{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# CNN Cancer Detection\n*A deep learning project* 🦾 \n\n### Overview\n\nIn today's world we are fortunate enough to have advanced technology which allows the medical field to provide better patient care. Cancer is a highly researched area because there are so many people who suffer and/or die of cancerous disease. This study aims to improve cancer detection in lymph nodes by using computer vision machine learning technqiues. We will examine the data given in this competition to get a better understanding of it. Then, we will run multiple convolutional neural network models with the intent to be able to classify cancerous (1) and non-cancerous cells (0). With improved and faster cancer detection, patients will be able to recieve life-saving treatments faster. This the first step in those peoples cancer survival story. This notebook covers the thought process as to how to create simple CNN models. We will create two models, one without hyperparameter tuning, and one with tuning. Finally, we will suggest ways to improve the models in future studies.\n\nLayout for this notebook was given in assignment brief and is as follows: \n\n\n1. Brief Description of the Problem and Data\n2. Exploratory Data Analysis (EDA) - Inspect, Visualize and Clean the Data\n3. Describe Model Architecture \n4. Results and Analysis\n5. Conclusion","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"code","source":"#import libraries\n\n#general libraries \nimport numpy as np \nimport pandas as pd \nimport os\nimport random\nfrom sklearn.utils import shuffle\nimport shutil\n\n#visualizations\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport plotly.express as px\nimport matplotlib.patches as patches\n\n# work with images\nfrom skimage.transform import rotate\nfrom skimage import io\nimport cv2 as cv\n\n# model development\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.layers import RandomFlip, RandomZoom, RandomRotation\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, AveragePooling2D\nfrom tensorflow.keras.layers import Dense, Flatten, Dropout\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import BatchNormalization\nfrom tensorflow.keras.optimizers import Adam\n\nimport warnings\nwarnings.simplefilter(\"ignore\", category=DeprecationWarning)","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:46.876789Z","iopub.execute_input":"2022-09-13T18:02:46.877516Z","iopub.status.idle":"2022-09-13T18:02:56.288416Z","shell.execute_reply.started":"2022-09-13T18:02:46.877425Z","shell.execute_reply":"2022-09-13T18:02:56.287202Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tf.__version__","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:56.290241Z","iopub.execute_input":"2022-09-13T18:02:56.291079Z","iopub.status.idle":"2022-09-13T18:02:56.306684Z","shell.execute_reply.started":"2022-09-13T18:02:56.291039Z","shell.execute_reply":"2022-09-13T18:02:56.305844Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#get files\ntest_path = '../input/histopathologic-cancer-detection/test/'\ntrain_path = '../input/histopathologic-cancer-detection/train/'\nsample_submission = pd.read_csv('../input/histopathologic-cancer-detection/sample_submission.csv')\ntrain_data = pd.read_csv('../input/histopathologic-cancer-detection/train_labels.csv')","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:56.308298Z","iopub.execute_input":"2022-09-13T18:02:56.308876Z","iopub.status.idle":"2022-09-13T18:02:56.929454Z","shell.execute_reply.started":"2022-09-13T18:02:56.308840Z","shell.execute_reply":"2022-09-13T18:02:56.928472Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# declare constants for reproduciblity\nRANDOM_STATE = 49","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:56.931984Z","iopub.execute_input":"2022-09-13T18:02:56.932390Z","iopub.status.idle":"2022-09-13T18:02:56.937244Z","shell.execute_reply.started":"2022-09-13T18:02:56.932346Z","shell.execute_reply":"2022-09-13T18:02:56.936234Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 1. Brief Description of the Problem and Data\n\nThis data contains thousands of small images where the 96x96 pixel images with 3 channels, each with an identifying label and id. We have two datasets, a training and testing set already split for us. The training set contains 220,025 unique images and the test set contains about 57,500. To use these images in a machine learning model, we are also given an identifying dataframe with two columns: 'id' which is the unique image ID correpsonding to the training directory, and 'label' which tells us the classification category. Each label is either a 0 or 1, depending whether the image is non-cancerous (0) or cancerous (1). In the competition description, we find that if at least one pixel of an image is identified as cancerous then the whole image is therefore marked with a 1, otherwise it is 0. It is important to note that we do not have any missing values in this data which will make preprocessing more efficient.","metadata":{}},{"cell_type":"code","source":"# have a look at the format of the data\ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:56.938587Z","iopub.execute_input":"2022-09-13T18:02:56.939559Z","iopub.status.idle":"2022-09-13T18:02:56.958683Z","shell.execute_reply.started":"2022-09-13T18:02:56.939522Z","shell.execute_reply":"2022-09-13T18:02:56.957853Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# take a look at the data further\ntrain_data.describe()","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:56.960862Z","iopub.execute_input":"2022-09-13T18:02:56.961707Z","iopub.status.idle":"2022-09-13T18:02:56.990799Z","shell.execute_reply.started":"2022-09-13T18:02:56.961670Z","shell.execute_reply":"2022-09-13T18:02:56.989908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# check information, data types, and for missing data\ntrain_data.info()","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:56.992489Z","iopub.execute_input":"2022-09-13T18:02:56.992835Z","iopub.status.idle":"2022-09-13T18:02:57.018937Z","shell.execute_reply.started":"2022-09-13T18:02:56.992801Z","shell.execute_reply":"2022-09-13T18:02:57.017931Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 2. Exploratory Data Analysis (EDA) - Inspect, Visualize and Clean the Data\n\nFirst, we will visualize the data. Then we will clean/preprocess the data. \n\nWe can see in the histogram and pie chart below that we have 59.5% of the labels are 0 (non-cancerous images) and 40.5% are labeled 1 (cancerous images). We were told in the competition description that the data is 50/50 split between cancerous and non-cancerous images however, from what we are finding here, we have a split which is closer to 40/60. This means that our data is unbalanced, however it is not severely unbalanced either (compared to a split such as 30/70 or even 10/90). We also have thousands of images to train with. For this reason, we can assume we will be able to create a sufficiently performing model which identifies cancerous images. ","metadata":{}},{"cell_type":"code","source":"#create histogram\nprint(pd.DataFrame(data={'Label Counts': train_data['label'].value_counts()}))\nsns.countplot(x=train_data['label'], palette='colorblind').set(title='Label Counts Histogram');","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:57.020452Z","iopub.execute_input":"2022-09-13T18:02:57.021094Z","iopub.status.idle":"2022-09-13T18:02:57.246757Z","shell.execute_reply.started":"2022-09-13T18:02:57.021056Z","shell.execute_reply":"2022-09-13T18:02:57.245835Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#create pie chart\nfig = px.pie(train_data, \n             values = train_data['label'].value_counts().values, \n             names = train_data['label'].unique())\nfig.update_layout(\n    title={\n        'text': \"Label Percentage Pie Chart\",\n        'y':.99,\n        'x':0.5,\n        'xanchor': 'center',\n        'yanchor': 'top'})\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-09-13T18:02:57.248325Z","iopub.execute_input":"2022-09-13T18:02:57.248720Z","iopub.status.idle":"2022-09-13T18:02:58.072664Z","shell.execute_reply.started":"2022-09-13T18:02:57.248680Z","shell.execute_reply":"2022-09-13T18:02:58.071267Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Below we can see some example images from the training data. As someone who is not familiar at looking at cancer cells and images, it would be very challenging for me to classify these. However, we mitigate this by putting the correct label for each image is below it. Additionally, we were told that each image has the (potentially) cancerous cells centered in each 32x32 pixel image, so we have drawn a box around this area as a focal point. ","metadata":{}},{"cell_type":"code","source":"#visualize a few images\nfig, ax = plt.subplots(5, 5, figsize=(15, 15))\nfor i, axis in enumerate(ax.flat):\n    file = str(train_path + train_data.id[i] + '.tif')\n    image = io.imread(file)\n    axis.imshow(image)\n    box = patches.Rectangle((32,32),32,32, linewidth=2, edgecolor='r',facecolor='none', linestyle='-')\n    axis.add_patch(box)\n    axis.set(xticks=[], yticks=[], xlabel = train_data.label[i]);\n    #cv2.waitKey(0)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-09-13T18:02:58.078250Z","iopub.execute_input":"2022-09-13T18:02:58.078601Z","iopub.status.idle":"2022-09-13T18:02:59.892606Z","shell.execute_reply.started":"2022-09-13T18:02:58.078567Z","shell.execute_reply":"2022-09-13T18:02:59.891287Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Preprocessing Techniques**\n\n\nWhen working with training data, first we want to handle any missing data. From the source description and our findings above, we can see that we have no missing data in the training set. Next, we are told that the part of the image which is going to be of interest is the center pixels (red box above). Right now the images are 96x96x3 and we know that the \"3\" is the RGB channel. For now, we will leave this as well. Lastly, there are many augmentations you can perform on images to produce better results and facilitate model learning, but to start we will not touch these either for simplicity. \n\nWhat we will do with the image data is **shuffle** the data so that the model doesn't learn based on the image ordering/pattern of input, which could potentially have consequences in the model training. We will also **split** the data into training and validation set to improve model development. During training we will also **normalize** the pixels by dividing by 255.0, which should help data processing and model training.","metadata":{}},{"cell_type":"markdown","source":"# 3. Describe Model Architecture \n\nFor this model we will be using Keras' library to run a convolutional neural network (CNN). The first model we will run without tuning any hyperparameters within the model and use that as our baseline. Then, we will run a second model, tuning hyperparameters such as learning rate, batch normalization, regularization, filter size, stride, activation layers, etc. \n\nOur CNN model will have a network such that there are two convolutional layers then a MaxPool layer, and we repeat this *n* number of times. Specifically, we will create a fairly simple model with two (n=2) of these clusters. In other words, our model will be input --> Conv2D --> Conv2D --> MaxPool --> Conv2D --> Conv2D --> MaxPool --> Flatten --> Output with sigmoid activation.\n\n**First model:**\n1. Normalize images pre-training (image/255)\n2. Output layer activation (sigmoid)\n\n**Second model contains all the first model parameters, but we also add:**\n1. Dropout (0.1)\n2. Batch Normalization\n3. Optimization (Adam)\n4. Learning rate (0.0001) \n5. Hidden layer activations (ReLU)\n\nBefore we start with the models, let's describe what each of the parameters will do to the model. In both models we will use 1 and 2, numbers 3 to 5 will be used in the second and final models. \n1. **Normalize images** : this will take the pixels and divide each pixel by 255 to normalize the data and have values between 0-1.\n2. **Output layer activation** : we will use a sigmoid activation function on the output layer since we are working with binary data\n3. **Dropout** : we will set dropout at 0.1 which will randonly select some weights and set them to equal 0 which regularizes the model because it is using a smaller number of weights for each training run. \n4. **Optimization** : we will use adaptive moment estimation (Adam) for optimizing the model which essentially mimics momentum for gradient adn gradient-squared. \n5. **Learning rate**: we will set our learning rate to 0.0001 which will assist in the gradient descent such that as the model learns, the speed of learning decreases so that it is less likely to overstep the (hopefully) global minimum. \n6. **Hidden layer activations**: we will use rectified linear regression (ReLU) as our hidden layer activation function which will help the model to converge better, prevent saturation, and provide less need for computation power. \n\nIn addition, we will use fairly large **batch sizes**, set at 256 to help reduce variance. Finally we wil train our two models with 10 **epochs**. We will use accuracy and the ROC-AUC curve to measure model performance, as well as binary cross-entropy as our loss function.","metadata":{}},{"cell_type":"code","source":"# set model constants\nBATCH_SIZE = 256","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:59.893736Z","iopub.execute_input":"2022-09-13T18:02:59.894044Z","iopub.status.idle":"2022-09-13T18:02:59.898605Z","shell.execute_reply.started":"2022-09-13T18:02:59.894015Z","shell.execute_reply":"2022-09-13T18:02:59.897801Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# prepare data for training\ndef append_tif(string):\n    return string+\".tif\"\n\ntrain_data[\"id\"] = train_data[\"id\"].apply(append_tif)\ntrain_data['label'] = train_data['label'].astype(str)\n\n# randomly shuffle training data\ntrain_data = shuffle(train_data, random_state=RANDOM_STATE)","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:02:59.900233Z","iopub.execute_input":"2022-09-13T18:02:59.900961Z","iopub.status.idle":"2022-09-13T18:03:00.136749Z","shell.execute_reply.started":"2022-09-13T18:02:59.900927Z","shell.execute_reply":"2022-09-13T18:03:00.135718Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# modify training data by normalizing it \n# and split data into training and validation sets\ndatagen = ImageDataGenerator(rescale=1./255.,\n                            validation_split=0.15)","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:03:00.138216Z","iopub.execute_input":"2022-09-13T18:03:00.138593Z","iopub.status.idle":"2022-09-13T18:03:00.144395Z","shell.execute_reply.started":"2022-09-13T18:03:00.138558Z","shell.execute_reply":"2022-09-13T18:03:00.143101Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# generate training data\ntrain_generator = datagen.flow_from_dataframe(\n    dataframe=train_data,\n    directory=train_path,\n    x_col=\"id\",\n    y_col=\"label\",\n    subset=\"training\",\n    batch_size=BATCH_SIZE,\n    seed=RANDOM_STATE,\n    class_mode=\"binary\",\n    target_size=(64,64))        # original image = (96, 96) ","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:03:00.145977Z","iopub.execute_input":"2022-09-13T18:03:00.146688Z","iopub.status.idle":"2022-09-13T18:14:09.853730Z","shell.execute_reply.started":"2022-09-13T18:03:00.146652Z","shell.execute_reply":"2022-09-13T18:14:09.852653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# generate validation data\nvalid_generator = datagen.flow_from_dataframe(\n    dataframe=train_data,\n    directory=train_path,\n    x_col=\"id\",\n    y_col=\"label\",\n    subset=\"validation\",\n    batch_size=BATCH_SIZE,\n    seed=RANDOM_STATE,\n    class_mode=\"binary\",\n    target_size=(64,64))       # original image = (96, 96) ","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:14:09.855635Z","iopub.execute_input":"2022-09-13T18:14:09.856064Z","iopub.status.idle":"2022-09-13T18:15:41.651466Z","shell.execute_reply.started":"2022-09-13T18:14:09.856022Z","shell.execute_reply":"2022-09-13T18:15:41.650384Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Setup GPU accelerator - configure Strategy. Assume TPU...if not set default for GPU/CPU\ntpu = None\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.TPUStrategy(tpu)\nexcept ValueError:\n    strategy = tf.distribute.get_strategy()","metadata":{"execution":{"iopub.status.busy":"2022-09-13T18:15:41.653053Z","iopub.execute_input":"2022-09-13T18:15:41.653612Z","iopub.status.idle":"2022-09-13T18:15:41.667858Z","shell.execute_reply.started":"2022-09-13T18:15:41.653574Z","shell.execute_reply":"2022-09-13T18:15:41.666821Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Start First model building and training**\n\nHere we build our first model. This model is fairly simple with a handful of layers, void of activations except the last layer. The last layer we use a sigmoid activation function since our data is binary (0-1). We can see below how the model is built and how many parameters we will need to train for this model. The next cell below we can see the model training per epoch. ","metadata":{}},{"cell_type":"code","source":"# set ROC AUC as metric\nROC_1 = tf.keras.metrics.AUC()\n\n# use GPU\nwith strategy.scope():\n    \n    #create model\n    model_one = Sequential()\n    \n    model_one.add(Conv2D(filters=16, kernel_size=(3,3)))\n    model_one.add(Conv2D(filters=16, kernel_size=(3,3)))\n    model_one.add(MaxPooling2D(pool_size=(2,2)))\n\n    model_one.add(Conv2D(filters=32, kernel_size=(3,3)))\n    model_one.add(Conv2D(filters=32, kernel_size=(3,3)))\n    model_one.add(AveragePooling2D(pool_size=(2,2)))\n\n    model_one.add(Flatten())\n    model_one.add(Dense(1, activation='sigmoid'))\n    \n    #build model by input size\n    model_one.build(input_shape=(BATCH_SIZE, 64, 64, 3))        # original image = (96, 96, 3) \n    \n    #compile\n    model_one.compile(loss='binary_crossentropy', metrics=['accuracy', ROC_1])\n    \n#quick look at model\nmodel_one.summary()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-09-13T20:36:06.565327Z","iopub.execute_input":"2022-09-13T20:36:06.565926Z","iopub.status.idle":"2022-09-13T20:36:06.629551Z","shell.execute_reply.started":"2022-09-13T20:36:06.565891Z","shell.execute_reply":"2022-09-13T20:36:06.628473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCHS = 10\n\n# train the model\nhistory_model_one = model_one.fit_generator(\n                        train_generator,\n                        epochs = EPOCHS,\n                        validation_data = valid_generator)","metadata":{"_kg_hide-input":false,"execution":{"iopub.status.busy":"2022-09-13T18:15:44.811975Z","iopub.execute_input":"2022-09-13T18:15:44.812677Z","iopub.status.idle":"2022-09-13T19:22:57.266750Z","shell.execute_reply.started":"2022-09-13T18:15:44.812636Z","shell.execute_reply":"2022-09-13T19:22:57.265691Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Now that we have trained the model, we can take at look at how it did graphically with the training data. Below we can see the accuracy and loss with regards to the validation and training