadb6JWz92H8eePx7h/vOnzPQw2hqDRX+n0jt7Y8tX7w9cZ+fTmVzN88dcSuPm04BJLa/r9wNUbNl+Nd/JmH2r53tTlKVJs2eOP99vTOikDKgxULCxd8eVWosrIyRERE6P6qUN27w25MBGAZbB36SCeUhOwE5C4KID60Od4b/Dqm/zJd/c/6VL+nsPfkXkz6aZLmvdNhxjAsGrpI039+Z3vCG0Y0RMGjBZqu1iFfOk9W07np1pWJszz46rST+q4270Ntrn5TX3hy/cCNff0LpO+L+sKXY0M8/Vr+zkNt+uPLUyXr+zov0PIAsLBwyZeFhdlshsFg0P0XRWQkUNb239OdGu8AjncC/h4GQ9u1MLf/zuEytb30qKMjG7VdObk6reqmLjdh4ZCFCDWG1vg8M9bOwJM/P2nXRnfPTQe056G+nHbib4H6PgTS+oHqjnkgmR7zEKjr6vqgPuRBy7Zzzbc0pFoxm83Izs6G2ez4hlN60vSSf093SswGQsuApluAAU86LSoUKEhp7Pya1SlNUqDA9j+HAgVpiWlYestS9W/rvwICGf21Xa4OAIZ0HoJltyxDetN0RIREoG3DtupRCusdmsurnJ92BQBvb3zbpqi455x71OdLb5pus9Ic0nkIsu7NwpmnziDr3iyblanWPFRve/XXChaB+j4E0vqB6o55IJke8xCo6+r6QG950H7nFgo+l0wFShXA8O9ef6kmsN60qvpeCleFQEb/DId7NqZeMhWDOw/GsluWeeww4pDOQ2yuSPH9ru8xePFglFWV4YvcL5DwUgIqTBV2d1nNzMnEhO8nIK84T1125uUz8Xhf59f49rTqbQ9WfB+IiOo/rqsJYGFBNaioAA5Xbj9bVEhCDaH4Z+I/+GrHV5oKAeueDWfLeHPldHWHq/H18K9x7SfXosJcod5MacuRLRi6ZCi6JHQBAIf3SejYuKNX2kREREQUCFhYkFNCAOcM+h2VfUyoduYSFCjoktAFocbQWhUC/tyzcXm7y5Ecl4zdJ3bbPebsxmsKFExbM417Y4iIiIic4OBtL6kPg23q6tlPv8Xk7JuBMNsb3wTCoCxf3oAHCIw8kOcwDyRjHkjGPJCsPuSBg7friYoK+2s613eZOZnoPrs7Qp8NxeTt16lFRYuwzuiW0C1gBmV1atLJ6QDybondHD7makC6O/SYB/Ie5oFkzAPJmAeS6SkPLCy8xGw2Izc3Vzej+IGzl4vbcmSL5eZs/25bRxT0wY5HNiF7XLbDKx7pUUb/DHXgOACbAeRTL5nq8LHaXJnKSo95IO9hHkjGPJCMeSCZ3vLAwoJUU9dMtZ8ogIQWpxEVFuH7BnmRq0vj8bJ5RERERNpx8Dapth/bbj9RAY6advi+MT7gagA5L5tHREREpA2PWHiR0Wj0dxPcJoRAqMHBXaiFgtQmdRtbQBZ6ygN5H/NAMuaBZMwDyfSUBx6x8BKj0Yi0tDR/N8NtmTmZOF152vKHgGV8hdlyU7yrwms/toAs9JYH8i7mgWTMA8mYB5LpLQ88YuElQggUFxdDD1fzPVN5Bv/58T9nJ5xsA1RGAEfTgcWZWPE6xxbUlZ7yQN7HPJCMeSAZ80AyveWBhYWXmM1m7NmzRxej+F/Z8Ar2ndxn+WP3AOD1PcBzZ4DZWUDOYOTm+rN1gUFPeSDvYx5IxjyQjHkgmd7ywMIiyB0sPogZv86w/GE2Aiteg3ybbUUBUjjEgoiIiIhqwMIiyE36aRJKKy03wbsm4T7gaDdYb+yoKIAQQAaHWBARERFRDVhYeFFERP2+98P6vPX4JPsTAEB8ZDw+vmsqli0D0tOBiAjLv5mZwGAOsfCI+p4H8i3mgWTMA8mYB5LpKQ+K0MtoEA8pLi5GXFwcioqKEBsb6+/m+I1ZmHH+nPPxx6E/AAC9C97GO2PGoVcvPzeMiIiIiOoNLdvOPGLhJWazGcePH6+Xg20yczLRelZrtahoiGRsfPcenHsu8PLLfm5cgKrPeSDfYx5IxjyQjHkgmd7ywMLCS4QQyMvLq3eXB8vMycTQJUNxsPigOu0k8oCUL6EowKBBfmxcAKuveSD/YB5IxjyQjHkgmd7ywMIiyExZPcV+olkB+k/D4MG8AhQRERER1Q7vvB1EhBDYVrDN/gGDABrn4vExvm8TEREREQUGHrHwopiYGH83wcas32bBJEz2D5gVNChPQe/evm9TMKlveSD/Yh5IxjyQjHkgmZ7ywKtCBYll25bh5s9uhoDl41agWH43K4BB4JlOmZg2nNeVJSIiIqKzeFWoesBsNiM/P79ejOL/7eBvGPn5SLWo6BN7M0IL04HKCOBoOhJ+zsTUYSwqvKk+5YH8j3kgGfNAMuaBZHrLA8dYeIkQAvn5+UhISPDL62fmZGLqmqnYfmw7TGaTegpU/4a3Y82EDwAo6rwFAD7/HBgyxC9NDQr+zgPVL8wDyZgHkjEPJNNbHnjEIgBZLymbfSQbFaYKtajoltANx+fPgaIoNvMrCjBtmj9aSkRERESBgoVFAJq6ZurZMRTV7MoNQ/VRNUIAubk+ahwRERERBSQWFl6iKAri4+Ptjg74wo5jOxwXFSd2oVMnyxEKmaLw/hXe5s88UP3DPJCMeSAZ80AyveWBhYWXGAwGtGrVCgaD79/iNo3a2E1ToCClcQoyMixHKKz5VBTL3xkZvm1jsPFnHqj+YR5IxjyQjHkgmd7yoI9W6pDZbMaBAwd8PopfCIGIkAibadbToib3z0C3bsCyZUB6OhARYfk3MxMYzItCeZW/8kD1E/NAMuaBZMwDyfSWBxYWXiKEQGFhIXx9m5BPsj9BVn4WACDEEIJwYzjSm6Yj85ZMNC8ajJQU4NVXgZkzgTNngKwsFhW+4K88UP3EPJCMeSAZ80AyveWBl5sNIAWnCzDh+wnq38tuWYbrU65X/x4zxvLvunVAfr6PG0dEREREAY1HLALIQ98/hONnjgMAbul6i01RcfIksHix5fe4OOCWW/zQQCIiIiIKWCwsvERRFCQlJflsFP/XO77Gor8XAQDiI+PxxtVv2Dz+0UeWU58AYNQoICrKJ82if/k6D1S/MQ8kYx5IxjyQTG95UIReTtrykOLiYsTFxaGoqAixsbH+bo5HFJcXo+s7XXGw+CAA4IMbP8Co7qPUx4UA0tKArVstf2dnA926+aOlRERERKQnWradecTCS0wmE3bv3g2TyeTV18nMyUS719upRUX3pt1xe/rtNvOsX3+2qLjwQhYV/uCrPJA+MA8kYx5IxjyQTG95YGHhRSUlJV59/sycTAxdMlQdVwEAfx35C59v/9xmvvfeO/v7//2fV5tELng7D6QvzAPJmAeSMQ8k01MeWFjo2NQ1U+2mKVAwbc009e/CQmDJEsvvjRoBN9/sq9YRERERUTBhYaFjO47tsJsmIJB7PFf9+6OPgPJyy++jRgGRkb5qHREREREFExYWXqIoCpKTk706ir9j4472rwsFKY1T1L+7dweuvRYwGIB77vFaU6gGvsgD6QfzQDLmgWTMA8n0lgcWFl5iMBjQuHFjGAzee4v/r5ftgAkFCgQEMvpnIDPTUlRccw1w8CDw3/8CXbp4rSlUA1/kgfSDeSAZ80Ay5oFkesuDPlqpQyaTCdu3b/fqKP7kuGT1d6NiRHrTdGTekgmRMxhDh1ouK1tWZvn37ruBzEyvNYVq4Is8kH4wDyRjHkjGPJBMb3kI8XcDAllZWZlXn39bwTb1948Gf4ThacMBAN2HAYpiuX8FYPlXUYBp04AhQ7zaJHLB23kgfWEeSMY8kIx5IJme8sAjFjqWcyxH/b1zQmf19x07zhYVVkIAubkgIiIiIvIKFhY6Zj1iUX3AdqdO9vMqCpCSYj+diIiIiMgTWFh4icFgQLt27bw22EYIgZwCyxGLto3aIjL07HVkMzJs57WeFlV9OvmOt/NA+sI8kIx5IBnzQDK95cHvrXz77bfRpk0bRERE4Pzzz8fGjRtdzj9r1iykpKQgMjISycnJePjhh+vluWeKoiA2NtZrlwfLK87D6crTAIAuCbaXe7rhBtv7VaSnWwZuDx7slaaQG7ydB9IX5oFkzAPJmAeS6S0Pfi0sFi9ejIkTJyIjIwObNm1C9+7dcdVVV+Ho0aMO51+4cCEmTZqEjIwM5OTkYO7cuVi8eDGefPJJH7e8ZiaTCdnZ2V4bxW89WgEAXZrYFhZ//w2cOWP5/aabgKwsFhX+5u08kL4wDyRjHkjGPJBMb3nwa2Hx6quvYuzYsRgzZgy6dOmC2bNnIyoqCvPmzXM4//r163HRRRfhtttuQ5s2bXDllVdi+PDhNR7l8BdvhkC+IpQ8cBsAfv317O8XXeS1JpBGelkpkG8wDyRjHkjGPJBMT3nw2+VmKyoq8Oeff+KJJ55QpxkMBgwYMAAbNmxwuMyFF16Ijz/+GBs3bkTv3r2xZ88efPvtt7j99tudvk55eTnKy8vVv4uLiwFYPiTrB6UoCgwGA8xmM4R0OSXr9OofqLPpBoMBiqKozy2EgMlkUs+LM5vNdvM7mm40GiGEcDjd2satR7eq07skdLFp+6+/KrDWjBdeaIbJ5Jk+udP2uvSppune+Jx81Sfra1WfV899cjadfXKvT9b1QyD1yZ22s0/2bbfmwfocgdAnV9PZJ9d9AmCzfgiEPgXi5+SrPsnfF/7qU/X31hW/FRbHjh2DyWRC06ZNbaY3bdoU27dvd7jMbbfdhmPHjqFv374QQqCqqgr33nuvy1OhZsyYgalTp9pN37p1K6KjowEA8fHxaNWqFQ4ePIjCwkJ1nqSkJCQlJWHfvn0oKSlRpycnJ6Nx48bYuXOnzfiOdu3aITY2Ftu2bUNVVRUKCwuxdetWpKamIiwsDNnZ2TZtSEtLQ0VFBXKl68AajUakpaWhpKQEe/bsUadHREQgNTUVJ06cQF5eHv488Kf6WGqTVBw9ehT5+fkAgNWruwAIQ1QU0LjxQWRne6ZPcthSUlI83iermJgYtG/f3qZP3vqcfNWnBg0aAAAKCgpsTvXTc58C8XPyVZ9ycnLU9YOiKAHRp0D8nHzVJyGE2q5A6RMQeJ+Tr/rUoEEDnDhxQl0/BEKfAvFz8lWfhBAoLCzE/v370bFjR7/0qXrh44oitJQhHnTo0CG0aNEC69evR58+fdTpjz32GNasWYP//e9/dsusXr0aw4YNw/Tp03H++edj165deOihhzB27Fg888wzDl/H0RGL5ORkFBYWIjY2FoD39kaWlZUhIiICRqMRgOcqWLPZjMRXEnGi7ARaxrRE3sQ8te0HDgDt2lle77LLgB9/1E9VXtN0Pe5psBJCoLKyEmFhYQ7bqMc+OZvOPtXcp6qqKnX9YJ1X730KxM/JV30SQqC8vBxRUVEQQgREn1xNZ59qPmJx+vRpdf0QCH0KxM/JV32StydDQkL80qfi4mI0bNgQRUVF6razM347YtGkSRMYjUYcOXLEZvqRI0eQlJTkcJlnnnkGt99+O+6++24Algrw9OnTuOeee/DUU0+pH5wsPDwc4eHhdtONRqO6wW/laHnrvFqnCyEQGRmpflBan0dRFIfTDQYDCkoLcKLsBICz4yusbZfPIuvb17N9qut0V31yROv0+twnIYT6n9nRlR302KfaTmefLNOrrx+0Pk997FNdpwdrn4QQiIiIsJvubH5Pt1Hr9GD9nOoyXUtbHG0/1OZ56lOfPDU9GPsk50Ge7mx+b7XRXX4bvB0WFoZevXph5cqV6jSz2YyVK1faHMGQlZaW2r1x1jfATwdenDKbzcjOztZ0+Mhd8sDt6pearaoC2rWz/M6B2/WHN/NA+sM8kIx5IBnzQDK95cFvRywAYOLEiRg9ejTOPfdc9O7dG7NmzcLp06cxZswYAMCoUaPQokULzJgxAwAwaNAgvPrqq+jZs6d6KtQzzzyDQYMGOa28AlHOMelSs9UKi1GjLD+HDwONGvm6ZUREREQUrPxaWNx6660oKCjA5MmTkZ+fjx49euD7779XB3QfOHDA5gjF008/DUVR8PTTT+Off/5BQkICBg0ahOeee85fXfALm0vNNunscJ5mzXzVGiIiIiIiPxcWADB+/HiMHz/e4WOrV6+2+TskJAQZGRnIyMjwQcvqL1enQhERERER+YPfrgrlL8XFxYiLi3NrZHtdWEf5OxusWxfNXmmG/FP5SIhKwNFHz1661GQCguiMMF3xZh5If5gHkjEPJGMeSFYf8qBl29mvd94OdBUVFR5/zhNnTiD/lOX6xdWPVlx1FdCzJ/DAA4AXXprqyBt5IP1iHkjGPJCMeSCZnvLAwsJLzGYzcnNzPT6KXx64LY+vqKgA1q8HsrKAr74Cqt0ugfzMW3kgfWIeSMY8kIx5IJne8sDCQmecja/YvBk4c8bye9++vm4VEREREQU7FhY646ywWLfu7DwsLIiIiIjI11hYeJE37q1hcypUwtlToX799ew8vDFe/RRM91qhmjEPJGMeSMY8kExPeeBVoXSm9azWOFB0AHHhcTjx+AkoigIhgKZNgYICIC4OKCwEnNzZnYiIiIjIbbwqVD0ghEBxcTE8WbedqjiFA0UHAFiOVlgvO7Zrl6WoACxHK1hU1D/eyAPpF/NAMuaBZMwDyfSWB26CeonZbMaePXs8Oop/+7Ht6u9dmpwdXyGfBsXxFfWTN/JA+sU8kIx5IBnzQDK95YGFhY7kFHB8BRERERHVTywsdMTZFaE2bLD8GxoKnHeer1tFRERERMTCwqsiIiI8+nzbjtkXFpmZljEVoaFAYiLw3XcefUnyIE/ngfSNeSAZ80Ay5oFkesoDrwqlI53e7ISdhTsRFRqFkidKsPxzA4YOBRQFEOLsv8uWAUOG+Lu1RERERKR3vCpUPWA2m3H8+HGPDbYpqyrD7hO7AQCpTVJhUAyYOvVsMQGcLS6mTfPIS5IHeToPpG/MA8mYB5IxDyTTWx5YWHiJEAJ5eXkeuzzYzuM7YRaWUHVuYhm4vWPH2aLi7OsCubkeeUnyIE/ngfSNeSAZ80Ay5oFkessDCwudcDRwu1MnyxEKmaIAKSm+bBkREREREQsL3cg5Jl1q9t8jFhkZtkcsrKdFZWT4unVEREREFOxYWHhRTEyMx57L0RGLyy8/+7jBAKSnW64SNXiwx16WPMiTeSD9Yx5IxjyQjHkgmZ7yEOLvBgQqo9GI9u3be+S5MnMy8WXul+rfW45sQUqTFOTlnZ3n9tuBBQs88nLkBZ7MA+kf80Ay5oFkzAPJ9JYHHrHwErPZjPz8/DqP4s/MycTQJUNRbipXp92y9BZk5mTiwIGz87VqVaeXIS/zVB4oMDAPJGMeSMY8kExveWBh4SVCCOTn59d5FP/UNVOhwHaEtgIF09ZMY2GhI57KAwUG5oFkzAPJmAeS6S0PPBWqnttxbAcEbMMkIJB7PBcHTp+dxsKCiIiIiPyJRyzquU5NOtlNU6AgpXEKj1gQERERUb3BwsJLFEVBfHw8lOo3mtAoo7/ttWMVKBAQyOifYVNYJCfX6WXIyzyVBwoMzAPJmAeSMQ8k01seFKGXk7Y8pLi4GHFxcSgqKkJsbKy/m+OWxJcSUVBaAABIb5qOKf2nYHDnwWjTBti/H2jcGDh2zL9tJCIiIqLAo2XbmUcsvMRsNuPAgQN1HsVfVFakFhV9WvbBX/f+hcGdB0MIoFs3IDXV8kP1m6fyQIGBeSAZ80Ay5oFkesuD5sLi9OnTNc9EEEKgsLCwzqP4s49mq7+nN01Xf1cU4OuvgZwc4Ndf6/QS5AOeygMFBuaBZMwDyZgHkuktD5oLi6ZNm+LOO+/Er9ya9Ym/8v9Sf+/etLsfW0JERERE5JzmwuLjjz9GYWEhLrvsMnTq1AkzZ87EoUOHvNE2guUu21bdk1hYEBEREVH9pLmwuPHGG7F8+XL8888/uPfee7Fw4UK0bt0aAwcORGZmJqqqqrzRTt1RFAVJSUl1HsX/15GzRyzSEtPq2izyE0/lgQID80Ay5oFkzAPJ9JYHj1wV6s0338Sjjz6KiooKNGnSBPfeey8mTZqEqKgoT7TRo/R0VSiT2YTYmbEorSxFu0btsPvB3epjTz4JfP+95f4Vr78OtG7tx4YSERERUUDyyVWhjhw5ghdffBFdunTBpEmTcNNNN2HlypV45ZVXkJmZiRtvvLG2Tx0QTCYTdu/eDZPJVOvn2HNiD0orSwHYDtwGgL//BjZvBr74AggNrVNTyQc8kQcKHMwDyZgHkjEPJNNbHkK0LpCZmYn58+djxYoV6NKlC8aNG4eRI0eiYcOG6jwXXnghOnfu7Ml26lJJSUmdlpdPg6o+cNt6c7zQUCApqU4vQz5S1zxQYGEeSMY8kIx5IJme8qC5sBgzZgyGDRuGdevW4bzzznM4T/PmzfHUU0/VuXHBzmbgtpPComVLwMC7kRARERGRn2kuLA4fPlzj2InIyEhkZGTUulFkIR+xkE+FKikBTpyw/N6qla9bRURERERkT/O+7tWrV2PFihV201esWIHvvvvOI40KBIqiIDk5uU6j+K33sIgOi0bbRm3V6Xl5Z+dhYaEPnsgDBQ7mgWTMA8mYB5LpLQ+aC4tJkyY5HEAihMCkSZM80qhAYDAY0LhxYxhqeZ5SUVkR9hftB2C5zKxBOfs81tOgABYWelHXPFBgYR5IxjyQjHkgmd7yoLmVO3fuRJcuXeymp6amYteuXR5pVCAwmUzYvn17rUfxuzO+AmBhoRd1zQMFFuaBZMwDyZgHkuktD5oLi7i4OOzZs8du+q5du9CgQQOPNCpQlJWV1XpZV3fcZmGhT3XJAwUe5oFkzAPJmAeS6SkPmguLG264ARMmTMDu3Wdv1rZr1y488sgjuP766z3auGDmbOA2wMKCiIiIiOofzVeFevHFF3H11VcjNTUVLVu2BAAcPHgQ/fr1w8svv+zxBgYrubBIS0yzeeyee4DzzrMUGLzjNhERERHVB4oQQmhdSAiBH3/8EX/99RciIyORnp6Oiy++2Bvt8zgttyWvCyEESkpKEBMTo3kkv8lsQuzMWJRWlqJdo3bY/eDumheieq0ueaDAwzyQjHkgGfNAsvqQBy3bzpqPWACWS19deeWVuPLKK2vVwGCgKEqtC5fdJ3ajtLIUgP3AbdKnuuSBAg/zQDLmgWTMA8n0lodaFRanT5/GmjVrcODAAVRUVNg89uCDD3qkYXpnMpmwbds2dOnSBUajUdOy8sDt6uMrSJ/qkgcKPMwDyZgHkjEPJNNbHjQXFps3b8a1116L0tJSnD59GvHx8Th27BiioqKQmJjIwkJS20uDWW+MB9gfsTh2DNi92zJou2lTQCeXNSbUPg8UmJgHkjEPJGMeSKanPGjeLH344YcxaNAgnDhxApGRkfjtt9+wf/9+9OrVi4O3PUQeuF39UrMrVwIXXAA0bw688oqvW0ZERERE5JjmwiIrKwuPPPIIDAYDjEYjysvLkZycjBdffBFPPvmkN9oYdKynQkWHRaNNwzY2j/FSs0RERERUH2kuLEJDQ9XbiicmJuLAv1u6cXFxyMvL82zrdMxgMCAlJUXzLdhPlp3E/qL9ACzjKwyK7fIsLPSptnmgwMQ8kIx5IBnzQDK95UHzGIuePXvi999/R8eOHdG/f39MnjwZx44dw0cffYRu3bp5o426FRYWpnmZ7CPZ6u/pifYDt1lY6Fdt8kCBi3kgGfNAMuaBZHrKg+by5/nnn0ezZs0AAM899xwaNWqE++67DwUFBfjvf//r8QbqldlsRnZ2Nsxms6blXI2vAM4WFiEhQFJSnZpIPlTbPFBgYh5IxjyQjHkgmd7yoOmIhRACiYmJ6pGJxMREfP/9915pWLBydUUo4Gxh0bIloIOrjhERERFRkNB0xEIIgQ4dOnAshRdtOXr2HhbdEm1PLTt1CigstPzO06CIiIiIqD7RVFgYDAZ07NgRx48f91Z7gprJbFLHWLRv1B4x4TE2j8v1HAsLIiIiIqpPNI+xmDlzJh599FH8/fff3mhPwDAYDEhLS9M0in/3id04U3UGgOM7bnPgtn7VJg8UuJgHkjEPJGMeSKa3PGhu5ahRo7Bx40Z0794dkZGRiI+Pt/mhsyoqKjTN/98/zw5+X5+3Hpk5mTaPHzly9ncWFvqjNQ8U2JgHkjEPJGMeSKanPGi+3OysWbO80IzAYzabkZubi7S0NBjdGGWdmZOJVzacvZX20dNHMXTJUCy7ZRmGdB4CABg1Crj1VuCff4CGDb3VcvIGrXmgwMY8kIx5IBnzQDK95UFzYTF69GhvtCPoTV0z1eZvAQEFCqatmaYWFgAQHg60a+fr1hERERERuaa5sDggn+jvQCueo1MrO47tsJsmIJB7PNcPrSEiIiIi0kZzYdGmTRsoiuL0cZPJVKcGBRIth6w6NemELUe22ExToCClcYqnm0V+oodDmOQ7zAPJmAeSMQ8k01MeFCGE0LLAX3/9ZfN3ZWUlNm/ejFdffRXPPfcchgwZ4mTJ+qG4uBhxcXEoKipCbGysv5ujWrZtGW767Cb1bwUKBAQyb8nE4M6DYTYDd91luTHeOecAgwf7sbFEREREFBS0bDtrLiyc+eabb/DSSy9h9erVnng6r/FVYSGEQElJCWJiYlwe4bEqrSxFg+cbAAAMMCCtaRoy+mdgcGdLBXH4MNC8uWXegQOBr77yWtPJC7TmgQIb80Ay5oFkzAPJ6kMetGw7e+yiuCkpKfj999899XS6ZzabsWfPHpjNZrfmP3HmhPr79anXI+veLLWoAHgPC73TmgcKbMwDyZgHkjEPJNNbHjSPsSguLrb5WwiBw4cPY8qUKejYsaPHGhZsTpadVH9vGNHQ7nEWFkRERERUn2kuLBo2bGh3KEYIgeTkZHz66acea1iwkQuLRhGN7B5nYUFERERE9ZnmwuLnn3+2KSwMBgMSEhLQoUMHhIRofrqAFhER4fa8PGIR+LTkgQIf80Ay5oFkzAPJ9JQHzZXAJZdc4oVmBB6j0YjU1FS352dhEdi05oECG/NAMuaBZMwDyfSWB82Dt2fMmIF58+bZTZ83bx5eeOEFjzQqEJjNZhw/ftz9wdtlZwdvuyosjEagWTNPtJB8SWseKLAxDyRjHkjGPJBMb3nQXFi89957Diunrl27Yvbs2R5pVCAQQiAvLw/uXs3X1RGLzEzAevsQgwH48ksPNZJ8RmseKLAxDyRjHkjGPJBMb3nQXFjk5+ejmYNd5gkJCTh8+LBHGhWMnA3ezswEhg4FrDc0r6y0/J2Z6eMGEhERERG5oLmwSE5Oxrp16+ymr1u3Ds2td3AjzZwdsZg6Fah+PxRFAaZN8027iIiIiIjcoXnw9tixYzFhwgRUVlbisssuAwCsXLkSjz32GB555BGPN1DPYmJi3J7XWWGxYwdQ/eiXEEBubh0bRz6nJQ8U+JgHkjEPJGMeSKanPGguLB599FEcP34c48aNQ0VFBQDLZbAef/xxTJo0yeMN1Cuj0Yj27du7Pb+zwdudOgHZ2bbFhaIAKSmeaCX5itY8UGBjHkjGPJCMeSCZ3vKg+VQoRVHwwgsvoKCgAL/99hv++usvFBYWYvLkyXY3zgtmZrMZ+fn5bo/itx6xMCpGRIdFq9MzMixFhfWtVRTL3xkZnm4xeZPWPFBgYx5IxjyQjHkgmd7yoLmwKCoqQmFhIaKjo3HeeeehW7duCA8PR2FhIYqLi73RRl0SQiA/P1/zVaEaRtje2XzIEGDpUiA9HYiIsPybmQkMHuyNVpO3aM0DBTbmgWTMA8mYB5LpLQ+aC4thw4bh008/tZu+ZMkSDBs2zCONCkZyYVHd998Dhw4BHToAn3/OooKIiIiI6h/NhcX//vc/XHrppXbTL7nkEvzvf//zSKOCjRDCZWFx+DBQUAD8/TfQoIFv20ZERERE5A7NhUV5eTmqqqrspldWVuLMmTMeaVQgUBQF8fHxbo07OVVxCmZhOXfOUWFx9Kj1OYHGjT3ZSvIVLXmgwMc8kIx5IBnzQDK95UFzYdG7d2/897//tZs+e/Zs9OrVS3MD3n77bbRp0wYRERE4//zzsXHjRpfznzx5Evfffz+aNWuG8PBwdOrUCd9++63m1/U2g8GAVq1awWCo+S12dkUoK2th0aQJYDR6qoXkS1ryQIGPeSAZ80Ay5oFkesuD5svNTp8+HQMGDMBff/2Fyy+/HIDlPha///47fvjhB03PtXjxYkycOBGzZ8/G+eefj1mzZuGqq65Cbm4uEhMT7eavqKjAFVdcgcTERCxduhQtWrTA/v370bBhQ63d8Dqz2YyDBw+iZcuWNYbB2V23AcsVoI4csfzetKmnW0m+oiUPFPiYB5IxDyRjHkimtzxobuFFF12EDRs2IDk5GUuWLMFXX32FDh06YMuWLejXr5+m53r11VcxduxYjBkzBl26dMHs2bMRFRWFefPmOZx/3rx5KCwsxPLly3HRRRehTZs26N+/P7p37661G14nhEBhYaFbo/id3RwPAE6dAsrKLL87qLVIJ7TkgQIf80Ay5oFkzAPJ9JYHzUcsAKBHjx745JNP7KYXFhYiPj7ereeoqKjAn3/+iSeeeEKdZjAYMGDAAGzYsMHhMl9++SX69OmD+++/H1988QUSEhJw22234fHHH4fRyTlC5eXlKC8vV/+2XhLXZDLBZDIBsJy/ZjAYYDabbT4463TrfDVNNxgMUBRFfW4hBEwmk1phVr8GsXV6YWmhOi02PBaAJUhmsxmHDgGApW+JibBrI2C5eYqztnuyT47a7qxP1acbjUa1TzW1PRD7ZH2t6vPquU/OprNP7vXJun4IpD6503b2yb7t1jxYnyMQ+uRqOvvkuk8AbNYPgdCnQPycfNUn+fvCX33SUtTUqrCo7ocffsCcOXPw1VdfuT2A+9ixYzCZTGha7fyepk2bYvv27Q6X2bNnD37++WeMGDEC3377LXbt2oVx48ahsrISGU7uGDdjxgxMnTrVbvrWrVsRHW25EV18fDxatWqFgwcPorDw7EZ+UlISkpKSsG/fPpSUlKjTk5OT0bhxY+zcuRNl1sMJANq1a4fY2Fhs27YNVVVVKCwsxNatW5GamoqwsDBkZ2fbtCEtLQ0VFRXI3nl2etkJy/OVlJRgz549yMqKAtDp3/cGOHHiBPLy8tT5Y2Ji0L59exw9ehT5+fnqdG/0SQ5bSkqKyz7l5uaq04xGI9LS0tQ+WUVERCA1NTUo+tTg38t5FRQU4Kh10IzO+xSIn5Ov+pSTk6OuHxRFCYg+BeLn5Ks+CSHUdgVKn4DA+5x81acGDRrgxIkT6vohEPoUiJ+Tr/pkPWKxf/9+dOzY0S990nJzPkXU8tjK/v37MW/ePHzwwQc4ceIErrnmGgwdOhQ333yzW8sfOnQILVq0wPr169GnTx91+mOPPYY1a9Y4vHRtp06dUFZWhr1796pHKF599VW89NJLOHz4sMPXcXTEIjk5GYWFhYiNtRwd8Ea1ZzabUVBQgISEBISEWOo3ZxXsrN9mYeIPEwEAH97wIW7vcbtawS5fDtx0k6Wvzz0HTJoUuFV5IPfJbDbj+PHjaNKkic2VHfTcJ2fT2aea+1RZWamuHwwGQ0D0KRA/J1/1yfp9kZSUBAAB0SdX09kn132y3hDNun4IhD4F4ufkqz7J25OhoaF+6VNxcTEaNmyIoqIiddvZGU1HLCoqKpCZmYk5c+Zg3bp1GDBgAA4ePIjNmzcjLS1Ny1OhSZMmMBqNOGIdmfyvI0eOqCvX6po1a4bQ0FCb0546d+6M/Px8VFRUICwszG6Z8PBwhIeH2003Go12p09ZP3hH82qdbjQa0bx5c7fmLy4/e8fy+CjLqWSKosBoNOLYsbPzJSY6b6PW6bXpU12nW/vkbhsDqU9Go9Fprh3N78k2ap0ezJ9TbadrbWNoaKjd+kHr89S3PgXi5+SrPjn6vnA1v6fbqHV6sH5OdZmutS3O8qDXPnlqejD2qfr6wR990nKpW7cHbz/wwANo3rw5Xn/9dQwePBgHDx7EV1995fQNqUlYWBh69eqFlStXqtPMZjNWrlxpcwRDdtFFF2HXrl02ld2OHTvQrFkzh0WFP5lMJuzevduu8nPE5qpQkbZXhbrmGiAzE3j3XUDj2HiqR7TkgQIf80Ay5oFkzAPJ9JYHt49YvPvuu3j88ccxadIkxMTEeOTFJ06ciNGjR+Pcc89F7969MWvWLJw+fRpjxowBAIwaNQotWrTAjBkzAAD33Xcf3nrrLTz00EN44IEHsHPnTjz//PN48MEHPdIeT5PPaXPlZPlJ9ffqV4Vq1cryQ/rnbh4oODAPJGMeSMY8kExPeXC7sPjoo48wb948NGvWDNdddx1uv/12XHPNNXV68VtvvRUFBQWYPHky8vPz0aNHD3z//ffqgO4DBw7YHNpJTk7GihUr8PDDDyM9PR0tWrTAQw89hMcff7xO7fA3V5ebJSIiIiLSA7cLi+HDh2P48OHYu3cvFixYgPvvvx+lpaUwm83Ytm0bunTpUqsGjB8/HuPHj3f42OrVq+2m9enTB7/99lutXqu+OnHG9Z23iYiIiIjqO803yGvbti2mTp2Kffv24eOPP8bQoUMxcuRItGzZst6ekuQPiqIgOTnZrQEv1iMWoYZQRIZE2jz200/Ahg3A3r3eaCX5ipY8UOBjHkjGPJCMeSCZ3vJQ68vNygoLC/Hhhx9i/vz5+OuvvzzRLq8pLi5GXFycW5fM8pU2s9pgf9F+JDZIxJH/2F4lKz4eOHECaN8e2LXLTw0kIiIioqCkZdtZ8xELR+Lj4zFhwoR6X1T4kslkwvbt2zVdFar6aVAVFZaiArBcapb0S0seKPAxDyRjHkjGPJBMb3nwSGFBjsl3NHTGLMzqfSyqFxYFBWd/Z2Ghf+7kgYIH80Ay5oFkzAPJ9JQHFhZ+VlxeDAHL2WjVC4ujR8/+/u+FsoiIiIiI6iUWFn7m6opQcmHBIxZEREREVJ+xsPASg8GAdu3aOb3FupXNXbcjbO+6fUQax80jFvrmbh4oODAPJGMeSMY8kExveXDrPhZbtmxx+wnT09Nr3ZhAoiiKW1edcnVzPB6xCBzu5oGCA/NAMuaBZMwDyfSWB7cKix49ekBRFAgharyOrl5GrXubyWRSbxxoNBqdzueqsJCPWLCw0Dd380DBgXkgGfNAMuaBZHrLg1vHVfbu3Ys9e/Zg7969WLZsGdq2bYt33nkHmzdvxubNm/HOO++gffv2WLZsmbfbqytaLjULcPB2oGPRTTLmgWTMA8mYB5LpKQ9uHbFo3bq1+vvNN9+MN954A9dee606LT09HcnJyXjmmWdw4403eryRgexEmfPB22fOAIoCCMEjFkRERERUv7lVWMiys7PRtm1bu+lt27bFtm3bPNKoYOJq8PaSJUBVFXDsmOUO3ERERERE9ZXmIeadO3fGjBkzUFFRoU6rqKjAjBkz0LlzZ482Ts8MBgNSUlI0XRWq+hELAAgJAZKSLEcuSL/czQMFB+aBZMwDyZgHkuktD5qPWMyePRuDBg1Cy5Yt1StAbdmyBYqi4KuvvvJ4A/UsLCysxnlqKiwocLiTBwoezAPJmAeSMQ8k01MeNJc/vXv3xp49ezB9+nSkp6cjPT0dzz33HPbs2YPevXt7o426ZDabkZ2dDbPZ7HI+FhbBwd08UHBgHkjGPJCMeSCZ3vKg+YgFADRo0AD33HOPp9sSlOTB23ERcerveXlARoZl0PYllwBXX+2HxhERERERualWJ2x99NFH6Nu3L5o3b479+/cDAF577TV88cUXHm1cMLAesYgIiUBESIQ6fe9eYP584IUXgJ9+8lPjiIiIiIjcpLmwePfddzFx4kRcc801OHHihHpt3UaNGmHWrFmebl/AsxYW1a8IJd8cj/ewICIiIqL6TnNh8eabb+L999/HU089hZCQs2dSnXvuucjOzvZo4/TMYDAgLS3N7atCubo5Hu9hoX/u5oGCA/NAMuaBZMwDyfSWB82t3Lt3L3r27Gk3PTw8HKdPn/ZIowKFfEleR6rMVThVcQoA77odDGrKAwUX5oFkzAPJmAeS6SkPmguLtm3bIisry276999/z/tYSMxmM3Jzc12O4i8qK1J/r15YyKdC8YiF/rmTBwoezAPJmAeSMQ8k01seNF8VauLEibj//vtRVlYGIQQ2btyIRYsWYcaMGZgzZ4432hiw5CtC8VQoIiIiItIzzYXF3XffjcjISDz99NMoLS3FbbfdhubNm+P111/HsGHDvNHGgCXfw8LV4G0WFkRERERU39XqPhYjRozAiBEjUFpailOnTiGRW74OGY1Gl4+7ujme9YhFw4aAjm64SC7UlAcKLswDyZgHkjEPJNNTHjSPsThz5gxKS0sBAFFRUThz5gxmzZqFH374weON0zOj0Yi0tDSXYXBVWFiPWHDgdmBwJw8UPJgHkjEPJGMeSKa3PGguLG644QZ8+OGHAICTJ0+id+/eeOWVV3DDDTfg3Xff9XgD9UoIgeLiYgghnM7jrLAwm4GbbwYGDgT69/diI8ln3MkDBQ/mgWTMA8mYB5LpLQ+aC4tNmzahX79+AIClS5ciKSkJ+/fvx4cffog33njD4w3UK7PZjD179rgcxX/ijOPB2wYDMHcu8NVXwHvvebOV5Cvu5IGCB/NAMuaBZMwDyfSWB82FRWlpKWJiYgAAP/zwA4YMGQKDwYALLrgA+/fv93gDA5nN4O3IRs5nJCIiIiKq5zQXFh06dMDy5cuRl5eHFStW4MorrwQAHD16FLGxsR5vYCBzNcaCiIiIiEhPNBcWkydPxn/+8x+0adMGvXv3Rp8+fQBYjl44uiN3MIuIiHD5+Mnyk+rvcmGhk9PoSKOa8kDBhXkgGfNAMuaBZHrKgyJqMRokPz8fhw8fRvfu3WEwWGqTjRs3IjY2FqmpqR5vpCcVFxcjLi4ORUVFfj/Cct3C6/Dtzm8BAAWPFqBJVBMAwAsvWH4SE4H//he4+GJ/tpKIiIiIgpWWbWfNRywAICkpCT179sShQ4dw8OBBAEDv3r3rfVHhS2azGcePH3d78HZceJz6e34+cOIEkJsL6OTqYlQDd/JAwYN5IBnzQDLmgWR6y4PmwsJsNmPatGmIi4tD69at0bp1azRs2BDPPvusbjrtC0II5OXluXW52eiwaIQaQ9Xp1pvjAbzrdqBwJw8UPJgHkjEPJGMeSKa3PGi+8/ZTTz2FuXPnYubMmbjooosAAL/++iumTJmCsrIyPPfccx5vZKCyFhbObo4H8AZ5RERERKQPmguLDz74AHPmzMH111+vTktPT0eLFi0wbtw4FhYaOCssrEcswsOBf6/sS0RERERUr2k+FaqwsNDhWIrU1FQUFhZ6pFGBIsZFVVBeVY4zVWcAOC8smjYFFMVbrSNfc5UHCj7MA8mYB5IxDyTTUx40Fxbdu3fHW2+9ZTf9rbfeQvfu3T3SqEBgNBrRvn17GJ2Mvi4qL1J/lwsLkwkoKLD8zvEVgaOmPFBwYR5IxjyQjHkgmd7yoPlUqBdffBHXXXcdfvrpJ/UeFhs2bEBeXh6+/fZbjzdQr8xmM44ePYrExET1krwy+YpQcmFRWAhYx8CzsAgcNeWBggvzQDLmgWTMA8n0lgfNLezfvz927NiBwYMH4+TJkzh58iSGDBmC3Nxc9OvXzxtt1CUhBPLz852O4pfvut0oopH6OwduB6aa8kDBhXkgGfNAMuaBZHrLg+YjFgDQvHlzDtKuI7mwkI9Y8FKzRERERKRHtSosTpw4gblz5yInJwcA0KVLF4wZMwbx8fEebVwgc1ZYpKcDX35pOXKRlub7dhERERER1YbmU6F++eUXtGnTBm+88QZOnDiBEydO4I033kDbtm3xyy+/eKONuqQoCuLj46E4uayTs8KiSRNg0CDg7ruB88/3ciPJZ2rKAwUX5oFkzAPJmAeS6S0Pmo9Y3H///bj11lvx7rvvqiPUTSYTxo0bh/vvvx/Z2dkeb6QeGQwGtGrVyunjJ8ocD96mwFRTHii4MA8kYx5IxjyQTG950HzEYteuXXjkkUdsLntlNBoxceJE7Nq1y6ON0zOz2YwDBw7AbL3EUzXOBm9TYKopDxRcmAeSMQ8kYx5Iprc8aC4szjnnHHVshSwnJ4f3sZAIIVBYWOjWVaHkIxbr1wNr1wI7dpy97CzpX015oODCPJCMeSAZ80AyveVB86lQDz74IB566CHs2rULF1xwAQDgt99+w9tvv42ZM2diy5Yt6rzp6emea2mAcVZYPPwwsHGj5Y7bFRWADi5ZTERERESkvbAYPnw4AOCxxx5z+JiiKBBCQFEUmEymurcwQNV0udnGjYGQWl2zi4iIiIjI9zRvuu7du9cb7Qg4iqIgKSnJ6Sh+efB2bHgsAECIszfI483xAktNeaDgwjyQjHkgGfNAMr3lQXNh0bp1a2+0I+AYDAYkJSU5fdx6xCIuPA5Gg2Ug/OnTwJkzlsd5c7zAUlMeKLgwDyRjHkjGPJBMb3mo1Rn8u3fvxgMPPIABAwZgwIABePDBB7F7925Pt03XTCYTdu/e7fR0MGth4eyu2zxiEVhqygMFF+aBZMwDyZgHkuktD5oLixUrVqBLly7YuHEj0tPTkZ6ejv/973/o2rUrfvzxR2+0UbdKSkocThdCOCwsrKdBATxiEYic5YGCE/NAMuaBZMwDyfSUB82nQk2aNAkPP/wwZs6caTf98ccfxxVXXOGxxgWqsqoyVJgqADg/YsHCgoiIiIj0RPMRi5ycHNx111120++8805s27bNI40KdM6uCCUfseCpUERERESkJ5oLi4SEBGRlZdlNz8rKQiJ3s6sURUFycrLDUfzyFaEaRZ696zaPWAQuV3mg4MM8kIx5IBnzQDK95UHzqVBjx47FPffcgz179uDCCy8EAKxbtw4vvPACJk6c6PEG6pXBYEDjxo0dPmZzxCK8ofr76dOWG+KZzTxiEWhc5YGCD/NAMuaBZMwDyfSWB81HLJ555hlMnjwZb775Jvr374/+/fvjrbfewpQpU/D00097o426ZDKZsH37doej+J2dCnXeeUDXrkB4ODB2LJCZ6YOGkk+4ygMFH+aBZMwDyZgHkuktD5qOWAghkJeXh/vuuw8PP/ywOko9JibGK43Tu7KyMofTHRUWmZnA0KGAolhulPf335a/ly0DhgzxQWPJ65zlgYIT80Ay5oFkzAPJ9JQHTUcshBDo0KED8vLyAFgKChYV2jkqLKZOPVtUAJZ/FQWYNs337SMiIiIi0kpTYWEwGNCxY0ccP37cW+0JCifO2A/e3rHjbFFhJQSQm+vLlhERERER1Y7mMRYzZ87Eo48+ir///tsb7QkYBoMB7dq1g8Fg/xY7OmLRqZP9cygKkJLipQaST7nKAwUf5oFkzAPJmAeS6S0Pmq8KNWrUKJSWlqJ79+4ICwtDZGSkzeOFhYUea5yeKYqC2NhYh485KiwmTwZuukle3nLEIiPDi40kn3GVBwo+zAPJmAeSMQ8k01seNBcWr732mm6upetPJpMJ27ZtQ5cuXWA0Gm0eO1l+Uv3dWlhcffXZxw0GIC3NUlQMHuyDxpLXucoDBR/mgWTMA8mYB5LpLQ+aC4s77rjDC80ITM4uDeboiMW/F9gCAAwcCHzxhRcbRn6hl0vFkW8wDyRjHkjGPJBMT3lw+4Qts9mMF154ARdddBHOO+88TJo0CWfOnPFm2wKWdfC2QTEgOiwagG1hwQttEREREZHeuF1YPPfcc3jyyScRHR2NFi1a4PXXX8f999/vzbYFLOsRi4YRDWFQLB8BCwsiIiIi0jO3C4sPP/wQ77zzDlasWIHly5fjq6++wieffAKz2ezN9umWwWBASkqKy6tCyXfdZmER2FzlgYIP80Ay5oFkzAPJ9JYHt1t54MABXHvtterfAwYMgKIoOHTokFcaFgjCwsLspgkhWFgEKUd5oODFPJCMeSAZ80AyPeXB7cKiqqoKERERNtNCQ0NRWVnp8UYFArPZjOzsbLsjOqcrT8MkLINwWFgED2d5oODEPJCMeSAZ80AyveXB7atCCSFwxx13IDw8XJ1WVlaGe++9Fw0aNFCnZWZmeraFAcbRFaEAFhZEREREpG9uFxajR4+2mzZy5EiPNiYYWK8IBQCNIhqpv7dsCVx/vaXAaN3aHy0jIiIiIqo9twuL+fPne7MdQcPZEYtrr7X8EBERERHpkT6GmOuQwWBAWlqa3Sj+b3d+q/7+8ZaPkZnDU8eCgbM8UHBiHkjGPJCMeSCZ3vKgj1bqVEVFhc3fmTmZmLlupvr30dNHMXTJUBYXQaJ6Hii4MQ8kYx5IxjyQTE95YGHhJWazGbm5uTaj+KeumWozj4CAAgXT1kzzdfPIxxzlgYIX80Ay5oFkzAPJ9JYHFhY+tOPYDrtpAgK5x3Nx++1Ahw5Az55AUZEfGkdEREREVAcsLHyoU5NOUKDYTFOgIKVxCg4cAHbvBrKygGq3CyEiIiIiqvfqRWHx9ttvo02bNoiIiMD555+PjRs3urXcp59+CkVRcOONN3q3gbVkNBpt/s7on6Ge/gRYigoBgYz+GSgutswTGgpItwqhAFI9DxTcmAeSMQ8kYx5Ipqc8KEII4c8GLF68GKNGjcLs2bNx/vnnY9asWfjss8+Qm5uLxMREp8vt27cPffv2Rbt27RAfH4/ly5e79XrFxcWIi4tDUVERYmNjPdQL92XmZGLammnIPZ6LlMYpyOifgcGdB6NDB8sRi/h44PhxnzeLiIiIiMiOlm1nvxcW559/Ps477zy89dZbACyDVJKTk/HAAw9g0qRJDpcxmUy4+OKLceedd2Lt2rU4efJkvSsshBAoKSlBTEwMFEWpcf6mTYGjRy03x9u3z2vNIj/RmgcKbMwDyZgHkjEPJKsPedCy7ezXU6EqKirw559/YsCAAeo0g8GAAQMGYMOGDU6XmzZtGhITE3HXXXf5opm1YjabsWfPHrdH8ZeUWP6NifFio8hvtOaBAhvzQDLmgWTMA8n0lge377ztDceOHYPJZELTpk1tpjdt2hTbt293uMyvv/6KuXPnIisry63XKC8vR3l5ufp38b+DGUwmE0wmEwBAURQYDAaYzWbIB3Cs063z1TTdYDBAURT1uYUQMJlM6k1NqofCOr2iwowzZyznz0VHCwAKhBB28xuNRrs2OpvujT45aruzPjlqezD3yfpa1efVc5+cTWef3OuTdf0QSH1yp+3sk33brXmwPkcg9MnVdPbJdZ8A2KwfAqFPgfg5+apP8veFv/qk5eQmvxYWWpWUlOD222/H+++/jyZNmri1zIwZMzB16lS76Vu3bkV0dDQAID4+Hq1atcLBgwdRWFiozpOUlISkpCTs27cPJdZDCgCSk5PRuHFj7Ny5E2VlZer0du3aITY2Ftu2bUNVVRUKCwuxdetWpKamIiwsDNnZ2TZtSEtLQ0VFBf74YxeANACAwXAKQAxKSkqwZ88edd6IiAikpqbixIkTyMvLU6fHxMSgffv2OHr0KPLz89Xp3uiTHLaUlBSXfcrNzVWnGY1GpKWlBXWfGjRoAAAoKCjA0aNHA6JPgfg5+apPOTk56vpBUZSA6FMgfk6+6pP1VAcAAdMnIPA+J1/1qUGDBjhx4oS6fgiEPgXi5+SrPgkhUFhYiP3796Njx45+6ZOWoyV+HWNRUVGBqKgoLF261ObKTqNHj8bJkyfxxRdf2MyflZWFnj172oyOt3bWYDAgNzcX7du3t1nG0RGL5ORkFBYWqueJeeuIxa5du9ChQweEhobatFWeHwD27zejbVtLn4YMEVi2jEcsAq1PJpMJe/bsQfv27dXn03ufnE1nn2ruU0VFhbp+MBqNAdGnQPycfHnEYteuXUhJSYGiKAHRJ1fT2SfXfTKbLTdEs64fAqFPgfg5+fKIhfX7IiwszC99Ki4uRsOGDfUzeLt379548803AVje9FatWmH8+PF2g7fLysqwa9cum2lPP/00SkpK8Prrr6NTp04ICwtz+Xr+viqUI9u2AV27Wn6/4w5g/ny/NoeIiIiICIC2bWe/nwo1ceJEjB49Gueeey569+6NWbNm4fTp0xgzZgwAYNSoUWjRogVmzJiBiIgIdOvWzWb5hg0bAoDddH8zm804ceIEGjVqZLOH2pGkJGDuXMsA7tRUHzWQfEpLHijwMQ8kYx5IxjyQTG958Hthceutt6KgoACTJ09Gfn4+evToge+//14d0H3gwAFdvJHVCSGQl5enFj6uxMcDd97p/TaR/2jJAwU+5oFkzAPJmAeS6S0Pfi8sAGD8+PEYP368w8dWr17tctkFCxZ4vkFERERERKSJ/g4FEBERERFRvVMvjlgEqhg373Z35Ahw7Jjl5niJiUBEhJcbRn7hbh4oODAPJGMeSMY8kExPefD7VaF8rT5eFWrmTOCJJyy/L1sGDBni3/YQEREREQHatp15KpSXmM1m5Ofnu3VTEem+JagntQ55mJY8UOBjHkjGPJCMeSCZ3vLAwsJLhBDIz8936zbocmGho6NdpIGWPFDgYx5IxjyQjHkgmd7ywMKiHmBhQURERER6x8KiHmBhQURERER6x8LCSxRFQXx8PBRFqXFeFhaBT0seKPAxDyRjHkjGPJBMb3ngVaHqgQsvBDZssPxeWQmE8CLARERERFQP8KpQ9YDZbMaBAwc0XRUqMpJFRaDSkgcKfMwDyZgHkjEPJNNbHlhYeIkQAoWFhZquCsXToAKXljxQ4GMeSMY8kIx5IJne8sDCoh5gYUFEREREescTb+qBHTssxUVlpb9bQkRERERUOywsvERRFCQlJbk1ir9xY8sPBS4teaDAxzyQjHkgGfNAMr3lgVeFIiIiIiIih3hVqHrAZDJh9+7dMJlM/m4K1QPMA8mYB5IxDyRjHkimtzzwVCgvKpHvfOfE4cPAvHlAbCzQq5flnhYUmNzJAwUP5oFkzAPJmAeS6SkPLCz8bM8e4OmnLb8//DALCyIiIiLSJ54K5WdyEcrLzRIRERGRXrGw8BJFUZCcnFzjKH4WFsHB3TxQcGAeSMY8kIx5IJne8sBTobzEYDCgsRvXkJULC16kKnC5mwcKDswDyZgHkjEPJNNbHnjEwktMJhO2b99e4yh+HrEIDu7mgYID80Ay5oFkzAPJ9JYHFhZeVFZWVuM8LCyChzt5oODBPJCMeSAZ80AyPeWBhYWfsbAgIiIiokDAwsLPiovP/s7CgoiIiIj0ioWFlxgMBrRr1w4Gg+u3mEcsgoO7eaDgwDyQjHkgGfNAMr3lgVeF8hJFURDrxmWekpOB9HRLgREX54OGkV+4mwcKDswDyZgHkjEPJNNbHvRR/uiQyWRCdnZ2jaP4Z8wA/vrLcgfuxEQfNY58zt08UHBgHkjGPJCMeSCZ3vLAwsKL9BIC8g3mgWTMA8mYB5IxDyTTUx5YWBARERERUZ2xsCAiIiIiojpThBDC343wpeLiYsTFxaGoqMirg2GEECgrK0NERAQURXE636WXAgYD0KUL8OabXmsO+Zm7eaDgwDyQjHkgGfNAsvqQBy3bzrwqlBeFhYW5fFwIYM0ay7/yZWcpMNWUBwouzAPJmAeSMQ8k01MeeCqUl5jNZmRnZ8NsNjud5/RpS1EB8B4Wgc6dPFDwYB5IxjyQjHkgmd7ywMLCj3hzPCIiIiIKFCws/IiFBREREREFChYWfsTCgoiIiIgCBQsLLzEYDEhLS4PB4PwtZmERPNzJAwUP5oFkzAPJmAeS6S0P+milTlVUVLh8nIVFcKkpDxRcmAeSMQ8kYx5Ipqc8sLDwErPZjNzcXJej+FlYBA938kDBg3kgGfNAMuaBZHrLAwsLP2JhQURERESBgjfI86NzzgEmT7YUGOnp/m4NEREREVHtsbDwIqPR6PLx886z/FBwqCkPFFyYB5IxDyRjHkimpzwoQljv/RwciouLERcXh6KiIsTGxvq7OURERERE9ZaWbWeOsfASIQSKi4sRZHUbOcE8kIx5IBnzQDLmgWR6ywMLCy8xm83Ys2ePy1H8J08Cp04BOskK1YE7eaDgwTyQjHkgGfNAMr3lgYWFH40YYbkalNEIHD/u79YQEREREdUeCws/sl5uVgggOtq/bSEiIiIiqgsWFl4UERHh8nFrYREaCoSH+6BB5Fc15YGCC/NAMuaBZMwDyfSUB14Vyo86dAB27wbi43kqFBERERHVP7wqVD1gNptx/Phxl4NtrEcseNftwOdOHih4MA8kYx5IxjyQTG95YGHhJUII5OXlubw8GAuL4OFOHih4MA8kYx5IxjyQTG95YGHhJ1VVwJkzlt9ZWBARERGR3rGw8JNTp87+zsKCiIiIiPSOhYUXxbioGKynQQGAn8eQk4+4ygMFH+aBZMwDyZgHkukpDyH+bkCgMhqNaN++vdPH5cJCR3mhWqopDxRcmAeSMQ8kYx5Iprc88IiFl5jNZuTn5zsdxd+2LfDnn8Dq1cAjj/i2beR7NeWBggvzQDLmgWTMA8n0lgcWFl4ihEB+fr7TUfyRkcA55wD9+wNdu/q4ceRzNeWBggvzQDLmgWTMA8n0lgcWFkREREREVGcsLIiIiIiIqM44eNtLFEVBfHw8FEVx+PjffwNZWZYrQvXuDSQl+bZ95Fs15YGCC/NAMuaBZMwDyfSWB0Xo5aQtDykuLkZcXByKiooQ68frvM6YATz5pOX3zz8HbrzRb00hIiIiInJIy7YzT4XyErPZjAMHDjgdxc/LzQaXmvJAwYV5IBnzQDLmgWR6ywMLCy8RQqCwsNDpKH4WFsGlpjxQcGEeSMY8kIx5IJne8sDCwk9YWBARERFRIOHgbT9hYUFERKQPJpMJlZWVPnstIQTKyspgNBp98ppUf/kiD6GhoR57bhYWXqIoCpKSkpyO4mdhEVxqygMFF+aBZMxD/WW9OdnJkyd9+pqhoaHYv38/M0E+y0PDhg09sh5iYeElBoMBSS6uISsXFtHRPmgQ+VVNeaDgwjyQjHmov6xFRWJiIqKiorihTwFHCIHS0lIcPXoUANCsWbM6PR8LCy8xmUzYt28f2rRp4/DwkrWwiIoCeKQz8NWUBwouzAPJmIf6yWQyqUVF48aNffa6QgiUl5cjPDychQz5JA+RkZEAgKNHjyIxMbFO6yEO3vaiEvmwhN1jln95GlTwcJUHCj7MA8mYh/rHOqYiKirK56+tl0uLkm/4Ig/WnNd1LBELCz+Ji7P8NGzo75YQERGRMzxqQMHAUzlnYeEnW7YAJ08COTn+bgkRERFRzZKSkjB79my35//++++hKArKysq82CqqT1hYeImiKEhOTq6xAuSOkODgbh4oODAPJGMeqLqwsLBaLacoisufKVOm1Kld2dnZGD16tNvzX3bZZTh8+DAiIiLq9LruEkKgbdu2iIyMxPHjx33ymr5Q2zz4Awdve4nBYPDpYC+q35gHkjEPJGMeSKYoCkJCard5dvjwYfX3xYsXY/LkycjNzVWnRTu4DKUQAiaTya3XTEhI0NSesLAwn17xbOXKlQgNDcV1112Hjz/+GA899JDPXtuRioqKOhcFdcmDP/CIhZeYTCZs374dJpPJ302heoB5IBnzQDLmIbBlZgLduwORkZZ/MzNdzy+EwJkzZyCE0PxaSUlJ6k9cXJx6jxTrT3R0tHp60g8//IAePXogLCwMf/zxB7Zv346BAwciMTERMTExuOCCC7B69Wq757eeClVWVgZFUfDBBx9g4MCBiIqKQkpKCr777jt1/uqnQs2ePRtJSUn4+uuvkZKSgpiYGAwcOBAFBQXqMhUVFbjvvvsQGxuLJk2a4JlnnsGwYcMwbNiwGvs/d+5cjBgxAiNHjsTcuXPtHj9z5gweeeQRtGzZEuHh4ejUqRM++ugj9fEtW7bgmmuuQUxMDGJjY9G/f38cOHAAAHDBBRdg0qRJNs939dVX495777V5f2bOnInbbrsNMTExePDBBwEADz/8MDp27IjIyEi0b98e06ZNQ1VVlc1zZWZm4pxzzkFERAQSExPV/j7xxBM455xz7PLQuXNnPPfcczW+J77GwsKLnJ1TuGcPcPPNwJ13AosX+7hR5Dc8x5RkzAPJmIfAlJkJDB0KZGcDZWWWf4cOda+48LYnnngCr732GnJycpCamopTp07hxhtvxKpVq/Dnn3/i4osvxsCBA22OgjiSkZGB0aNHY8uWLbj00ktx2223obi42On8J0+exFtvvYVFixZh1apVyM3Ntdlgf/bZZ7Fs2TJ88sknWLt2LQ4dOmRTrDhTWFiI5cuXY+TIkbj22mvxzz//4Pfff7eZZ9iwYcjMzMQ777yDnJwcvP322+qlVvft24d+/fohLi4Oq1evxsaNGzFq1CjNV0l64YUXcP755yMrKwuPPfYYAMvN5z766CPk5OTglVdewZtvvol33nlHXSYzMxO33HILhgwZgqysLKxYsQI9e/YEANx1113IyspCdna2Ov+GDRuwY8cOTael+Yp+jq0EkEOHgKVLLb83agTceqt/20NERETue/VVy09NiostYymtdYL131tvBZo2db6cEBGYOBF45JG6t9WZ559/Hpdeeqn697nnnotzzz1X/fvFF19EZmYmvvnmG9x9991On2fs2LG4+eab1ed87733sGnTJlxyySUO5y8vL8fcuXPRokULAMB9992HN954Q338rbfewrPPPotBgwYBsBzlcKew+OSTT9CjRw+0b98eAHDzzTdj7ty5OO+88wBYjkZ8+eWXWLt2Lfr27QsAaNeunbr8G2+8gWbNmuGTTz5R7+OQmppa4+tWd/XVV9udgpWRkaH+3qZNG/z9999YsmSJekRj+vTpuOOOO/D000+r81kLi/bt26Nfv36YP38+XnvtNQDA/PnzceWVV6Jly5aa2+dt9eKIxdtvv402bdogIiIC559/PjZu3Oh03vfffx/9+vVDo0aN0KhRIwwYMMDl/PWRfLly3seCiIhIX4qLgX/+qfnn1KmzxYSsqsrVcgoOHTLAxU5/j5CLCAAoKirChAkTkJqaioYNGyI6Ohp79+5VTwVyJj09Xf09Pj4eYWFh6l2cHYmPj1eLCsByp2fr/EeOHMHJkyfRu3dv9fHQ0FD06NGjxv7MmzcPI0eOVP8eOXIkFi1ahDNnzgAAsrKyEBERgYsuusjh8llZWejfv3+db1JZ/X0FgI8//hh9+vRB06ZNER0djenTp6vvqxACW7ZsweWXX+70OceMGYNPPvkElZWVOHPmDJYsWYI777yzTu30Fr8XFosXL8bEiRORkZGBTZs2oXv37rjqqquchnL16tUYPnw4Vq1ahQ0bNiA5ORlXXnkl/vnnHx+33DWDwYB27drBYLB/i1lYBB9XeaDgwzyQjHnQn9hYoEWLmn+iox1f/TEkxNVyAi1aCMTGercPDRo0sPn7oYcewnfffYeZM2di7dq1yMrKQqdOnVBRUeHyeUJDQ23+VhTF5Q3dtM7vjk2bNiErKwsPPfQQQkJCEBISgksuuQTFxcVY+u8pItZTnpyp6XGDwWB3ipqj06Sqv6+rVq3CHXfcgcGDB+Pbb7/F5s2b8Z///Ed9XxVFqfGqWbfccgtMJhO+/vprZGZmIiQkBDfccIPLZfzF72uxV199FWPHjsWYMWPQpUsXzJ49G1FRUZg3b57D+T/55BOMGzcOPXr0QGpqKubMmQOz2YyVK1f6uOWuKYqC2NhYh5cPZGERfFzlgYIP80Ay5kF/Jk4EDh6s+WfBAssRC+tHa/13yRJXyyk4eFDBI4/4Ng/r1q3D3XffjRtvvBFpaWlo0qQJ8vLyfNqGpk2bomHDhjZjIyorK5GVleVyublz52LAgAHIysqy+Rk/frw6iDs9PR1lZWVYt26dw+dIT0/HmjVrnF5EISEhwWa8SWVlJbZt21Zjn9avX4+UlBQ89thj6NWrFzp27Ih9+/bZzJOWluZ0O1ZRFERFRWHkyJGYP38+5s+fjxEjRtTbS9D6tbCoqKjAn3/+iQEDBqjTDAYDBgwYgA0bNrj1HKWlpaisrER8fLy3mlkrJpMJ2dnZDgPKwiL4uMoDBR/mgWTMQ+AaMgRYtgxITwciIiz/ZmYCgwc7X0YIgdLSUp8M4JZ17NgRn332GbZs2YLNmzfjtttu88tRtPHjx2PatGn45ptvsH37dowbNw6nT592WniXlZVh4cKFGDFiBLp162bzc+edd+KXX37Brl27kJKSgmHDhuH222/HV199hb179+Lnn3/GsmXLAAATJkxAfn4+RowYgU2bNmHnzp1YsGABdu/eDcByT47ly5djxYoVyMnJwdixY1FaWlpjfzp27Ihdu3Zh2bJl2L17N1555RV88803NvNkZGRgwYIFmD59OrZv344tW7bg5ZdfBnA2D3fddRe+++47rFq1qt6eBgX4efD2sWPHYDKZ0LTaCKamTZti+/btbj3H448/jubNm9sUJ7Ly8nKUl5erf1uvVGAymdSVuKIoMBgMMJvNNv+RrdOrr+ydTTcYDFAURX3uqqoqmEwm9T+m9VBfUZECa00XHS1gMtkeAjQajRBC2B0aNBqNdm10Nt0bfao+Xe5TTdODvU/WTFSfV899cjadfXKvT9b1QyD1yZ22s0/2bbfmwfocgdAnV9P10ifAslFn/ZHb42ij39n0IUMUDB5sO91yFMPx/PJr15b83M7aLvdLURS8/vrruPvuu3HBBRcgMTERTz75JAoLC+36X/15qz+PPK36co7aVH3a008/jaNHj2L48OEICwvDvffei0suuQQREREO35Nly5bh1KlTGDRokF1fe/TogbZt22Lu3Ll4/vnn8f777+PJJ5/E2LFjcfLkSbRu3RrPPPMMhBBo2rQpVq5ciccffxx9+/ZFaGgozjnnHFx22WUQQuD//u//kJ2drbbr8ccfR35+vst+AsBNN92EdevW4Z577kFlZSWuv/56TJo0SR2ILYTAVVddhY8//hjPP/88nn32WcTFxWHAgAE2z9WtWzf07NkTJpMJ6enpdcqko+ny+kj+P+XoFDBXFOHrklhy6NAhtGjRAuvXr0efPn3U6Y899hjWrFmD//3vfy6XnzlzJl588UWsXr3aZvCQbMqUKZg6dard9LVr16o3iomPj0erVq1w4MABFBYWqvNYr/u8e/dulEiHGZKTk9G4cWNs377d5hKB7dq1Q2xsLLKzs1FVVYXCwkLEx8cjNTUVYWFh6qXCZs1qhg8+sBRTK1aUIzExR30Oo9GItLQ0FBcXY8+ePer0iIgIpKam4vjx4zaHJmNiYtC+fXvk5+cjPz9fne6NPslBS0lJsemTVVpaGioqKmxuyMM+Wc65PH36NBITE23GD+m5T4H4OfmqT3/99ReOHTuG+Ph4KIoSEH0KxM/JV30SQqCkpAQXXXQRCgoKAqJPgP4/pzZt2mDXrl1o0aIFwsPDAVg2siIiIlBZWWlzfr3RaER4eDjKy8tt2hIaGorQ0FCUlZXZFC5hYWEICQmxu19FeHg4DAYDSkpKbG6KFhERAUVR1IHIVpGRkRBC2F2uOCoqCiaTyWbHqqIoiIyMRFVVlc24CV/0yWg02u3dd7dPJpMJaWlpGDt2LCZNmhQQfbJy93OqqqqC0WhE586d8eijj+Kuu+7yeJ+EEDhw4AAqKytt5k9JSUFZWRni4+NRVFSE2BoG//i1sKioqEBUVBSWLl2KG2+8UZ0+evRonDx5El988YXTZV9++WVMnz4dP/30k8MR+FaOjlgkJyejsLBQfXO8dcRi69at6Nq1qzpQyfpB3X+/gvfes+w5+eMPgR49gnePULD0yWQyYdu2bejatavNoWU998nZdPap5j5VVFSo6wej0RgQfQrEz8mXRyy2bt2K9PR0uz2Jeu2Tq+l66VNlZSX27NmDtm3b2gyu9cTeYVfTAcuN3KwbqbXh7TZ6sq/V7d69G2vWrEG/fv1w5swZzJo1C4sWLcLWrVttLg/r77Zr6ZMz7jy3EAJ5eXlYsmQJnnvuORw4cAAx1c6j90Tby8rKsG/fPrRq1com7waDAcXFxWjYsKFbhYVfT4UKCwtDr169sHLlSrWwsA7EHj9+vNPlXnzxRTz33HNYsWKFy6ICsFSV1j0NMqPRaHdJMWfnEjq79Jir6QaDAampqQgNDVVXDNb5T506O29srOLweRTF8XRnbdQ6vTZ9quv0YO6TwWBASkoKQkJCHH5R6LFPtZ3OPln2JFVfP2h9nvrWp0D8nHzVJ+v3hXVD2RG99aku0+tLnyorK6EoivpTfX5HPDFdCKEWFbUtLLzdRk9Or85gMGDOnDl4+OGHoSgK0tPT8fPPP6v3p/BHG+vaJ1dqeu6ysjK0adMGiYmJmDNnjtMN+7q2Xd5Wrf5/QUs//X6DvIkTJ2L06NE499xz0bt3b8yaNQunT5/GmDFjAACjRo1CixYtMGPGDACWOxpOnjwZCxcuRJs2bdTDq9HR0eqpTfWFsxH7F19sudRcSQnQuLGPG0V+U1+v4ED+wTyQjHkgmSc2WPWqXbt2bl/AJxhERESoR9P0kAu/X2721ltvxcsvv4zJkyejR48eyMrKwvfff68O6D5w4IDN5b3effddVFRU4KabbkKzZs3UH+vo+frCbDYjOzvb4WCwe+6xXIJu2TKgnl3MirzEVR4o+DAPJGMeqLrq5+hTcNNTHvx+xAKwXFrM2alPq1evtvm7+rV/iYiIiIjI//x+xIKIiIiIiPSPhQUREREREdUZCwsvMRgMSEtLc3jViyZNLIO2r7jCDw0jv3CVBwo+zAPJmAeqLjIy0t9NoHpET3ngWsyL5Ju1WJnNwPHjQGEh8O9NwClIOMoDBS/mgWTMA8n8eIsxqof0lAcWFl5iNpuRm5trd5WP06fP/l7Pro5LXuQsDxScmAeSMQ9UXfU7NPvDyJEjcdNNN6l/9+3bF//5z39cLtOyZUu89dZbdX5tTz1PoKgPeXAXCwsfKyk5+3u1GycSERER1dqgQYNw9dVXO3xs7dq1UBQFW7ZsqdVzf/nll8jIyKhL8+zMmTMHTZo0sZu+efNm3HnnnR59LWeEEOjQoQMiIiJw9OhRn7xmIGNh4WMsLIiIiMgb7rrrLvz44484ePCg3WPz58/Hueeei/T09Fo9d3x8PGJ8tOGSkJCAqKgon7zWmjVrYDabceONN+Kjjz7yyWu6ovfTIllYeFH1W6IDLCyCmaM8UPBiHkjGPASuzJxMdJ/dHZHTI9F9dndk5mR67bUGDhyIhIQELFiwwGb6qVOn8Nlnn+Guu+4CAFRWVuLOO+9EmzZtEBkZiZSUFLz55psun7v6qVD5+fkYOHAgIiMj0a5dO3z66ad2y7z00kvo1q0boqKikJycjPHjx+P0v+eE//TTTxg7diyOHz8ORVGgKAqmT58OwP5UqH379uH6669HgwYNEBcXh2HDhqGgoEB9/Omnn8a5556LDz74AK1bt0ZcXBxGjBiBU6dO1fiezZ07FyNGjMDIkSMxd+5cu8fLysrw6KOPomXLloiIiEDHjh1t3t+///4b1157LWJjYxEbG4uLL74Ye/fudfieAZbP6O6771b/btmyJZ5//nmMHDkSsbGxGDduHADgP//5Dzp27IioqCh07doVGRkZqKqqsnmu5cuXo1evXoiIiEBCQgJuvvlmAFBvOl1dt27dMHXq1Brfk7pgYeElRqMRaWlpdl8WLCyCk7M8UHBiHkjGPASuzJxMDF0yFNlHslFmKkP2kWwMXTLUZXGhKAqioqKgKIrm1wsJCcGoUaOwYMECmwG/n332GUwmE4YPHw4AMJlMaNWqFZYuXYpt27bh6aefxuOPP47MTPeLnlGjRuHQoUNYs2YNFi9ejNdffx3Hjx+3a89bb72Fbdu2YcGCBfjhhx/wxBNPAAAuvvhivPLKK4iPj8fhw4dx+PBhPPzww3avYzabcf3116O4uBhr167FihUrkJubq/bFKjc3F9988w2++eYbfPnll/jpp5/w0ksvuexDUVERli1bhpEjR+Lqq69GQUEBNmzYYDPPiBEjsGTJErz99tvYtm0b3nnnHfVoyoEDB9CvXz80aNAAq1atwu+//4477rjDrgCoyYsvvohevXph8+bNePLJJwEAcXFx+PDDD5GTk4NZs2bhvffewxtvvKEu8+WXX+Kmm27C9ddfj82bN+PHH39Er169AAB33nkntmzZgs2bN6vz//7778jJycEdd9yhqW1a1Ys7bwciIQRKSkoQExNjs3L44Yez83zwAXD++cCQIX5oIPmUszxQcGIeSMY86Mu5/z0X+afy3Zr3yOkjAAABYfPvrUtvRdMGTd1+zaToJPxxzx9uzXvnnXfipZdewpo1a3DJJZcAsJwGNXToUMTFxQEAIiIiMGXKFHWZtm3bYt26dViyZAmGuLFRsm3bNvz444/YtGkTevbsCQB4//33kZaWZjOfXCi0adMG06ZNw4QJE/DGG28gLCwMsbGxUBQFSUlJTl9rxYoVyMnJwf79+9G8eXMAwAcffIDu3btj8+bN6utb+9mgQQMAloJg5cqVLvfQL1y4EF27dkVKSgoA4NZbb8XcuXPRp08ftZ+ZmZlYtWqV+l62a9dOXf6tt95CkyZNsGjRIoSEWDaprc+lxRVXXGFXVD3zzDMALOuH5ORkTJgwAUuWLMHEiRMBANOnT8fIkSNtxr1Yj1K0adMGAwYMwPz589X3Z/78+bjsssvQunVrze3TgkcsvMRsNmPPnj02V/nIzARmzjw7z5EjwNChlukU2BzlgYIX80Ay5kFf8k/l45+Sf9z6qTI73nNdZa5y+zn+KfnH7UIGAFJTU3HhhRdi3rx5AIBdu3Zh7dq16mlQVm+++SZ69eqFJk2aIDo6GvPmzcOBAwfceo2cnByEh4fbnG7TrVs3uzEYP/zwAy677DI0b94c0dHRGDNmDI4cOYLy8nK3+5OTk4M2bdqoRQUApKenIzo6Gjk5Oeq0du3aqUUFADRr1qzGwdjz5s3DyJEj1b9HjhyJxYsXq6drZWVlITQ0FP369XO4fFZWFi6++GK1qKitc889127aokWLcOGFFyIpKQlxcXGYOnWqzeeTlZWFyy+/3Olzjh07FgsXLkRFRQXKy8vx6aef+mRAPAsLH5o6Fai+M0pRgGnT/NMeIiIi0iYpOgktYlq49RNicLzBGWIIcblc8+jmNn8nRTvfo+/IXXfdhWXLlqGkpATz589H+/bt0b9/f/Xxjz/+GI8//jjGjh2LH3/8EVlZWRg1apRHBw7v3r0bgwYNQs+ePfH5559j06ZN6qk8lZWVHnsdq9DQUJu/FUVxWaxv2bIFf/zxByZOnIiQkBCEhISgb9++OHXqFJYsWQKg5hvT1fS4wWCwuweFo77