Full Code of 0809zheng/CS231n-assignment2019 for AI

Repository: 0809zheng/CS231n-assignment2019
Branch: master
Commit: 3f5c85398663
Files: 83
Total size: 13.3 MB

Directory structure:
gitextract_bcs05ngm/

├── README.md
├── assignment1/
│   ├── README.md
│   ├── collectSubmission.sh
│   ├── cs231n/
│   │   ├── classifiers/
│   │   │   ├── __init__.py
│   │   │   ├── k_nearest_neighbor.py
│   │   │   ├── linear_classifier.py
│   │   │   ├── linear_svm.py
│   │   │   ├── neural_net.py
│   │   │   └── softmax.py
│   │   ├── data_utils.py
│   │   ├── datasets/
│   │   │   └── get_datasets.sh
│   │   ├── features.py
│   │   ├── gradient_check.py
│   │   └── vis_utils.py
│   ├── features.ipynb
│   ├── frameworkpython
│   ├── knn.ipynb
│   ├── requirements.txt
│   ├── softmax.ipynb
│   ├── start_ipython_osx.sh
│   ├── svm.ipynb
│   └── two_layer_net.ipynb
├── assignment2/
│   ├── BatchNormalization.ipynb
│   ├── ConvolutionalNetworks.ipynb
│   ├── Dropout.ipynb
│   ├── FullyConnectedNets.ipynb
│   ├── PyTorch.ipynb
│   ├── TensorFlow.ipynb
│   ├── collectSubmission.sh
│   ├── cs231n/
│   │   ├── classifiers/
│   │   │   ├── cnn.py
│   │   │   └── fc_net.py
│   │   ├── data_utils.py
│   │   ├── datasets/
│   │   │   └── get_datasets.sh
│   │   ├── fast_layers.py
│   │   ├── gradient_check.py
│   │   ├── im2col.py
│   │   ├── im2col_cython.c
│   │   ├── im2col_cython.cp37-win_amd64.pyd
│   │   ├── im2col_cython.pyx
│   │   ├── layer_utils.py
│   │   ├── layers.py
│   │   ├── optim.py
│   │   ├── setup.py
│   │   ├── solver.py
│   │   └── vis_utils.py
│   ├── frameworkpython
│   ├── requirements.txt
│   └── start_ipython_osx.sh
└── assignment3/
    ├── Generative_Adversarial_Networks_PyTorch.ipynb
    ├── Generative_Adversarial_Networks_TF.ipynb
    ├── LSTM_Captioning.ipynb
    ├── NetworkVisualization-PyTorch.ipynb
    ├── NetworkVisualization-TensorFlow.ipynb
    ├── RNN_Captioning.ipynb
    ├── StyleTransfer-PyTorch.ipynb
    ├── StyleTransfer-TensorFlow.ipynb
    ├── collectSubmission_pytorch.sh
    ├── collectSubmission_tensorflow.sh
    ├── cs231n/
    │   ├── captioning_solver.py
    │   ├── classifiers/
    │   │   ├── rnn.py
    │   │   └── squeezenet.py
    │   ├── coco_utils.py
    │   ├── data_utils.py
    │   ├── datasets/
    │   │   ├── get_assignment3_data.sh
    │   │   ├── get_coco_captioning.sh
    │   │   ├── get_imagenet_val.sh
    │   │   └── get_squeezenet_tf.sh
    │   ├── fast_layers.py
    │   ├── gradient_check.py
    │   ├── im2col.py
    │   ├── im2col_cython.pyx
    │   ├── image_utils.py
    │   ├── layer_utils.py
    │   ├── layers.py
    │   ├── optim.py
    │   ├── rnn_layers.py
    │   └── setup.py
    ├── frameworkpython
    ├── gan-checks-tf.npz
    ├── requirements.txt
    ├── start_ipython_osx.sh
    ├── style-transfer-checks-tf.npz
    └── style-transfer-checks.npz

================================================
FILE CONTENTS
================================================

================================================
FILE: README.md
================================================
# CS231n-assignment2019
CS231n 2019春季学期课程作业。
课程网站：http://cs231n.stanford.edu/syllabus.html


================================================
FILE: assignment1/README.md
================================================
Details about this assignment can be found [on the course webpage](http://cs231n.github.io/), under Assignment #1 of Spring 2019.


================================================
FILE: assignment1/collectSubmission.sh
================================================
#!/bin/bash
#NOTE: DO NOT EDIT THIS FILE-- MAY RESULT IN INCOMPLETE SUBMISSIONS

NOTEBOOKS="knn.ipynb 
svm.ipynb 
softmax.ipynb 
two_layer_net.ipynb 
features.ipynb"

CODE="cs231n/classifiers/k_nearest_neighbor.py
cs231n/classifiers/linear_classifier.py
cs231n/classifiers/linear_svm.py
cs231n/classifiers/softmax.py
cs231n/classifiers/neural_net.py"

LOCAL_DIR=`pwd`
REMOTE_DIR="cs231n-2019-assignment1"
ASSIGNMENT_NO=1
ZIP_FILENAME="a1.zip"

C_R="\e[31m"
C_G="\e[32m"
C_BLD="\e[1m"
C_E="\e[0m"

FILES=""
for FILE in "${NOTEBOOKS} ${CODE}"
do
	if [ ! -f ${F} ]; then
		echo -e "${C_R}Required file ${FILE} not found, Exiting.${C_E}"
		exit 0
	fi
	FILES="${FILES} ${LOCAL_DIR}/${FILE}"
done

echo -e "${C_BLD}### Zipping file ###${C_E}"
rm -f ${ZIP_FILENAME}
zip -r ${ZIP_FILENAME} . -x "*.git*" "*cs231n/datasets*" "*.ipynb_checkpoints*" "*README.md" "collectSubmission.sh" "*requirements.txt" "*__pycache__*" ".env/*" > assignment_zip.log
echo ""

echo -e "${C_BLD}### Submitting to myth ###${C_E}"
echo "Type in your Stanford student ID (alphanumeric, *not* the 8-digit ID):"
read -p "Student ID: " SUID
echo ""

echo -e "${C_BLD}### Copying to ${SUID}@myth.stanford.edu:${REMOTE_DIR} ###${C_E}"
echo -e "${C_G}Note: if myth is under heavy use, this may hang: If this happens, rerun the script.${C_E}"
FILES="${FILES} ${LOCAL_DIR}/${ZIP_FILENAME}"
rsync -avP ${FILES} ${SUID}@myth.stanford.edu:${REMOTE_DIR}
echo ""

echo -e "${C_BLD}### Running remote submission script from ${SUID}@myth.stanford.edu:${REMOTE_DIR} ###${C_E}"
ssh ${SUID}@myth.stanford.edu "cd ${REMOTE_DIR} && /afs/ir/class/cs231n/grading/submit ${ASSIGNMENT_NO} ${SUID} ${ZIP_FILENAME} && exit"

================================================
FILE: assignment1/cs231n/classifiers/__init__.py
================================================
from cs231n.classifiers.k_nearest_neighbor import *
from cs231n.classifiers.linear_classifier import *


================================================
FILE: assignment1/cs231n/classifiers/k_nearest_neighbor.py
================================================
from builtins import range
from builtins import object
import numpy as np
from past.builtins import xrange


class KNearestNeighbor(object):
    """ a kNN classifier with L2 distance """

    def __init__(self):
        pass

    def train(self, X, y):
        """
        Train the classifier. For k-nearest neighbors this is just
        memorizing the training data.

        Inputs:
        - X: A numpy array of shape (num_train, D) containing the training data
          consisting of num_train samples each of dimension D.
        - y: A numpy array of shape (N,) containing the training labels, where
             y[i] is the label for X[i].
        """
        self.X_train = X
        self.y_train = y

    def predict(self, X, k=1, num_loops=0):
        """
        Predict labels for test data using this classifier.

        Inputs:
        - X: A numpy array of shape (num_test, D) containing test data consisting
             of num_test samples each of dimension D.
        - k: The number of nearest neighbors that vote for the predicted labels.
        - num_loops: Determines which implementation to use to compute distances
          between training points and testing points.

        Returns:
        - y: A numpy array of shape (num_test,) containing predicted labels for the
          test data, where y[i] is the predicted label for the test point X[i].
        """
        if num_loops == 0:
            dists = self.compute_distances_no_loops(X)
        elif num_loops == 1:
            dists = self.compute_distances_one_loop(X)
        elif num_loops == 2:
            dists = self.compute_distances_two_loops(X)
        else:
            raise ValueError('Invalid value %d for num_loops' % num_loops)

        return self.predict_labels(dists, k=k)

    def compute_distances_two_loops(self, X):
        """
        Compute the distance between each test point in X and each training point
        in self.X_train using a nested loop over both the training data and the
        test data.

        Inputs:
        - X: A numpy array of shape (num_test, D) containing test data.

        Returns:
        - dists: A numpy array of shape (num_test, num_train) where dists[i, j]
          is the Euclidean distance between the ith test point and the jth training
          point.
        """
        num_test = X.shape[0]
        num_train = self.X_train.shape[0]
        dists = np.zeros((num_test, num_train))
        for i in range(num_test):
            for j in range(num_train):
                #####################################################################
                # TODO:                                                             #
                # Compute the l2 distance between the ith test point and the jth    #
                # training point, and store the result in dists[i, j]. You should   #
                # not use a loop over dimension, nor use np.linalg.norm().          #
                #####################################################################
                # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
                
                dists[i, j] = np.sqrt(np.sum(np.square((X[i] - self.X_train[j]))))
                
                # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
        return dists

    def compute_distances_one_loop(self, X):
        """
        Compute the distance between each test point in X and each training point
        in self.X_train using a single loop over the test data.

        Input / Output: Same as compute_distances_two_loops
        """
        num_test = X.shape[0]
        num_train = self.X_train.shape[0]
        dists = np.zeros((num_test, num_train))
        for i in range(num_test):
            #######################################################################
            # TODO:                                                               #
            # Compute the l2 distance between the ith test point and all training #
            # points, and store the result in dists[i, :].                        #
            # Do not use np.linalg.norm().                                        #
            #######################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            dists[i, :] = np.sqrt(np.sum(np.square((X[i]-self.X_train)), axis = 1))

            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
        return dists

    def compute_distances_no_loops(self, X):
        """
        Compute the distance between each test point in X and each training point
        in self.X_train using no explicit loops.

        Input / Output: Same as compute_distances_two_loops
        """
        num_test = X.shape[0]
        num_train = self.X_train.shape[0]
        dists = np.zeros((num_test, num_train))
        #########################################################################
        # TODO:                                                                 #
        # Compute the l2 distance between all test points and all training      #
        # points without using any explicit loops, and store the result in      #
        # dists.                                                                #
        #                                                                       #
        # You should implement this function using only basic array operations; #
        # in particular you should not use functions from scipy,                #
        # nor use np.linalg.norm().                                             #
        #                                                                       #
        # HINT: Try to formulate the l2 distance using matrix multiplication    #
        #       and two broadcast sums.                                         #
        #########################################################################
        # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        num_test = X.shape[0]
        num_train = self.X_train.shape[0]
        dists = np.zeros((num_test, num_train)) 
        dists = np.sqrt(
                np.sum(X**2, axis = 1, keepdims = True)
                + np.sum(self.X_train**2, axis = 1, keepdims = True).T
                - 2*np.dot(X, self.X_train.T)
                )
        

        # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
        return dists

    def predict_labels(self, dists, k=1):
        """
        Given a matrix of distances between test points and training points,
        predict a label for each test point.

        Inputs:
        - dists: A numpy array of shape (num_test, num_train) where dists[i, j]
          gives the distance betwen the ith test point and the jth training point.

        Returns:
        - y: A numpy array of shape (num_test,) containing predicted labels for the
          test data, where y[i] is the predicted label for the test point X[i].
        """
        num_test = dists.shape[0]
        y_pred = np.zeros(num_test)
        for i in range(num_test):
            # A list of length k storing the labels of the k nearest neighbors to
            # the ith test point.
            closest_y = []
            #########################################################################
            # TODO:                                                                 #
            # Use the distance matrix to find the k nearest neighbors of the ith    #
            # testing point, and use self.y_train to find the labels of these       #
            # neighbors. Store these labels in closest_y.                           #
            # Hint: Look up the function numpy.argsort.                             #
            #########################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
            
            max_index = np.argsort(dists[i])
            for j in range(k):
                index = max_index[j]
                closest_y.append(self.y_train[index])
                
            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
            #########################################################################
            # TODO:                                                                 #
            # Now that you have found the labels of the k nearest neighbors, you    #
            # need to find the most common label in the list closest_y of labels.   #
            # Store this label in y_pred[i]. Break ties by choosing the smaller     #
            # label.                                                                #
            #########################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
            
            maxdir = {}
            sy = set(closest_y)
            for s in sy:
                count = closest_y.count(s)
                maxdir[s] = count 
            y_pred[i] = int(max(maxdir, key = maxdir.get)) 
            
            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        return y_pred

================================================
FILE: assignment1/cs231n/classifiers/linear_classifier.py
================================================
from __future__ import print_function

from builtins import range
from builtins import object
import numpy as np
from cs231n.classifiers.linear_svm import *
from cs231n.classifiers.softmax import *
from past.builtins import xrange


class LinearClassifier(object):

    def __init__(self):
        self.W = None

    def train(self, X, y, learning_rate=1e-3, reg=1e-5, num_iters=100,
              batch_size=200, verbose=False):
        """
        Train this linear classifier using stochastic gradient descent.

        Inputs:
        - X: A numpy array of shape (N, D) containing training data; there are N
          training samples each of dimension D.
        - y: A numpy array of shape (N,) containing training labels; y[i] = c
          means that X[i] has label 0 <= c < C for C classes.
        - learning_rate: (float) learning rate for optimization.
        - reg: (float) regularization strength.
        - num_iters: (integer) number of steps to take when optimizing
        - batch_size: (integer) number of training examples to use at each step.
        - verbose: (boolean) If true, print progress during optimization.

        Outputs:
        A list containing the value of the loss function at each training iteration.
        """
        num_train, dim = X.shape
        num_classes = np.max(y) + 1 # assume y takes values 0...K-1 where K is number of classes
        if self.W is None:
            # lazily initialize W
            self.W = 0.001 * np.random.randn(dim, num_classes)

        # Run stochastic gradient descent to optimize W
        loss_history = []
        for it in range(num_iters):
            X_batch = None
            y_batch = None

            #########################################################################
            # TODO:                                                                 #
            # Sample batch_size elements from the training data and their           #
            # corresponding labels to use in this round of gradient descent.        #
            # Store the data in X_batch and their corresponding labels in           #
            # y_batch; after sampling X_batch should have shape (batch_size, dim)   #
            # and y_batch should have shape (batch_size,)                           #
            #                                                                       #
            # Hint: Use np.random.choice to generate indices. Sampling with         #
            # replacement is faster than sampling without replacement.              #
            #########################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            indices = np.random.choice(num_train,batch_size,replace = False)
            X_batch = X[indices]
            y_batch = y[indices]

            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            # evaluate loss and gradient
            loss, grad = self.loss(X_batch, y_batch, reg)
            loss_history.append(loss)

            # perform parameter update
            #########################################################################
            # TODO:                                                                 #
            # Update the weights using the gradient and the learning rate.          #
            #########################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            loss, grad = self.loss(X_batch, y_batch, reg)
            loss_history.append(loss)
            self.W -= learning_rate*grad  

            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            if verbose and it % 100 == 0:
                print('iteration %d / %d: loss %f' % (it, num_iters, loss))

        return loss_history

    def predict(self, X):
        """
        Use the trained weights of this linear classifier to predict labels for
        data points.

        Inputs:
        - X: A numpy array of shape (N, D) containing training data; there are N
          training samples each of dimension D.

        Returns:
        - y_pred: Predicted labels for the data in X. y_pred is a 1-dimensional
          array of length N, and each element is an integer giving the predicted
          class.
        """
        y_pred = np.zeros(X.shape[0])
        ###########################################################################
        # TODO:                                                                   #
        # Implement this method. Store the predicted labels in y_pred.            #
        ###########################################################################
        # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        scores = X.dot(self.W)
        y_pred = np.argsort(scores,axis = 1)[:,-1]

        # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
        return y_pred

    def loss(self, X_batch, y_batch, reg):
        """
        Compute the loss function and its derivative.
        Subclasses will override this.

        Inputs:
        - X_batch: A numpy array of shape (N, D) containing a minibatch of N
          data points; each point has dimension D.
        - y_batch: A numpy array of shape (N,) containing labels for the minibatch.
        - reg: (float) regularization strength.

        Returns: A tuple containing:
        - loss as a single float
        - gradient with respect to self.W; an array of the same shape as W
        """
        pass


class LinearSVM(LinearClassifier):
    """ A subclass that uses the Multiclass SVM loss function """

    def loss(self, X_batch, y_batch, reg):
        return svm_loss_vectorized(self.W, X_batch, y_batch, reg)


class Softmax(LinearClassifier):
    """ A subclass that uses the Softmax + Cross-entropy loss function """

    def loss(self, X_batch, y_batch, reg):
        return softmax_loss_vectorized(self.W, X_batch, y_batch, reg)


================================================
FILE: assignment1/cs231n/classifiers/linear_svm.py
================================================
from builtins import range
import numpy as np
from random import shuffle
from past.builtins import xrange

def svm_loss_naive(W, X, y, reg):
    """
    Structured SVM loss function, naive implementation (with loops).

    Inputs have dimension D, there are C classes, and we operate on minibatches
    of N examples.

    Inputs:
    - W: A numpy array of shape (D, C) containing weights.
    - X: A numpy array of shape (N, D) containing a minibatch of data.
    - y: A numpy array of shape (N,) containing training labels; y[i] = c means
      that X[i] has label c, where 0 <= c < C.
    - reg: (float) regularization strength

    Returns a tuple of:
    - loss as single float
    - gradient with respect to weights W; an array of same shape as W
    """
    dW = np.zeros(W.shape) # initialize the gradient as zero

    # compute the loss and the gradient
    num_classes = W.shape[1]
    num_train = X.shape[0]
    loss = 0.0
    for i in range(num_train):
        scores = X[i].dot(W)
        correct_class_score = scores[y[i]]
        for j in range(num_classes):
            if j == y[i]:
                continue
            margin = scores[j] - correct_class_score + 1 # note delta = 1
            if margin > 0:
                loss += margin

    # Right now the loss is a sum over all training examples, but we want it
    # to be an average instead so we divide by num_train.
    loss /= num_train

    # Add regularization to the loss.
    loss += reg * np.sum(W * W)

    #############################################################################
    # TODO:                                                                     #
    # Compute the gradient of the loss function and store it dW.                #
    # Rather that first computing the loss and then computing the derivative,   #
    # it may be simpler to compute the derivative at the same time that the     #
    # loss is being computed. As a result you may need to modify some of the    #
    # code above to compute the gradient.                                       #
    #############################################################################
    # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    for i in range(num_train):
        scores = X[i].dot(W)
        index = y[i]
        for j in range(num_classes):
            if j != index and scores[j] >= scores[index]-1:
                dW[:,j] += X[i]
                dW[:,index] -= X[i]
 
    dW /= num_train
    dW += 2*reg*W

    # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
    
    return loss, dW



def svm_loss_vectorized(W, X, y, reg):
    """
    Structured SVM loss function, vectorized implementation.

    Inputs and outputs are the same as svm_loss_naive.
    """
    loss = 0.0
    dW = np.zeros(W.shape) # initialize the gradient as zero

    #############################################################################
    # TODO:                                                                     #
    # Implement a vectorized version of the structured SVM loss, storing the    #
    # result in loss.                                                           #
    #############################################################################
    # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    num_train = X.shape[0]
    scores = X.dot(W)
    rightscore = scores[np.arange(num_train), y]
    scores = scores - rightscore.reshape(-1, 1) + 1.
    scores[scores <= 0] = 0
    scores[np.arange(num_train), y] = 0
    loss = np.sum(scores)/num_train

    # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    #############################################################################
    # TODO:                                                                     #
    # Implement a vectorized version of the gradient for the structured SVM     #
    # loss, storing the result in dW.                                           #
    #                                                                           #
    # Hint: Instead of computing the gradient from scratch, it may be easier    #
    # to reuse some of the intermediate values that you used to compute the     #
    # loss.                                                                     #
    #############################################################################
    # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    C = W.shape[1]
    mask = np.zeros((num_train, C))
    scores[scores > 0] = 1
    mask += scores
    mask[np.arange(num_train), y] = -np.sum(scores,axis = 1)
    dW = X.T.dot(mask)/num_train
    dW += 2*reg*W

    # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    return loss, dW


================================================
FILE: assignment1/cs231n/classifiers/neural_net.py
================================================
from __future__ import print_function

from builtins import range
from builtins import object
import numpy as np
import matplotlib.pyplot as plt
from past.builtins import xrange

class TwoLayerNet(object):
    """
    A two-layer fully-connected neural network. The net has an input dimension of
    N, a hidden layer dimension of H, and performs classification over C classes.
    We train the network with a softmax loss function and L2 regularization on the
    weight matrices. The network uses a ReLU nonlinearity after the first fully
    connected layer.

    In other words, the network has the following architecture:

    input - fully connected layer - ReLU - fully connected layer - softmax

    The outputs of the second fully-connected layer are the scores for each class.
    """

    def __init__(self, input_size, hidden_size, output_size, std=1e-4):
        """
        Initialize the model. Weights are initialized to small random values and
        biases are initialized to zero. Weights and biases are stored in the
        variable self.params, which is a dictionary with the following keys:

        W1: First layer weights; has shape (D, H)
        b1: First layer biases; has shape (H,)
        W2: Second layer weights; has shape (H, C)
        b2: Second layer biases; has shape (C,)

        Inputs:
        - input_size: The dimension D of the input data.
        - hidden_size: The number of neurons H in the hidden layer.
        - output_size: The number of classes C.
        """
        self.params = {}
        self.params['W1'] = std * np.random.randn(input_size, hidden_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W2'] = std * np.random.randn(hidden_size, output_size)
        self.params['b2'] = np.zeros(output_size)

    def loss(self, X, y=None, reg=0.0):
        """
        Compute the loss and gradients for a two layer fully connected neural
        network.

        Inputs:
        - X: Input data of shape (N, D). Each X[i] is a training sample.
        - y: Vector of training labels. y[i] is the label for X[i], and each y[i] is
          an integer in the range 0 <= y[i] < C. This parameter is optional; if it
          is not passed then we only return scores, and if it is passed then we
          instead return the loss and gradients.
        - reg: Regularization strength.

        Returns:
        If y is None, return a matrix scores of shape (N, C) where scores[i, c] is
        the score for class c on input X[i].

        If y is not None, instead return a tuple of:
        - loss: Loss (data loss and regularization loss) for this batch of training
          samples.
        - grads: Dictionary mapping parameter names to gradients of those parameters
          with respect to the loss function; has the same keys as self.params.
        """
        # Unpack variables from the params dictionary
        W1, b1 = self.params['W1'], self.params['b1']
        W2, b2 = self.params['W2'], self.params['b2']
        N, D = X.shape

        # Compute the forward pass
        scores = None
        #############################################################################
        # TODO: Perform the forward pass, computing the class scores for the input. #
        # Store the result in the scores variable, which should be an array of      #
        # shape (N, C).                                                             #
        #############################################################################
        # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        z1 = X.dot(W1)+b1
        a1 = np.maximum(0, z1)
        scores = a1.dot(W2)+b2

        # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        # If the targets are not given then jump out, we're done
        if y is None:
            return scores

        # Compute the loss
        loss = None
        #############################################################################
        # TODO: Finish the forward pass, and compute the loss. This should include  #
        # both the data loss and L2 regularization for W1 and W2. Store the result  #
        # in the variable loss, which should be a scalar. Use the Softmax           #
        # classifier loss.                                                          #
        #############################################################################
        # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        exp_scores = np.exp(scores-np.max(scores, axis = 1, keepdims = True))
        final_scores = exp_scores/np.sum(exp_scores, axis=1, keepdims = True)
        loss = np.sum(-np.log(final_scores[np.arange(N),y]))/N
        loss += reg*np.sum(np.square(W1))
        loss += reg*np.sum(np.square(W2))

        # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        # Backward pass: compute gradients
        grads = {}
        #############################################################################
        # TODO: Compute the backward pass, computing the derivatives of the weights #
        # and biases. Store the results in the grads dictionary. For example,       #
        # grads['W1'] should store the gradient on W1, and be a matrix of same size #
        #############################################################################
        # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        dexp_scores = np.ones(exp_scores.shape)/np.sum(exp_scores, axis=1, keepdims = True)
        dexp_scores[np.arange(N), y] -= 1/exp_scores[np.arange(N), y]
        dexp_scores /= N
        dscores = exp_scores*dexp_scores
        db2 = np.sum(dscores,axis=0)
        dW2 = a1.T.dot(dscores)
        da1 = dscores.dot(W2.T)
        dz1 = da1
        dz1[z1 <= 0] = 0 
        db1 = np.sum(dz1, axis=0)
        dW1 = X.T.dot(dz1)
        
        dW1 += 2*reg*W1   
        dW2 += 2*reg*W2
        grads['W1'] = dW1
        grads['b1'] = db1
        grads['W2'] = dW2
        grads['b2'] = db2   

        # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        return loss, grads

    def train(self, X, y, X_val, y_val,
              learning_rate=1e-3, learning_rate_decay=0.95,
              reg=5e-6, num_iters=100,
              batch_size=200, verbose=False):
        """
        Train this neural network using stochastic gradient descent.

        Inputs:
        - X: A numpy array of shape (N, D) giving training data.
        - y: A numpy array f shape (N,) giving training labels; y[i] = c means that
          X[i] has label c, where 0 <= c < C.
        - X_val: A numpy array of shape (N_val, D) giving validation data.
        - y_val: A numpy array of shape (N_val,) giving validation labels.
        - learning_rate: Scalar giving learning rate for optimization.
        - learning_rate_decay: Scalar giving factor used to decay the learning rate
          after each epoch.
        - reg: Scalar giving regularization strength.
        - num_iters: Number of steps to take when optimizing.
        - batch_size: Number of training examples to use per step.
        - verbose: boolean; if true print progress during optimization.
        """
        num_train = X.shape[0]
        iterations_per_epoch = max(num_train / batch_size, 1)

        # Use SGD to optimize the parameters in self.model
        loss_history = []
        train_acc_history = []
        val_acc_history = []

        for it in range(num_iters):
            X_batch = None
            y_batch = None

            #########################################################################
            # TODO: Create a random minibatch of training data and labels, storing  #
            # them in X_batch and y_batch respectively.                             #
            #########################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            incides = np.random.choice(num_train,batch_size,replace = True)
            X_batch = X[incides]
            y_batch = y[incides]

            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            # Compute loss and gradients using the current minibatch
            loss, grads = self.loss(X_batch, y=y_batch, reg=reg)
            loss_history.append(loss)

            #########################################################################
            # TODO: Use the gradients in the grads dictionary to update the         #
            # parameters of the network (stored in the dictionary self.params)      #
            # using stochastic gradient descent. You'll need to use the gradients   #
            # stored in the grads dictionary defined above.                         #
            #########################################################################
            # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            self.params['W1'] -= learning_rate*grads['W1']
            self.params['W2'] -= learning_rate*grads['W2']
            self.params['b1'] -= learning_rate*grads['b1']
            self.params['b2'] -= learning_rate*grads['b2']

            # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

            if verbose and it % 100 == 0:
                print('iteration %d / %d: loss %f' % (it, num_iters, loss))

            # Every epoch, check train and val accuracy and decay learning rate.
            if it % iterations_per_epoch == 0:
                # Check accuracy
                train_acc = (self.predict(X_batch) == y_batch).mean()
                val_acc = (self.predict(X_val) == y_val).mean()
                train_acc_history.append(train_acc)
                val_acc_history.append(val_acc)

                # Decay learning rate
                learning_rate *= learning_rate_decay

        return {
          'loss_history': loss_history,
          'train_acc_history': train_acc_history,
          'val_acc_history': val_acc_history,
        }

    def predict(self, X):
        """
        Use the trained weights of this two-layer network to predict labels for
        data points. For each data point we predict scores for each of the C
        classes, and assign each data point to the class with the highest score.

        Inputs:
        - X: A numpy array of shape (N, D) giving N D-dimensional data points to
          classify.

        Returns:
        - y_pred: A numpy array of shape (N,) giving predicted labels for each of
          the elements of X. For all i, y_pred[i] = c means that X[i] is predicted
          to have class c, where 0 <= c < C.
        """
        y_pred = None

        ###########################################################################
        # TODO: Implement this function; it should be VERY simple!                #
        ###########################################################################
        # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        scores = np.maximum(X.dot(self.params['W1']) + self.params['b1'], 0).dot(self.params['W2']) + self.params['b2']
        y_pred = np.argsort(scores,axis = 1)[:,-1]

        # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

        return y_pred


================================================
FILE: assignment1/cs231n/classifiers/softmax.py
================================================
from builtins import range
import numpy as np
from random import shuffle
from past.builtins import xrange

def softmax_loss_naive(W, X, y, reg):
    """
    Softmax loss function, naive implementation (with loops)

    Inputs have dimension D, there are C classes, and we operate on minibatches
    of N examples.

    Inputs:
    - W: A numpy array of shape (D, C) containing weights.
    - X: A numpy array of shape (N, D) containing a minibatch of data.
    - y: A numpy array of shape (N,) containing training labels; y[i] = c means
      that X[i] has label c, where 0 <= c < C.
    - reg: (float) regularization strength

    Returns a tuple of:
    - loss as single float
    - gradient with respect to weights W; an array of same shape as W
    """
    # Initialize the loss and gradient to zero.
    loss = 0.0
    dW = np.zeros_like(W)

    #############################################################################
    # TODO: Compute the softmax loss and its gradient using explicit loops.     #
    # Store the loss in loss and the gradient in dW. If you are not careful     #
    # here, it is easy to run into numeric instability. Don't forget the        #
    # regularization!                                                           #
    #############################################################################
    # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    num_train, dim = X.shape
    classes = W.shape[1]
    scores = X.dot(W)
    
    sta_scores = scores - np.max(scores, axis = 1, keepdims = True) #Numerical Stability
    exp_scores = np.exp(sta_scores)
    final_scores = exp_scores/np.sum(exp_scores, axis = 1, keepdims = True)
  
    for i in range(num_train):
        loss -= np.log(final_scores[i,y[i]])
  
    loss /= num_train
    loss += reg*np.sum(np.square(W))
  
    for i in range(num_train):
        for d in range(dim):
            for c in range(classes):
                dW[d, c] += (final_scores[i, c]*X[i, d])
                if c == y[i]:
                    dW[d, c] -= X[i, d]
          
    dW /= num_train
    dW += 2*reg*W

    # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    return loss, dW


def softmax_loss_vectorized(W, X, y, reg):
    """
    Softmax loss function, vectorized version.

    Inputs and outputs are the same as softmax_loss_naive.
    """
    # Initialize the loss and gradient to zero.
    loss = 0.0
    dW = np.zeros_like(W)

    #############################################################################
    # TODO: Compute the softmax loss and its gradient using no explicit loops.  #
    # Store the loss in loss and the gradient in dW. If you are not careful     #
    # here, it is easy to run into numeric instability. Don't forget the        #
    # regularization!                                                           #
    #############################################################################
    # *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    num_train, dim = X.shape
    classes = W.shape[1]
    scores = X.dot(W)
    
    sta_scores = scores - np.max(scores, axis = 1, keepdims = True) #Numerical Stability
    exp_scores = np.exp(sta_scores)
    final_scores = exp_scores/np.sum(exp_scores, axis = 1, keepdims = True)
    loss = -np.sum(np.log(final_scores[np.arange(num_train), y]))/num_train
    loss += reg*np.sum(np.square(W))
  
    mask = final_scores.copy()
    mask[np.arange(num_train), y] -= 1
    dW = X.T.dot(mask)/num_train
    dW += 2*reg*W

    # *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****

    return loss, dW


================================================
FILE: assignment1/cs231n/data_utils.py
================================================
from __future__ import print_function

from builtins import range
from six.moves import cPickle as pickle
import numpy as np
import os
from imageio import imread
import platform

def load_pickle(f):
    version = platform.python_version_tuple()
    if version[0] == '2':
        return  pickle.load(f)
    elif version[0] == '3':
        return  pickle.load(f, encoding='latin1')
    raise ValueError("invalid python version: {}".format(version))

def load_CIFAR_batch(filename):
    """ load single batch of cifar """
    with open(filename, 'rb') as f:
        datadict = load_pickle(f)
        X = datadict['data']
        Y = datadict['labels']
        X = X.reshape(10000, 3, 32, 32).transpose(0,2,3,1).astype("float")
        Y = np.array(Y)
        return X, Y

def load_CIFAR10(ROOT):
    """ load all of cifar """
    xs = []
    ys = []
    for b in range(1,6):
        f = os.path.join(ROOT, 'data_batch_%d' % (b, ))
        X, Y = load_CIFAR_batch(f)
        xs.append(X)
        ys.append(Y)
    Xtr = np.concatenate(xs)
    Ytr = np.concatenate(ys)
    del X, Y
    Xte, Yte = load_CIFAR_batch(os.path.join(ROOT, 'test_batch'))
    return Xtr, Ytr, Xte, Yte


def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000,
                     subtract_mean=True):
    """
    Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
    it for classifiers. These are the same steps as we used for the SVM, but
    condensed to a single function.
    """
    # Load the raw CIFAR-10 data
    cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
    X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)

    # Subsample the data
    mask = list(range(num_training, num_training + num_validation))
    X_val = X_train[mask]
    y_val = y_train[mask]
    mask = list(range(num_training))
    X_train = X_train[mask]
    y_train = y_train[mask]
    mask = list(range(num_test))
    X_test = X_test[mask]
    y_test = y_test[mask]

    # Normalize the data: subtract the mean image
    if subtract_mean:
        mean_image = np.mean(X_train, axis=0)
        X_train -= mean_image
        X_val -= mean_image
        X_test -= mean_image

    # Transpose so that channels come first
    X_train = X_train.transpose(0, 3, 1, 2).copy()
    X_val = X_val.transpose(0, 3, 1, 2).copy()
    X_test = X_test.transpose(0, 3, 1, 2).copy()

    # Package data into a dictionary
    return {
      'X_train': X_train, 'y_train': y_train,
      'X_val': X_val, 'y_val': y_val,
      'X_test': X_test, 'y_test': y_test,
    }


def load_tiny_imagenet(path, dtype=np.float32, subtract_mean=True):
    """
    Load TinyImageNet. Each of TinyImageNet-100-A, TinyImageNet-100-B, and
    TinyImageNet-200 have the same directory structure, so this can be used
    to load any of them.

    Inputs:
    - path: String giving path to the directory to load.
    - dtype: numpy datatype used to load the data.
    - subtract_mean: Whether to subtract the mean training image.

    Returns: A dictionary with the following entries:
    - class_names: A list where class_names[i] is a list of strings giving the
      WordNet names for class i in the loaded dataset.
    - X_train: (N_tr, 3, 64, 64) array of training images
    - y_train: (N_tr,) array of training labels
    - X_val: (N_val, 3, 64, 64) array of validation images
    - y_val: (N_val,) array of validation labels
    - X_test: (N_test, 3, 64, 64) array of testing images.
    - y_test: (N_test,) array of test labels; if test labels are not available
      (such as in student code) then y_test will be None.
    - mean_image: (3, 64, 64) array giving mean training image
    """
    # First load wnids
    with open(os.path.join(path, 'wnids.txt'), 'r') as f:
        wnids = [x.strip() for x in f]

    # Map wnids to integer labels
    wnid_to_label = {wnid: i for i, wnid in enumerate(wnids)}

    # Use words.txt to get names for each class
    with open(os.path.join(path, 'words.txt'), 'r') as f:
        wnid_to_words = dict(line.split('\t') for line in f)
        for wnid, words in wnid_to_words.items():
            wnid_to_words[wnid] = [w.strip() for w in words.split(',')]
    class_names = [wnid_to_words[wnid] for wnid in wnids]

    # Next load training data.
    X_train = []
    y_train = []
    for i, wnid in enumerate(wnids):
        if (i + 1) % 20 == 0:
            print('loading training data for synset %d / %d'
                  % (i + 1, len(wnids)))
        # To figure out the filenames we need to open the boxes file
        boxes_file = os.path.join(path, 'train', wnid, '%s_boxes.txt' % wnid)
        with open(boxes_file, 'r') as f:
            filenames = [x.split('\t')[0] for x in f]
        num_images = len(filenames)

        X_train_block = np.zeros((num_images, 3, 64, 64), dtype=dtype)
        y_train_block = wnid_to_label[wnid] * \
                        np.ones(num_images, dtype=np.int64)
        for j, img_file in enumerate(filenames):
            img_file = os.path.join(path, 'train', wnid, 'images', img_file)
            img = imread(img_file)
            if img.ndim == 2:
        ## grayscale file
                img.shape = (64, 64, 1)
            X_train_block[j] = img.transpose(2, 0, 1)
        X_train.append(X_train_block)
        y_train.append(y_train_block)

    # We need to concatenate all training data
    X_train = np.concatenate(X_train, axis=0)
    y_train = np.concatenate(y_train, axis=0)

    # Next load validation data
    with open(os.path.join(path, 'val', 'val_annotations.txt'), 'r') as f:
        img_files = []
        val_wnids = []
        for line in f:
            img_file, wnid = line.split('\t')[:2]
            img_files.append(img_file)
            val_wnids.append(wnid)
        num_val = len(img_files)
        y_val = np.array([wnid_to_label[wnid] for wnid in val_wnids])
        X_val = np.zeros((num_val, 3, 64, 64), dtype=dtype)
        for i, img_file in enumerate(img_files):
            img_file = os.path.join(path, 'val', 'images', img_file)
            img = imread(img_file)
            if img.ndim == 2:
                img.shape = (64, 64, 1)
            X_val[i] = img.transpose(2, 0, 1)

    # Next load test images
    # Students won't have test labels, so we need to iterate over files in the
    # images directory.
    img_files = os.listdir(os.path.join(path, 'test', 'images'))
    X_test = np.zeros((len(img_files), 3, 64, 64), dtype=dtype)
    for i, img_file in enumerate(img_files):
        img_file = os.path.join(path, 'test', 'images', img_file)
        img = imread(img_file)
        if img.ndim == 2:
            img.shape = (64, 64, 1)
        X_test[i] = img.transpose(2, 0, 1)

    y_test = None
    y_test_file = os.path.join(path, 'test', 'test_annotations.txt')
    if os.path.isfile(y_test_file):
        with open(y_test_file, 'r') as f:
            img_file_to_wnid = {}
            for line in f:
                line = line.split('\t')
                img_file_to_wnid[line[0]] = line[1]
        y_test = [wnid_to_label[img_file_to_wnid[img_file]]
                  for img_file in img_files]
        y_test = np.array(y_test)

    mean_image = X_train.mean(axis=0)
    if subtract_mean:
        X_train -= mean_image[None]
        X_val -= mean_image[None]
        X_test -= mean_image[None]

    return {
      'class_names': class_names,
      'X_train': X_train,
      'y_train': y_train,
      'X_val': X_val,
      'y_val': y_val,
      'X_test': X_test,
      'y_test': y_test,
      'class_names': class_names,
      'mean_image': mean_image,
    }


def load_models(models_dir):
    """
    Load saved models from disk. This will attempt to unpickle all files in a
    directory; any files that give errors on unpickling (such as README.txt)
    will be skipped.

    Inputs:
    - models_dir: String giving the path to a directory containing model files.
      Each model file is a pickled dictionary with a 'model' field.

    Returns:
    A dictionary mapping model file names to models.
    """
    models = {}
    for model_file in os.listdir(models_dir):
        with open(os.path.join(models_dir, model_file), 'rb') as f:
            try:
                models[model_file] = load_pickle(f)['model']
            except pickle.UnpicklingError:
                continue
    return models


def load_imagenet_val(num=None):
    """Load a handful of validation images from ImageNet.

    Inputs:
    - num: Number of images to load (max of 25)

    Returns:
    - X: numpy array with shape [num, 224, 224, 3]
    - y: numpy array of integer image labels, shape [num]
    - class_names: dict mapping integer label to class name
    """
    imagenet_fn = 'cs231n/datasets/imagenet_val_25.npz'
    if not os.path.isfile(imagenet_fn):
      print('file %s not found' % imagenet_fn)
      print('Run the following:')
      print('cd cs231n/datasets')
      print('bash get_imagenet_val.sh')
      assert False, 'Need to download imagenet_val_25.npz'
    f = np.load(imagenet_fn)
    X = f['X']
    y = f['y']
    class_names = f['label_map'].item()
    if num is not None:
        X = X[:num]
        y = y[:num]
    return X, y, class_names


================================================
FILE: assignment1/cs231n/datasets/get_datasets.sh
================================================
# Get CIFAR10
wget http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz
tar -xzvf cifar-10-python.tar.gz
rm cifar-10-python.tar.gz 


================================================
FILE: assignment1/cs231n/features.py
================================================
from __future__ import print_function
from builtins import zip
from builtins import range
from past.builtins import xrange

import matplotlib
import numpy as np
from scipy.ndimage import uniform_filter


def extract_features(imgs, feature_fns, verbose=False):
    """
    Given pixel data for images and several feature functions that can operate on
    single images, apply all feature functions to all images, concatenating the
    feature vectors for each image and storing the features for all images in
    a single matrix.

    Inputs:
    - imgs: N x H X W X C array of pixel data for N images.
    - feature_fns: List of k feature functions. The ith feature function should
      take as input an H x W x D array and return a (one-dimensional) array of
      length F_i.
    - verbose: Boolean; if true, print progress.

    Returns:
    An array of shape (N, F_1 + ... + F_k) where each column is the concatenation
    of all features for a single image.
    """
    num_images = imgs.shape[0]
    if num_images == 0:
        return np.array([])

    # Use the first image to determine feature dimensions
    feature_dims = []
    first_image_features = []
    for feature_fn in feature_fns:
        feats = feature_fn(imgs[0].squeeze())
        assert len(feats.shape) == 1, 'Feature functions must be one-dimensional'
        feature_dims.append(feats.size)
        first_image_features.append(feats)

    # Now that we know the dimensions of the features, we can allocate a single
    # big array to store all features as columns.
    total_feature_dim = sum(feature_dims)
    imgs_features = np.zeros((num_images, total_feature_dim))
    imgs_features[0] = np.hstack(first_image_features).T

    # Extract features for the rest of the images.
    for i in range(1, num_images):
        idx = 0
        for feature_fn, feature_dim in zip(feature_fns, feature_dims):
            next_idx = idx + feature_dim
            imgs_features[i, idx:next_idx] = feature_fn(imgs[i].squeeze())
            idx = next_idx
        if verbose and i % 1000 == 999:
            print('Done extracting features for %d / %d images' % (i+1, num_images))

    return imgs_features


def rgb2gray(rgb):
    """Convert RGB image to grayscale

      Parameters:
        rgb : RGB image

      Returns:
        gray : grayscale image

    """
    return np.dot(rgb[...,:3], [0.299, 0.587, 0.144])


def hog_feature(im):
    """Compute Histogram of Gradient (HOG) feature for an image

         Modified from skimage.feature.hog
         http://pydoc.net/Python/scikits-image/0.4.2/skimage.feature.hog

       Reference:
         Histograms of Oriented Gradients for Human Detection
         Navneet Dalal and Bill Triggs, CVPR 2005

      Parameters:
        im : an input grayscale or rgb image

      Returns:
        feat: Histogram of Gradient (HOG) feature

    """

    # convert rgb to grayscale if needed
    if im.ndim == 3:
        image = rgb2gray(im)
    else:
        image = np.at_least_2d(im)

    sx, sy = image.shape # image size
    orientations = 9 # number of gradient bins
    cx, cy = (8, 8) # pixels per cell

    gx = np.zeros(image.shape)
    gy = np.zeros(image.shape)
    gx[:, :-1] = np.diff(image, n=1, axis=1) # compute gradient on x-direction
    gy[:-1, :] = np.diff(image, n=1, axis=0) # compute gradient on y-direction
    grad_mag = np.sqrt(gx ** 2 + gy ** 2) # gradient magnitude
    grad_ori = np.arctan2(gy, (gx + 1e-15)) * (180 / np.pi) + 90 # gradient orientation

    n_cellsx = int(np.floor(sx / cx))  # number of cells in x
    n_cellsy = int(np.floor(sy / cy))  # number of cells in y
    # compute orientations integral images
    orientation_histogram = np.zeros((n_cellsx, n_cellsy, orientations))
    for i in range(orientations):
        # create new integral image for this orientation
        # isolate orientations in this range
        temp_ori = np.where(grad_ori < 180 / orientations * (i + 1),
                            grad_ori, 0)
        temp_ori = np.where(grad_ori >= 180 / orientations * i,
                            temp_ori, 0)
        # select magnitudes for those orientations
        cond2 = temp_ori > 0
        temp_mag = np.where(cond2, grad_mag, 0)
        orientation_histogram[:,:,i] = uniform_filter(temp_mag, size=(cx, cy))[round(cx/2)::cx, round(cy/2)::cy].T

    return orientation_histogram.ravel()


def color_histogram_hsv(im, nbin=10, xmin=0, xmax=255, normalized=True):
    """
    Compute color histogram for an image using hue.