set. We can also see how it did with the ROC AUC per epoch. ","metadata":{}},{"cell_type":"code","source":"# plot model accuracy per epoch \nplt.plot(history_model_one.history['accuracy'])\nplt.plot(history_model_one.history['val_accuracy'])\nplt.title('Model One Accuracy per Epoch')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'validate'], loc='upper left')\nplt.show();\n\n# plot model loss per epoch\nplt.plot(history_model_one.history['loss'])\nplt.plot(history_model_one.history['val_loss'])\nplt.title('Model One Loss per Epoch')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'validate'], loc='upper left')\nplt.show();\n\n# plot model ROC per epoch\nplt.plot(history_model_one.history['auc'])\nplt.plot(history_model_one.history['val_auc'])\nplt.title('Model One AUC ROC per Epoch')\nplt.ylabel('ROC')\nplt.xlabel('epoch')\nplt.legend(['train', 'validate'], loc='upper left')\nplt.show();","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-09-13T19:22:57.279091Z","iopub.execute_input":"2022-09-13T19:22:57.279996Z","iopub.status.idle":"2022-09-13T19:22:57.892200Z","shell.execute_reply.started":"2022-09-13T19:22:57.279960Z","shell.execute_reply":"2022-09-13T19:22:57.891108Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Start second model building and training**\n\nOur second model incorporates hyperparameter tuning. We can see we are using ReLU activation functions for hidden layers, dropout between clusters, and batch normalization. In addition, we have added another hidden layer before the flatten and output layers. Lastly, we are using Adam optimizer with a low learning rate. ","metadata":{}},{"cell_type":"code","source":"# build second model like first but with hyperparameters and optimizer(s)\nROC_2 = tf.keras.metrics.AUC()\n\nwith strategy.scope():\n    \n    #create model\n    model_two = Sequential()\n    \n    model_two.add(Conv2D(filters=16, kernel_size=(3,3), activation='relu', ))\n    model_two.add(Conv2D(filters=16, kernel_size=(3,3), activation='relu'))\n    model_two.add(MaxPooling2D(pool_size=(2,2)))\n    model_two.add(Dropout(0.1))\n    \n    model_two.add(BatchNormalization())\n    model_two.add(Conv2D(filters=32, kernel_size=(3,3), activation='relu'))\n    model_two.add(Conv2D(filters=32, kernel_size=(3,3), activation='relu'))\n    model_two.add(AveragePooling2D(pool_size=(2,2)))\n    model_two.add(Dropout(0.1))\n    \n    model_two.add(BatchNormalization())\n    model_two.add(Conv2D(filters=32, kernel_size=(3,3), activation='relu'))\n    model_two.add(Flatten())\n    model_two.add(Dense(1, activation='sigmoid'))\n    \n    #build model by input size\n    model_two.build(input_shape=(BATCH_SIZE, 64, 64, 3))       # original image = (96, 96, 3) \n    \n    #compile\n    adam_optimizer = Adam(learning_rate=0.0001)\n    model_two.compile(loss='binary_crossentropy', metrics=['accuracy', ROC_2], optimizer=adam_optimizer)\n\n#quick look at model\nmodel_two.summary()","metadata":{"execution":{"iopub.status.busy":"2022-09-13T19:22:57.893603Z","iopub.execute_input":"2022-09-13T19:22:57.893963Z","iopub.status.idle":"2022-09-13T19:22:57.991242Z","shell.execute_reply.started":"2022-09-13T19:22:57.893927Z","shell.execute_reply":"2022-09-13T19:22:57.990221Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCHS = 10\n\n# train model\nhistory_model_two = model_two.fit_generator(\n                        train_generator,\n                        epochs = EPOCHS,\n                        validation_data = valid_generator)","metadata":{"execution":{"iopub.status.busy":"2022-09-13T19:22:57.992475Z","iopub.execute_input":"2022-09-13T19:22:57.992819Z","iopub.status.idle":"2022-09-13T20:11:55.188799Z","shell.execute_reply.started":"2022-09-13T19:22:57.992784Z","shell.execute_reply":"2022-09-13T20:11:55.187752Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# graph loss\nplt.plot(history_model_two.history['accuracy'])\nplt.plot(history_model_two.history['val_accuracy'])\nplt.title('Model Two Accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'validate'], loc='upper left')\nplt.show();\n\nplt.plot(history_model_two.history['loss'])\nplt.plot(history_model_two.history['val_loss'])\nplt.title('Model Two Loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'validate'], loc='upper left')\nplt.show();\n\n# plot model ROC per epoch\nplt.plot(history_model_two.history['auc_1'])\nplt.plot(history_model_two.history['val_auc_1'])\nplt.title('Model Two AUC ROC per Epoch')\nplt.ylabel('ROC')\nplt.xlabel('epoch')\nplt.legend(['train', 'validate'], loc='upper left')\nplt.show();","metadata":{"execution":{"iopub.status.busy":"2022-09-13T20:11:55.199659Z","iopub.execute_input":"2022-09-13T20:11:55.200961Z","iopub.status.idle":"2022-09-13T20:11:55.774518Z","shell.execute_reply.started":"2022-09-13T20:11:55.200905Z","shell.execute_reply":"2022-09-13T20:11:55.773571Z"},"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Test final model against the test set**\n\nNow that we have a trained model, we can test it on the unseen test data images. We must also normalize the test data like we did with the training data. Then we run the model to find its predictions. Let's hope it does well in the competition! ","metadata":{}},{"cell_type":"code","source":"#double check what you're aiming the submission data set to look like\nsample_submission.head()","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-09-13T20:11:55.777789Z","iopub.execute_input":"2022-09-13T20:11:55.778113Z","iopub.status.idle":"2022-09-13T20:11:55.789589Z","shell.execute_reply.started":"2022-09-13T20:11:55.778076Z","shell.execute_reply":"2022-09-13T20:11:55.788369Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#create a dataframe to run the predictions\ntest_df = pd.DataFrame({'id':os.listdir(test_path)})\ntest_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-09-13T20:11:55.791006Z","iopub.execute_input":"2022-09-13T20:11:55.791350Z","iopub.status.idle":"2022-09-13T20:11:59.095220Z","shell.execute_reply.started":"2022-09-13T20:11:55.791316Z","shell.execute_reply":"2022-09-13T20:11:59.094303Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# prepare test data (in same way as train data)\ndatagen_test = ImageDataGenerator(rescale=1./255.)\n\ntest_generator = datagen_test.flow_from_dataframe(\n    dataframe=test_df,\n    directory=test_path,\n    x_col='id', \n    y_col=None,\n    target_size=(64,64),         # original image = (96, 96) \n    batch_size=1,\n    shuffle=False,\n    class_mode=None)","metadata":{"execution":{"iopub.status.busy":"2022-09-13T20:11:59.096541Z","iopub.execute_input":"2022-09-13T20:11:59.096915Z","iopub.status.idle":"2022-09-13T20:14:57.485960Z","shell.execute_reply.started":"2022-09-13T20:11:59.096878Z","shell.execute_reply":"2022-09-13T20:14:57.484495Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#run model to find predictions\n\n# predictions = model_one.predict(test_generator, verbose=1)\npredictions = model_two.predict(test_generator, verbose=1)\n","metadata":{"execution":{"iopub.status.busy":"2022-09-13T20:14:57.491079Z","iopub.execute_input":"2022-09-13T20:14:57.491410Z","iopub.status.idle":"2022-09-13T20:22:00.187723Z","shell.execute_reply.started":"2022-09-13T20:14:57.491380Z","shell.execute_reply":"2022-09-13T20:22:00.186639Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#create submission dataframe\npredictions = np.transpose(predictions)[0]\nsubmission_df = pd.DataFrame()\nsubmission_df['id'] = test_df['id'].apply(lambda x: x.split('.')[0])\nsubmission_df['label'] = list(map(lambda x: 0 if x < 0.5 else 1, predictions))\nsubmission_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-09-13T20:22:00.200710Z","iopub.execute_input":"2022-09-13T20:22:00.201222Z","iopub.status.idle":"2022-09-13T20:22:00.344098Z","shell.execute_reply.started":"2022-09-13T20:22:00.201182Z","shell.execute_reply":"2022-09-13T20:22:00.343048Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#view test prediction counts\nsubmission_df['label'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-09-13T20:22:00.345652Z","iopub.execute_input":"2022-09-13T20:22:00.346014Z","iopub.status.idle":"2022-09-13T20:22:00.355033Z","shell.execute_reply.started":"2022-09-13T20:22:00.345979Z","shell.execute_reply":"2022-09-13T20:22:00.353851Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#plot test predictions\nsns.countplot(data=submission_df, x='label').set(title='Predicted Labels for Test Set');","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-09-13T20:22:00.356641Z","iopub.execute_input":"2022-09-13T20:22:00.357059Z","iopub.status.idle":"2022-09-13T20:22:00.554929Z","shell.execute_reply.started":"2022-09-13T20:22:00.357021Z","shell.execute_reply":"2022-09-13T20:22:00.553847Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#convert to csv to submit to competition\nsubmission_df.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2022-09-13T20:22:00.556464Z","iopub.execute_input":"2022-09-13T20:22:00.557479Z","iopub.status.idle":"2022-09-13T20:22:00.647971Z","shell.execute_reply.started":"2022-09-13T20:22:00.557440Z","shell.execute_reply":"2022-09-13T20:22:00.647017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 4. Results and Analysis\n\nWe can see from the above plots and diagrams for each model how well they performed with the training (and validation) sets. We see that model-one seemed to steady out a bit more than our more complex model (model-two) with regards to the ROC metric. We see in both models that the accuracy and loss does not steady, nor does the ROC in the second model. This could pertain towards the fact that we trained with very few epochs (10) and a simple CNN model with so many pictures may need more \"time\" to train to converge. \n\nAfter submitting both trained models separately on the test set, we can see (below) how each model performed. As expected, we see that model-one (the model without hyperparameters) performed worse than model-two (with hyperparameters). Model-two performed with a score of about 0.80 which is fairly good considering the models we created. ","metadata":{}},{"cell_type":"markdown","source":"![Screen Shot 2022-09-14 at 13.06.50.jpg](attachment:7c805a2e-712d-4cbd-aa34-6ccb30b72bfe.jpg)","metadata":{},"attachments":{"7c805a2e-712d-4cbd-aa34-6ccb30b72bfe.jpg":{"image/jpeg":"/9j/4AAQSkZJRgABAgEASABIAAD/4QDoRXhpZgAATU0AKgAAAAgABgESAAMAAAABAAEAAAEaAAUAAAABAAAAVgEbAAUAAAABAAAAXgEoAAMAAAABAAIAAAITAAMAAAABAAEAAIdpAAQAAAABAAAAZgAAAAAAAACQAAAAAQAAAJAAAAABAAiQAAAHAAAABDAyMjGRAQAHAAAABAECAwCShgAHAAAAEgAAAMygAAAHAAAABDAxMDCgAQADAAAAAQABAACgAgAEAAAAAQAABdqgAwAEAAAAAQAAAkSkBgADAAAAAQAAAAAAAAAAQVNDSUkAAABTY3JlZW5zaG90AAD/4g/QSUNDX1BST0ZJTEUAAQEAAA/AYXBwbAIQAABtbnRyUkdCIFhZWiAH5gAIAA0AFQAUAAZhY3NwQVBQTAAAAABBUFBMAAAAAAAAAAAAAAAAAAAAAAAA9tYAAQAAAADTLWFwcGwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABFkZXNjAAABUAAAAGJkc2NtAAABtAAABJxjcHJ0AAAGUAAAACN3dHB0AAAGdAAAABRyWFlaAAAGiAAAABRnWFlaAAAGnAAAABRiWFlaAAAGsAAAABRyVFJDAAAGxAAACAxhYXJnAAAO0AAAACB2Y2d0AAAO8AAAADBuZGluAAAPIAAAAD5tbW9kAAAPYAAAACh2Y2dwAAAPiAAAADhiVFJDAAAGxAAACAxnVFJDAAAGxAAACAxhYWJnAAAO0AAAACBhYWdnAAAO0AAAACBkZXNjAAAAAAAAAAhEaXNwbGF5AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAbWx1YwAAAAAAAAAmAAAADGhySFIAAAAUAAAB2GtvS1IAAAAMAAAB7G5iTk8AAAASAAAB+GlkAAAAAAASAAACCmh1SFUAAAAUAAACHGNzQ1oAAAAWAAACMGRhREsAAAAcAAACRm5sTkwAAAAWAAACYmZpRkkAAAAQAAACeGl0SVQAAAAYAAACiGVzRVMAAAAWAAACoHJvUk8AAAASAAACtmZyQ0EAAAAWAAACyGFyAAAAAAAUAAAC3nVrVUEAAAAcAAAC8mhlSUwAAAAWAAADDnpoVFcAAAAKAAADJHZpVk4AAAAOAAADLnNrU0sAAAAWAAADPHpoQ04AAAAKAAADJHJ1UlUAAAAkAAADUmVuR0IAAAAUAAADdmZyRlIAAAAWAAADim1zAAAAAAASAAADoGhpSU4AAAASAAADsnRoVEgAAAAMAAADxGNhRVMAAAAYAAAD0GVuQVUAAAAUAAADdmVzWEwAAAASAAACtmRlREUAAAAQAAAD6GVuVVMAAAASAAAD+HB0QlIAAAAYAAAECnBsUEwAAAASAAAEImVsR1IAAAAiAAAENHN2U0UAAAAQAAAEVnRyVFIAAAAUAAAEZnB0UFQAAAAWAAAEemphSlAAAAAMAAAEkABMAEMARAAgAHUAIABiAG8AagBpzuy37AAgAEwAQwBEAEYAYQByAGcAZQAtAEwAQwBEAEwAQwBEACAAVwBhAHIAbgBhAFMAegDtAG4AZQBzACAATABDAEQAQgBhAHIAZQB2AG4A/QAgAEwAQwBEAEwAQwBEAC0AZgBhAHIAdgBlAHMAawDmAHIAbQBLAGwAZQB1AHIAZQBuAC0ATABDAEQAVgDkAHIAaQAtAEwAQwBEAEwAQwBEACAAYQAgAGMAbwBsAG8AcgBpAEwAQwBEACAAYQAgAGMAbwBsAG8AcgBMAEMARAAgAGMAbwBsAG8AcgBBAEMATAAgAGMAbwB1AGwAZQB1AHIgDwBMAEMARAAgBkUGRAZIBkYGKQQaBD4EOwRMBD4EQAQ+BDIEOAQ5ACAATABDAEQgDwBMAEMARAAgBeYF0QXiBdUF4AXZX2mCcgBMAEMARABMAEMARAAgAE0A4AB1AEYAYQByAGUAYgBuAP0AIABMAEMARAQmBDIENQRCBD0EPgQ5ACAEFgQaAC0ENAQ4BEEEPwQ7BDUEOQBDAG8AbABvAHUAcgAgAEwAQwBEAEwAQwBEACAAYwBvAHUAbABlAHUAcgBXAGEAcgBuAGEAIABMAEMARAkwCQIJFwlACSgAIABMAEMARABMAEMARAAgDioONQBMAEMARAAgAGUAbgAgAGMAbwBsAG8AcgBGAGEAcgBiAC0ATABDAEQAQwBvAGwAbwByACAATABDAEQATABDAEQAIABDAG8AbABvAHIAaQBkAG8ASwBvAGwAbwByACAATABDAEQDiAOzA8cDwQPJA7wDtwAgA78DuAPMA70DtwAgAEwAQwBEAEYA5AByAGcALQBMAEMARABSAGUAbgBrAGwAaQAgAEwAQwBEAEwAQwBEACAAYQAgAGMAbwByAGUAczCrMOkw/ABMAEMARHRleHQAAAAAQ29weXJpZ2h0IEFwcGxlIEluYy4sIDIwMjIAAFhZWiAAAAAAAADwzwABAAAAARkRWFlaIAAAAAAAAIGGAAA8p////7lYWVogAAAAAAAATbIAALSJAAAK1FhZWiAAAAAAAAAnngAADtAAAMigY3VydgAAAAAAAAQAAAAABQAKAA8AFAAZAB4AIwAoAC0AMgA2ADsAQABFAEoATwBUAFkAXgBjAGgAbQByAHcAfACBAIYAiwCQAJUAmgCfAKMAqACtALIAtwC8AMEAxgDLANAA1QDbAOAA5QDrAPAA9gD7AQEBBwENARMBGQEfASUBKwEyATgBPgFFAUwBUgFZAWABZwFuAXUBfAGDAYsBkgGaAaEBqQGxAbkBwQHJAdEB2QHhAekB8gH6AgMCDAIUAh0CJgIvAjgCQQJLAlQCXQJnAnECegKEAo4CmAKiAqwCtgLBAssC1QLgAusC9QMAAwsDFgMhAy0DOANDA08DWgNmA3IDfgOKA5YDogOuA7oDxwPTA+AD7AP5BAYEEwQgBC0EOwRIBFUEYwRxBH4EjASaBKgEtgTEBNME4QTwBP4FDQUcBSsFOgVJBVgFZwV3BYYFlgWmBbUFxQXVBeUF9gYGBhYGJwY3BkgGWQZqBnsGjAadBq8GwAbRBuMG9QcHBxkHKwc9B08HYQd0B4YHmQesB78H0gflB/gICwgfCDIIRghaCG4IggiWCKoIvgjSCOcI+wkQCSUJOglPCWQJeQmPCaQJugnPCeUJ+woRCicKPQpUCmoKgQqYCq4KxQrcCvMLCwsiCzkLUQtpC4ALmAuwC8gL4Qv5DBIMKgxDDFwMdQyODKcMwAzZDPMNDQ0mDUANWg10DY4NqQ3DDd4N+A4TDi4OSQ5kDn8Omw62DtIO7g8JDyUPQQ9eD3oPlg+zD88P7BAJECYQQxBhEH4QmxC5ENcQ9RETETERTxFtEYwRqhHJEegSBxImEkUSZBKEEqMSwxLjEwMTIxNDE2MTgxOkE8UT5RQGFCcUSRRqFIsUrRTOFPAVEhU0FVYVeBWbFb0V4BYDFiYWSRZsFo8WshbWFvoXHRdBF2UXiReuF9IX9xgbGEAYZRiKGK8Y1Rj6GSAZRRlrGZEZtxndGgQaKhpRGncanhrFGuwbFBs7G2MbihuyG9ocAhwqHFIcexyjHMwc9R0eHUcdcB2ZHcMd7B4WHkAeah6UHr4e6R8THz4faR+UH78f6iAVIEEgbCCYIMQg8CEcIUghdSGhIc4h+yInIlUigiKvIt0jCiM4I2YjlCPCI/AkHyRNJHwkqyTaJQklOCVoJZclxyX3JicmVyaHJrcm6CcYJ0kneierJ9woDSg/KHEooijUKQYpOClrKZ0p0CoCKjUqaCqbKs8rAis2K2krnSvRLAUsOSxuLKIs1y0MLUEtdi2rLeEuFi5MLoIuty7uLyQvWi+RL8cv/jA1MGwwpDDbMRIxSjGCMbox8jIqMmMymzLUMw0zRjN/M7gz8TQrNGU0njTYNRM1TTWHNcI1/TY3NnI2rjbpNyQ3YDecN9c4FDhQOIw4yDkFOUI5fzm8Ofk6Njp0OrI67zstO2s7qjvoPCc8ZTykPOM9Ij1hPaE94D4gPmA+oD7gPyE/YT+iP+JAI0BkQKZA50EpQWpBrEHuQjBCckK1QvdDOkN9Q8BEA0RHRIpEzkUSRVVFmkXeRiJGZ0arRvBHNUd7R8BIBUhLSJFI10kdSWNJqUnwSjdKfUrESwxLU0uaS+JMKkxyTLpNAk1KTZNN3E4lTm5Ot08AT0lPk0/dUCdQcVC7UQZRUFGbUeZSMVJ8UsdTE1NfU6pT9lRCVI9U21UoVXVVwlYPVlxWqVb3V0RXklfgWC9YfVjLWRpZaVm4WgdaVlqmWvVbRVuVW+VcNVyGXNZdJ114XcleGl5sXr1fD19hX7NgBWBXYKpg/GFPYaJh9WJJYpxi8GNDY5dj62RAZJRk6WU9ZZJl52Y9ZpJm6Gc9Z5Nn6Wg/aJZo7GlDaZpp8WpIap9q92tPa6dr/2xXbK9tCG1gbbluEm5rbsRvHm94b9FwK3CGcOBxOnGVcfByS3KmcwFzXXO4dBR0cHTMdSh1hXXhdj52m3b4d1Z3s3gReG54zHkqeYl553pGeqV7BHtje8J8IXyBfOF9QX2hfgF+Yn7CfyN/hH/lgEeAqIEKgWuBzYIwgpKC9INXg7qEHYSAhOOFR4Wrhg6GcobXhzuHn4gEiGmIzokziZmJ/opkisqLMIuWi/yMY4zKjTGNmI3/jmaOzo82j56QBpBukNaRP5GokhGSepLjk02TtpQglIqU9JVflcmWNJaflwqXdZfgmEyYuJkkmZCZ/JpomtWbQpuvnByciZz3nWSd0p5Anq6fHZ+Ln/qgaaDYoUehtqImopajBqN2o+akVqTHpTilqaYapoum/adup+CoUqjEqTepqaocqo+rAqt1q+msXKzQrUStuK4trqGvFq+LsACwdbDqsWCx1rJLssKzOLOutCW0nLUTtYq2AbZ5tvC3aLfguFm40blKucK6O7q1uy67p7whvJu9Fb2Pvgq+hL7/v3q/9cBwwOzBZ8Hjwl/C28NYw9TEUcTOxUvFyMZGxsPHQce/yD3IvMk6ybnKOMq3yzbLtsw1zLXNNc21zjbOts83z7jQOdC60TzRvtI/0sHTRNPG1EnUy9VO1dHWVdbY11zX4Nhk2OjZbNnx2nba+9uA3AXcit0Q3ZbeHN6i3ynfr+A24L3hROHM4lPi2+Nj4+vkc+T85YTmDeaW5x/nqegy6LzpRunQ6lvq5etw6/vshu0R7ZzuKO6070DvzPBY8OXxcvH/8ozzGfOn9DT0wvVQ9d72bfb794r4Gfio+Tj5x/pX+uf7d/wH/Jj9Kf26/kv+3P9t//9wYXJhAAAAAAADAAAAAmZmAADypwAADVkAABPQAAAKW3ZjZ3QAAAAAAAAAAQABAAAAAAAAAAEAAAABAAAAAAAAAAEAAAABAAAAAAAAAAEAAG5kaW4AAAAAAAAANgAArgAAAFIAAABDwAAAsMAAACZAAAANwAAAT0AAAFRAAAIzMwACMzMAAjMzAAAAAAAAAABtbW9kAAAAAAAABhAAAKAwAAAAANIfpPAAAAAAAAAAAAAAAAAAAAAAdmNncAAAAAAAAwAAAAJmZgADAAAAAmZmAAMAAAACZmYAAAACMzM0AAAAAAIzMzQAAAAAAjMzNAD/wAARCAJEBdoDASIAAhEBAxEB/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQAAAF9AQIDAAQRBRIhMUEGE1FhByJxFDKBkaEII0KxwRVS0fAkM2JyggkKFhcYGRolJicoKSo0NTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uHi4+Tl5ufo6erx8vP09fb3+Pn6/8QAHwEAAwEBAQEBAQEBAQAAAAAAAAECAwQFBgcICQoL/8QAtREAAgECBAQDBAcFBAQAAQJ3AAECAxEEBSExBhJBUQdhcRMiMoEIFEKRobHBCSMzUvAVYnLRChYkNOEl8RcYGRomJygpKjU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6goOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4uPk5ebn6Onq8vP09fb3+Pn6/9sAQwABAQEBAQECAQECAwICAgMEAwMDAwQFBAQEBAQFBgUFBQUFBQYGBgYGBgYGBwcHBwcHCAgICAgJCQkJCQkJCQkJ/9sAQwEBAQECAgIEAgIECQYFBgkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJCQkJ/90ABABe/9oADAMBAAIRAxEAPwD+4jwD4B8J634TtNT1O08yeXzNzeZIudsjKOFYDoB2rsP+FWeBP+fH/wAiy/8AxdHwt/5ESx/7a/8Ao169Aqm3clJWPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69AopXY7I8//AOFWeBP+fH/yLL/8XR/wqzwJ/wA+P/kWX/4uvQKKLsLI8/8A+FWeBP8Anx/8iy//ABdH/CrPAn/Pj/5Fl/8Ai69Aoouwsjz/AP4VZ4E/58f/ACLL/wDF0f8ACrPAn/Pj/wCRZf8A4uvQKKLsLI8//wCFWeBP+fH/AMiy/wDxdH/CrPAn/Pj/AORZf/i69Aoouwsjz/8A4VZ4E/58f/Isv/xdH/CrPAn/AD4/+RZf/i69Aoouwsjz/wD4VZ4E/wCfH/yLL/8AF0f8Ks8Cf8+P/kWX/wCLr0Cii7CyPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69Aoouwsjz//AIVZ4E/58f8AyLL/APF0f8Ks8Cf8+P8A5Fl/+Lr0Cii7CyPP/wDhVngT/nx/8iy//F0f8Ks8Cf8APj/5Fl/+Lr0Cii7CyPP/APhVngT/AJ8f/Isv/wAXR/wqzwJ/z4/+RZf/AIuvQKKLsLI8/wD+FWeBP+fH/wAiy/8AxdH/AAqzwJ/z4/8AkWX/AOLr0Cii7CyPP/8AhVngT/nx/wDIsv8A8XR/wqzwJ/z4/wDkWX/4uvQKKLsLI8//AOFWeBP+fH/yLL/8XR/wqzwJ/wA+P/kWX/4uvQKKLsLI8/8A+FWeBP8Anx/8iy//ABdH/CrPAn/Pj/5Fl/8Ai69Aoouwsjz/AP4VZ4E/58f/ACLL/wDF0f8ACrPAn/Pj/wCRZf8A4uvQKKLsLI8//wCFWeBP+fH/AMiy/wDxdH/CrPAn/Pj/AORZf/i69Aoouwsjz/8A4VZ4E/58f/Isv/xdH/CrPAn/AD4/+RZf/i69Aoouwsjz/wD4VZ4E/wCfH/yLL/8AF0f8Ks8Cf8+P/kWX/wCLr0Cii7CyPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69Aoouwsjz//AIVZ4E/58f8AyLL/APF0f8Ks8Cf8+P8A5Fl/+Lr0Cii7CyPP/wDhVngT/nx/8iy//F0f8Ks8Cf8APj/5Fl/+Lr0Cii7CyPP/APhVngT/AJ8f/Isv/wAXR/wqzwJ/z4/+RZf/AIuvQKKLsLI8/wD+FWeBP+fH/wAiy/8AxdH/AAqzwJ/z4/8AkWX/AOLr0Cii7CyPP/8AhVngT/nx/wDIsv8A8XR/wqzwJ/z4/wDkWX/4uvQKKLsLI8//AOFWeBP+fH/yLL/8XR/wqzwJ/wA+P/kWX/4uvQKKLsLI8/8A+FWeBP8Anx/8iy//ABdH/CrPAn/Pj/5Fl/8Ai69Aoouwsjz/AP4VZ4E/58f/ACLL/wDF0f8ACrPAn/Pj/wCRZf8A4uvQKKLsLI8//wCFWeBP+fH/AMiy/wDxdH/CrPAn/Pj/AORZf/i69Aoouwsjz/8A4VZ4E/58f/Isv/xdH/CrPAn/AD4/+RZf/i69Aoouwsjz/wD4VZ4E/wCfH/yLL/8AF0f8Ks8Cf8+P/kWX/wCLr0Cii7CyPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69Aoouwsjz//AIVZ4E/58f8AyLL/APF0f8Ks8Cf8+P8A5Fl/+Lr0Cii7CyPP/wDhVngT/nx/8iy//F0f8Ks8Cf8APj/5Fl/+Lr0Cii7CyPP/APhVngT/AJ8f/Isv/wAXR/wqzwJ/z4/+RZf/AIuvQKKLsLI8/wD+FWeBP+fH/wAiy/8AxdH/AAqzwJ/z4/8AkWX/AOLr0Cii7CyPP/8AhVngT/nx/wDIsv8A8XR/wqzwJ/z4/wDkWX/4uvQKKLsLI8//AOFWeBP+fH/yLL/8XR/wqzwJ/wA+P/kWX/4uvQKKLsLI8/8A+FWeBP8Anx/8iy//ABdH/CrPAn/Pj/5Fl/8Ai69Aoouwsjz/AP4VZ4E/58f/ACLL/wDF0f8ACrPAn/Pj/wCRZf8A4uvQKKLsLI8//wCFWeBP+fH/AMiy/wDxdH/CrPAn/Pj/AORZf/i69Aoouwsjz/8A4VZ4E/58f/Isv/xdH/CrPAn/AD4/+RZf/i69Aoouwsjz/wD4VZ4E/wCfH/yLL/8AF0f8Ks8Cf8+P/kWX/wCLr0Cii7CyPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69Aoouwsjz//AIVZ4E/58f8AyLL/APF0f8Ks8Cf8+P8A5Fl/+Lr0Cii7CyPP/wDhVngT/nx/8iy//F0f8Ks8Cf8APj/5Fl/+Lr0Cii7CyPP/APhVngT/AJ8f/Isv/wAXR/wqzwJ/z4/+RZf/AIuvQKKLsLI8/wD+FWeBP+fH/wAiy/8AxdH/AAqzwJ/z4/8AkWX/AOLr0Cii7CyPP/8AhVngT/nx/wDIsv8A8XR/wqzwJ/z4/wDkWX/4uvQKKLsLI8//AOFWeBP+fH/yLL/8XR/wqzwJ/wA+P/kWX/4uvQKKLsLI8/8A+FWeBP8Anx/8iy//ABdH/CrPAn/Pj/5Fl/8Ai69Aoouwsjz/AP4VZ4E/58f/ACLL/wDF0f8ACrPAn/Pj/wCRZf8A4uvQKKLsLI8//wCFWeBP+fH/AMiy/wDxdH/CrPAn/Pj/AORZf/i69Aoouwsjz/8A4VZ4E/58f/Isv/xdH/CrPAn/AD4/+RZf/i69Aoouwsjz/wD4VZ4E/wCfH/yLL/8AF0f8Ks8Cf8+P/kWX/wCLr0Cii7CyPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69Aoouwsjz//AIVZ4E/58f8AyLL/APF0f8Ks8Cf8+P8A5Fl/+Lr0Cii7CyPP/wDhVngT/nx/8iy//F0f8Ks8Cf8APj/5Fl/+Lr0Cii7CyPP/APhVngT/AJ8f/Isv/wAXR/wqzwJ/z4/+RZf/AIuvQKKLsLI8/wD+FWeBP+fH/wAiy/8AxdH/AAqzwJ/z4/8AkWX/AOLr0Cii7CyPP/8AhVngT/nx/wDIsv8A8XR/wqzwJ/z4/wDkWX/4uvQKKLsLI8//AOFWeBP+fH/yLL/8XR/wqzwJ/wA+P/kWX/4uvQKKLsLI8/8A+FWeBP8Anx/8iy//ABdH/CrPAn/Pj/5Fl/8Ai69Aoouwsjz/AP4VZ4E/58f/ACLL/wDF0f8ACrPAn/Pj/wCRZf8A4uvQKKLsLI8//wCFWeBP+fH/AMiy/wDxdH/CrPAn/Pj/AORZf/i69Aoouwsjz/8A4VZ4E/58f/Isv/xdH/CrPAn/AD4/+RZf/i69Aoouwsjz/wD4VZ4E/wCfH/yLL/8AF0f8Ks8Cf8+P/kWX/wCLr0Cii7CyPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69Aoouwsjz//AIVZ4E/58f8AyLL/APF0f8Ks8Cf8+P8A5Fl/+Lr0Cii7CyPP/wDhVngT/nx/8iy//F0f8Ks8Cf8APj/5Fl/+Lr0Cii7CyPP/APhVngT/AJ8f/Isv/wAXR/wqzwJ/z4/+RZf/AIuvQKKLsLI8/wD+FWeBP+fH/wAiy/8AxdH/AAqzwJ/z4/8AkWX/AOLr0Cii7CyPP/8AhVngT/nx/wDIsv8A8XR/wqzwJ/z4/wDkWX/4uvQKKLsLI8//AOFWeBP+fH/yLL/8XR/wqzwJ/wA+P/kWX/4uvQKKLsLI8/8A+FWeBP8Anx/8iy//ABdH/CrPAn/Pj/5Fl/8Ai69Aoouwsjz/AP4VZ4E/58f/ACLL/wDF0f8ACrPAn/Pj/wCRZf8A4uvQKKLsLI8//wCFWeBP+fH/AMiy/wDxdH/CrPAn/Pj/AORZf/i69Aoouwsjz/8A4VZ4E/58f/Isv/xdH/CrPAn/AD4/+RZf/i69Aoouwsjz/wD4VZ4E/wCfH/yLL/8AF0f8Ks8Cf8+P/kWX/wCLr0Cii7CyPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69Aoouwsjz//AIVZ4E/58f8AyLL/APF0f8Ks8Cf8+P8A5Fl/+Lr0Cii7CyPP/wDhVngT/nx/8iy//F0f8Ks8Cf8APj/5Fl/+Lr0Cii7CyPP/APhVngT/AJ8f/Isv/wAXR/wqzwJ/z4/+RZf/AIuvQKKLsLI8/wD+FWeBP+fH/wAiy/8AxdH/AAqzwJ/z4/8AkWX/AOLr0Cii7CyPP/8AhVngT/nx/wDIsv8A8XR/wqzwJ/z4/wDkWX/4uvQKKLsLI8//AOFWeBP+fH/yLL/8XR/wqzwJ/wA+P/kWX/4uvQKKLsLI8/8A+FWeBP8Anx/8iy//ABdH/CrPAn/Pj/5Fl/8Ai69Aoouwsjz/AP4VZ4E/58f/ACLL/wDF0f8ACrPAn/Pj/wCRZf8A4uvQKKLsLI8//wCFWeBP+fH/AMiy/wDxdH/CrPAn/Pj/AORZf/i69Aoouwsjz/8A4VZ4E/58f/Isv/xdH/CrPAn/AD4/+RZf/i69Aoouwsjz/wD4VZ4E/wCfH/yLL/8AF0f8Ks8Cf8+P/kWX/wCLr0Cii7CyPP8A/hVngT/nx/8AIsv/AMXR/wAKs8Cf8+P/AJFl/wDi69Aoouwsjz//AIVZ4E/58f8AyLL/APF18f1+gFfn/WkGRNH/0P7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P8Ar9AK/P8ArSmZ1D//0f7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P8Ar9AK/P8ArSmZ1D//0v7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P8Ar9AK/P8ArSmZ1D//0/7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKK+A/26fiZ438NL4L+Ffg7VT4dTxvqTWN5q68NawBoUOHyNm7ztxYFThCNwBJrnfEn/BPzStB8PXHiD4Q+K/EFn4wt4/Ot72a9yLieMblSbCphWPGQflzk7gCCAfo9RXzTafFvxD8HP2e7P4h/tNR/ZdUsVSHUfsQWbdI03kxuojO3MilXYDAUkgdK93uvEul2fhaTxhOWFlFam8Y4y3lKnmHj129qAN+ivhv4/8AxZ0H4q/sQ+I/ih8P5p47K+tG8iRwYZR5V2IX4ByPmRh15Fee+Av28fgH8N/hd4P8J+I7+8v9Qs9C0xL6S0gadIJTax7hLISAWDcMF3ENweQaAP0morgPDHxR8C+NfAQ+JnhK/TUNGaB5xPEDnbGCXBQgMrrggowDA8EV8t3n/BQ/9mu00ex1eO9vbn7ajSmGC1Z5YI1laIvOAdqDcpIGSxUg7cMMgH3HRXx94s/br/Zw8K6Fp+uprEmqjUrc3cUOnwtNMsIYqzSr8oiwwIIkKtkHjivWfAnxZ+GP7QHwzvPE3gy+e60qaOa2udoaKeE7P3iMOGRwrAgj1BUkUAeyRTQzxiWBg6nOCpyOODyPepK+P/2P1+Cfg/8AZ8/tf4W6jet4YjuLu6lu9ZZEkQpxMzkBESNQmeABwWPJJrmJP+Cin7NCaobRb2/eyWXyW1FbKU2it7tjf054Q8c0Afc9FcH4z+J/gL4f+CJPiN4s1OG10aONZRc53rIrjKeWFyZC4PyhQS3avm/wP+3l+z5478V2XhCyur2xm1SQRWU17atDBcOTtVUkycZbgbtozx1IFAH2Q00KSLE7AM+doJ5OOTgd8CpK+Nfjf4f+C+oftIfDbUPHF3qkPiVJJzo8NowFrIYSsjfaMqSACR90ruHytkYFexfGj9oD4XfALSLfVfiPfm3a9Ypa28SNLPOy43bI15wuRljhQSBnJAIB7RRXzF8HP2u/gx8bvEUng7wvdXNnrMaGQWOoQG3mdFALFOWViAclQ27HOMAkbPxN/ai+Dvwe8Zr4G+IWoNp922nHVN7RkxeQHeMAEZLSM0ZCooJPFAH0JRXyb8L/ANtT4EfFjxjH4D0G9ubPU7jJtor+3a3FwAMjymOQSw5UEhj2Br6yoAKK8Y+M3x/+FnwD0iDV/iVqItPtZZbaCNGlnmK43bEUE4XIyxwoyMnJFedfCT9sz4IfGPxSngjQbm60/V50Mlva6jAbd51A3ExHLIx2/MF3biMkAgHAB9WUV4D8T/2mvhF8HPF9r4M+Id+2n3F3ZS6gkjRkxCKIPkFhkl2KEKiqWY4ABJrhPhv+298Avif4zg8B6NfXNnqF4cWi31u1ulzkZXy2ORlv4Q20seACcUAfXNFeWfFz40fDn4HeGf8AhLPiRqC2Ns7+XEoUvLNJjOyONQWY+pxgDkkDmvzj/aZ/bP8Ag/8AGX9m/wAU+HfAd/d6frKiymhgu4zbSyx/bICzQsrEN8vJAbdtycYBwAfrfRXFfDZ3k+HWgSSEszabakk8kkwrya+H/wDgppeX9p8CtFXT7iW2abxFaxM0LlGKtb3ORkfgfqKAP0Vor8+L3/gnj4JtIGuPBHjTxTo+oqMw3C3wdVbsWVUjYgH+66n3ra/ZQ+L3xLbxx4l/Zq+OVwt94l8KhZre+Xg3lk23a7cDJAeM7upDgMNykkA+7aK+ZvjT+1v8GPgRrUPhjxjdz3GrToJBY2MJnmVGztLchVzjgFgxHIGOa6v4LftEfCj4/wCmz6h8NtR+0yWhAuLaVDFPFuztLI38JwcMpK9s5BFAHt1FfLPxZ/bH+CHwe8UHwRr13cX+sooaSy06BriWMEbhvwQqnb820tuC4OMEZ9O+D3xs+HXx28MN4s+HN6bq3ikMMyOjRywyAA7ZEYAg4IIIyD2JwaAPWKK+QfiT+3H8Afhj4xn8CareXV/qNmSt0mn27TrbkDLB2yBlR94KWKnggEEV7T4E+Nfw2+JngOb4keB9STUNLt0kaZkBEkRiXc6SRth1cDnBAyCCMggkA9VqMTQtK0CuC6gFlzyAehI98Gviq1/4KAfs76lJo1po1zfX13rbqkVtBbFpYd0zQBp8sFQblzjcW2ENtwRm98OvD/wVtP2w/HGp+G7vU5PGX2CD+04JmH2JIpUt3UxcBixUR8MxC8hcDoAfZdFfFusft9fs6aLp1xd3N9dSXEF/Npws4rctcvLAFLsqA4EeWAVmKhjkDODj1v4JftI/CX9oKyuLn4cagZp7PBuLWdDFcRBujFD1U/3lLLngkHigD3eo2mhSRYnYBnztBPJxycDvgV+S6ft/6Xa/tR38V7Pqx8GRab9njsVslMovgUYy7B+927dwyT74xg19LfF/TPgl4i/aB+F/iHxjdatB4hl8yXRYLchbeTZtlIuQVJXGRwpXd91sjAoA+1qK8X+NH7QHwu+AWkW+q/Ee/Nu16xS1t4kaWedlxu2RrzhcjLHCgkDOSAeK+Dn7XfwY+N3iKTwd4Xurmz1mNDILHUIDbzOigFinLKxAOSobdjnGASAD6dorwH4n/tNfCL4OeL7XwZ8Q79tPuLuyl1BJGjJiEUQfILDJLsUIVFUsxwACTXCfDf8Abe+AXxP8ZweA9Gvrmz1C8OLRb63a3S5yMr5bHIy38IbaWPABOKAPrmiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKK/LT/gqlquqaV8MfDEmmXMtsz6o4YxOyEjyG67SKqeOP+Ced/4T8L3vib4VfEDXrbWLCF7iAXE+FdoxuC74fLZCcYDc4POKAP1Wor4B/Zd/avfxJ+yxe/Fz4tyvLL4Xnezv54Y8yTBBEUk2DALssqhsYBIJwOldro/7d/7PniHxT4f8GeH7y6vdQ8RSQRQxxQ8QtcNtQTsWAU8jIUsRnkCgD7AhvLO4mlt7eVHkgIEiqwLISMgMByMjnmrNfnl8CF+AHg340/Fjxb4DvNavdZsXuZtZt7hQ0UZSaWSVbYKA0pMisE3EnGADySfrH4L/ABt8BfHvwk/jT4ezSS2cVw9rIJk8uRJUVWIK5OPldSPY0AeuUV4Z4Y/aI+HPjD4vat8EvD73E+s6JG8l2wi/0dAhQMPMz1DOFxjrn0rw3xj/AMFEv2ZfB2vyeHjqN1qbwOY5JrCAywqw64kYoHA9U3D0zQB9y0V4NL+0r8Ij8Grn486ZqJv/AA7abRLLbxsZUZpFi2NE21lcM65VgDg56EE/AH7HX7dMnijxhf8Agn4u6ne399rmpww6IDbxBI45WZdjmLbtwSuSc+xNAH68UV89fHH9qL4Pfs9/Zrf4h37re3imSGztozNOyA4LlRgKueAXYZIOM4OK3wR/at+C37QFzNpngDUX/tCBPNeyuozDP5fALqDlXUE4OxjjjOMjIB9HUUV+PXji78c/tYftia58Adb8UXPhnw14dikMdpZt5ct0YxGr9wJHcuXBYMEjXhfvMQD9haK/KSb9lP8AaB/Zn8aaN4n/AGYNYv8AxLpJm8vUNIv7iCNRBkE5814om3DIDKquhwRkE1+iPxV+Lvw/+CvhR/GXxG1BbCyVxGnDPJLI2SEjRQWZjgngcAEkgAmgD0qivjT4Zft6fs5fFLxLB4R0rUp9Pvrt/Kt01CEwrK5+6qyAsgLdFDMpY8AZIB+gPit8Xvh78E/CreMviRqC2FkHESfKzySyNkhI0QFmYgE8DAAJJABIAPS6K+Mvhj+3t+zr8VPFdv4L0i/ubC/vHEVsL+DykmkPRFcFlDN0UMVycAZJAr2H4yftAfDr4EDSH+IMs0Ka1cG2t3jTeodduS5JAVRuGSaAPbKK+avhR+1l8HfjX451PwJ8Pbqe7m0q2a6luWi8u2aNJFjJR2IY8sDkqARyDXlOvf8ABRr9mDQfEcnh7+0ru8WFzG93a2zSW4KnBwxIZxnoyKwPUEjBoA+66K5nwf4y8L/EDw3a+L/Bl9FqOm3q74biE5VgCQR2IIIIZSAQQQQCK6agAooooAKKK/KD/gpl/aF54l+F/h20vbiyi1O9vLeVreQocO9mmeDglQxxnNAH6v0V+SXxV/YT1z4U+BNU+JPwj+IGuw6noVrLfiO4nIEi26mR1V4thVioO3IIJwDgHI+ifgr+1tp97+ydbfHr4uMwfT5DZag9rFkvKJhCjiMEDLh0ZscAk4AGAAD7korjNB8eaB4j8AWvxK05pP7MvLFdRjLLh/IePzQSvY7e3rXyf8TPjp4R+N37Hvjj4gfDWa5S1gtLm2DyoYZBLGqMcAHOMOOc0AfcdFfk1+z3+278E/g1+zv4R8MePdTur7WfIneeK2jNxJEHu5tnmuzBQSuCF3btuDjBGf0c+Ffxc+H/AMafCqeMvhxqCahZM5jfAKSRSKATHIjAMjAEHBHIIIyCCQD0d3SNDJIQqqMkngACorW6tb63S7spFmikG5XQhlYeoI4Ir8cf2L7nRvEX7KXxTi+J17etpHm3AvJYXLXCW4tQXMW7cNwGSAQQehBBIr7t/ZDh+FXh39nTS7n4ZX93P4cjN3Mt1qhWOUbZpPOZwAERFZWxgABRk5JJIB9UUV8HXf8AwUh/ZbtNebRf7SvJYkYqbyO0ka347j/loR7iPmvtfw54j0Hxdodr4m8MXcV/p97GJYJ4WDo6nuCPyI6g8HmgDaor5R/bS+Lviv4K/ALUvGHggiPU5JYbSGdlDiDzmw0m05BIUELkEBiCQRwfjT4a/sJL8Xfhlo/xZ1v4i6xP4k1i0S9S7ilEsULTrvMfzMZGKE7XxIvzA8DoAD9eaK+Rv2QtP/aR8OeEdQ8G/tEwmSTS51j0y/eeGeS6tyGB3mN3c7CoIaUByHAOSDWR8R/2+f2cvhn4tn8FatqFze3lpIYbk2UBljhkHDKzkqCV6ME3YPB5BAAPtCivOvhh8WPh/wDGTwunjD4c6lHqNizFGK5V43HVJI2AZGHBwwGQQRkEE/NXxA/4KCfs3fDzxTceEL6/utQubSQw3D2MBlijkU4ZS7FQxU8HZuAPHUHAB9tUVwXw1+J3gf4veE4PG3w9v01DTpyVDqCrK6/eR0YBkYdwwHBBGQQT8oXP/BRn9mW18PNr7X14zCd7dbRbcm4coqszBNwUJ8wAZmUE5Azg4APuyivAfif+018Ifg94P0zxn47v2tYtZiWWyt1QyXMysofiNc4ChhuYkKCQM5IzyvwY/bL+BHx11seF/B+oy2+qupaOzvYjDJKFBLeWcsjkAElQ27GTjAOAD6oooooAKKK/PX9gDUdQ1Gz+IzahPJOY/FV0qmRi21cDgZJwPagD9CqK+Nf2/wC9vNP/AGTvE93YSvBKrWOHjYqwzewA4IweRxXqmhfEbwj8M/2fdB8d/EHUEsbC20exaWeUlizNAmFUDLO7HoqgsT2oA92or4z8D/t5fs+eO/Fdl4Qsrq9sZtUkEVlNe2rQwXDk7VVJMnGW4G7aM8dSBX0Z8Tfij4F+D3hKbxt8Q79dP0+Eqm8gszu33UjRQWdj6AHgEnABIAPQKK+N/hx+3f8As8/EvxRbeD9PvrnTb6+ZUtBqEBgSdnOEVHyy5c8KGI3Hgc4FfZFADJJI4o2llYKqgkknAAHUk1laR4h0DxAsj6DfW98sLbZDbypKFb0bYTg+xr8w/wDgpZ8ctO0vwSnwW02W9tr28u7WW/kjiYRPYskrMiy5VWcuqEoTggHNfQ37Ll1+zT4N+Fut+MfhDY3Hh7Q7ac/2lcap5yOz28SsZGM7sdoV/wCHC5JwM0AfZ1FfC9l/wUU/ZpvNWjsXu9Qt7OaXyk1GazkW0Zv97lwPXKDA5OOa+ofiV8VfB/wp+Hd38UvE8zPo9msLvJbL5pZZ5EijKAHDAtIvIOMc0Aej0V8r+Cv2x/gp8RfidZ/CnwTcXWo6heK7edFD/o0RSFpirykjnapHyhhuGM19UUAFFfjD+zZ+zb4V/aI1Hx34h8dazrcM2n+Iru1iWyvPKTy87+QyPzluxHHavv74L/sneAPgb4qm8X+FtT1m9uJ7V7Rk1C7E8QR3RyQojX5soADnoT60AfTkc0M24RMG2Ha2DnBHY+9SV8Tfsu2PwN8FxfETWvhfearcpb6vcNq51AhvLnt97OsAAXcoy3zNl243McCq99/wUN/Zss9Dstahvb26a9jeb7Nb2zSTQxJI0ReYAhYxlCcFt23DYwRkA+4aK85+FvxY8BfGfwnF41+Hd+t/YSM0ZIBR45F+8kiMAyMMg4I5BBGQQa+b/GX7f37Ovg7xLc+FUvLzV7ixLLcvp1s00URQ4fLkqGCnqybh7+gB9rUV4pbfFHwV8Wfgrqnjv4c6gt9YTWN2FlQMjpIkTbkdWAZHXjggHGCOCCfGf+CfV7eah+yl4cur+Z55WkvsvIxZji8mAySSaAPtGiiigAooooAKKKKACiiigAooooAK/P8Ar9AK/P8ArSmZ1D//1P7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooA8Z+NHw2+Evxl0GP4a/FEQSi6fzbWMzCK5WVQQJIDnduAJBwCCMhgRkV8Ya9+zh+0r+z5odz4m/Z/+Il3qmnaXE0w0TW1EytDENzRxucoCVGAFSL2YZr6L/ad/ZvufjlbaN4k8I6s2g+KvDE5udLvQNyBmKMUkA5xlFIIztOflYEg+E+IfhZ/wUF+JOhz/AA/8YeKvDmlaXdJ5F3eafHKbmaJxhwAYkAyMggGLPTODQBxX7RXxiX48/wDBO2b4mNbCznvJrVLiBSSqTQ3qxvtJ52sV3LnkAgHnNfdfia4gg/Z11C7mcLEnhyV2YngKLQknPpiuLuf2V/Aw/Zom/Zn02aaHTZLcoLpsPL9o80XAnYcAnzgGKjAx8oI4I+XrL9mb9tDXPAx+Cvjrxxpi+E4bRrUPZh/ttxEiYhgkkaAFYjwsh3M2zI+cE0AcL4V/5RNT/wDXref+naSvtb9kPwN4P8P/ALMnhXT9ItIWg1XTILu8yoYTTXMYebzM/e+ZiuDkAAAcACvNtE/Zh8e6b+xBJ+zVPd6eddeGeMTrJL9kzLetcr85iEmNjAH939725rzXwv8AAT9uH4M+Drb4bfCPxVol1pJgTa+oLIZrGd1DTrA3ksGi80sYyyk4P3FNAHPfsrW1t4V1L9oD4Y+HW/4kOi3kxs4lJKwtIt3G6DPXasKJ6/JzXrX/AATm8JeHbb9lawvks4ml1ue8a9LIp87ZPJAqvkfMoRAMHI5Pqa9M+Bf7MsfwU+DuseCY7/8AtTXvEC3E2oahLuAluZoyg5O5ti56nLElmIycDqf2VfhJ4k+BvwO0j4Z+LJ7a4v7B7lpJLRneEiaeSVdpkSNuFYA5Uc569aAPlr/gmZ4a0LT/AIb+MNRtLWNJ28SXNmZMDcYIIYTHGT12qZGIHuaT9ke0ttI+I3x70DTI1gsrbWWMMKABE3m7yFA4AwAABwAABX0J+yR8DfFnwE8Fa74b8X3Fpcz6nrlzqcTWbyOghmjhRVYyRxkODGcgAjGOTVL4L/ATxf8ADnx18UfE+t3NnLB43v8A7VYrA8jPGmZziYNGoVv3q/cLjg89MgHzh+yX8Pbv4r/8E/Lz4dafdfYp9XOoQRzHO1XMpK7sc7CRhsfwk8GuYsPiX8X/AIA/CGP4Q/tJfCo6v4P0+2FjNqGlOksTWyjAeWNcgMepkZ4ju54Y5r6Q+En7LvjDwn+yjc/s/wDiPWxp+qXDXDpqGkSzfumkl82MhisLkZAEi8BlJXPNeUXfwV/b613wJJ8Fdb8UeHToMtsbCbUis0t7LZsvlsrbo8M5j4JOGOT+8zzQB3Pxz+Een/tL/sueHbX9naS2gs7Ka21PS7WUeXbyxwpJH9ndWBCld54YEbl2tgEkeV+LP2jZIbbSfB/7cXwqfS7BbmPytRixc2CXCggMApIQAZyqyyErn5SK+gfHP7K2tf8AChfDvwq+D/ia60DUvCrxz2d2HdI7iVSXf7QkZwQ8hLjhtp7EE58g8V/s9/tgftBWtn4I+P8Ar+hWPhiC4jmuk0iORrm5MWSMGRFVc5IzuUA87GxigDoP2jpI5f2w/glLCQyNJqBUjkEFEwRWH4J0yw8e/wDBRzxlfeMALmXwlpVqNJgl+YQ+ZFAWlQdMgyuR6GTPUAj334p/AfxL4y+Onw5+JPh6azt9K8Gm5FzDK8iyssqKqCFVjZTjbzuZfbNc38d/2cfHGt/EnT/j98ANVt9F8Y2cf2a5W83G0vrfGNkoVXIIHH3TnC8qVVqAPJf+CjWnWPhrRPBXxi0JRB4l0nX7a3tZ48iR43SSUxEjqN0akbuBlgPvHMfxT8L6L4q/4KU+CbfXoEuYbTw0btI5FDIZYpb0xsQf7jEOvowBrqdD/Zx+O3xa+J2jfEH9qzVdMnsPDT+fp2j6P5gga5BBEsxkUE4IBxls4A+Vdwb13X/gd4s1X9r3RPj9b3FoujaboT6ZLCzyC5MzPcMGVRGUKYlXkuDweOmQDxH9vfT7Kx1r4WeNbWJU1Oz8V2cMVwAN4jZvMKk9SNyKcdOvqa/Ravln9qH4IeK/jZa+EYPCtxaW50HXrbVLj7W8iboYQwZY9kb5c54BwPevqagD4M/aS+Jvwt8KfGbw7pdn4Fl8d/EWG2M+nQwDb9ngLOA0kpDqBney5RtmN5K/KT8sfG3xh8evEnx3+EHiT4p+DLbweqeIre3tHS7iu7mVZbiASI7Rtwm09Co5J6Z5+v8A47fs/fFvUPjDp37Qn7PurWFj4gtrE6ddWupIxt7iDLMCGVXYN8wBGBwqkMMHPj2u/st/tU/FT4l+DPiv8XPEWiyTeG9Wtrr+zbQTR28FrFNHNKYmMbF55NgBDYHyr85H3QC98dfDOjeLf+Chfwx0nX4EurVdKuLgxSKGVntxdSx5B4O11VvwrW/4KK2NnY+GvAXja1iVdU0/xXZRQXGBvRHSWVlB64LxIceor2/xl8DvFniL9rHwh8drK4tF0jQNNubO4hd5Bcs8yXCqY1EZQqDKucup4PB4yv7WnwO8WfHnwboPh7whcWltPpeu2upytePIimGGOZGVTHHIS5MgwCAMZ5FAHz58XdL03x9/wUQ8DeDvGSrcaZpehyaja2sozHJc7rht2O+DEjYPB8oZyOu7/wAFLvB/hjV/2cZ/FGowR/2jo93bGymxhx50ixSRgj+FkYsVPGVBxkDHqH7Tv7N3iD4tanofxL+F2rLoPjTww5axupATFKhOfKlwGIGc4O1gQzKykNx82fFf9l79sf8AaK8HS6R8W/E2h27WHlyadY2IlS3muN6q8t0/klhthMmwIG+dhwozkA/Rr4Z/8k38P/8AYNtP/RK18Nf8FOv+SG6B/wBjNZ/+k91X314Q0i58P+E9L0G8ZWmsbSC3dkyVLRRqpK5AOMjjIFfNX7ZnwH8a/tC/DDT/AAd4DurK0vbPVob8vfPIkeyKGZCAY45Tu3SKQCuMZ57EA+t6/OXwbeQeKv8AgpJ4m1HQT5lvofhxLO8lTlPPZ4TsJ/vDOCOxQjsa0rz4df8ABRPxJA2k6t448N6PbzfLJPpsErzhT12eZbrg46EMp9COtfQX7O37OfhT9njwzc6bpNxLqeq6nL9o1LU7n/XXUvPJ5YqgJYqpZjliSSSSQD80P2Y/HfxutfGnjz4k+CPh0vjPVdR1q4iutSl1GG2lt1U7hbKsoLBBkHK4BAVf4Bj3X4Y+D/2hNX/bG0/41+Ifh8PBumX2nzWOrmG+t7hJWEcjxzOI2VmZnWFCNp+6GJ616D4q/Zx+OXwz+KOrfE/9lPWNPtLfxG/n6po+rCQ2zXJYs00RRWI3Ek4yhXLYYqQq958Evg18eLH4k3nxg+P3ipL6/mt/sltpOlPKmnQx5yGZW2B2GWwGQ4JLbmONoB4LfeCf2k/2afjr4x+Kfw48LweO9C8X3Au5kSYRX0BDO4iUtlgoLsAFSQFQn3SMV1/wy+N/ws8U+Bfif4z+GXhqXwp45sNPubzVrO4i8u4a4iglaJyeA2JAQcqjBiSyjdk29Y+DH7Xvw3+IeveI/gV4o0/VdH8Q3BuWsvELzyNaOxPETAP8i7sLhh8oUFWK5PoP7Ov7N/if4f614n+JHxk1S317xT4v2pem2j22scKAjykyqFgwwCSi8KoxwSQDlv8Agnd4S8OaT+zTpXivT40k1LXpbq41C5PMksiXEkQVmbLYVUAx0zlurEn2Jfgl8OvhN4Y8c634CsmsZPENtcXN5GsjmEyLHKcxxElI+XPCADGB0Ar5l0T9nL9qf4A6vqOhfsza/pE3hLUJ2ngsdc81nsnk+8EZEYso7HdzgFlLZJ9n+Cn7OXin4deCPFUnjTXP7d8W+MRK99dtuW3V2SQIkYxkIpkJJCjrgKAoFAHBf8E3PC+haR+zHpniDT7aOO91a4u5LqYKN8hineJAWxkhVQYGcDk9zWX8I/8AlIf8Vv8AsFab/wCk9pX0L+yr8JPEnwN+B2kfDPxZPbXF/YPctJJaM7wkTTySrtMiRtwrAHKjnPXrXP8Agb4HeLPDH7VXjb45X9xaPpPiSytLa2hjeQ3CPBFBGxkUxhACYjja7HBGQOwB8x/8E6vCHhhtb+I3jp4I5NYGvT2QlYZeO3BMmFP8IdmO7HXaM9BWz8QtJ0zwL/wUW8C6t4RRba48T6bdR6pFENomVIptsjgdSfLU+5iBr50/Zd+Hn7QElx40+J/7Pet2NtejxFe6ffabqisbW4ij2yxSKUVmEiNIw7ZU/eHIb7U+A/7NXxH0r4r3n7Qn7Q+s2+teK5rc2lpDZgi2s4SMHYWVOSuVACgDc5JdmyADltI/5SW6p/2KC/8Ao6Gl/aS/5PH+Cn/XXUf/AEBK6X45/s+fGe9+Ndl+0D+z1rGn2GtLp/8AZt5bamrGGWLcSGDKkhzyuVwuNgIbqD1/xF+B/j/x78aPhn8U3uLCOPwks7anGXlDPJPGgP2cCMhlDA/fKcYoA8M8E6ZYePf+CjnjK+8YAXMvhLSrUaTBL8wh8yKAtKg6ZBlcj0MmeoBCf8FGtOsfDWieCvjFoSiDxLpOv21vazx5EjxukkpiJHUbo1I3cDLAfeOfWvjv+zj441v4k6f8fvgBqtvovjGzj+zXK3m42l9b4xslCq5BA4+6c4XlSqtXFaH+zj8dvi18TtG+IP7Vmq6ZPYeGn8/TtH0fzBA1yCCJZjIoJwQDjLZwB8q7gwBy3x18M6N4t/4KF/DHSdfgS6tV0q4uDFIoZWe3F1LHkHg7XVW/Ctb/AIKK2NnY+GvAXja1iVdU0/xXZRQXGBvRHSWVlB64LxIceor2/wAZfA7xZ4i/ax8IfHayuLRdI0DTbmzuIXeQXLPMlwqmNRGUKgyrnLqeDweMr+1p8DvFnx58G6D4e8IXFpbT6XrtrqcrXjyIphhjmRlUxxyEuTIMAgDGeRQB9UUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFAH5S/8FYf+SXeFv8AsKv/AOiGq54sX/gpr8TdCufBV9pGheHbbUI2gmu7aZA4jk+Vhu+0XDLkZGUTcAeDnFe7ftufs3eOP2lPBmjeHfAt3Y2k+nXrXMjX7yxoUMZTCmKKUk5PcAY719sUAfmz8QvgRp37O37APij4e2dz9suDb/ary4xtElxLLEHKjqFAVVXPOAM816Z+wb8OfBfh/wDZt8Na7p+nW4v9Sje7ubpo1M0khlfbl8ZwgAVRngD1yT7l+0R8Odb+LfwW8QfDjw5LBBfarbiKF7lmWJWEit85RXYDC9lNP/Z6+HetfCb4L+H/AIc+IpYJ73SbYwzPbMzRM29m+QuqMRg91FAHwt+xiqt+1v8AG5WGQdTmBB/6/J64v4BeKLD9kX4+fFb4TeISYtFhtJtf05TwDFbqZljj9WaCQKcdWix14r6z/Z9/Zz8a/Cj45/EX4neIrqxmsPF149xZx2zyNMitcSygTB40VTtcD5WbnPPevNf22P2MvF37RPibRvGnw3vbDT9RtLaWyvDeySxiSEndFtMMUhJG+QNkDIYDtQBwf7CHh3TtI+Cnjj9pH4skbfFUt5c3kxDc2Vv5jTsAvzfPK02QvJ2rjnFcr8Jvijqmp+GNQ0n9kj4FrN4d1CaUPeandKsdwx4YP55wyrjGxZ2VegxX6OQ/Bbw1H8CR8BclNNOkHSWkUDfhovLaUA8byxL/AO9Xwn4B/Zr/AG5vhp4Z/wCFNeD/ABro1n4VV5VhvFiY3kEMzs8hiUw5EjF2bHmnax+WQcGgDP8A+CVgu4vBfjXQr5QqW2qREw5DKshjKvg5OfuAZyeg5NX/APgmfb24l+JD+WuV1lApwMgDzeBXuf7Ff7MnjD9mjSvEmkeKryzvE1S7jltWtHkYiKNWUebvjjwxyOF3D3rzf4efssftCfA346X3iL4TeINNPgvXtTju9SsrkMs/2fzGZo1BhlG9EdlRlkXfxux2APkbwl4m+Jup/tpfETxn4e8ER+PdV0q+urWCO5uEh+xQwztBE6eblSfLQICBkAnGMnPq0vgf9pXxp+1J4O+NbfDEeEjY3cMOqTW15BIJrd32SySBWUkrC7g4BLDA5wK+g/jN+yl8T7f4vP8AH/8AZe12DQPEF6hTUra8ybe5zgFsbJV+YKNysmNwDgq3NTfC39nj9pDV/jBZ/GP9o3xhFOdMTba6Vo7yR27cHAmwsK7VY7iu1y5wGbaNpAPv+vgj4x/sw/s9/tOeNrzxD4T8SR6d4z0srHd3GkXUU0sbxkon2qBW3K6FSoOY3+XaSdoA+96/N34m/sdfFjQPi/f/ABx/ZX8Tw6BqesNJJf2l6CYJJJGDSFcRSqyyN85SRDh+QwyAoB4n4u8X/tU/sI67o+p+PPE48deC7+5+zP8AaSxuFwNxAMhaSN9gJTEjpwQw6Vv/ALSFnp3xS/b/APh58N/GmLjw6tglylvISYpXb7RKSV7iVoY0YdCFweK6aP8AY2/aF+N/jLTPEH7XHi211DSdLcyR6ZpowrcglDiGFFDYw7AO5X5QwyCv0D+1X+yu/wAdU0rxl4F1AaF4x8PMrafeksEKq29Y3KAsu1/mR1UlTn5SDwAd58Zf2Y/gv8Y7LTo/GNkLGTS5A1tc2LLazIMY8sOF+5wCF7EAjHOfh39o3SrP4j/8FA/h58MPHLG50GCwSdbeY5jlkH2mUlgOD5rwxow6ELjGK6O8/ZN/an+O+s6PZ/tUeLdPufDujzCY2mmriS4dQQWbbBCgLA7dxztBO1Rk5+g/2p/2VW+OEek+MPAV+ug+MPDjKdOvDuWMojb1jfYCVCv8yMqnacjaQaAPIv8AgpH8OPAp/Z7PjGKyt7TVNEu7ZbKaFFjcLI4jaIFQPl2ndt6AqCK+c/2zL2/+IHwC+B994lkd7nWI7drmT+Jmntrfe/1bJb8a9hvf2Tf2rfjxrek6b+1R4tsLnwzpUome000bZLh1BGTsghUFgSu8klQTtUZNe7/tWfsy+KPjTZ+CdN+Hk1hp9t4WvBM8d08iDyFEaqkQjjkyQExg4HTmgDJ/bS0rSfhN+yFr9h8NrCHSIvKtbD/RY1jK2808cci5UAkOvytnJOeeea+W/gTq/wAbND+BGmeEPC3wPs9b0PUrJXlupL63H9oCZctLIrAtl88KTlBhRjFfrF8QfAfhv4n+C9R8A+LoTPp2qQmGZQdrAZyrKezKwDKexAr85PDf7Ov7d3wk0ib4Z/CfxtpEvhoF1spr1WFxbRuSTtBt5Sh54AZ1B5XFAHov/BPj4afFv4T+DfEfhX4maPNo1tJfpdafDLNHMAsqFZFUozY27FznGSc461+g9fPn7NfwS1P4F/D7/hGdf1258Q6lcym4ubm4eRkVmAHlwq7MVRcderEljjIA+g6ACiiigAr8j/8AgqDLq8Hif4WTeH41mv0vb1raN8BWmD2XlqclRgtgHJH1FfrhXxP+1r+zd45+PPirwHrnhC6sbaHwvezXN0LySVGdJJLZgIhHFICcQtncVHI564APn3xzof8AwUn+NPh25+HfiLTdC8N6bqaGC7nt5lBaF+HViJrlwrDhgigkEjoTW9+0v8HtJ+BH/BPbUPhlo87Xa2D2bS3DgK0s0t9E8j4HQbmwoySFABJIyf08rzT4xfDLSfjJ8M9Y+GetytBb6tB5fmoAWjdWEkbgHg7XVWxxnGMjrQB5J8KbiCD9jDQ7qZwscfhCJmYngBbIZJPtjmvz6/Z2/wCUanxB/wCu2of+ibevRPCv7G/7X9v4Vf4J+I/iDaw+BBHJGYLMk3MkbZPkh3tw6RseHXzWUKSArDivXPhV+yZ8RvA37Inij4Bate6bJrGtyXTwTQyTG2UTxxIu9mhVxgoc4Q9utADP+CePwy+Hw/Zf07XpNMtbq812W7a/kmjWVn8u4khSNt4PyBI1Oz7uSTjJJPkf7EVha+A/2tvit8MPCTEaDbNI8cQJKRvBc7I0GecosjpnqdvOaf4I/ZO/bV+BngyHw18F/GumQxXytJqFrOC8cFyzbfMtXltnO1owu7KoQc8Nww+pP2RP2WP+GctC1LUPEeoDV/EuvSLJqF0pYoAhYqiF/nb5nZmdgC5IyBgUAfAH7Jf/ACZP8Zv+ud9/6RVn6x4g1rQv+CVuiW+kO8a6jqctpcshwfJa9uZCCR2ZkVT6g4PBNfXXwP8A2QviR8NP2ePiB8JddvtNl1LxWtytpJBJM0Cedb+Svms0KMPm5O1G49TxXpXww/ZTitP2TIf2bPi5JBdMRcebNYO5VHkuXnhkieREbchZTymCQQQVPIB03wj+A/whuv2adF8AvpVrc6XqmkQSXEmxd8z3EId5/MxuDkuWVs5TjbgAY9R+DHwo8H/BbwPH4D8CTzzaZDNJLGLiUTMhkO5lVgBhd2Wx6k+tfnlpv7L37dvhrwZP8EfDvjnST4TeN7aOaQOLlLZ87o1PkPImQSNolIUcK6ivvv8AZ/8Agpof7P8A8LrD4baHM139nLy3Fy6hWnnlO53KjOB0VRkkKACSRkgGr8ZE+EV/4EuvDvxtu9PtNC1XFtJ/aNwltG7/AH1CSOyYkG3cpUhgVyOlfAt1+wX8R/hv5mu/sr/Ee+0qN/30VhdOxglJGRuki/dsD23QN2ya+3f2hfgR4Z/aJ+G8/wAPfEsr2v7xbm1uYwGaC4jDBX2nhhhmVlyMqSAQcEfEGk/AX/got4V0CL4c+G/iBpP9jQxiCG5kybiKEDaFDtaNKCBwuHJXACsMcAE3ws/ar+J3xA/Z2+KGl+NEW38Y+BtPuY5Lq3ATexjmQSbU+USRPExYphT8pAFdd/wTl+GngEfs32/iqTT7a71HXbi6F9LNGsjssUrRJES4PybFDbemWJ6mvYv2af2S/DXwH8Bat4d1y5Ou6j4mGNYuJQRHMpV18pVJ3bAJHyWJZixJxwq/NOlfsoftafAjWdU0T9mLxfp8HhfU5mmjt9TG6S3dhjdgwTDcqgDepG/A3JwKAPWPHvwa8Efsy/Av4neJvgtJc2dzqlhLJJAs+6O3b51DQqADH5aytjnIAH90VT/4J7fDH4f237MGl68un211d6+109/LLGsjSbLiSFY23g/IqRqNv3c5bGWOe5/Zx/ZI034S+CvEem/ES8XxHrHjPf8A21OQ3lyo4cNGpOHIbzHLMcFi2cDAr500j9lb9sb4F3Go+FP2bvGWnp4Xvpnmgi1EAzW7PgZw1vMoYKACyHDdSgNAGf8AsZWcHw//AGxvij8J/CJKeHoVknSFSTHFJFcRqiAHuqyunqQvOcVif8Euvh54N1XQ/FfjnVtPgu9Sjv1s4ppkWQxRBN5Cbgdu5m+YjrgelfZn7KX7L1r+zxoeoajrl8dZ8Ua9J52p35LFWIZmCR7vmIyxZmb5nY5OAABi/sWfs5+Nf2cfCGuaB43urG6m1PUPtURsXkdQnlqmGMscRDZHYEe9AHwV8RtY8cav/wAFCdcl0XwjH43uvDtpElhpc86QRQRJBCRKvmZQ7WlZguPvPuHK8dJ8XPCP7U3xb+JHhT4j2fwnHhvVfD15HM95a31uzzxLIjhJMMmQm0468MR0NfXH7RX7K3jHxf8AESx+PPwB1qPw740s1EUzz58i5jVdq78JINwX5CCjK64BAxmuP8M/s6/tWfEL4kaL43/aK8Z28On6C4lh0/Q3ki85gwJWVlSEBXKjccuSuVAXOQAfoxRRRQAV+cf/AAT1uIVb4naUzAXEHim5eSP+JVfKqT9SjD8DX6OV+efxE/ZU+L3hH4taj8bP2VPENto17rhL6ppl+pNrPIx3M4wkgJZiWwygqxYq4DbaAOx/4KJXdtbfsl+I4Z3CtcS2McYP8TC8hfA/4CpP4VgfHH4EeMfjp+yf4Q8M+C5YYtW0mHTNQiguuIZzDa7GifIK5w+RuBUkYOASRwt1+yx+0p+0B4m066/au8SWH/COaZMLhdH0gMFmcdRIdiYyONxaRgpYLtLE19T/ALR3wa8W/FjwTZ6b8NvEE3hjWNIuY7uzlid0gdo+kcyR9UzgqdrbSOhBIIB8e+LP2jZIbbSfB/7cXwqfS7BbmPytRixc2CXCggMApIQAZyqyyErn5SKxf2ydb8T6t+1z8OfCuiaAvi+2tdPk1K00iSdIILq4JnJYu+U/drCkmGBDAbf4jXeeK/2e/wBsD9oK1s/BHx/1/QrHwxBcRzXSaRHI1zcmLJGDIiquckZ3KAedjYxX0D+0b+zbJ8W7HRfEfw+1L/hHfFvhVw+kX658tV4zDKozmM7R/CccjBVmUgHx7+0ZaftV/tDeAV8H6h8HF0y7tpo57LUE1a0kltnRgW2DKHDrlSAwHQ8kCv1L8