LBRFguYLX7bffjuuvvx5ff/011q9fj8cee8zm86lpcPsNN9wAg8GAL774AsuXLwcADB482OUynsBToXxoxw6g+j1OhAByc/3THiIiItLG3VOSgLNjLBQoEBDqv0tuWoLBnR1v5AkhcObMGURGRtb61LhbbrkFDz30EBYuXIgPP/wQ9913n81zrVu3Dv369cO9996rTtu1a5fbz9+5c2eUl5cjKytLPdVm69atKJEGkv7xxx9QFAWvvPKKOm3hwoU2zxMWFgaTyVTja+3btw+HDh1Sj1ps2bIFp06dQpcuXdxuc3Vz587FpZdeajNuAbBcAnfu3LkYM2YM0tLSUFlZibVr16qnQsnS09Px6aefoqqqyuFRi4SEBBw+fFj9u6qqClu3bkVycrLLtq1fvx7t27fHpEn/396dx0R1tWEAf4ZtABEH2VGpqFRQ1Ci44NKmQkRqtCjaqiMBqyKKe9q6VbH1s7i0tnEpFlOtDVaU1gWNtKWgGI0iIriURVOpEhFxQxAVlTnfH4bpXEGLHWYGmOeXTMLce5x5x/uI8+bec+4idR5ePJvUo0cPpKWlISwsrN7XsLCwQFhYGLZv3w6VSoUJEybA0tLyle/bGHjGQodePIBvvln/GYv/cDkeNUP6+AdNzQfzQJqYh5ZpjPcY/PL+L+jp3BOWZpbo6dwTe9/f+9Kmopa2c21sbGzwwQcfYPHixbhx40adCbuenp7IzMxEamoqLl26hCVLlkgm+v6bbt26ITAwENOmTUNWVhbOnDmDyMhISY67dOmC6upqbNq0CVeuXMGOHTsQHx8veZ2OHTvi/v37OHr0KG7fvo1Hjx7Vea+goCB4e3tDqVQiJycHp06dQkREBAICAupd+aghqqurkZCQgIkTJ8LHx0fymDJlCk6cOIHCwkJ06dIFkyZNQkREBA4cOICioiIcOXIESUlJAIA5c+bgzp07mDhxIrKzs3H58mXs2LEDly9fBgAMHToUycnJSElJQUFBAaZPny5pvl7G09MTRUVF2LNnD/766y9s3rwZycnJkjExMTFISEjA559/joKCAly4cAFr166VjJk6dSp+//13pKam6u2+IGwsdMTU1BReXl6SVT5iYp6foaj9fSGTPX/eyPeboSaovjyQ8WIeSBPz0LKN8R6D3KhcPFr6CLlRuQ1qKrQ5W1FrypQpuHfvHoKCgiTzEwBg5syZGDVqFMaNG4cBAwagoqIC06dPf63X//HHH+Hk5IQhQ4Zg7NixiI6Ohr29vXq/r68v1q1bh1WrVsHHxwe7d+9GbGys5DWGDBmCqVOnYuzYsXB0dJSc3ahlYmKC5ORk2NjYYPDgwQgKCsKbb76JXbt2vVa9mvbv34/79+8jJCSkzr4ePXrA09NTvfRsfHw8QkJCEBUVBS8vL0yfPl3dADk6OiI9PR3l5eV466234Ovri+3bt6svy5o2bRomTZoEpVKJt99+G97e3i+dr6Fp9OjRmD17NmbOnIk+ffogJycHS5culYwJDAxEYmIifvnlF/Tq1QsBAQHIzs6WjPH29ka/fv3g4+OjXjFK12TixYu/WriKigq0adMG9+/fh62trc7eR6VS4d69e7Czs4OJyT/92969z+dUFBY+P1MREwPo4ZI3MrCX5YGME/NAmpiHpunx48coKiqCh4eHXs8oCSFQU1MDU1NTrhJGWuVBpVKhc+fOmD9/PubMmfPKsa/K++t8d+YcCx0RQqC4uBgKhUKyfcwYLi9rjF6WBzJOzANpYh7oRU+ePPnXicFkPP5LHm7duoWdO3fizp07CA8P11FldbGxICIiIiJqIZ49ewYnJyc4Ojpi69at6vuX6AMbCyIiIiKiFsLMzKzOMrf6wos5dejFG8WQcWMeSBPzQJqYB9LEuTakqTnlgWcsdMTU1BSdO3c2dBnURDAPpIl5IE3MA2mSyWRcfpjUmlsemk8L1MyoVCqUlpa+8q6PZDyYB9LEPJAm5qFp0/clJUIIPH361GCXslDToq88NNbrs7HQESEESktL+YuBADAPJMU8kCbmoWmqvRfBw4cP9f7eT58+1ft7UtOljzzU5rw29/8VL4UiIiIieoGpqSkUCgXKysoAANbW1nq5r4QQAtXV1ZDJZLyPBek8D0IIPHz4EGVlZVAoFFrfqJONBREREVE9XFxcAEDdXOhD7aUv5ubmbCxIb3lQKBTqvGuDjYWOyGQytG3blr8UCADzQFLMA2liHpoumUwGV1dXODk56e3ypNo5Ny4uLs1qNSDSDX3kwdzcXOszFbVkwsgu6nyd25ITERERERmz1/nuzFZYR1QqFa5du8ZVPggA80BSzANpYh5IE/NAmppbHthY6IgQAnfv3uUqHwSAeSAp5oE0MQ+kiXkgTc0tD2wsiIiIiIhIa0Y3ebu246uoqNDp+9TU1ODBgweoqKhotAkx1HwxD6SJeSBNzANpYh5IU1PIQ+135oacNTG6xqKyshIA0KFDBwNXQkRERETUPFRWVqJNmzavHGN0q0KpVCqUlJSgdevWOl3ar6KiAh06dEBxcTFXnyLmgSSYB9LEPJAm5oE0NYU8CCFQWVkJNze3f13y1ujOWJiYmKB9+/Z6ez9bW1v+YiA15oE0MQ+kiXkgTcwDaTJ0Hv7tTEUtTt4mIiIiIiKtsbEgIiIiIiKtsbHQEblcjpiYGMjlckOXQk0A80CamAfSxDyQJuaBNDW3PBjd5G0iIiIiImp8PGNBRERERERaY2NBRERERERaY2NBRERERERaY2OhI5s3b0bHjh1haWmJ/v374/Tp04YuifQgNjYWffv2RevWreHk5ISQkBAUFhZKxjx+/BjR0dGwt7eHjY0NQkNDcfPmTQNVTPqyevVqyGQyzJs3T72NWTA+169fx6RJk2Bvbw8rKyv06NEDZ86cUe8XQmD58uVwdXWFlZUVAgMDcfnyZQNWTLpSU1ODZcuWwcPDA1ZWVujcuTNWrlwJzamvzEPLdezYMYwcORJubm6QyWTYv3+/ZH9Djv3du3ehVCpha2sLhUKBKVOm4MGDB3r8FHWxsdCB3bt3Y8GCBYiJicHZs2fRq1cvBAUFoayszNClkY5lZGQgOjoap06dQmpqKp4+fYphw4ahqqpKPWb+/Pk4ePAgkpKSkJGRgZKSEowZM8aAVZOuZWVl4bvvvkPPnj0l25kF43Lv3j0MGjQI5ubmSElJQV5eHr766ivY2dmpx6xduxYbNmzAli1bkJmZiVatWiEoKAiPHz82YOWkC2vWrEFcXBw2bdqE/Px8rFmzBmvXrsXGjRvVY5iHlquqqgq9evXC5s2b693fkGOvVCrx559/IjU1FYcOHcKxY8cQGRmpr49QP0GNrl+/fiI6Olr9vKamRri5uYnY2FgDVkWGUFZWJgCIjIwMIYQQ5eXlwtzcXCQlJanH5OfnCwDi5MmThiqTdKiyslJ4enqK1NRU8fbbb4u5c+cKIZgFY7Rw4UIxePDgl+5XqVTCxcVFrFu3Tr2tvLxcyOVysWvXLn2USHo0YsQI8eGHH0q2jRkzRiiVSiEE82BMAIh9+/apnzfk2Ofl5QkAIisrSz0mJSVFyGQycf36db3V/iKesWhkT548QXZ2NgIDA9XbTExMEBgYiJMnTxqwMjKE+/fvAwDatm0LAMjOzsbTp08l+fDy8oK7uzvz0UJFR0djxIgRkmMOMAvGKDk5GX5+fhg3bhycnJzQu3dvbN26Vb2/qKgIpaWlkky0adMG/fv3ZyZaoIEDByItLQ2XLl0CAJw7dw7Hjx9HcHAwAObBmDXk2J88eRIKhQJ+fn7qMYGBgTAxMUFmZqbea65lZrB3bqFu376NmpoaODs7S7Y7OzujoKDAQFWRIahUKsybNw+DBg2Cj48PAKC0tBQWFhZQKBSSsc7OzigtLTVAlaRLiYmJOHv2LLKysursYxaMz5UrVxAXF4cFCxZgyZIlyMrKwpw5c2BhYYHw8HD1ca/v/w9mouVZtGgRKioq4OXlBVNTU9TU1GDVqlVQKpUAwDwYsYYc+9LSUjg5OUn2m5mZoW3btgbNBxsLIh2Jjo7GxYsXcfz4cUOXQgZQXFyMuXPnIjU1FZaWloYuh5oAlUoFPz8/fPHFFwCA3r174+LFi9iyZQvCw8MNXB3p2549e7Bz50789NNP6N69O3JzczFv3jy4ubkxD9Rs8VKoRubg4ABTU9M6K7vcvHkTLi4uBqqK9G3WrFk4dOgQjhw5gvbt26u3u7i44MmTJygvL5eMZz5anuzsbJSVlaFPnz4wMzODmZkZMjIysGHDBpiZmcHZ2ZlZMDKurq7o1q2bZJu3tzeuXbsGAOrjzv8/jMPHH3+MRYsWYfz48ejRowfCwsIwf/58xMbGAmAejFlDjr2Li0udRYGePXuGu3fvGjQfbCwamYWFBXx9fZGWlqbeplKpkJaWBn9/fwNWRvoghMCsWbOwb98+pKenw8PDQ7Lf19cX5ubmknwUFhbi2rVrzEcLExAQgAsXLiA3N1f98PPzg1KpVP/MLBiXQYMG1Vl++tKlS3jjjTcAAB4eHnBxcZFkoqKiApmZmcxEC/Tw4UOYmEi/hpmamkKlUgFgHoxZQ469v78/ysvLkZ2drR6Tnp4OlUqF/v37671mNYNNG2/BEhMThVwuFz/88IPIy8sTkZGRQqFQiNLSUkOXRjo2Y8YM0aZNG3H06FFx48YN9ePhw4fqMVFRUcLd3V2kp6eLM2fOCH9/f+Hv72/AqklfNFeFEoJZMDanT58WZmZmYtWqVeLy5cti586dwtraWiQkJKjHrF69WigUCnHgwAFx/vx58d577wkPDw/x6NEjA1ZOuhAeHi7atWsnDh06JIqKisTevXuFg4OD+OSTT9RjmIeWq7KyUuTk5IicnBwBQKxfv17k5OSIq1evCiEaduyHDx8uevfuLTIzM8Xx48eFp6enmDBhgqE+khBCCDYWOrJx40bh7u4uLCwsRL9+/cSpU6cMXRLpAYB6H9u3b1ePefTokZg5c6aws7MT1tbWYvTo0eLGjRuGK5r05sXGglkwPgcPHhQ+Pj5CLpcLLy8vER8fL9mvUqnEsmXLhLOzs5DL5SIgIEAUFhYaqFrSpYqKCjF37lzh7u4uLC0tRadOncTSpUtFdXW1egzz0HIdOXKk3u8L4eHhQoiGHfs7d+6ICRMmCBsbG2FraysmT54sKisrDfBp/iETQuMWj0RERERERP8B51gQEREREZHW2FgQEREREZHW2FgQEREREZHW2FgQEREREZHW2FgQEREREZHW2FgQEREREZHW2FgQEREREZHW2FgQEREREZHW2FgQEVGzIpPJsH//fkOXQUREL2BjQUREDRYREQGZTFbnMXz4cEOXRkREBmZm6AKIiKh5GT58OLZv3y7ZJpfLDVQNERE1FTxjQUREr0Uul8PFxUXysLOzA/D8MqW4uDgEBwfDysoKnTp1ws8//yz58xcuXMDQoUNhZWUFe3t7REZG4sGDB5Ix27ZtQ/fu3SGXy+Hq6opZs2ZJ9t++fRujR4+GtbU1PD09kZycrN537949KJVKODo