    Inputs:
    - im: H x W x C array of pixel data for an RGB image.
    - nbin: Number of histogram bins. (default: 10)
    - xmin: Minimum pixel value (default: 0)
    - xmax: Maximum pixel value (default: 255)
    - normalized: Whether to normalize the histogram (default: True)

    Returns:
      1D vector of length nbin giving the color histogram over the hue of the
      input image.
    """
    ndim = im.ndim
    bins = np.linspace(xmin, xmax, nbin+1)
    hsv = matplotlib.colors.rgb_to_hsv(im/xmax) * xmax
    imhist, bin_edges = np.histogram(hsv[:,:,0], bins=bins, density=normalized)
    imhist = imhist * np.diff(bin_edges)

    # return histogram
    return imhist


================================================
FILE: assignment1/cs231n/gradient_check.py
================================================
from __future__ import print_function
from builtins import range
from past.builtins import xrange

import numpy as np
from random import randrange

def eval_numerical_gradient(f, x, verbose=True, h=0.00001):
    """
    a naive implementation of numerical gradient of f at x
    - f should be a function that takes a single argument
    - x is the point (numpy array) to evaluate the gradient at
    """

    fx = f(x) # evaluate function value at original point
    grad = np.zeros_like(x)
    # iterate over all indexes in x
    it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])
    while not it.finished:

        # evaluate function at x+h
        ix = it.multi_index
        oldval = x[ix]
        x[ix] = oldval + h # increment by h
        fxph = f(x) # evalute f(x + h)
        x[ix] = oldval - h
        fxmh = f(x) # evaluate f(x - h)
        x[ix] = oldval # restore

        # compute the partial derivative with centered formula
        grad[ix] = (fxph - fxmh) / (2 * h) # the slope
        if verbose:
            print(ix, grad[ix])
        it.iternext() # step to next dimension

    return grad


def eval_numerical_gradient_array(f, x, df, h=1e-5):
    """
    Evaluate a numeric gradient for a function that accepts a numpy
    array and returns a numpy array.
    """
    grad = np.zeros_like(x)
    it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])
    while not it.finished:
        ix = it.multi_index

        oldval = x[ix]
        x[ix] = oldval + h
        pos = f(x).copy()
        x[ix] = oldval - h
        neg = f(x).copy()
        x[ix] = oldval

        grad[ix] = np.sum((pos - neg) * df) / (2 * h)
        it.iternext()
    return grad


def eval_numerical_gradient_blobs(f, inputs, output, h=1e-5):
    """
    Compute numeric gradients for a function that operates on input
    and output blobs.

    We assume that f accepts several input blobs as arguments, followed by a
    blob where outputs will be written. For example, f might be called like:

    f(x, w, out)

    where x and w are input Blobs, and the result of f will be written to out.

    Inputs:
    - f: function
    - inputs: tuple of input blobs
    - output: output blob
    - h: step size
    """
    numeric_diffs = []
    for input_blob in inputs:
        diff = np.zeros_like(input_blob.diffs)
        it = np.nditer(input_blob.vals, flags=['multi_index'],
                       op_flags=['readwrite'])
        while not it.finished:
            idx = it.multi_index
            orig = input_blob.vals[idx]

            input_blob.vals[idx] = orig + h
            f(*(inputs + (output,)))
            pos = np.copy(output.vals)
            input_blob.vals[idx] = orig - h
            f(*(inputs + (output,)))
            neg = np.copy(output.vals)
            input_blob.vals[idx] = orig

            diff[idx] = np.sum((pos - neg) * output.diffs) / (2.0 * h)

            it.iternext()
        numeric_diffs.append(diff)
    return numeric_diffs


def eval_numerical_gradient_net(net, inputs, output, h=1e-5):
    return eval_numerical_gradient_blobs(lambda *args: net.forward(),
                inputs, output, h=h)


def grad_check_sparse(f, x, analytic_grad, num_checks=10, h=1e-5):
    """
    sample a few random elements and only return numerical
    in this dimensions.
    """

    for i in range(num_checks):
        ix = tuple([randrange(m) for m in x.shape])

        oldval = x[ix]
        x[ix] = oldval + h # increment by h
        fxph = f(x) # evaluate f(x + h)
        x[ix] = oldval - h # increment by h
        fxmh = f(x) # evaluate f(x - h)
        x[ix] = oldval # reset

        grad_numerical = (fxph - fxmh) / (2 * h)
        grad_analytic = analytic_grad[ix]
        rel_error = (abs(grad_numerical - grad_analytic) /
                    (abs(grad_numerical) + abs(grad_analytic)))
        print('numerical: %f analytic: %f, relative error: %e'
              %(grad_numerical, grad_analytic, rel_error))


================================================
FILE: assignment1/cs231n/vis_utils.py
================================================
from builtins import range
from past.builtins import xrange

from math import sqrt, ceil
import numpy as np

def visualize_grid(Xs, ubound=255.0, padding=1):
    """
    Reshape a 4D tensor of image data to a grid for easy visualization.

    Inputs:
    - Xs: Data of shape (N, H, W, C)
    - ubound: Output grid will have values scaled to the range [0, ubound]
    - padding: The number of blank pixels between elements of the grid
    """
    (N, H, W, C) = Xs.shape
    grid_size = int(ceil(sqrt(N)))
    grid_height = H * grid_size + padding * (grid_size - 1)
    grid_width = W * grid_size + padding * (grid_size - 1)
    grid = np.zeros((grid_height, grid_width, C))
    next_idx = 0
    y0, y1 = 0, H
    for y in range(grid_size):
        x0, x1 = 0, W
        for x in range(grid_size):
            if next_idx < N:
                img = Xs[next_idx]
                low, high = np.min(img), np.max(img)
                grid[y0:y1, x0:x1] = ubound * (img - low) / (high - low)
                # grid[y0:y1, x0:x1] = Xs[next_idx]
                next_idx += 1
            x0 += W + padding
            x1 += W + padding
        y0 += H + padding
        y1 += H + padding
    # grid_max = np.max(grid)
    # grid_min = np.min(grid)
    # grid = ubound * (grid - grid_min) / (grid_max - grid_min)
    return grid

def vis_grid(Xs):
    """ visualize a grid of images """
    (N, H, W, C) = Xs.shape
    A = int(ceil(sqrt(N)))
    G = np.ones((A*H+A, A*W+A, C), Xs.dtype)
    G *= np.min(Xs)
    n = 0
    for y in range(A):
        for x in range(A):
            if n < N:
                G[y*H+y:(y+1)*H+y, x*W+x:(x+1)*W+x, :] = Xs[n,:,:,:]
                n += 1
    # normalize to [0,1]
    maxg = G.max()
    ming = G.min()
    G = (G - ming)/(maxg-ming)
    return G

def vis_nn(rows):
    """ visualize array of arrays of images """
    N = len(rows)
    D = len(rows[0])
    H,W,C = rows[0][0].shape
    Xs = rows[0][0]
    G = np.ones((N*H+N, D*W+D, C), Xs.dtype)
    for y in range(N):
        for x in range(D):
            G[y*H+y:(y+1)*H+y, x*W+x:(x+1)*W+x, :] = rows[y][x]
    # normalize to [0,1]
    maxg = G.max()
    ming = G.min()
    G = (G - ming)/(maxg-ming)
    return G