HvrUnhLS5PEsZh1FrOA3UZIYrOY18xSQSDhsjIJBr4L1H4N/txfFt7Dw18WPF2k+H9DtZ0muZvD5nS+uDGcqAxVAufUMoBwSjYAr9EreFbaBLdCxWNQoLsWYgDHLMSSfUk5NAH56f8ABSf/AJJN4S/7G2w/9EXVM/4KMz3N94G8HeB552t9L17xJa21+6nAMWGIVsdgTv8AqgPavaf2uPgb4s+PfgjQ/DXg+4tLafTNcttTla8eREMMMUyMqmOOQlyZBgEAYzyO/oPx++CHhn9oH4bXXw+8SM0BdhPaXKDLW9ygIjlAyM43EMvGVJGQTkAGt40+GHgHWfhJe/C/ULGCHQBYNbLAFxHDHGnyMmPumPAZSOQRnrX5NaXr2sa5/wAEoNZj1eR5RYXcVrAzkk+Sup27KMnnCliqjsAAOAK+jtT+Dv7fPivwefg94l8VaBFoksf2S41WFZ21CW1xtIYFFUs6cNypPOXOST7T8UP2Xor79ku6/Zq+ErwWh8u2S3lvncIzR3cdzLJK8aO26Qq54TG4gABegB7B+z/4W0Hwb8FPC+h+HLaO1t10y1kIRQu+SSJXkkbAGXdiWZupJJr2GuX8D6JdeGvBekeHL5kefT7K3tpGjJKF4o1RipIBwSOMgHHauooA/FT9mD4L/FP4l6j4+1XwF8Q77wdb2/iS7iktrWDzllfO7zCTLHg4IXGO3Wv0o+B3wk+JHwwl1KTx/wCO73xmL0RCBbuEQi38vfuK/vJM79wz0xtFcp+yx8C/FvwPt/FsXiy4s7g69rc+pW/2R5H2xSAYWTzI0w/qBke9fV1AH5ifsn/8ij8cv+w/q3/ot67/AP4JueFdC0r9mDT9cs7aNbrWbm7ku5do3SGKd4UDHqVVEGAeBk+prt/gj+z34z+GuhfEjTNdurKWTxhqd9e2ZgeRgkdyrKgm3RqVYE/MF3D0Jrvf2VfhJ4k+BvwO0j4Z+LJ7a4v7B7lpJLRneEiaeSVdpkSNuFYA5Uc569aAPlr9kBtB8GfEb476BMI7Tw/pGsef5W3EcMTG6MuFA4UJGBgDgDFYvwl+NfiGTQ7q0/Y3+C7v4cubmVhf3d1FZRTyZ2u+2TO9RjGBKdoG0AYwPoL4Wfs2654a8YfFq+8bz2lxpPxEuMwx2zu0qW7i5WRZg8aqrFZhjaXHXn18V8EfAz9uP4R+HR8IPh14m8PN4ageRbPULqKX7bbwyuzkiMRshfLFgrFxnjcB0AOQ/YlbWbb4Z/GTRtaghspbbU78yWlsQYIJmhdZUiwSNilAq4J4Ar6E/wCCd/8AyaV4b/6633/pZNVD9mr9lzxz8EfBnjvwp4i1S11OXxJPM9ncq8pdleN41e53oNsjFgzhS4Bzye/sP7Kvwk8SfA34HaR8M/Fk9tcX9g9y0klozvCRNPJKu0yJG3CsAcqOc9etAH0RRRRQAUUUUAFFFFABRRRQAUUUUAFfn/X6AV+f9aUzOof/1f7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKAPJfhH8F/B3wVsNV03wabgx6xqEupXH2hw586YKG24VcLhRgc/WvWqKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiivzZ0/4zftP/tN+Ldetv2c59N8L+FtBunsDql/H9onuZ4z8xjQo6gbSrBSowpBLEnaAD9JqK+Dvhl8Zf2g/A/xqs/gT+0ZZWmo/wBsxPLpmt6WjLCxjViUmXaACduPuqVbHDKwYfcOqatpWiWT6lrVzFZ20f35Z3WNFz6sxAH50AaFFY+ieIvD/iW0+3+HL631CDp5ltKkqf8AfSEipNY1zRPDti2p+ILyCxtlODLcSLEgJ9WcgfrQBqUVkaLr+g+JLIal4dvbe/ticCW2kWVCfTchIpJ/EPh+1vZNNub63juIYvPkiaVA6RZxvZSchcn7xGKANiisfRPEXh/xNp/9reHL631C1LMvnW0qSx7lOGG5CRkHgjPFZ2k+OPBWvag+k6FrFje3UWd8MFxHJIuOuVViR+IoA6miiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P+v0Ar8/60pmdQ//W/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACvzZuf2ff2lv2d/F+teKP2Wb7T9X0LW7l72fQNU+QpM/J8p9yA8cBvMjONoYNtDV+kjp5iFMkbhjI4PPpX5leGPjF+0z+zVqureC/jR4Y1vx7pn2lptP1zTUNy/ktgLHIFUAdM4YqysSBuUqaAPXvg1+1zqfij4jJ8E/jX4WufBniuZGe2jkbzLa7CKWPlPgYJAYjBdDtI37vlrxPxF4Rh/a8/a/8QfD74jTSyeDfh7BEI9OidoluLq4RcvI6Mr5yX5UghUUDG5s3PDejfGX9qP9o/wz8YPFPha58F+F/BYeS2TUVaO9upJBnGwqpwWC5yNoUHBYtgavxR8OfFP9nD9o+/8A2i/h3oNz4s8PeKrdLfWNPsVLXNvLEqKsqKoZiCVDZwRy6ttyrUAeo+HP2OtE+Fvxq0v4ofA7UD4c0wRNDq2kfvZoLxMEKQWkyrDORnIDKCAMtnwXw/4K039sj9qXxtN8WC974X+HlwNL0/Sw7RwtOXdJJHKMrE7oWLc5OUBO1cH2PwD8Yv2iPjh8XtLn8OeGr/wZ4F05HfUZNZt1jub1iDsjiV1JA3ADKHAG4ls7VrzrxBpHxO/ZM/aE8R/Ffwr4dvfFvg7x0VuL+DTIzLd2d3GWbdsGdylnkIPyqQ+CQUG4A5zxt4C0v9jf9pHwN4k+DofT/Dnjm9TRtW0wu8kIdpEWOVd7MwI80sOflKED5XIrK+JXwg0P43f8FCb3wV4rmnXSB4dgub23gkaL7VHE8ZWF2Qg7DKUc4IPyDBBwR2Vhp/xN/bA+PPhjx74h8N3/AIR8FeBZhfW0eqRGG6vbzcrrhDj5Q0adNygKwyS+F9L0fwj4si/4KD6r40k0u7XRpPCy26X5gkFs03mwnyxNt2F8AnbuzweKAPB/20r7wd8AvAnhD9nbwRI/hTwr4nvZm1ee282aWKyR4vOC7i7tv8wlgD823b91iD80fFfVP2AtO+Hzah+z7qd7o/jHSds+nXcS6gJJZUOSsjSjYNwzhht2nGDtyp/SX9sf4L+NfH1l4b+KXwujjuvEvgW9N/a2coyl3GWjaSLqAWzEpAyMjcAQSK8l1b9qz4z+MdFTwv8ACz4Q6zY+Krh0jaTU7QpYWxzlmaVljBGAQN/ljnOTjBAPtb4E+Ob34l/Brwz481QqbvVNOgmuCg2qZygEpUdhvBwOwr1isPwzFrkHh2xh8Tm3OpLBGLo2iskHnbR5nlKxZgm7O3JJx1rcoAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACvz/r9AK/P+tKZnUP/9f+7j4W/wDIiWP/AG1/9GvXoFef/C3/AJESx/7a/wDo169ApvcS2CiiikMKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACvz/AK/QCvz/AK0pmdQ//9D+5/4ceINHsfBlna3U22RfMyNrHrIx7DHSu3/4SvQP+fj/AMcf/CsH4W/8iJY/9tf/AEa9egVTtcS2Od/4SvQP+fj/AMcf/Cj/AISvQP8An4/8cf8AwroqKWgznf8AhK9A/wCfj/xx/wDCj/hK9A/5+P8Axx/8K6KijQDnf+Er0D/n4/8AHH/wo/4SvQP+fj/xx/8ACuioo0A53/hK9A/5+P8Axx/8KP8AhK9A/wCfj/xx/wDCuioo0A53/hK9A/5+P/HH/wAKP+Er0D/n4/8AHH/wroqKNAOd/wCEr0D/AJ+P/HH/AMKP+Er0D/n4/wDHH/wroqKNAOd/4SvQP+fj/wAcf/Cj/hK9A/5+P/HH/wAK6KijQDnf+Er0D/n4/wDHH/wo/wCEr0D/AJ+P/HH/AMK6KijQDnf+Er0D/n4/8cf/AAo/4SvQP+fj/wAcf/Cuioo0A53/AISvQP8An4/8cf8Awo/4SvQP+fj/AMcf/Cuioo0A53/hK9A/5+P/ABx/8KP+Er0D/n4/8cf/AAroqKNAOd/4SvQP+fj/AMcf/Cj/AISvQP8An4/8cf8AwroqKNAOd/4SvQP+fj/xx/8ACj/hK9A/5+P/ABx/8K6KijQDnf8AhK9A/wCfj/xx/wDCj/hK9A/5+P8Axx/8K6KijQDnf+Er0D/n4/8AHH/wo/4SvQP+fj/xx/8ACuioo0A53/hK9A/5+P8Axx/8KP8AhK9A/wCfj/xx/wDCuioo0A53/hK9A/5+P/HH/wAKP+Er0D/n4/8AHH/wroqKNAOd/wCEr0D/AJ+P/HH/AMKP+Er0D/n4/wDHH/wroqKNAOd/4SvQP+fj/wAcf/Cj/hK9A/5+P/HH/wAK6KijQDnf+Er0D/n4/wDHH/wo/wCEr0D/AJ+P/HH/AMK6KijQDnf+Er0D/n4/8cf/AAo/4SvQP+fj/wAcf/Cuioo0A53/AISvQP8An4/8cf8Awo/4SvQP+fj/AMcf/Cuioo0A53/hK9A/5+P/ABx/8KP+Er0D/n4/8cf/AAroqKNAOd/4SvQP+fj/AMcf/Cj/AISvQP8An4/8cf8AwroqKNAOd/4SvQP+fj/xx/8ACj/hK9A/5+P/ABx/8K6KijQDnf8AhK9A/wCfj/xx/wDCj/hK9A/5+P8Axx/8K6KijQDnf+Er0D/n4/8AHH/wo/4SvQP+fj/xx/8ACuioo0A53/hK9A/5+P8Axx/8KP8AhK9A/wCfj/xx/wDCuioo0A53/hK9A/5+P/HH/wAKP+Er0D/n4/8AHH/wroqKNAOd/wCEr0D/AJ+P/HH/AMKP+Er0D/n4/wDHH/wroqKNAOd/4SvQP+fj/wAcf/Cj/hK9A/5+P/HH/wAK6KijQDnf+Er0D/n4/wDHH/wo/wCEr0D/AJ+P/HH/AMK6KijQDnf+Er0D/n4/8cf/AAo/4SvQP+fj/wAcf/Cuioo0A53/AISvQP8An4/8cf8Awo/4SvQP+fj/AMcf/Cuioo0A53/hK9A/5+P/ABx/8KP+Er0D/n4/8cf/AAroqKNAOd/4SvQP+fj/AMcf/Cj/AISvQP8An4/8cf8AwroqKNAOd/4SvQP+fj/xx/8ACj/hK9A/5+P/ABx/8K6KijQDnf8AhK9A/wCfj/xx/wDCj/hK9A/5+P8Axx/8K6KijQDnf+Er0D/n4/8AHH/wo/4SvQP+fj/xx/8ACuioo0A53/hK9A/5+P8Axx/8KP8AhK9A/wCfj/xx/wDCuioo0A53/hK9A/5+P/HH/wAKP+Er0D/n4/8AHH/wroqKNAOd/wCEr0D/AJ+P/HH/AMKP+Er0D/n4/wDHH/wroqKNAOd/4SvQP+fj/wAcf/Cj/hK9A/5+P/HH/wAK6KijQDnf+Er0D/n4/wDHH/wo/wCEr0D/AJ+P/HH/AMK6KijQDnf+Er0D/n4/8cf/AAo/4SvQP+fj/wAcf/Cuioo0A53/AISvQP8An4/8cf8Awo/4SvQP+fj/AMcf/Cuioo0A53/hK9A/5+P/ABx/8KP+Er0D/n4/8cf/AAroqKNAOd/4SvQP+fj/AMcf/Cj/AISvQP8An4/8cf8AwroqKNAOd/4SvQP+fj/xx/8ACj/hK9A/5+P/ABx/8K6KijQDnf8AhK9A/wCfj/xx/wDCj/hK9A/5+P8Axx/8K6KijQDnf+Er0D/n4/8AHH/wo/4SvQP+fj/xx/8ACuioo0A53/hK9A/5+P8Axx/8KP8AhK9A/wCfj/xx/wDCuioo0A53/hK9A/5+P/HH/wAKP+Er0D/n4/8AHH/wroqKNAOd/wCEr0D/AJ+P/HH/AMKP+Er0D/n4/wDHH/wroqKNAOd/4SvQP+fj/wAcf/Cj/hK9A/5+P/HH/wAK6KijQDnf+Er0D/n4/wDHH/wo/wCEr0D/AJ+P/HH/AMK6KijQDnf+Er0D/n4/8cf/AAo/4SvQP+fj/wAcf/Cuioo0A53/AISvQP8An4/8cf8Awo/4SvQP+fj/AMcf/Cuioo0A53/hK9A/5+P/ABx/8KP+Er0D/n4/8cf/AAroqKNAOd/4SvQP+fj/AMcf/Cj/AISvQP8An4/8cf8AwroqKNAOd/4SvQP+fj/xx/8ACj/hK9A/5+P/ABx/8K6KijQDnf8AhK9A/wCfj/xx/wDCj/hK9A/5+P8Axx/8K6KijQDnf+Er0D/n4/8AHH/wo/4SvQP+fj/xx/8ACuioo0A53/hK9A/5+P8Axx/8KP8AhK9A/wCfj/xx/wDCuioo0A53/hK9A/5+P/HH/wAKP+Er0D/n4/8AHH/wroqKNAOd/wCEr0D/AJ+P/HH/AMKP+Er0D/n4/wDHH/wroqKNAOd/4SvQP+fj/wAcf/Cj/hK9A/5+P/HH/wAK6KijQDnf+Er0D/n4/wDHH/wo/wCEr0D/AJ+P/HH/AMK6KijQDnf+Er0D/n4/8cf/AAo/4SvQP+fj/wAcf/Cuioo0A53/AISvQP8An4/8cf8Awo/4SvQP+fj/AMcf/Cuioo0A53/hK9A/5+P/ABx/8KP+Er0D/n4/8cf/AAroqKNAOd/4SvQP+fj/AMcf/Cj/AISvQP8An4/8cf8AwroqKNAOd/4SvQP+fj/xx/8ACj/hK9A/5+P/ABx/8K6KijQDnf8AhK9A/wCfj/xx/wDCj/hK9A/5+P8Axx/8K6KijQDnf+Er0D/n4/8AHH/wo/4SvQP+fj/xx/8ACuioo0A53/hK9A/5+P8Axx/8KP8AhK9A/wCfj/xx/wDCuioo0A53/hK9A/5+P/HH/wAKP+Er0D/n4/8AHH/wroqKNAOd/wCEr0D/AJ+P/HH/AMKP+Er0D/n4/wDHH/wroqKNAOd/4SvQP+fj/wAcf/Cj/hK9A/5+P/HH/wAK6KijQDnf+Er0D/n4/wDHH/wo/wCEr0D/AJ+P/HH/AMK6KijQDnf+Er0D/n4/8cf/AAo/4SvQP+fj/wAcf/Cuioo0A53/AISvQP8An4/8cf8Awo/4SvQP+fj/AMcf/Cuioo0A53/hK9A/5+P/ABx/8KP+Er0D/n4/8cf/AAroqKNAOd/4SvQP+fj/AMcf/Cj/AISvQP8An4/8cf8AwroqKNAOd/4SvQP+fj/xx/8ACj/hK9A/5+P/ABx/8K6KijQDnf8AhK9A/wCfj/xx/wDCj/hK9A/5+P8Axx/8K6KijQDnf+Er0D/n4/8AHH/wo/4SvQP+fj/xx/8ACuioo0A53/hK9A/5+P8Axx/8KP8AhK9A/wCfj/xx/wDCuioo0A53/hK9A/5+P/HH/wAKP+Er0D/n4/8AHH/wroqKNAOd/wCEr0D/AJ+P/HH/AMKP+Er0D/n4/wDHH/wroqKNAOd/4SvQP+fj/wAcf/Cj/hK9A/5+P/HH/wAK6KijQDnf+Er0D/n4/wDHH/wo/wCEr0D/AJ+P/HH/AMK6KijQDnf+Er0D/n4/8cf/AAr4hr9AK/P+tIGdQ//R/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKydd17R/DOlTa5r9ylpaW4zJLIcAdh9STwAOSeBWtXyR+2bI6fCyyVCQH1SINjuPJmOD+IBq4Ru7Eydlc7w/tPfA0Eg650/6drn/41Sf8NP8AwM/6Dn/ktdf/ABquR+H37Onwb1zwFomtapo/m3N5YW08z/aLhd0kkSsxwsoAySTgAD0rrv8AhmD4Gf8AQD/8mbr/AOO1o1TWmpK5w/4af+Bn/Qc/8lrr/wCNVbsf2k/glqF0lnb66geQhQZIZ41yfV3jVR9SQKqf8MwfAz/oB/8Akzdf/Ha+dP2nPg38N/h54CtNa8H6d9juZb+OBn86aTMbRSsRiR2HVQc4zxTjGDdlcTckrn6DAhgGU5B6GlrhPhdJJN8MvDk0p3M+l2ZJPcmFMmu7rBqzsaoKKKKQBRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABX5/1+gFfn/WlMzqH//S/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigCC6uraxtpL29kWGGFS8kjkKqKoyWYngADkk9K+INY/4KV/sNaH4gbwze/ESxe5Rthe3huri3yPS5hheAj3EmPevjX/gr38R/HmuXPw8/ZC+Hd0bOb4i6gsV64Yr5iGeK3toXI58ppZC8g4/1a9sivrDwR/wTE/Yw8I/DuLwBqPg211pzCI7nUb0u17NJtw0gmVlaEseQsJRV7CvvcFkWW4fA0sZmsp3q35YwtdJOzk3Lz2X49vzXH8R5tisxrYDJoQtRtzyqc1nKSuoxUddFu393f7d8JeMPCnj3w/beLPBGpW2r6ZeLvgurOVJoZB0+V0JBweDzweDXR1+WH7DP7HHxs/Y9+NHjTQbfVLe++Fesb59Mge4d7uK4V08p3i8tUDeSXjlZWG/YhxwAPM/EX/BRb9pn4rfE3xD4F/Ys+Fo8TWHhedoLvUdTdolkKluVQyW6xiQIxiVpGkdcHYD8o5qnCDr4qpTy6op04pPnbUUk9lJt2TvpY7KXHKw+Dp1c1pSp1ZNx5EnNtx3cUk2421v2P2bor8/P2GP24n/AGsU8R+DvGfh5/C3jHwhMsOpWJcvG2WeMsm8K6MkkbJJGwJQ7fmbJA+Jfhr/AMFUP2lvjNc654E+EHwrh8R+KrC7kEYtpZEs7ezjJUS3LyOMuz8KoeMEA854qKXAeZSq1aPIk6dua8kklLZ3btbre5pW8R8phRo11NtVebltGTbcd1ZK909LWP3dor8zf2If2+PEX7R3xA8QfAn4xeFj4R8c+G4WuJ7ZC/lSRxSJFL8knzxujyJ8pZwytuDYBrhv2gv+Ci/xDtfjtcfsz/sceDE8e+KNLD/2nPIz/ZraSNtskRCGMfumKrJI8qIrny+W6ZR4IzF4uWCcEpRXM3dcqj/NzXtb5msvELKlgY49TbjJ8qSi+Zy/l5bc112t+B+tdFfmF+yZ/wAFBPEvxa+Mt7+zL+0J4Pk8D+PbSFpooN5aG4CIJXUK/wA6P5Z81MNIjxgsGGBu5r49/wDBQz4lL8dLv9mr9jPwWnj7xNpAb+1biZ2W0tZI22SRHa0Y/dsQskjzIqudnLZw1wRmP1p4RwSaXM3dcvL/ADc17W87g/ELKvqaxqm2nLkSUZc/Ot48lubmXa3nsfrFRX5kfsqft+eKPib8Zbv9mP8AaQ8It4F8fQQtPbwBy1vdqieYyxhssH8vMi4aRHRWIYYwfnrxf/wVF+ONj+0P41/Zz+HHw5j8U61pN/NY6PHaNLucQORJNdcnCKgz8oQZPLKBzrS4BzOdeeHUFeMVK/Mrcr2kpXs1537mFbxJymGGhipTdpScEuWXNzJXcXG10/K3buft5VS/v7HSrGbU9Umjtra2RpZZpWCRxogyzMzEBVUAkknAFeSfs9+J/i14y+D2jeJPjposPh7xXcrN9v0+DPlwsk8iR7cyS/eiVH++3LfhX5R/8Fa/HPjjx/4++G37E/gW9awXxzeRS6k4zh45Lhbe2D4IJiRxLK69GKIeq1x5Hw3LGZj9Qc0km+aS1SUbttW30WnfQ7+I+K4YDK3mSg5NqPLF6NuVlFO+zu9b7an21qH/AAUu/YZ0zX38NXPxDsWuUYoXihuprfI9LmOFoCPcSYPrX2V4Y8U+GvGug23inwfqFtqum3qeZBdWkqTQyqe6SISrD6GviPw1/wAExv2KvD3w9j+H1z4KttSXyhHNqF2ztfyvjDSm4VleNmPOIiiA/dUDivNP2CP2Rfjp+x/8RPG3g3UtUttR+GmpSvc6KhuGe7imWQLGzxeUqK0kBxMytgtGmFwePSx+X5JUw1SpgKs1OFtJ8vvq9vdts1vZ9DysszPiGliqVPM6MJU531p83uO11zc26e11bXofanwu/aT+Bvxp8S6z4O+GHiO21bVPD7lL+2jEiSREO0ZOJFXeodSpZNyg4yeRntPid8T/AAJ8GvBF78SPiZqKaVomneX9oupFd1j86RYY8rGrMd0jqvAPX0r+P/4aeIfjT8FPjp47/a2+E8X2mz8A+JBBrVuGIEtpqlzdJslABHkuYNjMclJHjYDIyP3a/b++Lngv47f8EuPEfxX+H9x9p0rWYdJmjJxvjb+1LVZIpACQskTgo4ycMDyRzX0We+G9PC5jhqNOblRqShFvS8ZO109LXs7rTbvY+V4c8VqmNyvF16sFGvShOaWvLKMeZKS1u1zRcZWe/a+n3V4n/ad+BHgz4S6d8dPE/iKG08J6t5X2TUGjmKS+eC0e1FQyfMFJ5UYwc16z4T8V+HPHXhmw8ZeELyPUNL1OBLm1uYTlJYpAGVgfcHoeR0IBr+e79rf/AJQ1/C3/AK6aP/6IuK1/+CZHx+8afs1+PrD9jT4/P9n03xTaWus+FLt2PlA6jGJ0gRmAHl3BYhQPu3KunLPxhifDyEstq4zCzbnCc1yu2sIOza03W78jowvihOObUcDjIJU6lOm+ZX0nNNpPydml57+X7aap+0J8HNF+MVh+z/qeuRReMNUhNxa6aY5S8kQSSTcHCeWPlic4Lg8e4z7NX4XfFv8A5Tf/AA7/AOwG3/pFqNfujXyXEeS08HDDSptv2lNTd+7bWnlofb8LZ/Vx08XGqkvZVZQVuqSi7vXfXyPj7x/+31+yF8LfGN/8P/HvjW20/WNLk8q6tmguXMb4DbS0cLKTgjoTXb/Cj9rf9mr44amND+FnjTTNW1BgWW0SXy7lgASSsEoSRgAMkhTjvivxr+DHwj+GXxn/AOCuHxi8L/FbQ7TX9Og066uo7e9jEsazLcaeiyAH+IK7DPoxr1P/AIKG/wDBPD4J+BvgnqX7Qn7PWmt4Q8TeD/L1Af2bLLHFNFHIu8hNxEUkIJlSSLaflIbOQV+zrcKZLCvRwE6lSNWpGDUvdcE5pWutHa/mfBUONM/nh8RmNOlTlSpTmnH3lNxg2m09Y3sr7H7l0V+enwQ/bZ8N/wDDA+i/tX/Gu5MRgsnhvvLUebc3ttM9ptijGF8y5kjDKvCrvySqgkfGsf8AwUk/bmuvBT/tCWvwRiPw3RftHmmeX7V9lB5mEmQxjCgkyi18sD5s7a+XwvAuYVqlSnFJcknC7kopyX2Vdq79D6/GeI+V0KdKpKUn7SCmlGMpNQf2pKKdl6/ofujLLFBE087BEQFmZjgADkknsBUFlf2Gp24utOnjuIiSA8bB1yOvIJFflv8AtJ/tP+Kvjf8A8E/dQ+L/AOzHoUevaf4h07ULTXIruVIptLsfsVwt7Iy+Ym6WBgMKu7eCGVWBBr5s/wCCNvjf9pE/D3T/AAO/hK1Pw1FxqEq6/wCcouBc5B8ryTNuYeZkbhEBjvxk7w4Hrf2bVx1SajKnLlcW0npe/XfTRWu+hhPxCoPNqGW0oOUasOZTSbWrVtlbls9ZXtHZn7zUV+O3xA/4KN/G34ifGDWPhJ+wp4Ai8dp4bOzUdWuZGW1MgJVlj+eBAu5WVHaX96QxRSoDN7x+xp+3bN+0V4v134KfFbw3L4L+IPhpTJdabIxZJolYK7xbwGUoWTch3ZVldGZSdvHi+CcxoYZ4mpFWSTauuaKezcb3S+XqduB8QsrxGKWEpTd23FPllySkt1GduVtWez16XP0Ror8iPjf/AMFG/ife/Ha//Zy/Yt8EJ481zRA41O7md/s0MsTbJYwqtEAsTlUaV5VXflADwx7b9lj/AIKCeK/jP478Q/s/fFrwZJ4Q+JWiWct1Dp7ufJujGitsHmbXjc71dRl1aPLh8Cqq8DZlDDfWpQVrKTXMuZRe0nG90vO3qTR8RMqqYv6nCbu24p8suVyW8VK3K35X9D9Mk1TTJL99LjuYmuoxuaEOpkA45K5yByO3evn7xv8AtZfAz4efHHQv2dvFmrm38U+Io0ks7cQyNGfOdkhV5VUorSsjBATnIGcblz/PR8Nfil+2vY/8FHfGnjfw38PLC8+I91pnl6noDXMawW9t5VmA6zG5CltqQniVs7zx/d/U342fHPTfDn/BQ34U/CjxB4E0K/1fWdIhn/tu5h8zUbBpZLtWit5eQFRoSV64Lvg/Mc/Q4nw/WFrxp1Je0TpOfuyimmo387xXR/aWx8xg/E365h5VacXScayp+/GbTTly6aRtJ9Vryv4j9WqK/Mn9r/8A4KC6l8F/ifp37OXwB8Mnxz8RNRAZ7FWfy7RXTzUEixjc7tHmQqGQJHh2YAjPnHwb/wCCjnxW0T456d+z3+214Hj8B6tru1dNvrd2NrJLI2yJGDNKCkjgoJUmZVfCsoBLL89Q4HzKphViowVmuZK65nFfaUb3a+XofT4jxEyqli3g5zd1JRcuWXIpPaLnblT8r+p+vtFflT+2R/wUR8UfsqftK+Hfg7Z+GE8QabrOkJfFYPMN/LdTS3UEFvAqnb+8lhjXO1iNxIBIAPjlz/wU5/aN+DHxQ0PRf2u/hUPCHhrxJMEtruGVpJYIyQGd2LNHKYyymRB5TqpztJwDthOAMzr0YVqcU1Nc0VzRvJLeyvdtdjDG+JmUYevPD1ptOElGT5ZcsW7W5pJWSd9G3+R+3NFFFfFn3wUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFc94s8XeFfAXhq98ZeN9StdH0jTYmnu729lSC3giXlnklkKqijuSQK6Gv5sf+C83iXxf8W/ip8B/2CvDd/Jp+n/ETXYpNUaMn5991BZ2pYD7yRGWaVlYFSyo2MoKAP1G8Af8ABVn/AIJ5/E7x3D8NfBvxT0mbV7mVYII51uLSKWVzhEiuLmGKCRmPChZCWJAGSQD+hFfgr/wUR/4JP/sb6N+wB4sk+EngnT/D2u/D/RJ9Y0/VbSILfTf2bCZpku5xiS6E0SOreaWwxDrggV9Yf8Ed/jz4n/aG/wCCfXgXxf43uXvdZ0yO40a7uZWLPMdPmaGGR2JLM7QCIuzHLPljnNAH6dV8OfGH/gpV+wr8A/HT/DT4r/ErStM12GUQT2aedcvbyEbttwbaOVYDjr5pXHfrVr/go58e9b/Zk/Yh+I3xp8MP5Wq6XpfkWMuceVdX00dlBKPUxyTq4Hcriv5mf2S/Hn/BGz9m39nXRbf9sG1t/iL8S/G9oNW12VrCTVZLBL/MkEImbCQSrCytKY3M/mMxYj5AAD+w34ffETwJ8WPB9j8QPhnrFpr2iaknmWt9YyrPBKoJU7XQkZDAqw6ggggEYrwD9o/9uf8AZM/ZHmtbP9ofxvY+Hbu8j86G0ZZrm7eLJXzBbWscs2wlSA+zaSCASRXwx/wRw/Zx+E3wV+G/irx3+zT8VW+Ifw18a363emafJYtayaRPAZFkilZ5mdp2iaJJQ8MRby0cKA3P5k/8Er/gv8If25P22fj/APF/9saxt/GXi3Q9WWKy0bWVFxBbwSXN1G7fZpcpIluIYreNSCkK8EZdCAD+lP4BftR/s9/tR+Hp/FH7P/i2w8UWlqypcfZHIlgZhlRNBIFli3D7u9BnBx0Ndr8V/i98MPgZ4Hu/iT8YNds/DmhWO0TXt9KIowznCqCeWdjwqKCzHgAmv5dvjXo/wn/4J1f8Fu/hXZ/stLDoem+P4tP0vxJoNmQLaFdXvGs/uZxEjYhuViGNrxhwNrha9D/4KxWVh8ff+CsfwI/ZL+OWozWXwxvbK2vZLYTNBDc3lzcXkbAuCAHm8iG2Vhh0EjbSC+aAP2m+Bv8AwUs/YX/aR8Yx/D74OfEfTtU1udmSCymS4spp2XkrAt5FCZjjnEe4kAkcA4+5q/mW/wCC3f7EX7HfwK/ZAtvjj8IfD2mfD3xj4c1awh0ebRUSwlvHllAeJhFt82SONWuFk5lUxEhsFgf2l/ZD+LfjH9pX9h/wV8WLm4SHxH4m8MxSTXAGxBqHkmKSUBQdqmdS4ABwOO1AG18fP24P2TP2XtYtPDvx68d6Z4c1G9jMsNpM7SXBj6b2hhWR0QnhWYAMQQCcHH1UDnmv4bv+Csv/AATb0D9i79nTwp8UvGXijUfHfxN8X+IXXXdevpZCsg+yySGOKN2Ziu5RmSVnkbHGxTsH9x6/dH0oAdRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABTWZUUu5AAGST0Ap1fjB/wXo+Pnif4F/wDBP/U7PwfcyWV9421W18NmeE4dLe4jmubkA9hJDbPCx64kOMHmgD6L1z/grT/wTk8OeOW+Heq/FjRxqSS+SzRC4mtFcHBDXsUT2oAJ5JlwOcng1+gWjazpHiLSbXX/AA/dw31hexJPb3Nu6ywzRSAMkkciEq6MpBVgSCDkV+Mv7On/AARv/Y0T9iPRvhX8Q/B1hf8AiXX9Ehn1PxC0StqcWoXUIkaS1uWHmRJBI2I41IRlQeYrZbPg/wDwbw/Ffxpd/CL4kfsueNrp7uT4W66kNqXOfJgvjOrQJnkIs9rM4B6GQjpgAA/ojJABJ6CvzW/4fCf8E1f+is6X/wB+bz/4xX6VEAjBr4A8X/8ABP8A/wCCbngXwtqfjnxf8J/B1hpWj2s19e3MumW6xw28CGSWRjs4VUUk+woA6n4Mf8FFv2Kf2hviBa/Cz4MfECx1/wAQXqSyQWUEdwrusKGSQgyRIvyopJye1Wfjd/wUK/Yy/Zv8dyfDP43ePbHw9rsUMdw1nPHcM4imGUbMcTrhgPWvwr/4IkfAXw38d/2sPiP/AMFE9D8M2/hHwha3dxo3hDSLOFbaCLzUVJG8uPC7obTy0kYZV5ppG+8tf0E/FP8AYy/ZP+OHitvHXxg+HegeJdZeJIGvdQsYZ5zHHnYpd1JIXPA7UAfNv/D4T/gmr/0VnS/+/N5/8Yr9IbO8ttQs4r+zcSQzosiMOhVhkH8RX8hH7Y37Ln7OP7Uf/BTrwR+wF+yz4J0bwxo/hVTqHjfUtGtI7eTyyI5p4WkjUHEUHlxIQcC4uNrDKV/VH8afBPjLxZ8DPE/w7+Eeqf8ACOa9qGjXWn6RqIZ0+xXMkDRQTBkBceUxDAr8wxxzQB5l8R/24P2TPhH8VNO+CHxC8d6Zp/i3VJoILfSt7y3BluXVIUdYVfymkZhtEhXIOenNfVVfxT/tjf8ABPr4d/sE/tN/su6foGr3/ibxN4r8WC78Q63qDtvvbmLUdNKskW5hGoaaQ8s8jFiXkfjH9hPxu+I8Hwc+DHi74u3UQnj8K6Lf6u0bHaHWxt5LgqSOgOzGaAPDf2gv2/P2Of2WNdj8K/Hnx9pug6rIkcn2E+bc3SpKcI7wWySyojdQzKBjnOOa9s+Dnxy+EH7Qfg5PiB8E/Edh4n0d5GhN1YSrKqSqAWjkA+ZHAIJRwGAIOMEV/HN+xJ8Xf+Ca3gX4e6p+1T/wUgmg+IfxN+JOqXt5Hps9k2rNaWUcpiMkkDAwRSSzLIVMjBhEsYiAUMT+vf8AwST+Af7L1n8Z/Hn7Uv7DPxNfUPAHiZDZ3ngeXT5IJNKuS6TQl5ZZ/MxF++WAmAqY5GUSOULUAfvnRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFfIv7aH/JLrD/sKxf+iJ6+uq+Rf20P+SXWH/YVi/8ARE9a0fiRFT4We+fCn/kl3hv/ALBVn/6ISu+rgfhT/wAku8N/9gqz/wDRCV31RPdlLYK+Rf20P+SXWH/YVi/9ET19dV8i/tof8kusP+wrF/6Inq6PxImp8LPfPhT/AMku8N/9gqz/APRCV31cD8Kf+SXeG/8AsFWf/ohK76onuylsFFFFSMKKKKACiiigAooooAKKKKACiiigAooooAK/P+v0Ar8/60pmdQ//0/7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooA/Cj/grpp2t/DD4v8Awc/azs7N73TvCuqxx3oQdGt7iK8gQnoPNCTKCcAEdeRX7F+CPjL8LPiL8PIfiv4P16yu/D0sPnm+EyrFEoGWExYjymTo6vtZDkMARW54++H/AIL+KXg+/wDAHxD02HVtH1OPyrm1uF3I65BB45VlIDKykMrAMpBAI/JrVv8Agh9+ylqGvPqVhrXiSxs5GLGziubZlTPRUkltncKP9ou3+1X6Fh8xyzHYCjhMwqSpzpXSko8ylFu9mrqzT2e1j8vxWVZvl2ZV8bllONWFflbi5cjjKK5bp2aaatdb32PoP9nr/goLon7SPxv8afDvwB4bkm8L+DraW4bxHHcmRLoo6oix2wgBHnYkaM+adyRk45wPh39n/wCKH/BQL/gojDrvxE8C/EDTfhn4QsdQexS0tLSO5ulYIso+Z0ErYjkXMhmjVmztQAED9ivgN+z18Jf2avAyfD74QaWum2G/zpmLNJNcTEAGWaVyWdyAPZRwoCgAfAPiv/gjj+zRrnjG/wDEvhjWfEXhmy1V2a70zTLqFLUq3JjjEkDusZOTtZnAzhQowB6GV5zkdOtXVKHs1aKhKUPabfE3FuylLTyW2h5mcZDxFVoYZ1qntWnN1Iwm6V725UpJXcYap3s3u79Pjr/gk7YnS/24/i7ph8RHxa0FrdRvrTcf2g66gga5+/LnzWywIdgQcgkGvU/+CJtrbo/xfvVQCWTWbRGbuVT7UVH4Fj+dfoB+zZ+wL8DP2UviJrPxG+E0upxy61aizezup45raGIOjgRfulmzlBzJK5POeea6z9l79jz4Zfslr4jT4cX2p3o8T3SXl1/aUsMmx49+BF5MMOF+c/e3Hpz69vE3GmCxVPGRot/vY0krq3wP3r20Xy07HFwjwDj8HUwEq8UvZSruVne3tPhs3q/nr3Pzd8C/uv8AguZ4zEfyh9Di3Y4z/wASuxPP4iuY/wCCT2r6X4P/AGqPjn8NvHcqQeLrzUg8STHEsy2t1eC62E9cNLG5AJ3Kd3RSa/UnSv2PfhnpH7Vupftg219qbeJtUtVs5bZpYTYhFgitwVjEIlDbIVPMpG4njGAPK/2pP+CbnwB/ao8YQ/EjxBJqHh/xJGiI+oaRJHE84i4jM6yRyKzIOFcbXwFUsVVQJfFuX16TwVaTjCdGlBySu4yp67X1XcceCczw1ZZhQjGU4V61RRbspQqK29naSWquj1O6+N/7LF5+1LafBt/sV58TYoGaNksGmuLeNYHlKteiIrF+63HaZBw4GMuAfwR/Y3+Gn7Qnin9pr4vfDz4b/E9fh14nh1SWS9gktI7qbUfJurkSOnmEECBnydudwlB6DNfuJ+yt+wJ8Bf2R9QvfEfgJLzVNd1BPKm1TVZUmuRGSGaOPy440RWYbmwu5uNzEAVzP7UP/AATg+Af7UfjGH4la5LqHh3xLEiI+o6PJHE84jGIzMrxyKzIOFcbX2gKWKqoGOS8SZbgqlbCUpydOcIrnlFStKLvfkenK+zu1v6bcQcJ5tmFKhja9OKq05ylyQnKF4yXLb2is+db3SSe22/xF4U/Zp8R6R+3l4M8SfGv49ab4l8f6FGhh0p7EQXk1kVnbyFMcgQEpJK2CCwU7sbSKf+wrbQN/wVL+Pd2yAyp9uRWxyFfUIiwB9CVGfoK+6/2X/wDgnf8AAL9lfxPcfEDwudQ13xLco0Z1TWJlmmiWQYkESxpGi7+7FWfBK78Eg+gfCf8AY8+GXwc+PPi/9ofwxfanPrXjUyG+hupYWtY/NlEzeSiQpIvzKMbpH4/OtMx4yws6eIoqo5XpKEXyRgr83M7KO0e19SMp4DxdOphq7pKDVZ1JLnlN25HFNyk3eW17WR9XV+Df/BVWLVPgt+0/8G/2vXtZLrRtFuorK+8pclfstz9pEeSQA80Uk3l5PVDmv3krhviT8NPAnxf8F33w7+JWmQ6vo2pJ5c9tODtI6hlIIZHU4ZHUhlYAqQRmviOE88jl+NjiKkeaFmpLvGSs/nrdH6Dxpw7PNMvlhaUuWd1KL6KUWmr+Wln5FLw38Xvhd4u+H0fxW8O+ILC58NyQ/aDqInRbdIwMsZHYgRlf41faVPDAEEV8h/sp/t46f+1r8YvGPgXwF4aePwz4UB8vxCboul2zS+XAFtjAhjEyLJIuZCQqDKgnj5pv/wDgh5+ynd662oW2ueJbWzdi32SO5tSFychVke1Z9o6fNuYj+LNfpz8EPgP8K/2dfAsXw7+EOlR6VpkbmVwCzyTTMAGlmkcl5HYADJPAAVQFAA9PH08ioYaosNKVWpL4brlUFfVuz95207dTyMsq8R4nFUni4Qo04X5uWXO5u2iV4+7G+r1v0ufjV/wSb8N6D4x+IP7SPhPxRaR32m6nqVra3VvKN0csMs2qo6MO4ZSQa+C/2qdA+Jf7COifET9jS9E2peAfH/2XVPD1zIf9U9te28zHd90yCOIwTqACWEUgCqcN/Rv+zZ+xz8Mv2WvEvjHxT8P7/VLy48b3MV1fLqEsMiRvC87qIBFBEVUm4fO8ucBeRg53P2o/2UfhR+114Bh8AfFRLmKO0uFurW8sXSO7t5Bw3lvJHKu2Rcq6sjAjBwGVWH2NDxEw1PPZ4iScsPP2batqpQjG0ku6kvmj4PE+F2MqcOQwsGoYqHtEmno41JSvFvtKL+Tt5n4x/tb/APKGv4W/9dNH/wDRFxX1v+0F+x2P2pv2Ffh9qvgxPJ8c+FfDemXuizxt5bykWcLSWhfjHm7QYySNkoU5Cl8/VHxF/YU+EfxN/Zo0D9lbXtR1eHw94dNs1tcW80C3rm1R0TzHe3eM5DndtiXnGMV9VeB/CWm+APBWj+BNHeSW00Syt7CB5iGkaO2jWJC5VVUsVUFiFAz0A6V4+M43jTpU54KTVSFWpPbS0tr+q0a7H0GC8Pp1q1WnmEU6U6NOno9eaN7tdrOzT7n8vP7KP7QHi/8AaM/4KVfCnxd8Q7doPEGlaZcaPqLOuxprizsb8GZkwNjurKZFwMPuwAMCv6rq+Jbf9gT4E6f+1bF+2BorahYeJEklnktLeWFdPmnnt5LeWZ4jCZN7rIWYrKoZ/mIJLbvtqvL4+4gweY16NTBR5Yxgo27O8m0vJX0PW8NOGcfleHxFLMJ88pVHJS/mXLFJvs3bVH4TfslkD/gsd8aM/wDQGvP/AEq0yvpb/gqP+1B8Nfhh+zH4n+G8es203ijxRanTbXT4ZFknEc7BZ5ZUUkxxiHeAzAAthRyeK/xo/wCCRn7N/wAdfilrXxc8W634lt9S124+03