6wsrKCp6ennUaISIianxsLIiIqFEtW7YMoaGhOHfuHJRKJcaPH4/8/HwAQFVVFYKCgmBnZ4esrCwkJSXhjz/+kDQOcXFxiI6ORmRkJC5cuIDk5GR06dJF8h6fffYZ3n//fZw/fx7vvvsulEol7t69q37/vLw8pKSkID8/H3FxcXBwcNDfXwARkZGSCSGEoYsgIqLmISIiAgkJCbC0tJRsX7JkCZYsWQKZTIaoqCjExcWp9w0YMAB9+vTBt99+i61bt2LhwoUoLi5Gq1atAACHDx/GyJEjUVJSAmdnZ7Rr1w6TJ0/G//73v3prkMlk+PTTT7Fy5UoAz5sVGxsbpKSkYPjw4Rg1ahQcHBywbds2Hf0tEBFRfTjHgoiIXss777wjaRwAoG3btuqf/f39Jfv8/f2Rm5sLAMjPz0evXr3UTQUADBo0CCqVCoWFhZDJZCgpKUFAQMAra+jZs6f651atWsHW1hZlZWUAgBkzZiA0NBRnz57FsGHDEBISgoEDB/6nz0pERA3HxoKIiF5Lq1at6lya1FisrKwaNM7c3FzyXCaTQaVSAQCCg4Nx9epVHD58GKmpqQgICEB0dDS+/PLLRq+XiIj+wTkWRETUqE6dOlXnube3NwDA29sb586dQ1VVlXr/iRMnYGJigq5du6J169bo2LEj0tLStKrB0dER4eHhSEhIwDfffIP4+HitXo+IiP4dz1gQEdFrqa6uRmlpqWSbmZmZeoJ0UlIS/Pz8MHjwYOzcuROnT5/G999/DwBQKpWIiYlBeHg4VqxYgVu3bmH27NkICwuDs7MzAGDFihWIioqCk5MTgoODUVlZiRMnTmD27NkNqm/58uXw9fVF9+7dUV1djUOHDqkbGyIi0h02FkRE9Fp+/fVXuLq6SrZ17doVBQUFAJ6v2JSYmIiZM2fC1dUVu3btQrdu3QAA1tbW+O233zB37lz07dsX1tbWCA0Nxfr169WvFR4ejsePH+Prr7/GRx99BAcHB4wdO7bB9VlYWGDx4sX4+++/YWVlhSFDhiAxMbERPjkREb0KV4UiIqJGI5PJsG/fPoSEhBi6FCIi0jPOsSAiIiIiIq2xsSAiIiIiIq1xjgURETUaXl1LRGS8eMaCiIiIiIi0xsaCiIiIiIi0xsaCiIiIiIi0xsaCiIiIiIi0xsaCiIiIiIi0xsaCiIiIiIi0xsaCiIiIiIi0xsaCiIiIiIi0xsaCiIiIiIi09n8Y3nU5yLYflgAAAABJRU5ErkJggg==", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "\n", "# Assuming you have a model training history object `hist`\n", "# For example:\n", "# hist = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=60, batch_size=128)\n", "\n", "# Extract metrics\n", "history = hist.history\n", "epochs = range(1, len(history[\"loss\"]) + 1)\n", "\n", "# Set up the plot style\n", "plt.style.use('_classic_test_patch') # Professional style\n", "\n", "# Create the figure\n", "plt.figure(figsize=(8, 5))\n", "\n", "# Plot training and validation accuracy\n", "plt.plot(epochs, history['accuracy'], label='Training Accuracy', color='blue', markersize=4,marker='o', linestyle='--', linewidth=2)\n", "plt.plot(epochs, history['val_accuracy'], label='Validation Accuracy', color='green', markersize=4,marker='o', linestyle='-', linewidth=2)\n", "plt.title('Proposed ENeTAMIB Model', fontsize=13, fontweight='bold')\n", "plt.xlabel('Epochs', fontsize=10)\n", "plt.ylabel('Proposed Accuracy', fontsize=10)\n", "plt.legend(loc='lower right', fontsize=10)\n", "plt.grid(alpha=0.6, linestyle='--')\n", "\n", "# Adjust layout for better spacing\n", "plt.tight_layout()\n", "plt.savefig(\"SK_LC_ACC-5k\", bbox_inches='tight',dpi=300)\n", "# Show the plot\n", "plt.show()\n" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "\n", "# Assuming you have a model training history object `hist`\n", "# For example:\n", "# hist = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=60, batch_size=128)\n", "\n", "# Extract metrics\n", "history = hist.history\n", "epochs = range(1, len(history[\"loss\"]) + 1)\n", "\n", "# Set up the plot style\n", "plt.style.use('_classic_test_patch') # Professional style\n", "\n", "# Create the figure\n", "plt.figure(figsize=(8, 5))\n", "\n", "# Plot training and validation accuracy\n", "plt.plot(epochs, history['loss'], label='Training Loss', color='red', markersize=4,marker='o', linestyle='--', linewidth=2)\n", "plt.plot(epochs, history['val_loss'], label='Validation Loss', color='orange', markersize=4,marker='o', linestyle='-', linewidth=2)\n", "plt.title('Proposed ENeTAMIB Model', fontsize=13, fontweight='bold')\n", "plt.xlabel('Epochs', fontsize=10)\n", "plt.ylabel('Proposed Loss', fontsize=10)\n", "plt.legend(loc='best', fontsize=10)\n", "plt.grid(alpha=0.6, linestyle='--')\n", "\n", "# Adjust layout for better spacing\n", "plt.tight_layout()\n", "plt.savefig(\"SK_LC_LOSS-5k\", bbox_inches='tight',dpi=300)\n", "# Show the plot\n", "plt.show()\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import numpy as np\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "from sklearn.metrics import confusion_matrix\n", "\n", "# Assuming y_true and y_pred are your true labels and predicted labels\n", "y_true = rounded_labels # Replace with your true labels (for 57 classes)\n", "y_pred_classes = classes # Replace with your predicted labels (for 57 classes)\n", "\n", "# Generate confusion matrix for 57 classes\n", "cm = confusion_matrix(y_true, y_pred_classes)\n", "\n", "# Set up the figure size for a larger matrix\n", "plt.figure(figsize=(15, 12))\n", "\n", "# Create the heatmap with reduced font size\n", "sns.set(font_scale=0.8) # Reduced font scale for smaller font size\n", "sns.heatmap(cm, annot=True, fmt='g', cmap='Oranges', cbar=True,\n", " xticklabels=[f'Class {i}' for i in range(1, 58)], # Label for 57 classes\n", " yticklabels=[f'Class {i}' for i in range(1, 58)], # Label for 57 classes\n", " linewidths=0.5, linecolor='black')\n", "\n", "# Add labels and title with smaller font size\n", "plt.xlabel('Predicted Labels', fontsize=10)\n", "plt.ylabel('True Labels', fontsize=10)\n", "plt.title('Confusion Matrix (57 Classes)', fontsize=12)\n", "\n", "# Rotate the x and y labels to avoid overlap with smaller font\n", "plt.xticks(rotation=90, fontsize=8) # Adjusted font size for x-ticks\n", "plt.yticks(rotation=0, fontsize=8) # Adjusted font size for y-ticks\n", "\n", "# Display the plot\n", "plt.tight_layout()\n", "\n", "# Save the figure to a file\n", "plt.savefig(\"confusion_matrix_57_classes-5k.png\",dpi=400)\n", "\n", "# Show the plot\n", "plt.show()\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "accelerator": "GPU", "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.14" } }, "nbformat": 4, "nbformat_minor": 4 }