================================================
FILE: assignment1/features.ipynb
================================================
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": [
     "pdf-title"
    ]
   },
   "source": [
    "# Image features exercise\n",
    "*Complete and hand in this completed worksheet (including its outputs and any supporting code outside of the worksheet) with your assignment submission. For more details see the [assignments page](http://vision.stanford.edu/teaching/cs231n/assignments.html) on the course website.*\n",
    "\n",
    "We have seen that we can achieve reasonable performance on an image classification task by training a linear classifier on the pixels of the input image. In this exercise we will show that we can improve our classification performance by training linear classifiers not on raw pixels but on features that are computed from the raw pixels.\n",
    "\n",
    "All of your work for this exercise will be done in this notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "tags": [
     "pdf-ignore"
    ]
   },
   "outputs": [],
   "source": [
    "import random\n",
    "import numpy as np\n",
    "from cs231n.data_utils import load_CIFAR10\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots\n",
    "plt.rcParams['image.interpolation'] = 'nearest'\n",
    "plt.rcParams['image.cmap'] = 'gray'\n",
    "\n",
    "# for auto-reloading extenrnal modules\n",
    "# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython\n",
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": [
     "pdf-ignore"
    ]
   },
   "source": [
    "## Load data\n",
    "Similar to previous exercises, we will load CIFAR-10 data from disk."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "tags": [
     "pdf-ignore"
    ]
   },
   "outputs": [],
   "source": [
    "from cs231n.features import color_histogram_hsv, hog_feature\n",
    "\n",
    "def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):\n",
    "    # Load the raw CIFAR-10 data\n",
    "    cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'\n",
    "\n",
    "    # Cleaning up variables to prevent loading data multiple times (which may cause memory issue)\n",
    "    try:\n",
    "       del X_train, y_train\n",
    "       del X_test, y_test\n",
    "       print('Clear previously loaded data.')\n",
    "    except:\n",
    "       pass\n",
    "\n",
    "    X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)\n",
    "    \n",
    "    # Subsample the data\n",
    "    mask = list(range(num_training, num_training + num_validation))\n",
    "    X_val = X_train[mask]\n",
    "    y_val = y_train[mask]\n",
    "    mask = list(range(num_training))\n",
    "    X_train = X_train[mask]\n",
    "    y_train = y_train[mask]\n",
    "    mask = list(range(num_test))\n",
    "    X_test = X_test[mask]\n",
    "    y_test = y_test[mask]\n",
    "    \n",
    "    return X_train, y_train, X_val, y_val, X_test, y_test\n",
    "\n",
    "X_train, y_train, X_val, y_val, X_test, y_test = get_CIFAR10_data()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": [
     "pdf-ignore"
    ]
   },
   "source": [
    "## Extract Features\n",
    "For each image we will compute a Histogram of Oriented\n",
    "Gradients (HOG) as well as a color histogram using the hue channel in HSV\n",
    "color space. We form our final feature vector for each image by concatenating\n",
    "the HOG and color histogram feature vectors.\n",
    "\n",
    "Roughly speaking, HOG should capture the texture of the image while ignoring\n",
    "color information, and the color histogram represents the color of the input\n",
    "image while ignoring texture. As a result, we expect that using both together\n",
    "ought to work better than using either alone. Verifying this assumption would\n",
    "be a good thing to try for your own interest.\n",
    "\n",
    "The `hog_feature` and `color_histogram_hsv` functions both operate on a single\n",
    "image and return a feature vector for that image. The extract_features\n",
    "function takes a set of images and a list of feature functions and evaluates\n",
    "each feature function on each image, storing the results in a matrix where\n",
    "each column is the concatenation of all feature vectors for a single image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": true,
    "tags": [
     "pdf-ignore"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Done extracting features for 1000 / 49000 images\n",
      "Done extracting features for 2000 / 49000 images\n",
      "Done extracting features for 3000 / 49000 images\n",
      "Done extracting features for 4000 / 49000 images\n",
      "Done extracting features for 5000 / 49000 images\n",
      "Done extracting features for 6000 / 49000 images\n",
      "Done extracting features for 7000 / 49000 images\n",
      "Done extracting features for 8000 / 49000 images\n",
      "Done extracting features for 9000 / 49000 images\n",
      "Done extracting features for 10000 / 49000 images\n",
      "Done extracting features for 11000 / 49000 images\n",
      "Done extracting features for 12000 / 49000 images\n",
      "Done extracting features for 13000 / 49000 images\n",
      "Done extracting features for 14000 / 49000 images\n",
      "Done extracting features for 15000 / 49000 images\n",
      "Done extracting features for 16000 / 49000 images\n",
      "Done extracting features for 17000 / 49000 images\n",
      "Done extracting features for 18000 / 49000 images\n",
      "Done extracting features for 19000 / 49000 images\n",
      "Done extracting features for 20000 / 49000 images\n",
      "Done extracting features for 21000 / 49000 images\n",
      "Done extracting features for 22000 / 49000 images\n",
      "Done extracting features for 23000 / 49000 images\n",
      "Done extracting features for 24000 / 49000 images\n",
      "Done extracting features for 25000 / 49000 images\n",
      "Done extracting features for 26000 / 49000 images\n",
      "Done extracting features for 27000 / 49000 images\n",
      "Done extracting features for 28000 / 49000 images\n",
      "Done extracting features for 29000 / 49000 images\n",
      "Done extracting features for 30000 / 49000 images\n",
      "Done extracting features for 31000 / 49000 images\n",
      "Done extracting features for 32000 / 49000 images\n",
      "Done extracting features for 33000 / 49000 images\n",
      "Done extracting features for 34000 / 49000 images\n",
      "Done extracting features for 35000 / 49000 images\n",
      "Done extracting features for 36000 / 49000 images\n",
      "Done extracting features for 37000 / 49000 images\n",
      "Done extracting features for 38000 / 49000 images\n",
      "Done extracting features for 39000 / 49000 images\n",
      "Done extracting features for 40000 / 49000 images\n",
      "Done extracting features for 41000 / 49000 images\n",
      "Done extracting features for 42000 / 49000 images\n",
      "Done extracting features for 43000 / 49000 images\n",
      "Done extracting features for 44000 / 49000 images\n",
      "Done extracting features for 45000 / 49000 images\n",
      "Done extracting features for 46000 / 49000 images\n",
      "Done extracting features for 47000 / 49000 images\n",
      "Done extracting features for 48000 / 49000 images\n",
      "Done extracting features for 49000 / 49000 images\n"
     ]
    }
   ],
   "source": [
    "from cs231n.features import *\n",
    "\n",
    "num_color_bins = 10 # Number of bins in the color histogram\n",
    "feature_fns = [hog_feature, lambda img: color_histogram_hsv(img, nbin=num_color_bins)]\n",
    "X_train_feats = extract_features(X_train, feature_fns, verbose=True)\n",
    "X_val_feats = extract_features(X_val, feature_fns)\n",
    "X_test_feats = extract_features(X_test, feature_fns)\n",
    "\n",
    "# Preprocessing: Subtract the mean feature\n",
    "mean_feat = np.mean(X_train_feats, axis=0, keepdims=True)\n",
    "X_train_feats -= mean_feat\n",
    "X_val_feats -= mean_feat\n",
    "X_test_feats -= mean_feat\n",
    "\n",
    "# Preprocessing: Divide by standard deviation. This ensures that each feature\n",
    "# has roughly the same scale.\n",
    "std_feat = np.std(X_train_feats, axis=0, keepdims=True)\n",
    "X_train_feats /= std_feat\n",
    "X_val_feats /= std_feat\n",
    "X_test_feats /= std_feat\n",
    "\n",
    "# Preprocessing: Add a bias dimension\n",
    "X_train_feats = np.hstack([X_train_feats, np.ones((X_train_feats.shape[0], 1))])\n",
    "X_val_feats = np.hstack([X_val_feats, np.ones((X_val_feats.shape[0], 1))])\n",
    "X_test_feats = np.hstack([X_test_feats, np.ones((X_test_feats.shape[0], 1))])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train SVM on features\n",
    "Using the multiclass SVM code developed earlier in the assignment, train SVMs on top of the features extracted above; this should achieve better results than training SVMs directly on top of raw pixels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "tags": [
     "code"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "lr 1.000000e-09 reg 5.000000e+04 train accuracy: 0.090714 val accuracy: 0.093000\n",
      "lr 1.000000e-09 reg 5.000000e+05 train accuracy: 0.111184 val accuracy: 0.101000\n",
      "lr 1.000000e-09 reg 5.000000e+06 train accuracy: 0.413245 val accuracy: 0.414000\n",
      "lr 1.000000e-08 reg 5.000000e+04 train accuracy: 0.106082 val accuracy: 0.092000\n",
      "lr 1.000000e-08 reg 5.000000e+05 train accuracy: 0.416102 val accuracy: 0.417000\n",
      "lr 1.000000e-08 reg 5.000000e+06 train accuracy: 0.412061 val accuracy: 0.421000\n",
      "lr 1.000000e-07 reg 5.000000e+04 train accuracy: 0.413184 val accuracy: 0.414000\n",
      "lr 1.000000e-07 reg 5.000000e+05 train accuracy: 0.410347 val accuracy: 0.403000\n",
      "lr 1.000000e-07 reg 5.000000e+06 train accuracy: 0.336694 val accuracy: 0.323000\n",
      "best validation accuracy achieved during cross-validation: 0.421000\n"
     ]
    }
   ],
   "source": [
    "# Use the validation set to tune the learning rate and regularization strength\n",
    "\n",
    "from cs231n.classifiers.linear_classifier import LinearSVM\n",
    "\n",
    "learning_rates = [1e-9, 1e-8, 1e-7]\n",
    "regularization_strengths = [5e4, 5e5, 5e6]\n",
    "\n",
    "results = {}\n",
    "best_val = -1\n",
    "best_svm = None\n",
    "\n",
    "################################################################################\n",
    "# TODO:                                                                        #\n",
    "# Use the validation set to set the learning rate and regularization strength. #\n",
    "# This should be identical to the validation that you did for the SVM; save    #\n",
    "# the best trained classifer in best_svm. You might also want to play          #\n",
    "# with different numbers of bins in the color histogram. If you are careful    #\n",
    "# you should be able to get accuracy of near 0.44 on the validation set.       #\n",
    "################################################################################\n",
    "# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****\n",
    "\n",
    "for learning_rate in learning_rates:\n",
    "    for regularization_strength in regularization_strengths:\n",
    "        svm = LinearSVM()\n",
    "        loss_hist = svm.train(X_train_feats, y_train, learning_rate=learning_rate, \n",
    "                              reg=regularization_strength, num_iters=1500, verbose=False)\n",
    "        y_train_pred = svm.predict(X_train_feats)\n",
    "        training_accuracy = np.mean(y_train == y_train_pred)\n",
    "        y_val_pred = svm.predict(X_val_feats)\n",
    "        validation_accuracy = np.mean(y_val == y_val_pred)\n",
    "        results[(learning_rate, regularization_strength)] = (training_accuracy, validation_accuracy)\n",
    "        if best_val < validation_accuracy:\n",
    "            best_val = validation_accuracy\n",
    "            best_svm = svm\n",
    "\n",
    "# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****\n",
    "\n",
    "# Print out results.\n",
    "for lr, reg in sorted(results):\n",
    "    train_accuracy, val_accuracy = results[(lr, reg)]\n",
    "    print('lr %e reg %e train accuracy: %f val accuracy: %f' % (\n",
    "                lr, reg, train_accuracy, val_accuracy))\n",
    "    \n",
    "print('best validation accuracy achieved during cross-validation: %f' % best_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.427\n"
     ]
    }
   ],
   "source": [
    "# Evaluate your trained SVM on the test set\n",
    "y_test_pred = best_svm.predict(X_test_feats)\n",
    "test_accuracy = np.mean(y_test == y_test_pred)\n",
    "print(test_accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWEAAAD3CAYAAADMt+U9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAgAElEQVR4nOy9d5xkx3Xf+z11c8fpnjyzOQFYYLFLgoAAAiQYwEyJQVTyo2nKEp9kJetJsvQUnp+eLT3JsmVFS7JlBVNWoMQEWpEkSASCBEHkXexysTnM7OTu6XxT1fvj9oJDaLHbs4AIUW9+n898PtNddW/9qurUqapzTlWLMYYNbGADG9jASwP1UhPYwAY2sIH/P2NDCW9gAxvYwEuIDSW8gQ1sYAMvITaU8AY2sIENvITYUMIb2MAGNvASYkMJb2ADG9jAS4irVsIi8hoROf9ikvl6hYicFpG7LvH9q0Tk6Drf9Yci8nMvHruXFv8Y6/O15iQi14jI4yLSFJEf+hqWe0m5/McKEflZEfmfl0l/WkRe8zWktC6IiBGRXet9bmMl/A8IY8wDxphrXmoeg+LrbdB+HeHHgXuNMUVjzK+/1GS+XmGMud4Yc+8Lecc/RhnfUMJ9iIj9T7m8f0r4Omy7rcDTl0oQEetrzGVd+Dps66vGS1XXKyrh/szxkyJyWERqIvIHIuJfIt//KSIn+luuwyLyrjVp7xeRz4nIf+q/45SIvGVNellEfk9ELojIjIj83HqFU0Q2i8hHRWRRRJZF5DdFZKeIfKb/eUlE/lhEhp5Tt58QkaeA9gvshJuf20bPNdlcqjwReZmIPNZvtw8Bf69trwbrbQ8R+SNgC/C/RKQlIj9+leU+b31E5O0i8oSI1EXk8yJy45q0KRH5SJ/vqbXb9v429cMi8j9FpAG8/0Xk9AEROS4iKyLyCRGZWpP2RhE5KiKrIvJbInKfiHz3Osv+DPBa4Df77fonIvLbIvLXItIGXtuX/w/2635GRH5GRFT/eUtEfrnfX6dE5Ack2/YOKqsHROSpfh0+dHHsXqHeRkS+X0SOAcckw6+IyEL/PU+JyA39vJ5k4/qsiMyLyO+ISDBAu/yEZGO92W/j1/eT3H5bNCUzP7xizTPPrmLXyMSH+nkfE5H9Vyjz78l4v67fJSJngc/IJcyszynXEpGfkq/oukdFZPMlyrpDRM6JyGuv1BYYYy77B5wGDgGbgSrwIPBzwGuA82vyfQswRabYvw1oA5P9tPcDMfABwAL+FTALSD/948B/BfLAGPAw8D1X4rambAt4EviV/jt84A5gF/AGwANGgfuBX31O3Z7o1y0YtLwX0EZfVR7gAmeA/wNwgPf02+nnrpbLi9Aed72Acp+3PsDLgQXgG/r8/kW/PK8vM48C/7b/jh3ASeBN/ff+bP897+znHbivrsDpdcBSn5sH/AZwf/+5EaABvBuwgX/df+67r6Jd7r34HPCHwCpwe78uPvBB4G6gCGwDngG+q5//e4HDwCagAnwaMIA9oFw+TDYuq8CR/vuet9795wzwqf4zAfCmfv8MAQJcx1fG9q8Cn+jnLQL/C/iFK/C6BjgHTPU/bwN29vu5B7y1LyO/ADx0KflcIxPv6ffrjwGnAGeANrlrTbmm3/75fl1fw5oxe4ln/g1wsF8HAfYDw2vabVe/vc4BtwwkHwN25Peu+fxW4MSlyD7nuSeAd/T/fz9wfE1ark94AhgHQtYMLOA7gM+uQ8hvAxavJJhkg/jx59TtX16t0llvGz23PODVrJmM+t99nheuhF9Ie7wQJfy89QF+G/j3z8l/FLiTTDGffU7aTwJ/0P//Z1mjJF5ETr8H/NKa7wtkA3sb8D7gC2vSpD+wXgwl/ME1aVZf/veu+e57yGzIAJ9hzYIEuIv1KeH3rvn8S8DvXK7e/c8GeN2a9NeRTQy3Auo5bdIGdj5H9k5dgdcusgn5LtYozX4/f3rN571A91Ly2c+7VkEr4ALwqgHa5LlKeMea9NdweSV8lL5eu8S7TV9uzwD7BpWPQbc059b8f4ZsZv0qiMj7gB/pVwyyjh1Zk2Xu4j/GmI6IXMxTJZvJLvS/u9iga8u8EjYDZ4wxyXM4jQG/DryKbJZWQO05z66nnMvhim10iXxTwIzp9+CaZ18oXkh7vBBcrj5bgX8hIj+4Js3tP5MCUyJSX5NmAQ+s+Xy1/XQ5TlPAYxe/NMa0RGQZmO6nnVuTZp67TX0BWFuXEb6yWl/Lb3oNx7X519sOc2v+7/TfN8zz1/v0c8sxxnxGRH4T+C/AFhH5GNnK0ydbUD26ZuwKWd89L4wxx0Xkh8kU6fUi8ndkuuNSfH0RsZ8ry5fgqPv983zj7nJYr645cZn0HyabZA8O+sJBHXNrbR5byFYWz0JEtgK/C/wA2dJ8iGx7LlwZ58hWAiPGmKH+X8kYc/2A3C6+Y8sl7GS/QDY73WiMKQHvvQSnF+saucu20fOUdwGYljUS3H/2heJq2+OFtsXl6nMO+Pk1fTxkjMkZY/60n3bqOWlFY8xbXwRul+M0SzY5ACAieTIFNdN/btOaNFn7+QVibV2WyFahW9d8t6XP4SL/teX+PfvjVeBy9b4UR4wxv26MuQm4HthDti1fArrA9Wv6rWyMKVyJgDHmT4wxd/R5GOA/XEU9nm2Lvg19E88/7p4t+grftckmlovvtchMdxdxjsx08nz4FuCd/UlmIAyqhL9fRDaJSBX4KeBDz0nPk1VkEUBEvhO4YZAXG2MuAJ8EfllESiKiJHMg3TkgN8jsXheAXxSRvGROsdvJVnstoC4i02SC8w+FK7XRpfAFIAF+SDIn3buBW14ELlfbHvNk9tirxeXq87vA94rIN/QdPXkReZuIFPt8G31nTdB3ftwgIje/AC6DcPoT4DtF5ICIeMD/C3zRGHMa+Ctgn4i8sz+ZfT+Z+exFhTEmBf4c+HkRKfYXND8CXIyX/XPgX4vItGRO1J94EYq9XL3/HkTk5n6/OWRKqgekxhhN1q+/0t9l0ef5pssVLlnc9Ov6ZffIFHl6FfW4SUTe3e+fHyZbzD10hWeuJOPPkK2+39av78+Q2c0v4r8D/15Edvfl+EYRGV6TPgu8nkzevm+QSgyqhP+ETFGe7P99VaC7MeYw8MtkAj8P7CNzTg2K95FtyQ6TbY8/DEwO+nBfkL+RzNZ0FjhP5hz8f8icD6tkg+qj6+C0Xly2jS4FY0xE5vh5P1m9v40XgeMLaI9fAH5GsuiFH7uKcp+3PsaYR8gcs7/ZTzvez7eW7wEy58oSmbCX18thnZzuAf4v4CNkk9ZO4Nv7aUtkq5pfApbJ7JOPkA30Fxs/SKbcTgKfI5Ol3++n/S6ZXD0FPA78NdmkcjVKC7h8vZ8HpT6PGpmpZBn4T/20nyDry4cki1z5NJnT6nLwgF8k6+c5Mmf8T11FVe4m688a8M+Bdxtj4is886yMkzn1vgrGmFXg+8jkb4asX9aaof4z2cT4STLH7e+ROfTWvuMsmSL+CRkgmuZidMLzZxA5TeZU+PSVXraBDfxTRX+7ex7434wxn30JebwF+B1jzNYrZv4nDBH5WWCXMea9LzWXF4qNwxob2MDzQETeJCJD/W3zT5HZz6+03X2xOQQi8ta+KWUa+L+Bj30tOWzgHxYbSngDG3h+3EbmCV8iM5e80xjT/RpzEDIzUo3MHHGELJ56A/9EcEVzxAY2sIENbOAfDhsr4Q1sYAMbeAmx7rsSfvNXfy07nqIUuXyeoWIJHadIqtESorXOTo8oIUVod3okscGIQzt1yJkWmJhUOTzw6U9Tr9cZGhoin8+TJAl/9OEPDRJbzPe97+3mpgM38MzxWWJJGKqO0u05JBpKQxUcx6XgOzTDFls3XUuEw8L5YziSsnPfrcQ6wPFsTp08wjW7r6HbDZmc3s2x40/i2Xm+9R2vHIjHj//bbzIKhTYpqUmITYJG0EBsEiwElMagcMRDaYOkBk/5uLbNsWPnqA6VKVQ9IpVidApoDBow/MbPf2YgHgA3fdcvm03TOxEsUtOhouvMHrkHohWGhsqEYYhCsC2LxmoD5TjcNBVw++5xzp86za/cf5Ldu3YThQlx3GXu3HlOL2tufP9/oLtU48nf/1cDcXGnXZMfySG2Q7laAjGkRkB6BD2bbpLg5HwsKyAKE8Iows752L6LEou4k2DbNpZSmDiiF0ekAoHjoCw4/rdPDcTjfTsDYysL0KTKIje1jf1vfAcPf/KviWeOYIxDagT17GGnTHaVCEiKZUAhGAyp1ogIInLxdBQfPNkbiMcrXr3ZfNu33sX4+DgX5mt8/OMPMDZa5tvf+zbuu+/znDk7y/ZdU9z9sc8xMlSinHfoWV2KZYfpTSO89c2vY3m+ze//9v1s2ZHj5lv285cff4QnHj1G1ItIuslAPF72hp0mbKRsn5ygsm2KZ44dwZiYrds2EXZtrHaeA5s286WTM5SLBfZsnabdXiUXFNi6dycPPvAQR06fZ+v0Vu5/4i957evfxs6tN3Hn3v1cs2c705umB+LxA7/4x8Zofdk8L2SH/ls//b6BeHz/9/6A2bRlMzaGhfl5zpw5hx8EhL0ON950EzfffBthr0eplIU9zy8sEva6DA9XSZKUVrtFfWUF3/NZbTQQJYhSHD30NF6uyK/8+n8ciMe6lfDFw4rKsnA9Dx3HCAatUrQxiKUQA0maEiYxnW4Hg4dlWyiT4jg2JtWYNGH3rp3MLsxjjOA6Dq7vXan4Z9Fpt0l1xOlzpyiNB6yeWeTA/tupVkY5dOQwuVyJuaVVQgmpz88QaUUah5QKDmfuOU1laAuFvE/YafLgqYOIgpWdN/D0l7/MSGUE3vHKwYhooZOGpAIJKT0dgSWkaUSqQ2zHw6QpyrKJdIhvXMpeHhuHiVKFD93zSbbt3MbuW3Zh+T1sxyFODV16WNbA+hcA26S4ItgmYbKkqUQNbn7TawhyLk8+8STnz8+gBFzboVQoYTseng7p1Jv0ugn79+3HsV16dshiR4gArRxWOyGklx80a+HlXPx8DmW5dDoJRilIDSaMSOOUVhRSdXziKKTbi7AdG9f3SAXiOEHrbArSaYKFQRtDmmq0UpiBzv9k6OkU37JRYmG0wS8P409sxhTKpALGcdGWT9qq4xiNEZOpYkMm0309YPqx/BcVw3oVRJAfIkpD6qsLpGnC+GSea3Zv48HPPUh9tUOr3eGRRx8hDW1yXoU9e3aQ2opOu0a3EfHFL3yZG/ft5BvfcScf/+g97Ny1gu2A0YYsVHcwiNgkJsFyfMZyY8wUTxF2gcQnahtcnTCUg8XZGRo64sbNk+y+8QaiOKHRbXDLgeuZnJhi+7bdPHzoE/Say0TNeZQyaH2pA22XhmVZGLl8P34tzKSiBNu28CyXKEoRUQgK13WZm59nYX6ekeERwrCHUgoRIUkS6rUaYRShMbRaLSxRlMol0jQlimPSVNPptAbmsW4lnGIQBC0QJSkSdsmXArTSECm0BiVZ5ZQ2RElImAiBX0B0B2OBJQqlNJunp6hOjGOUQmID1uANv2f3HiamRqiMFVjqzmNFCtvqMVbxePkNO7GdHCeOH2K2XqO+2GT/DTfyyQcO4riaVBImD1ToLFzA9QIWZk+QL3h8+eAcrVqC1Z0fmEdiwFU2iTEEloeVpJCCVj49JWitcJSNa1zG/RHyqc35sytMDjuMVcvsP3AdhZGANGrh51xMalBGcBD0OhROBhuleuwYc7n9mmkevf9JRkqjXHfdHnK2zwPRg1yYPU+UanrdLlYSE5RzJKmi041RjkWr0yZqd+iGIWmcIm4ZZfS6Bpmb9xHPQ6GwwohuuwOpwcEm1BqdGsJ2Quoo7JxPkMuDEdIwIo1ibNvGSAqWkPRiwl6PTjvE5B3EGVxkY2NjabAtAyhKWyY5OXuOtm2jRkbZ/4rXUqu1OHb/X2ULC0x/3SsYo7Kz/Zj+mcJsBSxolGFdfWO7FiNjFc4cP0GcWtx00166rZgnnjjMuXMN/JxHoezwvn/2Xl59x2vYuXMXTx85jDIaLM2n7rub2fM19u+/hce/uMSxZ04yNjaCqGMoNbhFsdeLyPk+W7ZsZ3h8K/nlEyTxIpJa1JZWmBodo5wPCLyAqhHqc7M4Qy6TwyOoVHNgepjrt++kFSssV1Fv1Dh99ijm1rt48MEv8O1bBouasy0LfQUlLFdIfzEwMTGJTjXPnDhGFMakaZr1vghgiNMYx3VotVYRESqVCp7nEIY9wjiiUW/g+QGe79MNe0RRRLfbRWOw12HoXf9K2Bhs26bRaDA/P0fFzjFtbyJXHaU45OG6LkopjAaMxXW7NIlSJKlFEic0lhexxdDrtDh46AmKo6N4ng8qRa8j/vzE+VMc2L+VNKpjRW2q5UlqK+dZCnK0O0v0YhAnYqVeY2y0xNSES6nkU2/MoBRMlxXVTVMYJ0fUq3Pt7h1o1eb+B46wfcvgx899x8ZzfFxl040jLNshTSJSoympAl5/JaxtOHp4hocfOk3g+1SKPvt2LFLMe1Q3VYkKDTqmi5gUk8bkvWK2LV5P3yDcuSvPXbdcS3t1hW9/zzezvFTjc/fdy7d+x//Ovv03cc9nPsnn7r8Xx3WxbMX2sRGi+gUOXLuL1dOrzDo+K2IoBxZziZAbmkCZFL2OU8N+MU+33sLEMaSZUHtBDnFcmq0WsTLUwjYT5TGUUmij0WGK3Y3QUYQpZVcPuLaN1mAjeMqmWwsRd3AZ6RlFMxZcrRnZtYvK3gPcdueb2brnWrrLZygH45z5m7+jmQbYYrBUgmUUtmhsQhwRxAhGMgMRAoKQYBGto19sy+Lhhw/TC5vYtiKOEmYvzOOWbO64/XYmJ8aYGtvGN771fUyMjRP4Ltfu2EOj1WFpqcYTTzzJ4w8d5N6//SiOledLXzxFamJsy0IFg+8e40Tzppe/nNe/4lU81F1lRfn4ns+K6bDvxn3s3HwdzbjB9d/8dpy5c0wM+SzMnmHraIXpQomHdcytYyW2LTa4dsd2cqUCQ8srHD/0DJ2wPTAP1/Uuv4I3IObvy77Qn/yeHRcGZPCdwHMRRTFJ2GP3tdcwd3aWubnzOJ5DnCTsnd7E2NQ4WsCybVKdYlkW8wsLxHHEtm3baDbbdNo9knSVfC67HdW2LPJDJXQ8+KLlqu7PTZIYrVN6vS5tAcQmF5RwHMFoiJMUo8lWDH0FJDhYyqZUKqPjmOXFJYwxBEFACv3l/uAcmr1VenFMHHfx7JSo12B2bpZKeQuHvnyEZjuiUPJpNVawdZduvJNmo4EyMDkyhaDohQlx1MKgWVpeZGyiQHWkinKcgXkUcgXmVi/gOgFKucRJB8GQkBCjMaJJrJSc5MlZZXKeC1oTeB7t2KIXaXpnF9l+SwnLKKI0RbDwxFtXewBoo5kcLpGzgULAH/z33+Kd73gX+XwR1/Epl6ts27qdLzqfA8CyLYqFMo32MkGQJ++0Sdoa23EQJaTawvGLKFnfymS12SBpdnE8F+XYFEtFjIZEG6I4JklTStYQ4UqEJBqvHGAsQ2Q03TQhv2aVmcYxFgqdJOjYYK/DRJMqm24qaGUzvu8mdu+9mdpKjeW5Gdx4lVQU2F1C26BNiCQprniIaERp7Iv30HzV/CMkBvQ6+mb7zmlWl2aJ0pBWu8n2W3dicJg78gxRpOl2Oxw9fpi5//FH3HHbq9m6ZZprtm1icWmFB77wEE8/dYSHH34c2/bZND2JEps4ThAg5+euWP6zzI2iUh1DS8rpJ55i9fwcth2jjCJfzhHk8pw/c5TRqRGGtpTYMzbJSD5PpVTArpR45ORZVqYdKsVp4nKe8pCFtHwuzMxQGBr8GmzbsbmiTfj5njXqKwpaDOYFKGHfD7AwnD52jOPHTxLFMUZauI5Do16ntrSCZbtYJkUsi16vR7fTxfddOp0ulmOj0fR6HVbrK6Rpiue6rCwvUSlc8fqMr9Tpash3e22iuEecRARj43jFHI5lZVu3JCbqdYh0jKttlBK0GIxlExqF1hqdJHQTjZfLo5SVrYQs6N9jPRB6cZt6s0HgB4iKiUJDLwqZX1nk6NkzhLEwHpVJow46FrodzbapneQDCPIufuBTKBSYWVxheGwE37dpt9soGxZqiwPzqPfqpCollRSjY1pphCgQleJ6QqJCjNa0LjgcP34WbQylUp5GN+LkY0f5oQ/8M3rSoGPOZY4nEhzLx9YKsw7zDECqNY6fIxXB8h16OsIOXO56wxswBjzXZ3x8nCRJ0WmKWIrT5+fYMTFOnAgXFpdZ6doo2yLuhXS6Ia7YiFnf7TlppLF8B9tXBL5DpVqm0+4Rx5rUgGMKTJa206stctONeymWAh488hQNuvREUzAK33UxRtPphWhtSHSE7TmIGnzQxanCcVxylSF23ngL1aERllcXUWLz5aefYOuWLUzsmKa5shu6i5w/X6fbE4qi8ARsSeHi9vSifdiAIcFZhzlieLTEytwMYSjUlrscOvQMiYYL52t0VmZI4y7dXsTNO95C5I3wzIUWRW+Rez57L3/20Q/jEYN2IFG0Gg10YkgjQGvGN40PzCPveRT8EpJqOucWsOqGtqvJxdA0izy48gV6zTO8xc+zsDhPKEXGh0cYzxcJI8Or2gGjvR46V2ZrPoft+5xpzBMnp9nmD37vlGPb6MsoYYPByEUzUNb0F1tbpWuUMCbzN1wlHNvh1KlTdBvL2JYhToRUp6SRYWV5hebqKvmhCrWVFRzbpttu4zk2k2MT1Bp1LMumWimDSXnq0NMU8wWCIGBx7gIta/CF3LqVsGVZrK7W6PU6aK0YnZjAcV3CsEt9ZY728jJKDBRdbNvHc1w8UaRxSopFalmZUrY1nh9gTN+6pmRdxvh2o8Xc3BLHnmmgkyZ+4NOTGl5QIY4j0thm/vwC27dswbIDbGcYY7cJymVWGku0TYPpsRHaqsIf/Jff4JW3vox8zvClg4cp5K74wwDPYricZyj28V0HEY3vj0OckCYJaZjguD7tVYvf+9TfkqbgWFBvhDSaHfzA46N/9bdY/gjXXLOD63d0yaHAWPieTbrO2wFMmhLkbKKwBSl84Ds/gOd7JCZFVIRtLDZPb0YpGy0GJQ56bBqdsyFqc3x2GWtkChCW23XCNKWYLyM4GDX4D504ysYKhLHxEdIkxnI9TC/BcRTVoSpBlCNcPMm3vOM9OE7A0UNPsrM0xlic59jZ09QWlsmHOYzSpBpajRjXG8KxI5Jk8G1eJ07wbZvp3XvZtut6er0e+fIEr3z9N/LZT/0FsXWePXtv49a37+EjH/ozvrS8wpix2DJmiJVwplZkIogpSg87AQRSJSjA0YN3zv/4r5/G9x08zyKKhNrKGVzfQ3c8nEKR1bomNTm2bjtAGHnYls9f/OXf8JEPf4h2p8nW8QnyuSJah9yw9wCNRpNc4JPGmnqtfmUCfYjVYWnpLDkDgbjk3BEqo0MQOYzuuYbm2RPEq4pf/fgnqFDg4OFzVCoem0cnsCYmWV5cwTp1lPmlGhfSRUZLo7TmVzjrwuj26SsT6OPK5giNZRIsJdncZ8yzilgrwRhBAKNU31k72HWNz8X87GnCNEGMoWRCtOtkDjrPptlpc+Tol7n11ttpNjt0V+bYvXcfQzmfhfNnKFQqGMfhqScPk6YpmzZtIoojzl04z+jEBI1aY2Ae61bCWmuSJKXb7eF6AbXaCqTQbXY5+NjnqeYLjAwPUcmNIcqG2NBdbbM0v0gjjHErZdxCjtV2Cx2GOLGHchyUpdDr8MCjFUkUs7raZevWKZSdUCnk6LU1nsljK4ty1UNR5MSpRdrREZ45v0ouWMC1Q4bLis3TWzh5+jSpGJ45eZxcLgUrprYyeAPmJUBbPfJunjAKMbGGNAWjcVyLNBYeeeIElaESMxeWiAyIAyDEPc1KrYdln6cxkaJlmoSUNMlu01PKXXffaK3RRiGi8IISQeATa/2sCcmyBKUUjuuyY+d29t78CrywS7dZo4cihyYOY5I4AcvFLZQxWpOuY0ZwPQ+xU7QB5XjUm20QhUYTeD7SjhmvxNz32Y+Ty02QL+SYnpii0apRX66R9DroOCHRMdoYcgWbVLexbMHIerzwEEYxhXIZ23OxPAeUg9awutxganyEXK5ItxuyUGvhaLhuImT7TkUrzvHkbEhk24z7LmW6WEaj0xRP2aTrCLHXiYXnlijmbOYbXVKEwAvYND3FNXv2ESUJ7Z5mYXaWkYktWMQcPXSQ9uoqrmNj0ERJwvYdu0m1BqWynY3nrMtMlIrD0xeeZqWzzOTmUS7oBW7YvYOV+ZiHjncpxT2qtk1oe1QmxqlMTuLGHR45dZZhbwjpNvDtVbos4ucV1ZIiHMuhdJ7UHnzlZ1kWRgvIxe2FPOsAFQQLwdeaUydPYozB8zxGRoZJU00YJ9Bf/SrHxc0VEMviaoIpbr71NnADwk6bow/dz8t37qY6MYUA+UKenJ+jWhmh2WwyPVqmVCiQz/mszp6hNDXFuTNHCZOIcqlCEPjUFxfpddq0mk2iaHCvwfqVcKqxrMx+a3RKkmoazRa9ZpvVxWWqfoAi8+7nLQtJYXm1xcLsPOcWFrArJapT48RoSkHfbmIMRpt1CVTeLyLKplotsnXbFrqtGpu2b6Hb7tGtLeP6OcRKcByf8bERpsZztLotgpxQa3To9RKWV+rUa8t4gUM37BBGHRwrT6FQGpiH0f0QvShFaSHqtRFJiQFLe5w8VefUuUVcRyjmfeYXG/jYOJ5HLsijuhF3vmYf190SEIfZ+7Ro2lEL213/z8212210uYhSFuXKWGbiCbsYIE0jRAnbt2/HdV3GJ8bIV4bxlUvBJLzqzW/i5KkzrC6t4Lou2B6WlydN4nXtUnzPozhcQIshTjWJySJmUm1QiWZsaIiRss/sjMZ4VSw3wA1ylEQzNTbBhVPHSCKD7bvkSi6iugR5n7QXYdLBRdYRaEcxURRhAOU6iFKYOCTIuUxOTTM0OkE8N4uJI8Y8zb6Xj5Mb2cqJx04RqYT5TkqkLcT28UyKRYJlDPY6TGeYlKgX00WIYxBlc901+xmpTvGud7+HXqRZWGly+Pgc+fIIjoTk/YDrr9vL8ePPUB6q8MpXvpLt27dz8KnHEEhpqfUAACAASURBVEuhE4Of8xipDl+5/D6KQ+McPfcMxtEc2DnMjrzD6KQmrwIOndvMzumYUlTBP2MTj1SoTI0zaWtmam1y+VFyQ5pO9xyFEeiupKi0SHVMUS1OY9LB5cOxVLYblszpaacqC/FUKYExpL0OF2ZPcOrIIRTg+S7tpWH2XLOHUt4ml/NptlqEaReiBBUUSRwXlah+hP5g+KZ3fjPdOKLeaBKIxkJz+5130mv3qG6ZYubEaVIUcZzgVSuYuIvjFiFscviJR7iwVCNXKJPEESef+TLNWhNjCVG7i7qEY/H5sH4lbDSe55PL5Wi3GhQrFSQVVhcXeP3b3k6xkMN1LNqtOp1OF23A3TTF1vExqksrLDdqWIFHoBT5IMjCgNIEreWKsYNroYzP333yYaamqoRhnZHhCpXKCI4fs2lHik4tirk8KId6Y4mwvcSmIZtc3qZiFXFUj1Z7haFSmfH8Zqr5It2oxsziMjt2X+7O5q9GT0ISE9OjgWN7SKuEEU3e9/ncw2e59/OH8HM+Nho/yFMsGcR2yLtwy63XoU+ehSdPkm6/gShvI9qgQqHseTTa67umwFaKTz58kGTfFNunpymECUrZiNjofpRCksS87a1vxnVd2u0WflDA87Jfm7rz1a/HdR7kseZjtM+3wC6hvQBbbFiH0hmZHEHlPFYbDYwSjNEkUYwkKVHPEEwWGN56HS+7fTetZsj8/Cx+UKJQrFIojpIbqnC2sUQt7OD6ERPjeXL5kKHSGGGtMzAPXww9sTh74hSrC0vkiluzEDSj+dF/92sYYGmlwbZdO3j9G76BhdOH2HLXj/Knf/4XHDwa4SiF0YYuhnkxJLGPLzAhMYEZfGdgofBdn15cx81F/OXH72PL9C7Onp3hI5+4m6lNW9i8ZTuvftVrOXzkOI3lZZaXl3n5y17GLTffRKvdpN1cplObwXUVlaEyiS4Q+A5GDa78CqWY65ovo7ja5d4vfpLbx69l0T7Gq699I1+up7zxjluITYp67GkaOsXEAeWpIlt2OkRxjWIp5ujpBq12RKm8mflaRKPWYynt4NVXBuYR+B5aa1LJTAl2qlFWdkDp6GOPEoddLE+Bo0jimDRq8LY73kCn0+aRxx7n9ttfTSfq0mjUKOeHaKwuU5qaxs4NsR6VJrYNYY/2ao1XvOY1/Mh3fDt3/+kf8873fyf3/MyHGZkY45bXvYn6/AxH77+bwPX55z/277jhtW/jC/d9BisooBwbE8Xsu/lmjh45Sppq6ksL9LpXulHzK7hKc0S2ukjTlMZqg1KuRKFQwCvkENsiTVPatVVEG7SycL0AbSsIHJKmIXBd2p0Oxvf7v7MkiKVYTziAG2g0mY1wdGwCk8LJc2dYqK2gox5JrNm9dTu2ypHLVWh3W4RxSL40QpIqZhbqFKoWTz4zQyuOmCq70PZApxSLg3ucw6iNbdnono1OFWISPNtCGcXCcpeRkWE8z6bValGvt2m3QkqTVdq+R1M73HbnLVSVS1I12FEXx/VxC3mssWsoqMFt0wApmkePzDLuREyNjCBronmUUhijkDTBdV2GhobwfA+lLEQ0tm0zXh3humv3sri0wpNPPQXWEJbrYjRX9GavRS7vMV9bJkXAKFSUYhKNzlwudDtdlDicPHmCRqPN1OQEQ0ND2Wk1Syj5OapRgW4ag0Cr2WFswmextsTk8NCVCfRhoXGUoHs90qiHTjTYKSIOrl+m2+nQa7cZGhuiPLaJ0ak9/M3f/g2HvvQINl0cBamClx+YoLVY45nTXdrGoqqydw8K27Ko12tUJxUH9t7Irl27eOKRp5mdmeOu193J3MISixfOMz05zstv2MXsWZujm6fYtmmSpaUFat0WlhgSk+D2TRBKWYRhQroO52273SEXj+AlkDoe5ZESC80OcadNPm4QxmM89NiTPP7I48wsLhIUi/jeu+ikZdqdFTYNu2ye3s1Sa4ajR5vYOsGzS1moV3MdNtC+Y+7iSUXPMpg0YnnhAknYxLGEMI7QaUy326bTq7Np8xT33XcfxVIBx3Opjo7guBYqTIhadebPdNl2/c3oy/+y0ldBMNi2Raw1nShmfHqS86dO8rlP3cPCwgKWDQ/83V9z6vxZdHOO7bv3c2H2Aq4N+Vwe00xpt9osL8xTCjxGh0eYnb1AoTqMbTcHb4+Bc14kLpIp2XaHOOyxtLSIN+ExOjqKLQqJU5rLy9i9FLQmTkM6TgM7FyCuQ7laJYkiup0Ow9XqV7a5otZl1ylVNVOWTzGfEpkLxCksN1dpdlvkPR/XcQj1KtPTB6gOj9Nu1zl58jTloSIxGo9xjpysMbNqoZwh2sqnWM4zNV3FXkcsqti7yU0eII6a2dYITapsTNxmafUxHD+H61tUXRvXaeM4NpZojNEosdj89h/E8lzoNakf+jh+aYJgYi81PYQfrE8Jx8bQXOpx4uQF3nCH6Q9WBUaeDeo3RpPL5XHdTAHrtH9SSCyCXMDY2BhTk5OAQllOlkfrdR0KKFoWK0mCFoVyXJROieKUmIRSoUK1WmVhYYWJiXEmJyco5AvPDkxxLIqez5AXsNBdpR0KjgqYm20jTg/xBreTWxhsDBKH9DpN0lSD0tlhIdHYJqLoCUY8rHyJ62/8Bv7kz+7G8Vx27txGa2EGL1BsmRrikZk6vcRGFERkx5kHhVKKdrPFvk17uP6GfRgcRGB0bJibbzpArxdTr9VZrq/ilUv0WnUmRoZYnDtPs7mKo3TmL1HC7OwMruvQaHUoFIpEvd7APLyiR5SE1OtNrFyeM+Fp5toBu5sroA0PPfEkM/U6U9s3cXrmLBWnQmm0xDIOndp2jp5/ish0wR4myHdIQoXtBfiWImZwW72yLJRSKJ1kx9Kb87QbdS6cO0ensUySRCRiKAQKF5ux4UkOPvYo9cUFpjZvp9Oq0242WVyYp+IGjJRynLgwS6AgWke/aG3wfQ/P9agtrfCqt7yVj/zhBzl68ClEaeZnLzB/+GlyvkN1dILt+28mjnt85qN/QRiCPTqGSmPidpO582eZ3nUtu/dcQ215mc2bB/+Bmqs4thwTBDmSRBOFmqTT5PzpY7Qro2weG6E+u8jKqRnqS0sgKStLywzv2oI7MgTFPI1Oh15fcHpJjOO66DRF6ZR17KwISjHBkIWrFIm0SB2X4TGHiYkKKvGZnD7ALbe+k+HRTfTCLr7r81oliFjoJKFeW+Wxg3/F8OFTmCig6MboNCG3ZRpk8Nl052v/DWIMSgmCYNsw7sPBBz5Bu9thYmIMraGnoRMKsbYIbId9N1zLG7/tu1FunjTVOPkR2PluGnGMXxqj6vnIOlafAK4oGu0GB584Sf2b7iCKYoLAxVI2SZxkdx/g4HsFjLZwHRdtZXciGAyuazEyPMzNN9/Mz/z0zzK693qUchGtMgU2IM7MzzFUKZAIrDZ7TO4uU68vUl8VhrwAL+cyOlRly/QEvu3SjXpYtiJwPNwAwtUyfi+hZNXQVogbpKRGGB/zqeQHnyBTA64t1GbP8dkP/xnvvX4/dixoS+N6PmHtLNKa4UwnYtuOfYyOj/M9P/QDbN++Hcd3+PTdf0DSnGN1aZFj51MSY+M7ikQ5dPTgjhcn55PXimJQZm6mxoMPPsn+G66jWsmhBOy8RSE3SeD5fO6Be5k5c5I06qJNgmcZol4PGwOxZniozOTUGG98zWv5z7/x37jtjlsH5jExWqAwbTPVnmCvm2NsSGN7OUqFhKNnl5jothjevYe0G/Ke9/1L5k6f5lMPnaYysY1cvkq349NpzNFZnmO8rAk8i27osLJSo6oHH7ye43H+xCEe//z9pJ0Gw8MBhVyBrZu2ccM1W3E9i1LRZc+uXVSHqrhuwH2f+Swve+ObGZ+eYLXVwLZtwngvSRgTxj2uu2479TDEW0fctNYpSZKQpilxGHHTna/jhltu5dzRw/z8T/wkS7bgpQlfnl9if26IY4ee4skvfIFd+/YxNDrG+bOnqYcdcvkc26/ZTW25wbYdu9i95xp2X7d3YB5XFSecz+fZsmULM2fPEeRyWGIjQJymRGlCpBOMEkg0w9UqSRzjaE3YbZPGEa4lJGlKt9vFcZzsoMY63Zu7tr4W21ZosdGicGwPbSJc18GWHJ2u8Kcf+hh3veGNpGlCmurM2YRCIWzZPMGObftQqdBtR+T9Aq5rgbKRdYRjoQ2e7xKGEXEUUSz6LDdbHD16DLFcXMcm7LTpxRqjbOKkg+MHlEem8aqbCKOEMIyxuiHnz5xlZHwMy7bpdXrr/v2aFI1ShqVajZV6DbTCxCnGMSRphGVZXIx7zXYgJrt0RLIJJNUaQcj5ASNjwyjfw1YOWhLcdawwcgWFlg5x7KFTC6SD4xnCMMQveyjLIjWaRKdoMZTLZfxcQJIkmETjeS6OqzCE5ApdCiXBsqFcLDA9uQ6nqQElBsuGC08fzk7vOTa2nYWZ9bqrxL0msZWnOrENrQ3X3XA9Wqd0O03Oz8zh6w6BShn3QhZ7NkFQBN1b164tiSJ816HT0uQCl4/d/VHa7Tfyipv2Mz1WycKtBA4+dYil/okspQwm0cRpFqqllKLX7aIsm6FyCQswtqIbDj4ZHNh+J+XCEN2lDqurXZ6+0CbSLUKjaXUdorTE3GwHk2q67S6tThFtFWl3Qty84ARVgsQDM0L9/P3o4TFCxyEqbKK1Dmm1lXDhxFPc96lPMFyp0u22uf76G5ia3sz83BLlUp7rr9nHtq1bUZbF/PwimzdNo+OUTqPBmRPHKRSLuI7LYm2FMM3MNM0oopyrDsyj2+mBBblcjpnzs6wur7DaXOXMsaM02m1EGRLXxlUWo1Ob+YbXvYnRkWFm5y7QWK2zfeduOlOTPPXYl5g5e47NO/dy4OWvII760UWDtsfAOdcgTVMKhQKVSoVCPo/vBfR6Ce2oR6xTbM/DKEHbCstxkMAjVoY46qG0zpRinPQvZsmOA6431m/PzptIkgixFdlOTWUrnyBHr6tZrp1heWWF+fk5lpdX6HR6uK5LGIaEUcy73vEW4sQByuTzF8+zG9IkWddRyE6nSy7n4zgOvbCHEkVb28y3E1rNFq2WjzIx3XaM7bgUq8PYlmLLtfsYGhlhtd7AUhBHMZXhKkEuR5ok2Zn1c6dZz29LGhFsr0xL+9RbXdBCmsRoDHEcAU7/JjDTv+1OYdbYjNM0xWiNY1nccOPNnOhVUFhoiXHWYa8vl4t0unUajVXa3RTfH6cXuth2JpwGQwo4voftegT5HLlcjjiOsWIbkRUMEZYds/3aMo4X02mFJGGXNB7cMZfJVGb3i+o12vVVhsZGs3hTA8p2soMtSuGobGWkgTgOOX3sCIcOHkeFDXaORuweE7qLQr6YRy83sdchrEkUUyh4TI1vZXhkCx+5+2M0W13CKOFVt70Mk8aIgdlz5zBpdoue1jFRHGbjybbpdENa7TZaGwLPJ+y0yedyLCwMfrDo1a94M2licVzOMLNykqPzIb04RwwoJ2W152T28zTlQtzAcQNwu2A0y3FIYXwCPTXE9kKB5MKjLBdHqK3UaFamaFzyF+kvDaUScoFQrRSJ4xDLsti9eyeNRgPLslheWe6bDod48smnKA9VKHnZmYJOp4Nt28RRtuiJ4hg38IiikLBnoazBzWaLS4uMToyThBFxEhMEPocfepAv/d1fkaQpJCmp1oRJSqkyQnW4iuVYpElMdXiYWq3O0vwCvXaH6R27KBQLtDttbjiwn3Nnz1+ZQB9XdXfExesqHd/DcvN4+QKr3VnmnjjM4tw89eUVbJ1d4iMIE2YC01ilZ4PK+dl5bMfBFQVJCiZTIPE6zmU9+ujj7Ni5jV6Uki8OUyiOkct5+L6DSJv9B4a57Y47iOOYTdOb0UnGPdWaMI4J/BJDW6sEXkAUhSRJwrmzJzhx7CDOOm7fsCyLJEmwrGyl8sTpk9x3zz00F5aoLy8SNesUSgUi7ZAv+4xOjpFP2ni2w8KFRUpDBcIwJEkyS2PYjWg5IbP3/wZ2vAhv/G8Dc9FJxPSum2gVc5xdikiTDlGiidMsysLTHrblopRFkkSEYUiUxDiOg+/7RFGIbdvk83l+9Ed+ko989hBHFjuklv1sbOYgsE2ArTS+32DT5gLKccHYlEsFZs7P41t5ysUiqYkxyiZKekios74JQ1LLcOL0PB3qOEUFEmEbh2G/Qq89+EonZyW0tYNjDMpLufcTf85b3vt+jLgoI+hOk/NP3M3W1/00jThERS5xZ5VTRw/ypS98idp8h0rOIu5prrt+K+3ZAIxLY3F2XYN9YnycYing3JmTxEmXRq3O5+79LE8/fpCP79nKwoUZNk+M88bXv4l2o0GzU0fHHWqNJrVmC9vOcfzkKY6dOMmNN1xLpVTGmIRvft2buOcLnx+Yh+/m+NGf/gVOnDmDZQOSp9cNMSS4Xp7VBRtjFEplvgBsn7j7JcKoR3VqJ1PyaoY2BfSWznNnaPHB08eQUomzxw+v6zAPaYfNUyP8+q/9R5qtLrbtPLtYOnLkCN1Om7jX4uMf+wRhFHHy1Ak+8P7vpNtsEcURzXYr2zUZQ2V0lPs//yDNZoNXv+U72LznZQPTyAUFom5EMV9k6+QU+XyRzuo8Ya9O4CiWG120EVzX5c//4iM8c+oM73jXN7J95y5c26FQLHHbK+8gTmIqQxXavQjLtlien8P3B/ddXJUSBvrB+4ZcPkeapogIC50GTR3hVIpE7S4JYFmKhfYqlm3j5gM8smOJlp05fMIwxLYs2r0eyTpOIfm+w/z8BXqpkCyuksoyvmeRCxSVchXHc2i2myilsC0bMYJt2eQCj1KlSJLExFH4/7H35rF+ptd93+d5nnf77dvdebkOlyGHs2g0m1ZLliwvkmXLcu3Ycuq0qNPCadqmaJu6QJLCSBG4gAOnKRzUaZHUcd04tmVbsrWOJtKMRqOZ0XCGywzncucledffvrz7+zz9473kSLYb/34uUv/DAxAgCYI4913Oe55zvguVSgMw1KpVPM/lzGsv4s1wVcIgwvMctLbyYiwttjZ3GO7sAnmXHgYxoeXRau3noz/5s3zr//41mnqH/p1L1GqPU6tVSeKQMMxxvqnOWF5dIunNZuxrKYVVgFKrQZRKkiQg1po4DbAsK0dKOAIpbIwxpFlGkiakaXqPhCNV3hUvzlk8/ehBJm/c5ko/F2GaNmKhsL0yLauAJUEKB61DhBT4QUB/0GdpucVoPEAKgzYpKEMYBvh+yCgYsr3TprRguH27R7FsyFKLZx78JJXC6tR5eJZgEmZoKZEClpfmKRQ9kkwjdEKSZchChTicYNkuutqgt73Bm2ffYG3tKlIplAJllxClRSo1m2zsMxLMNI6Ybzbz05Uw2MLQbDbxR0MqJRuv6NAoSKTf5+bmOl//+rOUSxb7VpfY7g5QlsOrr7zK7s4ujbkWKwtzLC8t0aiVsGyfdz16cuo8kiRhd2uDotI8/q6HePXcNVxLoo1AGYHIyAkUWYRJIUtiJt3b1KtF/J3LDEvLTMIxXaXZDMdk5TImi/FCf6YibAmbz/7uH1CvV1GWS6vVREqJUopbt27iTyaYNGU8HrOwsMD8/DyvnzlDMJ5ggCiJciSNlAwDnyRNCMOQMIpm4hq4npX3Fspm/6FDaAErK/tI4hSjM4RUaC3RElCSi+cvsLN+Fbfg4SiL+QOH+B/+wS9TazUplspEnQ5JkhCF0b/fcUQcRyhlASbvhi07l2/LMgr1CpM4QicpVrmAyTTaGGTBxXFdXNfNjxOeixSSNE3vXbQkSWYqwoNhF6kEmTFIq8jS/lWklDiOpFgu4Lq5oluhUEBJiST/IAgpMVISRQFmr/CAoD8YUa+3iMIE6cwynxbEYYyyNa7jsdvpEaYZ2B5WoYqRIi+CtQalWovRJGBh9TCu0uybK7C7s0OxXEEKxWg4IssSwmBCqbyfuH1llluDZ9m4BYeiKZPFIcNRGy0t3GKJIPLJRAYSpNREaUqcpOg0L/RJGueym5ZBWRZSh5zcV0CbFW692p5JyjLMMlQU4bklgiAlSw2W7dEo2YTdCf1xn3a/R6VYBAR2ZJGYhCAICIOIqzcv0x1vs3p6Hq8wwHZDLEdilETNIGWJ0VjCEGQCJSz2HdiPZVkMeh1KRZfS4lFWn/gJ+r2AqhflCIFvPs+Fs+fY3R4hLYsoS4lNCZ8atYpHd7e9pzU8/chqoVlnZd8KxYrHnVsbPHjiKO2dLZTSVGp1/M42lu1w7q3zhElE1BtTqlVRTgl/MqHb61KtlFleWeL4sQeolis06g3iVPPwIw9NncdoNCKJJywvzfHwqWO8dWmdwAiSDCQ6J08YgxAaEFhkHFpd5MFjR7i93SYMdxl3YqRd4GbkU4oi4jhDJYIZEHt4jsfly9dRSqNsi1KxxPz8PKdOnaLVaqKkJAxj5uYW8ApFFheXSLMMsSfyZZl3ngHPK7C8tEyv16NarWBZ038MhsMBtm1j2Q7JXiOZacEkzGUt8wZBo7XIr4kS3Fi/jVIKy7I58/ZlHn7X0/z0Z/5aPsaTil5vF9ux9sZ/08XMRXjkRzQ8gUxSKl6ZIJyQpDG2bVMp1UkqKYNuhzAMcm1cIaBU2sMVp5RrdZTrYtvePSqsMQZLKTxveobY+vp1lAVpmuLYNp1+SCrrFEp15uZiKuUi1YpHsRBh2zZKgL4ryo0kDEOSJMGYBK/gEoYhnTd2aS4eRsww36o3q6RJTBT4YDT9/pBMelhuGW/hKCbyycZ3kMpmoz3iC195gb//P/5DJuMJURRy8NA+jDFsjHxsx8EWFlobSgffS5JMLwwNcOnF30M+16bslvGeeoYwOkqj2iAZjfFk3oVJrUlNQBQl3N7YZDiaUCwWEVIw7PcoFAq4rsOg3SMaj+h1h7z927+NcQvAL0yVh9e+QwuPURhjSmWizJCRYDsuiwcW6ex0uNPeJEtjJOAVHaRlSNKYcrlKoeXx5Pc9QmUuojfsIk0ZrR2ee/lrHFk6yc996BenysMykpIF0ii2hhG1uUWSSYcXvvY5PvTDP86161v8zr/8QzZv7XLo6ANYBY+3X3+VIA7JUkmtNce+fSskqc9j7/s4vfVbfPYbXwGjZ2IQ/sxP/hhSSTJj2Ly9yZ31K1SrdfavLvPxj3yYhZ/9Oa5cushv/qv/g/e+572srV1ke3fCufMXqBYdHnn0FIcOH2ZzY4Oz588S+wGPP/YoXqWCY02PBtjd7ZKmIUdPnODQsZPYznP5Edp10FGAMSIn90iNFA5ZFvKJT36CUrnAwtYWf/Lls6hyRFdk6NENdtKM7zv5fp49fwl7hnfmX/3GP6LaanHl0kVMltJsNun3B1y8+DaDweAeHPLHf/zHac63OHPmJvPz88RSQRqBSRFCkmp48duv8uSTT/Dgg4/x2GNPI2dANrlugclkgqvzsWIYhJx56zpv3e6jpCFM0txkQHgcbrX4yA/9CP/Xv/k9dtsdHFeTpSm//mu/xlxzjk/8xCdwvHwRv3XjJkk6/fMxcxG2LIfxYEAwGhEhqTZz5fkoinCcAsVyhTgKUWjSOL9YBnAcB9excxqtkYC6N8aAvVnzDEcJPxhTKDg5UDyJaY9vcWfnGmEsKZcrVKpF6s0y5XIZz/OwpEAphVIS25KYvaO40QmVcpk0SzFpukdKmP4C6iwjSzVpkmLZCikVluORxRNUqQqVOax6C6vcwrJsjp84ntO9k5g4DhmNJxSLORpBWAq1N0e3lI1dmV7XGCBOU7wsRkcDzn/nBX5tcpu5egNtKVZWlzh05BDVconh2Gd7t80b587z5ltvU6lWKZdKhOMUpRQCaPtjkjAg9CMyy59JPzeMY3YdN1/KGk0qHQp2ERMLgjTFrZdRwHgyZDAagRIoD6LUZ35+gaJXAUsx2NZIsZ80AeUYFhb34zlzU+ehtEY4iqIn8IzELtQZ9sY40iIa+bzxyhkuvnmRLEwJJyOEbWMSnZPuhaFS8igVHJq1OjqMeOOVl0lTjY1CzYCnLBbL3Lq1zm6vx4vffpVJmLD/wEF2tjc59/qrrC7fJg4mVCsVbMtmMBjx1tpVHNdm/+oSc40and1tTh0/xuriAjrNSDQkI58kmp4kMRwM8AoeSZLS7fSZjCbo1KDTDGVE3jBpjdYxGk2mY44ff5Bi2eH6tUu45TJutUY8meDV6+xeucpXn/0KrcPHkOn0p9hRZ4tm2WGuWafTySnynueRJMneWCyHjRlj2N7eZnt7m3PnzlEul0mjgGa9hue5jCYB/dGEnZ0d6vU5ejsdrFEETKfoJqTKDQWEQGuN7ThsbW0zCiIqnr2nHS3I0hRfa8bBBNcyIAxxmiExtLu7nH3jdX7kUx9HALbjUKzUSGc4Oc5chG0hSaSgNx4y9EP2H3mAMAyJ4wipFAXPI6tUmGQJxs7JHZZl3ft11ypGZxla56DtJElyhMQM3UWWJSQpJGmKFJJytcSqk6KlplL2sG0PxylTqVRwHAdL5ow8KUCJDNctgDGIPbsfhMBSkjfPvcYMJxoEgl6vgxISr9Ck3R2AtNDGoBwXbA9BFZRicWWOZ55+AoFBqZxKPB5OUCrnw9drVZI4JQhD4ihAFabXBQCwozHpqEdgIBSGr2/exEUgLIXr2RSLBYpujsse+wGTSUAaxwxsGzB4ytljMAIq1wXRWrJiKSazjAEaCwTjPk6YYSUOpZIkiRImGjzHAZGTFdIg13QIgwBbWLQWFlHSJQoNqUjQUqBcF+1HlBMJuzGdZHomksRQKClMxaYYJQw728iSzcqBfVy7cYWXvvUCyWRCuVAGY4jDAEM+rsowLMy3WJpvsjBf59k//jwXX3kFF52LvM8wsRJSYdkOb15cYxKl7LbbvP32RR46cZwwzRj0u0idMh77DEdDtrZ3sB3F8vICjzxyigOr+9jY3uID73kG17HpDUZ0hyNa9RbV8vSi7qNhh8X5JtduE1rJhgAAIABJREFUXOf4g8fp7m7nP69RGDJs285PjbaDEAkmS+l3h8zPH6XoVZn0L+CPuiRRTBbsopSg2aiz2iwRB9M3UA8cXGV7e4tiocBg7DMcDkmSBCEE1WqVNE1J05Tr169TLpfZ2Nh4Z3RpNJMwIjUGy3HY3b3BlStXaTR6bO3+BnahyM9+8ulpbwyIPVKTpdBZgtAGgSTSgswIjMwp+1vtHp//w89hO1Aplxn6Ecq2iKOQs2fP5Po3maZaq+G3FvPF55QxeydsIBKSlUOHOFIos729fa+jzTKNpQTFQoFk4pCSYdtOzhJTCkzO/DHkL1+yZ5zoODa2Zc2k1JUmgmLRzQGWVoFKoUq97CFth2KxiOdZeJ7EtiVK5rY1UuTed4k2VAoOQgiiMIQsQlkWwXhCd3cD155+CTUZ+9jKxisU0GgePv0gmzu7FEpzbA5BIxFSoJTF/PwCruMwHvu4nkeFGrs723S7XSrVCs1WE20ybMtmPB7jzFiEP3r6Yd5bOYoxuViObdm52Iu9RwnfWyjpbE8VzRiUspEit/JJTHYPQ2yUjSE/pllZwrVg+i9TEku8+QcYjrYpKI0ej8Et4Fk2lsw94xINrusxN2fRH/WoN+ex3RJRGOSym46N1inNIMbRMV6UEdo2m7vT9+RVNyNNEoqBQ0PBs7/0HyCFxFYOUZTyjIFgSdAxMR3hcWcMUsQUpWCxVSe89DqXz4+5YWlIMg4UNFJkFAB3Bi2Nra0NhpMRP/zDH6M5P8fvf+5LTPwJL778KpeuXufxRx7F930u37jBpds3kY7ib/31z3B09QC2srh67SYH9x3AKIsr1zawLUm1UmLY2yGwpn+FDx/cz9/+T3+eOAoZDIf8nf/i5/D9gOFgyPrtbcbjMZOxT3u3Txj6xGnCWxfOs7uzw/lzbzLcvUIwGWO04NTDpzh25CBzc/OsLrVm+ii9+sYFlHrHL7BSqex9/A1zrRbs1YUsyxgOhxw7dhRjeMdolbtwVsHjjz8O5H6Efm8H056hA7Wsveddk2Yp/nDEkeMP8lM/8zeQyqLgFUiSmIMHDlCpVNi4vcm3X3mRMMzHeUsLSxidsr29jVsoIVSE0YaDh4/MhPGfnbYsJY7lEcURgQnvQdaUUrC36LKEwZIKPw4AQbFYvDcw1zr/9yJLMKmFZVu5c0KSImZACguhMFqilAvCIY0zlJchiMEokiQFyyUxgEnB5Fv/KAxJkwzHcpBKMRmPciypbZNEAUan6GwGhSwlc3lBZSGkTavZpFwqEXd2kXYxXwoKhes63Nnc4eXvvMETj5+mWmuQpjllOKcWS/xJQBhGZJkmy2LSdDbGXDC3yu2lGg6SxAhs28YIiEy+1DDsaUnsPcVaazRWXpz3iBp5GLK90ZCUEhFHdIbTIzXqlRLjvcWcZ0tSJUl0RtVRmCDOkRk6f6lSrXGdAlrny1lpK6IkwQQ5bnOUWCRhvDeiGaGd6a9JwXPQRiESH8fJKEsbowWZ1DjGYLSmZDRZ5hOGMS0t8GxDUQnc/pCSiXGEwdL5Jl4qjSXBQ6BmEPBxHJelxSWkELz/6fdw5cpN7mxt0u32ubW5wWA4wJIKaSn2Ly9z+sHjLM0vUCwUCSY+Dxw7zJ2tXW7euMPC3FxO1hCGgSBvIqaMsR/jKYXjFllcrLB88EAuyKk1o0lAFIUEk4Dd7Wv0eyG9UcT162tsbNykvbtJqWhRcKpIJGkS4bl1Go0qrfmlPSLQlHmM813H3QKoM50vOk1uvnm3wN6l3d8t0JBDWe96/u0NMoGcJ2BjIWfAb989pRujERJq9To//fM/h1I2lp2f3KUQ+a7GskBrep2/QRiE+Yi1UMAIQWdzGz8M2ftSIGz7nkrnVHn8/+Fqej/ux/24H/fjz4+/vDfI/bgf9+N+3I//z3G/CN+P+3E/7sdfYdwvwvfjftyP+/FXGPeL8P24H/fjfvwVxszoiN2br5ve+hmWjn4Qu9Sge+NlkqCDDidkTpXKwlG8yjzZ4AbK9qisPIpySt/zf2RZSqe9Q3vjIi985Xf4zivPEUx8dKb57a9uTbXf/PQP/pip1xtIKbh06RLVRp0wjImiFCkshMg3qkmSkiQJlqVymnOWoaQk0ymOY3PixAneeusttNEkOsaQIz1efu07U+Wxb3nJOK5GyyHNxZRblxUmNhQbNlGyRL3U4eiK4c0bKbFvkxqHVAuyNFeDWmrkAPTBOARl4xULOZoDm0qryYWz56fe9/760hFjMo2j7Hvc+rvb5lSA0AYHSSoVickZP+Of+RTVlVWMTsni3KkkSWJG4zFpYtAGhqMh1fkWv/JP/uepcvmF//4z5oXXXsMpCso1h+MnVxgnY4JggmNbDHtDmq0yBbfMsBdSKluMRh3K5VxJbefOhO07E4LAILTAn+TaF0EwYU5VuHxud6o8PvbJkyYIMlS1Qmtpjp1hh9RPKBbK+P0tsA2WMvRuZFi2Q2Nljv2PP4ylSlSay+gkYnvjbRI/JIoE0aRPlASoUkCh0OBL/8tzU+WRmcwYo/+UroHgu3UDDe9Yu//p/9QYUHt61WE0oT/aJE4iev0tbt54hU/+8C9Nlcetq9tG6zSXztSGTmfA229cYP2Ns9jSxrUET33/Bzh/5gzj8QinVODxD7yf8txcLvY0CRgPBzSac9y4ep2VI4dJspQbz77I5sY6f/e3/slUeYzBJOkemGAPPan3PCbFHrN1t9Plv/tv/jMW56scOPgAv/iL/y3cc83Qe/Kr5Kiqu9IHJsOWFg3HnvadMXedfd68fIPXXruAyVzm5/Zxc/02QRAShD79dpvd3V36/R6f/vTH+cGPPcn8XHMaLPBUecxchKVycNwCluuhbBfLssikQjouOAUsp4iyPVAWSqh/J+wsV2N7RxRoFqRGo1aiVPS4euUanuMiMQijKbgWlrLJslwmUwJKgLIkUgmSJC/OBdfF8xzauxs0amWCMEYIF03OEZ82ojDCZCmqkpGmEstRlKoSP5BoEzOeZFy+ERMFIFUBZSBKcm5+7l4BRlhI5WJIsEWEsiDOLEw6vU/V3esnxR7zSQgsBHLvsCMBofK/i4BIZ2BJ7FubuA8cIwkDUpFrfWRG5iB+cgcQo81MgiST8RjPCFwbCpYkCzWhn2JbBUadEe3NCUQutowoFAQiTRhs2AyMT5KmtDd9wolAa0FjoUGWDJiMJyQTEOXpH1kpBGXPyWF6sU/QHRN0AvrpgFJNYNsgHYNXryBdiyDyqVbmSFJB4I8p2nW21q+SRuCYmEQC0iYcxuhgZ+o8RqPunlDUO5Ej1+8eRQViDzWbe+AJjE73YIUCSypG4z7Pv/BF3v/+j3Br8ztUy6usXf4Ttu9ML5kIufCWJXJBo2LFY/+Jw9QX5rl28TrRsMdGp0P3ynV0tUh1cYFvfvlZlo4dZfngKlmSUqnX6HQ7XD9/kV57QG2+hViao2xPDx3889/yd965wPfZ3d3hQx/8ARbmmpTKRdI0+TO6EH9W/nZW4/v8WgdBzFsXr9JoLSBFCUt5GClRjoNII6I0YhL6DCdjzpw9R2u+wPve+25qlSJyFkzc/0vMricsFcp2QFr3QNVS5aBnLSVCWkhpo9kjB/yFFODceHHWC9ioVxiPQ5I4olgqM9zDHiql0Fqgda4PK6XIySKWvPfVhfyxbzRqpFlAlgmUVLlTqzHIGeguqZYoDZaSxHGCFpIgttCZi1QpmdEMffAThTD5KxcnGQKJZdl70sUKYSkMCqQBk5LGESKdTUWNPe8xbQxKSSwj8yIs8oIkpcRg8IxAqFyEP7yxThLFGKnQQqFl9mfo40LJmdSpPFuRphorUQjjsnlnxHgc4hUcwsjHsjwm44TuRgclQ6oNidAlOu3BHoMyo1woIQRIJXOpTdeBKM5tfqYMt1SmvzvCziJUWREPQ3SckaWCGInMJCYVFGoFJoMAQ0KWJOhUMhn2yNzc+Xc0DHnwxHEm0kPrjM21c2Te9Hl85Rv/Jz/x8f+Ku4L6eZg/1QfnkWYxApXLitoeyIwbVy/yG//7P+X551/gj//kSVy7yO07X8e2WgTx9EU4CAKUEmQ6Pw2O+wMuvPE6zVqTx596BKEsbq3f4PZ3XuGmNNS3HqHRquL0hyh7lziJSeY0WZrQmG+hhMGSMP/gYfbb0ztJvBN/tjYkqWY4nuA4Dh/92CcoOEVcj+95J7/7tHD3Wc3h73fPE9OHANbWrnHz5gZLK8vUax5jf4BQmsgPSLKQwXgHaacoO6M/7LK12+U7Zy7wwfc+jm19r4ZxLoA0Wy37S4i6i1yYR1ooaaFNtndBJAhJmsYEkxHuvzOPveItBFpnOVgaZpSh81hbu0ahWGRhYQnZHSEEOe1SSeIkolwuYwwEgY82KXPzue7AcDQiDnM1uEcefTdra5cZD0McxwIF42AGR1837xqDSYFifYE0GRD6GUYEFKwMy4ZYS4peGa0Vk4mP1hlIF2G59Me5tY9TcEnSAqEWJGlE2Qsp2LMoNkCcpURKYgsoI3J3EymRQmC0wBiBFiCNzgkywiBcRWoyTAaZTtAmI0lT0r0TSpplKMeZyTbmxJH94KQEQcJjj51mrmrjGhhHCbthB4nEZBFxHBEkuSN0FPm43nGkEKQmQ6SSJE6ozs3Ta3fxbIf1jQ6dq4Op83CKJQbDbaymizvRxO2MuRNzGJERxSHZxJAKi8aChbQt/E7G+o23yHRKf32AtoZ4hYj9h48i5peg3yWKR1iOg3GmPxmcef1lfuyHUtQeYQbu8Q2+KwxB4LO29hrPfe1LbG9u8iOf+ARxJPjHv/orYAxzLcW/+fzfwpIBnlXl9voIt7Bv6jz6Fy7j1UpUDuwDATt3NliqL1Asljl/5g22eztce/0t/ut/9AHWbpX5/IsbPPOhH+LyjSu8+eKrfPulb7Bv3woP7D/A8tICzcUW42xMISyxsDi9zkkuqq+BuwQhAeRaEUM/ItZg2R5xmmFEBJZFxYDaU67T4ruKMLmYkkGgTbrX0E2r5Wvodoa8/dZN/GHMB37y3Tiuw/lzF7l9K2LcHxNGQ95+6zUc26FSqYHJePnVNxgOh5w8eoDl5cV7ZBKBmL0Z5y/jtpzF6DQhyxKEzkjikCQMECZDa4ssTbBcsWcOaf7cEcM9F+C7RXcGWcC7USlXsZTFoYNHGI4nLO1bxXFy9+bxuMt8uYUSAoHGnwgycmZatVJhaWGOYX+I6zmE/gShNa1GA6UMYRyh0+n5+JbIyCSMBxFZGhH7em+WalhoeqRpTIJG6xQhcwlQmVODEIhcNFoKpDK5noawsC2J6zlkUz9MeQiZs/fyrvounyhn8bA3VkiUwLJzm8rEUgSjHubWOu7yClkaMx5PmEwCLKXItCHbY4vNQkWqtWrsd5pkUUyWtLlxsU3Vtcmk5MjJA0R7Gq3aDjFagJAM+zE6A9/3iYJRzkK0LMZhRH88oVmzOXJyPw17elF3q+jhFSx0khK2M0qWQ71Ug5Jh49JNHFmgUq9SKFYIfEN1scLhE08yGt5hYdHl1tvP45UVhUaR1YOnebv/dSxXU6i3QLanzuPmnW0Gw12a9aV7rCqDyRli994BwdpbL/GP/+k/48yZC/zA97+Pb730Ku07t0h0hhKSYh3u3GkjtGBlXmPbRdzi9EX40hf+iEMPP0axVmMsBJvX13G8InEcod++yILrELkCK7xFo3qA73/yEfqDIcVSlTCIuX7zBq7nsDK3QHunTRLHzM3Pc2D5IINhGzg6dS7fHcbk18Jgcov7TKPTDJPlIkKJ0FDJkCLbe67fKVtSp6AzMpHr0qQzuC2Dod3uMugPKXolTJZSLVd47LGTXLywjU4EZJKFuXna7S7SKNo7beb3rXD23AUaBcFnPvPTGCTWHn38L0N+m7kIZ0lIMOmTJgHCKRH5I2J/iC3BiFJuEWNMvuhJ89nW3cTeUUzLB/HfdS3+9G/+wjh58iGe+9o38bwijz7+BNe3Ojz68OM0mg0uX36DR089yHg05Pqlt3AsRbm5wNqV6zzz1JNUii7+JKDX7/DSt5/n5InjPPTQY2Q6Yntrh8l4eipoGAQY2yGJU8Cg07zrFELgFCS2tgmGCSaKMFY+rjE6zQuxMSjbwghBnOaG8JZS6Ezg2Arbmf5jAOBaNmQGKRSZEWg0wuR+fgC+zBgvlkms3N9vHEeEaUT8whepHD2Js3wQbQSFQpEoCslMPrKwLQszg5NEz+8TxAN6525zZP4QN1+5TrXoEcUBy8KmtNRE1Wt0rSgXERcpzX1ljFE0sgqRbkCSPyvd/hDhtTBpRnu4je9PTxeOooT5ag03iOmlCfVj8xTqHuiUtrFxtKHoJ2RFhY5g+eAKlm2wPYmSRSq1JZxajVJ1niSJOHj0ISbjNpvDK+zcnv4ZiWPDm5de4j3v/kSuaf3nFQoh+MqzX+bZr76E67qkacylN88RRRFCQLlmsXqwRLe7S71aY9BPsT3F0sKhqfN4vXyHybCKftOj1FimVWtw/JHTRDrmjUtnGI2HNJoWURDiyTuopEXCANtWPPX0Yywul9i/uo+DqysoW+C6Fp1Om1G4SbfT5j1MbzoKfM8+KP9z3rwgQCgHgyExJtcPljZGZpi9umG0RhuwTYIkI1G535xVmmdh6tdG0un36I+6jP2Uz/7+5zh0eD/1egPHM1RqLmmm+chHf4gsMxS8Ep5XRrk2URiihebVM5dxXCiVXZrNOnOtJgq9119O90GYuQj7fkh/MGAxiRFxzGB3kzjo4xXLSMqUlYVUinC0jR8Lru2mbHTzo+f6jXU2N7d44onHePLJx0ni3GJHG7GnQTF9EX7syffy9375IM899w3Ovfk2Z984w8vfeB6v4HHswUNUKnVqtQq/89nPs7y0wGg84fiph/ncF7/KYDwhjg2nHzrJT/1H/zn93ogHjz9EGvncvnWdb3zjuanziFKDkgbH3hOpl3sOFsYwnGjqJYlJC0jXxRiB40nsOMOxBZ4ncR3wI0kYG2yZ4AcTLEtAKpFy+iMvAKkmTHMfN0cqsCWkGqEN2w+U2I1SUjPAzgDHUGjWKNqCNIyJNi5SWlxEtZYZDEZEUYgQCntPPU3OMCqKh2P64z71lTnU7Qgrsthu91ldWSK6rilvD8hUj+YTh7DqZbQQOEND3J2QjlKyoosuCmIvxSvUiYo1kiwlNAm3/c2p85i0d2mVWvSDHoU5m8XVfURbbYLtHR6URdI4YQ6X67eHnDp+ikNPfZgw2kYOt7l8/RzN+aMo16VSXSDxU4wpI5UkSs5iZtBKSLOYLzz7L9DG8H1P/yTGfK+Eax4Z1y+v8QMfeRcCOLh/gX97dY1JEOF6kgcfLaCFpFl+jIpXIfF3aFUfolKe3vi0dmCet/pXOHvxIsIIgo5D8txncxuyWogouJx++EFeHS8idUpWV7x95SU8TyFMwEQaruzc4mZXoTyX2GR7J94Md4Y9ikADab6a1MDeHiPVhl5vyPbmDpvtCWfP5UI/5XKJD77nUfYtNZlr1Pnac8/SKjooy+PJJx7iX//mv+Db5y+x3u3htx7htX/+P02dSZpafPgjH6NQKGDZKj/hS0GpsoRSNsWSS61ic/78Bfr9EadOnkZnCes3b7Gz3eH82WskiUApSavVIk3f4Gc/82FmaShnLsLKdigUPJRdwHZcHK8AOs41dE2+EMMYPvull3ju+de4ujGgM8xFadI4xh9POPLAIf7m3/x5nnj4AHESY/SefOIsAxVLcuTYA9QaTWq1Kr/4C/8xOoto1pp8+Utf5g8+90XSNKFe9mg0m4zHAa5b5PDRAxw4/AD79h1FKUWp5FCtG7Rw0SRcvXGdb357et8u6bhIJXGki4ny7tZIgck0IslQseTgAYVSHku1IhevjghihyQxZDojy/IxScGFLDFIMixpaNi5e/IsYTBYJhdFSQwIqbGNIrQ0oZuQjAJGaUbJ9ahUSrQWWrTqBVI/xNeSm1t3UHaZJIixlEKYXHWOPZW1aSONYqQxGGE48vDDvLl2jXZvCNJiYaHE4twhVGrw+jbS5OI+7iSlt7ZO3B+yuP8wpuFhrdboOAlpkn+os2hCFk+PGJkrNBle2sb2LOxGic71O3j9MTXHxY8j7JKHvbzEk/X3Ut63n0Z9lWhcY+HwQRbnQl554/MYHWMrBU6ZTncTp1AlHY8oVkp/cQJ3r0eW0O+NefPi85w48giLc0f+nKGw5MSJ47S7fTqdNhfefJPd3pBapcTRBytkGtrtHvMLSxSac2Akl6+9jJI+8NenykNKyUK9gdaaOI6ZiAhpiriew+3OiMlwwtWbV6mUPFyniAi6eXFMIzqdPjvjiEa1SLPqUbNtLEuRGQNGzNRAoVNEmpAZMPId9I7JMqRwaFSqhLFiaWEBx3ORlsBxHUqFIq7t8Udf+DwPlDP8QLC29aN86/UbrG/v0qwqJMHUaRgDt29vonWXTMd4no0ho1yporVNvV6n4Nl4rsXJB48xHI6QJOxbnmPS7/Kt57/BaByQJIb+YMwT7343P/LDH8QYwSy7udlV1IzGchws20EpgVECLJkvV/aE0UfDPr/6G5/jztYOCIHrehh9F4hj2NnZ4ewbZ3n36X2kSUSOkJjNtwuVYGUp1TIIFfMzP/UpnvvKHyLTDo6wCLWPMpooSnh77Qof/tBH+OiHfoA4STh88DBepUwQxxQ8B69oYyvF1bd38AoGI6d/0aXMfyoEuLaNznIr90rJxVWS1f0tKksSValzrFohTFNu31EkUYTONbRxJNi2JBUKu6hwLUOrlNCe4egN4FkWfpLt4YMlBalQUjJZ9IjDEY6naLklik4Jz3OpVmsoK6bSLBN2ffzuDoXKPE6xSZroXOQ+SdGofEY7ZRSLRfyBj2db1JeWCfUEWZe4lSKZ1sSuixEparOL2pW4BQ/XSTFxh35vk6OHjhKMY/QWZAcsMmXQAorawZrh6T7p1entt+n2u+AnWKmiXivTqJbZ6PYptlbYf+JHWTzwbiq1OWqNYm5pI+wcR9ve5cqlLxL1NvCFBygm/R6GDCud/tXROqNW99jYuMI3XvwtfvpT/+DPvKhZllKtV3n70hXqjTprr17FdRyklJSqNlFs02qVWZk/yG57jVqpSTAYcOPGS1PnkaYJJcvFCIXlSOymxJIeKMEiC4RZgtCCfhgQ9xOiUZ8o8unttBmHivryfoSwMMbCkOIpizjTGPKOeNpIEgcVhcS2IjYGf/c2JhxTshXBMKHT6fL62jpf/OpL+JOY0WTEX/v0R/j0Jz/KOMwdQAwxqRD8r7/5NcJeF+mWyQa3sSvXps4D4NLaNYrFFnE6RimQSmDbDlIVWFpaoFhyCSNBuVKgXPbY3tzGZAnFgs3Xn3uWSq3EyuoCa2tvcfz4MpVqgVm3czMX4d/73d9CWQ77b/wGURLTGcQ59En0mExCam9e4d++cIbbm5s4jk2pWCKKYmzXoVwucujQKp/61I/yoe/7ADs338QQYDkWQegzw33kl/7Lv4+XQZjEjKOQRrXIQmmB+UaZm9duMRgngERrzcLCAr1eh4tr59ne2ubzf/xZ6vUl5heWqTeqdDrbRJHPQr3ExYuXaBSmd2+olFz80RB0LhB/YNlmEjhEsaA9iFiNPBZFjWbgc10FqP0l9rsFgtBjc3fA9saYZt3Gs11QKWmmkcrw5p0R7clsN9P5e7/C4B/+HcqWxHEctlYKjJMI25Psbx2i0Gwx6vUI05T9+xcpV5somZEORhD1WLUCbr78JXpBQus9H6HaXMZTFUBhOtNDoSbRhOJClbq3iEJTPF3m4LFFOq9ucmTlKezYUHQF61fOY7mKWnOO8r5Fql4JsXiAt+68Ta1Wp+UsUuxN0EVFbEAnDp6eflk5X6hClLJQ3EejXgVjKJWLKAPqxA9y5IkfZDyZkPhdrLJNSViMIxvXAaEMn/zoL7B26GG+/LV/htVQBJNd+v0xgR9j4uln5GkUsXZph3q1xGj4EseOPMe7Hvn+72k6tDbcvnMTz7O5c3sDIS08W3Di2AGWlk/wnqd/kJ2tm6ysHOP5F3+L3u4thCigs8rUeShj2B52EBHYXg4j1WaUy0mKEiaz6PWHnD9zi+3tHQa9Acq2se0STqnJI80qO9s+kwE0qykmzeGIUaxnKjvbO6/zS3/7P8ESkoLjMNq8Thj4HH34afY9/CTohGoc8f7VkPEoZjAOKO2+xNXnLhNnikG3z/XeLjv+hI3wNEJohBQE7SHNeHpLMCFgPBmgVAHLsXEchTEZSZwwmXRI4yH9zg4f/MBTWA2bMAqxpGJ9/Ra1Wp1jx44ihIUyBd739Mco2C3++I++wRNPPcDT73l8aoPy2Ttht4awLe4MDVK4yIJLDjmDslvBj2ISFI1GjYdOHePE8cOgNZVKhaWFBSrlIpDw+ivfZDTskZgqSarIMj2TWaBwC3R3e2jAOEX6gSIJQrRR7HZ7JJlE6xRjLDa3thgMBmxs3iEIAoQQFLwSjuth24o48cmyBCUNhjLSmf6yGJ13sXGSYrSgUMphbkE3xZYW19a7tOaamKpHq1RjkGyRWQlCWwwHEzIDw3GIbdskcYayDEJBz89w3ek99wCyh5+i50kmZUG17mJ5AhOnpCl4xQIlr0Dq+DilEmEUUtAZrmMRG40SmqInWKgXsI3h5qVLnHx8EaNSNtpbdG6tTZ1HsVxEakjMhIk/pHW8Qbbs0Xx/lex2xtgP8ccTwolPIVYkcky2PE+YJaQmpeR4tHc69PtDquUFYmGjLQeRmZnGEUuLi9hekZLjYjsWljQYNDdvbbDvyfcx8QPiIECbgJ3dNn6Q0Gg2SbCxlCFOFccOPETvyBN8a/0rjMMJpVoFfwj1lSPTX49ikYmv8GyBJTSXr57l4VPvx7KcvdFhvkxVyiFOEsI4RGtNpVrm+MkjPPbE91Mo1LHsq0TRgOXFB7AFSBVTr09XZ2hmAAAgAElEQVQPHTSZII4149sjFg42iE2OrlXKwZ9ILpy9wY0bN+l3x3ta0xIlBIWCR3N+gfb2VRwRcuSho0iR097Cuy4XM8zIz3/ndR5+1/tJ/Ak2hrVQoGopstRka2sdkUyIAk13t0cURQwGPS5euIHfabGwskqSxHi1Kg23DD0woUaiEFTph7OhE77whc/x8Y9/moWFfUiZY+lt2+LXf/2fc/r0I3zwAz/AhXNrOG7ufrOzs4Xnusy1Qp56+n0YbYH2SNOUKIpo73Z5/fUxTz/zLqbtiGcuwufOvoxt2cg9mJmQe1wfIfYwf5KSm1FwbepVl2pR4HlO7s2U9knDiDTT9Doxg36brds3GY36CCPuGXFOEzpJmUQJ2oCVQqxBO1CLAyJhgwJtUhKdIZP4nolooVAgjhOEhCyLSZIM13UoeB4Hlue5ebubs/+mjHGQLxgKRYeiI9jYiTBGgDFkKPzxgJ2dPl6lQVnBA4tLbKqbGBNi0hTbcojTjDhLEEaAUZg0w3UV2QymhQC2W4L5Gv3eJqlvaFkVlKXICkVik2FLQ6laIpEW9aqF69n44zGjyRitDbYtKJddkhRqlsU4gmpBMWy32elMj53O2GMpChhkitpcE2k5sOgSXR3juor+cEAQ5d5mURAR+j5RmtAdDti/Umfit0nGY5ywgVaQEqNsG2VN33Ntbm2yb/kQlmsziXwW5pusb+7g1JcQ0iEatJn4EUtzZaLQZ4