Ednc2aQK+0LiNZLORgMDu5PvXRfBL/AIJP/shfBHxPb+MbfT77xLqFm6y2z65OlxHDIvRxDDFDCzDqPMR9pAIwQCPosTnWR1cTQzGtUm5U4wXIo7uCX2m9r76bHyuEyDiKlhMTldClCMas6j9o53tGbf2FHdJ6e9vufmD+018F/HXww/4I7fDnw/q1pLBdW2uw6tqkRUq0MV+L54RKpwVK+fAjKRkOcHBFfQ/gX4DftY+LP2a9P8f2f7Sdrb+B59CWSTdpkDW9vZLBtlhkfdx5Kho5AcMCpBAIxX7f+LfCfhrx34ZvvBvjGyi1HS9The3uradd0csbjDKw/kRyDyCCK/Jaf/gij+zQ+oTx2fiXxTa6NcSec+mxXdv5W4HKjc1sxKr0G7L4/izzW+W8eYevQlTxk/Zy9pKd/ZxqJqTu0ub4Wns+25hm3hticNiY1cDB1YeyjTt7WVJpwVk24/Emt1vfYz/2cvhR4T+E3/BM34r+HvAXjaz8fabe6d4hu4b6wiaJI2fSlja3KM7sHUpvIOD8/Suu/wCCREkup/sFrp+hTqL1L/VIVIIzHMxDJu9Dhlb6EGv0f+H3wc+Gvwt+GVt8HfA+kxWXhy1ge2Wz5dWjl3GXeXJZzIWYuzEliSSa+OvgH/wTQ+Bf7Nfxu/4XX8LNU1u2kEdxGumTXEUtmEuFKlOYRMyICCm6UtuUFmbnPi4nifC4vDYulXnJSnNTi3FPmsmrStZJu61Wh7+E4QxmCxmBrYenFwhTdOaUmuXmad4uV3JKz0bT/T8a/wDgmb8K/wBov4geHfFfhH4LfFlfh5qOl6gH1DRnsI7ieT5FjFwfMIfCspjYYwrAZwWr7p/Zr/Z3uPCf7f8AL468ffG3TfGnjzTrOaDVdKSz8i7lia1EaBismz90DEzYUkBQDg19M/tC/wDBLv8AZ9+PvxIl+LsV5qvhPxBdHfdT6LLHElxJjBldHifErD7zIV3HJYMxJPrf7K37CvwJ/ZDa+1P4bw3d9rOpp5VzqupyrNdPFuD+UpRI40QuAxCoCxA3ltq4+hz/AI8wmJpVsRRqNSqxtyKnC6bSTvUtdx7W122sfMcM+G+NwlbD4avSUoUZ8ym6tSzSbcXGle0Za6393fe5+Zn/AARp1XS/CfxT+MPws8ZyLb+MjqETyxTNiaZbSW5juNoPJ8qVwX/66D04/U20+N/7LGsftRyfCHTvsd58TLKBmlki09pJ4I1h3Mr3yxFUxG20qZB94JjJxXkH7T3/AATQ+AH7T3jlfihq0+o+HPEe1FmvdIkjjNwYxhHmSSNwZFGAHXa2AASQBj0H9lX9hH4EfshyX+rfDmK7v9Z1NPKuNV1ORJroxZDGJDHHGiRlwGYKgLEDcW2rjwOI83ynHzqZk6k1VnFLkSslJJLWV9Y6bWv6H0vCmR51lsKWUqnB0ac2/aN3bi25WULK07u17tLsz4A+C9zb2n/Bbf4mQXTiN7jQgkSscF2+y6a+FB6nYpb6Amm/tX/8pi/gt/2Brb/0o1KvsL9qP/gmj+z9+1V47T4neKbjVNE14xJDcXOlTRILlIwFTzUmilG5EG1WXacYDbgBj07xT+xb8MvGPx98G/tH65qmsSeIPBNhDp9mgmg+zzpAZiHuFMBdpGM7lijoDxgDnPfDirL/AGlPE8z5vYOk422ko8qad9U/lY82fBuaOnVwnJHl+sKtGXNvFz5mmraOK83f5a/mR8AtU0rwF/wWe+JGnfEuVLe+12xuIdHefgSPN9juIUjY8bmtkdVOexTqcVH/AMFq9S0nxT4p+FPws8JOtx40l1CaS2hhIM8Ud00MMOQOR50yjZ6mM+lfpX+1j+wj8C/2worG7+I8V1YavpqGK31TTXSK5ERO7ynMiSJJHuyQGUlSW2FdzZ85/Zk/4Jl/s/fsy+Ov+Fo6ZPqPiTxEissF5q8kUgti4wzwpHGgEhXK72LMASFIyc74Pi7LI16GbzlL21KCj7O2jai4p819ItO7Vr+pzY/gjN54fEZJThH2Fao5+05vejFyUmuS2sk1ZO9ttj49/a5tLa9/4LD/AAVhu0EiLpNpIAem6O61F0P1VgCPcV0n/BdGKI/s1eFZyo3r4mjUN3AazuiR+OB+VfoN8Qf2Pvhn8Sf2lPDH7U2u32pxeIPCdqlpaW8EsK2bojzuDKjQtIWzcP8AdlUYC8dc2/2rv2S/hz+2H4FsPh/8TL3UrGy06/XUI30ySGKUyrFJEAxmhmUrtlY4Cg5A57Hz8v4twlPG5dXk3y0Y2lp1vLbvuj1M04Jx1XL80w8EuavO8NelorXtsz6M0JmfQ7N3JLGCMknkk7RWrVaztY7K0isoiSsKKgJ64UYGelWa/Lpu7bR+wwVkkwoooqSgooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAr+ZX/guM938E/wBsX9mj9r7U0kXw94e1qODUriNC4iWzvbe8KHHUywGfYByfLb0r+mqvEv2hv2dvhD+1N8LNQ+Dfxu0hNY0LUNrNGxKSRSpzHNDIuGjlQn5WU9CVOVJBAPk//gph+0j8Mvhf/wAE8fH/AMQJdZtZbbxX4du9K0OWGVHF7c6vbPBbm3wSJQBJ5x25HlozH5QSPCv+CKHhaP4E/wDBMHwt4o+JdxDodpqLahr8896628UFpPO/kzSySFUVHgRJQxIGxgc1494F/wCDdf8AYn8K+M7LxD4l1zxT4n0rTZTJBo+o3duLQgncUlNvbxSMhbkhGjz/ABZGc/r58dv2c/hr+0H8AtZ/Zs8YQy2XhnWbJLBo9NZbZ4IoWRofIwrInlNGhVShTA2lSuRQB8J/8FadKtf2kv8Agln8QdU+C19b+JLSays9YtbnTZkuoLi20++gubh4pIS6yBYYZG+Unla8J/4IrfDP9jrXf+Cc2lajpWlaHql3eLdp4ylv4beab7UkshaK9MoO2JINjRK2F8ohwMsSf1H/AGVf2Wfhr+yF8A9J/Z1+Gz3d7oelC4Ik1ORJp5mupXmlMhREjwzOflVFUDjHUn8tPit/wbzfsN/EPxne+KvCuoeJPBdrqcm+50rRru3+w8neRElzbzvGN/zBd7IvARFAAAB8qf8ABBz+xNP/AGvP2lPD/wADJnm+FlvqS/2SVdnt9gvrtbFomYtkNbBsMTudFUtyBiTxT+zR+x9+3r+3Z44vv2SPiT4m+B3xj8Nzzx+IYbW2Nt9tmhuGhu7q1EN1BLvMir57JKFcskhQszsf38/Zg/ZY+Cn7H3wrtvg/8CtJGmaVC7TTSO3mXN1cPjfPczH5pJGAAyeFUBVCqqqPiv8AbC/4I4/sjftjfEGT4v8AiMar4U8WToq3OpeH54rdrooNqvcRSxSxu4X5S6hHYABmIAwAfhN/wx58KPDn/BXj4OfAL4O+I9T+I3ijwzqUfinx34l1O6+0yyXVnMt2IZSCwTyEtkBVi7F7hUd2bhf1d/4LAaZ+wb8XPGPgH9nD9qu61Xwn4s11w/hjxXZWyNBaNNMIHhuJ3YDyfM8syowAQMj705Nfcn7E/wDwTe/Zh/YJ02+X4Kafc3Or6ooju9Z1WRLi/liXBEIkSOJI4tw3FI0QM2C24quPQf2vf2Jf2fP24fAEPw/+PWktdpZSGawv7VxDfWUj4Dm3m2ttEgUB0ZWR8KWUlVIAP5fv+CnX7CHgD9kX9miTxL+0N8afEnxc+IGomLTfBWnatdSLFaI88T3dzHbSXN1KyR26GPcJFiDugZCxTb/UN+wt8Kda+B/7HHwz+FPiaD7Lqmi+HbGG+h/553TRK86H3WVmB9xXwf8As2/8EJ/2KP2dPiZY/FiV9b8aappEqy6eniG4gntrd4+IXEEFvCsjxcFDJuVWAZVBVSP2eoA/ml/4Oav+Tavh1/2M0v8A6Ry1/Swn3B9K+H/26P2A/g7/AMFAvA+i+AfjLqWs6ZZ6FfNqFu+izW8MrStE0RDm4t7lSu1icBQc9+1fcIGBigBaKKKACiiigAooooAKKKKACiiigAooooAK/CD/AIOJfhjrvj39gGHxNoUTSr4Q8S2Gq3e1SxFs8NxZMeOgEl1GSegAP1r93657xb4T8M+PPC+oeCfGlhBqmkatbyWl5Z3KCSGeCZSkkciNwyspIINAHyZ+zd+1f8IfGP7D/hr9p7UtdtYPD9r4dt7nVbqSRQtpPbQKt3DLzxLHKrIU6lsBc5GfyG/4N4dE1zxdH8dv2oL62ktrDx74lgW0Eg53WzXd1Ng9GA+3IpI43KR2Nena1/wbl/sT6j4pk1HS/EPi7TNCmuBcNokF9bvbKR0RJJrZ5tuMrl3eTBPzjrX7S/Cj4F/Cn4H/AAk0/wCBvws0eLR/C+mWzWkFnCWHySZMjO5Jd5JGZmkkZi7sSxJJzQBveAfin8MvirY3Wp/C/wARaZ4jtrG4e0uZdLu4btIbiP78UjQu4SRe6kgj0r8Mf+C7H7Q/i7UPCvhD/gnn8DSbnxr8Xb23iuoYmIePTfPCRo5HKLc3Awzcr5UMwb5TX6PfsNf8E9Pgb/wT+0TxLoXwUutWvI/FF5Hd3L6tcRztGIFZYYYvKihUIgduWDOxPzMQFAraR/wTu+Cdj+23eft763qet6340nt2trW21Ce3k07T1MK2wNnDHbRyRlYQyDdK4/eSMQXbcAD3X9lf9nnwj+yn+z74V+APgkBrPw5YpA8wUKbi4bL3FwwH8U0zPIR23YHArl/21v2n/Dn7HX7Mviv4/eIdksmj2hWwtnOPtV/N+7tYOOcPKy7yMlUDN0U19UV8N/tvfsC/Cn9vrQPDvhD4za5r9ho3h29e/Fho9xb28N3OyhFa5862nc+Wm9U8t4yBK/JJUqAfAP8AwQl/Zh8R+Dfgprn7Zfxh33Xjr4y3b6o9zcD98NOaRpY3PobuVnuG24DIYePlr94qztH0jS/D+kWug6Hbx2llYwpb28EShY4oolCoiKOAqqAAB0ArRoA/ml/4Li/8no/sjf8AYzSf+nHSa/cn9sf4f698V/2Svib8M/CsZm1TXvC2r2NlGvWS4ns5UiTj+85A/GvL/wBqn9gP4Ofte/E/4c/Fj4lalrNlqPwxvm1DS49Mmt4oJpWnt5ytys1vM7LutkGI3jOC3OSCPuGgD+ZX/g3T+Hf7M2tfs6eLL2603TdQ+IkWrzW2tJfRRS3kFgY0FsipICyWzkSZwAHkDhs7ABwn7DNh8PvC/wDwXt+KXhn9k/yU8A/2Nc/2jDpxBsI5Vjs2uFiCEoFj1FmRQMBCXRMJwf0H/aY/4IV/sY/tG/EvUfi3aT634J1nWZJJdSGgXEMdtdSTEmaR4J4Zgjy5O/yyiMSWZCxYn7S/Yw/YM/Z4/YP8DXPgv4GafN52ousmo6pfus1/esgwnnSqiKEQE7I40SNSWIXczEgH2ZRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFfJH7Z0bv8LbJkBITVIi2Ow8mYZP4kCvresnXdB0fxNpU2h6/bJd2lwMSRSDKnByPoQeQRyDyOauErO5MldWPmv4fftF/BvQ/AWiaLqmseVc2dhbQTJ9nuG2yRxKrDKxEHBBGQSPSuu/4af+Bn/Qc/8AJa6/+NUp/Zh+BpJJ0Pr/ANPNz/8AHaT/AIZg+Bn/AEA//Jm6/wDjtaN03rqSucP+Gn/gZ/0HP/Ja6/8AjVfOn7Tnxk+G/wAQ/AVpovg/UftlzFfxzsnkzR4jWKVScyIo6sBjOea+i/8AhmD4Gf8AQD/8mbr/AOO1asv2bPglp90l5b6EjPGQwEk08i5HqjyMpHsQRTjKCd1cTUmrHb/C6OSH4ZeHIZRtZNLswQexEKZFd3SABQFUYA6ClrBu7uaoKKKKQBRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABX5/wBfoBX5/wBaUzOof//U/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigAor+aL/AILaz+O/2U/2nfgn/wAFA/BF1eDTNN1GLSdbtIZXWGYW0jXMaNHnYWubZrqJiccIv4f0N+Jfil4I8LfCm/8AjVqV6h8OafpUutSXanKGyigNwZQTjgxjcKAPQqK/ms/4ITp41+K2q/Gb/gof8bdSlhh8S6nc2toLu4cWtpCH+337qZCEWFC8EasAqoIXHQED6q1X/gv7/wAE4NL8bSeEf7e1a5tY5DG2qwaZM9lwcFh0uGX3WE5AyM8ZAP2por51+IH7VPwV+H37OF3+1fcaqNW8EWljHqIvtMAufNt5HWNWiAI3fMwBGQRyDggivijwr/wWk/YZ8d/EjwP8JvBGrajq2uePJ7O2tYbe0ytpJfOEhW8kZ1SNskF0QyOgI3KDxQB+sNFfmN+1V/wV5/Yj/ZB8dT/C/wCJOvXWo+JLRUa60/R7Y3cltv5VZn3JCj7fmMZk3hSCVGRn3z9lD9tv9mv9ufwZqHiH4B662oLYFYNRspkktb20MoOzzI2wwDgHZIjFCQQrblYAA+rdO1bStYjkm0m5iukhkaF2hdXCyIcMjFScMp4IPI71oV+K3/BFTwt+xn4d+Fvjyf8AY01rxLrWmXGvKuov4kVEkjnSEGOOFIlRSojf5pCNznqcBQOr+OP/AAXI/YA+BPxIvvhbrGt6jrmo6XO1rfS6NZG5treZCQ6GZ3jWQoRhjF5gB4zkEAA/X6ivC/gT+0n8F/2l/hPB8bPglrceueH5xIDNGrJJHJD/AKyKWKQLJHIvdHUHBDDKspP5wz/8F4f+CeNv8MU+J0mu6lsmvriwg00WDHUJXtooZZJBEG2pFidFWSV0DsHC5KNgA/ZKivk39kn9tz9nP9tzwfeeMf2ftbOoppkqwX1pPE1vd2ruu5PNhfB2uM7HXcjFWCsSrAfT+tXd5YaNd32nQ/aLiGGSSKIZ/eOqkqvHPzHigDTor+GH/gqJoX/BS2T4T+Hf2s/2yvFDeG5PEWr/ANnaR4L0uWSGPTIHgkn8yRYpNiSnywCHaWYg/vHUqIx/SJ/wV1/bF8efsW/sRS/ET4XyJB4m1++tdB067kQSC1luoZZpLgI3ys6QwSeXuBUSFSysAVIB+rVFfy0+A/8AghR498ZfAOx+PuofGPxPH8bdW0yPVob0XjG1S5mjE8dvJMc3jHJVGnE4wwLiMgBa/Q7/AIIpftu+Nf2zf2V5x8Wbhr3xh4Lvv7K1C8cKHvIXQS21w4UACQoWjfj5mjLk5Y4AP2IrCu/FPhnT9Zg8OX+o2sGo3Q3Q2skyLNIOeUjJDMODyB2PpW4SFBZjgDqa/mp/4JY3j/t2/wDBQ34x/wDBQnxmPtth4ZkXw94QSX5ltreYyKrRdkdbRBuxwWupD1bNAH9K9FfG37Jf7dnwE/bQuPFOnfBya/S+8G3MVpqtpqVsbWeGSUyBfkLMSN0Mik9mUik8Q/t2/AXw9+13pX7EMkt/d+PNWthdrDbWxkt4YzDJcfv5twEZEMRcgjoy92xQB9lUV+ZX7WX/AAVz/Yr/AGN/HrfCz4n61eah4kgRHutP0e1N1JarIAyee5aOJGZTu8vfvCkEqAyk/Q/7J/7bP7N/7a3hK68W/s+eIF1VdOdEvrOVGgvLRpN2zzoJAGVX2tscZRsEKxKkAA+rqK/JHxp/wW1/YK+H154z0nxXrWpW2o+CNWOiXVl9hZp7m7V7lGFqqsd8aG1ffK5SNd0YLAyKD7149/4KU/smfCv9nDwp+1B8TNdk0TQfG1rHd6NaTwl9RulkVXKpawmRiYwy+YwJRMjcw3LkA+9Kz21bSk1RdEe5iF68ZmW3Lr5pjUgFwmdxUEgE4xmvzD/Zg/4LHfsO/tYfEi3+EfgDW73S/EF+Stja6xaG1F26gkpDIGkjLkDKozqzdFBPFeN+NfCH7F83/Bajwr4g1nWvE8fxj/sN5LPTYtv9ivCtjdLveTb5ikW6y5jVwjPtJHLbgD9sKK+Ff2xf+Cjn7Kn7DH9n2Hx21uWPVtVjae00rT4GurySFTtMpRcJHHuyFaV0DkMEyVbGR+x1/wAFN/2SP25NUvPDHwS1udNesIftMuk6nbta3fkZCmWMEtHKqsQG8uRimRuADKSAfoDRXwD8cf8Agpl+yV+zf8b7j4CfGbWrjRNXtNIbW5riW3ZrRbZY5JABIhLPK/llUiRGd3KqoJIry79nP/gsp+wp+098Vbf4M+AfEF5Za5qEph09dVtHtIr2QDISGUkrvfoiSbHc/KqkkAgH6n0UV/Px/wAFPPCn/BSH4/eIviH4G+G2rJ8Ovgr4G0CTVbvV4S8d7rs0Nh9sltY2RxK8YceSwUxQ/e3tKw8sAH9A9Ffhd/wQi8c31r/wTSl8b+L7u4vxp2r6zcSySu0snlQKjkAuSegOBmvzY/ZH/Zf+Jf8AwXM1Pxj+1f8AtY+PtY0Xw1Yau+k6LoWhyqkdrLFFFcYjE6SRJHEk0Q3CMyTPuZnUjkA/r4rM1nWtH8OaVPrniC7hsLK1QyTXFxIsUUaDqzu5CqB3JIFfze/sG/Ev43fsK/8ABSDUv+CX/wAX/F95448Ja9ZNf+FL2/cvNassD3ioS5ZkWSKOaOSMMU81FaMLvYH6d/4L7fFrUPBH7Cj/AAs8N75NY+JGt2GhW8MR/evGr/a5do7hjAkRHfzQOhoA/aLQ9e0PxPpMGv8Ahq9g1Gxul3w3NtIs0Mi5xlHQlWGRjIJrWr8Mf24/hl+2n8If2N/hP+xh+wjpt951za22ha7r2m/JJYWlpDBC8nmhlaI3MkjSPKnzhUcLjdX5/wD7af8AwTK8Sf8ABNz9na6/bW/Z7+M/iweNvDF1p0+qvfXKeRqTz3MVr8kahTgPKrGK4a4V41ZGznNAH9Z1FfiF+1f/AMFIviB8Jf8Agkn4W/aysIodO8d+P9L0u0sMIDFBqGoW5lmuI433AqkUc0sStuGdgbcM5+EPAP8AwQ++LfxO/Zws/wBpTxZ8WfFMXx21jTU1u0eS8byYLiZBcRWk8zZuvN5VHmWZRG+SEcKNwB/Tx8RvH/hv4VeAdZ+JfjJ5YtI0Gzmv72SCGS4kS3gQvI6xQq8j7VBJCqTgdK4r9n79oX4RftRfC6x+MnwP1dda8P6g8scVwI5IXEkLmORJIpVSSNlYdHUEghhlSCfzb/4Itftm+MP20f2TLuw+M8v9o+K/Bt62i6nPMoL3tu0Ye3nnXGC7IXikyPnaMseWNfF3/BHTULv9mr9vv9ob/gn+JMaJZXs+v6NDztijhuI4Rj/aktbm13D/AKZcdDQB/S9RRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFfn/X6AV+f9aUzOof/V/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigD4N/wCCmf7Nv/DVn7Enjv4UWEHn6uLE6lpIUZf7fYH7RAiehmKGEn+7Ia/ms8Xf8FDbrxL/AMEH/D/wV0+7abxnqGrL8P5Ios+ebCx2XasicsyNZm2tGxnczsBjt/aLX8xvgn/gg3458Mf8FGYP2hbvV9Ck+FFh4om8SWmkrNc/2gmWNzb2/wBnNqLfYlyI0b9+d0KDOW+WgCz/AMFHvhh4i/Yf/wCCHHhf9nvwmzWs8txpWm6/JA23fLdmW+v8sDkpJdrsxnlDtPynFee/A3Wv2zIf2KtC/Z98OfsYaXrfgzV9At1e7/tmyjOpfabcMdQYODIs0xczKS2+NmAUjaMf0W/tQfs3fDj9rb4G698A/irFI+ka7EqmWBtk1vNEwkhnibkB4pFVgCCrY2sCpIP4XeEv2Fv+C4Hwe+Gkn7Lvwo+MfhWXwLBC1hp2p3YlTUbSxOR5UTfYZpYiFJVFEsnlDCxyIFXAB4n8O/gd+0z+zh/wQm+N/wAIP2mdCudBu7G7luNKt7meGfFjcyWLssfkSSKq/aBM+Mg7nY45yf09/wCCK/wE+Engb/gn98PfGeh6DZDW/EFvNqd/qLwRtdTTtcy7C0pXdiJFRIwDhQoPUkm9f/8ABODx1oH/AATG8TfsReGfGUnibxV4htiZNa8QXFz9na6eaFyqj/SpILdEiCIiBucsRuZjX19+wt8B/F37MX7JPgb4C+PLmzvNY8M2BtbqaweSS2dzLJJmJpY4nK4YcsinPagD8IvEv7Pn/BQf/gnj+3b8TP2rvgh8M7P4z+FviDfXV+zowfU7WK5ne5NvEATcxPGzmMmOKaKSNUyAwCp9ff8ABKv9pj9i74+fGz4gXPw1+F03wm+MNxE134n0y4aRjPGsyJM0efLVfLnZBKht4GDuDtJZjXGeM/2Bv+CnXwA/aI8YfFv9hL4q6be+HvG9w1xcaR4vlnuGs2Z2dI4i8FyrRwNI4idWjYJtR1kxuP0D/wAE7f8AgnD8U/2c/jH4z/a3/ap8XWnjH4qeOImtbqbTovLsreB3jkk2FooCzO0UY+WGJUVAoByTQB+Mf/BMzxt4q+HX/BIv9qTxh4JmkttUtLm8EE8JKyQmWxiiaVGGCrRq5ZWHIIyORX6rf8ELv2dvgdp//BOnw541TQtP1PVPG0moza3c3MCTvOYr2a1S3fzVY+VHFAg8v7m7c+MuSe2/4Jh/8E1/G/7Jv7PXxH+A37S0+ieIrHx7qE7zQaVNcywSWNxarbSxStPBbOrMNw+UHAOQ2enx34X/AOCa/wDwVb/Y0v8AX/hp+wB8WNDh+HGsXct1Z22vKrXdi82AWxJY3SB1RVUvEwWQ5cxK2KAOH/4JdaVZfBD/AIKdftPfsy/C5mj8C2lle3sNojM0NtPbXcUcUSgngxpcyxZ6kRgEnAq7/wAG1/wV+GWq/ADx38YNa0a0vten8Qto4uriFJZI7SCzt5vLjLg7Vd7hi4XG7C7s4GP00/4Jy/8ABNmx/Yh+HXiXUPFmtf8ACVfEnx0zza/rbmQxuxLskUPmfOUDyM8kjjzJXYs2AEVaP/BIX9hX4t/sBfs++IPhT8Y9R0jUtR1bxDLq0UmjTTzQLA9pawBXa4t7dg+6FiQEIwR82SQAD89f+CbnhrQvhN/wW1/aN+Efw9tYtL8O/wBkzXqWNuoSGOT7XYSKI0HCIhupQqgAKGwAAAK/pmr8kf2df2CvjB8I/wDgp98V/wBtXxJqWjz+FfHWlPY2FrbTXDahHI0li4M8b26QquLV+Umc5K8cnH63UAfzZ/8ABzN/yax8P/8Asa//AGxuK/Ub/got+zZ8Jv2rf2RLz4R/FnxJaeEUme3udK1e9liihttShRjAW81lV1dTIjoCGMbNtIIBHi3/AAWA/YJ+MH/BQH4LeF/hz8G9S0fTL7RNb/tKd9amuIYmi+zSw7UNvb3LF9zg4KgYzzng/Zv7Wn7KngX9sT9nHWf2dfiNLJa2mqxQmO8twpltbq3dZIZ4wwwdrqAy8b0LLkbs0Afhp8Mfh3/wXi0z4J237LE+o+DtL8F2+nrYR/EB7uO4uodJCYD28sU+9ttv8sUj2iybdpMqt+8Fz/g2q8FxaN8Kfi34q0qeS70q88R22n2lw6GNZlsYHfeFOcMy3KFhk4yAay7P/gmX/wAFkrb4Up+x/F8dPD8Hwpjt/wCzxJEkv2/+zj8v2bP2IT7AuV8r7YE8s+Xv2fKP3h/ZG/Zb+Hf7G3wE0T4AfDIyy2GkK7y3Vxjz7q5mcyTTylQBudjwBwqBUHCigD1D4vS3sHwm8UTab/x8ppF60WP74gcr+uK/CH/g2nXTx+xH4uaD/j5Pje78312/2dp+z8PvY981/Q7PBDcwvbXCh45FKsrDIKkYII7giv5qP+CNMd1+x1+2V8cv+CdPjiU2zR3q654cWUFftVrFuVpEZvvNLaSWsm0HICSddrYAIPDyW/7Af/BeLVtOvHXT/BPx70uW9R3wlvHfS7p3Z2Jxv+228wH91bpcjnNVv+CR9rqn7TP7Vf7Qn/BT7VbY3Md1dXOjeGhIpyYgqy7MHo8VpFZRZ6kO446H7v8A+Cu//BOLxp/wUA+HvhFvg/qOm6N4y8I6lJNbXmqSzwQmzuY/38YktoZ5BIJYoHQ7CBtbkE5r6y/4J/fsqx/sX/sm+E/gDcy29zqmmQPPqtzalmin1C6kaa4ZGdI3ZFZvLjZkVjGi5UHgAH8q/wDwST+KH7WGk2Xjr47/AAg+Alv8Z/EXiDWZF1PxNe6pbW1zBI6LPJbqlwCw8xpTK7rgSbgpzsGP0O/YL+AH7Z/hr/gqLqv7TXiz4LH4TeDPGWl3Vrq9jZ6haXFlHceUkizeXDICWmuIQxAiwHkY55NeoeJP+CZX7b/7J3x48R/FP/glx450bQvDHjGUXOpeGPEAdreGfJOIR9nuFZFZmMbAxSIp8vLr1+p/2Df2Gv2pvhP8ZvEn7UX7Z3xOfxj4y8RQ/Zl0vS5p00a1T5B5giZYI3kVEEcai3RYxuOXZtygH5n/APBIX4JfC74jf8FHP2pPiH470W01fUvC/ia6i0xryJJltzfapqJmkRXBVZCLdVDgbgpYAgMc/W3/AAV5/YY/aS+Mvjv4WftIfspaVpviW/8AhfMXPhfUPKW3nVJ4riNkimeKGRCYtk0fmRuyBfLJYce+f8E8v2Cvi9+yV+0d8e/i/wDEbUtHvdM+KWuDUtJi02a4knhhF5f3GLpZreFEfZdIMRvIMhucAEy/8FFv2Fv2j/2g/HXhD9oH9kb4jSeC/HHgzasNpezzjSrpUkaRHeONZkEq73Vt8EizIwRwFUUAfnNZ/t4/Bj4iftT/AA48J/8ABTr9nG7+Hfj7TbyCDw34gkM/2aO4aaIwybSsBMCTrHscPdJCxJ+UF2rt/iR/ysneAP8AsU5v/TVqVdPY/wDBM/8Ab+/a1+PfgX4r/wDBSTx94evPD3w+uxfWGieHYCTNKJIZHSVjbQKqTtBH5rFpW2KURY924fW3iz9gr4va9/wVw8Mft72mpaOvg/RdDk02ezea4GpNM9nd2wKRC3MBTdOpyZwcA8ZwCAfnD/wT28G+Fv2jv+CyP7R3xN+OVrDrWteCdSvLLRLe+QSrbww30ljHLGj5UNDbwIint5hYcnNM/wCCungnwp+z5/wUc/Zn+PfwVtIdG8V+Itb+zamLFRCbuO3vLKJTIiYVmnjvJ4JGPzOmFJIUY+uv2vf+CYv7QcX7VB/bl/4J0eMbHwT481KJodcs9T3GyvtwVWdf3NymZVRfNieLYXVZVZZBk5H7NX/BML9pzxx+1Zp37Z//AAUv8Z6d4y8R+GFj/wCEe0rSQRZ2skLmSGV8QWyKIHYukaRndJiR5GI2kA+Xf2lvhb4I+MP/AAcU/DzwZ8RNPh1XSR4fjvZbS4QSRSyWVjf3MIdG+VlWaNGIIIOMEEGtn/gvP8P/AAX8Pfid+z18Z/BGl2uleI7fxMLX7ZaxJE7xW8trPAshQDcIXBMefu7mx1r9B/Fn7BXxe17/AIK4eGP297TUtHXwfouhyabPZvNcDUmmezu7YFIhbmApunU5M4OAeM4Bf/wVP/YN+L37cCfDFfhPqWj6f/wheuvqd9/a01xF5kLeV8sPkW8+5/kPDbB05oA/WmvnH9sX/k0b4qf9ihrn/pBPX0dXk3x78Cav8UvgX40+GPh+SGG/8R6DqOl20lwWWFJry1khjaQorsEDOCxVWIGcAnigD8gP+Dfi30+7/wCCbKWurKjWsmu6ukwkxsMZ8sMGzxjGc+1fHHwT/Zf/AOCin7CvxC8V2n/BLjVfCfxX+FfiG/8AOS21DULeZbCbYABcbbq2InjjKoXilYSoqM8YOFH7Af8ABLH9j74lfsQfsow/An4tXumajq0eqXt60ukyTTWxjuSm0bp4YH3Dadw2Y9Ca/OC7/wCCU37ev7JHxY8V+Kf+CX/xP0jw14W8ZTCa40bXYlb7IxZyqxA2V5CywFyInCRyCPCN5m3LAHxJ8Dvg/wDtCWP/AAXm8BN+0h4ltfFHj2TTrjxB4lbTAfsulFtOvFtrFDtX93HB9lGdoGZcZf77/fn7bq/8NQ/8FnPgF+zNGDcaR8OLWTxfqgB+RJ9xuUWVe4Js7Vee0+OhOfrj/gnP/wAE2td/ZN8WeKf2h/j/AOKz48+LfjbdHqerDcYILdnWRoYGkVZG8xkQuxVFCpGiRqqZb5I/4JSKf2kf+Cgf7S37cl4omszqa+FNEuM7g9pA4BI7A/Z7SzbjP3yPqAfv/wCJ/E/hzwV4cvvF/i++g0zStMgkuru7uXWKGCGJSzySOxCqqqCSScAV/L14x8TfFL/gvR+0fH8N/h99q8P/ALNPw+1FZdS1NlaKbWLpBwEDAESyIxEMZH+jxOZpf3jxxV+lH/BXb9iv9rb9ub4ceGfhP+zn4r0jw/oMVxc3HiK01a4ubZb9l8g2Kg2trcM6RMJmZH2qWMbYZlBX4R+Df7BX/BeP9nz4caZ8I/g18Y/h5oHh3SEMdrZ29nCQu4lmZnfw60kkjsSzySMzuxJZiTmgDof+DjPwDbeGv2Evh/pPgqxWz0Lw74ns7OO2t02w20C6ddRQKFH3UQIEXsMgdxX9Avw48W6B4i+FOg+OtNliTS7/AEm1v4pQw8oW8sCyqwbptCHOemOa+RdV/ZK8d/tK/sJD9mL9urWrXxB4r1SzZNV1nSERI1vI7hprW5tlFvbKGiAiyPJQNhlIIYk/jnaf8E1f+C0PhP4SyfsceDvjN4ePwtdXskuJDKl6umynD24Y2UlzGpUkCFLkqF/diQRnFAHU/wDBujF/a7fH34haMhXQtY8SWa2OAQn7v7ZKwXPORHPFkHoMVH+y8Y/Ef/Bxf8atX0EZtbHw86TlOV3xQaTbyAn187OR6g1+tv7Mf7O/wp/4JifsbzeD9He51S08OW11rOsXsVuWu9SvNgaaSOCPcS7hEigiBZgqohZmBY/n/wD8EQP2ffiWo+Jv7dvx20yfSfFHxd1m4mtrO6R4pYLNbmWaVtjqros1w5VAwH7uFGUBWGQD99qKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAr8/6/QCvz/rSmZ1D//W/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAryfWfgR8F/EPxT0344a54W0u68Y6PD9nstbkto2v7eLEg8uO42+Yq4lkGAcYdvU16xRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABTI4o4hiNQoPPAxT6KACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P8Ar9AK/P8ArSmZ1D//1/7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKK+TP2rvDmqeItC0qC++IEXgHw0twf7WmEgtrm5THyxQ3BcBScEbNp3ZycgbT8G+EvHXw1+Ef7SvgfQf2d/H2p+JtL8QXRsNZsLyd7iFfNKJFKrNGkZYsxYlcspXqFbbQB+0tFfmB8SfDPjX4m/t2Xfw10rxLqWhaRN4Zinv/ALBMY5WgSZSViY5EbvJ5YZwM7Ny9GNafhXwzrn7Mn7XPhj4ZeHPEGp6p4W8bWN2Ws9SnNwYLi1jeXejEDGcAcAE7juzgYAP0sr59+CnxvuPi34o8b+HZtOWxHhDWZdKV1lMnniNmXzCCq7Cdv3ct9a+gq/ID4J/BPUfjV8aPi9p2t+IdT0jw5Z+J7pntNLmFu93cyTTDM0oBYxxoOE6FmzkbeQD9f6K/PL9mi88TfCX49+PP2d9b1y81zQ9Hs7fVtNmv5POmhikVPMjLnnA3gYGF+UsApYivNfhD8MPEf7bmnaj8dfit4l1jStNvLqa30XS9Jufs8VtBCdnmNlXDSbupA5KkkkEKoB+q9FfAX7NXjDx94P8AiJ43/Zd8f6pLrj+F4EvdL1K4YtcSWc6qwSVzyxj8xADzg7lztC46P/gntq2q63+y/pGo61cy3lw1zeBpZ3aRyBO4GWYk8D3oA+2qK/ML4O+Idfu/gn+0BeXV9cSTWWq+IVt3eV2aIJbMUEZJyoU8jGMdq0P2OfgNqvi7wN4Q+O3xK8VazqWpQp5thZfacWUEKFo41aMqTI7KNzsSMk4OSNxAP0topDnHHWvyM8deBvhHb+IdZ1T9p3423Umvm4kMFto92YY7GMHKILVBO6OvPy8cHnc3zEA/XSivyz+A/wC1B4u0n9iLxR8TdevzrOo+ErufTrO8utzG43CAWzy5w7fNOoO47iByc81t+B/2OvGviLwBZ/FTV/iB4gi+IOoWyahHcrdf6JDPKvmpC0JQ7ohlVdd204woC/KQD9MaK/J79nP45+Kfhx+w34s+MPiCSTUdW0/VLoRi6Zn/AH8zQQxqwJzsWSQEqCOM4xXU+Ev2MfFvj/4d2vxJ8YfEHxDF471a2W/S5huyltbSzL5kcQiC7giblDBHX7vybRxQB+nFeBftL/Gqf9n74TXnxMttOXVHtZoIvs7SmEN50gTO8K+MZz93muP/AGN/jD4n+MnwfN/44A/tzQ76bSL91G0SzWwQ+ZgcAsrruxxuzgAcDz7/AIKQf8mq6t/192X/AKPWgD7pgk86BJsY3qDj6ipa/NO+/Y48c6v8Pf8AhY9x498QD4hta/blmjuylmlxs3i3SFVBWEH5Bg++3HyV538Qfi3468ffsvfD/wDa60yaSPVfCepK2r29s7RxXEInEEweNTtIkaOM4IwqyNjFAH64UV+fv7ZHjrUvGugeBfg58MtQlhu/iJqFu63NsxV006ILLJKGUggfOj+6qwwa+99PsbfTLCDTbQERW8axICSTtQYGSeTwOpoA/Or9pr/goLp37NH7Ung34CeJNEjl0jxNb2s9zq7XJjNmLq6mttxi8shkjMYdjvHyk8cc/pBX4Af8FFvgV/w0d+3fpXwqtRm/u/hzdT6fzj/TbWe9mt1J7B3QIx7Kxr7Q/Z1/bX0q+/4J6t+0V43l83U/BunS2OrRytiSXUrJVijRyekl2Whb2aXHav0rOuFaUstwmIwUf3kklNd3Nvkfzs120R+UZDxlXjmuNwuYS/dxcnB6KyglzrztzRfV2b7Gkv8AwUC0/Uv2+rX9irw7okd3bkTRXesfaSDHcwWMt68aQiMhguxY2JcENu4+Xn9Ha/mO/Y++FPiDwR+2P8BPib47d5vEvxJtvEnibUJJPvEXlldmDp/ejxN6hpSOwr7p/bH+G/gTxJ8b7nVv2sPjp/wi3ghLOI6V4X0q7+w3Zfo8s8eZjMpIb94Itx3bQUCYbs4i4QwMcbRwmGnZezu2lKTlJSlFuKXdrTVKx5/C3HGYyy+vjcXDml7W0U5RgoQlCE4qUnbZS10cru3p+xFeBfC79o3wL8W/ij45+Efhq3vYtT+H9xa2+pPcRxrDI92JGQwMsjswHlNu3qmOMA9vyi/4J2fE3R/Enx3+J37KXgPxvq3jb4cDSBeaLqN/JILuBWEMFykUkscbph7ggbUVN0fmIo3EnjP2J/2Nvh3J+2d8XNL/ALa19I/hxrmkXOnlL7a107vcTkXxCD7QN0QHOMgtkknNclTgrD4ZYqGMqNOEISj7r2k47ptNPXlaez16a91Lj/FYuWCngaScak5wl7y3hGT0kk017vMpLdK2l9P2P1b9o/wJo37SGmfsuXdvenxFq2jtrcMyxxm0FukksZVn8wSCTMLHAjK4x82eKyPF3j79oXTP2lfDPgHwt4Pgv/h9qFhNNquvtOFltblfN2xrHuBxlYv4G3+ZwVCNX5B/GL9jn4d+KP8AgqfpHw8vtZ1+O08SeHrzxHPPFfbbmG5mub3dFbylCYrcYwIwOASM4Jr6t+Is+q+FP+CoHwU+H2l6jeHSofCl9E0LzuyzeTb3qq8oyFd/kUliM5Gaurw3goezeHlzOVGU2pJ7pSd1aW+mnRWu73JpcV4+p7RYqPIo4iFNOMldpyirO8Xprq1ZtOyatc/WSiv55vjv4w8C/EX9uTxr8L/23vHniHwN4b0xLRfCtlYTvaadcRPHl55ZVidcs3ziRh9/dGZAI1Svub4Xavrn7I37JHjr4kJ8QIfip4Z0aO5v/DFw8v2mVIQpWG1nvEkZZV83YvyKuz5scFUTycdwVKjRpS9pec+Wy5XZ8+yjPZtX12S11dj2Mu4/hiMRWh7O1Om5qUuaPMuS93KHxJO3uvVvS6Vz9M6K/Dz4M/sF+M/2ovhJp37SHxy+Jvii28b+LLcavYPpt55Vnp8Vz+9tVjhKbtoQqxSN41UHauMbzu/C/wDaD+LHxA/YE+Nfgn4r3rP41+GNrrOg3WoQuwkn+zW7rHOz/K3mhldC+AW2Bz8zGqr8G07uOHrqbhKMZ6NWcna6v8SvpfTppqThuPKloyxWGdNThKcPeT5lFc1ml8Mra21W+t1Y/aaivwZ+BP7DXjL9oP8AZL0H4xePfib4qi8W3Ok+foa218YrHT44UKWi+UFLOzqqtNIHRmLHncC7ff3/AATf+M3i746/sg+GPG3j66e/1qI3NjdXUmN0xtZ3jjdiOrGIJvY8swLHk1y53wvTwtGdWjWU/Zz5JKzVm72tfde6+33anZw/xjVxlenRxGHdP2kOeD5k7pct07bP3k7a6db6Heftn/tJXf7KHwJvfjJY6QmtyWlzbW4tZJjArfaJAhO8I5G3Ocbea+m9Ivjqmk2upsuw3EKS7c5xvUNjPtmvzJ/4LE/8mP6z/wBhLTv/AEeKwvD/AO3H+1nbaDZW9v8As1+IJo47eNVkGoKA4CgBgPsvcc11YbhaeKyqliMNFc/PNNuUY6JQt8Ukur2+fQ48VxjDB51WwuKlLkUKbilCUtW58z92Letlv206n1J8P/2or3xt+2H48/Zak0ZLeHwZp9nepqInLNcG6ht5Shh2AJt8/GQ5zt6DPHVfs1ePv2hvH2la/c/tCeD4PCFzZ6nLb6dHBcCcXFoo+WQkM3IPG/5Q/UIoHP5rfsOeOvF3xL/4KTfF/wAbeO/DNx4O1W90HTvP0i7kEs1t5cVnGm5wiA+YiLIPlGAwHPWuC+E/i7xZcf8ABPz9pLWLjVLt7uz8Ua5HbztPIZIkWO12rG5bcoGTgAgDJr3MfwlTi3h4Riny0E3rK0pr3mmpW1e+6fSx89lvG1WUViqkpSXNiWlpFONNvlUk4810rJbNP4rn7+UV+DngL9h3xp8Wv2QNH+PHjL4neK18bHw3FqOjm3vzDY2UUNoDZxLEq78tEqedIJFd3Jc/MWLd/P8At1/Enwt/wSk0f9oy6ukn8a6kG0WC