TORfilob19k+VDp9nfqPPTD/046ztr3Mo2UcUi8wvLrD5wYvobI0KC2OD4HsJ4fOuV55ifX+H9T38adQ91InLn8jDIjRMci4X5GivLS/ijLjoNKRRbPP/Cv8S2G6TRHeqNZa5demvqNOI4I/AjlHYIJhOwK6QpDPs+r712kYkfMhoG2OU5Tpw4iTARN6+tYTIY7Gzw+KOHOXb4Acolm8FojC0zpGUhpUUaTb9E/uzv/GtOnz7F4upBqrUGK6eewXE84nGbF1/8Io4wBGFGt7vLeDyiNxgxsCRpFIJdoLtxm6znEBqBE1qIVKOiiKzQILHs6e8LkGYRhhSp5B5nARApnd4WFy5oDh86gWd7NBo1ms05Dh16IHeGiVNWVg/RbXfptrtcv3GZXr+L63rsP/SevR3Kv6cifOPia3mxkLl1T5rlZAWp1J4KviZLDXNVydb6Oouu5o3rNwijiDgzSCU4sFjl+JEjHDl0mt7ti0gg07M52AZBF8fL0EYRB33cSok4idnY7FOqNFBpysSfkGUZmdZMfB/PdXMjSyHw/SFC5Aw7qQyYGEGCyULau9NjQNMkxXUV0kh6vZgo1iwu1FlYKPH2tS2UZXFr/RYrR6p881KXolvioaNLBNWMx584wu/9zhUef3qRzmTM+qXcEXc0yUBDvT6bvlLvxT+gevwR9Es3SEYw/8AKSllMxhEvePN8aDSkWirihwlXL+/iFnvILGPQ7lIre4wHEXdGCU6hAM1D+LVlRuGE2kKTK+vTz9rqXhFlWtiqyNru65QXG9iRpuQ6dN0t5lIHLeHWwEfpmNpowo1gxPpgTKolW701Rirj9COPcGvQp27XMFKTGJ8onkydx+EHTqGUIoh8yKAzCHClonHoJP3BDv1uh8lkxL6Fk3R275BmhkFlh+GgT2f3Dh9eeIS5tR5hzWbZXeLGtcvcPneZ0z/ySaJw+o/B2sUR73/wMU4cWeULZ76NH2ouvPkS1XKdU6c+jOM4YDSW4zG/uMjw2g2qtQofeN8TbG9e5Lmvf4FSOaFSW+Tm9Q2S9CLagGtt0GhO/wqHccZkN2b9VsQzB97N7//uV0nTjDSNwbJxbZuluXmk0GTDO1i24oNPn2Z1ZZVaucxkPCKKI9Yu3yEVY0qlu0v6GGuGU9viXIP9czUqFYvUtPnil1/i2rVtmvUCrhoitCQMI27duE0YpEyCBFsqglEf1zX8yt/9D1GOR7vb55d/9ffIRInjh/bzo88s8fy3vzN1HgCPnHqYNEi4cPYMTz71HlzHI81iHjr+KKcfeoRra2+TBbC4uEwSal597RvYVpF9+1b5zd/639jevYOQitWVFWqVCidOnOKZZ574HhbdXxQzF+E3r+eFVgiFNpBqjdYJQuSVXylFteTRrEgmUch2u4dbLDIKMoLEULJslFNhfn6BndtXGA669/CCsyzmatV5ojBDSgtTzsgslzQcUnLgZncDhEBZKndR3qMS5hb3Bsdx9uxUUrSR6CClVilz8OAq2+0R0pv+a2qMRqGIY40fZdhKgE5Zmityp9dEZSGn91dJBiOEzijP/z/svWm0pdlZ3/fb737n857pzvdW1a3h3pp7ntTqbrUky4DAgIIIyDFDMEkEjhcE/CVxAMdZdlbADrBI1srwIcbYOCgB2bAYhCYkNUhqdavVXT1Udc3Tne8983nPO+698+HcakngxOcKe/Glng9VtWrdOvep9+732c9+9n8QnDl5lq9duIGWGYeXQ8KKQDuS26Ygy0ssC1xh3sFEThreaI18NKASeSAclNJ4ocNs6KHCgJ3S4KdDwrBOZ6fF1YvXma5GUGa0jUV66n3oVo/W7jb59DEsI6jUGrzwyRfpDiYvflI62KlNnAzwagKVpxghMSamsjRNcq3N1dsbrA2H6Dymnqfkwzb+oTmWFo6x+dKbRCuLLC4fYafTYZCOxkdez0KryZestARJWjCIU8osYbpepZQVymgWnaWUeYIwJf3eHp3W7j5ppE2pSgI/4Ctvv84Tc6vUp6vMinkiewbHHVCLQkaDydmMwmie+eD7mZpqUr3yNkLG3Lj9NlevXuY//RFYXX2am9dfww88PM9FlYZKzac500S4KSdWttjZE3T3djFklIVHaUqqFUWcTE5ttzQszs6Qj1JaW20ePHsSQ4lWigKB5zgEwsINHKJqRD2KqNYCjBJkSUKn1+fG7Vts72yzdHQKYVsgFaHlju3EJowLF97g+qVLPProSY4en6cYdunvbkIRMFVXCC1JRzlJkpNkhqIEy4I80wgtqboB0raRlQArbWEHhtbWDc6fe5ZDy/MT5wFw9OgytWqdza113njtFRYXD9GcaqC1YXdnl8D3ybKc4XBIr99nbm6O1l4f13Wp1+ssH1vk4Uce47lnnqEaVvjDP/wEByXOHbgIp9n4KI/RKD12aBVGocoSYcGhuSmWpkN299qMMs3WrmT58DTztgtCMFV1UFpz9dYddrfvkObJO2OIg3TCljPFqNfBsiS+G1D0c5r1Ko+eP8ZWq8tau0OejJCWhTAaS4xpknmejX8vUiwpEFKQxiMcW3J3bZuyLA6EibVtOVYeywukNFQDG1RKu9Xj6Xed4+S0wdUx/9dnb9CYqzMfhVx8a5MjC9NsdFosH6pg8gLPsdFmhDWWeqAeOQfyywJYMHt86e3XOVR1cSs1siyjGlWpVOscKftshU1OFhDHCekwRmJQpkRbNu3mGZyj7yY4Cl6SoPo9wMWPKvz4j/4IX/ryVybOYxiPyIoS23VRqsT1bGzLplQJwyxh2GlT+i4nnnoQNzKkw5hqLWLq6CKeCdh++TKeH1EqmArqlMJQSNjeazEaTv6yJ1mGKkq01kzPzoMAJ2xg+REq7lAWOUYV5FlGnqUYA+1Oi7AaITyfm2WHmemCE/WcL9z4LIlImZpuUikszp95ePLnMSqYbjTod7s0qlUGaUy7nVGUNi9f+BQvv/IFimydirsCusTzXDzHptW5zjDdIYxWcIcdtjcuUWJIshJhGSzbodue/CJFK4304N3vOoMjPZIkR2kzJljdIxAbhTb3YGMWKlMoLUiynNfefJ12r0sUhRgNWhmMsbAsByEmz0MITZIOeOOtt7h84xKX3tyk207BKKq+jSlysjglSzWZEigtcNj3hHN8Ou0hwihsoTi8UKWbW5Rlwl4cE1Ymn5EDVCohruugVUartUW3s0dUjWg2G5w/f5atjW2azTqVSohj21QqFWrVKbIs4/DhI3z0J3+cJ558nMDz2FhbJ89TpORgaNsDZQzY/r49vDUu957v4TouxggcHSNUzm6rIC00pYZRWmBUQc0VzDYq2IFNri3KUhMXcnwZZ8S+otrkRbgR9rix9xpRFDHbWKS9s0W91uRLr1wiy8YXBVIItFIIa2zqqPT+ZiHMWIjIMhRxh7zUtI3h8o07IKA8AI26VBpFicHQCG2kgNZQs9vfwb2T8YIsiOMRwhL0hlDzAz70wcPsdWJqOuLmcAdfWOTB+ATRdYZopekPCzz7YDjhw9UqzzzzMFEtQKiE9toWRZIjG4L3VQJe9au8WZml8ulPMlWLaDZqFFGF3uH34VZPY9kG4TjYoWJ5dol+r093r4XRHf6zn/mJifNwPZcYC8pxV9xpdamHEUVuqNgWKhTMnT5C0w0IlioYA8OywAogHrSRFY9XX3qVSlRDeAW1pYA8TZn2amRicsv7fn+IkDaz8wt41TpZZ51eakgLi3g4BFPSae2wtDBNreqxtbVBp7NNqVJ0pUETzVbSxsqG4PmEgxEqcLnzuT/j4R9YnjiP9z39BJcuX2Jvt4Vvu2zHCYtzNpZSvH1pA13mHJ6fYa4hsYWkyApmjh1hd+cW29sbuMEeu1t75DkEkU+Rj0hGNoHbwJ2b/KJyGBdjNEw1ZaY2i2FIWZYoLcGwT70VGCEplSKOY1762mvs7LXA5FSbPkea09iOTX0qou4HFLoky1MsNTlqRZghjfkFXn/jCv1+QjzQ5JlmmOSMhjbNuk+WZmSp3MfySyqBzcxsRF7EfOqT/4xKGIGGD3zgfax3DO3tNW5cfYvDh5v/7gS+IZ57z9N89aVXuXr5NeZm5wmCCsPhLu9611M89uhjfOqTn+bajYsEfoVbt11qDY9GvYnjBKyurnDhwmv8yec/w8U33mI0HLK0tMSp0/fcoSfL4cBF+O/8xI/ie/5YjsAYwkqAEBYGye/9zm+xubaOQeB7NpYEZQRYLpV6BcuWNJp1CiXodDv0e0MqoXmHwnuQInx3s09hQoapzd31LmUm6HRHLJ84xJsXXyeoBhg0o1HyjmNrnmXvWLpLx0PohOOH5rh07Rai0mC33UbpEss5wJFXCrJU4VmCiifZ6xUgLFxbICzJYJTiSotCGbK84M1Lmzz+0BxTTZf1rTbDuGCQl8wtVSnKEmlb+L4kizVpcbBxhOPY1Bp1HNfC0oyVsgYDwihkthqwnGzz+sxZFutVvKiCETC7coZY1EBK9D7V0t1HE4RGko0K3nq7pPN7f8p3f/f3TJSHVpqsLPCFjyUsgjCktASpBl8r6tWIwrOoexX6I02uSoZxjONaBEFAUsRMNSOQGll10Y7BVT7a0oTBQZArmrmZJkWeUQz7GG0T5zm2GIMShvGAJB0xGsUEfkDo+yzMTuP7IX4Y4Vg5m1sbiJHiXYdPsrF1C+VaxKM2V66+NXEe51ZOjtEgyQhtNGlacPduTD3wWF7NKEufdtuwOJsgrPFIz2CRpCXChqIY4vmQZYoijzHaY2raQSkPrSc/GSgFgeWRpQkG8DwXx3beqRbGQJaWXL11m7X1DdrtFnk5olL3qfgBWJqwGuI6NqbMUVriuc5Y8lRMvhmY0rCz12c4zCgyhe0YwnCMDop7OSbXKDlmoSI0rhijYoa9nCzw0OEU124N6PVHOHe/yvpuzHc+9zBvXO2gnYMV4SiqMBwN6Pba45OS41KvN3Ecm+npKaaaDa7fuEZRZLiZS7s3AgPTU3Osb95lOOoyGPYp0oxRHPP+97+Pb1bL+3fHgYvw6dOrOPYYRC72RWiSPCNLMhx3rGDmODaBa1Gv+2hj0RrmzB8+zpETx7hz6wrDYcywH+/PkceEBcPByBqFpZGhi0aQYbBtFyEsPDein8aUlqYsSxBgO2P6bZLv52gUkedhI3ji8ce4s7FDtdEArcZ6CwcYqruOIB0aLE8Qj8pxY4+1rwlsxpeWYsxWCkOHlZUGcZISBg5KKPZ2NFN1j5pj0emOsCyB50qksinUwYqwhcV0o0kc97A9h7wsMcLQau0yv3yIMFPYu7scOb0CBrRl6NgRmfAxlkBYNtJ2sB0H6Tj4FUlQS1g6ehYdT35ZKUqN1AavYiMti8EwJvAlvm8jlaKwNMKGvW6XjifIiwJKhUDSdTXz0zP0y4Q90SfMbMqRi+c6jJKEYTr5bNoYQ7VSIU2HaFUQ1eo47jSbQJElqCIlTUYURnL4yAnCqEJrd40iL0Ao+t0t9CBiujLNTFlS1uokQhGbFtX+5C9ZSkGeJ5Qm21fzq1KMRjiOT2unjes1xut20BnPVgVUKgHS8ui2U3RhI90ML7QY9hyyXBFFIcINSAftifOYr9RIRyNGvR7ZTEJZQlFo4iTn9p3rtDtddrt90mI877YpODxXo1INUSqntASWtAhdG6U1rhSEvkemFfoAwjlRbZp+nNGs1UjsEbWmTRQ6mNyQdEqypCDWGZZnkLZhebHBwkwFz5MIFJsdeO1KG2NZhMMddnfa7Gw1eOlqwe01+Ps/N3EqIAyvvPIycRqT7hbkWY7jejz33vczGo2Iooi91jquE+I4HpYssB2bncvbdDot4tEAbRRpkuBIm/Pnz06MD74XBy7CwyTFdcY6r5Y1xjZa0sMOJA888jgYxe7W1lgyX5d40iIfDnj1lVe5dPESFdsQ+lAai/NPvp9rb34OpUb74h2T51GMRthmPM9KkoSKY9NszjIzNUuajWjUIuamm4zSPo4jSeMRWqdoxiIhkeeRpYqXXrlItTaLbSTTzSZ31+8eaByR5xZIi6Qcy/MpIzBSorKS0ihs20M6hmY94LHnlnjyfAVHldzaTLiyW3D2TMhMKPjahQ6WANcfj2qatQpxMrlIDIApFGuXrnL29HmKMiOIKviBRzqKSXsdGlMzvCcfspcUVCsh2q9xs5gjbx7C3b9UdW1n3Inp8fE0rNfptbvEevKl4joOZVwwHPap1Wo4tgfag1JRForCgb1+j+PBAt3dHXY6MdXIp8wyRF4iujFF6FKzQ3qdFmnm4IUOjm3j2pPfws8uLvOJN26RJQlR4LI634C5GVKdooqUIksRwnDz2hUqgc+w12Xt5jWGwyGlMcwun+Shh2ZYnGlww7NZb3W5LoY8cnoB91xj4jx0PuDW3S9jyYDIj0hHCZVqxPagh59WgBatzjWazz6O43hIS+A6HnEa4weSbirobQmM1kTVjGq1Qa87pMje4gCNMLbIkbIgz0s+8ce/x3o7w/VsHE8SSoOwBM0pB9+vYgkLV2gcY3A8gdEehQQpLTxHkigbozWj4ZBKeDBxc+EKGpbBsyp43iyjtENRxoQNOH6oARrWtmOGccGJ1SWWpgN21zcYtnOMsEhSxfmjUzi2g2MrvOPLTNVK1nb67LQn36QBnnjiEf7BP/g50jLlt3/74/zRH/0x7XYbMGRZysWLb7HXXidLS7QCpVPGIEwHIQTStiiKcef7yCOP8P4PvI+vu6j8B4KoeV4FuS/iPh5JlGMN4WRAte5xdHVlDB/ZWN//j2RIOR767/b69O0qYShQFqy86wjHzr+PWxdfIBn1D9QKL83P8PalSziOw7EjS2ytb5BlKS+88AWWFheYazaJKgEPPfw0lSjk2uUrfPqFz2MZidCwfOQI0rIpRj2imqI5u4Dv2FSiKm5wEJLEeDMyRpEWGiElljBjGU8lcKXEcxxMUbJ7p+CG7ZDnmo0tzUYnZ+WhBbrdNmCR5gmutvclOA3igBaAhVLcvPE26ajPwsI8s9NTxMMhWZJghMYBlACVFZRuyVqSYw4vYVtj2crxZ5S8I+NhDMqAlDbSCSbOI8kyirLEdV2SJAEElhTY2NQqDr4w7Pa2saouUaVCPy2ZatSI4yF2rvEWfNYGXYajEflgwOH6EqIUoC2S4eR45dsxvHR9jVqtgYhHXNpq89gzq8zMugijkZbAtiy6vR3a7V1MWYzXq2PjuA6h5zHYucWF7hqyrvHlIlOdHrNnFpG1ybUj2r07tAdgTEzfjilLl9bekCRNUWUM2CBsesMc20AYRWgMflihv5bhR+foxXcwRUKWlbS22vieQGkOhErAAiUMRZnRnG5g5BDLtijRBBIsWyJdidIFtuNQCTw8NVb6U6VBqxzHthiTSwR5NkYbBa6H5x0An2sVCBOTpQn9/gCtNHluiG0bXS8IPJciE6Bt4kHCrf4ecTfGsQP80MehTd2BKNBjGnyZsrbeRStDYQ5mhOC6Ls8+N1Z/e+973sMffvsf8Uv/5J/Q6w6JKk0OHTmEY7sMi/G6E8JCm3uvh0GV43WUpRmGMRS2Vq8fKIcDF+Gvz20tQKBUiVLjghEEPouHlwirVfrtFioZkJeKQWoIHBtb2mQYBt0hWHDt2hVWzjzAybDBq5/554gDsG5mpueo1bbwPJfFhUMM+iOywtDrJzzx+JOErosQmpOnTuE4Fr5j87k/e4Hlw4c5eXyFqcYcq6fOIU3OxtYmKycfQOuCNB2RZJN3oEIIhOWAFmhRIIXAluMxjesIXAc8Z0zeWLszpLWdUY1sBsn4UnNnZ8jtrZROt8D3bATjS09tQFgHG0coNEmW0um3qE0FBNInTUaAQboOGs1Ms0knznEs8OMdbuYuodDYNuPxjWW9g1ZRajzSsaSFewAcaKkVtjPuFLI8IwgChKXwHQfSjKlqjWDYZXtzFwKLmbkmgS0QVgVbgV0OqBiXbh5Tq0TUogY2kk57D11O/kzeurOF71dw3QBdZMS5wuxvcMZopBRIyzAadOl3WwRBgNKGvMzReYIqNdawxK/a3JUF1swsJ90AUXEYXN+aOI9eZ4dRkqEU9JXBthJ29gqEJSmLjDIXSMfnzvoGp4+ukhcZeZlj2QGFKmjvrLG320eiOX6iytWbu9QqLr4nSNLJ9UU0Npbj4WNIdUYUOUhrrAAmBShLUMC+KI8mUSWh7SAsjZAGh/EIUto2Os4oy7H9FUKgxeQNg8kSPFuNnVMci2ogsAnIipIyzxnkOetbPVw/pNiImYoypho1bMsnKwwjESAdFy8MyfoxpXJpZwVWOcKzD6a3AvfgseON5UMf+h7OnDnFP/yF/4k8LyhVOWbzvvN140IM7PsxFggh+P7v/34++tGPMj09feDvf+AinGQjXONiMUY0+L6PsCWWCDi8dHJf5d7w8IMPUWQj8iIjyTN0qVBKMUpzSqX2lZxK4v4Oth/x2Lf/JJdf+ezEefytH/1J/rbnEQQBWZFTGoVrS8o85V/9y3/Bf/ETP4EfeIQVietL1m9f5+KNW/zcz/93DDsthqOSxeVz6DLl137lH/D0zAdYODSPHg3pdjsT51EoMMZGSAvLjHVEXcvgOJIkZx+WJ7m7nUKRUOYp7a4h1w6OnTJKUlAKYwlG3SFhUKGbFWi/QB/QqiUZpayeXSZwXSyrpNdvU5QFZanpbHeYPxwxiIdM1ysM0hJruM3Mn/0qu8c+SDZ1nMBVKC1RwiIMg7H5aV5guQ7iAFRuLZ0xDReJ7djoTKHKFOFJbLfC165fI/Et5hciijLHFAVZCVIJsn7BTHWWjhR4tZBGJcCSkqwosCsBwptcJevu9jbVxiK7O3dYu/0mjXqTnc27TNfrWHJ8ARlVI9qdHfZ21jl89ARRY4HoSMSZZ05x/RMXsMMAHQ95dKbK229cI6bAjmoU3ck7UGE5XL/WRinB3HyNqGqYnQlZuxOT5SVSSlqtNuubVVaPHKff7dHu9FhYaIBdsHZ7E6VKpqccev2YuRmXOB6PBvf2Jm8YhmVGpcwohWSmHpAHY6IVQr5jBqsV5LpEaY0tIBMWrrQptKJQGULlqFJhS4lT8ZHSoj8YUDnA/UVZWiSFZGG+QRgIZhs1usOCVi9GqZKd3Q6VRkSvXzLKU3rdlGRGkaYtjLYZaMMCFt1WG4HDbnuHqcUGrsxQ2cGLsNi3aYOxB9/Kygo//wv/Nb/4i7/Mnbs36Ha7FEWBlJKVlRVWV1c5d+4cH/nIR1haWqLRaKC1HntaHnQgzLdQhLMsxRi971kmUNoZCyxrjWULjFZoU44V8kuFVgoLgSUlwhIEAspSodTY1VjaHpYtKVyP1cffO3Eell2CBb3BgCzP8cIAS0iCisMo6fD6Gy/zxFNP4HoNpLTodbo8+9xzzCzOE1Z9Drs2lhWgCxdpaxRD5pbOMtwzcABomDIGaYEtBVLaKFUixg57RIFFtWLh2IZRkuOHNqlhf9ELotDBlqAQqFTtz8UVtmOBsTDiYAsqz1M830FYFqVW9DopaZahVEG30yeaGmFrlzAMkdImrNSZS3fIbn+GUfoUo5kTSNfH2C6lGuejtN535pg8j9AElKZGqByKvKAaRVhYOKVN6FWYbozwqhVMliGCKoVdILXEUhaWa+GUhqZl4YUhvu0isclNRtOVhHPRxHlY0t7/2W9C3GH14eNs7N5maeEQWZrse/LZ2LbNKO6TJvukkLDOzMwyl9XL5KlGJRmNyiLGKpCRxNlNCBcmF3nqDcYXrtKS9DojGvUqUigadcnamsby5fhImynyLEcKC6MNo5Fi/Y7F9GyOY3uMhpp+V+0LXWmSUYm0Jz89ZllG5PqURUKajfBsh1yPxw1IC1UkkCvCMKDIczCQKbPvAiJIS4WxXGwgkGMbKqUEwvHIi8nXarszJHId0rwk6YPODRudjN3dIa7n0u0Kdtp97H0KsuvbGNth9lATjIPu9KlFNWRWsNmJEb5Pp5MwNxMxGh7MEuxe3Dvhj4uo4cTKMmfPrvLaha9w/vx5Tp06xWOPPcb3fu/3srCwgOd5f+Hf3nPXOGiIb8WO437cj/txP+7Hv584eO98P+7H/bgf9+PfW9wvwvfjftyP+/FXGPeL8P24H/fjfvwVxv0ifD/ux/24H3+F8a1c5xnKmK31i7z95ueILE0URTRnjzN75oOUGq5c/Cq3L38e6dX40ktfYevuTUpgbWuXS9d3GAmK490AACAASURBVMUpozhndqaCYzkMejnt1mCs5q/NRDSTP/mTTxvP83FdF8dxiKIISwjKsqTXbXPn7h2uX79BNWpw/vx5zp47x+zc3DuYwHuiy9/I9Ll3SSmENdaonyAynZiyLPcVqASGEjAg5DsGmfekNP/89/nzf76na3EvbNsmsCsTU5He+9SSefNyl7/+7CqL0wGvXtzg+t0urg+nF2pcWhvw9PlDrHVa1GzNTKPOGzc7zDYM4JCbkmu3Y544MwtCI12H+bpPb6RYmmnwT3/jqxPl8ukv/5n51X/493n1q68RRR5/48lFlBWwNvT4wpdfZ366xnQtJFY2RZLgiYK6U1Ii8VzJXlpQmzrEzPQMSwsBwySl248xoo60LT7+2787UR6/8ss/b/IsQ0oX23aRwkcYkEZgtIPAQZqAtBSURmDpkm48YJSl5LogzQdjMR8zIB3dxpQxWuWopE1Um+E3PvbqRHn82A8/bx77nuep1mtsr+/w2U+8QG+vh1aK+SM1kl5CIAJsKTG5AgVVqclHCd3dPRq1kK1WTHdoqFZgaqbOxm6bI48cJ4ym+K3f+NxEeTz0+MPGB2qhz2PHAh4+t0K4cIqnv+MjXHnlAtVaSF6O+OTv/QtWFkNCxxB5Ja7rYdsBrjfGUbuujWtrSiTGcjB2g3iU8fzf/IWJ8vjSi182e3t7dDptXNdmZWWVbqeN49hcu3aVaq2GH/gopXAdl0qlyt27dxmNRvR6XcqyQBtDkiXUZ+Zp1mfBSEK/znSjxnd98PnJnkejaW6TETYbhI0mvY0dqs2AZ973XjxXsLMHX7w64sjskN7uiHx3jWSwjeM4+N7YBaXenGJqbobIDXn1q19lcWmJ27fvYFmCXnc0UR7fEqZi9+5bvPrip7l76xqnVhbwbEk+6iBUgQUUasTNG1fpFR4bnSF3tjsgBe3BgCBwKYqCiuWR5xnaUpTlGN5yEOqjJcU7HO17QGvHcZDSZmFhkbm5Oc6cPssrr7zEi1/+Al958QV+5Mc+ysLCAkKIfUzfXyx8B1SP/P+Ie0X+XlEX7/z+/4dG+csiVcq8wPUEaVaiihLbHivdGaVpNmq4WyM2tvsIaaGkRZykNGoOM03Y3C4xFkhb4DgSrQ1T1WAMeUsGKD25QEsyivnOD/8gg/Ye61s7dDPNfM3i5HyFt6an6HRanFpucvdqawynsy1sIXAsi8AYmtUGJ44tU280GA52UUoRVVwG/ZT+ASBIWhnGCDuB0RblPtBeCwulXIRxQEuSUqCMQWiLpLRI1dhFOFegDOhSIwxgFOgSTAoHeB6lEcimwVR2OHq6wvuTp4jcKnvbHW7cvMaRRoN8qBj1WwzzIXmpUEkXRwuG/ZJOt41lCQLHZaoW4lgKW9vE24rAmfx5OMJQdwxnl2dZWRorCx4+dJjdzTVqtRp+6CBzwyOPP8Fw9xY5BaUqkGWBEB6W0dhSgCnJLIcxNFjjqSE1b/I3pyiKfaJDhqFglAzIixTH9bEsQxi6lKqgWo3G1PnApygylCqxpMCUiizLKMqcPM/p9/tMNWfJ8/xA79CZSpWjI0m/m9JNWlBzOfvgCYajPo2wRmSNoaq1Zsgui9jz53Av/jFJdxulCgLXZTiKeXD5SUyaIBHsbG6NoaYHQJd+S0X4zu3LDDtbNKpjg7w0z9lYv83CqRZxaROGFXKtubm+QaYkcVri+JJCK0bpmDygCkWaK7QePzg/cikOALR2pINtO2N8rgWt9i4vvvgySZIRxxmlKmk2Gjz6+IM89MhjbKzd4Q9+/3dZWlrk1OkzrK6ewpix9bdt79Ow90vwX74Qi2/SsfvGTtiYe5zH/a+8V5jNvlXUX2JDaEYejpODUZhSUQ8cHEsQeGPxoihw6I9Szq026fRzpA1ZMbZScmxFpjTSGgtoS2njuDbb213mFxpIa3I8qhEWi0dP8F0f+SE+87sfpz5/iAfOnaBQgifbOb//J3tcubnNw6dOsNMdUCqBp2IGSQ5G8Ld/+Ps5fuIY8Sjmf//1j6FNztRMHSmgLCYvflpblOWYDS+wENggBEZYFKUD2kFrQaYMSoPQkCqLTEvKokRpg+d7aDxG8bigG60xaiyEPmnEcczn/vDzHD86iy8jhusuzuwU09UjXM9vMygSklEOWYkrPRYPL7B5+TVGo5iSEumFoDJsK2e2OY2xDN1aSWpnBM3JrbikKji5PMWppQq+7BJEU1SrU3zt9QusHDuNK3xyBUE0TZaMUEU2Lmxa4dlj7LkrJNJySLWNsCwMIE15oLWqlKLT6ZDlKaWCLEswlKTpCMeV4/UHBKE71qexLbTRaKNQqqQsS4wZS98mo2TMpMszXNsabxITRnJsidlun7m8wEo1MvJYrs2xrQWuLRk5mtCxmPVs7KpF4TsMH/1ujr/5aa70dtguFVHFZpjnOHlGVA3o9WKE0NhycmnPb6EIGwZxH+nZFIWg289wZYG0YXf9EqJyiC9+6Ytcujmk1S8ZDDukxmVvt4UlJIN+TK0W4ruSu7d3MZpxN1SoAxYdsU8YsZBS0mw2efbZZ7hw4S2+8pU/ptVuI4Drt25y5uQKH/y2D7B68jRaazrtFr/+6/8M3/c5ffoMjzzy6Hj32hf3sZAHslYfswTHz+adMbt555d3Cus74w5AozHa4EqXGzdvUKlUmJ6d2VflH9OcD1qE+/0EqQ2+LugPLYQRONbYRHUUZ1y82aZR9TmtYBDHIHx6g5RRGhA2PPbWuzjSQhuBpcfdxtnTx9jc69FLJ9dsaPgDTj10iIcffJxv+9AhXvw3LzMzXScuK/zA987wHR94F29eWydtbfDY2WV6ccKNjSEffvYxTi/XGRQuu92EauSxtrFDox5SHRmSuH0gMH6uBQk+0rgUpYsyU2ij8cWAWnqXUeqTu9O08TFaosnx/JxTK3M8dWqFc8cs9i5fJevF/MYL29zY2sWyUowyGNObOI8TD63y8stX2XrtKodPzLP66ONIJ+LQ7BG8N15FWg6eLZB+hFYpne42jzz9AP5cld7mLrdeeptumlOdbVA/M0M6iHn6iZN0A4+sO/nPZXV2iidXa/jWDrn0OPPw87z62jU6vS6vl5e5ePEy7faAh8+d5diRVeZmp0juvELS2wYrxDHjNesbCAuFLrNx0bNtrAN4u21vbhIPuwwGPcIw4PbNWzSnGiilCWWduJVi+x79dslw0CbNc0o1wvNsstTCd31s4WDbOaVW5GlOr9vj0MIMeTJ5J3ylvcvraT7mIlV8jmJz98JlloKA2TdKDpc2CyagnHsEv1ZjZ+0q/092hGMPPcwTt65QL0tuG1DDGGMMhTbUZhtEkYe0Ji+t31In3Gq12Fhbx3V84mEX261QbRyhMXMG6Tf4G9/5Azzz7m+n0+2xvbPDxz7+MV57/SUGoyHaKOJhTGwUUgo0kOcaoeBAMmqMi5reZ+tprXFdj+XlZX7wIx8hTVM+//nPc/Gtt7n0xps88653EdUrYAxRtcqDDz7I5uYmWTY+5khpY2BfEKQgCiYTrPnzM9+vz5W/XkLvdbv36JFGaWxpo4TiH/2jf8wXv/hFfvqnf4pv+45v//rnHOhJjKOXaBzXxvM9LCFIsxSNpuLYzNUDDNCLS1xb0I8NUBCFY0+FJC4pSoPWBs91cURBoxog0fiehW1N/pIdah7i1rW3GBUJjZkmp8+dJd1rMRr2ids7uCLl2559hP/j/7xKNawSd/sszDV56OwhylGHQTchL3rI+SpZLkizAqU1zakphsnkmg0GiTIKrSRauAidE8mE5WqPxeIKNzZbvD2awjn5XrLCZq64ztEZwel6hWD3FV7/0pvc2drm4eeeY9Du4QqD1jnjHnjyLXK3t8n88UXIFJ1Oj71Oi2NnVpmfn6UeTbGweIT1u1uURtEf9aj4HtkooXWzTSMKefCBY2QO5LWAIrCxA5fb6zvUZk7gZZNb3j90qIKtcjIkvcziyq3L5EJyY2ODC597kV63h9aGbrtD9tSjPBzVqRx6hMLfJks7zE55qLSPkgpR5ighMZYetx0H8h8Q5HlGHMcoNWbWVqKAokyI3CpJlmAjMCIhLxS5EpTGwfUianWXLIkxBlqdFq5j49hgW4bAlbgHoNeXgaTqV8nTgrQUbHSHmNBh3RdcUQlTlkPgJyy0h+TKxkksVrbXWBvcZjAcIWY9KgMLowx9Y7Adl6hRAVHg+pMLPH1LRXjt7h3mmzMYDCunzlGZOs2hlQfx6jMYYzEXOszPHQZA5Zq5qWn+2//+LjfXbzM941CkOVmS4vmCsjBkaY5EHAirUZQlrueh9/XGhLBot/fodDp89nNf4Ps+9B+xurLCxsYGaVzQaXeZmWui9wu90xzrBkSVKhsbW7z99tukZcnhI4eIKlVOr0xuaf5vE3D+xqL7jX9njMGzXW7dus3v/8Hv87Hf+hg/87P/FU8++eRfKOQHDc8N0CZHK01hBNUwwHUSmvWAqVoF17axbcNUw+fUcoOsLEkKg21LlBJkmcZxXELXBaWxsXBtC5MWiAO8ZUeWzzB8u+DwoXmq1RrxlX9FL+6xtx5jyoQRI2q7m9zYaCGAIzMRJ1YP4Upoj/SY+l5qjIZqLSDJM27c3eLwfIN6NLl9jdJjdTiBg7ZcalLz8GGHVa9HMRxxtbfOGy++xIdPH6Pb2uZEukf/wjVarzYIl+tceu068tAclarLVG2KUadHoTQaDmSBNbVQ4+KFHocWj5HnsHHtOl/rpJSrPY4sHsFxXMpsRCUM8ZwGnqsZdrfotlqYZoMHHjtJ7gnuZhlrWwMsHaL7MYKcI0cnF4yJ3JK0sEhKh8SO6I0K7DDi+p27bG3t7gstGdY2NvnEJ3a5desuP/MzP8vMwjHuXL2IV/FozLvEvR1GvTWEazBWTl4WGCYfzwwGA5IkGZvwKk1WZORZQVkYUlOws9cj010kiiTXpMpCkVCvKRZnGpS6j5QWtmsz1WyilUGVOcmogy4PcGKLKuORSKmxcs3OoE0znCLNJJ18xOWhwslLnju8xfFDs5hRhe9I3yQZDRl6kmBmlrzfY5gXSM9FOi5IwdFjy1y5tDZxHgcuwmV/k6WZiDDwCMIpzjz1n1AU+b4QCPsW3i6bux0uXrmBFIJDi8ucOv0wl65c4/3PPsnNW+tceOMSthTkSQlaUBqDdQCL97de/xJRJcJzHbJSsXz8HJ3uACz4ax94jnolZLRxmywb4fouv/TLv0yj2eDBBx7m0KEj/OuP/w55MRZxTpJkf6RgYTvw7qef5td+7VcO+mi+OQQYxp06gGPZtNotvvjFL/J3Pvp36XS6PP/8e/ihH/pb44vKyjfvnF9HcEwelk4ILJtmNeDa1pBjsz6rixGzDZ+5GZ8HV6bY3OvjG0mhoZCSnQ2FLzVaG4TlMD9VYeVIk+GwQAtBlkOuQg4gUcDv/vY/phosMNP8dlSiGXbbFKWi0mxy5csXOXw8QkmP//UX/x71wMaUBb1WF9d2WTh0hM2N1/Ea86QEKC0IgghjSm7c2eLI0sLEeZTGpTQSLItcl/znP/A8i+4QTx/nl/633+bqlR1krjjDLfrlTVIKkshwNd7i9hdu0JtbxlcenU+9wLFT7yIYLvDq63+Aa9vIA+gEXLy0xfU/vcyV0dcYximzjRp6YYv4+i5PPftu3vrqi5xaPUGmCizRwHUNRx49xZ27d5manWN3VHL1rVskaYol4PDCAqeenKG916PXm9zuSUgFc4/RH8BuL+f3f/NTZFqBHF9qA2MNGMuiMPDqG2/yX/7UT/FjP/7jnDt3jma1Ttzt0c8tarUIP3CIk222t24yPzv5ZpAkIyzLYmZmBtd1UKqk307x7ZBM2Ox1NMOyyxPnT3BlbZfWXpfhoE+vojG5DUYjZI60fba316BIkEazdusKcVLykb/5fRPlkeUZtnSoOYYk6+PYLp4XYAvBTFjjxtptBoVmc3OH3FzE2IpLszB0JCJOaLS3kIHEBjJVIGxDVKmyt9ej1qhN/DwOXIQ7G5d5/fIdZqsu58/Nkg6HeIFPGFYYH6LH4jWOLWlUK/R7PYQ2PPHQI/T2ttH5kHgwxHNcLCMQro0wOdIYZpqTC2VXHI0qU5rTNYztE1Yq3Lh5hziOeerJR3GljcNYhOaetu1wkHL16i2uXr2DwCHPMrQG3/fJsow4TqhYHm+8/tpBH8u/pWAalFZ4rostHT75B5/kX/7mb/K5z32OTqfLmTOn+eEf/iE++tGf5Nf+l18hDEMK9eeUuQ44FPZsm+n5Op5rkWWKwJfUK94YwhdWCBwHYQRClNQdQ+k6DOoeWgs8W+BYgpmqR6c/YLY6w85gbAnkSgt9gGPKX/vO7+NrL32Sa29/hvr0Cn6tSV4UFManvddnanmWUrjk+YiBlkjGl1dho0bFCylxmKkECOlgixJX2pTGwUKwszu5k4S2GF+QCiiNYqoZYrKEwsywdXeP3GgUinackcuIQX+T1dVVdnoDXrx6geCxZVJLcbPTIbHX2GjfxQubWLKP5U2+Vg/NLnDLvonxCqpRlUEuadmSH/rQ97B+/SJnV5c5cWKZr735JoHnUQuavPni6yhb0Rt0yGTI0uEFTpw+hvENd968TDjlIuuH6G5NrubW6cW8fPlltrqK/iBjemEaigSLsQyq2EcY5VmJiyTPM4we8fF//TvkfCfve+ppkrJPNFUl7aQMOwlbuy2Wj5xgemZyQaOyVAhhoZTCmLGAkmUgTvZoVKdZPDJLoqsIaXH6zFma9RY3rl6lyA15ZhDSQpcaq9TovMSXAkdYGJ0dyO4pHQzHp9VCM0oTgihC5wWDQcrQGJI8x3E8hCcpTIZ0BNJy8MMad9a3WT5ynJFl0x8W6DRBlQWuJ3Edj6L8DzgTbu9cIvKqbG9uIfQVTj40wHFsVJFjuQ5al5hSUbUNp47MshU47Oy2KXLF2dNn+cyffArPCzl+dJnDi4e5cesWvuuwVKvw2ANnJ86j1R7yrvd+kOXDy1RrVYrSMD0zjypLpuem2d1pYzs+5GOR8tnZedbXNgjml9jc2sZyJBjNaBRTqQRj2EyWI0KXfq9/0MfyTXNfY8xYT1i6bG/t8PJXvsrP/vTfY3194x3QxNbWFr/6q7/Kc88/y4c//OH9z/j6LPgb0RqTxlQtoFpxKfKSRuQShj5TJUQVH0uMbZMqoU27n1GWBulZWJRYAnzPZr4ZUvUsOv2cWsUadxwYsjQmKw7gnBAp5s+uoDOBUALLqeC7kk7aZerwHH5zCaMtVDqg9AKUgKLoMuxZ+FMeU3PT2JYiyxJOL8/huAGDtORGnhAeYOZnbAshx46LAsbH29ZdKrZPs+KwFisKCYVOGaQxN3Z2WX3meaaaBfLCGqISoPUI4wfcWr9KnPWpzTfRrkSGcxPnMbNUJZit0dlsEQQuM9NNHnjiIYTJyJN17LBKkiZ02y02+z3k8RO8+5nHyLMOmxu3aXX7nDx/ktubaxx/6hGi6S162y3KyGV5+djEeex0MnaHLpYXEUmHB86fpSgybt++RbcckufjS88wCBFGj9XahMX65gaf+eyneOTMCv3+HhXXJY7HvnxBdY7m7FF6wyFLE+YhcHAdH6WysQKjAekLiiKm3ZFc29qjH8fszc3gOi06ez0CJ0QIH6cyjRYx6IxRPMDWIblOUZRYdoXAn3wsIoweC7b3R+x2u1hZRph4qFKRFTkqV9gqI6iHKJ2jRoKw0qDX26XVjqkcOkwjjLhx8RKmMETViJmZWUyaMignR/EcuAg7jYf5jz+yyuuvX+PUiVX2tjaZqdfI4wHaspDSZjQY8Nbbb7PWzRHhNP/3H3+Wr77wSbqbd0l7bZ587xP4FY94p8PxY8t893c8z0d++CeYOkALb1k2Dzz2JJ7jkqYZmxu3OXZkGYlFmg1I04yHn3+SP/yjz2Iryc7gCpYluf7a11g4coK7m3dIVYJdKkYjgS0UrmcQSBz34BeE9+a5rusyGo34xf/hF/ml//GffsNXfd1M0XFsut0ejuPwhT/9PFEU7Quqf/NnHjTOnJhne2+E43ucOOJgtEWtVsG1Jb1RTsW3OLHUYKOTsjBVJYw8hoFDWLFw8QmmbFSpcXLDmZUF3rjYY7rm02+7dA6wMeV5QaM2R1GUlJkirDVxy5jeXo/Tj56hPj2LK1LKwufa3XW299qIzg2EJTGVeYLaLNXFaZ48eZS//p7/hqhWJe9u828++TJvXr4+cR5ONaR0NMo4NCyLZPMGauM6shrQsx1UUuDpkvbuLhe+9ha7nZwHhznZbgdvrka02KQ0HpYoiOYMDRqUQiGYI/InP37PH5vnB//ud5GPSuqNef75//zrOLWS1/YuYB9qcvfmJhdv3OXssRVu9FoEtuHw/BGcykn+X/bePMi27Crv/O29z3jnvDlnvnl+9WpUSSpJVRqQAAkQbiAwWB3R4DbQAQG01BCy/UcHuAOi6Wgw7uhuh3GHMZjBZpBBQghMSaB5qirVPL058w05Z97x3DPuvfuPk+/VqxLdvhfs4J+34mW8iLwZN9Y95+7v7L3W+r7vkfd+H2aUsH39Ih9877v56K//Cq3FM8wdO8F8pUFYjD+idvDsO7l6eZvlAwu89eFzHF4+yPXVm9y4dJ4wLDciURQximOkVATVGnme48kGl1/s8Is/96ucOrZENNzhgx/8Du6952GuX7vJXt/FkbNj57Fy7RXmF6ZxlCRJUpSSWFMn3qljdEhoDxHJAlGdw4gBqYzwKzV0YuiNIoTNKHRKmuUcObBE6IErLelIUJnAfOBkHGAGCXkRsFSfIxeCYZ4xf/oUO3tdWn5IIBXxbkx9qkl3s0NjVhD3O3jSYXdlnVq7zsqlK/jVKkFhuPrqVTrXN3AnsOGaGIQ3r8e0mi6uEKRxxLFTDyCFRGG5ubLCCy+9zHMvvshuZ8h7v/N7eP6Vl9BRiu8FJINdPGXo7u0heh5zvseD957i7Q8cJ9tdZXtbMHvq4bHyqFcbXDp/hdGwx5kzZ5mabpNh6O5s05yaplqvY7KMv/fe9+B6VdzegGK6RR4nhEeWObc2hwhdtlZvUDhQCSypDXjyqRdRwfgzfvD6CYnnnnuO3/+93+ff/Otfv6PRBiUIlz95XnD27Gk++tGPUq1WMVqXO+g7ZiImcWu9FUoI8jwny3IcT5CLgtArhbexFul4ZPEQIQX9fkQxinjH0RbCczDGYTeOyeKC2akqmRGl+25agLTUq+MvdoEGkeO6Ho4jSVRMphOELbBak0dbVEKXV64X/Nlnn8cWCYfqCbkB4zs0wx4N2Sc5chBx4Uk2Cwg9zUKryrEPvG/8PDwHiUVYn1CJkuiRFszMOWynmvaDD5PtdfjqMxcZDXIKC9deeomt3ia106fwWhUUAkOOLOL92W+JxoAz/vV48Ysv8vD7HsLzXHa2+5y+/yBewxLrHlpW6SsYxn2yl18gdBSJyVjb6zIXzCL6XeLt63S3brK7UiffdRhlI64WXeqnD3Bg/szYebTml/iOYw8yPz9LtaYQyiWoNsDxcTMYDftIXaCkQ5EXBIGPUB5WW7CaYax54tmLZEnCPffd5MGHDc12m62tm0y3xn8o5fmIvT2N53kEfogvS1+9VrNGo7mI32oyVIrtXoMi7xKGimGakGYpUw0PaQ1FrpFY8iLn+vXrZMmIM0cfQKrx78uN4ZDt0BCPIpJRzKmpWb7l4BnEVIM/31nHpgWjKIE9hVPxka5Dd7iLU1gqgSJzLDd3tok7MdEowSRxOQLp+vT6429aJgbhoOaQJH0cx+P8patc3Yk5efQYSwvzVAKfOB6xeu0mC7MLxOuXuf7i03S2De3FY/hCoqM9ersDlIxpL8wwN9MgjXZYPb+LyfXYIDwz6/FTP/ljWC145JFH+KVf+WWSNKHZbIJQ1Bs1XMdnab6CF1RRbo6uShIMuDmyGpC5ComhXvHJ0g61ZpMgcOkPJitH3FmK+MxnPsPv/Pbv0uuWHdxyGqOkSJdhecc73sbP/fzP8ehj70Bbs/+S3f/3zeNu44YVgmo1wGiDowKM0aULgu+SxAl5luC7sNlNaB9c5C2n5zgQRsiwhhUuu90uQkjcwKcoJEWhMcYShAHhBLZCjcoyUoVgHbRO6JsvI52AIAgZ3XgZ0hpuY4pP/sVLbA8UnoypORWE61OMBAtTDrVam42tHmcaKavXbhDnhj3dxEvGz8OrhBhlkXhUHUkiasSFpLqzSzC9wH0/9MOk/YTnP/Xr5OEucW/A00+dp/62w8w9dIbM9xHCoJFInZbmtbhomyEmIAVc/MYFomLIwtwivq3TXpjh6LlzXHz5PGvXb3Jk8QiHpw/w6he+QSEL+lHEjbVVpuebrF29yvlnP81gYOkNN2h7bZ75xnM0azVaFi4+cY23ffc/GiuPqZlZEukTBB7G6rIR7QVoa8nTBFNkBL4iK1KkdBlFQ8J6myxPCAKFlRInrFEYl0uXr9Lp7pJngt29dQJ//M5tlqe4RWkz5TouRSFJGeCogpw98qhLMDPD7qZDEHp4qsVevEnUH3J4bhpXAhWXJE7xlIM1lmgU4/ruRE7pLXwW7z3H8y8+T6/IGDqW3pzP8nDETOjTWlxkc3OP7bU1PDT1SpXZg8vUPZ83N+a5p6iy2UmYqk/xTLxD1+SYuCCcDSey4ZoYhP/Dn3+FUQE2H2KLmFcvf44nvvY1pDScPnGE3Z09HMeh1Zzm8199gqW5Nu84cYKoKHh2oBDhInIvZGtjlS+e/zJf/OwXCKseR+5pkRYDLn/Ph8fK4xOfeJxa2GRxYYbVq1e4eWWF3/zN3+S5Z54BwA19bGrYO38VkVtkoDAedHtdhJUErSZLJ45RrQb0NxOuX9sgji5y33338+DBxbGvx63pByFKu6ePfOQjfPjDH2ZrbZOf+Zmf5Ytf/BI727sI8Rph4/HHH8egMdK8zszTGPPaDvgNehPjTeRm0gAAIABJREFUxEZvF9/1cJRHkscIIRgNY4ypo1xBLXQpMsHROYnjCg4stFlaPEbVd/Gr03Q2VylQCL/Gp7/8NL7jMRgmWCsmWmRXr11AKnBkhWpYR6cjOttr7GzcIO7v0ZpuM3PgEP/gO1xWbg4Y9ods7vXoxC6V+hQPPHCE+sxBQpXz2Wc2yXPFMM5wghGhGJ8kUan6OA0QwmNG+nhTi8jiPtTOl3nop/4X1KyPTTMeOvkRXM9h99WXOTG6xsrSAs50E6k1WlfK4TxZw1Dss+W6uBMwCN/x8Dv5+gtPMxUewGlqdq6s8RcvXmX98i7N2SZyS/PB93+Qxz78Tqan2vzu7/xbnv3EZ3jmmRfprW8xPe/y9W9c532PHKCx+BYeOXeOauCSqAqzx6fGzuPy+VeZWp5narbC6dP3I4XH1tYWH/7IT+FKjcCwubXOxz72R2xuluN4yWiA63ikaUqz2aTT6WC1ZWv7Bp/6s09y9PAZDi5XCSoT0JaTnNwBFUoGgx5BpU7qCJK0z8rzT1AUhqMnHqJSf4Qi28ZVKcLuUAl6mGKLXtRFSEPgejhFwVRQxfgJRsdgx78v73Ya8Mw1PrB0hsM/8tOEp45Q+9LLdD72af67+j30LsSIbI7g5APMCp+K51FkAtGYYu/hOkv/9IfR33iFnd9+nMHKZT5V6fMZBmAj3AmmZyYG4YZfkCAxWqKtwvcrHDt1ms7eNpevruB7Ps0wZLvX5fCJM+zGBZtf+gpJ3KU/7PD4n/05/+Jf/js+/qcbeEGINZClMUq1iPrj+2VdXF2n0V6iPdum2qhx+coVzp8/z6UrVygKS7s5hc5ylMhxqy6+79KaniIqcpIkpj49zdLiHPNLC5w/f4n2VJtdbTGmoLM3fgf+jSWEfJ9WOzs/y//1L/9PvvD5L/C7v/Pv+dSf/vntptyTTz7J2x99G0meIO7Qv/jr5oonCaM0uRNjbYoUZX03LTR2aJChQFQMxubMtJpIq9lZu8HCbEgvzwgyg0Xguh5JnjPoD6iEFXJdukhHo/G93e49+QEMGUZrtMm4mXyOUW+bJI6YOXCMyvRB8sKwfPgg1caQ8y9dIUPR2dbs9SOyYcRAbZMGpRdckZc87zwbEZjx+wZClj9SGKQEV0oCV6CLhFq7RSxjXE9hhMIIkFiudXbxz92DlgJ5h9ATSmCNBWlQVk3UNF195SUqmSUfROiqQQ5GyO0Ry+EUuc45fnCZk4cWuXhlhbxIOHRwmc8//gUq7Tqu59DZ7BIQsLvd58BDM6jAIk1ML5imtjT+zi/0JcsLsxw/fhzH8RFI5ufnaTYbZPGAIHA5dGQJay2f+uRnuLG+QWYFge+SGU2SJOUUSxDy9re/lcOHj+HIGq1mhbA6vu1U4Pp4qmyBFMaS5RLHqyAUKCWwKKSjcG1CGFRwvZDO3hUya/EcQ5QM6A+7jEYJ5tBR5mZmWZprk2Yx2QQbl1eSPR4zDY6fPMM9P/Df8PQrz/Cmf/Q9vPyV59ld2+GGGbAXj/jYCy/wXcEyj1XnaE1NczndoxeHfPvGHiLPafzw+0m/+iSPfOMlqMzyl51XmcB/dXIQHvT7aBuglMLxAmZm56k1GsTREtsb1/F8HykVX3/qGwzimGp9CpkmXFu9zOx0kwuXrnFzfY293jZSOhibY7XGsXU8MX5H0XUDLJZLly5x+PARXn75ZeI4ptVqUavVGfYHpEWKWw04eOQInufRHfaZPbBIq9lglGhOnDrJ1dWrnDlzhu2tLTzPYWlpATWB6/Odi/HOBp22mla7xff9/e/jHY+9g/S//1GefPIpet0B/+rXfo2z585QbVT4L+kuJVyN9VRZk7WCJE3xlEdhc0yW4wYOmbH0ixEH6nUWZtqsd1O+/NTLnFhuc3qpjVsrmXe9UYze/2ijRDNKx6cLdwdXSLIRuekgrQ9ClK6+rk+tPYMXBvQ767iVaYZxTFAJSfZGRINdBsMIq86ipOXiekw4iPBdB8eBKB5h7ATuwjovnYOVpsCh4vukcZ+XLl9GLhhyXWAxGAqkULhS0Bce7bCGyUaIkkKEoPTaM8ZgtUEbjRHjk1fqzSrv/Nb3cGPjJtkw41B7mbDt4bo1oiKiKl2SJGHQ6ZMMU7qb2ywcWOTcPfeyt3KJS5c2WV5us763w9tnQuoLChPXWbt5g2x3fCbj8SNLzLSnaDamEaqCNbrUOXAEXrNKnqdEoz5vfvhh4mHOx//kT9nrj8j23cdvzfZarTlz9hSLCwcR1IhHN+kPtzg85nBTrdZCORnaQKNWpzW9jOvV2dhaJ0sM1kIWjai3LFmeIPICpVPyqMdLz68zGnbJsrJGf+TgQSqVsqaMggmWLi7QyHP0aEAQOiRxiqqGGAfSdMSejvgCPQZHD/CJtS28nuaUTbm4ME3w2P381i/8c967oamdWObwz/8YU0cPkXzyk3x5L+ZaMf73dGIQ3uoMsDLHD0sg9lwHoQJC36VRb5ZqR2nMux57O8MoRrkhz33jKR559J3cuLHGj3z456iGHp5SSDukXvXpqwo3rq2gJqizTbXmub55g+n2FE8+8SR//B//hDRJ9i3oLdUwQBlI84ALly8hpCBNUgCuYZiaWyIpCr7rgx/kuWdewGKZm59meqY50fUoJSzta1XfO9TTtDGYPKPdbvOJT34c3/PZ2NhACEmjWafQ+nWzwG/c+YpJKITAPYdPsNkdkmUF9aDC8YUm/d6ATn9AKlOSJKFVreEqhzefPc7Q5Ly0cp2X1jd57to2s/U23/noGf7s60/TiRLmpGXUG5FkojT8HDM+9qe/R7XlcnLhOEIrHK9CUKnQasOos4se7BDnKd3VNS7cHHFjo0+mBbYYcmQuKJtGjmK2MuTPn2nz2KFVpBPg1loTsWOTNGJkCxyhqVcdKlg6wwGrjRN0hhtktqAs3WV4KFKZsfjwo6S2TiChUBqlDNoUFEW+b2hbuobrCUxYz549w+aNGyzUW5g4JzxwgCzPcCsedlPQnprn3/32x3j88a9y75vuYflYm9mGz0svnsephBx//7u59LWX6boOA6/L1uVtoh3L/NGCyxfHB2Fkj4WZBbB1rJFcvPAqfqAYRn0W2ks0W3WajVmGvR7vftejgOV3/+CPKQqDH1RYWFhgNBrR7exhbEqv10HnCadOniTqR2OnMb90mJnZKvecPoWSglcvXmdzs0e7PsOD595Cu12nEtTZ27tE0h+xt7fDYG8DiaUe+pjCRaoC1/U4dfoE7dYUrlRItxx9GzeOHDqOOzVHGvqsPPUcU602F199lf79B+kem6YQOf7eOvctHaF7ZIvfePIJfnS3oPmFHcSXL7NzpMHXKy73v7JH7yd+gcaP/yAHfubH4SM/TasxPrNzYhC2xmKUJcsylFJYUf6unI/QOK5Hq1Zl0Z1ibX2D9Y0dZufnOH3qJHtbm1y6cnHfTTbjXQ+f5uihZT7x6S9hrEDY8UGn2WqxubvFzvYuSjkEvkvolQpuCwszOErhex7GWnzPx2JJ46Ssc2UZcZbw7NNPlyD+5JPUa3WOHl6gSBPkBMX92xj6uhrua1MR1pYUV2MMcRIzPTNduhhrfaeY2l9zoV9f6hgnfN9npuVS6AJfSmq1gEJbdvsRSgZ4jsAVDj6C5y5eR3mail/hwZOHGA4ToE4nygh8Dz8tKApDWPEY5Bm+P/41WViews0DbB5ijEWZHD8M0aJCxhBrcoQBm65ybD6kWasgjaXVmKHiOORFivUqhBWPm1GFjHUCz0GIgFJfa7zQJqcwOcYWONaWo1BenUi1KUyGNfs1eSEQSGpTbYJGGy09HDyQBrs/OqisQgi3bKTq16vk/eciGUZUhYMjFd5si6g/wBYW35EMoiFXnnqai9ducPbe47QaVeLugLlGjTw2aE/iTyWEDY8Dp0/SGWzjihGvXrqGM93Eq86PnUdfN8iUh08OWC68+iInjh9DGotUAqUkAoEho1pTvOn+e/kPf/AnFDrDFymd7jYCxczMNJ5apFGbo1ZxsEmEMuOflDzfwwrLysolBt091rYH+H6LSsWjVq3iew5SCeJsk8JCkkVoXRKuOt0O0ahPtRZgrOXA8iF818NqTZxm5Pn4j+nGBx5FLx8gNgXPXrvC+tY2Oxvr7K5e48a1dYwrqNTrvPWRd9Lt7TKUgm0KlDQEFpw1Q+w6vKD63Lx5jcu/conrJqXeblGV/xV3wllRHu+0LnCth5GqbOZYgxXl7m2UFlTCgMMHD1OvNhi9eoG1tZuAQZsEIRWYgqsb2+xGIwphqLoeaTY+2+W+B85x8tQx0qSkQO7t7pHEMbVajVareRvo9L7kYCmco0m0IU5zVlZW2d3Z4eN/9HE8z+f06VM0awFFkSEnOdOMEbf0joFyHpjXJipuxd9kJO2NsTsYUmiJrwQIy3qnQ783IraWQAoqYYC0kjBwyY2myAWVQNAIQ4S1BJ5H6AlmGjWUEKRZRuC7GDLyCbq9MssIqi6F6FOtTpH2LU4QIHKD67rIoI2jpzHFCCcIWXR8pKriBzXSwZC4sPh5QZYU7PQSIjtFNQDlzWInEGo1QlPYHGEsdemSArJ1iFojJZIxUiiULMcRXalozx5GKAftSITxMAaUSDHSoLQDWKy0WOlwW8x6jKj4jXJsKY1YPFgppVd3tshx0UYyHESEfoCQmuuXL7O0OEPr5BFC18VWXfJ8yJFDR0i9gq989UXe9q4pDt3bYG3FI7fj70Bv7ox4rF7FdTRKweL8LNIYdGEwJifPM4Tw8EMXRUat6pFnGdpqanWPpcVFdne6HD9+lNCfo16ZQ8o9kmEPOcGpLU6H3Dy/jtQpngLHb3Hlynl2dwcsLS2CyJBOwLWb38BzWlQrbdI8p9Zo8sCJ43z2c48z1W4QRRngMIpSrNaMkgzB+Bjy+De+RvzlhCyOiOOYvd0OcZyQJilFXpK8apWQ7/4ffoKXzz9LlIxYVZYQgW/h0rRP1yoG186jZ6bJujlukbCweJZ0Ar3pyUE4S1HC4kgHI1J8RxEgEA6AS14UFNqyutnb182VVOstLl1dpd8fMDM9S+gLppo1mmGVvU6HI4uLxLkmDMYHop3dTYQxuFKAFSzMTyNVWcPzvHBfo9cipETeXjAZygsQyueBBx7EGEOelwpqxhgKZFlC0BNJQk3UQLsFvt8kb3lHU+6W5vCk9eLNrT5GgxEFQoApyt25xNLt5QRK4EhJph2ksghXYFNdXgNHonXEla0hng8zoqReusqhFVYnejAdPLVMbIZImSOKnGBugSjrIqM+ricQbrkjnTr8JoRSSKfOsB9hlUYHHlk0xA08dvop985scDM/zeFmRGFr+I322HkEYUCaGrTNabRqJLmLlHWa1uXm3hpTS8vo/WsvjWXWr/Jbv/yLvPXtD3Lm3P1croQYYTDijqkVIZBSMQmnPNcZjdkppoIqbrvG7FKF461p+kHE1D0e5/o+u5tD4r0Go1FEMsy599xxomjAk8+cZ2fQ4eihabaHEaQuF57VOMLyytdXJhIPP3OgyfbV5xEE4AUcO3qAvU7E1EyLRqNxuxfiuT4SS1hR+CEI7XHffQ/xfd/7/Rw5cgwlBauXrrLb3WF2NkS6Hq4aH0quXL6I6wkcpSgcH1kUpEnK3u46RuZcunyJmekZWq1p4rjAdzP6vQ7NRo0rly9z7z0PMT3dZnpmjitXruIIhRQCIUOUM/59uXzpElKW/QqAeqPG3PwMruuxu7tLPEoYDgesXXye3bWb7PWG/CEDAiEJhEBeG4DnY6Qh7naoWJ9DB2YRjkaNj8GTg3A9cJAOuCInDAMcT6EtaGNJsxxHWKywYEogkFKyNDfNTLOKzlOi/oCiSMnzlFRCtd0CoRgOurcdNsaJmzc2qVWrKCWIhhHHjx1DKQ+lFELYslRibbnz2gdiY8AqWarz78tgpmlKnkfU6w2kNSVxYkJJzTvjNriOsbMtwfb1kpe3Rt6wZUNokkiSGIsg8By0FgzSEY4jqDkOQhiQEuHs6wRYSEYZjhAMogTlSVRVkBY5nuOiHXAdD1cqhK+RYvxcapUKDTWFxeCJOrFMkSqmYzPMnoOxAiNcMuPhKh+rQjw3Ic0NW1s7zExNYa1Ea1ic9ekkhmjUxwsC7ARi6kopHNfBNRBIgadyPD2iuHaNp7/4h7ztfd/C4vISvu9TFAXVluD9b36Q44eX9ykaBcZmaFOgtXmdNdYkpaLCGHJjMDJnbfcSC/ccwqtrtle3yXbqhMFhGs0Cv9ol2Ytwg4BLl68x1Q65sbaG8SoE1Slawice7FDkPvc+eI5H3vwWBrvj74QPzE+RJwPCUBJnmiCYpVItVeHa7TZSlnZcnU5CYTRCgOsqojRj7eYm1WqVLIuRUpIVKVkyoj8wqDyl39tk6f7x8ojjFIuDFgUyVCW5KqzQ73U5cvgwu3u7OL5HnCYUusCLJfVGhdZUnfm5ZWZmZlDKIcsLHOWhEEghya3FFOPvhEt5AXl7zUolMCYnzQocVxGEHkLW+c3f+A3iUQ7WkEtFYQ1DY1CmQMRDCgeUkMhIs7G2w9zsHL77X3NELZBESUIqJEUMTu7gOAIrSiEWjKbIM6brHsKWwOL6VZRoILBEwyFRFDMYjihsKRyuCzg0VyFL07HzWFlZxffKSQxdaLr9CNd1cBwXYzN838fzPKzd32Fay7EjB5mbm8Ma0AjiOEHrAiElZr+5Zqy4LXf5t4k7673l+95RerjVyBPitf/fsO212IkFfFxXYdwKvd4ujuPSCAMym5NjcFyBEYL1vS5z01MoAcNRVo5tBSFCaYajmDDwKEzBKMnBCLSAiu/hTNAjbDeOUg4PuCjl4ZHh+y57azfAcVFS4GiPOMtAClSWopTD9maXaNBjcWEO5XvU6nUOHqvQWXHQRYbjSewkrTlrS/IJEpkWFNEm8eAmN66/zJsWZ/C31zmwOEM7qNIfxoTZHkdnm4g4oq8tUTiN0hmaoixtGY0uSmeHQoy/2JVf4bOf/Rz3P3oPu8MenWvbhA1Y27jOQye+jdVrW3QGI+TUNlc31llsHeHijU0enDrOm972Zv7qy58mbC5RbYYsLZ0gNlUKaRHNlEfue2jsPBwF8ShBBFUkBtdThJWAanMGx3Gwdn/zYiRFptDacuLEKZ578VIJnNaysnIVaw1KKLI8o9PNaQUGNYHMnhSKVnOKZrPGzPQM9VobqzUSiIuMc2fvYZQmpPt4UA08zt1ztvS6Ux6+F+L7Pm5R4Dk+Os8x2hInyUTTEWAx1iApP3fge1jKUqujJEG9Tr1eSm8KUlxHkReWQhcY9u2zXHARhNWAMAgRwiXPNe4EQwYTg/DJA9OsbvdpTs1grWYnShn0+zgKKg7Uq1XMAPrRiLq///ZFjnRd0jSjQCI9j6Bq2e70yHJLmmb0R5OVANJEo3WOlaW1SrbTwXMdlFRoU6CkwmJLaxtRUoUdITi0PI21GUHYolmrMhwl9AYZOhuRZCnKCRBifMQxptwhyTfUCO0dQAvjibS/0dpo0jnhpZkFjNNi6uwjFCZi0NtDa5idWSQZ9XFdD+k4rN+4zKC7TRgE9IYFoScIQr3PksvJC02hDdVKgINhfafPBMYJuCKk0CnKMQgygsBjFIUcOPUtLMx0uHBpjQsXrpHkloWpHmG9wfp6h2Swy4HFNm61TdhYZvpAk73r3+CFGw5ffFnywceGYMfvfg+iPQYUzFtJ/8qTrLcEaRTz4JtneeIr10i21uluVkl2BVOtJnVnhpeLFNmephP4jEZ9KAo0KbmOsHmBzjPMoAsTNG9PvmOJ2qJFS8nRs4dYX73BKHWJhkMu3XiJwhTMzLfZGXgcXzxLZ3vI8RPHqdbrODMVHh6e5PN/+RJ+vUpua0zPTtNo11hZTdm8mvHomDjc6fdpNOpk2mCFJk1G+JUW9VYLrTVxHKOUYm83QWiBqxT/40//Y165cA0pMl544XkOHznAiRMn2dvr0WrVCL0Ake0RReNfj0cffRfTM02qFQ/HUSSxxuaaRx5+M4UsJ3EkpZWU1oZMW4Ry8H0fIUBrgxDgW8ug38cag0KgdIftjfFF/4PAw/N8fM8lCHzCsGSZGmPo94dkWVlTOHDgAMPhkMGg1KS51WcyGqRUCCGo1nwazRrtdhOlLPkEJ7aJQfi7Hn2AP/yLL7Gzs44RgtxA4IKU5RNiMMyx1jJKMhwpcSiIRqPbYKTc11ZzGPiMRgmjJEGLyfRzjxw9CNjXRobytGwsYBHCEPgeQggcRyFlCS7CZgz7XXxfkYoIYzRW52BS8tyQxBFCJDjOZNoRb3TOgFvuRvZ1v7/T3uj/14OOyQEYIAgUqU64vvIcCIPJC+IsY2frBoGQKEeRmZwsK7C6tE8KfB9rocgFaaHJigIESCHJCovA0KhXMMX4D8nVzedZaN2DtC5FXuA7DeZmS2AeqhZz3R5PxSk7eyPqMsNxXQb9Pu2qIqw2QXkIx8cJGtQaLZrVgsubHsqtooLxHE8ASLNS6UEojJRsdHtsXL7GKI548D3fRneniztVxVGGyswMsVehQDB0FTGWIDVoo1BW4RQOthAUmUGlLsEETyUbRDQPNBiMhlxZeYG616Tuw30PHMVvFlTCkJsrm1y9tsI999/LkZOHGF26SlSkbHYtq+e7rFzY49R9Labm6hiR89yzzzNVrVE9MX4ege+SxgnaKtpTNbLhgHRYUKtOI5TAoknSDGMLhAQjHUSWsDhdo8hHvLq1i9VLYB1arSmkgDzNSYqEtBifzGOMIR4lyH0LL9cpp5cKY0gLgzYWecs1x1oMiso+YIIlyyKKoihfMwYlJXmWcuHSBQaD8fWVYR8flMLa/TLJvnedUg6eV56K47hknzYaDazt73vcWbyqty/I5bG0PIPvy9Io13Gxdvz1Iv62Dr93427cjbtxN/7mMRkb4G7cjbtxN+7Gf9G4C8J3427cjbvxdxh3Qfhu3I27cTf+DuMuCN+Nu3E37sbfYUw8HfEHf/wf7e998nfYG+6gpUFLwyiOcRyHqD+gUqngKAcsSK0I3ArWGjyv1CSN4wi/4pLmCbV2c9+E02V2+jgLs4v8Hx/9hbEG7P7ZT/6MjYYJcTzk+PEjdHq7RIMY8GhO10kyqDYanDh1hre9563Mzc/gV0NefvFF/u3//VtEW11Qmv5oxJmDC0hXYKwgCCr0Bnv8r//6X42VR2/zJWvMXz/dIKUsrb2NQZFRFAVBEOA6IUmSIKVA7jN8lPJAlAQTjC3polqzdPKRsQcO33Zi1mrzelIBvJ4E8v9Fj37jrLKxlqOtNj88Pc3cmx5AW807f/U3x8rlvR94zB46dLAc4bEVnn3qa6SjAt+p0u1tk5mcaqPK8uJMabZqS+biyZP3sra2xdPfeLkcL7EZR44sk6QRlWqFRrtJpVHh8U/95Vh5VKVr5xfa+IGDFZp3P3AC/IhnL6+zum5uk3h2NrdBBgSe5B/+vffw8b96kkFU0Ov2Sv0PDPw1lu7GmLHyePChc/Z9b30zqjKHlJbA75NnFp0aHFdiTIGw++OOQFrYcha5KMjz/LYDsnIENc8n8DxcKZk/do5Bd5d//M9+aaw8fup7v9NaHHQc4zkOlVYDoQQq8NBhAy0ChpFLV/tsdYYUheahI02OzNdpBJKaX+BJH4FChQVZYTFGsD7sExWGf/JPfn6sPC5dW7F3TgTdCrvPcBWA3SfHlHHH3wmD1iMcVcNahd2f17YWrCmJF2dPHB0rj5/7n37EplnGbqfPbqeL5/u0GnXqNR/PdffXREGlEpbrRxtcxyFJErI8x4iSEGS0wXF8kiShKApSY7DW8Gu/8fGx8pgYhHd2dnC9UnqvNt0gTVOULk3zyCF0KgRhQBQPEQi0LQiCsPzCa4kfltRmAwyGQ4QSuL6D4znsdcbX8d3rDikKg1Quyg+xwkFKh3iUMRh22NmOYKMcxu70t3jLW97EPQ/diyMVcZoxN9dmbWedQRxxfX0dKy1pXpClmigbTXpZvileR002hqASoLWmKAocta9rYSDwQhAgpLw902wxfyMBH3MHAMNrwHpLLP5OG6Zbr78xbr9mAWspaiEzj30regLjwna7jVIO/X6XhYUphCuIs4QsgWq1hsxLD7MkHRH6HlJ5SCWpNAynp5a5sX6D7m6fqcYs/X6HNBuhdY4XhkTJ+PdGyPKzjqIUpEYJhyTJGewNGA6hUgnxPI9KtUKhwVeGPMuJoox4tG90id2/GH/zaC+0kb5DQUrgOChZQXoa5WiSNAcDxb7TtrEWa1+7P47j3NYb0UWBU6ns89kFRZwg0vE1uA2SIrdgFbmGTmeAChQyixDxiEqtTkPWqNWquMblRk/w9MVNru90ObU8zf0HPLQsKHSBGGUlA7UQtPCpuZMfqssxrtdf2yRJMFoTBuGtYflbM50AKCm4ubHK0sJJwAdugXVpPTXJtNeHfvAfoLWm2+1x7do1Pv7xj7PR75LMTDM93cbzPBylyLIMCxRpinbc25rheZZhXXf/YVmyb621GCFu37NxYmIQfuCBB/ji03+1z6yxzDbbJKKkGA7iEVVZo1ltkIxiCl2gpSBJb80JW6QjcZRDkRmMlWAsg+EAZE5ranyXgO29HsZAWPF55cJlfN+hSDMQirzIcB2P2YUWRT5i0O2ydXOdE2eOUxQFYa3Ko29/C197+glGpqDT2WMYjxjGMb4bYiYYtIZvFmS/czd855eipFSL27scz/fLJ7+UCKHAWOwt2vLfQDvi1p/fop/eGbfp0G+IOwH51ucwxpRcfCFQg5iVf/GrGHLO/v0fGisPxym/uEHg7zMoS8bZaNTHcX3yIqbieEhRWt1U3Cquq9jYuInvhxw9ushG4DDVmmV6usXqtatsbm2Dkky3x7dWd12J0RCNEoJ6yPbmHrMLVdJejlJ+OWOqFJ7vIrShiCKyJCWOC4pCUj4dvxkoJg07MDiexRRSafWtAAAgAElEQVQj0C65plR0Q5cPt1sPYSxFXgASx5FIKdDa3CZRSCmw+/RcBaTxAK3HVy/r9yOUCnD29S+2Onso3wNR7nJNpHEqKYETMF8P8F3J6pbHVn9EEsWcmF8mJ8VYBbnGFAqdC4yU2AmEcxDs67OY1z3ghBBcuXwRqRRHDh3C94Pbm+BbgK2NJM8jjMmQeFhh9l+TE6+XxYUF8ixjYabN2eOHqTjwlSee4OraOlKUpr2uY8GW3xNTGIIgAAQGS5xkkKQ4rktRaPI8w1pLbu1toB4nJgbho0dPkGcWkwsco5j2mlTaM1SrNT7Z/wpKejTcFtfNDQpXkBU5Zjeh0GCwVEKBsYasyCiUxDqCsOKxurZCFI0/8J1rg+8HDKKY2ZkWH/iOb+cPf+8PyfMho42CVEuGhSVJhxRJzhNfeoqvfO2rPPDIW3jLW8/xLd/zrRRuztrKNTqOQ83z8bxKKVPnjm8WeKsUcQv0omGCQKJcgecp0thgrCaW5aWuVGsIlZF0C7RV5EVMo9HYB11b0puNvS1ANGn858oOt4D2mx4UQt2mcEqhsJhSGavIOfKzP8vcu7917Byur1yj0WjQbDbYuHEFB42jCsIpD2TOyZOH8T2fTmeIkopBP0cpzfzSLIN+n+3NDaZnZkh1wTu/7X08NBjy6U9/hg996Ad5+ZUXx86jnxj8wFDxG0S9Ls+ubvPj9z3IT37ou/nF3/k8xgh2trvkUcrx5Rl+9Ps/wC//1seICoEy5TVQQiGERE+givXGmF48TF1Jsrx8+AaVClmWkhmDkBb2T0FFoSmMxnUlYPf1OmRJ/XddrLXEWUmzz3VCsnOTMByfvOK45QYgM4Z0aBkkitAKhr0+MycPsDw/zerGFkW8Cl6dSujy/rdOk+aWNO2ztnOR0PWxxiHwPCgcPL8gThy8YHz9XOxr3zuLBpGVmxgU9WYF1/dZ29vmyMw8DhItBVZoQJHlEY1GG4GDNhph9W0tD2vHfyAB+CokzgYIDEYXvPnND/Omhx/EUGC0uy/UVNKYsyxjOBxwefU6W7tduv0hveFNer0uUirSNKYoUozNGaV6olPsxCB8/up5FhYXWD60zEvnn0OPMt507D6WqlN8+rmvEcVDTJqRZwkxOb70kblFFGAw2FCRZlmpXyqg0BqBJBrFHF6ujp1HliVk2lLEI3zlsLF1nZHW9Hojiiwj0ezbY1skBfEw5dvf82NkAl68/AIvPPUM22sbFFlO4Pm0Gi1yIVm5eZ0knuxmwr4Sl5QYU9aN8izFdUPSNMOYgqmpJkYbsjTD9SRaW4LAIQzLMoXzBu69sZMxCAG01t8EsvBameLW8faNJQsoxUtOHZrnxlqXPDcYUfoMByeOsvSB72f3ygu02ktj5RFHKY2a5OrlFWoVB8cVBIELCHy/xsb6Nq7rsrHWwXE8ms2yNrnbvUChM8IwZGNzm+b0HNEwIs9zHnroQfK8YHMCWqpFkmY5Rmh0VpBmOZub21RqDdI4JRtpjNH4UkKRMDvVpDPIEV6ILTRlQehvT2aarvmMkhSjJUHV/6ZThzEGI8RrJzALQr7GvHxj+Uiwv5NUktFo/PKM9DRRN6Q32KRaD8mKjDRLUU7I8vIcJ08c4OZuFx8IQoVbU3giZRjtYrIR2/0BQjroQlKrOoRenbqVDCMHP5vs9Hg7LCAs1kqkcLm2uka1WmV7Z5uD75jbfw2sFUgBSTLCUaUmDLfB99Z9mqwkYowuVdSEIk4TpFJIoRBCUa81cBwPKUtWruO6YHKOnzzJXnfA6s0NLvz2v2eUpBw+fIgHz50h9ByiYY8LK9cZDsdn7k0Mwr/1R/+GE8dOEg1G4CncIOBwpU29mzNlHAprSUdDRt0+WlqsSQithxIG4UoKrxTLcF235GZrQzSMCBtVuv3NsfNot+vEmaA+3WT54DK94S5IQ64195+7h2azQRonbK1tEeUR3d1dvv6lL7MzHBJFQ5KoT3d7l063UyqexSmpMSR5wQTONa9bUMB+861SAm1hGAwi8jxhcWmuFDnRoLVFa0sYVrG2uF23vX30oixLTOwxd0fJ4XU06X17IWFBIhCuoigyhABHKiww3XD5b3/ge/n4n32BV165iDEFrcOHeeh//iWKdESeT3DcNAKrod8doghxnQBHGaRU9HtDAHrdAdMzM4yimGgUkWYpXsXBcR0WFg9gEWTaYrRhMBgwMzPDzs4Ow2h81TCAUTzCE+VR/uThA0ivSqVaJ0tjtCibQMopOHv2GBt7HcAF7XKrEWeMLdXs/hZyzwfm24xGW/hBBSkMWZZhjMFxHPI8wyBKXx4hEFIglXxtp2i4rQh4Z4PV2S856QlKZxaX/rCDcAqEo/FDxc5uD2Nznn/hGc6eXCKs1pBpjFIaaQ3xICWPR+RZyqAfY6QkzQ3Cc6hUQ1TgUQwSimgy7Zdvys2AkC4vvXieShhw7eol3vXoYxQUuEYirAvSEI+GNFoNylVi4PbaEZPo7ANQ5AVCCLTRsH9tPc9DKIXj+DjKRSlIsxSBQlvNyvU1nn72BV589QIXr67iui4Xr6xwcGmJb333u1hemGN7b5t0glr9xCB8cfM5nnnxSaR2aM022Q4lLwWavbUV1rMBfrVOnm6S+YLADwmDAKsLPGvxXJdKrcpgFJHkGWFFUhUVskyiJAz6O2PnsTBb59zJ05w9fRqngGpgOeD4XFvd5Iknn6PveShj8EyOcn3yIucnPvoRNjodvvC5z/OhD/0An/3Uf+KrTz9LnGdsGYvjSkaJnMjh41bcArwkSfBcHz9wUNKjyC29XnS7ZqyUIk1yVq5eJwxqtKYq+11xe3s3bPePa5OWI6Qsue63FrCjFJ7j4DgOPpbQ9UBohBL4XgObG9pzUwQVH/KMT//JJ8iijKlGle3uAG92Ae03CIIqM4fGNBADLJqrK5eo1+u4boASAbLlMxz298FE4ro+rqOYatep1uulPT0GIUF5HkePHsUawcl7z2Ezw+7mJtt717F2fKU9x3VwTHlNlHAZra/wrJ7ne95/gnecXWZ1bQ+E4Gd++of4T5/+HP/7//P7aFtDGRdkxp2CbX+b/bAthvh+CBiKoiBJUlxXEccDsjTHqdRYPHqcqnQZDSMGccyguwF5DqjbgF1oA5nGcyWO55LnGXICsanr1/u86zuOYjHs7o7oRjHzR1zCSp3RXkQvNwyHMVdv3uDGdgdXQuBJwtDDCkmvP2I4GDE/0+Lk0VmG/S1M4RElCTPt8XWegf1TYynlmheaLB9wdfVFOoPL7HQ02sm5uvIMi/PzKN/HETP0+2vs7F5lqv32faXD4vZ7TS78CnmR8ewzz7HX7fHwww8x3W4ipYsAHKGwWpOmCZmBL3zpa3zx60/wzCvnSbIcISTN1gyOo7AIPv/Uizz+V1/m4Pwc/9sv/NOJVAcnBuG418daF5RCpgnRKOFKMuB6tM1QZ/hW44YuzUYDJSXSUQgkIS5OanjkoTfxwqWX2Rru4gQWnVmSUUKzVkVMIFP4o//wh4gHfYpRxgvPvcRbHnmQhdYce+dvsjS/yGyrTiUMWblygSw3BEqyfv0aMZpRv0Nnc4ub169T5BmFLc0FfcdHKvPXTSONEeWxKc8KlOOQpilh4CKloN2eQmv9moHovpjOMBowO9cgTbPXnuj2znecNF6/G6i6iplmBYWl3XBRyqXINe3pKoNehHJ83vPB95ANhrz66hV8v8VB5TLoDrh4cxcHuPDy85w+e448TWmNudAqtYD+sIvjKRrNJp2dmDhOUEqSFwVKKcKw9CzzggC/EhL/v+y9abBkyXXf98vMu9/a36u39L5MNwYzPSsGM9hmAALgIpoibdqSaFKkTNNGkKZDDNIWHQGZCou2/MFyeKEcYTEk0YZkUZYMGiAJEjQIgJjBMlhmwewz3dP78vbaq+6amf5wq3tAmKarSDP0Zc6XV939+r1Tt+49mXnOfylzlILyNgrDGsIgojSW0AsJvJCLb15kGSVLow3agrTVQOtnfuon+MrLF/nGN5/jcDtg61rGo48+wh999vNkheDsPXfzwqu71edo31pY/7zoiMlsRBTFWFtBzypVvxxtNNbCytohzj32OK2NLkoqnMLy7W9+iW8/83XI9HwoJ9GlnsvFVu/NGlgMJFeFG1qSJMfKFFRBs+UjZUG9rtgpY/rjGfv7+5y/epPrB2McbXEUtJoNxrMpcVAnmeQUswPQbWxREgdNCnJqjSWqTuWeinIUaZrz6quv4YWavOzz/iceYJak9EcTimLMZAjUYgLXp3dwg6KYIcXtsnUbFVG9/pNgb39aGFMipcOv/6NP8KHL1/jYz/wUNS/CEbrqzxc50qQ89bVn+M1P/jb9yQykxHUcjNZEQUhRVDZve/0e3XYDJ3R589oud59erHUHf4YiLLK5xJwoiTTkBxOu2Iu4RUmUW1aEi0hzWtZFICiNZaXW5XTnMHqUcbJ1nP36PoNJH0OGUi5gURKcJbJpuBKnHrHdG7JxbJOV06fZ3h9w6PgRJmtrqHTI2TNnSd2SUPn0D/b45P/2zzh06iiT3S3+8a/9GleuXSf0KzygrwLazQ5+MqO/N1j2slSbVgvD4Zi1tQ0c5VVi4KagVo8pimr1lLKy+fbDEDVXaVJKofXc4ULe3g0v3xP+4/lYSmMZTxNC1yUtKnxoOwoIfQcdedTaIU9/+QXS2RhXOfz4z/48o8EBr3z7abxah8KLcK3l2qU3CaM6xxf83UKI6sitDRjF1s19LJrSzGh2Vuh2V/A8l82NQ1ghKa1hOkzxlIvve5RlOVe+K9nf36fuxaRpxuXz15ZyTsBoqpm6xOQFP/Aj38/dj/X4yh/8DsX+DnWheO9jd3P51jaPfegHefnKDS5c/gRZlpOX5o52sbDf3Y5Y7tyrddWCqIpvgTWW0laoCJTD4PI2z/3TP6D73vtw2w0iN6C7fgztvIBNJjiOc6evf3tWUN6WU1zCgNWJPYb9HOnlRE0HXyjqUQ0/koQqQJoS6ToMRhOkNUglKE3JJJlhjWE0GYIVDBJDrSaoOSs0GyHEKVotfkKZ4yKYJjM+9Tuf5eq1C3z4ex/GCwV+UCPo1Gmtd/AcRVrMEMMS7ZYoO8YTOQqLEbKSnDVVIa46wuaPuZ//f14Px+Gdd99Nu93ik5/8LUpdcPrUO9jcWJ/PdhTrqy3+xac+w+VbewRhQKsZVcgHe/s+LwhChzxLOXTobtqNmD/8whdo1X+QtbML5rFwxvM44q0zboYcmQiOlgF19xgq6WCDQzz0rtMYN8DRE7xsBy+XZEJwYCzOzSk3pru8cuECaA+dSuq+zyjP0U6JqxTZEjJ0/f0d9lJFre1xa3CTL33+Swy2bnLXkTVOrXWIouM026u8e72BKUs2uh3G4xnjyZgTG+uoRp0nP/8UYS2mP03IswqUPU0L7JIPWbUCg5QOQRCSZRl+4JAkM4zRc5slQZaleJ5Hnhd4vken06EoijukgTIv0UWJmmvV/lmKsBCSdiskn+WsNmqsRD7NmkurFbO63sV3Jb//5eeZZZLu0PJv/dsfZDLLENJh1r/Ba6++xnic8q3nXubkO+7j6JHDxI3mUjuMoii47777iOOYqxcvI2SJEJpGLSYpoN5qce99Zygyye5eD6TAOhLP8/A9lzCK8P2AOKwhpODLX/kKf/TZP8CVGcs17DWlqMgWjnX5T/72f8NP/9gP8r5330t+I0TcdwSvAR/8vn+HV97Y5VtPf5OsyEjyKUYUiAqkAFD5Jxpb9dRVNWRc/DOB6XRaES5kdRowUlBYENJhOMu5fu08F156Gm0MZ9w204PrxMc7dDZW3poZMCfe6MqCy/WcpT6X0BGMDnqcPN2l3fQxeYEvA4pJyUpN4ToeV/eH1XHbVtKSAphOJ5i5e4WwllRrPOq0a3VqnsRVDbJy8WG21YaDvT3+5//1n/C5Lz5NFDs01zwOHW2TJimOo2g2a9ya7fLCM9+mIVf4we//MGG0QsdzMFm1WAgl0N/x/qVYDluvtUYIyd/5lV/mV/7uf80ffOmbZH/4FFqXHD58GKMNB70Bk1lGkqQIu89oGLO5uVmhTPK8gmKGIZ3OCkVRMB6P2d0/4B/9xj/nH3zgBxfKY+kifLinGZ1ew5MZe3sJl6SLs3qcMlxj7HqV/9yNl4lffhIHiMOQsw89wnA755RYxc99wqjDkZM1RDBle3+XF4fXmYwypsniq+naqTP84//uN3jHqRa+p9hc22S9cw/r3TppIYmCgDQtObS2xixLq6LnBRw9dpTRYMSJ+87hq4Cnnvwyb165Rl+PabdbDEbZUqLuMPeHm7+uLJU8ijzDWkjTjEajVunq+v58KGMp8gKpqiPmbUH424Oasij/TDthay1KCjq1gIlQnNysEwY+rWadjaPruKHLznaf06eOMRsmrK62cEROXI/wmoe4utMntw2297YZpxm7V6/wL/7h36e7cZw8m/Jz/+X/sFAe7TneezQaUeiSZjum3WlS6oxrt0a0uyvE9RqDbEwYeRioMJa1gEanVXmcicqG6dqlq7z+6qs06hFFluMsoy4vJHaO89Wi5MmvnWd4MOLRhzZ45OQKjtDsbm8zCW/w+S9/m9ffeBPXCZjZhMBxyYoCe9tajsrCRsyZkEIsbuFQGoOQEqSiMGZuByYwyApqpQs84CgBTi1gOhpTa7eQcUwpFA6ViLmtnEcxcx1tZSRyicXgcLdJHAb4IsfRBtf3KQqLMA4my3j6W1/hjTder/DspiKrVJjzEmEFUlgEmnrs0wg6tHyH0K/wzWqJvogFVrqr/Nhf+3fZ3hsxmw1oxC2GexNazSZ5XpBlMB1lCBHQaB/ixs6MvEgqs1i5ix/41DstOutrBEFA4Pv4gb9UD09KieO6NBo1Op02r9+8QqFn1AOHUf+AKI6p1+voUiOMYtCfkXkO/X4f13FxXfeORZrne7iuS79/wDRJOLDDhfNYugg7SUarXkdPBFkyJgk0o96QXPrkYcWG6vZzjrsxNlaUwyG7r7/BeDTk0c1TDK9tMR5MWWm3CY43ObZyFjly+NzBG0yXYGW9cfECB70DLpgpDz1wL64DYb3B9mSEaytrnNlgTE353Lh6jTOnTnLx6hVOnDjJ1SvXSKTDeDwmCHxOHj9Guz0lyzW9Xr+yNV8q7B0Rdyklruvi+ar6QKYTkiSmLGNc18VxHdLRmCRNkEKQ5pUV020rF6UUeVneOX4uE1JKItejEQRIHDqtGo7vEdVD6vWQ/tSwceQubm49yz3nTtPstPm/PvM18izhPT/0o2xduU6rs44tc3whUbbg4GCX1uZpJks4YSslkVLR7w/QRuD6Ci/0mRxMOHR4ndZqqxrC2QwlCoq8JPA9lC8I63W0huG4T11KnvrDr7GzdZ3IF3huQKPZXPx6CIFBVGgTZRgUOV974SXe9d4TPPT+xwlEwmQ45pf/3j/jykFKI66xP5zgCEnN97BAYTTGGnzHY3Ntjd7+AdLxYYmFWiNwXYdSWzQSjcUaCThYoSgxOHHMelRDxgFXhyP8sEVr8wTHz57g/HNfRc/xwkJJtDZoLD52qXb10Y0GSIEvJLXAxzqSUV6Qz0o84eIpRTty2J+UCOkgrEEIiefOMbnFlFro8cj9Z6m7EfW6wnElRa6r4e6CYVR1jD92/AQ/89N/g6e//iSPPfwYaTJCKYdCF5RCs5NKHrxvFVuGvPjKG1y7fo3ZZEQcuCg8misrRM2YdrvNfffdR6fTmZMpFgtrDUJYrt/c4qA/IpmMkSKl015lpV1je3cXowJMWQ1plXKZzRKw4AcBJ06GhLMArUs8qn876A+ZphmOXXyzsHQRnnygA7Nb1G+lvNPETK+8SO69StzdZDic0Kx1cCZDsmRAbnz8pMTdvcIsybgwKHE6oA8GONvbfGXLR+IQOA4f/9hPY5qLF7/N9TU+/h/9OKnwuXHzFtKV5LMJSkQc7O/R2z+g1CU3b13DWnj2udeYac3N7eex1nLx2jaaynBSOvDiG89x49YOmIrFtnhUNFNrDVKWXL+5xfrmOrXIRQqH0XBCHNc4dfpoBV9zA/b3e9y8ucWDD56br5592q0WyWyGpUKRTLJsqaMmVEW4Hrusxi712OPYkRYpEt8P6PdHtLsdVjZjlPcg128MCLzT/MjP/gBJrnnqs5/EJmNeefFF1g8d5ej6Gp6QeEKyunaI1bXNhfM4c+Yszz333Nwyxqd3MGJra5coqnH6HWcYDoccbF1HGYvjBRgrOXb0GJ12h61bPZ577iXKcsqpU4fZvvEmnqOgVCR5ccdyZpHYrDXJhaE/6NPA4/FzbU50j3KPU+eFb15G5ZcxyYgT3S696T6dmkffLRGex5G1Ta4ebDNIplgNuiiYjsacOXmK1954E89dzn0lzbKqN23mJycJoJEY9vt7zCYlcVxj7+oFIgP58ZD1Myd5+pvfpGFLUNXOSwgwtnKTKAG7xBj+vru67PcOWKl16a6scu1gm9APyGuCbJLx7nvv4bF7z/EP/88v88L5W9RrIY1AktmI9737ft7/zg69gyHPP/cNGoFEyII0s4ROgF5iMbgy3EcIgVcquqsd7j/3Dr74uS+y0urwkQ9/BGM0QsI9a2dJZlN2+7vcc/dJZtOEZy88R7Mdkw1dpuMcLxQ88MADXLhwgfWjR/CjxUkjeZExGAz49O9+hutb2zQih43uJve/4ww3rt/g4XP3cHVri63tXYzw6HRWyNIZnc4KKysr7O7uVKw66TIZj5lNp9Xw3Tok+RIonsUvXRXxoTrOFFSakG+PaEyGUI/oZxnXkimNfp8TjkMrTTHSJ1Vgs4TuWpfaw/ejDrcQN/a49vWXeTWdIGY5HQTvOdi+M5RaJIJghaQ/wwlDVtc2mQz3CEIf6cT0evvEtRpFUZBn1fFfAiov0KUGaxDKoSK/CyaTCbPhANdqEJrcLnG0qhRebvsZ0e8PKh0A4c6pmYLxeHKn5VAUBXlRkKYZWZpRi4K543OBlJUXXvldAjzL5OJaxU5/hh/71QrteSjHsNFtcfzsYd48fxlX1Rns7OLKXXphyFf/6ItcePHrnLrrJEXS4+alASur60xGA+Is5sbFV0mTCfCzC+XR7/fmfW6BtRprDaPhjE5ng8Jo9nZuEglLLQzxQ4U1At/3eemF53nh+dc5feosQobYQuO5mtD18dwIbUuSZHFWZWxyHr3nbnaunOedh7r8pffexWozxl3Z5LXemPRgm5VIsLnSZqWfU3c91jsrOCqhHbfxXcmV3S0OplMKaxmMp6znBbEjCJbQStBlWeFYEXMYocEIiZEu/d6IrdGQoL2CaoRMB4LdG9s88eAPE3g+vYMerdUQIdUfG8wJAcKRuOHiO7/Y83CbdRpxjcBVOEogC43ve3jSI/I8PGV54tGz7O8fENVc/o0PPsrv/dHrnDp2mHPHFaNuiM5OUm+62FLjOJZcCIolTkoGv3ouPRcZCHzPcO99J9ndH3NlawshDVEQ0A5DlLTUWi2UUER+xCMPPsbrb56n1oypd1xeeeNV3MsX+Nbzz3DivvsJzeLQJmMMvV6Pra1bWDRhWGmY9IZj0qJkPEsQEnzfISst1lYD1gpmmJIXGcZUVGYpq5mG4zjkhfl/eE7+abF0EW7XI8LMo5dsM5mNq1/q+VzIZ1yq+4RZCtblnUJUtuFSIvyQ+rGjrD9yP6yvUK7v89SL51mvbZKOh6TJkMsvvsSRh08unMdrlydM+zO82OB5Ds+9+BrtRky92WE86HObOFgWVREwFsrSzokSpno9/1nD4YhmLabTbJBlhmKJ2mdvC67M63aSJBRlAYSUWtNZWSEIPJIkIQiqguu5HnEUM0sSGrXoTjsi8D2KorgDZ1uGf347ZmXK4UaTwXiGdQOaNQfpRWyeOsQrL59HFJJbg31Gkxlq7zrPPPs1+ts3aTdqDA7257Chgv2DHq4jKLWhyCbYYnHw+csvv8KhQ5sURUGSpjQaTaQIqcUNdvf3mE2nRFFIFMUYa5lOZ3jRFF0krHRiAr/CMLUaTVbadbKZrqzMVcXnXzS+/5F7eOTBRxD3HmGjXrJRc5klPWTtJJurd9FyVxHDXUbTPdqhx6Q3Ya3ewBU+q7U6sV/DcxXnb20zLgxJMmFvb5/NRo3AW8Jjjqo1YqEyoLWwdvgYa8dO86/+5afobhwlL3KKNCMKQu77vu+hvbJCnma06g2wxVyE6S3XboHAcV0ee//7Fs5jmuSEjk8JjLOc3f0ZeWFBZxw/0iVwFcLmfN8H38HdZzeRKuDc6VMcHCQU2ZB6o0ur7bKx8SiuybFIwigmKSU6WOKhKRIm/R6y00bYgk69hmzFtDorfPUrX+PBh87he5JZIklnKbvDfdqNJpvdNZphg7uOn8ZxHLQ17PU7NGoR3/u9HyaKA9IlFmnHUWRZhpQQxyFaGxzXwfMj1tZ9ZukM13OxVuP5FRxtOp3hOH2CMCAMA7IsJ5ufWvM8x3XnaK8lbJ+XLsId9xRRXKf5WJfhXfsUXsC1Gzvs7O/hugF+7GI3V/FOHaIocoreAIPPuF4nzUb0v32VXm/INwa3eHfrLvorIWff/S7ed+4BdH3xvtLA1Li4W1Ake+hiRp4qDvp90vwW/d5uBbTOM2bTKaUuMMaitXhr0CIruBhUltZ5WbFmAt/HX+ICVj9X4yiF0ZrDh4/M4WaV4WmtVqPdblIUBbu7u0RRhFKKk6dO0mw0yPOcZrPJcDDA99w5eiJnNpsttesDCFyP9e46yID1jQY3BiGs3EfIFX7vU19lpd1l88RJmmGL4NaYZ579Cr508T2LsSVSg+8ownqAFCBdD1OkTHZvUi4BhTp+pIujFApDkjusrL6DWmOMGxl2z1/jwYfux5icW70BoR9w4shRvv2NbzEZjijzgptyh+76OsPRkFliaNYjlJT0+lOWQcH/yNkVfv8bz5D65B8AACAASURBVOMKgz21ihcENIIadQkP/tjPc/OlJ3nx87/L3q3rlPvbHPVi7jtxmKjVQDY6/OYXXqAdt3noqItrLZd3tskzzbvuPkueLf7ZuK5b7YxKTakth+97nMFwwpNPPcv73v8hTFlw+c3z7GzvUGQ5k/6Qf/Wbn2A2HbHebtI+tInVBbrICRstCm1RjsN/8PO/SHNtY+E8rm8PqQUOWkzY3e9T6oAwDIl8xXQ6JhFQi9q0AsO9ayG5Ldm+8gp/6fETXN0pQNRwbUroGAwKbQLSrMALQiZLqNudaCqON7oYUYCROM5REJpZmXFw5BhHOx3evHqZT/wvn+LWrX1mxYiP/63/lM3VQ7gmoxtFPPXkU6ytr/ND738CeGseZ8PFa0ieF6x1uzRaHdjp4SDJc8mtnW1qdR+Eh0XRqFcLRLO5wuUr1+n1Dtja2uKec+dwXJcsS9hcW2d1dZWdnR0O9g6Y5n+BjLly1mBrmjJKZlzq7TFJEkgsE2M41F5jZ3ebZHuXLTsmUgqhNf1co/cE8tIFPCmZTTN816VfJKSRZK8/IfNb+H5j4Tx8mXH88Dpl2cLogmw2YDYckeUJK+02QlbA+Ol0Spol8yNETl4UFEVBliYYTNVfy9yqrwvMipJlpCPSNK2opVF1LHQchaOcuUMrpElCUYsIwwZSykqqbz50K8uSrMjmR5lKoKUoqpyLolhKnAXAVw77/T7G1nj/Ax8iLzLWT9zDwS2fNHsDx1UoW+elr36GS5e2aEUhNUeBBCtENYSqGKDVImWhzEom4/FSRbjdWuH5Zy9gjKTWaSKVxZCR5SW1WgPfC7h+YweFQgtNlpUMJ1OKsiCMI3YH+5WQUHsFgWIyTvBcB89TSxVhVUzYWG3hS8nwYMTrRcK9RyLirKTISi5dvMVrb1zDlJZuPeZYo8mptZhmJ8RvxRzqtJgVUxxTcqjbZbXh0RtnbKyskEwmC+chhEDrkrLUWCH49G/9Sw6fOMUDDz3MhTcvkE0muEqyt7dNLY559plvsLpaZ2W1TRxHd/QlNJZxknL46DHe9ci76R49il7i2Jtk1WYhzXKsUYSui6fAihJr3aqrJjRaO1jjUBQpuVb4ocddJ5rkZY6jKpRIrgvSQoNUWA2TdPGHZjaeYY0FaVAChPYQSpAkJUUBvhdTD5sc9PqEtYhuo8PDDz2C71VtqZu3rnP9+jZ3332OyK8jBBRFiWY5skaWZeRFgdYlukyRpnIeL8oc14sYDWYURtPtdjlx4gSvv3ER13XodDoMhkOMKVGOIhABG2vdaiivJEYXdLtrC+exdBFORy774z474wmpdInqEW7LpSYk2ijamxu4rkDZEqPBCUJaKxF1FRJJh2a7hTGC977n/cS+h9eI8ZsNHNVAmcWLThC4KBFRFG61o20EzOKY2WxMMvGx8wJbrzdIshlKOSilSNOEPMuYTcYkeUZWFuBITH9EWWqMtpglcC7j4YggDLHWq3Y7tsQajecFTCcZyhFYUz30nvLABcEIV4k57AlmkzFRVKPX75NnOdoUhEGw1JEGwFOKJMuYFSX9/h5SRYy2b/LqM9/i9ddvUOts0C5HpMmMyJVEvlvpFlBpXtwWi9FzvYSizDDWIhyJ7y6ey7WrN7hy+QYrqxtsHutw4c3XcBxNvRnQqK9w6dIVLlx4gyPrFRZzMpqB45FMxqhAc/rEEYwV+H51tEuSGYFfKc05wRIQNddhrR1STkeUac713SmHV0PiSc6Ni6/z1Be+xM7lLbqepBnXaMQhtaZDq2ZJRrew0wGH65KjqzVQJWmucYVL3fcQ2eKPTjFf+BESTYm0GVHgUBYpu9u3uH7lCo3Ax/Md7r33HSSDXTY3Oniei+vOBZcA4bh88KMf5dH3vp/Dx06A67AMd8UKiVQu1uT4rocrDb5nyYqUOGzjuQohE7LSUBaSvIRxZqmt1GjVXNJZj8Ko6rRWwGiWI5RDLB2sWPxzcVUdK0HMi7ByQFtNksPrF65y4vRpGvEqq2srPPiud3Hu3L1cv34DBwESrt24TpJbDB6jcYZSqoLVSbEUdND3PRr1OmurbdZXG5SlJC8Ms1nK9Zs7uE5AOZ+rbG9vgRC0Wi3SNCXLEpTQWANR4DMYDJhMJoxGI1xXsbKyuCzv0kX49PFT3OOfwBo1V7834FTYRaE8wBI4Dp4AlKqEOYqSEo1VlSiz54YgJMbKOdbRoh2QS+y2Zrkm9EO8KEQIi0NIWIuppS2y6RRJiRBVj3Y6q1hHjUaDoqjcCmbTPjt7e+zu7zGdHy0rfK5EuIvf2VEYVnhfbRA4NBp1HMfB9QNgTBT6VZ/JqxT5lVNhTXWZU+YFcRSyf7DP17/xDEeOHGd9fY0iT/B9fyk2FFRAuVYQEjiKN145z9pKm4svPY0UkoYX8NWnnuW189f48HvOcWtvghcf5ZWv/B54HmEtZjYaIR2F9BxAYI3F6oI8n1EUi9/cO3s9No80UCrjyrWXaXdWMTqgt5vSOOkzm06oxXWEEUzHM67fuMW//7MfY+fWNb76lSfpH2xx6PAmtZolrFk2D60ThzHaSrob6wvn8chf/j5WLk648ca3GcspN7dLtnemoLf5Jz/xV7i5P6NTr3Hm/iNQ5Cg/YuOdJ1Fpn9n+Hn/13cfIkz02IsHIDZheHtDsrHD65EkO9voL51EUOVKqCgshBMlon2ee/ALPPPlUNSuIIrxmjUF/n/Ovv8zJoxvEsYdSiiiu80M/9MM8+NBDrB87RiEUpRXoQuDkFmFzcBdDBBw61EXJnKAuieM60+kU3/URxhJ4EkcYAr/O3mDMzl6f7b0ZG4eOolSDQa+HKzx0ZNkdDpjOIM0N42kfx8txl6C7hlGjEh6yJdZqkjRla2uLnd09imLMZz/7+6RJwUee+BD1eh2Rlbzw6rfprnbprnXZWNtkfGLC1776Td77vvfj+z5SSTxPznuyi8V0OiPLMh54x91cffMCQ2FxwoDOWpdkVuK4hslgiOu6DIcjstzgeiFCSO55510oEjynhrUVdng2m6G15sGHztGMl5AYXfg756GURFkLVpALgfAdhLUobapVWTkIJckVSCTKUh09HActDDU/QCCxpcE4DlYqsAZDAUugEoQ1c6KDgxTgOBIh3ArQXs7RmFbP7ZMCpBT4fohUBssM3/fnx5hiLqBTiccUWQl28YJTibRrrlx9EylcDg56OJ7LZDrG6kqBKYojpCNBierYX2iMFoxGU3b3d9jd2cVxHZqtGnmRopT4M6EjIs9FmBxRWJSn6e3uIJSitBB4CokhmyU4nqDIMg565zlz/2NErSbpuM9rLz1fTe2LqlWipMT1XMLQQywBxvdqddLBiMALacQeZVlgdIkjNdLC2btOYc2M0A9xAwcjNds3riKwrHQ6BGGlKTAZ75Hllt39CZ2OSxgFjJZpA7iCIG5QIAlaMatTSzKdMXMFJ1c7XLw+oKhZPEczTQu29/cRWrDfG5Fri5P3UIGg3mxy62CPskhJiilpnpJkS0hIzlE/EsgnUw53Vym0ICssvQPDNE3Y3ztgo9OkVYuJgxDhKE7cdRfv+eBHePyJJ3Bcl9xUTjG3kTia/3fd6D8prNbMKNDWMh4MKLUm1pJinOFvNsmLEoMEqk2F7wcUeUlZVMQN5VgKbekNUrJMUhhNfzTF8YOlRN2N0ZRlgdY5RpcMBgMGgyFlUfChD32QOK4RhXXqjTq+V0l/3nfuHL7vV2gfpTh16iTGQruzgi5LhqMhzWZ9KZzwbfODZJaRJRrpB0jXoz8Y4HtNlCOrQagQrK52GY5nOK4zl62FlXabna0+/d6EZqdDp9Oez3wqI4tFY/mesBZYK1GqEuAQwqLnjCDH9ZBKUWqNnXPvtbGUmIpxYyVKONgsp0wSXN8gpIMrJTJNQS6+inkKhNEIY1FS4ilBaS3CUzg6wIpKTL00FazHaF09DFIg5O2ji7gDMQlDn2ajSb3WRqnFL4vrOtiiZGdnj9k0oz+asNs7QEhLu1ZnNp1VO+9sVgm2GMu1azeQUtLrHbA/2ENJxdkzp8iyFD/wCd3Fb6TvjNJkuFTC3Z47V98SAjV3AvA8hzKbceXqiMK4nHvwHK8+9wzbNy+RJjOYM+48X6KCuTKVlaSJIS8X35VrrRHKIYgigshjb69HWVrSpODypTdxnBM0GnWGgzEIRaNR583z59na3iLLUh546B4816XfH9Fd2yDLMtK8JC8TinLxojPeGeB6h8jzjGYcEMQGrMY6krNH1nnz1gGOr9Cui6o5jPcOyEZT8rSgub7G0PTQJoXAw/UVzUZMliqGkz7SW3yBNEbP9SM0eZazubGBtZXVkGsNo+kUowTrnSa1KKK0ivc+8QE++gM/wOaxk8zSlNLC3O/njkvNbUusRaN3MCL3crQAcHA8l92DAf0bB/ihM2//gDGCWhwT1iv1tEKPiAKXyWhA1k/Z3x/hRy3SImea5mSzGbVabeE8btt83X4vzWaTWq2GlBLf9wGB0ZZSlxRzOnQY+mitq02KUdQbMSBIkillWTIej/B9dylomFKKOI45885zPJEZvvncc8zylFpcQ1CJcYVRjbLUuEFIUyoEguFwCNpF55IiL2k0YrorDaIoxHVcpGOXYu4tr6I2zXE98DwXZaqeju/51S9X1QPiSInRFZYRKXDmODopFUq4pDqj1IbI5FCmSAQ6yTHOErzvNEEqS+g3UEoTKEmuJbrM8T2F47gUpsToAqslaZljpUI6gjgOOXPyHk6eOMXJM6dpr6/guT7MJ9imXHyymWYV8uL0qdO8+OLLFa1WyAr+kud4gU9/OKA3rlbGPM/xnIqBNJlOOHz4MN3uKoHvVqKq3PaqWk6cBaqDhAWiOMZVFisqIRyLqP5sIXB9Lr1+AbAc3LjCancdx/PxVIGp+RS5Js81SVEiqBZZKTTN2uJT50YQE62tkxc5jiup1eoo5dJqVmpyYRTglg5GS7Isw40iXnvtNRzls752iN3tHmfvPkut1WEynVR+dEnKoe4G0RJg/G8+f4H7Hj7FxnqXdNJnWmaV11/sIfsTvvfxB+lPE0QUkYynyJrPJDdMc6i1Auxqm/0bV9kQguNnjtA4VPDlF3cYFRlmCVshrSt7nDDy8efaIlmSUuQFRzZXQa2R6ZK1w8d47LH38uhjH6DRXcFgmSbJnKQh7ngFirl27m1FtoWvxwuXOLLZIYo9otilEcSodo31Zoe9YY61ObFf0G1UcMJxliEdh9FoxMQa4ppC2ZiNoy32BgO08XDDBraQ9Pq7C+dxezgtpUUK7hiZWmsZDAZIKYlrEY4DFoEuS4zVKFdh57voPDdI5SCEQik4fHiDPC+XErm/rdvSbDZ44oOP88QTjyOFJZn2ee655zg42MdiOHfuHKurq9TjDmFQpxbXMMKQlilCVAM+Z44bT5KE8Wj0F2tv5CkXU+ZYaTACXN/Fc4LqZpgD860xOMqZ893tHA4mcJSqWgJA4bpk0mKlUyETIkmRLQ60LqmmtFlZEipJqedcd1XJzMn5zek4Ctd1yJIKY1mWJbbMuHTxIlhLGPkkeYYnq51BOksoi4RT955bKI+bN3eqB8LkCKWRlJjMkmVQzDf2Ut22yNFkWY5jy7kYt2BtbYU0mTAZFpSlRimJq5y5UMty7QglTDVMKBJEWREDSgPaaEoDjhV4jiKqeZXgkJKMhzugPUoks7RafJRSRKGDcsBzPGLPvXOTLRJFlmFsTKE1zUZEWRhqtVa1ixj1CUIfzwvwfb+SAdzb49jR40ynKVlWcPjIOlI6NNpNDh07WnkQao0vBK63hGZDvUGOwvd8pmXJaDbFqYccTCfkVqOLSoui35uS5hkuhuv7ewz294mCgFxICm2YJjle28dxKvPQ0TTDmCUEa6yttDGoJFO11gi3ovyK0EUoh2MbJ/nRH//32Ng8Qj0MyTFYAQrB/v4+1hhWVlfvCLxXWPeKNLBRX2wItLU7JE8NQSg4cXyDKPCxroPRFREhCAPi2EMLi/I8XOmgC422lsIYGn6N0lbKdF7oYUVJvdGtTrv54q44r7/+OsYY4jjE9yr5AKXkXGmuel7rjZjJZEK9XkdKyfb2Fq1Wm8lkwm3Zyiwr8IOq9xqGEbs7B0RRxHsefmTBz8VQlhWHwHEcgjDAkVD3mjxwz93s7++T5QmHuyv4gUfoO7iupCxS8jJHC43rOISeC6IEBCr08WQbrRdvz4g/j1zi2/F2vB1vx9vx54vlLSTejrfj7Xg73o7/3+LtIvx2vB1vx9vxrzHeLsJvx9vxdrwd/xpj6cHcYJDZqo9cTWgrPKuutAbmE04h5vbrQAVzmv9ncUdubC48prBWVrjZuXPq0c3mQuPeu8+esGmSsrnWZmJC2o0me1u3kGKKcFwwmt29IXffe47BwS7rG2tcuXKRIIgodc7RjQ2uXd3BGEF3Y42iSGm118DAK6++wM3tg4Xy+KVP3bQVKkYgpYOSzp33iKgsbRDVgMzOIUZ3/hmL1sV8mGkBD20EZaGZbF9FWMMnfvHxhcffv/JLv2CjKKIsCvIiR2Q50/GA6WxMs7uJROArSZKPka6LowKazSaOE1AWhslsSJZMcKRDfzii1qhVmO/5JP/X/un/vlAuf/vv/xe24yUoJfADD88t8RyL40gwHiBoNn3W6wl6ljLqjXDqES1HEHiWQgvSpCTXDtPMocjACMEwn1Cklp/+j//BQnk4sm6/23fstmxTZTRp5n/H3PfstrDIWxbzylFIpQiC4A6m3PM83MBn/8blhfJ4/tnXbQXJ4k+FUNk5JlVQDQC1Lvj0pz/F448/zlp38y0ZzHl+t7Hkjzx670J5/PLf+SHrez6FKSltyfkXbxHXAo6cbiKNrOjqQiKsoijzSrGtqFAZWZGTW1MN6ihwCo9xliB9SGYJsyl84dOvLJTHR37hR21txcf1JcItICgwskRKTZdqsG91wdi1CF8hbIlKcvSkJC+mFBisdhBZyWyQUiY5WarpTWCmFZc/c2vRZ+ZPHYh9p4PdnxaGiuhVmgxtJbtJ5Uh9z1q42H26yDd9Z3i+Q57PtW5tZR0jq2p8x6ZHCIHrzt+fFJRlMb9hvhN2NcdTCYMb3DYsXBxu8673f5TXnv0WzcNnaUlB1DrE7kGPZryKcsasdgJcr0aZDlCiZLi3Q5mWFDYljAOK3LLaXWF7b49OvUUYhgx6BxTCIYpaC+cR14PKvmj+8Egl70CI7G1LGCHu2K4YXU2XS8BYgTJh5a6MhqJEGoP2XJy1Nca9nYXzAFitCQbjHucvXqJWq3N6bY3mWgfpdHnymZdwlMPRtVU8oXGFAw7sbN3i8NoanjHUXMlwkFGalDPHN9ClZpLmbI1nNJbAgYr0MuODKevHjzCdDWh1YiyCUng02gHS8Uhw2Ut8kuGQ0jqMb93iww8fp0h6OF5IEPhkmcFRGu0KZlnOVApKtYytkMDY7xbHr15rrRFS4DouQRAwHI2QjsT1vDsOKFiLtgatNbPpFADlOLiuu5S4kpSyotV+R/H87jyhovHeLqz//Dc/wcWLl/iFv/lLNOqrSCkQ4i2JxD/LQD32QkpjcHGQBh5+6BQVX9VSKIue45mTLAVTeeudbHbxhUdZGvAkma2gV8P+FJmVSAuzrsYJF1e3i5t1ZFRQeCV1q6gJi6TSSJ6KhDLv4RhDww+Icg9VCCY2Rbw8IGlY9CHwhEMvkjjCQUQCkWlaniTMl6P6w1uVWN/x8TOVdjUGr9Ds/+bnuPW5L9N69AHCn/woGFMprjnenU1noQLSPGCSZLz25sukswn3/LW/IHsjIeycMTK/cexbhnta63mRtThzGqOSAqVu75Alxdy6p2LH2cozTFiUdBByGYsUyWw6YjbcY5aWPH73fVwLIqJ6jYOdS+ztgJUxe/sTzhxfZa83YDZJSWaVd1im+qRpgrJwdHOTwuR02zVevnSD0WRxo09HKcDMFx9bXRdx+8FSb+1c7NyYUVbv25eWUhusdjFWYCgxeUo2HZFpBV5MuEThAxClJk9zJqMpUVDHd6vdTaE1fuAjbAU0j6hIA5maEIcBrrA40lBoS5am+EFEJAVGCqJak4tmh9Bf/OZ2dcIrz36b9fV12vUGrhKUUqGCWiUEpAuEF1SFTEG3WUdRqxiXjqA0BqUEnrEUokRLgVEGVxuKJbQSbp/MrP2T1UCsqR6gj33sY3z6d36Hq9euIoTEcVzuv/8BnnvuWaypHk5jzFzLFybjMYVcpgi+hfH9k4ro7SJsjKaSQXR4880r/MLf/CW6qxuV8M/8+7/76zI44dir4UgHayqFQd91cVW16y1tZRZSWMuVq5fpDUZoXTIMDujEEautBodWG0S6ACylmyGFIvBqTNSETC+Oi3WjgK6okdmSNMrIAhffCfF8n5YEZQICURDlwM2MKA3JmjG3ypz6Spu9YxllafATTdFP0KL6fLWjl2LdjvOULMsqzz6jKfP57t9YtAE5HLP95LfY//XfohwPuXb5Cvf/+EcppSJLE5xAoaRCSIe9mcusyBinM2orq3Sai4uRLV2EdTnX5zXznbC1CPHWEdvObYdvu8uWRlTYRqA6ss+pgBYwb9kCKSNQS4hveK6PV+tglYMSGfVmCy8KiOo1dH6U9kqd8WRAoxkQxiv4sxxtx9RqMSudNkIXCBHgB7A77uOFMTJwuH7jIkIuTpJwfYWgWoiEMHdMOoWo2jBivsMX1txxcM3zlPFwjzCIUXbO4HMsl2+8ybS3T7O9RlpaRDoEHlw4F2EtnqtwHIlBIx3JZDLl+s1btMKAZJrSCGOEKbEI0umU2A8Q85ZRXpaMZzNcP8STLlYpcqmwZYm3BBOp4QdcPX+N1zfP897v+QBSVQuOwmWWpcQ1H4XBmoxGXaJkweXrexxfr7FSr2x1rC1R0hC4BhwHVzoMZhlmCeH/alGXFQemMjlC2urEYub3mjHw/R/5Hu47d5ovfumLfO1rX+eJJz7IX/+Jv86v/urf4xvPv0S71WE46FHkGa7nIl2B9ZYz+vzuuL0p+c4TsRCVNOonP/l/8B/+zM+x1j1MliVIxfx7xR8rwss6r6jdA9yoSb2zilOrMNqOlHdcpXvDCS9evsxzz15DlxXL9Joa0O3UefTuAJIreI6D77o0w5AybhI02rwz6i7lJKFGKdEe1DwH3RJkR1ZIYp+ZCqjrPaLAwXFL/EmBvDjm8NW5BEHus3a6i7dqGPuGcpLhe2PytCBLS6wqWEJhlN3dXXRR3jGPldaihUBahXtzl91Pf57hHz0N0wnGMajRkN7nvkr9+z6A5wdIqSiUQ1KGDJOswucLiIMasf4LlLJUc+bV7b7wbT8xsJj5zsLayoLFGos1Gn1H7b4EKgGbO/qfFgQKA+iiJGKxY00ocu695x1EUcDl6ztcv/Aia502RhuOnryHV1+7yHiasXuQsbt9Hkc6OJ7PiRP3sLmxxmgyphj10UnCjRs7uH5IUWRkebaUhU4ceyibowRo5VWOr1ZjtMZ1AlwhKJKEa699nTQv8FyP3/6N/57e/lXa3SP88E9+HBU28WMXNesTlFM4uMTo2qtQpMC/uXAun/vmS+A4ZFbhCwdPukR+SCtuIITCqdUwuqA/GKJcBx/DYNjjYp6w2mxjgjrg3nZBqyTepEUKgbuEnc9Go80Dd7+TW29e5zO7v8tf/RsfpRlETJKEOICaKnBkgt92yLMp17YOuL6vuTAMGCM4EjiVEaowhFHVzsKUbNYjhsXiC6SwlZi6cB0cz0MpSZHOMNpgdXUisWjGvZusx4Kf/OEP8ws/9VfwvADPk/xXf+vn+aW/+9/yzKsXqK83abUbOJHP/uCAOKovnIe13GnT3XZOvtOymmurGGv59G//Fk8//Q0+/vH/nFZzlbIs5jtnfWeuUrX/JNZWbMZyCebeaGebgGvsv5bTnxbUjt7F+vo6x06f4rNPPsNr56/QH01YbdaR1lAUJeOkYJIavvrKNf7yR96Da2dMsiGbR85QrzUqKzABzSVo3GHD4vQCjoxO0LnhcOaLl8haM/bXGxy86wj9tZLSO2BGxpUy42ahefh1qDGFW5e553c9yoZi730hr3zQoTaUxGlI4kzx0yUWaVP1c4VVCCrzVeVIiqtXuPST/xlWWayV6KLSPFFKcf1X/0fqn/xdDv/iz7Fz9gGyqWa4d4FLX/0CSkmMUMwmQ3q7O3z03b++UB7LD+aGA+KgUkETUlbFVhsQIIWci9FW1uBm/hX7VoGWqrJ5QcyV1zTzm3K5Htcrb3yDY0fvR0jBdNyjGDlMBwOsFSSjA44dWmE48pD6DZIUUp3hBgH1dsQXn/w89z74Lt5dbxIJh//p5ZephSFlloDNCb3FL4t0JcpKpAAhHFxbUKZThClxsdiyJDCW8d4BSEjLjFuXXkLqgp1JwnD7DVY2jzGZ5Ix2ryB1ibaaMp3AEg8YwJmTJ0BJDvoHSFvZlruOi+/7DMZTsAadp7gSRqMxw2lK6Sn2i4L/m703D/btuuo7P/vsM/7mO49vnp9Ga7Ak27Il5AFP2ITEgOmYggqmQ0PTVDkhVZ0quiqdToeExjGBQBcQM8QMtgGDBxDGgyxbQpP1pKc36I13Hn/3N595791/nCtZVJzq3y+VVP7Ren+9W+++WnWGddZe6zs0gx2cyjh5nCB0CWMJlFKo/Zo3ivmpFJqNrRVSJdhdu8FU7b304gFCOpQDm0pgUGhULukNcvIcDs5N4/sOocpp9TRZpimVHRypEVJjRIp0HOwRqNxmXx8kV3mh1KdylNFI38MVNuONKvWSw+LiNBUbmttb6DTCdiUqTQkcxXu+92EurSxRW5zCrVUI4xAtJXEy/IdavIaaC68dkxTduRACx5ZcuHiBn/3Z/5WZ6Rmy7BUBJ40xiv11HYUG5CvjixzPG/7jOIhztO9TqZeJom0uX14m7YdUApflzTb9KMe1gjwr/wAAIABJREFUHRo1n5nGOLZjs7K1SydM6Q0GXFpa5+RslZm5Q4W+gpSvpiTt4Yuf8hzywykb/Zs4q3N4zUmmt5oc3Nhid2OP5ok+G4czdsY8bjHjzIQ5L/avc94PCbKAk840bgaeJSn7HpkWJJ4kyPW+xsZw0W7vUB0fQ+bFhxHHQe42af7GZ1A6JVOCTEjaOgJjqFoeZWkRX77GjY//Dv6//1dE25tsPvcErZUr+H4Jywuw7cJNetgYuQh/8g9+j5/7qZ8hS4vZkPXqHLeY72ptMK+xYZG2hWM7+w4UhXptoWcAeZoWD5RV/L41wvFqbW2FhfnTpJmFa0turKyyvLpOpVLHdiVn5xaQUcxOs4/luAhpY+KYXjumXKqgkpiZt72NrWtLfO/CIrZl0+u2efLxL5NEw1MOXVfgGAsLyDONjHuE28vkYQ87qBMOQhzLJhnEuA50dpfR+YDx2jhRnLFy6QnGSxlCG+htYLQiSlNUFhKFg6HzAFhcPFgIKqUJg0EPZTTGEoxNTfDy6kpBT80zxgIXL6hw/OApjp45yY1LF+jubNPutwiTlOaeYHtijEqlghGyGBaOcvJ1wNg50nJwHNje7uCXHYQIMbkoPtA4bG83GfQTHNtn0N+m5M2iVEYvNzi+T19lOEJgK4Nj2/SjkCwb/t44jSpxmlCrjGG5Dr1+n1KtjOsVjhJTY1VmagEHD84SdzvcvNFjcmYMITV5GlMZ83nknQ/yzNXLfOPlC/T3tlBpji+Kzf4o8UoHDPsIB4pmBVPIwX7uz7/Ij3z4Rzhy5AhxHCOEDWgsCXIfyVG8UgXNXwiDJSXnzn2b224/NVQOURSy1+4y2agQ5Zp7Ti7QzSK+/dRTzI3PsXntBkmaMHF4krvvvh0sSeuxx9na3iHt9ql7giAIcB0Hx/cQWORZhtIae4SdQSWukvZ2yBoJK7cdYeP+e7n168/zzgs3GF9vEg8SDm7CzfmUqXUfZy/hc35Eq67YcDpcnVZ4FYtbJyUVq0LiCBJLIi2HnOGlD/70k5/k3jc/QKVWw/d8JuwS7T//Grvf+lt6QjNQgo6raY9buELSywwHepoACy5fIr30Iks3XiLtbDAxMYZGIP0ywnNozB4eOo+Ri/Dn/vov+OaTj3H/vffxzre/i1OnTiOxQO+PIARYrsM3nniM8xdeYmNrnevXrhH4PtVqHW2KLaxtSd78wAPYto0lLN7+lrdTHmER5dg1rl29TKXUwPcs9iKHNEtp9frk2qKxk6AzTZLm6ERz4NARjp44ye7WBouHj5Pkht/7ky8gjeKhRx4hU4rxqQmWr75QWJoPGde/+jl6zS0Emr3mLp6OaAQ2lskRQZVMCRAeJoHll1/mwre/QcX38QKb5t4W25eeolPTOL5FSeeEg5g0jLEtF8uM1glnfp3JiQnuP3YLeZoSdzbJdYZjWSzOz7F0bYlet8v8+GGsoM6d9z3I3PwBmjttlldW8R2HMEpZ2+mwsfYkh48epTY9zdFTt2OPMBNe3e3SmDtAr7VHkLn86q98ig//w+/jxC1z2E6GUTm7ezG2qBS6wsCJQzZW2kP1e1QnpgvVMWXTyQ0BIMnRVoTvDv+S3X76IJV6jb1OmziJiesOvjbMTkxQrVYwWtGoVklyqM/McXdjDMR3IJZRFHJwqsQ/+vEf4PJv7DKOjRXnrDz2NHqEDhS+Ay17ZZZrTDGqe/Svv8Q3v/lNfvqnf5rp6ekCtSEEYdTHsuDRR7/EZ//kj3nooYd45HveyaEDZ8nznFJZ8o8++mO84x3fM3QOb//wj9Ld2+PFJx4jcxJ0xcc3kxy5bZ7Hnj5PM8mYm5rg7jtvZ3J2lun5A7x4/jm2dkps7/WwPZ/G5ASxMiDAcSR5nhI4/kjCOaXNnFN/O8/e5hrr3uNs/uxtNH/ynTzfvcm9X/0ywctt5rYVd2gJWY47Dv9SavrzDoMph2tnbOJJl+6sy26msFWGpRUd20fL4T/SDU9y4bGvYVQOgUvl8Zc5sd4n1hGD+47gz43hlRxmnUL3xnEcult9WheWqaz0qf2Tf4H/wAk60x7V+hQ4ZYLaOGWRIkcAGYxchB0BrW6LLzz6Bc699ALvfvf7ePD+t3BgdoEsz7CE4ObN6/zGb/06rUEXpTW+Xejrrm2uF92ZMRituXTlfAHhMoJLL13ktttu4wc/8A+GyqPd7eHlhoP1Gn2lqVU85mcabLcT7rnrDG4guXGjxX333o3rlHn/9/8Av/hv/zUTExPUajWaYYYv+yRKcP7cc9z9hruJw5DTB6o08/Ghr8f6+WcJbEiTkDxs4Qc2OBWUyXGMJIkyFC5RnNNrrSPSkCxRxHmCdC2SOCMJI3zPBZViTEaWRbieRIjRVNT6gx5a5UyOT1CvVqlML5LlCWkc4giXaqVGtz+gG0W0drv4ly4xc+gUifTZjVJM2mMQxsRpzi1Hj+L7hSvu2MTU/slnyGuyNaA2tkC/HSFEn2iQc+7cVWYOTjM5VcFxPMYaEs8dI0lysjQh6Q3Y22yxvdlC+jM4prCskbYBaaNzjdA2Jh8+j9bWBr12E6RESovpRo2pchmdJNg6p9vtMlYps76xTX38DIHrYzsucRRhC0hyC8toThw5zFijTm1qjp3lNfyqj6VGQPL8Z3CyV+bRhuef/zY/9mM/xoEDB0nTjFxpHMflF/7JP6fd3aPdabO1tszE+CS3nL2DA4sn8Hyb8y+9wEMPvY0PfegHh87D9Ut45ZzS5AJjB44yP3eAyYU5mttbzE5NMDVeo+w7TB06XNj1ODZziwdo9TOa7S6+79LpxyQa9l5epuy7+JbhxJFFjBhewCc5ZhM8v8ZdVbilm/Onn/gNmsdm4ewszx/wePxvnuVYM+fHK7cxMTA0IgdPlJi8AeGKxt8OScZimoc8ePMEoS1QImFg2eQjjDW1NnjlMYRRKM9mYqNHlqT0pjzqty0UMqf7/53ruoVvYqNOOl4nfH4Z69srTC7tkc8cJrc9jHDwbJ80T5mqDw9zHb0I234xC1aKre1dPvWpP+La5Ru8+53v4uCBg1y6fIm/+OLnSJKYkueBsNGZKqxMfLeA+xhdrKXzvJgjA489/hjPPPf00EX49JFbyLKU8fl5Fn2HqNNmO9CMzS1j6T12VnfIBm0e+HvfB8E4X/n2eaJUs7ndJo4Tjt/9CFl9kisXXqSztc32uReQ0pD0moTZ8F1f3FxClEtIWyJFgut6GAFRnKHpo1OF0iEq1vS6LTKVEziSe0/dwtLSEp1oQHvQRwiJJazCJFSDi2BUxKNlFUpUu7u79Hs9GpUSniOxtMTzS2jHozI1S7PXptmNWAhDSn6Vk8duYXdrk2tXvo2jcqIkolwviBqTk9OAIMmG337bToVOd4djx09Qq5xFWHUWD88h7TqtbozWXTQ2Ya+L1tBq73Dj4lVcJ0TZ0wxebhKQ09nd5K67TpBbILTESsEawQrbkQ5RGJEphe06HDp0iMWpSeJer7DEsW3K5TJ/8KlP8d73v4+5+TmOnziB6wfEUYTjeggdY9KcyUqDVquD7bqMHZijvbI78r0p4hUiiMWXvvglfvjDH+bokePEcVYYFFiGly6e56mnv4XjO0hb8siDD/DAW9/NW9/6EFqnPP/8k/zHT36Sf/OLv0Q6gvIglkNQreM3pqnWyjQmxqnXy0RhnbMnwXEdnnjiKR599MucPHGSTqx4+dx5drZ3OXl4ljfdcztCK1zfoxsVeOJBGNPsp5RGcJ/uNRxeGNvjtB1w3PF471bIC0+dY+P8s7xwT4Onlq/zdJbi7AoWO4K7vRne0GhQsT28NMdf7hCvJATLfTr9nP6US3kuQFVtOiMsCCdm5hjECVESk6U51TilJ3OyqXG8mo/OUgIhSTEIC6Qj8aXLYLIOdx5h58JNFla2qE+VaI5NYlRCMmjiVGvI+vAOMCMX4Z/9Z/+KdrtNkiYkaUo0SMmzjC8/dZ7osWcAKM0c57apg+zvcrH2Z6aaYl4s2NdE3TfXfAXW9l2xPP+FGOiMQ3NT3Fhdp1wpcdeBE7zlre+nsjBFudxAoen2I1a3dugMEo6ePE0WJdTH5/FrNVQSwtQUB06dYm3pBjvtNrWKx4MPvpFHv/atofOwRMwgivACHyE1ymjiNEMbi2efeoZWq0UURbT7MVmW4lig44gvfeFRarUyt955BtcWtLs9qr6NhbO/2MypB6PNHefm5nDlvi6xMYRRm+31XVauXWN9bYnG9AH+wQ/9MC8+/Thziwc5c8e9/M2XP0OWa9705gfZ62yz+uI56vV5Ttx9H6VKhSRW7Ow2RxLLngi6OAclVhLywrIk7A8YfPHPmDlY460P3Y7wBI6s4uU+SRqxvd2iffE6m3GGWx9grlynF0KmbF66us7kmM3ZU4eZm5pAm+EF76tBiSxJERhMrom7fRrHjjN/4gRCFBKRzeYujXqdqZqPlbTZWbpErV7HsyyESknTDE9Ba2WdyPEwns2h++6kNjW8fi4UmsKWBUZkfPWrX+ErX/kKH/3oP+bA4uFC3N32+JVP/CKf/eyn92FpLskgpOwLpht1Tpw4hrDgp/+Xn+Ftb3sbv/Zr/4EoTLHE8K/wo1/+KkG5gUpjSoHH8tJNXFkc5wPX4pbjMzRqD/L//tYf8/Tjz2JZhonJcR588xs4e+IoQak4KVi2gxMoHHcSobJiLjzCyWDp+joX7S7P2S3G6j4/Yk3xg9EUcx3BzbWAf3gq4K82XubyC7tcbVi8+CbJ5Z+fp5JoSk3JgWfHKO8oxvc0D113CS8a2vGAc7M5N+aGHyV++Cd/hn/xv3+MgABjZUQypW9Z5FNleqnFeLXBoL2DjSYKO/RRLO86qCzi+OFF4jceYefSOjMvXse87XaypE9nd43awiOEwX9HnLAM6shYI60UW6YIFYPMEJaLFD55nhckBOHtEzEK1pjRusAOy31WnbRR+8gJS1igDKPgI1pb29RLPvOLx5mdn+P0A2/Cki67/QGXN1aIkwStBWGUEMYhSmkmDx4uMKJ5xLlnvkmtWqPf73PnGx+kekLiDTbo9ga43gh+WeUyg7iLUUmBdxZgVE6v02Vpaek7gtXkpElIqjUOFpkFnThkdrJBlicYISgFLukgxTIp1VIVkw/ffQKsb2zQqDbwPBcpobOzy9Lli4TtJlO1Mo5liHsdDp2+A60NOkt59C//nDjTeOUSdrnK+Mw889OzGMtnt9UjiVOq5TKOPXyno3REqTxGbcrncNVm0Ac5HXP3/Sfxgja1iWk6bYt0MGDh6Bluv6fGX6sv0t6Cza0290w5OOOCZg7lRoXNpSUev7nOnXceZ35meIt3KWyqtTrdfh+/HDAxNUNrb5dTRw8iLAtpTRKFfQQKVM7M7DTLqzfYWLvO1MQ0rlPDL1epNcrkdgGj7O51KY9NMDE/fB5af4euL4Tgq1/9Gh/5yEc4evQoWaqxHcGVKxf5s8/8YaFnO15l0I0oVTzG6gFjU3MsHFjguWef5nsefoQPfOADhIMIaXmMovs/HgS0ogF7ey1urG0RhTE3mwNOH5pkrFQmCBwm6lXUPkHFEoKpmSkW5hYIowxjOfTDkFp9nDSL6fZ6hQ6xX0GO8JGemhhjqbJEJw0ZaMFnK3vcYXs84kxxRJWpC4cuNTbzDoN2jLWlMBsOzNRIDtpcPemgegnBSshMt4YbSTrXtll4cR3d6wydx/bWFp7IIB3gOGBpiF1NUBNcuXKNU4emEWlIN4zJjcayJSpJ8cpjdKKU0qFpolYXrvexbBdHuTTGpkgGffykN3QeIxdhLAukRAgbYRSWMPsQGgvLvPIzQbbPcx/s7TLo7mGMwnFLeJ6HV6kivQAlLSyzvyHGHomK+cg7HqGxeBQlLKJM8yd//XXicIDtevR7PUqVKr29ZmFdVKljEET9FkkcYVk2B44cQxhFfaxOq71FV1h44S6tlcuoZHigdaVewxDRqFeJ4wTbgo31TVZX1woB+X0okiXB9RzyOKcUVIh1QhT2qI9V2G3uYEsHpQqCgmdramWLsDfaYi7PFZtb20gpsG3D+oXLqLDLRLWEZ0uMyehurXD8Te+g2WySJAkT5RqtfkQWJRycO0TJdpCWAgOO9PBrAfY+i2jYqNUDbHmAqRmbuuewdGOHA/V7mJoZJ0uuE6YJ/Syj1Q/51ldf4q0P34l/20G8mQk+cPvbSb/wWwz6e6wsX+a4u8B0ZYJ2a8DXv36Oe94w/DXJtcEPyihLkmQpkzMz7C5fI45CpqanadSqJFFInuekWY50XA4dPQSWJI8UlfIctufTJqedx6hcYDJDvxtTHcEM9hVNBsdx+IvPf46PfOTHOX78+L4ouc3S0jV+7dc/TrXk4fsO2uQEVY962cOShne+7we4fOUK/+k//T7/6v/6t6j9QaUuDjxDxy2nT7Kytsrx2QbC8bixsUuzE3J9tckbbx0njgZ0221KJY+wH2OMoFYrMzZWp+y7qCRCJQlxu0m31yOOY5CSdBCN5AxeqpWZPz5Pa22TZDXihupSyh3u9aZYNwM2djaIWx0erDYI04TuuZBrH38JeWKCxqkpxt49RzppkdXKtFSJILVJjk6STqa04uEbF1dKpmsBZIVBRW4EzmRAMFVDb8fs7OxSIieME1SuydKcWFa5srHFVmuLD771DkJPEKkcN6iihMCorNDRif47eszZdrHkkFJiOw6dzS1qfom//dZTjDcCxsZ8NpduYNt2gTPNFeurK7Q7bYSwmD94hBN33FuwtJQiVzlKWCD1SLTlly+fp/fSS0zMz6G1QjglHClJ0hDX90nTmHKjQWokgyTFEQa3VMMt14snV2UobJSApN8DDEZL9vISzb3hv6ZaGI4dWWTp+hWiKOPEiVtobm3T2t0mjGM8x8WgkdLg+Q6VoIKOoVpyGG9UOHD6AIfkIfZ2I8qqi+N5NPdaVFyL6frwC0KAgwsHMEaTDdpceekcIm4zVrLxpKFeryCMRXPpIuMzE4zNHERbDh/60Y8SJSlYgt7eJps3Wpy6/Q4W5hewbAdhNHma7juBDBf1+gS9TJPmDm5uMU6FLA3ItIsUFr4NkxMxly4rbrQmyc7V8PRxnrmwzWq8xo9+8Cfot7d5i9AYZ4xBOyFb22LzK79NNor/XiWgF4WUyiXUwFAtlYmqddxyjTO338nm5ibVbp/t7S06acxaq41jB5SCEnEa0453EMJmddAhTiPKfolGvc4g69AZwQ9R65yvPfYof/VXf8lPfvSnOHz4CGtrq3zly1/mySce560PPsg//d8+xuT0JJuba/zRH/0hSdjnwMI8D771IX7h//yXfO+7vpeP//KvksTZq0QPrUczg50ar1GqnMBgsbq+jcgSHji9SH1yAqUFlfo41RgyZciFhcDQa/dRcUxtooHjBkReimU0h+tVjMrpdrrU6nWSdHhUQuIa5o/OcPDwOH4v4dG/+BZPLw04Wi3TXbnCi4M2XtXjp2aPcETUqAuPeNBj8Ng26395g6/90oA912IwU6H09+7COVDHVB06R8roaHgSTXN3j4nZo+y19kh7u2hXE02W+fzXb7LWijgxGXBk0mG9l1MLfGbHG1zc1HQRbLVzVm6sMF+vEU9kZGFMnEX4tsWRW++kOjk1dB6ja0fsM3+Kvwie+daTxO0ee80mlcBmrOGTpQlaawaDAdVqjVqpwXhtCoNCWDbtrV02mleZnZ+lMTmJFgVv/rsz/L97XLpwiSiBvZ0WC4fmMIHBkR6WdNE6QUqbVBfmipblYByJigdoCmNSnSZFwUpjsniAY0ukbXHi5BFOHJsfOo9Tpxa59OK3mZyZJOz3CXwbRwq0ykkBYQQ2YGmD0AJpC6QrwAZhG3xbMj01gatb2NgokzFh1WjtNKlVh7fNBvBdH+nAzZWrrFy9wnwtwBEC1y6U3VzfJ00y8u4usRfQmD2KOzVLlMR0ux0skzFeKyOBSqmMkDZohbLtV3Hfw0QcKZyKxnMVZUuzcGKWgbGJaeN7MVhl1lZzkkHK3IGArtrgnkMTpK6N768hsNC6S80tkWSbWCalPNbn6CO3M1UdHhoW6QxtCVKVMzMzQ6/bwwgLxy+RZJpSpQbCZnJ6jlRrzl24wPTEYZRqMjMzRZoN0Eqw3tyiMT5GNQjQgwSTJ4ygI4TruTz77DN89KM/walTJ/md3/kdvva1r+FIyS/881/gwMGDCCFQluTQkSrv+8DfR6mMiYkJVlbWeO973s173v1+slS9RmfC7JM+hs9ja2eHzWaPiUadyUYdfegIa6tLrKxu8Kb770RYmigKwQhsS6CAvUFC37hkXp0cQz+JsW1J1a0gyJEKoiQjHWEmnPoBqQCMTR7YvPnt9/J8/2n+4uLzzGHRrVlkQc4vbVzmhFfj1lKdR0rjTI6XqY9X8MKcrTDmxnbMC5/6W8zsGOVbFvDvmCMaga2RJwne+BSmucug1UbrnO1Wj14i8YMqGRYEDS5cX6PsGrypQ0i5C2GPQGpsYZicHkPEko2VFSwroX5gntQOiEbwqRxdRc1xsG2b3NbkGK5cuMTalWuU6zXi/gDPE3ie/yoeslTqEkcZxlggFZNjVdTlFbZaXTzP48ydt3HstjMF82aEJ6rTGxRd4/YqmJjq1AxpnKOUBkUxe3Zsqo2J4oLrvDDYVDlaaXzPwXVsPKFpjHuUqzVqtQa1coVuuzl0HovzM7T35jly+BBRt027Gb1qyujaNrYQmDyhIBRZWMKg7MLfyvN8XNul2+5Qr5XodhNW17dI4gzXdklHvD2+5xGGe6zcvIZnF2Rwx5IIU/jxua6HW1KoqEfc2iKrNDBjCyAVcRwxUauQTE6QJYVGQtFugWNbqBHGEbkSlC2FZ4UEjiEoO8SJTdRtU6pqWrsd1pZC3nzvHfRLDSKVc7gac2q+QpZJrGyNcdfgyRiIUUGKLGlix8bEw48j/HqZPE45MLuAIyTLN1dYXJgiTVJanS5ra+tcuX6TxcV55hcOcPDQYf7dL/82N2+u8JP/80e5864z2LbL86s3mZmeoruzQ8m2ibKc/u7wz8gXvvB5vv+DP8CxY8fJc8XnP/8F3vWud/HQ297G4sGDZPuGnQqBsAzHjp5keeU6v/u7v8fy0iqf+MSv7o+DvqMb8Qr1eZR3pt/vs7S6w/Mv3aAc+Nx12wlm5+b55tPnmL+5wcGD82RJhBZghMTGEEUpgzDGdT3iqE+lUkD8MqPJkpRcG4RwRhLwwfGQNkhcLEsze8TnjQ/fyTd3vk4rkeSORPmCG37KStTh2f4eV70+t5aqzJXrzPl16rUqCypjPO6wuxnRal9BH5omGx8eKmdnCdOTU+xduUhnawdLa2ytqIoMrzHO2dtuZaxWxrnRZxDFLG91ecudd7OxvoqaajM75+MvTKLqJUxrjygJMUcWCZVLzR5+Rj76Yg4X3ylhCQc7iTh963GWr79Ev1uwmdLMptnqICmYck2rRZoqBBLbtWm1u/tceklaKtPudLGFJNf5SKSs9/79R9BILFsCFuXqOMYU9EnbdrGEwHM9tFL4pTIK0LnCGIFtF3oXWZLuE/ttPDfAdVz2mptY1vCXJeq3OXDoKK3egL3tPbp7EctrG4RxxoQfoPOUO+48y8HZCcI457GnnqVvbGxlmB6bYBBDu7uHJQ22VUb689gyZ21ni2SnNdK9CcolXvjmo8w3ypyZvw3Vj1/Vv7Vtm7LvkOU2RoOrQrZWLmAZB1tKtFKMzR5BOzUGWYojIE4TjBRkCLJ8BONCoWlYBifN6Q8yQtWhNegjPIurFwe0W4qjp2/h7AGPSKds7yVYykYiSW3NoNej4thIFZGmITpPSbIYoxW9ERYe4/MVHFmiub3HzYvXmbQqPPzAXUyO1WhHKe0czi+v8tWnvoXlw9lTp1HA1Rs3+Myf/CnlekClUuPpp58j2uswKcvIJKVUHmPLDK8Uc+bMGWZnFkE7aKP44z/6E9I0AQSZFgjpFh2tMeR5Rrns83M/9zG+/4Pfz09+9KdRuXiNVnfxlryCVhlFxKff6ZEkESoZEOYhFy9dwzEx9549xme++ASuazExXsL3XHJp0Cpjb7fFlUsvc+zALLNzM4VZroBBEiK0wXZ9okFIlgw/A01jCIVCCYPlBMQ1i9mHzvDgXI0vfvKvqNSqnDlzgmcef5Kpg3M01/b460HClwYRzu4WCyWHyVKJxUqdhx95JzNRys7SGs+tRmSzC0PnceLkIqvLN9k7tkilWkE8s8bZ+WnO3LJIS9dZuPcdnD9/kYPTMxhlUfJcJm67DatRJYjXWZyr41s2ucw5snCW6bkjLJy9nefXYpLB8KfYkYuw73tEoU2eZZAp3nDfG1lfX+bmy5fIlML3fQQSyxRarUGlipQ+QkgmJicZnxzDmEKurzY9RVCtYHsuUo+GihWWR6lUQkqLPNN4jo/v79uhWxZy/6H1gwCdF12EVoY0TYhNQZHWSmNLC+zCERo0fqlUiMIPGVIYpO2yvHqFpN8mjYvjmWU7RNGAudlJzt56nHpgs7G1hy2hLFwMKXEYcenKNRzPoVQqMT5exkWR6ZDN7R0GgxEkoQBt++QaHAO2kJSq1f1rLQnDEJXlVIMySaaJs5R+nGDvbdLuDrCkg6zdynR9mitXL/Lnn/lzNne28ScbuI0ag/6AH/jg+4fKw7ctpMkRSIRlMej3cTwo1xyWWznNrQG33W0ROBkWgsB3eZWNrBW+I3EsSKMIC1NAzJQhSVIcZ/h7U/ddvn3uBeanFzh0eIH2zW1Sochs+P1P/yE77S7dbpvm9gbfeOZJKuM1jp4+zrWlJRzf4a433MHN6yssX71JX8QIIalJh6BcZrwy/FjkyJGjpLHBaIFBkKYZQsjX6EyLfXntDNeTPP3Mk7zn3e/mQx/6QcrlGio3r6rxAa92wKMqqfUSRRSlTNQDaiWfbq9LlAwol3zecu8trGw32drZAZUAWf8xAAAgAElEQVQTx/m+6p8gikLCMCZN0kLNLOqjpCCwA5A+paqFMSN0wsZBWC55mhBGCUKlDMIuly9fRwY2k/PTvOG+e8hnAuanZ7n85HluPnEJW3koC14iwkoV5Z7hxfPPUw4qZOkA6ov4leFnwqsXL2P6LWSaMXv6NKuLs2hhaEyP0+1WyFKFDge4xmBJC1cIVJZiSY9YS1y/jDERVqVKVA5I6x4TU2OsPv3HTJTOAMNhhUcuwmG/R6e1R56mJHHM5MIC3/8jP8ru+jZpmuIHPhqFTvaXORYI4WB0MSIobL+LR08hiPKU3l4IWU4+yvJnbBqDVby0JRtpu2RZji0lWTLAsixc1yWP96Fv+6SQIPDR+1tzuW9Fb4SF1oVSlSUEwQi05fZekysb12l3B0w16qyuXKPZamO7Ls12i/uPHuLQ8QMcPTTL1SvLPP7k0/Q6Gbkq2IXKWORxoVWb5HvkWYplGbIkJhth0wvQVdBLUgwpg4EhyvJCo7XRoFQKUCrHcW3SKCNNU1SecfPCOQZxxokzt9MLExrjY/T7EZ//8t+QCo1dLWEFwWvE+P//w7WKmfsgN5RrDaQBr2QTdntYxuPBN91Gv72GNT2DUZAmBtsto7UmzxLKno1tDNoq5ve2JcmFhTF6pKJzcG6KTnuekl8mlpImCUsbK9QWplnb22ZpbZNBv4tt5Tx77jnm56a594638Gef/iznnt0kHfR54ZnnufTCRR543yMMtnfobO0ws7jATH04m3mALM2Lj/y++mBhW1/obr8WuuY5Ds899yy/+7u/x7/+v/8NlnDIshxLyL9Dd34tBXqUccRms4+xXLqJYqc3oOQ6pKmg1YlYXGygtKLb3iVOclzHIo4UWhl63T79bos8aaDTmNRAHKd4NRdUjuWXKY0N30TlmQZRNE8mUnja0Fnt0FsPmW40OHX8KJYtuPOOWwhKJaYmxrFsQefKDr32ACcrIbBI8pxL6yvYfoBxBDPMM50M/5xee+kq4cYK9myddCxn/G0Ps/HSNwBBlBh63Q5hu0O9XML3AgZxRNIZILQhzkDngjyLsOsNjNMntfoImVApZxg5Arlp6H/5yi9YUK0E5MrDKwfYPY9KZYLJuUNEUUSeZ2R5QtTro7KMXCUkSUYSp+QqJ82SV4uw1oUIvFG66BJGeKAcz8P36wixrxMrLRxpgzYkqYPjODiOiy1t4iwly3KmxscIw5A4iYtuhITC/0JSKlVQ+6LdSg1/9L5wc4PlpSbjEwG3Hj/O177wVdJ+QrvT5Xvf8y7e876HUbrH5l7Gl778LP3EJtItjLAYJCGWzjFAPOiTRVah+CUEtrEpeSMgAYD/8Pu/h9Xfpi41h6bGWBACneZsb2/joMhNCqGN8GfoRjlCJ6SdDllQ56+eeIL3V6epl1zuOHOWO77nLazt7ZLkObZwXmU2DhNWNsD3wK3XCXOFdCxuvLzB1Usb3H/HrYxXu9RKdVQk2RsYEA5xHO/T2TP8kkPc7eJKwyBJSOKcLM1xHGckjQJlMuolD9sWyIbPbY/cg39wjMaxaaoHG/iqy9G5k8xNTKPbW9RrVe46cYR//D99iM/+8aex84zDh+Y4e/wwveU1Vm8uUfFL7NzcZGPtBfg/hstDiH3VNAqxHmPEq+YHlhRorXAch5//+X/G/fffxy//P58gzw0Ca9+15TtQtNfOgUfVE15b20ALG9f1sKRDc5BjmTLNlQ6RAk8qdps98lQTpQmWtEhzwQsXl5BScmhhFsuxKfs+x+ZvpdNpYkuJyRXd/vCdcI5PZGxKlTKlisaOIqQbUZ6Z5PT8IpP1Mbp7MUFok8kBJd/j4Xe+Ax4x9No9nvvGM2ytbhH2Bmgrx+Q9Msthcfogqj38ziBLFGkfnE6KubbE0h01KofezOBvnse6417OX7pIY2aG2+57I1mcUhtr8NjjjxF2drn7jtMooSm7Nspb5PCpt1HyXLZbAScOvR1GONmPXITLlQpKKRKVY9IMJ1OYLCO3NCZWKJOh8phcxeQqI81zojQlVwqlDcrss+b3hbuFNghjyIVEjCDY7XsV0iRC50VRd10X5bi4jovGkOYpudYEpRJSSrSGeB//W6lUX932Z/vdoiUL8XIpbEahjQgKpbBw0Kbf6xCGEWmWEUURlXKNixdeZhDuMugqnn32BXyvDJZEGEmr3cUSDrnK0HkGUuLYNnEUA86+fOHwkQ36CMumYwzXmgN2sgiVJZQDl5mxKmrQxlGKY7ceI09CpEkYdDrc3AuJg3FeXlrGDxwqlsVb77qXp158kaWtDZJ9If+h88g1OockjcmwWVlqcv3qCoM9xYG5Gq7bxRGSQQJJJtGWJFd6H3ljkWYZwnbQOkc6AkcVwvmJSkbCo25s7BLYAa29Ft0oZub4UW5ev0kpqOBi4WhBb7vFuFUjaoesrG5x7dp1br31Vq5du8ba9jZBvczP/OxP8fGPf4JDi4vEcUrYi4pT2Ijxqqfda5oNpYoCfP78eR544E28973vJc9zLOF8R0P4uzQn/zWFWGlB4NuUXIM2CYPcwvVdPK/M1m6LJOyRpIosKxaFea7BglzB6uYezWaHqYkKmc5Zun4VRY50bMig5I+A5Mk0SisypdFSUArKlOYXmGo0KGFRDso4rkuuU5I0QRsK6VzXojI9yRsfeZittU02lte4vrpcLDY9l1wZshEWhFGnD5ZLN0mYrwumu4Lxux9i7VurjGnB1bCLqZRBKLqdJlIaHHKmxsqUHEklqOEmkFoeMt7FtTymaxW2l9dwpAMMN58evRP2PCzXRaaiEHi3BApDroubrDJDnuTkudq/KIrcGLQQYBVHf7P/R1j7KpaWwHE85AjYy26vg7RdbMcDpdHSLort/lFNSomUNkVTKyiXygyiCNd1sGybNEmwLAvH8zEY0iwvtBfiiGQEssZ4fYKxRgWjQwZRQhSnZCrH8V2eeebbnDp9mLO3Hmdn8yq+F6ByQ5Jk2Lbct7uxIc/RRhVdfJKxurZGozY90ggAwDJZcT2MYWAMIYoccFKL9kDh5x7jtoNbG6ez3MZJYxrVCcqJQts2Ly9fJ0x7zJYq5JZFnhVedNq2Rsol1hbCcoi1YmA02xttbAX33H6QLNym5PjkWtIMc8LckAkJwimcVlRKbxDj2DYIG2XywslFGeI4IktH0BPupaxtb1KrNXDR5K2Ysva48bdXqPslgp6k29nl0tUW/XCX9ZeXoKOZnphkr5fw2//xU7hln/GpSYSQJJlCKcjyQtt46DyMId9HQBSjiO+MFnzf57nnnuM3f/M3+fgv/zu0MljS/jvQs++GgnjtSGLYyPOQkushBbiOjV+uoC2HdnuPziCk3Q4ZDOICMqo0UlhkKicDoiRltdmmPl5hqtqg1Y0KzLflQuCwuzf8ElnkYAsLqQVK52TKEAgbv1ynZEuksXBcj0qlDqIweU2FRgFpphD4zFVrTCwsUF6ZZRCH4Hr4QRmdjyD6nyqEsNFhRJhlmO2UdMEmoEG4tM6RxSkGecLK1cus3lhirNFgdqLK3FSNQ/Nz2JkmaXWxqjmDvXUcXccSC0gdF44wQ8bIRTg3gkwZoiwjjCPCJCZJYuI0IU5C4jhE5TlG2CgU2ihsWcBvjFIYy+wziFzM/mLCsiTS9kbq+4yQSOkUX0ipUFkBPbOtHI3A8wKiKKJa9VBK048jHNsmTVOyQYhl2ziOW/D0LbsYi2gNCCw5/AuWhE22tzew7YCmtIhzg1epcOzsCW4/e4JSyaPX63H85CFOnz5NvxextHIZoy3GxhooPcB2ASmwbZt+v0+57FKtD5/DK6GwkDkI2yEXBsu2sJwyGotQeoQutG1B89IV7j9zmsONOgsa5PYmL1y/SZYorm1ucAVFrjTagHEkZoTCB7DRjhBasTvIMZbNTMnj9jcuImSfzGTsJTadKKOjBKkReI5CqxQpJcXWQJNkCVmekMchJs7xnRLdTsJgMAKLMHYYnz8ClqRhLHaWN/FwkLaNVYOzJ04SBD6bSyvUS0cwRrPe3ePS6k0sBFaSkxpDuVYHrwxGUK2WSJKM3ghaz0JYr2J6C2hZMYqzbcnHPvYx7rvvfn7lV34FrQoSRjE71n9n8fYK7NF6LU5/xFisV/A8izDJ2NoNKVUE0nbp9UI21zdJ0rQQfs+L0c9YzWOnFWJZUAskx46eIMkTBnlhyhlFA7a2tilVaugR3t5emOD6ApWDyhLqfgBS4EgbOxPYppi/5FYhvFQqB9QrZfLAx9gOiRKkUYLq9mB8jCiNCZOM3TAnyoffK0kssBVS+7TW2lSdgAuf/Pdw9SYnf/TDnDw8S7e1zVa7x9kTb6FaqVEZq2IbQ9TpsPwHn0fe3GDhh+5HvOc4ud6jE06xkT9Ncyvj7B1vHiqPkYtwkuXEWU6W5+RaoUyhiqZ1jhAGaQm0lEghsI1G6WKjKkXh9yVM0f0ZKFg5otgYayhErocM23GJ4xDXc1FK4dlOgREWkkq1QhzHOI5LmhXQNyMEeV64yTqOQ5Jl2LazL5a9b4MurWJmPQImdnX1OvXaFCorGIJnbrkVadvUGiV8X+J4kjxXZNmAOI9IMsXBQ7MMBglKZQSBj+t5eH6VwSCk2WwiLENQsslHEDAHmJibQipNmmVYrkSrfN/92SKOU0yucYwER7LV7KLDnFAl7EaDwiNv37zStmykMeRKkWdqJIwwQJTkxDpgcmaBKIyYCgY4JsEYyU5f0ksV+DYJDlrYhXzj/phBU4jdpGmK7Qi0tsgyRZr08LwS0WD4XKTr4VaqeKUyWkF/b0DUL2aMTsnBr7rUaiV6HR9POmRJUpxqhKLb7mBLSdjpkuUKzytTqdYKso/RWCOMRV7DbQIE