6mRTuulu5rb7QV+60gghaXBG0yD5gVyD4tbgfmkoYOsqkvaKm9GrSd7O73jo9dNtj3sP4hckHVx9B04+zdVaqV4q100rWl7y0133P2kr5F/bJ/aevP2VfAnh/wAZWWjJrTa34gs9DMTzmARrdRzOZQwR9xXysbcDOeoxz+H3ifSv2ZfBvwuu/ij4G/aX1y9+LlhZtfi6+3TyW15eRL5jWwiaESGOUgxpvlPLZcMuUr6G/a7+NGo/tDf8E9/gn8YNaREv9X8Y6V9r8sYQ3Nul/bzsq/whpImIXsDjJxmvdwPh/Gli6Eqrc6Up8rvGUHezatfVp2dmrbapHz2P8TJ1sHiIUkoVYw548s41FbmSd7XSaurpq2ujZ+sGuePv2hbP9p7Rfh7o/g+C5+HN3pss9/4gM4EtvdqJCsYj3AkFljXbsJPmbwwCMK+la/LTx/r+uw/8FdPA/h2G9nTT5fAs8r2okYQtJ598N5jztLfKOSM8D0r5R+D/AMEfGX7VX7XHx68E+LvHXiDR/Buha+Gm0/SrswPdTTSXCwoZWD7YI0jk3RKAGLIeCgryHwtSq0Y1qs1TjGlGbaTd7zce7970sttFue2uMatGvKhSpyqzlWlBJyircsFLR2Vo773e+r0R+/NFfkN+xTJ44+A/7ZHxF/Yv1PxLqPibwzpelW+u6NJqsvnz20b+QrxbzjA/fhSq4QlN6qpZgfhTRfjD8Bf2z/G3ij4n/ta/GPUfB+nW2pSWXhzw7pNzJaJBZxAGO6fMMyPJJuBLABi6tk7NqKUOAZ1K01GpenGMZc0YuTamrxtFa33vdpKz1DE+JVOnQpuVNKrKU48spxik6btK83pba1k27rTe39MlFfjz/wAE0Pj7qGtfEvx/+zOfGj/EHQfDHkX/AId1y4ZnuJLGbAeGR3+Z/JZ41yejbwPk2Kv7DV8vxBklTL8U8NUd9E07NXTSa0eq0eqez0Pr+GeIKWZ4OOLpK1201dOzi2mrrRq60a0aswooorxT3wooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAr8/wCv0Ar8/wCtKZnUP//Q/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigD85P2xvAutN8YfBPxd1fwndeOvCeiw3MF9pNrELh0lkBKTGDnzFJ2kgjb+7AYjIz494o1Dxz8XvjN8MNZ8B/DHVfC/hHQtcikeWewFvIzM8ZaSSKEERQxovDsdrFjz8vH6+UUAfE2k+FPFMf7f2p+MpNNul0eTwgtst8YXFs032mFvKE2NhfAJ25zgE4pfjF4T8U6p+2L8KPE+m6bdXGm6dDqou7uKF3ggMluwQSyAFE3E4XcRk8DNfbFFABXxN+yZ4T8U+G/iF8XL3xFpt1YQ6l4puLi0kuIXiW4hZ5CJIi4AdCCMMuR719s0UAfEPhDwb4kH7cvjbxNqOl3SaNfeHrW3jvHhdbaVx5IaNJSNjMADlQcjBrxL4XeLPih+xRbaj8FvE/gvWvFegw3UtzomqaLbm43xTHd5UyjhGDcnnIJbAZdpP6l0UAfC/7MPw5+IWvfEPxf8AtLfFrT20W+8XJHaWWlSZEttYwhVXzc4Ku4RMjCnILEDdgeE/Arxl8ev2XvDl/wDs+XHw21bxHcWV5cPpF/ZjFlPHK25TNOV2Iu47i2cgNtZVI5/V6igD8t/2ePh/8VtH/Zy+M2ieOtIu4td1W51lkj+zyr9rllsyu+2V1DSpJJkRlQd3GOa+wP2TNE1rw3+zj4R0PxFaTWF7bWISa3uI2iljbexw6OAyn2Ir6IooAztXtbq+0m6srGY2800LpHKOSjMpCsPoea/H34D3t1+z74Xk+HPif4K6rrfjuK4nA1KOxjuLe8Z5GMbm9cHy4lBVSV3KACxwSa/ZOigD8tf2bfgN458cfsu/Eb4WfFDT5tB1PxDrt5Kv2q3eNBIY7Z45kVgN8QmT5WUkEA7TxXS+DPix+2L4X8EW3wbm+Gktx4i0+BdOg1trlBpxVB5cdzIdpB2qFZlDZfBPyk7R+g/inQIvFfhq/wDDM9xcWiX8EkBntJDFPGJFK745F5V1zkH1r4asv2cP2t9B0Bvh34d+LSLoCoYIZ59PWS/hg6BFl3biQvAbzAw/h28AAHi/7J/wif4w/sMeKfhNcXKxT6hqt3HHcHLIJ4DBLGxPUp5ka574zxXceFv2oPjn8PPh/b/CzxD8L9fv/GOlW66fBPb27SadcNEvlxztOv8ACQFL7cqefmXt9s/BD4OeGPgP8ObL4ceE2klt7Uu7zTY8yaWQ7ndsYAyeAB0UAc4zXrVAHy9+yH8Ftd+CHwiXQ/F0yza3q13Nquo7TlVuLgICgI4O1UUMRwWzjjFch+354V8T+Mv2atU0Lwhp11qt9JdWjLb2cLzysFmUsQkYZiAOTgcCvtCigD80dT/aX/aA0XwE/wAIW+Gmtz+Oo7b+z1vIYS+lu+3yxdpcDqpHz4OFB4LjBx9D/B/9nO18IfstQfs/eLnSd7uwuYL94uV828Lu5QnBPll8I3GdoPFfU9eQfGjwd8UPG/hmHRvhV4oHhK888NPd/ZVuneDYymNQ5AUksG3D5gVGCKAPzf8A2BvCHjXxd8UrzxR8Rysw+GVgfC2nkcoJRNLvKnOC0cRMeQBlHX0r9f68a+A3wU8PfAL4c23gDw/M92Vke4uruUASXNxKRvlYAnGcBVGThVAJJBJ9loA/M7x94C8c3n/BVXwP8RLPRb6Xw/aeC7i1n1NLaVrOKdpb0iJ7gL5ayEOpClgTuHHIr4H+O37HHxzvf2wNU/Z88D6bfj4SfE/XdP8AFGr3cEExtLbyPPe8ha4VfJhd38xljOCx+zgdAD/RTRX3OW8d4jCyjKnFaU1DXyblGXrFu6PzvNvDjC42EoVZv3qjqO3ZxUZQ/wAMkrP/AIB+Zfxj+HHi2b/gpB8D/FnhzQrx/Dmh6RrFvc3tvbSNZWm+yuY4Y5ZVXy4txKqisRkkAda+PvEPhqT9nL9tD4lfEn9oD4Oax8UrDxdcw3Xh7V7DTU1ZLWPD4t/Lkykbj5IskiRViBVSjZP760VGB40nSiqc4Xj7P2b1abXO53utU7uz6NbmmY8A068pVYVLS9p7RXipJPkVO3K9GrK6e6ex+Jv7Euh/GzxD/wAFAvHHxs+IPw61DwFoms+F0h063ntWit4ollshDCZQixee0cZkkiB3I25So24HTeENQ+K37Kn7fXxDutX8Ba54h8L/ABZv9Iez1rSbZrmC0Kbo3NxsDBFjM8m/cQ+2PcqlWBH7GUVWI409rVqSnRXJOEYON3tGzTT3umlve/UnC8Bewo04068ueFSVRStHVyUlJNWtZqTWlraWPyK/a+s/iv8ABf8Abg8Efte+GfBmq+NfDlp4em0G/t9FhNxdQSGS5kVzGoJ2nz1wxAX5SCwJXPReN/Dfjvxv/wAFIfgv8ZNO8N6tDoC+Fbxru6ms5ljspbm2vGSC6k27IZgZFUo5DbjjGa/VOiuanxa1ShH2a5o05U73esZJrba6u/XqdVTgqMqs5e1fJKpCry2WkotN672lyrR7dD8h/jh8eviV4X+K3iX4eftV/AyX4ieCzNv8L32haR/aamJ92FuRcPIqzHKKxXy2VlYqjKVNeZ/sb/seeNfFXwg+N+h+J/D958OfC3xPbyvD+hX7PJPp4QThZ5IXw6Yd4htbazrHg/KEY/uJRXQuNZ08K8Phqag3y3abavFppqLdk20m367XOWXAEKuNWKxdZ1EueyainaaaackuZxSbSXTS97I/Ef4Q/tbftJfstfCm1/Zw+JfwZ8TeIfE/hSH+y9KvdHtpJ9Nv4IPktm89UJVVjCrlFckDJCNlR1nwx/Zf+Lvw6/YM+MF/8QrR774hfE611fWbzT7GNpZI57u3fyrVETeZJd7MxCZ+Z9g3bdzfsZRRiOM07yoUFBykpTs2+Zxd7K/wq+tl99kGF4CatHE4iVRQhKEE0lyqS5W3b4pW0u+l9Lu58pfsd+HPEPhj9jzwN4Y8S2Fxp+pWmgQQz2lzE8U8UgjwUeNwGVgeoIBFeG/8Ep/A3jb4dfsd6V4Y+IGj32halHqF+72moW8lrOqvMSrGOVVcBhyCRyK/R+ivHxOfTqUq9Jx/izU35Nc2n/k34HvYXhuFKthqyk/3MHBeafJq/wDwBfefnD/wVX8DeNviL+x1q3hj4f6Pe67qUl/YOlpp9vJdTsqTAswiiVnIUckgcDrX6BeGYZbfw3p9vOpSRLaJWVhgghACCOxFblFctbNZTwdPBtaRlKV/8Siv/bTroZNGnj6uPUtZxjG3+Fyd/nzfgfmD8FfAHjvSv+Conxj+IGqaJf22g6poulxWepS20qWdxJHa2KukM7KI5GVkYMFYkFSD0NfMvwt+D/xZ079g79ojwdf+GNWg1fWvEutT6dZSWU63F3FLHaiOS3iKb5UcqwVkBDYOCcV+7FFfQQ40qxt7i0VJf+Ctvv6nzU+AaLTXtHq6z6f8vr3/APAb6Hyl8DfDniHSf2I/CnhLVbC4tdVt/Bdnay2c0TJcRzrp6o0TxMA6yBvlKkZB4IzX5yfDb9jz4ifGb/gkppnwH1fTZ9B8XWdzd6hZWmrQSWsi3EWoXEiJIkqq0fnQuyqzDADhuV6/uRRXJheLa9BynSSUnUjUv2cebT0947MbwVhsSowrtuKpSpNd1Llu79GuXT1PwdX9obWpvAP/AAhVr+yjd/8ACz/KW2Afw7D/AGL9pOENy0+xWEG759vCY+XzgPnr1v8Abg+FHxg8SfsifCvwxaeEYj4hsvFek32qaX4VspHtLPMN207RxReYUijkkAeQkqWOc/MK/YeivR/11jCvTr0KCjyy5vik7u1rat2S7fieZ/qDKeHq4fE4hy548vwxjZXvfRat2V3t5H5l+O/APjq8/wCCrfgr4i2mi38vh608EzWk+ppbStZx3BmvSInuAvlrIQ6kIWDYYccimfsP+APHfhL9p79onxB4q0W/0yw1vxDaz6dc3VvLDDdxK14S9u7qFlUb1yyEgbh61+m9FedW4pqTwzwzgrOEYfKM+e/6HqUODqUMXHFqbuqkqlvOUOS3olqfmR4A8AeOrL/gq145+I15ot9F4evPBlvawam9vKtnLOJbEmJJyvltIAjEqGJG08cGvjb4feD5v2BvGHif4T/Fb4JXPxI8J6hqcup6Dr+i6PFqU6wzhVFrOJFwuzYoCs6kNvKh0ZSP6AKK7cPxrOKdOpTvBwhFq7XwfC01qnv3Wr0PPxXAFOTVSlUcainOadlJfvH70Wno1t2d0tT8/v2Jbv4neLtQ8TfELxn8LNI+F+h3UiQ6Dax2K2msS24J8w32NuF3KpVTGhJJ4KqrN+gNFFfNZtmH1qu6yiop7JXdrK27bb82+p9bk2WPCYaNBzcmr3bsrtu+ySS8klogooorzT1AooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAr8/6/QCvz/rSmZ1D/9H+7j4W/wDIiWP/AG1/9GvXoFef/C3/AJESx/7a/wDo169ApvcS2CiiikMKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACvz/AK/QCvz/AK0pmdQ//9L+7j4W/wDIiWP/AG1/9GvXoFef/C3/AJESx/7a/wDo169ApvcS2CiiikMKKKKACiv56P8Ag4A/aP8A2hf2dvBfwuvv2e/FGp+Gr7VdUv47j+zZCrXAiihaNHUA7wGY4Ugg56V+xH7If7QuiftV/s0+Dfj/AKFsVfEenRz3EUZysF4mYruDP/TK4SRPfbmgD6Por+a3/gvx+378V/2fj4P+Av7OviC98P8AiC4R9f1q902Qxzw2IY2trEzqDtSeZpC2ccxx9d1fvh8H/FW/9n/wt438aX6rnw/Y31/e3cgVRm1SSaaWRyAB1ZmJAHJNAHsVFfB/hb/gp9/wT/8AGvjyL4a+GvivoNxq9xMLeFDM0cMsrHaqRXMirBIzNwoSQ7iQBkkZ+5r6+stMsptS1KZLe2t0aWWWVgiIiDLMzHAVVAySeAKALVFfCXhv/gpZ+wl8QvHJ+E/gX4paHf8AiG4LQW0MUzCOebkKkFwyiCV2PCCORixxtzkV85f8EQvjL8VPjv8AsL2fj74x6/e+JNafW9Rga9v5TLMY4mQIm484XJwKAP16or4k+J//AAUh/YW+DPj2b4YfEr4naLpmu20hhuLQytMbeQdUnaFXSFx3WRlI7gV6f8cfiPZ3n7J/jX4qfCrWYrmNfC2qahpeqadMssZaOzlkimhljLK2GAKspIyKAPoyivzj/wCCSXxN+IHxj/4J5/Dr4kfFLV7nXte1KLUTdX145knmMWp3cSF2PJ2xoqj2Ar2n9tD45fF/4CfBr/hJvgH4In+IPjDU7+30rS9KiLKgmuQ58+4ZRkQQhC0hLIMfekjGXAB9Z0V/OJ+wV8Tf2+dM/wCCqniL4Eftl+OP7auH8FSa7No9hJjSrGa4nszFFDGqIm6CNyhYA5Jb53yXb+jugAor8R/29f2jv2pfHn7Z3gr/AIJvfsm6/b+A9Q8R6Sdf1nxTNEJ57ezRp/3VrG3BbbbsTtwzMyKHjUSNXlPxW/Zh/wCCpP7FGhW3xz/Z2+M2vfHCTT7uJtW8Ia/atcNfQzOI3NqfOmkUKWDGOMxlEBcOdpRgD+g6ivn/AFz9pX4XeAPDngnVPjJfL4P1Dx5JaWmnadqIZbg6hdojCyIVTiZGcI2cAN6V3/xT+Kvw8+CPgHUPij8V9Wg0Pw/pKo13fXBIiiEsixJu2gn5pHVRgdSKAPQaK/Fv/gsT+0d4++Hf7J/w3+KX7PHim60hPEvjXRIVv9OkMRutOvLO7nCbsA+XKFjbHGcDNfYGuf8ABS/9gjw18RpPhPrvxV0C21yGdraWJ7j9zFMjbGjkuQPs8bK2VYPICpBBxigD7korz/4kfFT4efCH4f3/AMVfiTq0GkeHdMiSa6v5iTDHG7KisSoJIZmUDAOcivmHxJ/wUm/YO8H+I9P8JeJ/ipoFjf6nbwXUMctzgLFcxJPC0z42QeZE6OomZCVYHFAH29RXyD8Z/wBvz9jP9nrxRD4J+MfxF0fRNXmWN/sbzGWZElXfG8qQq5iV1IZWk2gggg4NV/2uL7wl8Vf2L/FWseHPib/wgeiatpSXUPjTSpPPW1ty6SCeJ4ZFLxyqPLYxyKSjnawOCAD7Gor5e/Zw1Hwv8M/2R/CWt+JfiD/wl+jaZoMF1N4w1WTyVvbbyxIL2aSZyURkIOZJGYLjc7Nljwnw3/4KR/sK/F34hQfCv4dfE7RdT167kENtarK0f2iU/djgkkVI5nboqxsxJ4ANAH25RXmvxY+Mfwq+BXg6b4gfGPxBYeGtFgdY2vNQmWGPe/3UUsRuduyrljzgV438A/25v2R/2odcufC/wG8e6X4i1S0jaaSyhdo7nylYK0iwzLHI8akgM6qVGRk8jIB9XUV+Z+i+EbBf+Co+r+Jk+OGoXV43hdHb4ZESfZbeACKL7aD5nk7C+JMeUJfMkP7zYdh+mP2gf2yf2Xf2V/skX7QPjfTfDM98hkt7a4kL3MsYJBkS3iV5imQRvCbc8ZzQB9MUV4z8EP2iPgd+0n4Wfxp8CPFOn+KdNhk8maWwlDmGTGdk0fDxORyFdVJBBAwa4Lxf+2x+yd4A1nxR4f8AHHj7SNIvPBbWya1HdzeSbR7xd9ujFwAzyqCURCzHB44NAH1HRXzn8AP2uf2av2prW8uv2fvGem+KDp4RrqK0kIngWQkI0kEgSVFYqQrMgBwcGvoygAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P8Ar9AK/P8ArSmZ1D//0/7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooA/CP8A4LA2dpqH7Sv7IVhfxrNBP8SrWOSNwGV0a6sQysDwQRwQetc1/wAEvNbj/Yx/ad+Nn/BN/wAb3X2XRvD91J4x8KTXLnZ/Y9yEMyiRzgiKNoC2D98Tt2avqP8A4KL/ALNHxr+PPx4/Zt8Z/CnRv7U0zwB45t9Z16b7TbQfZLKO4tJGl2zyxvLhYnO2IO/H3eRn5p/4LOfsDftG/tDa94Q+O/7Glk1x42s7O/8ADGsJDd2tlJNouowSo26W6lhjZEEs8TIGLkXGVHykgA/JX41abfftU/sk/tY/8FO/FUT/AGbxRqej+GvCKzKwMWkWOtacGdVbgeYqW6EqBiRJv7xr9KP+Cnfifxdr37Jv7Mv7KmgarcaLpnxe1Tw/oms3VuwRmsjBbRmFmIICF51kIPB8sA5XcD9S/tZfsG+M7H/gkBdfsM/s36Uuua9Y6fo1tbwJNBai7uLfU7W8vp/MuZIolMjLNMdzjJOBkkCu5/bB/YH8SftW/sTeC/hnpV//AMIz8RvANrpmp6FeFwUg1WxtVjMEske/ETtwZI87XVJAHC7WANH9pf8A4JifsZeJ/wBj7X/g74d8C6LoP9laNPJpep2trDFe2t1bRF4p2uwomcs6Dzy7nzVLB85zX4g/Fz9qT40/F7/ghl8KPDet61ONV8ceLofBOqarM7eZNp9tNdGPzZSdzFlggSVmY+Yqvuzuavu34ieO/wDgtx+0L8Ibj9lnUvhBpPgvUddtv7J1nxv/AGzavbi1kXy7ieC2hkeSNpkyP3fmsu47EVsFPpT42f8ABJvwb4s/4JqaX+wp8OdT+z6j4UMep6Nq12u0PrCPLLLNME3MiXBnmQ7dxiSQY37ACAeifEf/AIJTfsQy/ssaj8ENA8C6Rpj2WlSJZ66ltAmrQ3cMP7u9a/Cec029FeQs21gCrKU4r8q/+CfXxf8AFvwF/wCCBfj34seA5mtda0qXWvsNwgy8E87xQRzqCCN0TSCQZBGV5BFfQdt4p/4LifF74Xn9lHxp8OdF8K3WoW39jar8RJNSt5lWzZfKmu4rSGdna5lj3EFB99s+XF1X2v8A4Ju/sH+PPCP/AATP1r9jv9rXRH0K68ST6vBeW0Vza3MkdvfBVjmjltpJ4RIpG9OTtZRkdiAflF+xf8S/2TPAH7Mmk6F4/wD2SPH/AMS9b8RWgvda8S3PhWLVf7Snuv3rS215MxfyMkGFkK5wJD+8JY/RP/BOCH4m+Ef2Nv2q/hRrnhLxT4R8D6ZaavqXg+z8UWU9rPFYajZ3+bdWmGHeJYIjMEZlEkhbq5J9d+C1x/wWH/YR8Ej9lrwr8KNK+MXhzQTLa+GPEUeq22nEWe4mBLqGWVW/djqrbNudglcKGP2p8Ffg1+3ZffsW/EzQP2tvEUHif4geN9O1g6do9kLaO10sXtpKkNhHcBYw5Mr4LPK8cY2qrkBnYApf8ER/+UXvws/65ar/AOne9r9Vq/P/AP4Ja/BH4n/s5fsHeAfgx8ZtM/sbxLokeoLe2fnQXHlGfUbqeP8Ae28ksTbo5Eb5XOM4OCCB+gFAH4LeBP8AlYa8af8AZM4v/RthX701+SPhP9mL446Z/wAFlPE/7Vt7omzwDqPgaPR7fVPtNsd96sloTF9nEv2kcROdxiCcfe5Gf1uoA/NX9uv/AIJveF/2wfE3h74y+DfFOofDr4n+EIzFpHiXSxukWHcziGeMPGzxqzuV2yIV8xwdysVPwF49/aL/AOCuX/BNnSF+If7U8OgfGr4XWM8UWo6xpSiy1W0hlkWKN3RY4EB3MBzDKrNtDTIW3V9Iftrfs0/tveEf2qdG/bj/AGE7y21/UItOXSdc8GapdG3tb+Jd376JpJooQ7JsU5aMo0aOC4LLXzJ8etC/4K//APBRrwQf2a/GXw00j4K+CNZnhTX9XuNSh1G5khgkWUpDHBN5hUugO0IBJwhmVC5IB13/AAVY8deHPihqX7HnxL8HTfaNI8Q/EPQ9TspSMF7e7a2miYjtlGBx2r6w/wCC2zpH/wAEvvim0hCjydKGTxydXsgB+J4rjv2+f+Cd3jT4n/safDz4R/ss38dl4r+DN1pV74akvSqm4/su3+ziNpW+RJHwkoZgUMkYVsKxZfgr9rD4af8ABa39vv8AZq1j4SfEn4e6F4ItdNS1uZbCxvrSS58R3kNxEBFG73skNrbxfPdEySAlo0RWfOKAM3/gsHby3f8AwRu+AdrDIsTy3/hNFd22qpOg3YDFuwHUntX6t6p/wSV/Ybuf2aJP2drfwJpEIXTTax679kgGrrdCLYL43uzzTNvAc5Ow/dK7Plr5P/4KL/sQ/tFftHf8E3fg7+zd8OND+1eJvD994cOsQfabRPscNnpNxaXUm+aeKKXyZZFG2ORi/VcjJHDeL/Gv/BdOL4Xz/sn6b8NtFv8AVmtjo4+I0OqQJFNaFfJ+3fZ3lV47kplixTcH+ZYM4BAPkT4VfFfxd8UP+DcP4gWHjC4e8l8JzNoNtPIxYta29/YzQKGPVYln8pOwRFHavsLTP2CP2UdG/wCCKN1rL+CdJuNeuPhjJ4qfWZbWN9R/tU6S2oJMLsgzgRzHaiBwoj/d42kivXPGX/BOLxr8I/8Agjrr/wCw/wDBiFfFPjG+s0llZJIbVb3UZr6G5uCklw8UaxoilIzIykxxrn5jz9fTfBT4mSf8Eun/AGcxpv8AxWTfCw+G/wCz/Oh/5CZ0T7H5Hnb/ACP9f8nmeZ5ffdt5oA+Af+CWv7DX7LHxX/4Jk+G9Y+KXgvSvEer+NLO+n1PVNRto7i+LJcT20HlXMgMsIt4Y0SLy2XZt3DDEk/HP7K2varrP/BuT8RLPUpmlj0yLWrW3DEnZF9pjm2jJ4G+VjgetfuX/AME2fgx8S/gD+wh4C+DPxb03+yfEui2N1DeWfnQz+U8l3PKo823eSJso6nKuQM4PINfml+zj+wt+1P4C/wCCL3j79k3xX4X+y/EDW21M2WlfbrF/M+0PCYv9IS4a2XcEP3pRjHOKAK/7Qn7Ovxx/ac/4IW/Cn4ffAO3Opara6B4Y1K50tXCPqNnbWal7dCzKCwdo5gu4FvK2rliAfnn/AIaJ/wCCVfxW0zwt8Av2ufgrqn7OPiPTLq2uLK6/sz+yFtrmFxkRapbxxXaxs2DJJNDGoyJGcMA4/TLxb+z/APt46B/wTY+F3wz/AGYtej8GfFDwRpGipf6fO1rLDe/Y7VY7iwa4xNGp8wAq6P5b7SjNtfevxL+0x4J/4Ku/8FK/h3YfsxfFP4KaD8MdFlvra41bxLe6nb35gNu28vZQQzPKpYcYXzNwyjSIGLAA9n/4LFfAb4zeMPHvwZ/aB8F+AX+MPgn4d3V3NrnhJCZpLtZ/JKS+SFka4UrGQcJLghdyMjvXF/s4/HX/AIJW/tJ/tdeCNV0jwfqfwZ+MPhcyQ6dpNxYroJvHkj2m3l+yfurgBNyxxzGNnVmTawO2vsT9sP4ff8FCfhXqfw58e/sG38XibQ/Btmmm6v4J1CW3t11OKNPKS4F1MI2aQIcMDOu1kR0ViXDfH8/7Pv7e3/BQb9rb4U/Gr9qL4a6T8IPCnwn1JdZg238OoarfzRTQTrB5kDllj82BDhliCqXILsVoA9J8H/8AKwh4q/7JbH/6VWdeN/8ABKn4PeAP21Pi58af24P2ldNtvGPiFvF934e0m11mGO7g0uxtEjlRIIJlZUIjnSJWI3BYzggvIW+2fDf7NPxssP8AgsZ4g/apu9F2eAr7wCmiwap9ptjuvhPbOYfs4l+0D5Y2O8xBOPvZIz8xXH7PP7dP/BOj9pLxx8Rv2JfB1r8Vfhl8S7xtXvfDk1/Dp11pepyO7SNA8pVTEd2FKq5KbUdQYhI4By/jD4beGv2Gv+C0HwuX9niCPw94a+NemXtp4h0CxAismns4pDHPHbR4jiw/lOCqjBE2MCR6434D/sxfB79oL/gtz+0L4i+Mmi2niO08JQaZPZ6fqES3Fobq6tLeNZ5IHBjkaJEcIHVgpfcBuVSPp/8AZX/ZT/at+Ov7Zi/8FCf289MtvCeo+HbJ9M8H+EbO5ju0sIpUkjkuLiWNnjZ2WVyMNvZ33MIxHGletfss/s0/Gz4cf8FKf2g/j/4z0X7H4R8cQ6QmiX/2m2k+1G1gRJh5McrTR7WBH72NM9s0AfIHxH+EXw4/Zj/4LkfBPUPgZo1p4ZtfiFoGsW2tWOmxLbWs5gtrqQSeTEFRWZkiZ8ABmjDEbiWP9Dtfk/8AtJfs0/Gzx9/wVD+An7RXhLRftfg3wXp+rwazqH2m2j+zSXVtcRwjyJJVnk3M6jMcbgZ5wAcfrBQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFfn/X6AV+f9aUzOof/U/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAr8/wCv0Ar8/wCtKZnUP//V/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAr8/wCv0Ar8/wCtKZnUP//W/uf+HHh/R77wZZ3V1DukbzMncw6SMOxx0rt/+EU0D/n3/wDH3/xrB+Fv/IiWP/bX/wBGvXoFU27iWxzv/CKaB/z7/wDj7/40f8IpoH/Pv/4+/wDjXRUUrsZzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjR/wimgf8+//AI+/+NdFRRdgc7/wimgf8+//AI+/+NH/AAimgf8APv8A+Pv/AI10VFF2Bzv/AAimgf8APv8A+Pv/AI0f8IpoH/Pv/wCPv/jXRUUXYHO/8IpoH/Pv/wCPv/jR/wAIpoH/AD7/APj7/wCNdFRRdgc7/wAIpoH/AD7/APj7/wCNH/CKaB/z7/8Aj7/410VFF2Bzv/CKaB/z7/8Aj7/40f8ACKaB/wA+/wD4+/8AjXRUUXYHO/8ACKaB/wA+/wD4+/8AjXxDX6AV+f8AWkGZ1D//1/7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiqM2qaZb38OlT3ESXVwrNFCzqJHVPvFVJywXIyQOO9NJvYTkluXqKKKQwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK+YP2tvEWseHvhYg0ed7c317HbSshKsYzHI5XI5GSgB9RkdDX0/XyL+2h/yS6w/7CsX/AKInrWiveRFTY8j8K/sdnxT4Y03xM3iPyTqNrDdeX9k3bPOQPt3ecM4zjOBn0re/4Ye/6mj/AMkv/t9fXXwp/wCSXeG/+wVZ/wDohK76rlXlfclU49j4H/4Ye/6mj/yS/wDt9eW/Fr4A3vwO0G08Z6dr73MzXiW6COE27ISjyBw4lc8bOmO/Xiv1Kr5F/bQ/5JdYf9hWL/0RPVUq0nJJinBJXR9HeAtVu9d8C6LreoNunvLC2nkPTLyRKzHj3NdZXA/Cn/kl3hv/ALBVn/6ISu+rnktTVbBRRRUjCiiigAooooAKKKKACiiigAooooAKKKKACvz/AK/QCvz/AK0pmdQ//9D+7j4W/wDIiWP/AG1/9GvXoFef/C3/AJESx/7a/wDo169ApvcS2CiiikMKKKKAPy//AOCnv7XHjf8AZ1+H2ifD/wCDmf8AhNPHVw9pYyooeS3hjKLJJGpBBld5UjiyMcsw5UV8s6B/wRj13xX4bXxj8YPijrD+PrtBNJdxE3EUE7DJVpJX8+faeC4kj3dgKP8AgqZeQeA/2yPgB8WPFTeV4fsNShaeVvuRCz1C3nmY+4jcNz12+xr95EdJUEkZDKwyCOQQehFfq085xGT5ThJ5c+V1eaUpWTbalblu09EunmfjFPIcLnud42GapzjRcIwhdpJOPM5WTWsns/I/I7/gnZ4+/at8I/EjxZ+yj+03b6jqyeG1ebSfEVxFO8U0cTpG0Qu5FAmR1dZYS58xRvVjwFX2H46f8FRv2SvgJ4yuvh/r+pXmsatp8hhvIdJtxOLeVTho5JHeOPeh4ZVZipBBAYYr6W8M/tQfAnxl8XdZ+BHhjX0vPFXh+KSbUbNILgLbpCUWQtOYxB8jSKrASEhjjqDj8avhB+0L4Lm8e+Krr/gnd+ztL4mW9uDFfeIL+6eOKVzuyALoSLCkgYv5fnxswILxg9DCZbDMsXVxmLwrjaMXZONOF39pynaylukk7sMbm08pwVHA4HGRneU0m4yqztH7MYwu5ON0m5NWVj9j/wBnb9qH4L/tTeFJvFvwc1X7dHZusV3byo0NzbSONyrLE/IDDO113I2GCsSpx8oXf/BWv9jew8Oahr99qd/FJYXjWIsjak3U8iAlmijDEeWOhd2RckDOTXwf/wAEmW8Y6P8Atp/GLw54t0u38PXskM09/pNkyNa2tyl9/qYijyLsh810Ta7ADgGr/wDwRl+GHgbxB4w+KnxB8Qabb32p2OoQWdpLcRLIbeORrh5fL3A7TIQgYjnCgZwTnux/BeWYKWMq1+aUKSpyilJXfP0bs180tjz8t4+zjH08DSw/JCpWdWMm4uy9n1Ubpp+Te/kfrb+zP+2T8B/2s9NvLv4RalJJdacFN3YXcZguoVf7rFCSGQnjcjMoPBIOM8n+01+33+zj+yhqsHhr4majcXGs3EQnXTtOh+0XCxNkB5MskcYYj5Q7hj1AI5r86PgZ4e0P4Zf8FqvHfhHwHaRaZpl5opZ7aBQkQNxaWN5JtUcLuny+BwCTjisL/gmB4U8N/Gv9rH41/Gn4rWkWq+JdL1NFtPti+abYXVxdiQxq+QpRYI4kI5jQFVwrYPNX4Oy6jKpjp8zoRp06ijdcz9poot2tZPd22OnC8d5pXhSy+HIsRKrUpOVnyJUtXJRve7Wyvufqv+zZ+2t+z1+1ct1bfCTWDJqNkgluNOu4zb3aRkgeYI24dASAzRsyqSASMjPOftNft9/s4/sn6rB4a+Jmo3FxrNxEJ107TofPuFibIDyZZI4wSPlDuGPUAjmtDSv2Mv2f/C/7TEf7SvhSOXRfE7wvHJaWUscNncCSJoXaS2Ccll+YlSAXUORuyT+C37K/jz47al+1T8VfjL4L+FkXxR8SJqjrJNeXccLaUJbi4CrEs2Rl1iEalRmNItikKxBwyThjK8dVrYmg5eypxi+WUoxfNJ25ed+7yrva72tffq4g4wzjLqNDCYhR9tUnKKlGMprlir83s43lzNfZvZb3tt+/v7NP7an7Pv7WEV1F8JNWaTULFPNudOu4zBdxxkhfM2EkOmSAWjZlBIBIJGfH/HH/AAVA/ZO+HPivxV4K8Yaje2mo+Erg2txEbYsbidXKFLYKxL4IJJIVQOSRkZ+A/hl8KP2uNc/4KDeFP2mLz4Qf8K+01lNnraWV5byQTLLHNFJcyqjqSSrx5UIctGr/AHuaqfsj/C3wH8Rf+Cq3xn1Pxzplvq39hz6hcWcV1Gsscc73scfm7GBUuqFgpI43EjkAj0JcHZRTnWrSk5U401O0Zxk1Lms4uSun69nseZT46zurToUIQUak6rp80oTipR5eZTUZNSXmr7rfU/bj4EfGnwl+0P8ACfSPjH4FjuYdK1pZWgS8RY5x5MzwNvVHdR88bYwx4xXwP/wU9/ay+IvwS8O+G/gr8CCy+N/H9wbW2mi2ma3h3JEPKDcCaeSRY43P3cORhgpH6lWVjZabbLZadClvCmdscahVGTk4AwBknNfg7/wUevbX4f8A/BRD4EfFTxiwg8Po9rC08pAiia2vy00hJ6CJZ4nY9gBXzPAuEw2Jzi/s7xSnKMHreybjF9/PvY+t8Rsdi8JkVlUtOThCU1pbmkoykt7bu2ul9y1pX/BF3Vdb8OjxV8RPipq7+PrhPNlvogZoIp2GWG6VxcTANx5nmRluu0dK+gP+CcPxK/al03xP4s/Zj/ahtNRv7rwozNpuv3UM7RXUMUohkjF5IgE4O5JIWY+YyM27hQF/WIHPIrwbwN+058DfiV8Vtc+CXgbXl1HxN4bEp1K0jguAsHkyLDIDO0QgZlkcKVWQnOePlOKxPGOY5jha1HFw9rGyafKl7PXdNLRPaz0JwnAuV5VjKFfBVPYybaacm/a6bNSeslvda/p/MX+zV+2H44/Zc/a68VeM/EMt5feB9Q16fTNeDeZLHCJridreZeoE0flyOq9XjWRQMnI/dD/gqF4ggvv+CfHjDxL4XvRJBdR6RPbXVtJlZIpdStCro6HlWU5BBwQa/N3/AIJ7/A3wV+0dcftN/CHx7FustU1SxCTKAZLadbjVDFPET0eN8MOzDKtlSQfnHx98avHvwT/ZR+KP/BOn9oMsNZ0GSwk8O3JyyT2y6lazNCjHkxmLNxASOE3oduxUr9azfKsPjs8pTw0bVaEqXOv5oPkfN6xbs/KzPxHI86xOXcPV4YuV6OIhX5H/ACVFzrkflNK8f7111PrD9rDW9Ztv+CO3wx1C2vJo55X0gPIsjB2HkTnDMDk8gHk9hX0N/wAEnf2yNV+JfhFv2aPjBLLF4v8ADFsklg92Cst7pu1THndy0kCsvPV4Sjjdh2r5l/a3/wCUNfwt/wCumj/+iLiuy/ai/Zt8XaN8A/hb+3f+z1mz8aeB/Dmjz6kIQc3NlBZxfvmUffMKZSVT9+3LKxxGFPmVcLg8Tl0sBibRdStVUJfyzT0v5S2fqj2aWMx+EzWOZYS8o0qFFzh/NBp8zX96NuZejXr3vxY1TU4/+C2Xw80yO5lW2fRGLRB2CE/YtRPK5x29K/cKv5pfhh+0V4Z/am/4KpfCP4v+Gk+zteaC8N7ak5NteRWOoCaHP8QDco3G5CpwCcD+lqvz7xFwVTDvB0KsbSjRimvNSkfpvhbmFLFLH4ihLmhKvJp+ThCx/MvL+zrB+17/AMFPviv8KvFPiTVdFstNgn1KN7CQbt8MllAqYfcoXbMTwM5Ar0T47fsu/tP/APBOXw0P2if2d/iVqWvaBo80X9qaRqZZoxDI4jVni3mKeMs4RtqRyRhtyN1ZPS/2Sv8AlMd8aP8AsDXn/pVplffv/BRzxX4f8I/sUfEG78QmMpeaa1jAjnBe4umWKLaOpZWYPgdlJ6A19tmHEmLpZlg8vjaVKUKScGk0+ZJPdbn5/lnCmCr5Vjs0leFaFSs1NSkmuVtrZ2t5WPY/gl+0B4O+Mf7PujftDebHpek6hpzX1008gEdoYNy3SvK2BthkjdS5wMLnivih/wDgsh+xMvio+HRqOqtah9n9pCwf7JjON2M/aNvf/U5x2r8wPinfeNfAH/BFP4faQkktrF4k8RPHcJ93dZyTahdRoe5WR4Y5R2Ix617t4bf9p/U/2XrX4D6P+zBp9z4bv9JSJLhdQtg8zSxAre5PzeezHzQ5bcG71wUeAsvpurWr6xdWcIr2kYWjF2veXxPyXzep6FfxJzSp7Ghh1yzVGFST9nOpzSmrqNofCu7evRLRn6a/tiftfeAvgl+y7c/FnQdVeY+J7Oez8OahpyJcIb64s5pbSbJOzywyAkkMB0KnkV8m/wDBMT/goLb/ABy0ay+CXxX1LUNW+IMkl7ctdS28SQPbR4dAHiKgFVOMFAcj6E5X7NXwr+M/wj/4Jc/FD4b/AB60eXSr3TdO8Rtp9tcvHLts5dN80Mnlu6qDO83GQc5OOa9B/wCCRsn9l/sGw63Y26yXUN5qsiDA3OyOSq568kAVw4rK8uw2UYqlGHtJRqqMZprW6fK72endXs31R6eDzjNcXnmDrSn7KMqLlKm4vSzipK11rf4ZNXS6O57r+0Z/wUj/AGXv2ZPGDfD7xxqF3qGuQqrXNnpcAne3DgMvnO7xxqxU7tm8uBglQCM+1/s6ftV/BD9qjw7ceIfg5q4vvsLKl5ayo0N1bM+dnmxNyA+07XXKNggMSCB/Op/wTq8b/tB6XD4r+LXw1+EMHxP1rVtRZb7XLu9iinhd1ErwqJckeY0hkd1xvyAc7Bj7N/ZA+Df7UWgft/Xnx28QfC8/Dzwv4msrm31K1trq3ktIpDCrhwsbgky3ESsQE4Zyema6c+4Cy/CUa1HntUpxvzOpD3pKzcfZ/EuvL17+fHw14lZpjcRQr+zvSqytyqlU9yLulL2nwStpzaW7bH6FftL/APBQn9mr9lXX08HfEbUbm71xo1mbTtNh+0TxRvko0pZkiTcBkKzhyCG27SCeq+A37bn7O/7SHhzVfEHwv1hp5dEga5vbCeMw3kUSLuL+U3307b0LLuwCQTX5Uf8ABIzwt4b+Mvxi+Lfx4+KVrDq/i2HUYQjXaCVrT7XJcSSsgbKqWMYRSBlFjKqQrEH9S/Cv7GnwB8BftI3P7RXgiObRvEV9bvDc2NpLHFYzJIgRy1qqdWKrIdpAMi7yM5z4PEOS5Rl8p5fU5/bQinzXXK5NJ25bXSs9Hf5M+l4Xz/PMzjTzOl7P2E5NcjT5oxTcebmvZyutY2St1ufkJ4M/4K9aTa/ti+JPFvi7WdXm+FFzZeVpWmrZwGWG5CW43soIcAskx5kb7wyP7v2n8cdL/ZX8R/8ABQz4WeI/GWpeIbfx3Pplrc6Ra2oQafLCJbp4DO5/eIdwl3ohCsNoI5bd4x8EbGyb/gtZ8ULZoUMa6ACFKjaD5GmcgYx3pf2r/wDlMX8Fv+wNbf8ApRqVfZYnC4N42EcHB0n9WcnZrVOF0n7q1/mf2vI+EwmMx6wE54+pGsvrailKL0aqWbXvPT+WO0dtT9Lf2lv2xPgR+ydpVpf/ABe1R4bnUdxtLG1jM91OExuZUGAqjP3nZVzwCTxXnn7NX/BRD9mf9qfxI3gr4e6hc2WueW8sen6nB9nmmSMZcxMrSROVHJQPv2gtt2gkfnF8JPC+gfHv/gsd8Q5fjBbJqi+E7CaTSrO7HmQobVrW2hIibKEKkzyhcf6xvMxuGar/APBYrwp4b+EXjv4X/H74Z20Ok+L11KVfMtEET3ItTFNE7hQAzRu23ceSJNpJAAHhYPg3LZVqOVT5vb1Yc3Pdcqbi5JctrtWWrvufRY7jzNYUK+dQ5Pq9Ko4OFnzyipKLlzXsnd3Sta3nv+p/xo/be+AX7P3xZ034PfFS/n03UNS05tUS5aLNpHbr54Jkk3bgxNu4CqrFjtABJArx74Xf8FVP2Pfiz8Rrf4Z6Fq95Y3l9OtvZ3F/atBbXMr/dVJCxKFj8q+aseWIA5IB+Gv27vAnhv4mf8FYPg/4J8YWyXmmXmkWJuLeQBo5kivdQl8t1PDI5TawPBBIrc/4LcfDnwR4c+Dfgv4ieHNLttP1ix1tbCK5tolicW7200vlkoBlVeFSgP3eduNxzWV8JZTVeDwtVT9pXhe6atF62dra3ttdWM8442zujHHYyi4eyw07cri7yVo3V72Vr6Ozu/TX95KKoaTcyXml213NjfLEjtjpllBNX6/H2rOx+6J3VwooopDCiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACvwo/4Ldftc/Gj4R+FPAX7LX7NF7Npvjf4uakdPjvbVzHcwWweGARwyKQ8UtzPcRosq/MqJJtwxVh+69fzL/8ABYS5Hgv/AIKe/snfETxCoGjrrFpEXlO2NGt9WtWmk3HvGs0bnPoKAPIv2lP+CP3xJ/Yf/Z1vP2vv2dvi94ml+JXgu3TV9amecR215FDg3RgCgSBUG6QpcPOssalGHzV+/P8AwT6/ael/bE/ZB8F/H3UY44NU1W1eHU4ohhFvrSV7a4KrztR5IzIikkhHUZPWrn/BQbXtC8NfsKfGHVPEbILX/hDtah2yHaryT2UsMUeexkkdUHuRXwv/AMEAdG1PS/8Agmz4dvNQVhHqOratcW+7oYhdNCSvt5kb/jmgD9N/2kvgZpH7SvwQ8QfA7XdVv9EtPEEMcMl9pjrHdw+XKkwMTMrAElADkH5SRX4J/HD/AIIofs1/s/fCHxH8aviD8Z/iDBo/hmwmv7ki+ttzCJcrGmYBmSVsRov8TsB3r+l2v5tP+Cz3xM8XftSfHv4cf8Eo/gldEX/ii+t9T8TSx/MLe2XMkKSgHlYYlkvJEOCQkJHJoA2P+Dcv4U/FPSPgL40+P/xA1C8uNO8c39rbaPDeSvM32fSTcpLcKzEjbJNcNFwBzAT0Ir5Y+HHw0+J//BdD9qz4n6n8ZfGuqeGPhT8O70aZpuiaPII2lEks6QnbKJIvNMcLSXE0kbsWdUQBBhP6nfhZ8NPCHwa+G+hfCjwDbCz0Xw7YwafZxDkrDboEXcf4mIGWY8sxJPJr+cCb9k/9s/8AZK/a58efGv8A4JN6z4Y8f+HvF9x52v8Ahm9v7VzY3TzTSCK4T7Rb4SKRpfs7rOkqqzxsrbSzgGf8GdU+L3/BJT/gpP4O/Y113xvqPjT4TfFSGGPSo9UkDzWF3dStbW5UHhJFuI1jcR7I5I5gxXzFAX64/wCCwP7THx2tvGXw3/YF/ZV1OTRfGfxauSl5qUJaOWz00yCHckq/PGHIleSSP51jhYLy1fkN8a/hJ+1zr/8AwVe/Z51n9sDxBpuofEPxDrWmapJoehhmttE0fTr9ZookbJ++Yrp2ILgFSxkck49r/wCCwPw58c/FH/gsX8H/AIc6Dr0/hf8A4Srw9p+jwatbsY5LeG7vtRguxEwIzKYpXUDIJLqMjINAHZfEH/glN8U/gFFa/EP/AIJ1fHHVfFfxm0i8hn1bSbnV7GI3wB2yuYnlVQEOC8V28qvHuUnICt+7nxX+APiT9tP9j2w+E/x7m1DwFr2uWem3OsrotzC09lfwGOaeGKdfOiePzVZcqTlD1r8If+CkH/BI39nz9if9luT9rT9lDVdY8K+L/h1cafdLdS3zStdmW6itt+5tvlXCvKsimLah2lPL+YEf0DfsNfGfxN+0P+yF8O/jR40VV1jxBoltcXxRQivchdksioAAqyOpcKOAGAHFAH4O/tW/8EeP2cP2UP2efFXx/wDGfxh+IDWvh2yeaOE39upubl8R21up8j700zJGD2zk8A19Y/8ABvv8JPil4L/Y5vfil8UL25uD481Rr/TYbt5JJEsbdBBHITISQJnWRlA4KbHBO7j5y/4KoeKNf/b8/bp+Hn/BLX4Y3Ui6LpV1HrXjK5tzxDiPzCrHkBre0ZmQN8rTXEaHDKK/pM8LeGNA8E+GdO8G+FLSOw0vSbaKzs7aIYjhggQRxRqOyqigD2FAG9RRRQAUUUUAFFFFABRRRQAUUUUAFFFFABX5z/8ABVT9r3W/2Kf2Ndf+LXg1o18SXs0Oj6K0oDKl5d7v3u1gQxhhSWVVIIZkAYbSa/Riv58P+DkzRNW1P9hXw5qVgjSQad40sZrnaOER7G/iV29vMdU+rigD5e+E/wDwRJ+Knx1/Zwsf2nviP8W/FEHxs8R6cmt6fK92xgtZLhBPbwXMjg3XmFSgkeOVBExICOE+b9Ff+CJX7aPxE/ax/Zu1Xwr8bLl73xr8PNQGk391Mcz3Nu6Fraaf1myksTtyXMW9iWZq/T74DeKdE8W/Abwb400WSP8As7UtB0+8gdGBjEMtrHIpDdMBT1r+ff8A4N8fK8QfFT9pn4keHl/4p/WvEVj/AGfIn+rcCfU5sLn+7HPEfowoA/plr+RX9n74N+Nv+C0f7UnxkvP2p/iJr+g+H/AWopp+neGNEuI7byY3uLlIsxypLCBCLfEjmFpJZGyXUKAf629U1Oy0XTLnWNSkEVtaRPNK56KkalmP4AZr+N39mL9mD4s/8Fdv2h/iL+298JPEkfwB0b+0JNMWbw7HcHUL2V1WdzceTdW6+a8bxPcyq6rJIQRGTuegD7O/4JzeMPjX+yv/AMFQ/HX/AATbn8a33xC8BWGnvqFnNqLme40+QW9tcRjeS3l7Vm8iWNCI2k2uERiy1+p3/BQ7V/27rvwv4a+F37B1nawa14qup7fVNfvQPK0ezjjU+eHfciO7NhT5cr4B8uMt8y/jH/wTv0jxD/wTP/4Kdal+w98YbTTPFGofEy1e+sfGsaSrqUysktzGs5llk2xTSW0qyRDLfaNrGR1AI/qxoA/lW/4Ix+FviZ8Lf+Cmnxu+C/xL8XXvjC+8OaRPb3F/dyzOLi4W+tvMm2zSSMCxJ5JJPU9cV+tf/BYH9pT4q/sq/sN+IfiZ8GJTZ69PdWemxX4QObJLuTbJOoYFd+0bEJB2u6t1Ar85f+Ccv/Kb39p3/r3vP/S+1r7a/wCC237UXh39mz9im/03WPDlh4ruPHV2mg29hqas9ooZHuJLiVEZHbyREDHsdWWYxuCNpoA/KKf/AIJSW9v+wOf294/jj4s/4WWvhAeLf7U/tH/Qj/ov277IJMfa8kfuRL9pz5nz+X/yzr9j/wDglR+098av2mv+CfekfGD4jwf214ttf7Qskk+S3OpvYuywOT8savJgRu/C71ZjjJx+JU//AAQU/awh/Y6MB+Mc73Mdl/a3/CC7br+xfNA+0G3Ev2vZ5u7nzPsoHmd8fvK/YL/gjN+1x4M/aC/YZt9QGh6Z4JT4fTzaNf2tj+409I4IkuRdoJHYxpIkpaUyOT5qyMWwc0AfC3wv/wCCSf7V37bF94g+Mn/BUXx54j8O67c35/snQNBv7M21nFGqtHMnlm8to4wx2pFGqyDyy7yMz5Hef8EbfjH8ZvCP7T3xm/YF8f8Ai658f6D8O5pZNI1i6YyvF5F19mlhMrs7jfvU+UWZY3jkCnBOfvn9tv8AZZ8aft/eEvDt5+zr8dtR+H9jpH2+K5l8OTSXNpqhuDb7UuTaXtsreR5LBQxfb5rcDkN+V/8AwR11jVP2Lf20fiF/wTK+JPh/R38QRxf2kPE+mCX7TqHlRJdQpdNKx3R/ZbnfEqhBE29SHZy9AH9QdFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAV8i/tof8AJLrD/sKxf+iJ6+uq+Rf20P8Akl1h/wBhWL/0RPWtH4kRU+Fnvnwp/wCSXeG/+wVZ/wDohK76uB+FP/JLvDf/AGCrP/0Qld9UT3ZS2CvkX9tD/kl1h/2FYv8A0RPX11XyL+2h/wAkusP+wrF/6Inq6PxImp8LPfPhT/yS7w3/ANgqz/8ARCV31cD8Kf8Akl3hv/sFWf8A6ISu+qJ7spbBRRRUjCiiigAooooAKKKKACiiigAooooAKKKKACvz/r9AK/P+tKZnUP/R/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigD5o/av/AGW/AH7XHwnuPhh45Z7V1kFzYX8KhpbO5QELIoPDKQSroSNykgFW2sv5b6F+x7/wVr+G3h4fCL4b/FzSP+EWhRoLWad2+0RQAbVVZJLGa4hwvCLFMVTgKwAr936K+qyfjHF4Oh9Wiozhe6U4qST7q+zPjc94FwWPxH1uTlCpazlCTg2uztuj8/8A9ij9grwn+yj4Y1i48Q6gfFHivxSCNX1OZWAeNsloIwzM2wsxZ3Y7pW+ZsAKq/Ffw4/Yc/wCCiX7K1zrXw8/ZX8eeH08G6vevdwvqcWbmB3RE810NpMBJsRUO13RtobapOB+6lFbUuOceqtWrWcantLcylFNabadLdLaeRz1vDvLXRoUaClT9lflcJOMkpfEm93zbu+t+p+TH7CP7A/xi/ZY+PvjH4o/EfxJYeJLbxFZtEt1G85vZ7iS4SeWa4SSIKpdgxOJZDk8k8mvRP+CeX7HfxL/ZKj8dJ8Rb/TL4+J9Riu7X+zZJpNkcfm5EvnQw4b5xwu4defX9I6KyzLjTHYtVo1mv3qipaW+Da3Y3yngLLsE6DoJ/unNxu2/j+K99/K5+bvh39j34maR/wUg179sG5vtMbwzqmnJZxWyyzG+DrZ21uS0ZhEQXfCx4lJ2kcZyB4p8av2A/2g/A37RGo/tM/sI+KLLw3qXiESPq+najkwyyzP5kzR7oZ0ZJnAco6go+WRwCFX9jaKvD8bY6nUjNWaUFTs0nFxWyae5nifD/AC6rSlTakm6jqKSk1KM5buLWq9Nj8qf2Vv2F/jN4c/aDuv2tv2uvFVr4n8amBrawisAfs1qkkflM2WihAKxs0axxxhRuZizM2RyXxi/YO/aI+H37QOq/tIfsH+KrLw7e+Jd8mtaVqeTbzTSOZJHjzDOjCR/n2uqmNixRwG2r+wdFUuOcf9ZeIfK048nLyrk5VtHl2st0Q/DvLfqqwsVJNSc1NSfPzveXPvdrR+XQ/LT9mv8AZC/aot/j6f2lv2uvH6avqttbm3s9J0aSVLIKVZV85QlvGVj3uVjEbAuRIzkjB6j9mz9jv4l/Bz9sn4n/ALQ/ia/0yfRfGpnNjBayTNdR+bcrMPOR4UjXCrg7ZH59q/SOisMVxhjKvtE7JTioWUUkop3SSW2p04PgXA0fZOPM3Tm5puTbcmrNyb30YV8q/tffsl+Af2wfhY/w88ZSPY3dtJ9p03UoVDS2lxtK7tpxvjYHEkeRuGMFWCsv1VRXg4DH1sLWjiMPLllF3TPpMyy2hjKE8LiYqUJKzT6o/CHSv2RP+Cuvgzw4PhF4N+Lukjw1FG1vb3Esr/aY4B8qqszWMl1EQuAqxzEJjCsAK+9v2Hv2HvCf7G3hLUETUH17xPrzpJqmqSIU37MlIYkLMVjUsxJJLOxLMcBVX7oor6TNeNsbi6EsO1GEZO8uWKjzNdZW3PlMl8PsvwWIjiouc5QVo885S5E91FN6aaeh+a/7BX7HPxN/Za8e/FLxT8QL/S7y38b6hbXViunyzSPGkMt47CcSwRBWIuExsLjIbkYGan/BRj/gn/H+2T4d0zX/AAJPZaX410ZhDDdXpdILizdiXgmeKORxsYmSIhGwSy4Acsv6Z0VguMMcsxWaxlarpstNEo2t6LU6HwJlzyp5NON6Lvo3rdycr37pu6Pyh+Of7Cnxb+Jv7Afgz9lbQdR0iLxD4dewa5uLia4Wyb7LFKj+W6W7ynJcbd0S5Gc4r9F/hN4NvfA/wi8M/D3XzDcXGj6PZadcmLLwu9vbpFJt3qpKEqcblBI6gdK9HorjzDiHE4miqFVrlUpT26y3O/LeGMJhMQ8TRT5nCMN/sx2Pxd+F3/BLbX/gl+3rp/7Q/wANtQ0yHwFZ3F3dJpsjzLe25urSaEwRIITE0SSyjYWlUiPggsuW/aKiijPeIsVmU4VMXK7jFRT8lffu9dxcOcLYLKoVKWBjyxnJza6Xdlp2Wisj8PfHn7CH7d+g/tbeNP2lf2aPGXhrw6/ihnhRrsyTT/ZZDC7RyRy6dcxKTJChypJ44bBIpV/4JoftSftC+LdP1b9uz4prr+j6ZKJV0vR94jlOCCATDaxQEjhnWBnK5UFeGH7g0V9AvEXMYxjyKCkkoqShHnSSt8Vr7HzL8K8rlOXtHOUJScnBzlyNt3fuppbnzp8cv2YPhf8AHX4DT/s961ajT9FW3ihsPsqhTYvbKBbvCvAHlYA29GXKng1+Wmk/skf8FYfCfw9f9nzwx8TNA/4RJIGsbe8laQXcVkQV8pJPsbzodhwoDsYwAqSKoGP3Wory8o4vxeDpuilGcW+a04qVpd1fZnsZ3wPgsdVVduUJqPLeEnBuP8rtuu3Y+UPg1+yxp3wz/Zhn/Zv8Ta7e+I11Oxu7TUdQupHaSX7bG0UnlK7v5Uao22NA2ABk5YsT8gfsM/si/tlfsj+PD4D1nxZo2s/CsSXc/wBmjDLdmaVcRSqr2xaNiyKXjFw0YBYgs3X9bqKzhxXi1Tr0p2kqrvK6T111XZq+ljWpwZgnVw9amnGVFWjyya93T3ZfzJ2V7n4r63+wT+1d+zn8XNb8e/sAeLNN0fQPEjiW80PVsmOKTJO2MNBMjIhJKNmORFOzLDJP0F+yB+yN+0B8Oviprn7QX7UPjtvEvifWYjbrY6fJKunQqdg8woVhRnCoERBCqRjJyzMCv6TUV2YzjjHV6Do1OW8kouXKueSXRy36LzdtzhwHh5l+GxEa9JytFuUYcz5IyfVR2W78lfRH4zfFT9gP9pH4WftAat+0H+wT4qsfDz+Jd8mq6VqWTC0sknmSGMNDPG0bv84VgrREsI2CkKvp/wCyN+wx8WPAnx11b9q/9q3xPa+KfHd/A1tbLYqfs1sjoqM4ZoofnEa+UiJGqIhb75bK/qVRTr8dY+phnh5OOseVy5VzuP8AK5b2/pk4bw5y2lilioKVlLnUOZ8ik/tKGyer9Oh+Pf7R/wCwz+1EP2rbv9rT9jzxbpmh6xrVolrfw6mpwu2KOAlAbe5jkR0iRmDopV1ypYkY9S+Kn7Hvxg+JH7cHwz/ala+0eLTfCek21pqluZZ/tD3Mb3byG3UQFGjzcLtLuh4OVHGf0yoqFxtjeWEfdvGDgnyq/K1azfWy27fM0fh9l/PUl71pzVRrmfKpp3ul0u97b/cflR+1x+wX8TfGPxvsf2sP2RvEcHhP4gQII7z7Xn7NdBYxCsmfLmAfyh5bo8bRyKFJ2kEt5z8Nf2A/2l/i/wDHjRvjr+334rsPEKeGNr6XpOm8Q+aj+YnmqkEEaoHAZgodpSqq7bF2n9naK0ocd5hTw6w8XG6jyqXKudR/lUt0vy6GWI8OMsq4qWJkpWlLncOZ+zlL+Zw2b6vu97n5v/G39j34l/En9vf4fftTaHfaZD4f8J6fFaXdvPJMt47xy3bkxIsLRlcXCfelU5DccDOn/wAFIv2S/iN+2H8H9F+H/wAM73TbG907WU1CR9TkmiiMS288RCmGGZi26VTgqBgHnsf0NoriocWYynWw9eLXNRVo6dNd++7PQxPBWBq0MThpp8td809etktO2yKOl2sllplvZSkFoYkQkdMqoBx0q9RRXzbd3c+rSsrBRRRSGFFQXN1bWUDXN5IsUa9XchVGTjknjrT4pYp4lngYOjgMrKcgg9CCOooAkooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACvz4/4KQfsBeDv+Cg3wOj+HOq3/8AYmv6Nc/b9E1UR+Z9nnKlHjkTKs0My4DhWBDKjjJTB/QeigD+YLxb/wAE0v8AgsX+034V0n9nH9q34y6E/wANrCWA3ctiWmvbuO3OYjJiytpLl0wCBcTBd4Ejb3UGv2v+If7Mnifwr+xFefssfse61/whGqafokelaBqTu6tbtGV3SSSxKZFkmAffMil1dzIAWGK+zqKAPkj9iX4XftCfBX9l7w78OP2kvE6eNfG2mx3AutSM80wlDzO8EbXM6CaXy4yqGV03HHQ4yfiX/gn1/wAE7PjH8EP2lPiV+2R+1vq+jeIPiB42mZLJtGluJ7extJn8yZFa6gt2B+SKGMBDsiiwGO8gfsjRQAV/Pv8AGv8A4Ja/te/CL9qbxP8AtZf8Ez/iHp3hO98amWbWtG1pN1u89xJ5sxizbXUTq8n7xFkiVomLBZNrbR/QRRQB+Mn7B/8AwTN+K3wl+Puq/to/treNo/iD8V9Qga0tprUH7FYwyIEdoi8UJ3lMxIEiijjjLAKS+V9n/wCClf8AwTp0v9vLwTod/wCF9cbwh4/8GXJvNA1yNWzG5KsYZWjZZFRnRHSRDvhdQ6hvmVv00ooA/me8X/8ABM3/AIK0ftf3Gj/Cj9uv4yaLcfDfTLqKe7i0NQLu98k8NtTT7RXcqSFe4ZljbDiJ2Bz/AEMeF/AOn/CP4SWXw0+DdhbW1v4d0pLDRrS4kdbdfs0Pl26TSqskgTKqJHCu+Mthm6+k0UAfj9/wTD/4J1fE39k/xf8AET4/ftOaxpfib4nfEC/eSe/0t5pYIrR3+0SKj3EEDhp7hi0ihNgWKIKeCB+wNFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABXg37Tn7O3gD9q74FeIvgF8TEc6T4htvJaWLb51vKjCSGeIsCBJFKquuQQSMEEEg+80UAfy9aX/wTX/4LQfDj4WXH7IPwz+M3h7/AIVfKJLSK5lMkV7HYTE+ZCp+xTXEIYMcRRXLKPurIqkiv2o/YX/Yl8IfsKfs123wI8AX7XeoyNLealrEkKq91qM6hWn8rJARAqJHGWOERQzM25j9u0UAfmf/AME5/wBmr9sn4CeDPGnhz9tX4hx/EaXWtS87TCbm5vRBbFWEwaS7jjZBMWGLdAY4gvyn5iB+e2k/8Erv2+v2KPiD4i1b/gmT8UNJ0/wf4jmW4l0DxOjSeSwyAFY21zG5jBwsoEUjIFV9+0E/0c0UAfiD+xp/wS1+MnhH9qOX9uf9uzx7D4++JUUbRadFpysmn2e+FoGcbooM7Y3ZIo0hijTLOQzsCv7fUUUAfkT+yf8AsCfGH4E/8FFfjH+134u1PRrjw38Qop0062s5rh76Iy3UMw+0JJbxxLhYyDslfkjtzX0r/wAFAf2GfAP7f3wGk+DnjO9m0i8tLldR0nUoFDta3scbxqzxkgSxMsjLJHuUkHIZWCkfcNFAH83z/sRf8F0pfhv/AMM2yfHDwv8A8IabP+zjqmJf7VNjs8vyfO/s/wA/ft43+fvx/wAtu1fp/wDsb/8ABO34Pfsj/spah+yzBJJ4is/Esd1/wkV3cqIzqEt9bi2uMRqT5UXlKI0jDMVUcszFmP6BUUAfzU+Ev+CXv/BUb9irUNZ8G/8ABPL4y6RB4E1e7a5jsfEUStcW7uFXzNr2F5D5iqAryReX5gVSYuAF+yf+CeP/AAS98Ufsy/FrxF+1f+014ybx/wDFnxOksM99Hv8AsttDMUMnlmVVeSRvLVA2yNI4gI441XOf2NooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigArz34n/DjR/il4Uk8Law7wgussUqYLRyLkBsHg8EgjuCeQeR6FRTTtqgaPgg/sPDJ2+J+P+vL/wC30n/DD3/U0f8Akl/9vr74orX6xPuZ+zj2Pgf/AIYe/wCpo/8AJL/7fVqy/Yhso7pH1HxG8sII3pHaiNiO4DGVwD77T9K+7qKPrE+4ezj2KWm6daaRp1vpOnp5cFrGkMa9dqIAqjn0Aq7RRWJoFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABX5/wBfoBX5/wBaUzOof//S/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigD8MP+Cj37c/7Rf7D37Z3whuJtRtR8G/Gcsdpq8MtpEZIJYZxHeSfadu9QsE8UyLuGSjjpmv3Hu7y1sLSW/vZFighRpJJHICqijJYk8AAck1+Sn/AAW6/Zt/4aJ/YD8T3Wl2/naz4GZfE1jgfNts1YXa8ckG0eZgvd1X0BHw38Tf+Ci/9p/8EE7T4ri+/wCKt8Q6angGQl8SnUMNaXcpKnKyPZRS3SkcgsvTsAfR3/BKD9tv9pX9u/4z/Fr4jeKb2BPhXoN61j4ctEs4oZGa4neSHfMF81ngtUTzAxALTA44wP1/u/jN8HrDxaPAN94r0aHXSwUadJfW63e44wPIMgkycjjb3r+c/XdS8d/8Eqv+CFWiXfw/P9keO/G8ttJcXgXEtrea4DO747TwWMSwK38LoG7Yr8t/AXh3/ghxqX7LkOkfFHxf4jb4sanpgubzWza6k32XVZozI0awIrW0sMUrbGLB2kClg6lsgA/ut1vXdE8NaVNrviO8g0+xthuluLmRYooxkDLO5CqMkDk1x0/xh+EdtPpFrc+KdIjl8QMqaWjX1uGvWc7VW2BfMxJ4AjySeK/lv+CX7Svj/wDaJ/4N+vi5ZfE7UJdV1XwXI+hx3dwzSTy2ayWNxbmWRiSzIJmiBPOyNc5OSfoX/gkJ/wAEvPgZ4r+BHwz/AG0fjDc6n4g8bh4tT0gveyra6bDp9yy2UMUSkb1VYg7K+VyxUKAMkA/ob8afEv4c/De1S++IniDTdBgkOEk1G7htUY9OGmZQefStrStd0nxXoSa34P1C2vra5Qm3urd1uIG6gMGjba4B64b2yK/iz+Nd9+zxov8AwVK+Kcv/AAWG0PxHf6He3c8fhKaF7xbCLTVnc2jgWskc7wfZym37OzBZjIJELltv7d/8Ei/gf+y38Nr3x341/Yu+L8vjfwF4huI5o/DMisp0aU5MbSLOwuVkZNyb5IYmkRVDb2j3UAfQv/BNjT/2ubDwV4s/4a1+Jnh/4lXsmrk6bcaDNFcJaw7fnSR4YYFXexDRxFSY174O1fuDxh8ZPhB8PNSh0bx/4r0fQ7y5AMUGoX1vbSyA5wUSV1Zs4PQV/LP/AMEefjbqf7N//BND9oz446HEk2oeG9SubuzSUZjN19hjW33jjKCVlLDIyMjIrvf+Ccf/AASf+Cf7cX7N8n7Yn7aV5q3izxj8Sry+vFuReSWzWscVw9ssg8o7XldomcbwYljZEWMbckA/qciurWe1W9gkV4XUOsikFSpGQwYcEEc5rzw/Gb4P/wDCMTeN/wDhK9G/sW2kMM1/9vt/sscgUMUebf5asFYEgtnBB71/Pd/wSJ8efE34E/tB/G7/AIJjeM9Yl17Q/h9BeahoE84+eG3jnSKRV67UmW5hl8sHaj79v3jXw3/wRN/4Jw/Bj9tr4G+JfGX7SE2pav4e0HXZrPSdFgvJbW1hvJrS2e7vG8lldpXjFsg+YDEfzBuMAH9lOh6/oXifS4tb8NXsGoWU43R3FtIssTj1V0JUj6Gp9U1G10fTLnV70kQ2sTzSEDJ2opZsDvwK/me/4I9aHqn7LX/BRr49/sG+HtVu9Q8H6LA2rafHcvu8top7aNGKgBfNeC7RJXVV3mJSQMKB/TZNDDcQtb3Ch43BVlYZBB4IIPBBFAH8gv7Xv/Bcj9tzV9CtPjX+zB4QbwR8KptQbS9P1rWrOK4udVugjudqykxqirG2VhEgRgQ8pYhB/R9+3L8cfE37Pf7F/j345eEpo7fWdD0SS4sZZEWREu5NscLFGyrASOvyng9K/Gb/AIOU9N03Rv2R/hxpGj28dpaWvidYoYIUEcccaWFwFREUBVVQMAAYA6V+sP8AwUU/Zw+Jv7W/7EPiX9nv4RXdhZa14hTTgkupSyw24jtby3upFLwxTOCywlQNhBzgkAk0Afkh8AvGH/Bf79o74OeH/jj4C8X+CING8SW32u0S9toop/KLMoLotk4GduRhjwRX7n/sj6b+1FpXwTsbP9sTUNM1Px0J7g3U+kKFtTCZD5AUCKIZEeN3yde5r8Gj+wJ/wWc+B37Omnaz8OfjnaRal4H0pI7DwjpUIW0NvZRjbCk8sKxXE7ImcTw7XckGTB3V+p3/AASl/bo1L9vb9lyL4k+LbOOy8TaHevo2sLBxDNcRRRSrcxL/AALMkqkpztcMBwBQB+lrusal3IVVGSTwABX4Rf8ABPL9qr42/tzftl/Fv47v4muLD4L+CH/sjQdKj8tLO7kO4C8lkK7iRDGZ3UthTPGAcJz+qH7Y3inUfA/7IvxT8a6O5ju9I8Ia5ewMvVZLewmkQj6MoNflh/wbz+C9D07/AIJ1G98mOU+IvEOqXF2rYYPtWK02sDnjy4R8vTnPegD9ufCvjTwd46099X8E6tZ6xaRyGJprGeO4jWQAMULxswDAMCRnOCD3qB/HvgWPxWngOTWrBdcdd66cbmIXZXaXyIN3mEbQWzt6AnpX85P/AASQMn7F37fvx3/4J5eIZjb6SZf+Eh8P+c2F+zxbWUhm6vLZXEDOeQPIbng1zX/BMbU4f2jv21/2iP8Agqf4pia60TQvtenaAzD70McQIKE/dki0+3gQ9v8ASDxQB/SZ41+KXwy+GqwSfEbxHpegLdHbCdSvIbUSHIGE8513HJHT1rrNL1XS9c0+HVtFuYry0uFDxTQOskbqehV1JBHuDX8H/wCz78cf+Cff7UXjzxp+0j/wVq8Tavq3i/Wr8waZo9lDfrZ2lgkamNo5LIZCqzmOKHeAojLuHaTNfoL/AMEW/j94E8Fft/ePf2Uf2cPE9/4i+DGt6dNq/h5NTSVJre7g8iR1VJQhTCyzxSHYPO8uNzyOQD+n2f41/Bu10O88T3Pi3RY9N06Tyru7a/txBBIc/JLIX2I3B4Yg8V1sni3wrF4cTxjLqdoukSwpcJfGaMWzQyAMkgm3bCjAgqwOCCMGv40/+CUX/BO/4V/tz+Pfi1q37QV7qV34V8K+IWW00Szu5LaCa+u3m824mKYbKRRoi7CCdxyQFwfpb/guJ4NuPhb40+AvhPx3pWvXn7N/hW0t7HUrXR5n3GS1dYfLmkdhH532RY1t2lZGbMwSRSWYAH9Pvgr4n/DT4kxzTfDrxFpmvpbECZtNu4boRk5wHMLvtzg9fSvgkaZ+2F/w8v8A7S/4Wf4d/wCFRf2Vj/hDt8X9reZ9kxnyfL8zd9p/0jz/ADceT+7296/KL9jH4Nf8ErPiB+1z4H+Mf/BO74q3fw/1zRlZb/whci7M2sR8PLAG1OXcweIOJkhadeFdBG0eT6TF/wArJcv/AGKP/uMFAH9C/jHx74F+Helf278QNasNCsd237RqFzFaxbsZxvlZVzgZxmrXhbxf4T8caPH4h8Fapaaxp8pIS5sZ47iFiOoEkbMpx3wa/lT/AGdvghpv/BZ39vP4u/FL9q2+vL7wL8Mrz+xtC0G2me2i8qa4uEgXzI2DqBHbNJOVKvJLIp3hECVv2nw4l/4JCf8ABV/4d/C74B6ldn4YfGs2tjd6NeSmcRTyzmzXDtyzQTPHJHIfn2O8ZJBJIB/UEfH3gQeIrnwgdasP7Ws4vPnsvtMX2iKLareY8W7eq7WU7iAMEHuKr+EfiT8OviAbgeA9f03WzaOY5/sF1Dc+U4OCr+UzbSDxg4r+Ur41fs12P7Wv/Bf3x78EvE2q32meGtQ0Wwm12PT5TBLe2FvpOny/ZC46RyzrDv4J2qcYOCLP7R37LHw9/wCCWf8AwU0/Z28X/soT3+jaP8QNVj0jUtMe7lnQwm8tbW5TzJGZ3jljulby5CwWSMMCPl2gH9cNfgb/AMFGf+Cpvx8+F/j/AMafs2fsVeB7jWfE/gLS/wC2PFPiK8hElhpFl9jW/LohYI7fZ2yGmZRuBRI5WPH75V8Yft66Jo2mfsOfHTUNNtIbe41HwXr011LFGqPPIulSxK8rKAXYRoiBmyQqqvQAAA8o/wCCT37SvxT/AGrv2J9C+N3xsvILzXr281GGeeGFLeMpbXLxp+7jAUYRRk456mvzYP7dP/BSr/gob8YfFugf8E0ItE8LfD3wfdfYf+Em1qOOX7dOjH5kaSK4TEy4dI44GZIyrSSKZFUdD/wTP8Q33hL/AIIMeKfFelgm50zQvGd3CF6+ZCt26498gV+dn/BJn4Sf8FEP2kP2YLnwV+zV4/tPhD4C0DU7vz9SgtvNv9Y1edY5H3MAHWOCAwxlldAOBiQgiMA/Yn/gnN/wUG/aL+JH7Q/i/wDYY/be0G00n4j+FIXu4L6wXy7e+gjMYZfLBKbikqTRSRkLJExyiFMv6j/wWk/ah8Zfst/sRahrvww1SfR/FniTVLHRtJurU4nikkc3EzR4BOTbwSJnsXHcivl//gnN+2V+1l4J/bG8Tf8ABNT9um+i8R+JdLgkvtF8QRBA1xEkSTiNiiIJY5bd/OjkcCVCrxybjgJkf8FJM/tM/wDBU79m79ji3Jm07QJpPGGsxAZjaONzMqS9cfurCRB04nHdhQB6v+2n+3P8b/2C/gD8H/2fvBlm3jn43+PLSz0uCfUm8xGvkW3guJ5huQyST3MwSFN6rklmbCbX+Vfi9+1d/wAFmf8AgnbZ6R8eP2vT4V8f+ANQ1CK31Kz0hI4riwEwO2FZUt7YoxwdjkXKbhtZhuXP9JOreDPB2vataeINd0myvb/TyGtbmeCOSaAg7gYpGUshBGcqRzzX803/AAUB+OPib/gq5+0Bpn/BNj9kBhe+FNF1GO/8aeKIx5lpELZipWNx8rRwEttIP7+42qhCKXYA/Yr9rX9vj4b/ALMn7F4/bCghOr2mr2VlNoFmW8pr641OMS2sZbnYvlkyyEZIjR9oLAA/i5bfHr/gv7ffAg/tzwSeGF8K/Yv7aXwj9hi+0vpuPN85YvLNx5fkjzAv28TmM5ClsVrf8HE3hjTPhv8Asg/Bv4VeHhJB4b0fWY7JEByVistPaCDjgFliLgdO/TNf01WulaI3h+PQ7OGP+zjbiCOJAPL8jZtCgDjbt4A9KAPzo/Z++MPwk/4K7/sBX0/iHTxZ2niq1udD1zTwwlaw1GIKSY2PUxsYrm3Y8gGMsAwIHxd/wQI+O/jjV/hD43/Y5+K8rP4g+DmrtYRBySUsppJk8gMfmb7PcwTqCcbY2jQABRXkP/BtNLNB8GfitollM0+l2viWBrVyeGLW+1mx0BZEjJ/D0qL/AIJoQrpX/Ba39qLSdGJNhMNQuZsdPtD6nA5/HdJL+tAH9MdFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAV+f9foBX5/1pTM6h//T/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigCnqOn2Or6fPpWqQrcW11G0U0TjcrxuCrKwPBBBII9K/hx8Cf8EzP2rJf22tN/Yl8S+F/EB+COkePLrWjqUun3P9kT2QjRjK16Y/IMk9lbx24+c4lYpy2RX9zVFAHwR/wUo/Y6n/AG4P2SNc+Bmg3cWnayJINR0iaYHyFvLQkokm3lUlQvEWAOzfv2tt2n8X/hP+3p+2v8CPgZYfs1+M/wBkvXtZ+IfhnTo9GsNSttOlk0+5+zxiGG5m8m1lV9iBTIYZmjlIJDxBsL/UvRQB+Gvxd+H37afj3/gjv4+8PftB+HrW7+J2v2PmR6J4ZsMzrF9og8qF4bUyia52o0jmIYAIXGUJP2h/wS48G+L/AIe/sAfDDwZ4+0q80TWNP0ox3VjfwSW1zA5nlbbLDKqujYIOGAODX31RQB/Oh8ZP2uf29PgV8cPGfwz/AGv/AIByfGv4b39w58NXWgaT9ptxbhn8rzl8m6QvLG6JLHNsdHRim9CCcf8A4I4/sjfGjwz+1b8Sv2y/FXw8n+Dng/xRZS6fo/hGcvHJH59xBOWMEiRukcIhIUtHFzIwjUIMV/SPRQB/M3/wSC/Yx+I/iL9hX45fs6ftA+G9a8EnxxqVzaQNq2nz2cwSaySNLqGK4WIyLFJhgR8pK4J615h+zH+03/wUB/4JX/D28/Yx+IfwB134kWfh+7u28OaxoS3LWk0VzM02wSw2dyskbyvJKMlZkD7HjHGP6s6KAPwR/wCCU37Gn7QvhTxH8UP26P2srP8Asvx98VVuFh0YIUls7WWUzv5qZOxpXWNY4Tlo4413ksxVJv8Ag3t+D3xc+C37JXi3w58Y/C2r+EtRufF09zDa6zZT2E8kJsLJBKkdwkbMhZWUMBglSM5Br96KKAP5/wD9j74M/GDwz/wW9+PXxY8SeFNY0/wrrGhSQ2Gs3NjcRafdSGbSyEgunQQytiNzhHJwjf3Tj+gCiigD+f3/AIOGfgz8YPjV+zb4H0L4N+FNY8W31p4l8+e30WxuL+WKL7HOvmOlukjKm4gbiAMkDOTX6c/tsfC/9oX4rfst6t4T/Zc8TTeEfHcSW9zpt1HKYPMeBg0ls8mDsEyblBIwH2lsLmvsmigD+YS2/wCCl/8AwVP8M/BGH9nXWv2bvFF98UUshpK+JjBdSWkrhPKGoOkdqYnlz8zlbkQl8vuC/u6/S3/gkL+w14q/YT/ZW/4Qj4jzxy+KfEmoPrWqRQsHjtHkhihjtVkHDmJIgXYfL5jMFLKFY/qdRQB5x8Y/AEHxX+EXir4W3T+XF4l0e+0p2PZby3eAn8A9fhN/wbo+Ory1/Z38f/s3eK4Ws/EXgDxTMbu0k4khjvIwmxhk/Mtxa3CnHFf0QV8J+BP2A/hd8Lv2zvEX7aXw71XU9J1XxdaNba1o0LQ/2XeO+0tcNGY/MWYyIspZXGX3n/lo4IB+Q3/Bcf8AZi/aMt/jL4I/bA/ZB8P6xrPiSbStS8K6uuhWU99cxwXNvNFFMYrZHYbobm5jMpA2kRDOduP1J/4Jo/sl237OP7AnhX4H+MbFoNS1nT5b/wAQQSKUl+16qpeaGUcEPDGy257/ALsfWv0cooA/k6+ANt+1P/wRq8X+Lf2ffE3wT1P4y/DvWNTfVtF1/QrN5plZ4o4T5pSCdVZo44leFzGUdXZGkRga/Un/AIJ4/Eb9uz47/FLxT8XP2gfh3YfC74dyRmPw/ot3YeRrQlJRcvIwilEQRWZzLAu93HlgIpr9fKKAPwG/4IU/Bn4v/CC3+Nq/FnwrrHhc6r4oSey/taxnsvtMQE+ZIfPRPMT5h8y5HI5r3n/gor8cP+ChP7O/xQ8L/ED4B+BoviZ8J3g8rxFoVjZtcam0pZ1cEossgheN0ZHjhcI6N5o2EZ/YCigD+QmH4JfFL/goL+3h8L/jF8F/2eL/AOA/h7wdqdvqeu65e2p003621zDPuCfZ7eN51EbRx+WsjMXzIwRfl+/Yvgz8Xx/wcAyfGc+FdY/4Q8+F/IGu/YZ/7N83+zxH5f2vZ5O/f8u3fnPGK/fmigD+XG88Eftcf8Eff20PiD8WPg78ONS+LPwo+K1wb+aDRo5WubCfz5p0STyYbh42tvPmRCyeXNG65dZAQvVfAb4SftY/8FLP+ChPhr9uL9o3wLe/C3wD8M44ToOj6okq3l1cQu8sRHmxwO379vOlmMSptWOJA53OP6ZKKAPwC+HPwZ+MFj/wcB+PfjPe+FNYh8H3nhiGC3117G4XTZZRp2nRmOO7KeSzh0dSocnKsMZBw3/grx8GvjB8Sv2yf2VPFHw58Kax4g0zw74mNxqt3ptjcXUFjF/aOlP5l1LCjpCmyN23SFRtRjnAOP3/AKKACvlv9uPw9r/i39i74t+FvCtjcanqmpeDdctbSztInmnuJ5bCZI4ookBd5HYhVVQSxIABNfUlFAH46/8ABHT4H+KvD/8AwTO034L/AB28N6joNxqEut2t/pmq2s1lc/Zry4lUhoZ1R1Ekb5BK8g5Ffmh8APE37en/AARc1Xxd+zyfg1rHxf8Ah1qWqz6poGq6L57MpkVYlMslvbXQiMqRRCSB44ykgdkMitlv6uaKAP52v+Ccv7NX7Vnx5/bi8Sf8FQv2v/D7+B5ry1k0/wAPeHbiOSO6jjeFLdHeOXDxxxW4ZP3iq80rvJsjUANY/wCCdOf2m/8Agq/+0d+1/cBptN8LvH4O0d25jKxuIGkh64zHYB+3FwSRljX9DhGRj1r52/Zr/ZP+An7InhLUfA/7P2hnQ9O1a/fU7tHurq8klupI0iaRpbuWaTlY1G3dtByQMsxIB+Vf/Bb74vftv6T8OtK+Af7H/grxFrFt4vt7g67rWgafeX01vboVT7GrWsTiEzhiXYsGKAquAWNfAH7EX7W/7Rf7CfwYtvhL8LP2HvHk9xJtm1bVpf7SW51G7xgyy40I7VHIiiBKxrwCWLM39btFAH5C/t1/sz+Of+Cnn/BOjSrc+H5PB3j2WGy8TadoupuyyWmoLCwksLh5IoWVmilkiy8cYEm1nVQpx+Zaf8FFv+CpNt+zmv7II/Z48Tn4mrp//CPjxN9nuvI2BBbi+2C28kzbMnzftPkb/wB7nZ+7r+q6igD8o/8Agml+yxZ/8Ez/ANhe5i+NF3Baap/pfinxROrq8NqVgXMQk6MtvbwqGIJUybypKkE/E3/BA3wD4n+IGpfGb9vfxnatbP8AFDxDMunLIDu8pLia6u3VujRmadYgRjDQMPp+/nxK+GngX4w+B9Q+G3xM02LWNC1VFju7Kfd5cyK6uFfaQSNygkZwehyOKs+APAHgr4V+DNO+Hfw50y30bQ9IhFvZ2VqgSKGNedqqPckk9SSSSSaAOwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACvz/AK/QCvz/AK0pmdQ//9T+7j4W/wDIiWP/AG1/9GvXoFef/C3/AJESx/7a/wDo169ApvcS2CiiikMKKKKACiuV8aeOPCPw68Oz+LPHGowaZp1sMyTzttXJ6KO7MeiqoLE8AE1zvwo+L3gL42eF28ZfDm7a909Z3tzI0UkR8xApYbZFVuAw5xigD0yivmH4oftjfs9fCHxE/hHxhrw/tOLHnW9rDLcNFnn94YlZVIHJUncBzjmvY/hz8TfAfxb8Mx+Mfh1qUWqadKxQSR7lKuvVXRwrowyDtZQcEHoRQB3dFMllSGJppDhUBYn2HWuC+GPxP8GfGHwhB468A3LXmmXLyJHK0bxEtExRvlkCsMEdxQB6BRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUV53oPxU8E+JfH2t/DLR7ppNZ8OrC99CY3URi4QPHhyoVsqQflJx3oA9EooooAKKKxvEWv6X4U8P33ijXJDFZabby3Vw4UsVihQu7bVBJwoJwASe1VGLk7Lcmc1FOUnojZorxD4CftFfCT9pnwbN48+DmpnU9Ntrp7KV2ikgdJkVHKskqqw+V1IOMEHjvXffEHx94U+FvgjVPiL45uxY6Ro1s