2mRYUvDt55/h4Ye+h0ceeSd5XsA4Xzv/hb+LCf5uIkqjFORTx6dZXt+j3ekTuC6g2d1r0e4N6IUxljFIDJMTFfIsZ7wW0OmnRSefJmhhMzc7z+72GiXfplJvUG5M8cL5lyhXhxes0VKCbWEsjdQ2URiBEDiBD8ZCYCGRWAqkBjIDmUa4AunYJAKEtPfF+csYS6KtFCdPccUIUEqrKDlCUJzChMATNoNOn3h7i9psg3q9Tm18AukFxHtdsp2UpNOnc3WJ8MVrBGlG55svMXhzFdvYrD6/w9WlJbJ8hOfjv8Y6+/V4PV6P1+P1+G8To28XXo/X4/V4PV6P/2bxehF+PV6P1+P1+B8Yrxfh1+P1eD1ej/+BMfJirtKomzzLii2tVZAkBALHLkDc3UGfXCvmj82DgCxO6bX66CzFKIUtLOq1OrVqna3dXYJyianpaa5cvEqaZXQ7vaE2DQfP3meSJCFNY8DCCao4no9lC5I4xpY2YHPk4GFuOXKco7PzLLf3GPOquM0mWgjGTt1GOxWcHNO09rpc30v47Jf/FM/zufzEp4fK49d/42MmTTO01thILCWQ+zKellUsxmzpABKtXFy3xsT4FKVSmVLZpzNYYWn5KkmSIN0AKQWeZbPYmCTPc971Q/906M3LO97+fWZqqoHr+tj71OtXFjdSyr+jP1Bs23Ms4VLQGnOMyWHfWv21GFWtNVprfvO3fnWoXD7ww7ebq7s3qAcTjAcztHa2iXSC9D066xkqSRGOZu4dFeq1Gp31ATuXevi5y2Tdo5U1CZXg8MHDbO6tkymFlC4xPSYnynzzdzaHyuPtD99v7rr7VnaaERs7MTf92wtRJZ3S7bYZn54DCVXTQ9geg6TNgTzj+47MEdcm+cQXfx+xeq24fyZBSo3ruXS3+2Qi5+LGcM8q/OfA83PnnucjP/Fh/vTTn6deq/Dy9QuMjy9w6sgJivXkSP3RUHncuPgL5sjpD2L6a3SbL7LVDEhVTifMMVsdtM7J6hZG13CMYHZxkSe/9TR+KeX++4/zxNM9Yhn/f7S9Z5Bm2Xnf9zvn3Pzm1HFy2NmMxWKRCIBIpGjDpAnZpESZwVU2ZQaXLZNVLMmSbLpcVtkuuszokqocZJO0HGi5AKJIIjIgLQEi7O5gd2ZnJ+xM93R++803nnuOP9zeJSHTpX5p8vnSMz31dp+54bnnPs/z//1pDRy+9LG7rK4H/Bs//E4oPfYP9vmO9/z9U63jdz75RVvKasZ+MRky3Nsl0SnXv/UVRvsPmYzHCOuQ6SEray5eYHj1pTGBX8OKmFY3oDloV8KmVKJ1SZrOaLZ9yrLk479991Tr+L0vPW+LMkYaQaENx5MRaZpQGs3h4RHxbE6eZThRiJKKwPfZWFunHkW0Wm26zTauVDhCYU1OaSzGQmEsuYDvfufbT7WOpZOwKUt0WaJOhlKMNUgBwhpq/Q6qUc0N+i0ftMFzFTa3mNKvVHJlSW6rMZ2LF89jpGAymZLM5ycwntNFoStJq+eFOI7LIltghSaQIa7n4jgevttgfbBB6NdwgoAoDMmKko0rj5GZjGQ8RqY5C7/BxqBPFCX8RjZHF6dXZQWOhzAWYywOiiCoCHJZliGUqbjL0gE8prOS8dExnWaLIhPEVhMEIYEfksQJyoIuNK5TnTu75CSSKc3JPGqBtXxbR70sS5wTpKWUCikER0f79PsrmNJFyBLHqc5nWVqw1eestbCkPNbIhAuXV2l4qyS7JfNFih+51PyI2C2xeQKiJB6VbPQ6pJQM2g56Zgkjl1Gi8GWd2TQlilxmsSbLMnJyHHH6Lnw0OEtiFIUuadQbmEwjHEmRp0gMRue4quIBZHGOI8HxJb5bkqHp1Cyi10WVmkUqmM0mzGcZV8502R2dHiT058Urr7zCbDjmv/snv8Tx/Ihb97/Jf/EPfoVrF6+enLv/Xz/+z414kVGkx+TFgqDdplt6qLygM0/QtsbO7h7TmwvqtQSdz8koEPOCWqdPs32OUjzPYjFHenXGkzkPtu9w8bEBAkMUnl6sYXDRWCQSJR0O9o+I2jXWVs/z4PartJptLl54hDuvP48fZhQ6wfUN9SYkiUeZuxR5RlSXaB0jHUWaaYrcxSzhUD6dLRDKIgygNZ2ohqzX8R2Xd165RjyfsX+wz/VXb2B9h3yR8IU/uk6Jptns8MzFx3CExK2FXDp/obqvHAcQyCVO4PJGnydD6sYarKnG1AQCIw1ZnkHgohyXeDxDlIZA+Vx75BH25iMKLGWpqXkBapFzfHxMbkrm8zn1Rh2WgLq7YUhWpjieUwF7dKV4S+YzlF/DUOKoglYQ4AmB7ymKnX0Woymy1eaL//v/iDQlnjXsZxl1Y2l1BvilQ7wEoLruh/hSQeUtQhRUDITM9TA2OeFTeJTa5fhwh+PjOZtn2rhuhyTO6NVqtKIGaAPKoTQFaMN4MUMvQS6rwlIUVQLW2iClOPn9AoQgzVKkUERRSKY133zxG7z//e9DmAiMxQ88HCGZTeeIE++yN5LvMmINKyDJC7LFiGxq8aMIrQ3HBzEHh3N85SONZe9mgZqOSacJNatwhKTZqHNgXdJCMxxNcOsxSVYihU8Y+SRLCGlq/fPM8gKT7PPWc2c42tFMdI5ORig8SgPKVrZF0mSI3LCfZExSTV4LubhyjqQUmHyOVArXEeRZUakw58txPaByXDTGoKTD+XMXaDb6fPxT/weNgYvnKd7yxDMnNAlTSZb/9IMnXw2FqN64hC2xQiDE6Tcuvltjb/tVhPJQrqIVdpntv066O+To9i7DacydBzManSHSzpjrBFEGoDOG45gn33qe6Sxjb3+GUBYvqLO7k+AFBcZMT70OI1RlKYlCKI84mdPotQn8OsPjESBI04wsLZnHU7ROqdc9Or0AhtX3i9QiIgdEQak1UgryrMSK0yvmjNbkWY40BiWglBJHCLwS8iJFpzFNzyEqM8gKnn7mbeRPPMVwfEScJcTHh7jK4972Xb517zar/VXW+qus99cIl0AOLC/W0NWu5I3rolWPaEYRjoBWrYENXGToU9YD0iRBY9ke7jCodUimc1wjOdNb4ZsPXmbv4ICyLMkLjcHiuacnU1mhabdXsUBWZLT7bbwTHXteCrSpOBC+72NsyWg6RLolrm8xVnLhbe+l5UUEUURr0KJeC2i4HvVf/1Vme6d30t0cbIIFx3HIdUFhqgdNoyVRSpCmMUJKdraOORgespjFzMeHeCREfoBbeHSbHTrNLr7jkmRxRTyzBpEteaNLy3SagMwpTclsPqYe+mBK6lGb2SzG80o2LjzCheYWv/CTV3nxfsJrB4paXfLYtcuYouT6t+6Q6rya5c4N8kQ8cNrISx8hu6R5idtyePjqPabHGlfU8ZTCcRwkDvH9lLsPDhBS0+t7rA1cSqOZxDlzq3Fcl16zh94b4bkuYcdDeae/ZPuh5f5n/i8++M4Pcb7b5ZXn/ym9fMa+GSCe/XcYDPpoXfJwxyG1OW4U8d41H5PsMx1ldN7+07RHN5m9/Nt402Pm0xDXd4kXU9pLAHzeDFthqz76Y/8ar959gcEVn7YbsUgMH37/91MLWxR5UUH4/8x+RNsEKUNyI/iDT/7fHImEt1x9lmuXnsITp6xFAMczzdm25M69HRKT8/hqj5VL/yqtzpCXvvzfMDKSeb3klb1jPCVRRwcYm/DofIAZzcjXG9R9l8dam7y4NuTrr72M31vH02Nc7/TlE9+RVeIUglIKhIhpRC69zmV6/T6HBzvMZ0cEvgYhyDNDliaUpSQIXKbxhHjHMpsomk0faxRFUaKUetP66TSxmI1RrkJYS2EKrHLxjKEbOPQaTUbJgqPJmNVGnVEy4eOf+C0+8D0f5ezGeWQ8x7nSxQYRj+YZbrFgNJtwNNvnf/7iJzicLvjs+z52qnUsnYTfJDcJUbEebGV51KhFbJw7A5HH4WLK8e5DdJ6dmChLsiSn5YYMegPuPNxiHi9wTwDxQkoMLMUFENYhLxZVbTPPmcwnuJ6HtZZGp0+Ra8KwRp7nNIOKC5v2HZyWIHVqsHGJmY0oXR8RQOq5jKXCDTrYbPfU61gsKoi757loY5jEc8rSVIlGOCRpgnJgGs9J8wSUJY0TMk/hlDm6aCNdB4PECPD84Nug+EudG+kwOp6BVCAEizgniqIKYB+EyEST5QvixYT1S4q3vzXkzn5GWbic2bzGSn+dfqfLzZv38SKfZqPNSy/dQkrnTSHHaWI4nhAKRT3o4BjFfJohrYPWCfUwoCwMhvIE51j5FSYLQ9lzcGoRWgtcFdHsBMTTDKUl9ShA5yl+cPpL9vD6F7h49hrN7lm+/MIfIL2S0cgyj2q875lnqKucdBETKpfj8Zxau4czeY1OL0I3m8StPlnaYipcgsADLdBYdAmdXmu5c2MtQiju3HmVo+kD3vHeZzi7eonbd+7z1a8/z+e/8AfMf3xIr76CTkuc0HmzHu+okOPdAz728f+VT/zz/5rXVgLed/lD/OOf/59YpnYxnORMkvsks5xOq4WTQrm9Tzzcx187x8GN28xERm5VhR8wmoPxnHFacPXwmHd+4F2c39xE5QGHwyHj8ZS7d+7w5OU+LLEDrUcujXqDIs+5fecByXzIaPiAtY0rbGwMmBzvkaULHGUR0uK6LotZwWKmwSrqtRrKBd8XlNriez4ydMiy7KTkdrpwpKQsT+yiAKs188WMh0dz2hevIqVLvdZib28Xp5S0XJ/rf/x5PvCe91EmGaMcwl6VxI12abdW6bQGbPZWGP9Vesx5nkueV7skqQTKUSjHwY9Cao16ZVE0ickXMa7r4Ple9e9+hIfD61v3OZhNMIUBW9m0CCRC2KXqKPUwYDqN0VZUqhk/JC8KtC6ZzWYEQUSv3WEeF9RCQRQ0eHCwy0K79DuaO3sT9o4OgBCvXcf3PSLfodN5BH1+CVhNWZDnBXZuEI5CmxJrLY7jI4QkCDw8z6HUhxS6pBZGzOcL6qGDr3ziJMEYD6RDbi3KPVGOleVS1jUAN27dxnNrRFGD0hiyAnb2hoSuxNoRurRgS9J8TPnEOlq6RDWHPB1z7epVLl46x6DT57nnnuF4dszF89f4g9//ClpWNeNTh3JZTBNqzRZpUlBmCgcJVuM4LlmSoJQEUVbQHgSlVozGJe7hBKiak8l0gR6DZ1yKCFyjMNnpSzRBNufRa9/Bw707HBzc5SARjE1Avd2j321TTA8JA5fN9TXarYJpkTPfmpKvrpHX2yidgy7pdFcxcU6n7rC1u09Yr9NpLZeE37i0w6DOz//cP2JtY5OV1gXub73Oz937afJ4yi/84n/K937XD3DlwtOshetgQUnFb/7Gb/I7n/wt4lt/wg9Mp/xjN8fEMakqCezpd6C7u2NEIGi7IXW3wWy4oJzFJNMhM8dHNFrs7RySFB55nJBZwUJE6NgSDues3tpBpiFJaTieTGk0Wuw+3ON73v8WpHP6JPzWpx7B8wWj4SEvfHOH4cE2k+k+N29dZzY7wJgcXeRY61BqQxiGGJO/yYFRjkRJgRAS54QR4/uVu/syruDT8ZCwHlFYA0bQcDyOJiPuPrjLhbV1Go0OEonNS0Ruubq+ySPXLqPTBSWKu6++RHf9DIO1DaQTUJSGoigwxmPQqp96HUsn4TDyCWoeQgqEKxHakBuNEIrL585yFI/ZW3icaZ9FlBZpYW2wSqw1s/mc/a3jyuRTCRZJDsaihECXGiNPn/wO93fI0hQ3CinKHN/3cTyfIGpR5DnNeovNlQ0aXohUluPxjCsbq+isxCliPvTUGR5s72FRaFJaNZdBK+APjwwv79899TqEJwiC4KQuJfFs5ceWZzHT2fxNqaqUHu1mh9XVATo+ZG9vj7geEHQ75DrHILBICqNPphgM7hJcY4D5bE4USYwu0UWO51c/zxUe/UEHqSSzyYRf/uV/RM9NKEqDCJ/nJ376bQyPhyBrPHi4RX/g8oEPfw+//fFPEngF0vc5Ph6feh2LeEG7scrieM7h9jFSB4AGUVKLGiSLnCRJEEqAqJjOrl9jnntM72ece6rN4XhKNLjA5WefpZzPifycnb3n2d89/To2ulQUlWkAACAASURBVKvsHbzC/dEuOxPNxuXH2DhvWeSSbLSLClvUO6tstnsYFNPxnFvW8nnPxZkr2P06a/WCYO0cX//Dr5EkBYPVASurvaUalVVUWfjM5lk2N85WMyjCstJZ4XO//VV+83/4NT75q/8lvznMeO5tD3juubfylRc+x+9/8VPcP7iL9C3mqsP/9mCDv/1Df4e/8QM/hqclOEs4awxj1q+eJcDy4jduMZt4dCMP35TszI55PTvi7rDA2hTf5pjSI1WGgoI9G/HxL3yNC+f2aXVb3N/aYfPiObKkQOeKcIlyxGI044d/6gepNRwm0xEmjsnJKaxGCUEUQRTWKvcRq5iMYqKaTxJnpKmm2WqyWMQ4skZc5Exmc4LAoxZVrPDTxvVbNzh/4QLtqE54gvd86pm3kZw7R5wu6DTrtJsu3/eux7l35yYvfutFfvfGN7h07Wk6a2foDwb4QYAoLZP5EVIpBAqsIiv+Cj3mXM8lzTJKXaBwqPk+Os3ZerjFvYdbbJxZ59lHn+TmrZtEtYAyKxjvHDBKE5Isw/d8XN+n9Fx6zirkmjItyPKq1nzaCMOQRqMBykEoRZxUoBFrqomEXrdH6AVgNZiMwAed6AoQYyU1X+C5lnle4iiDjA+5ffOrFFlJuUSDsNA5fhAgHVlNi5QGY0qUU+2CrS0xJaRpgef5+L6PTRXj40OyRPHYs89WpqDa4CoXaZ034QHLMHwBbJlhi4xev40jQyazY4wtSeYpa49fpNNtMtxXjMZjUiSzacIrtx9CYx1bSK5ffwWTl8RxwcaZTd773rczGY14cH+Hw63TP5jqdZfFJCY+iklGBbZ0sAqEdE4gNeqkQeWDcUAKjAXhCISOyM0EZ3WNcuUZ5qbBwe4dLq5HCN8i3NNfsotszGRR8vrBBD/qVm4r0uA5GaPXv0V781Gs72KtwDcp09ER04MtpE5Jjh+wOLjNjXyM1Tln+wGXr1wlqoVonS9NuHsj3nBKPvkbWIujFH/9B3+I//4/+Rlufe15TJbTaNf5ytdeZHt/C+sXlUlspnj3v/4D/NAP/hhBUOP01eAq/FqD4cMjbMPHlYqdoyH7bkm/3iBPF8wmUxaJxg19sAVKuYxmMY2Wx2gBKtPEacH2zbtsnu+TzMfUGy32h2Na+vTX6s7Dh8TJjDhP0EWO0OVJ016ibUlpSxwFnuegtaZIUxynievKirMswPecNzc4uqzu6TSzlPnpc0ij1SLXRTX9UxryPGMymzPo9DinepSLKSZfoIpD7j94hfsHr7N6+S1Yz2GexASdPq7nVZUBW1K1TQS1eoszG6c3C14e4JMVlEVJrjW2KMimC5RSBLWAIp0x3zO0axF9a3G1RrmK82c2eGX7IYdZThTVEELitVpoY4iTCclsjhBqqaQznU3p9/o0Wh3yokTrCs9eWksYBHQ7XTzl4itJ4DtgE6TjYI1DbiXCizjKLK9sH/PUpXXaIuWlP/4SwTPvoN7tn3oduc5xrYsuNUqq6jUbW9W6xRtzuor5/ADfD5BSohxFt9cjno+RjgRTgUlc4eBLRWmq8T+5jKUv4ApQtmA+OaTTaaKLBY7yqIU+Z9c7pNmcXjvgc5/+DKFTI01jXC/g8GCIL0P6vRUOhvsIoTjcf8jlC5d5/wffxYtf+CzT7dPvylstn50jsFog5AkNDIGjKij7t9ftqpE5jEFmJVaAsHUCcZF4/yp37n8FVw95UGzzyLMbTGbbp15HrjLubWf4jRU6/R6O46CcgHh2SK18QLY9It+tcbz+LMlon517t5jtvc5icsR8eoBeHOG7Dmc2N7l44QLtXrsa4SuWmxb5l4U1hmZ3Fc6e4eHeHiL7Kk+//Tu4dP5Jtg9vM2WOTV30XPIf/uTPEIY1jBHLDBMBIHyP+OEUHUbUwjqz+TbH8YQb6Q6RLchMSFwssBJkYdDpgrEBvSgpXUNX1SitQhvJD3z0QxxtH3L/lYdY1yG3py9X3XztGyinwFD1TvRJU831BEmsSdMS31N4jqRWqyGlxJSqwt06AqVkRfezJTovwECW5AStEOGcfifseRX2NUlitMpo19skixnjLOFSp8n08ABdTOkFgs0zV8iDFq3z15gtNKPphFR6dP06xhYIXREisyJFGMPt6Zhnn3vLqdaxdBJOFilCSgI/rByDFMgowOs08GtthFTs7Q6JlE8yjzmeTun1u2y265Rk3J/PSeMMuZORH8/xHJciyTBvJqzTRavZwlrD5HhIENSIIp9cV4DsjVaDrh+glIPr+oRhRKPW4fD127h+l8y3aBMwTATbo5LjV7Z5z1MXedd3fT+fuXUTVZz+RNYbTRxHVUhNIarJEWtJk5jrLzwgzwzPvf05brz6GmurK3R6Ic21OmtrV9jZ2mK2GJFLiXJ9MpNjS1MRpVyXcsn7vN5oEzgQpzFB7uP5NRqNFpfObfDut14jzRN6g1WeevJZXrt1m8XkmN5qn3avh/R9pLBYcxVfCBwyIqMJzq5Sf+sN3nb59LW2ZDbFEy06KyHjUUGeajy/RpbHiDQlDMNva8JWr/YCgVMNzm/VsPWzaLfBmc4Mgn2avRo3/mSLmhOdeh03tkrOXL5E4CgCLyDJC3xP89y7nmZ6eITKdtHxiAdf/nX2xilbhyParTplofFLw1OPXGT3YE4jCuh1u7iRxJSmelP6SwJfvTE+aIxh5bk11F7A9t6If/rrv0J/o4nwNfM7lve+40P8vZ/9z6jXBlSu3Sy7Eea1l1/kiUuP8/HPXWf/4YJnnzyLXBgOj2LiacZBnmJEiM5TlGhgEYSeJixTOi3L8Ninnmd8+CPvxrExjU7Bk9+xyf3t+6ytnH5++5d/9T/HDy2lAddxUY5CU83al2VJs9XA8zzyNDmxJhMkcY7jSLI8P6kFO2R5RhT4BIEDQpAtcuaL089veyjyRczM19TqdWbJgjD0UZ7H4c49svGIuMwp/U0uPPEE5xzJp770eSaTMbPFnMwbkpYZg5UNMmNxdQrTEe5wzvF0CvytU61j6STc7bQoTbW7idM5yaja2YS5JalPmOUJi2xBp+5ji4I0K9je3mXj3AaUJU7k0u20yY4TZrtH5HlKKQXW2KV2wkq5pGlGnmumswWm2oDiSsHlfh9HvNE4FlhrKLUhiupY4VEYAaWmEThYnbDIG7y2P6dR7xAEAQOvt+RRESc7X4HW+s164eraCi++8ArbWw/x/YDAc9hc6+NHOVHo0ahFeJ5fzak6DlZrDH8qkBBLliPy0lCLQlxjicIm+9N9rJ3R73eZL2Ic10GXcP2Vl8FYDkdDVjZXmC8myMKlmM+QRUEZJ3Q6NY6mGZff/i44/52U+RKNudLBdSyDQQ3Hh+HxCCsqCytdFIgTt5Oy/DPqPCkpJCgNyUFGw4kIGiFpOqPdr5PlgsjUkfHpJ2gG66sVxFwqvCDCEvPYE48S1UPcskQVKXXr4+qU48kDPAVn1lco8pyjyZTt3SPW185w/sI5iiIllBEGiXDEX8pOuEKoSoTQ/OGXP8HxfI/+ZpfVSys8/3svYGVGa6VNSJ8f/5Gf5MLmBfK8IM+yylB3yemZeJ6wmKdoDYs05/EnnmH8pc8RKUOvVyM9zhjHMa1QkOaglYtPzma7zuOPXuXzL77GE88+wcUrF2k2faZJjYcHB0S+j85O35gLo4DSpJSlodAxTT8iy3KQLr5UNDyFKAp8I8gLTS2I0JkmDD3yLEFZD2kVtqzegIs8RUmJHwQESzh8eErhe3XiIiXJUwqdEaeKluMQNlrUlEuQp5y9+gjCaJIy5+79u9SaTYxwsFYwmU5ZW7uApzSizMl1wWwxI1mitLq8Ys4YFvM55QnrNqg36Lc7PHruPE0JU6MRRcFkmOB7LmEQMZpMOZ4kWKPwfCgF2IZL88oKJisIHA9ZSrIljC19P8RxPGq1anbZuoqyBEcqWp0+UvmIE5musVAqSdhuM5nbKtEZzUqvTd1XHMQFu8czJn7Iw507WHH6dbwB2jbm2yHcUkrW1/uMjje5ceMm6+urnN8c0Ijcau7zpA7lKBdT5JiixBUKow2lLgncALPEzCOA4zkskgW1sEaapvh+QFGkXLpykZWVDv3VVYKwQWlK5vMZ6ijADwIQJUbn/MlnP4dIUpL5gg9/319jPkkotGb9kR9niTFhXFHDCxVBt0bZzKhbRbarYeEijEZJg3RcrFZIU9WDi9JiRIGnHfxI4jk+uBOGRw/o6DXyScps//SCAADlu5TW4nseo/GI5557hk6nU9UUV9egLNCLMQkPWN1Yp9VfoSgNrhfQbMLFC5fptru4vkMUBAhDJYevjAiXWsufF9WoJ3zsd36L/+X//BUcLyS3hstnBnQGbSbDFFumXFp/nK88/1WuXLpGluY4jkMQLuc/CLAx2CDwmww6bfLYsLc/Qrl19kb3eHRlgLQJNafg+z/8Pj72u18l14JBN+Itl9eRwLW3btDbaCMdhyIRJAuBsT7Z9Ji23z31OqRrMTk4gSDLCzxTbaisY/lIbZVinpLHmn6twb5O2FY++/kQlEBZic0LnEBVdvOlJFABkaPQwiDE6d/Y2s0W4+kIJSWudAiiAEpNr9NhZbVHEc/pei4ynXHn5g3++Zf+mNd393jnc8+gc43MC0bD4YkdFZR5wdHuHmt1RRDWTr2OpZPwux9ZQYo1wiDAaM35tRphrcX+ccrW/hH74xG7+8cniakayEYIRnFKv1VnrRWyNZpTGkFxnGPTjMPZMaUReN7pxRqHRw+rPwiLLnLSNEFIj8B36Lc/gnQcpNGYsqAoLHmaYlWlNHJESVkUPL7SxXlihXtzw0v39vjqLU1Yb1KY099gWmum0ylxHOO6lXW94zg4jkNZas6eW+H27Qc88sg1Ns718Ns+JtWIoEZ3dRPXDWiFdQpjcQw4NVX5jjnOmz54p43RwRaRJ4lnQ5CVKKLb69Bq1VnMY5QzR8sUS87O7g5FIanVexTZgtLEvONd72Z/6z46L3EabdYHZ7m7s8PhdA4CHn3ydJ5Z6Tzh/PlLiFCSzUo2L2+ylwzJj2PwXFJdYKylVj+i2+kwmVnG8xItUqRTY3HsE7g36K8neBser9/dYzEc8fZLT/Ce59536uPh+x5KKiazMW955i10V7p4jo+jXFSjjpAKJc8zmKesWoc8S3nxxesEUcS7n34vngRrSvIi4+y5M8zSBJSiyHP0Eg4O/2K88aYkpcO5K2dwG5rHnj3L2mANYyS3Xn2AE8J7H/1OdOyyu7/DL/3yL3E0HPEP/uN/eNJ3WD6mScSFgcO5uAcs+PQf/hHHo5yVwTlmsmBzo8f6hTaXLnW49vh5/vjr9/Ajj+3JA/bGBd/9fe+kiI+ZHjUYHkzx15tMreXsxgAlTz86qHPLY+0V8knMfhmwceFxnogljx0u+MWv/hGvoRAq4JG1iMv9ASuFj7owICVnb3+Xgpg4neEKhTKKaZ6T+R5KOoj09LuFr13/OteuXKKFx/7eHmVnQDeqM9w7Qp6/wPzwgOO7Byz2HnBza5u1do93XTnLtHSpbw7YenifcZxycHzIubrDZ/74czzY2eJHv/sjLManL4ssnYQ/+Mx5GvUGSrnM5jH9pkcU1pCPhry6dcjuwZjX7j7kSy/eojgZ22o0GhRWMotTzvbaePGUeJ6ArpxntTHowi5lbLmIR6RpiuO4BGFYjTtZS+B6FVTD85DWxXVDlBQUSYwSPqLU4IHQGV6p2P/68wy6K7y9XeOV+9u8erjDMsXY0Wj05k74jYaTPDGsdD2JNgWT8aSamQ4DrFLg+Ci/hh+5lGWGVaCUg6fkCYdDYE5qw8uEc6IYEkqCgTidc7l7jsO9HW4+3KY9WGW6mCNEJRX3ZEj+nucA0KbkYDJiqgsQCuX5RO0mSgXcu3H9JAm//1Tr0FmOlYLhZEIyTylVpR6MmpJClEgPRJ6zvtbg6aefZHcv5stfuUMQOjQbAWJUsrGyoLk+48FrU5JY0qhFOK7DJz/9KX72757ueASOx3w64/GnHmewOsBx3YrloRyUK5AIHCFoNrusrqwxmk4ZzSYs5nOKLKHd6yCEwYqATBeoEz9C19qlnDX+xbBUpbfPfvozSC/lyeeu0lmt4bgehwcjdncO+dG//u/xoz/445QaPvjh78TzPMbjUdV/+AvGo089ivQSCh3Taob06yFPX32UUmYcDncpsXhOyVq3QWhyIlFijUNWNug0JK0oYpHEDGcTvJrLfHJIf9AgsB5LOIKRJDnvavfoqiZZV3F8OKOzsKxMpnxnq8cjBhJrCWsu3eMjuhPN4cRjfWPASq2JKVz20imxNNV4py6wbg2VG7Li9OyIle4auQbPq3LY7v4eewgO63Xe99yzFHFMOp/itZs8tfpWHELu3n+ZBSXxCahMm5LReMR8b8L+wZAi0xzMp5glpjSWTsKtxoBer4cVCivnNLttaoHLfDLifNNnLexwvqN4fXuL0aLAConjOviOh9Y548mMbrPBZF750QGgwLEKucQT/uz5p0mShEInFEVGoCSOdLmw3if0fYTjVjeZKyrBhGNxVYgUisJmKMfFDwK6Z87w8p3b1FbXaHcCBmoTs4StkHfSAHRcB9d1seJk3MqCEhJHeYAAWeL7lRxVKhchJEpJTFaCaxGislepHKmrRtWyI2r9/tqJUk8iJKR6yoc+9AE++tHv5+6rd4habSw5WZZhypJ20ARboI0hT3PK0tBfW6fe6NJotomaTXYe7PLHX/4SQgq++6M/cap1WG1wfR+RSdCQpRqpoLsSMi8zWlFEs6U4v9nnaO8InShkWVKP6mhiejWXfn9CEk1YGEGvN2Alcrlz93XG0/mpj0dRllx54hrrZzcQAhyhKpqcI3CERNjKWKvVqHNmcw3pSJ586nEW0ylFnOAFHkJWXXnHD3GlwpiC3Jil6/UnR+ZPE/Dv/wE/+3M/w3Pvf4LOmTrtesS9ezvcv/OQZq3Pz/7UPwQrMMLyi//tL3Hnzl329w7+Ar/zT2ORHpGVBVEoEMbl3W99gvW1dT79hc9y8coq48Wcs1fWSPUUJTIansUahwfbI9a6dRwF08WUbq9Dr99EzQp8UeIahzA8fcM0jguK4ZT6RNMR4E9mqFSTqIKP6Bojr6QUJXamGCUZw2TKD/vn0Pdn1HwX2+6QtHvkwrIzPOB1MWc7SZm1JFad/t51nZBcW46zOYEf0O25lLrkeD4jWcxQjkNeatqdNqkuyXLDqJRM4jlWKqaLFOX6eH5InMxw3QCPOdsHB0RLMD2WTsJrFy6wiBcEUYgqNBmaPE7wI590ZsnzEk8onjjb587DIfuThONxRuhIHM9DD3MuXFjnzJV1pkVBURQUacH04ZQ8O/1TbDib8t3veQ+v7+yyd3jEZrNJq9Emata5e7hPXmgix6+81qwFK3jvs9f4zg8+y517B2xvDTFRg8aT72S4d8jVK+f4hf/gJ/lbf/vvwRKqGy+IUMoh8H10WTXlcm0RpcbRJWtrq3zgg+/F2pQ0mSGy6nU0FwtsWVLmWTXZUWRYt/Lgc052a2LJ184wDAmCAMdxcF2HMm9x++ZtXnv9FmcvXcLYEq0NZjYjiiIKXXDvwUNGh2OeeuJJNs9HVV3bsRQGhscpv/O7XybLE/L89OfGdXy8RoxMDXYikPUFxmpc1eHxy4/TCAOaoc/17a8xLab0Nvo8eaVFsp3jZ23ycEx61ZKWBYOOg71/SEOdI+218DunVyItJjMGrTaRG1CrRziBU/nniYoih7VILP2VPpPZmFoYoFSXdquJIwRIBysUGJCyAiHluQVXVGN1S0ZVArZ85IPv5soXv86vrfb56nNvo0gVX73+Gk+ffxe/9vf/GWsr56sPCFAINtbO8sRjT3Pu3Lm/kJz9jeg0R/Q7Z0hDwfVvHfDa1g2OR4fUa2tc2GyzvvEItXqNW69ex/OgUfd47m0X6XQ63Lz5CqtnetQGbVrdsyi9oNlpsbJ6ka27X8YucTje89waL3ziJl/KMrY03HEcVKFZt5ZuaRDS4BoLSlZ+j0Jwf/4K9cBHGsHntyCrhTTykn9fNXhcedTPb/Klq4L0UvvU6xicO4vJEx5svc7+cUw9COm0WvhuhS6tdVr0sjX2dx5yOJszjRPwPaJai0znrF+8xjjOmEwXNMMG/cEKtcBlOsvw66d/KC2dhIu4YDZPmSc5Ukjm8xnonFGeofPK5h7Hp9Nt0ZxmjGJDGk9BKAJtCRyH2XTOvDRVjU1U8kMcgbOE5X18uMtP/cjf5J997OO8+soLrAWXONjfZ3r3Ht3VDYRymCwWxCdiitVWj++wF4nqksPjXfJcg2nRrQW87YlHuPbIVT7+e5/hYDRE/L/xr/+foRD4rosuKqaw1ppS64qH4YAWMX4gyfJqGFwqiVKKvCgQxqBLTZ7nGAnpYoFDlYC1LClZrgP/BtdDa01pSmSRs/fwAXu721y5/BjYnDwvKUMfbMn+3kMiB85sbqJLS6ZPmovWYlE82N7hpeuvsLd9fSmuR61bJ2x5ZDuHzGdjrp7fgEhhFgGtRoN+p8XqoMunv/B5Vi70aa74XH3ngO2vJExeL5gUMfcOc4rcopOCdhhSD13GJcTz02vyc6154Zsv0Bmscu3RR7l0cZN6VKtGCYscU5YYrZGOQiIotUEKiRECpEJIB4HESouUEtd1MUZj7fJJ2FIlz/l4TBQe8dGViCd2dvncaMbXbuxi4oC/+x/9PFFYx5Yaof701jx37hyNRuMvoNL79tjo9lBKkgrL9sNDrFLMkpK9/TnRrQkb7RZNCZ1CEWlJq9WgFimee9tl7j98FSuh3WzgKVBOgJQ1MiMgMOjy9O7TTqQ5zAsmxrJtS5wzG8TjIduTWYVQFeDLSlEoFUgDEzfEtWClolxr0x4MyEYTPru3y8VSsHYAptPAv3L6JDyezuk3IvrdAY4zYTqdkOuMKAzw/RBbZLi+T5ItGI+GJLqk2znH5PiY4WTC2sU1SDWlzsmKkl5/jYXj4zhQj/4KKWr7+wektrpwtS4x6RydJSekrgZlWSKEZK3fYzpPmSYJh3FAWRTk1qBrDjujKbkUGClw3cp63jadpXbCvf4ZfuezX2Tr/hYdTxC40FlbQwnB3tExTz35Vo6Gx6ydO0NRahaTOVG9yac+90Vmswy90EwnDuv9OvF8nfkk5/lvvMgkmeMsMXgenggwrC5xXa8qZUiJ67j4ocJaRb3hEegGQlRoSWstpdb4nod1K6EHVqLTHG0FSjkURU6+ZAe+eBO2rwBDN4RHLp3h3mu3GPTOsLt1m7KEMKqhlGI2HbG+1qPb6qExZCfkNGkVt+/c50++eZ1FOmc0KpeiZLUHHZI45mB/n3qk6NUb5NIhw+fyxXX6gz6HBwd4pqQeORSy4PBoxjwp2D7YwV/3SDU0O2uc70k6qY8ZF4SFR5Kefh2dlT6R71Fvdylxee3l26wMetSaNXprK5RlJTjSma1UjlYh9AmDWSqsBXkCwIfqISelg1JiKXls9WFAwPNf/yPOv+UsZWo5Chy++JWbbAye4Cf/zs8RuHWsEYh/4YHX6fwFiG1/TshZxKyYMEFyMMpQQlPkOUVhSWYhL33jNt6lC7z90lXuvDplLGOyPOH8hR4rgzbjoxGtJjgGVKvNIk/Y2b6BU+ZESwiLgq7PgaeZF5ZCKjrNkJrbYpSmFEZUrGf7p+brUiisA4UwJGVOp92iFUZo3+PGaIfYcblnEjpOj80lauZJmpE6Ek85bK5vgiNRCkRZ4HkBcZbSaDbIipyiLNg8cxbVaDLLCpwkq5rpnkeap8RpQadeR7UlSTpB+acXNy2dhLf2dsl1QZ5naJ0wGU2RwuHCuXPsbN/C8zys43Nna5s41ziug9AFEohqdRaFJdNFVfs8gd1IKZFSfDtD9V8Sf/N7v59kHtPpb/DoowWRjmmHiiCI6DRqdAOHd7zvXRyOjpkv5nQvn6OpfC5deRoUBJ6DsBZtDesXz/G5P/wiz3/5C7iuoVii8x36QQVM9xXKqZi4nFCZNClCFgxW6pUkU5dvQtaVUjiOwnVrFfBHKdI3kjTgKR9PL7cTLsuCogBQ5HnKT/y7P4ouFhyPpnz847/Ld777rbzlyQscHY85PDwk8iz9/gA/DCiQvHTzNV568SVmswWPPXqZdrfDM888zs6D0VKs5432BRw94gNPvpu4PMYX8CDWSL/Ha69+DSue4PqNVzlz+QJ+V1Hr+ZidgPH2ffS0QIUBnV6f1VZEL/BpRn3MQnD0+du066e/uKUwdNo9AiG5dvURwkYXx1PMFlMe3B8ynu2QzKecW+vTqdfwGxGOJ3CVQ15WwgFrLdoYTFGiywLHc5COYnQ8WercCCHITcrLW99i6oX8k2cvEL6txyf/q9/AdTxsYapXeiHeyNd/6bEWNtgp4FsP7qJ8jWs93vH0o1Au+PQffJObyuErN+7x195xkalT0h00mcYzPvY7n8ENm2xtT1AXmhwcPCAapCjPQ6gSWUKSnv6eqYdt3vFvfweHwzn3bk3pDTYZHh3y0B6yazV+6FP3fNIiq+4nYxChxKQJXhjSDwNavYjpPGE699iquRhf8+6ViIzTzyt7VnEwnyAxRLak5tUYTY+4vDpgcfSA17fvotOEW/dus5gZrr/8Om/7yL/Cg6MhZ9cGXH/lJfprm9SDgNx6FFLRXVlFjhV7o9MzTpZOwg8P90jTFGOqZLW7eww4LLSH0AmuW3I4PuKl29sncmJBrgVh5GCMYR7PSYsChMT1vOo1z/EIQvfEkuh0cePWKyAg1hnd3jqXzjxG6Ls0o4iz585WmExluXjlKZIkIfRc+t1eBR5SkGQJk/EEXeZI6bF7eER9bYWHd14iT08/XpLGCaUpwYJ0JBZb/T+kwFLteEHgKB/Pc08mHip1EKKairDGYIxFOg5GCpSUlMbAkjVhY0ssCmFBCstXvv4SUc3jR374LU0F4gAAIABJREFUR/mBf/NHefXVG/yN7/8wr9y6zcHhEGtLvqvwGAwW7A2H/PYnfo9arUGv22Ge5Mwe7jE6nlJSYPXpd35yPkaECZ4bIUVAOU/xPUEWxHjWcHh/m/nhjKi1QZmmeAsXMR5RDyThhVWG8wlmPMXthFjfBcfB8RTC04wmo1OvIwwCtra2WN/Y5PW7t3nu3e9j72CfXqPL5rs22N1f53h/l70HD7h1e5tms8GlMyuErYBaM+B4OsPYipFToTclCIuwgiROljo3AK4M+N4P/VuYrGDQPct7nvsQrlONZQpX/pUk3j8b11/+FqLWoObXefTxCzy8e0yaTYkiwebZTfaPRmyurCKNS92RLGILfsDxsaUkJaqHHB0PkTYjtJZFPCdPZ5zt1Cjt6RtivnB4eesmh8cxw0WO12gxTQ9p9z0abgPhSBwpadWbLOZJJVAREgqHQrpMZkP8pstwPGIcaMZOiedadtMZYX76HCKoDAfAMJvHdKMmruMxms741Be/yeef/yKhkoSh4ps3XiPs9CgLjZumjHZ32Nvbw4uabGycwZUCVZYn2oUG5RK2OEsn4TuvD5nNZpTWEOea8SShKEru7EwY9OqkacbhZMFwUbGElZDUgwDf9ymKgtIYfN8DqXBd72Scq6qxLVPz2tl7wMPtLUoJtXqb+XDCxbOXEKtneOnFl3Fch6Du0Wg0KkGFgLK8RZ5lFNmCdqvB6soqrW6bT3ziU7z0rZdxlEu9fwZdnP4GS5MYayxCSpSVFKYgCEMc4SCsRCkXTqDoUooTHoTEmAKLQZtK8GGNobAWawS+71IYg/oLNH/KsjxREmleeOEl3v/+93L79utkWcG3vvUq+SJl/3hMUZQgLJMFNBp1dFly9eojYCWTyYRv/D/svWeQpel13/d7nufNN9/bOffk3VlsBBbYRSAABpCmSbFoQqLpkmmzKFslllRlVdkuF+0vLsup/MFlUyWprHJZtkXJpC2TFEGCROASwGJznDw9qWemc9+++b75efzh7V0AZqjbS9P6Mqc/TPdMV8/pN5z3vOf8w9uX0XmBAjDHdNJJY3lugTA5YOn0WeI05sG120RyzMjT1E0VW9pM+XVSWSBWKolLONrDkSkmcHhq5TS1aoBluRxFMbk5YqY6TXDKxj2cfOGhjWEwGOAedbhy+T2ee+FFpPRRluTK1ds8tnKWmTPTJGunuXrtMiZKuXz9NraSLCzNU61WsC2reDgeO8oYrckNJNHko7PvJQSnF8/wt3/pP8W2XQpi5EdftJ007rQPWHAkgVvDyBghJEmeksbgliUXZ9dYnZ0lGR/i+SUW6xVGpksYZ1iOZDAa4pag7CuiKGKcRlgih1yCnLxhGPZGBH6FlYUG81PQ64xp1R1mmlNUypVjjXFDoxHgeR6e6+K6VqHYloECEJIoaXD6zAzjaAwiZX6+hmtNPov1ywGxyhHGoKyEME5JtM0wV7zycIsr3YzZSkC4eYPFuVme/+wXUMouNNHv3iYXDkeDMVNArVzGxIU2sR+U0H+ZRfiVqw+JogiDQYuim5NCoHJDO85I04Q0zYpNsATHkVx4+hw7O3uIRBBYAsuyiZIUrQ1ZVsga5od5oQk6YbSas6yvn0NZDv3+EXOtMkqGRMku5XIJ13UIwzavvP/HZHlObzBkbX0dKSXJKKXVmOKN11+nNx5y//4m+50DUqOpuiVye/IbfapRRwhJmqYFnVUWBA4lJTniQ2HuD0w2lRBFwRZ2Qf9WohC+VxLrmD2mM41Ewgnnjnmes7W1dazTnLO3J7lz6z6//k//Bb7vsXh2mZnpOrX5KYbjGJM5zC4sEwQuaZKws71HGCbEcYaSHlKY4lyfsFBsxgNeWD/H3bv32GqPuLC8RiuP6Y4GnFo/x+adayzMeSytXKDSqvP+9XdRTp3pyjy+V2cw7NO/u4frSuaeW8Otl8lImDnjQzx5Hjs7+1hKcdhrI23DK3/8TZ586knebIf8Z5vP8yuNLueG9zlTCXj67DmcSoO9vVPkWY5A8ebL3+TwcI/hYMjCwiKNZpNGrUpzZpqjzsnYe8CxML45Nn794Jj+/1OAAeZnqpyam2J/HFNaWORwZ4PUEpQDl7U1h34q2B2ElMsVxtqgRJdKoDDDmOlaFekaUBA4Ho4TE4VHjA5yxhWHKJl8DPDHf7RBKsBkEqXNsfuNJjUjUhNhjCZOUyx7Hss4SBzmp5Zxp8rYts3to018x8fBYzGRGFUlisYYMjz7BHZPpTKBzknRZDksrz7OC/OLnD+1SC8Z8cZ3v4V9sEN2+zKJ67GX5TiOzzAoo+eWeOp8g3I5wHFtBv0+rm3j2S6eCpDuXyJjLhMGbAUYFAZ1vO33PJ/hYEx+THQQx6/dBkO326ffHyGFIteCcDxGi+Lfsiwny3IKxNDkRac/6nPnzlXanQ7jcIwtHASKmZkpPvvZLxaOH47CL08ThkO0HvLuu9foD/qFz11QRgDtXpvDgz3iZEyuE6SwkCeYf7q2jZQS17FJdUZmNIUf0PHxyrIPC5ilrAJyY3TR/QtJnGXovOiShbBAG7I0LUYaJ+yQsiwrtujH50BKRbVaYmFxFse1WFycol4N6A0j+sMRw0FENB4Q+A6+79PtDNG6kND0PPf4fBiGQ3UirYTpaoWRY/CW6iT7Y9rjkKlWlbpnk8QjmrUKTpJiwhA9dji7dorDrQeMBmP2dg+Zn59DJzGBEhzc3KHSqmKMptkss985mjiPKMlQZEhH0u52ef+dtxCWw9qzn2LR62MGEa3AoTMKWay28FwXQY6kmNk//8Knebi/xcHDHa68e4n2/hFplvLkkx87EcX+eyHQx5Skv6y5758Xj104jUwkTd/DEh5Lq2OSKGJhtkkUjegeDsi1QNplZupNxsN9vMCmVq/iCwj1AGk7gMFxFegUk8IoHJGdoPNL8hxswAIpBV7NFDq8yqfeKB+LYLmM0yH5AOLcpzJsEbfbuJ7DMA6JVIaSdsEJMJqgXCHPMzjBUt1g0NLDL5dorZ1nbmYBlaX0j3qofMDZqSZRFrG9sE5fSlA2Mhe4pRIrtSpkkCQJWWpwvQCdZVi2i5IWnjd5Qyn+orCXR/EoHsWjeBQfPT4aCf1RPIpH8Sgexf8n8agIP4pH8Sgexb/CeFSEH8WjeBSP4l9hPCrCj+JRPIpH8a8wToyOWPuFPzRaFqIaUkqMODak/DOXo8eWF8dwAWMKI0wMiAKqWmyL8xRjNJu/8dMTrVmvb1w1M1PL/N7v/2Pubn6XWsMnShSlcp1mc4ZonLO1vUW15lEuexzuP+TKpds4TonBKObsuRVaUw08a5qrN76N78zy7FOf4ePPXCRwy8wvPzNRHr/8K79sCipyoeIm7UIXQlqqOCTi2BPLiMLXUWvOzM4SDvqM44iOFih5TJVFoKSDUpIsL2yS/vu/999MvHb+zAs/YuwspeLWWFizuf4gZRSNWVi2uHajy9JSiy985gwv/e41uqOE+eU6S+cavPfqJsNxl89+4Rm+/UeXiIaK2XmXg4NdVpYW6AwGrJ8+y2/+s1+fKJeVZ88YkTlYSuL6LpZtMAgyLY8hbxqpCgSCshTK0ti2AgTC9cmFKqCEUYSjrGNZUIW2HXSU8PZvfXOiPP7q5y+aYbTHc8sJ377nc2/PplXLqJegH1kEIubCOZ9kKAjTEe9vWPj1jOlmxmHboxcV5zTwAtpHRwgpC1KOhlwn3HvQniiPX/wbf8X0RiGB8Ci7JRqlBn09gKjQQvCqCp1G5LbDOLNo1QO2N+9jWS7DXsrK6RYNb5qj7iGBU0abCNsoDpIBLSfgv/zv/v5EefzMl37MaHKMgSzXPL7WIlCwud3h1v7g+E7VH6I3MPBTX/g4P/SJ82ghmZuZw3HdY2y/dezwVMDW4jTn1Ccnu3f/t1cPDCbFcjwc8YFfX4GWinLItUEaxTCLibLCyb2MoGTbSEtxvxfST0GajMCEGGMIU8MwtfFsi//q505NlMf97S3z9W++AsIiMxlRGiFF4QFpH+PCPzgW8hhaallWwfA1GqkKjoNAkKaGPM1RKBZnmzz37GOUy5WJ8jhxEQYJMiv+PG6kDfLYwvvP+j9/8O+F0MXfHStZFR9/8vv+vPj2d36bZ57+OBBSCWrY0mJuZZ7MwI2bl/HdErc2brC2vkIcWXQ7A/LMMM5ClJJ0Ol2kVFQCG1vOMNM6xfzMWWamzvDg7kPmlydMxHzvNzRCszS1QKZzttp7aM2Hzh7WsYeeNILTC7N0DhUb165j1RqFsecxsLpgHhX6xCe10GlO+9gDm/3dXaaW1tk53MW1FUc7GhHDsD0iS2JspZiq15FGcvXSfXI0Z0/PcvX1h5iwjMljdh7uE0YJN4ebTC1PH8trThbCNljH2shGaSxXkmlT6DQrjZIC6xjmKKQ5tqEqyDo6S7Gc4sGk0cisgOtZGlKdok7AzNrY6WFLxWHFkESKRinDsxSHvRxUztHARj6c5sJSh+WqRa3ksdPrc3BUIYxydG7h+A5hnDAcJSjlFEQCk2GdQOTJsgIa9RoqNaRpinYF6TDFtTzSOCUaZ+RJRmzGGN9i0A4JeyOwQ7AD3LJHcy4gHdvIQNLeG9Ko10l7KcNscnzulRv3C2icMWhjeHqxTGd/RNrtsb/bIc6OSU0YhIHAdXn/0g2qVoxlWzjPWNRqNWxLFcJGpiDxvPSt7zIOQ/7OJ396skSyGClzRGoQFDBPYwqT10znpFGCsmwCaXDtoiiLOEKbBJlbNF1JyRNoPHSiSLMMIzJ8mWFbk9cQnWZUy35hnKoEWOqYOCZ+AMMtBEiRgzEkaUqWpeSZptM5AGA0GtJpPyBLctI4Jb/wJOtrc5TLlYnyOHERFh8Impjv//p7n0/wEz78Bb8fWiiFwJwAF3vv/rvE2RZlr8AWjsMRw2GfUZRgWYI0G+G6im6nTaeT4Nl1QBH4PkbmbG/vYFkucRhj0mmisc3+/gFvv/0mFb82cR5Ga0AhpEEIze72Di8+/wkunFrjW2++gWvbWEYS5zFZliKlzVSzTDoaU/VcKs1pHu5ugyo6ZS1T0PJDksdJ4uLTc9z8o/v4wiYaQQ4Io4ijnMArxNbfefMBWS7Io4QkygnHCY1ph0994iy/8U+vMBwOyPIxeRZjTMbY5Oxud1lZmjwXWxb6CugcYzTC8SHNUQiUiIoCLQuKt9aGzIDIcoQBT5ULQSOp0EYhhYWWhlzmSK0+fFxPEjudkKdXHJJEECY5QklGI8k4hfmWZrllsbLo8P61Ma2SYWluzJmmQmc2lkwZ5gYjbMKoh9FF2ZWWYBRnCDP5JC8ZF67WlvBACSwBpXINGQmCICAMU5Jc41Yr5EmCHfhUSmVszyVMMpI0IRtGlEolBr0B/cEA27IRmWEYTk4aETJFYAo/RwnhMAFZdHgLDZ+DUUYYa2yZU/JK+J5Dbzhmb++IUsnH6EJiwLaKbnHQH/DqG+/x1W+8QbUyOcEp1hKJQepC9S83ujivSpBoQS4UQoCjbBwEGItcSApjMoUvNBYJiZZkloMUAkdJfAOoyd15XMtm5+EdHM/Dq9Zwj4WtLGWhLPmhKmGaxkiRIaVgPB6T54Vy2nhUHPtwHJLkFkI5YDm0pudZWVmZOI+TF2FZ3Izm+EHx/SpTH+giIH7whi1uHBtNzoqzx95hTCibcGxzbwCjTsYQ63cMn3lugVv3NghDycFuSLPu4wceWWyQAtYX1+l1NMP+mEjB8vwF2nv3SdBUmnUO+iOIoEIf3b/Hjff+iKlWi3/nb/zdifP4oBv4wF0DZfGVb77Ec09+jL/2hR/hpVdf5s7mJlguriWYa1RptuZ4+GCHg+4RP/LsU1xcW+TlK1cZ9I/lANXxMeFkKmrf+sYGQabQUnFw/4AgScmjjEGW0WzVOTzocat7gKsEzz79BMtLFR689z6Pr7dYrtSQ4gBbZQijKZdcRqMcW1roVKNOACd3pIMKfPI4Ic80rl/BK9lIaTFUgixJSLL8mLAisHXE8499kYpXZdi+xidefAytqkinwj/59d9BCIU8FvY0J7hi63UPy6TEQtKJDRXb4syyolEq8Qt/8+e5dq3D7//W11iseGgtSdOAfjziyfM1GrOneOPt+yTjiKGjuDyQYBukjHlyKcAWkx8Q2/Ygl2QIpBOQC0OgFbqkSOwEoWGxNU8vGpAK8CLwluYZjVOMHjLYOeTtjT1mpqbIbUUlKFMtVxF+ioonp+k+/f