91dzkFtscYycKoLMx6KqgliQACTXTVwNanW+rzg1O9rW1v2tvc5KOY4epQ+tU5p07X5k1a3e+1jsaK8q+C/xp+Hv7QPw+tPij8Lrt77Rb15Y4ZnikhYtDIY3+SVVYYZSORzXqtZYjDzpTdKqrSWjT3T8zbDYmnWpxrUZKUZK6a1TT2aYUVznizxj4R8BaHL4n8c6rZ6LpsBUSXd/PHbQIXYKoaSVlQbmIAyeSQBzWpd6rpdhpcut31zFDZQxNPJcSOqxJEq7mkZyQoUKMlicAc1HspWUraMv2sbuN9VqX6K5Gz8e+DdU8GP8Q9C1K31PRFgkuVvLGRbqKSKENvaNoS4kxtIwuTkY615r+zn+0Z8Of2o/hwPih8Lzdf2abqW0K3kPkyrLDjcNuWBBDKQVYjnBwQQOj6hX9nKryPli0m+zd7J/czm/tLD+1hR51zSTaV90rXa8tUe8UUUVyHaFFFFABRRRQAUV434X+Pfwx8ZfF3xF8DNAvnl8SeFYoJtStzDIqxJcIjxkSsoR8q68Kxxnmug+LHxU8E/BL4e6l8UfiLctZ6LpKI9zMkbysokkWJcJGGY5d1HAPr0rreArqpGi4Pmlaytq+bay63vp3OJZlh3SlXU1yxvd3Vly35rvpazv2seiUV8pfFb9s34I/B3wL4N+I/iqe9l0nx1JbJpUtravIzLdxrNHJIh2sihGBK4L84CEg4+raeIy+vShGpVg0pXtfrbR/c9xYbMsPWnKnRmm42bSe3Mrr71qgooorjO4KKK+f9B/ad+Dvia88eWGiahLPN8NS419BbzAwFFlchMp+9OIXx5e7OPcV00MHVqpypxbStey2u7K/q3b1OXEY6jRcY1ZpOV7Xdr2Tbt6JNvyR9AUV4n+z38fvAP7THwxtPiz8NvtI0u7llhVbuLyZVeFyjhlBZTyOCrEe+cge2VOKwtShUlRqq0ouzT6MeDxlLEUo16ElKMldNbNPqFFFFYHSFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABX5/1+gFfn/WlMzqH/1f7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooA8I+JH7O3w7+LvjrSPGnxEik1OLRImS206Vs2Zkdtxlki/5aMAAAD8uPvBuMfOH/BNVEj/AGf7+OMBVXXr0ADgABYuBX6DV+fX/BNrP/CgdR28n+3r7Gf92KgDvLg/s3/sRaff+IvFF7PBc+Lb+e6lu7mJ7q6uZmw7x74YeEBJYK2Blic5Nea/sHWMut618Q/jBoNkNL8LeKtUjk0mzBQMoh83zJGjQkRF96/L7HHyhSeu8C/th/Bvx/Dq3hf47W1l4O1zRrqS3uNL1eVZFKqBh45JYolcNyNoXdwDggqT5X+xyNC1X9pX4keKvgvbvb/Du4jgjhKI0drJfqE3mBWAAAPmnAHCsvRSooA/SvU/+Qbcf9cn/wDQTX48fsY3X7V3iT4A2uj/AAUbRdF0rS57lfteqCSWW8uHkMrLGqKypEoZVZiMls4J5x+w+p/8g24/65P/AOgmviL/AIJwgD9lPRsd7q9/9KHoA6f4C/tNXni/4ReJvGHxftYtJ1TwNc3dprUdvlk3Wa72eNCWOTyoXc2WU4OCBXjvhn4hft1/Gnw83xe+GkWgaJoVyXl0zS9QSRrm5gViFaRwpALgfKQyBuowuGPAfDLwXrHxE8HftJeC/Dy77/UPEWqR26ZA3yiSVkTJwBvIC5PHPNewfs6ftbfA7w98ANG0Xx1rUGg6t4XsY9NvtOu8x3Sy2aiE7YSN7ltmcKCQTggEEAA6PSv2qtS8b/sqeJvi7oNoNL8S+GobiC9s50LLBfW6qWG1sEodwIzyOVJypr3vwH4513xB+z3pHxJ1ExnU7zw/DqUhVcJ572olbC9l3HpnpXwB8IvA/i7xp+yt8YvH0enTWp8f3Op6rpdmyHzXgZWkj2oM8yElUx97AIypBPUeAv2v/gvpn7IGm6Dbamtx4itdBTSY9IRHa6kvI7fyFUIoJ2OwDbxxtPqMUAb0/wC0/wDFKP8AYEh/aKV7X/hJHcqW8n9zj+02tf8AV5/55j16816t8L/GH7TE9ldfGb4ynS9O8Kf2TNfw6PZq8l7GFUSxtLIUwX8sNuVWxkj5QcgfEV1/yiOtv+up/wDT29frRJrNr4d+F39v31pNfwWWlieS2t0EksqRw7mREYgOzAEBSeTxQB8EeDPin+2/8Yvh43x1+HEnhqPTZDNJZ6EVkmnlSF2UxSS/KBKduAAybs87M4H6JeD9W1jXvC2n6z4h06TSb65gSS4s5GV2gkI+ZCyEq2D0IPI6gHgfjTrFt+yInw6vvjZ+z/49v/h5rbQy3Eejw3u1muE3FYZLMF5CHYbQUcxgNnBXiv1J/Zr8V+N/HPwJ8M+LPiMmzWb6zElwdoQv8zCOQqAApkjCuQAAC3AAoArfH/xh8ZvC3hyytfgd4eTW9Y1K5W2M07AW1mjdZphvV2GTxt4ABLHgBvmC4+Lv7VPwG+IPhPTvj9PoeuaD4tv49MM2mpJFLaXEpAU5ZUDIC2eVJKg/dOM6P7cPjjxPoXiPwF4KfxHc+D/CviC7uItX1ezJjlQRrGY4/NUZjD7m56Hq2VQg/E3xp0H9mfw18Q/h/p3wg1+58Va9J4gsZLu/lv2v1S381QEaRT5QeR8NhRuAQ5wDyAfox+0H8cPibpfxG0b9n/4B2VtceK9Xt2v5rq/DG1srNSy+Y23ncWQjkHHA2sWGPAvHnx0/a++B3i3wl4C+Jg0fUI/EesWsEer2MT7GgaQRz27xuECy/OrIwAGAfvHO3pvjJ4ntP2dv2ytM+OvjmGZPCniHQjok1+qNKlrdLL5oDKgZgCsaEYGTlyAdrV49+1N+0b8OvjJ8Qfhr4Y+GE7avaab4msZ7vUI4pFt45XkVYoBI6rl2XexA4wvUkHAB9ZfHb46/EyL4n6d+zx+z1aWlz4qvLY395d34Y2ljaDIDPsydzHHUEDKjaxcY5Hw38a/j98HPizonwx/acXTdR07xW/2fS9Z0tGRVu8gLDOrBQN5ZQMKDkggsN23l/GfiTT/2e/255vib8R82nhrxpoiWEGpMuYYLqAxkxyNyUBEWTxjLqegYjK+P3xE8J/tIfGP4c/Cb4NXkWvS6RrMOuale2bCSC1trZhnMy5UkgngH72wdWFAH6dV+RbeIfjTa/ty/Ezwh8DLOyfVdWi05pb7US/2ayt7e0iLOyoCzM7OqoMHk9CMkfrpX5Q6B8ZPBnwi/4KB/EU+Pp10/TtYgsLZb6UYhinW0hkRJJOiCRVfBPGV/EAHunw0+NHxz8C/Guy+A37SsVhdzeIIJZ9F1fTFZIpWgDNJFKrBcMFGeFG0kD5gwI7H9nn4y+NvFnxJ8ffB/4ntAdX8K36tavDH5QlsJxmFtuTyAFYn/AKaAV4X408eeGf2jP2wPh1ovwouBq9h4J+2alqmpWhD28fnKojjEoOG3NEqnbkHeMZ2tin+174hv/wBmj456D+0/oduZrbVdNu9D1GNQMPMsTS2ZY/7TquT/AHIulAH0B8IfjJ43+Kv7QvjvQbF4R4O8JGPT4iI/3st+cCU+ZnlY2SQEAd0OfX174/f8kI8bf9gHUv8A0lkryn9in4a3fw3/AGftJOtAnVteLazfu/32mvMOu/PO5Ytitn+IGvVvj9/yQjxt/wBgHUv/AElkrsy7/eKfqvzOHM/92qf4X+R/P/8A8ElPFWu/AL4oeHvBvieY/wDCPfGjRpr7TXIIRNS0u6uYDFuJwGaOKTdjk74R1xX3D/wVM8U618R38EfsTeBpympePb37dqhTBMOlafmZnde4LI0o9fs7DvXyTa/C3XfEX/BJL4Z/HLwANnir4V3d34isJVXLCGHU7g3K/wC6qqs7eohA717/APsR6jqf7WXxf+J/7eniiye0s2sj4b8OW0x3G3gihD3JHYE/IdykjdLMua/eM7VJ5jVz92vRlODX/TyMuWm7f4Wn/wBuM/nHh51Y5ZR4ZV7V4wmn2pSjzVVf/EpR/wC34nYf8E7vGHjPwD/wTCsvF3w78PzeKdbsm1R7PS4GVHnlN7KqglmX5VzucLlioIUFsA8Z8Qfi7/wVU+CHwtk/ag+JbeEZdEslhub/AMMRxTLcwQTyImzzAuRIhk+b/SHC4z8/K14p8K/if8VPhB/wRYj8b/CCaSz1SG+uYZLyEAy2tvPqbxyypkHDYYLu6pu3AgqCPEP2l/Bn7CWi/s1XXjZPirq3xT8falaxiwW71Z7mRbqTb5k0lqo326RrvfbcEngKSxIzWHyanVzOvOtTUozryj8DnKyaur3UYLW/Nvu9kZYnPqlLKMNToVZQlTw0JfxFTjdp2aVnKo7q3L8Oy3Z9q/8ABU7xL8T/AIq/sRaR8W/AF/ZWngTWLLTNR1OwuELXspvJbeW08qQKVAjZx5gJXOO/Q+t+NPCX7csH7CfiO18U+K/Dk2sDTZJmmhtZBGdFXTZBPbjMQ/0lmwVk2bR7Z48s/ae0y/1P/gizoH9nxNMbfwz4XmkCjJEaGz3Nj0UHJ9Bk9Aa+4dM+KPgH9ov9jzxC/wAGNUg195PDFzYtFbNmSO6l087YJE6pJlgCpGQa+ZniJUMvowp04uNOvNNuKdrclrvz213SS6H2FPCwxOZ151aslOph6bSUmrt+0vZX2Wjstm2+p8nf8EpNO/aI0n9mbRfEfijWdKufAh0u/Oj6fDAwvobhb2Ulp5doVkyJcAEn5l9DTfhP+3V4y8Lf8E07n9q3xjp1nqGtW11PawWlrELS2eWS9+zxFliGFVd+98YL4IBDMDXRf8EuPjL8MfFH7GOhfCfRdatpvE2hafqT32mBsXMMZvJiJGQ8lCJYyGGR8wGc5A+cv2UfiB8Jvhx/wSRXW/jp4bvPFPhS41C8tNQsrKNJH2TXhCSNvlh2KkgTEiuHR9pXkAjszPBRrY7FSxNC7+sU1ZKzlFuptt8SS1vr3ODKcwlQy7BxwmJsnhqj5m+ZRklSs3vpBt6W0V1Y968OeN/+CpHh+w8N/GXVY/DHj3w9rclrJd6DoS7LmG0ugG8y3uJDHGzIp5LTOgOD8yZce4/tjftV/EP4ZeMPCv7Ov7O+lwav8SfG5L2i3oJtbGzTd5l1OFYE4COVA+UCN2bO0I/5GfF+4+An7MHhTSPif/wT0+M2ptrN/fQG38IxXh1GC5WdsGN7QKGjK55W5Dsx+UYYg19uftUeIr/9nz9u/wCFX7XPxVsmtvCV3oJ8N6pdxKZk069kNzJliuSFzOMEcsiSFQSMG6+Q0Z4mlWdKLTVTljyOm5SirqMo3s9Xo4v3tU2ZYbiOvTwlagq0k1Kkpz9oqkYxm7SlGdrq6Wqkvd0kkkal5+0h+2r+x1458Nyftqy6F4j8DeKLxdOfWNDjeOTTLqQZj80NHApj4YkbCxRGYMGXY3W/tT/tTftP+Bf20vDH7NH7P9jpmpP4o8Oi6gi1JSkMN0090HuZpUO/yYYbcuY1+ZiMLkkKfEP+Ci3x1+Gf7XHhHwr+yb+zbqlr4x8S+KNatrhm05hcQ2dtCjl5ZZV+VCN+WGcqiyF9uAD7L8QkUf8ABYvwCDzt8Az4J5P+vv656GAo8kMXisPGNR06rcLWT5UuSXL0u7rS17HViMxxHPUwODxUpUlVoxU+bma52+eClreys9b25g8FftB/tjfAr9qHwj8CP2uJNB1zR/iEtymlato6PAYLqBQxhZXVNwBZE2lMnzEYSEhkr9Y6/Jz9vv8A5O9/Zi/7GK//APQrGv1jr4fieFOdDC4uEFB1Iu6irK6nKN7dLpK9j9D4QnVp4jGYKdSU405pRcnd2lCMrN9bNu19T8KPDv7R/wAFf2cP+Cnfxu1v41a4mh2upWWlQW0jwzzCSRLS2ZlxBHIRgc8gCtv9vb9v79kP4v8A7JHjL4cfDjxlFqetapBbJa2y2l5GZGS7hkYbpYEQYRSeWHT1rsfgj4O8I+MP+CpXx3t/FulWeqRw6fpDRreQRzhCbW2BKiRWAJHpXq3/AAUq+FPwu0H9iHx7q+h+GtKsruC3tDHPBZwRyITe24yrqgYcHHBr72NTLVm2BVaE3U5aGqlFR+GFtOVv11+4/N3SzV5LmLoTpqlzYnRxk5W5p31U0u9vd08zz74kfG/xp8Ev2Q/2b7nwYlo7a9c+FdLuftcCzgQS2CljGG+5ICo2uOR2rd/an/am/af8C/tpeGP2aP2f7HTNSfxR4dF1BFqSlIYbpp7oPczSod/kww25cxr8zEYXJIU+BftTf8md/srf9hrwh/6b690+IgB/4LG+AiR08BT4/wC/9/WdDBYZL29SkpNRxEtVu4vS/obYjH4tv6vSrSgnLDR0eqUl71vUTwV+0H+2N8Cv2ofCPwI/a4k0HXNH+IS3KaVq2jo8BguoFDGFldU3AFkTaUyfMRhISGSut+Ov7Rv7SnxA/aIvP2Uf2NbbTbXVPDtpFeeIte1lGa2s/tCJJBDEqh9zsjAnMb5JIAUI7VyX7ff/ACd7+zF/2MV//wChWNfGHxd+EHwT8Mf8FDfHen/tW67rfhLRPGsdtqfh7WbW8NlaTukSrcQzTBXUeW5KJv2hAoyR5ibnlWW4PFeyxs6UVN0pS5VG6co1HG/JdXtHVrbS9tGZ51m2OwftcBTrScFWjHmlO0lGVJT5faNO156KTV9eW+qZ99/AL9pT9o7wd+0nF+yH+2FbaXcazq+nvqOg63owdbe9SFWeWN0YLh1WOQ52R4KEbWDI58n/AGONVu9B+P37WuuWG3z7LWEnj3DK7411BlyO4yORXDfs5fD39hG0/bX0TQ/gZrninxt4n0CyuL9dXS/i1DSLVGikheOaf5WOVkAHlBk3yKpbO4Dp/wBlL/ks37YH/YS/9k1GjMMJh4U8T7GDjzU6TaceVN+1jqo3dk1bTvfoVlmNxNSrhPb1FPlq1VFqXO0lRlo5WV2nfXta7uZd5+2p8bPDn/BLHRP2ndFbT7bxPc372reXaItqsY1Ge3wsC4VfkQdO+T3rY+Kfx1/4KZfDX4bN+1jq1l4Vi8JwLFez+FkE0l9Bp87rt864KqDOiMPMKPtXlvLOCg+MvE//ACgr8Of9hd//AE8XVftF+3YAP2IviGo6Dw/P/wCgitsfSwmGxMaaw8JKeIqwd1f3VKCsu2+j3XTqc+XVsbi8JOtLEzi6eFozVpW99xm+Z9/h1Wz69Lcx+0F+2lB8Mv2bvC3xe+HukNrWv/EMWFv4Z0tuRLd6nCJYRNtKkogOGCkFm2oCu7cPlPx78af+Clf7JvhuD48ftAjwv4r8Hx3EC6zp2kq8V3YQ3DiMNFIyRqxV2VMlpRuYD7uZB8/ftWfDa48QfsEfs5/FW+g1G68P+DbbR5tdXS223MWn3Frb+bcRnorx+UFR/wCFpATgZI5r4qeBP+CWHh/4bQeJT8RvFXjOPU5IYodF0vV1u7+YyOuA1pKieXs+9++2cjAy5AO+S5BgKdKEfZc/NOcZe45uylZRUuZcj5db+d9kc+f8SZjUrVJe29m4U4SheoqavKN3Jx5X7Rc3u28rJJu5/RV4e13S/FOgWPibQ5fOstRt4rq3kwRvimQOjYPIypBrXrhvhf4a0rwZ8NPDvg/Qobm3stJ0y0s7eK8INykUEKRosxXgyBVAcjjdnFdzX4fiIxVSShtfQ/obDym6cXU3sr+oUUUVibBRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFfn/X6AV+f9aUzOof/W/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigArn/DfhPwr4NsG0rwhplppVq8jStDZwpBGZGxucrGqgscDJxk10FFAHnni34R/Cvx9eJqPjjw3per3EYAWW8tIZpAB0G51Jx7Zx7V2Oj6Lo/h7TotH0C0hsbSEYjgt41ijQZzhUQBRz6CtKigBrKrqUcAqRgg8gisTw34X8M+DtJTQfCOnWulWMRZkt7OFIIlLHLEJGFUEk5OBya3aKAMDRfCnhbw3c3t54d021sJtSma5u3toUia4mYktJKUALuSTlmyT61xev/A34MeKte/4SjxL4U0m/1EkM1zcWcMkjEdCzMpLEds5r1OigCOKKKCJYIFCIgCqqjAAHAAA6AVwNn8JPhVp+t3Hiaw8NaVDqN0GE10lnCs0gcENucJuO4EhsnnvmvQqKAOKPw2+HTeER8P20DTToKnI037LD9jB3+b/qNvl/6z5/u/e56812UUUUESwwqERAFVVGAAOAAOwFPooA8ln+AnwQudfbxTc+ENGk1Fn8xrhrKAyF853klOWz/F1969aoooAwfEnhbwz4y0mTQPF2nW2qWMpBe3u4kmiYjkEo4K5B5BxxXFaT8DvgxoVjFpukeE9IggguEvI0WygwtxGCEmGU/wBYoJCv94A8GvU6KAPlr9obUvj9o2paZqXw28N6f4x8NbHj1bR5ysd1KxPyOkkpMZVePlCE5zkMCCnzZP4H+Mn7QvjnwdY3PgKL4c+DfCuqRazOJZIjNczwkbUjihVduRlclcYJbdkBT+nFFAHP+JvCfhfxrpL6B4w0621WxkILW93Ek0ZI6Ha4IyOx6isjwX8NPh58OIJbbwDodjoyTkGX7HBHCZCOm8ooLY7ZJxXb0UAFcJq/wu+GevvqUuueHtNu31gRi/ea1hdrryRiLzmKkyeWB8m7O3tiu7ooA43wZ8O/AXw6sZNN8BaNZaNBMwaRLOBIQ7DgF9gG4gdzk18VfHHwP8cP2l/iDYfCjW/DCaJ4B0jVkvbvVJrmKV9QigBCpFCvzx+YGYc5xkFiMbT+g9FADURI0EcYCqowAOAAKrX9hYarYT6XqkEdzbXMbRTQyqHjkjcFWR1YEMrAkEEYI4NW6KadtUJpNWZymieA/A3hnwkvgHw5o1jp+hLHJCNNtraKK0EcxYyIIEUR7XLMWG3DFjnOTTvCvgXwT4F8Op4P8E6PY6PpEe/ZZWNvHb2y+YSz4iiVUG4klsDkkk9a6mitZYio7pyeru/N9/UxhhqcWnGK0Vlpsuy8vI4/w98PPAHhHwofAnhTQ9P0zQysiHTrS2ihtNsxJkHkRqI8OWJYbfmyc5zXl2ifsn/sweHJb2bQ/h54ctTqMbQ3OzTLXEkT43xEeXjy2wNyAbT3FfQNFbQzDER5uWbV99Xr69zCpleGnyqdOL5dtFp6djEs/DPhvTvDkXg7T9PtoNIhtxZx2McSLbJbqnliFYQAgjCfKEA2heMYrmfh/wDCX4W/Ce2urL4X+HNM8Ow30gluI9NtYrVZXAwGZYlUEgcDPTtXoNFY/WanK48zs99d/U3eFpc0Z8qutnbb07HmWgfBX4PeFPFt/wCPfC/hXSdN1vVI3ivL+1s4Ybi4SVw8iyyIgZw7qGfcTuIBOSBW14f+HHw88JeFG8B+FdB07TNDcSK2nWlrDDaES58wGBFEZD5O75fmyc12dFXUxlWXxSb26vpt93QingaEPgglv0XXf7+vc8L8G/sw/s4/DzxCvi3wL4E0DSNURi0d3aafbxTRkgg+W6oGjyCQdmM969W8T+FfDHjbQrjwv4y0611bTLtds9peQpPBIuc4eOQFWGRnkHmt6inWx1apNVKk25Lq27/eKhl+HpU3SpwSi90kkvuPIvhx8APgf8ILyfUfhZ4R0jw/c3K7JZrCzhgldM52M6KGK5525x7V2Nx4C8DXnjGD4iXei2EviC1tzaQ6m9tE15HbksTElwV8xYyXYlA23LHjk11lFKpja05Oc5tt6Xu72ClgKFOCp04JRWqSSST72OT1/wABeBvFer6Z4g8UaLYalf6JI02nXN1bRTTWkj7dz28jqWiY7VyUIJwPQV1lFFYyqSaSb0Wx0RpRi3JLV7+Zyem+AvAujeKtQ8daRotha63qyol9qENtEl1crGAqLNOqiSQKFAUMxwAAOlXvFHhXwv430G48LeNNNtdX0y7AWezvYUuIJQrBgHikDIwDAEZBwQDW9RVOvPmU7u62+W33ELD0+Vw5VZ3urb33+/qcLqnwu+GeuaPpXh7WvDumXmn6C8MumW09pDJDZPbrsha2jZCsLRL8qFACo4GBV648BeBrzxjB8RLvRbCXxBa25tIdTe2ia8jtyWJiS4K+YsZLsSgbbljxya6yiq+tVNuZ9evff7+pP1Sle/KunTtt93Tscnr/AIC8DeK9X0zxB4o0Ww1K/wBEkabTrm6topprSR9u57eR1LRMdq5KEE4HoKzviD8LPhp8WdITQfifoGn+IbONt6Q6hbR3Co+MbkEittbHGVwfeu9oohiakXFxk01trt6dgqYSlNSjOKalvpv69zz34efCX4W/CPTpdJ+FvhzTfDttcMHmj061ithKyjAaTy1XewHALZPvV/Sfhz8PdBvdX1LQ9B06yufELb9UlgtYo3vmww3XLKoMxw7cyFvvH1OezopzxdWTcpSbb3139RU8HRhGMYwSUdtFp6djzOX4K/BufwJH8LZvCWjP4YhfzI9IawtzYK5cyblttnlA72L5C53Enqa7TXfDvh/xTolz4a8TWNvqOm3kZhuLS6iSaCWM8FHjcFWU9wQRWxRSliajd3J73369/UccJSiuWMVa1tui2XouxiWPhnw3pfh2Lwfpun21vpMFuLSOyiiRLZLdV2CFYgAgjCfKEA244xivJPCf7L37N3gPxInjHwX4C8P6VqsTb4ru1063ilibBBMTqgMZIJB2YzXu1FXTx1aClGE2lLfV6+vcirl+Hm4ynBNx2ulp6dvkFFFFcp1hRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABRRRQAUUUUAFFFFABX5/1+gFfn/WlMzqH/9f+7j4W/wDIiWP/AG1/9GvXoFef/C3/AJESx/7a/wDo169ApvcS2CiiikMKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACvz/AK/QCvz/AK0pmdQ//9D+7j4W/wDIiWP/AG1/9GvXoFef/C3/AJESx/7a/wDo169ApvcS2CiiikMKKKKAPyG/4K1f8FHPiB/wTt8L+CPEfgPw9p/iA+Jr27t7mO/eVNiWyROPLMTDDNvIywIHHFfp98L/AIjeF/i/8N9B+Kvgmb7RpHiPT7fUrOTuYbmNZUyOzANhh1ByDyK/DX/gtz4E8OfFL4w/ss/DPxhD9o0nxF49TTL2LON9vdzWUMq57ZRiM13f/BFHx94o8A+FviF/wT4+KlwZPEvwU12e1tWcFTcaRdyvJBKgYklPM3uOcLHLEOOKAPUf+CtP/BTa9/4J2+DfCi+B9Ksde8U+Kbuby7S+aQRR2Nqg86ZvKZW3GWSJEBIBG887a/T/AOF3iu78efDPw744v4khn1nTLS+kjjzsR7iFJWVc5OAWwM84r+NH/goY037b+p/tN/tn3RNx4Q+EkejeCfCcnWN7o6zaJdzxsCQ3ytO2cDMd1H121+zv7dX7U/xc+AP7DXwb+F37PMiWvjz4sx6L4X0q9dipshc2kSSTxkAkShnjjRsfJvLj5lAIB+5dFfzsfFf/AII5eJfgt8D9Q+N3wE+MHjc/GTw3ZNq51W61NnttSubZfOmheDZvCTbWWNXkcfMBL5ilsxfGv/gqp8Wdf/4JEeEP2jfhxDHpvxJ+ImpR+EY3tlBS11ESXEdzcwI5bb5kdszQglvLaVM7tvIB/RHeTNbWktwoyY0ZgD7DNfn/AP8ABMf9sPxj+3N+y7b/AB48daVZaNfzaneWJtrAyGEJbFQrfvWZsndzzivztuv+CNvxB+D3won+OHw1+NHjKf446TYtqT6hc6h5+mX17HH5ktrLBJE00ltKwZB5kjk7tzq4+SuP/wCCTXx3t/2Y/wDgir4n+Pk9qt83ha71u9htmYqs9wpjWCJmHKq8rIrMASASQD0oA/pLrzL41+Ob74X/AAb8W/EvTIUubnw7ot/qcUMuQkj2lu8yo23B2sUwcc4r+U/4OfDb9lL9q/4eRftHftxftZz6X8TfFIfUIrHTPElpY2+grK26G2W1mDsjRrw8amNUBKAbh5h+zf2Ff2q/iB8cP2FP2kPgd8UPFUPjvVPhRYa3pdt4lilE39q6bNZ3i2ly0mW8wMbeQpKWLPGV3EsCzAH61fsAftJ+JP2vv2RPB/7Rfi7T7bStR8SJeNNa2ZcwRm2vZ7UbDIWb5lhDHJPJNeu/tE/Hv4ffsv8AwV8Q/Hn4pTPDofhy28+48pQ0sjO6xRQxKSAZJZXSNASBuYZIGTXwl/wRH/5Re/Cz/rlqv/p3va/Rb4ofCn4b/GvwVdfDn4s6La+INCvmja4sb2MSwSGF1kjLIeDtdVYehANAH4b2v/BRH/gq7r/wvP7Vnhj9nnSJPhm1o2pw2Uupt/bk+ngeYt0gDg7DH8wUWhdlw6KyEE/sR+y1+0f4C/a2+Avh39oP4aiaPSfEMDyLDcALNBLDI0M8MgUkbo5UZcgkNjcCQQa+QP8Ago/+2R4Q/Ys+AVv8MfhzYrqPj7xdbf2D4O8OWcfmSNJIoto5fIT5vIg3KFUf6x9sa9SV9J/4Jl/ss67+xz+xh4Q+CnjCRZNdhjmv9UCEMkd3eytO8KkEhhCGEW4HDFCw4NAH178TfiN4R+D/AMO9c+Knj66+xaJ4dsZ9Rvp8FikFuhkchRyzYGFUcscAcmvxJ8Ef8FA/+Cov7U+it8Yf2P8A4EaOnw+lml/s648UaisF9qcETFd0KLcQLEzEfeIkiByokfBNfsF+0l8FNK/aO+Afi/4E6zdPY2/irS7nTjcou5oGmQhJQpIDbHw23IzjGRmvwr+DX7QP/BR//gmJ8NtO+A37QPwUuPiZ4G8Kxm007xP4PlM0qWEZJQzW6xyMQg+UGVLYhQNxYjcwB+k37A3/AAUAt/2wpPFPw28f+FrrwF8S/AU62/iDQLpvMWPezqk1vLhS8bFDkFQVJGCysjt+jdfBn7Ef7Wf7IP7adhrHxl/Z3tre28Q5it9fiubKK01mFio8pLwpuMqEJhHWSSMlCqtuRgPjj/gh74l8R+Jvhr8Z7jxJqFzqEkHxO1iGJrmV5Skaw2xCKXJIUEnAHHNAH7dV+dn7E37ZnjH9qL4x/HL4b+JtIstNtfhV4rl8P2MtqZDJcwxzXMXmTb2IDkQA4UAcmvlP9n/xN4kvP+C63x38MXeoXMum2ng3SXgtHldoImaDSyWSMnYpJZiSAM5PrX5l/spfsleO/wBsz9u/9qT4dap451vwh8N9I8eahe6za6BOLS61O+m1C+jtImnKP+4jjSdpFORlk+XcQ6AH9edFfzdeCfCvxP8A+CTn/BQf4Z/AXQvG2s+Lfg78aPtGnW1hr1x9quNO1KEoqtEwVEX95NAMoqB0kYOpaNHrl/ip8KPix+1H/wAFsfiN+z1pXxC1/wAHeEG8I6fe62NFuTDcy2kUdhi3tpG3C3aW4kjaR1Ulow6EEMaAP6baK/lD1T9mn41/s+f8FGtK/wCCa3wS+MHizTPhp8U9ATXb6Sa8E2pWFvavevNDY3BUCCWZrQoZY0UmOUCQSbBn2Cb4G6//AMEwv+ClnwT8MfBvx34k1vwZ8ZJ9R0/VtH128+2L51usY83cFjUkPcRujlPMUq4LsrlaAP2H07xh+2/J+3DqHg3UvCujJ8DE0dJbTXFnH9ovqGxC0bR+eW/1pkXb9nCeWFfzdx2H7Vr8RfCfiXxHL/wXy8T+FpNQuW0yP4YxzJZmVzAsn2m0+cRZ2BuTzjPJ9a/NjUvEnwb/AGtf2+vjH8Nf+Ckvxf1/4djwrrb6b4S8PpqI0bSjYRSTCKdp5IzAZWj8mZWcxtJ5gYNIvyoAf1w0V+dP7CfwO+M37M/wg8TeGNT+Ii/FrwwLiW88FTzSNPex2RRilrPe72jlUsECeWoVDvx8pVE/nt/ZD0L9m/8Ab407XvFf7dP7QXiXwx8ap9TuoE0q51VNFt9NZW2wfYre4RY3YEFWhjdSuCnlqRvYA/qx/ac1r4+eHfgP4l1r9l7SLLXvHtvbBtHsNRkEdtNKZEDhmMkS5WIuyBpEVnCqzAEkbPwB1X4ya78F/DWsftCaZZ6N42uLCJ9ZsbB/MtoLsj50jYPIMDuBI4ByA7ABj+YPx/8ABv7QnwH/AOCOXjvwj8Z/HK+L/FWieH7hIfENmZopprfzE8gyTO7SSTKh2tNkFwAWy25m+dPjd+1v8a/gt/wSz/Z28A/Ay6I+Ivxh0zQPDen6lcSMZLZruziWW5V8MxmLyRorkEqZDIMsoBAP6J6K/nY+K/8AwRy8S/Bb4H6h8bvgJ8YPG5+MnhuybVzqt1qbPbalc2y+dNC8GzeEm2ssavI4+YCXzFLZ5D9rr9sfxh+1L/wQab9pOOV9D8R31xp1rqJ0+R4At3a6tHbTtEVbcsc2zzFXcdquFJOMkA/pWor+b3xh/wAEsPiD46/ZPk/ab8c/GXxtJ8ZY/Dp1+G5g1L7PplpcLa/aFsbe2iRWigVQIi8cqncPMAA/d1+on/BLn9oLxj+1B+wj4A+MfxEuDd69e21xa39wVVTPNYXU1oZmCgLulEQdsADLHgdKAPv6iiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAr8/6/QCvz/rSmZ1D//R/u4+Fv8AyIlj/wBtf/Rr16BXn/wt/wCREsf+2v8A6NevQKb3EtgooopDCiiigD8LP+Cuik/tQfse4Gf+LmWn/pVYV8p/8Fmp/ij+wt+0to37fvwCTyZfH/h7UPA+tsvygXj2zfYbgkDJlCokkY6E2Sg4BNf0/wBFAH80H7T/AOy0n7IH/BvTrfwjvoBDrbwaJqet8AMdSvtZsJZ1Yjr5IKwA91iWvdP+Cgn7PXxe+Jv7EvwO+P3wCsP7Y8WfBk6J4pg01QzS3dvb2sMkqQqg3PKrxROI1+Z1VwuX2Kf3rooA/nn+MH/BdT4A/Ez9n6+8Dfs66Vrur/FzxVYyaVYeGP7Pn8601C6QxN5siqEkEBLNiJmZyoGEBLL5h8av+CZfx08Cf8EcfBHwk8Gwf2h8SvhvrKeNZbKy/evLctJcPNaw7R+8kgiuBgJkyPDhCdyg/wBK8WkaVBevqcFrElzJw8qoodvqwGT+JrQoA/nzuP8Agup8Kfi/8GW+H/wY8La/f/G7X7RtLtPCqWT/AOj6tKnlOz3BIT7PBIWcsSr7E+dY+SvlX/BLf4C3f7Tv/BD/AMW/AXTZ47W98S3Wt21nLNkRLdK0cluZCASE85E3kAkLkgE8V/SpDpunW93JfwW8aTzACSRUAdgOm5gMn8au0AfyH/s3ftFf8Evf2d/hPB8BP+ChXwT03w18U/A8TabqP2vw1DfSaqbYlI7mOdYjveZRkvIwjcjesjKwNfo/+zPrHhvx/wDsBfHD4veEvgVpvwS0rXdD1mPTFtII7W61jToLG5a2urmCOCLYFEpEZ3urkyMmEKl/3CutK0u+uIru9toppYDmN3RWZD6qSCR+FX6APyp/4Ij/APKL34Wf9ctV/wDTve19V/tr/tVeG/2Lf2bPEf7Q3iawl1RNGjjS3soSFNxdXMiwwRs5yEQyON74JVMkKxwp+q6KAP4vv2HP+Ch/7F+jfGbWP25v27/EOp+JPjFrMksWn28GmSy6f4fsQWRIbIFiocxkqGGSiMRku8rv/VH+yZ+138Gv21PhlP8AFz4GXF1c6NbahLprtdwNbyC4hjjkcbG5I2ypg/X0r6eooA8E/ahPx2j/AGf/ABVc/syvAvjy3smn0ZbmOOSKa4hZZPIKylY8zIrRKzMArMGJGK/Hr4Of8F6/gD4W+HFv4W/bR0/XfBnxN0OIWutac+lS4uLuEBZJYFX/AFayMCdkvl7GyoyoDH+gCqF3pWl39xDd31tFNLbNuheRFZo2PdCRlT7igD8Av+CVfhf4kfGz9tf4yf8ABRBfCN34C8AePrWGw0bTr1FhlvpImgD3jRL3/wBHZ3cfI0s7hWcqzV8zfsxftq+D/wDgkn8b/jV+zV+1n4e1ywsdc8XX3iTw7qdnai5S/t7shEC/OgO+JImUqWAcyJJ5brg/1S1DLb285Rp0VzG25dwB2t6jPQ+9AH80X/BM74o+OvjZ/wAFiPjd8WviD4bu/CN3r/hGxu7bSb8r9qgsG/s1bEzKvCSS2qxSvH1RnKnkE186/snftt6f+wz+3j+0/wCMfjDoupy/DPxN4+1GxvNdsIGuo9M1O21C9e3WeNPmVLiKaQbgCxaNQqthtv8AXbUNxb295A9rdxrLFICro4DKwPUEHgg0AfzTaX8Yp/8Agrp/wUj+Ffj/AOBei6hH8JfgbNcapda/fwNbpdahL5ciRRK2QSZILcKjESBBK5AAUH6E+CX/ACsD/GP/ALJzY/8AoWk1+6VnZWenWyWWnwpBDGMLHGoVVHoAMAVZoA/B342A/wDEQf8AB5scf8K4vP8A0PWKu/8ABTME/wDBSH9jLH/Qe1v/ANx1furRQB+FXg//AJWEPFX/AGS2P/0qs68E+O37eP7Enin4seNPgx/wVk+DNv4b1vw7dS2+hXz2EupNf6byEktr6KGK4TzCN6lCsZDrkqytX9KFUL7StL1Ty/7TtorjymDp5qK+1h0K7gcH3FAH86f/AARR8LePvCun/HX4lfAfQNXtfhJq12tx8PNF8QzPAbuaJbgkxyv5vlxv+5ieYCTPGWkeJq+fPiJ+3Z/wSz/aE8Ka5a/8FGPg5L4T+LdnNPaahptnpkw1SR1ciDyb+IW8hfYV4uHRd2cBkIz/AFfVnzaTpdxfR6ncW0T3MIIjlZFLoD12sRkfgaAP5d/gZ4A+Onw7/wCDf/4q6X8bItQs4buDULvw7ZapuFza6NILYQIysAUV5RNKilR8rhh8rAD0X48/s9fF74m/8Esf2Y/j98ArD+2PFnwZ07w74pg01QzS3dvb2cEkqQqg3PKrxROI1+Z1VwuX2Kf6U6KAP55/jB/wXU+APxM/Z+vvA37Oula7q/xc8VWMmlWHhj+z5/OtNQukMTebIqhJBASzYiZmcqBhASy+H/ta/su+Jf2Pf+Dfh/gl45aNtftrvT73UxCwdI7m91eOdogw4byVdYiwJDFSQcEV/TxFpGlQXr6nBaxJcycPKqKHb6sBk/ia0KAPmXXP+TNrz/sTJP8A03Gvhv8A4IQ/8owfh/8A9fGs/wDp1uq/X6igAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P+v0Ar8/60pmdQ//0v7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P8Ar9AK/P8ArSmZ1D//0/7uPhb/AMiJY/8AbX/0a9egV5/8Lf8AkRLH/tr/AOjXr0Cm9xLYKKKKQwooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAKKKKACiiigAooooAK/P8Ar9AK/P8ArSmZ1D//2Q=="}}},{"cell_type":"markdown","source":"# 5. Conclusion\n\nOur first model was simple with no hyperparameter tuning. The second model incorporated much more tuning and a few extra layers. Both models trained for 10 epochs and performed resonably well given that they both are fairly simple. As expected, the second model did better than the first. We can see that hyperparameter tuning does indeed contribute to the model performance and can improve the model if done correctly. \n\nSome ways to make the models better could be a variety of factors. First, I would suggest to train the model with augmented images. In the preprocessing step, we only normalized the images. Instead, you could normalize, flip, zoom  in/out, stretch, rotate, etc. with the images so that the model learns more instances of how images can be shaped. However, this was not done in this notebook due to time and memory constraints. In addition to image augmentation, using more epochs could allow the model to learn better. However, it is important that we don't overfit the data by training it too long. Since this project is for demonstration purposes, we did not use more epochs either. Some other ideas to make a stronger model would be to (1) transfer learning where part of the model is taken from another well-trained model, (2) tune hyperparameters in different ways such as strides, filter size, activation functions, learning rate, etc, and (3) have more complex model with more layers. It is hard to say which modification to the notebook and/or model would return in much better results without actually doing it and running the models however, we are confident that these are good steps to try in another notebook.","metadata":{}}]}