1 lines (1 with data), 379.4 kB

{"cells":[{"cell_type":"markdown","metadata":{"id":"ZshjB7s1VG3v"},"source":["Environment and Libraries"]},{"cell_type":"code","source":["# Note: Importing segmentation models library may give you generic_utils error on TF2.x\n","# When the error shows up, click the __init__.py link in the error message and change..\n","# keras.utils.generic_utils.get_custom_objects().update(custom_objects)\n","# to\n","# keras.utils.get_custom_objects().update(custom_objects)\n","!pip install -U segmentation-models\n","!pip install unet"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"KlFBYUK17oLx","executionInfo":{"status":"ok","timestamp":1696839787071,"user_tz":-780,"elapsed":15441,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"}},"outputId":"91858310-2b10-4ee2-caca-a8aa2139d3a9"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting segmentation-models\n","  Downloading segmentation_models-1.0.1-py3-none-any.whl (33 kB)\n","Collecting keras-applications<=1.0.8,>=1.0.7 (from segmentation-models)\n","  Downloading Keras_Applications-1.0.8-py3-none-any.whl (50 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.7/50.7 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting image-classifiers==1.0.0 (from segmentation-models)\n","  Downloading image_classifiers-1.0.0-py3-none-any.whl (19 kB)\n","Collecting efficientnet==1.0.0 (from segmentation-models)\n","  Downloading efficientnet-1.0.0-py3-none-any.whl (17 kB)\n","Requirement already satisfied: scikit-image in /usr/local/lib/python3.10/dist-packages (from efficientnet==1.0.0->segmentation-models) (0.19.3)\n","Requirement already satisfied: numpy>=1.9.1 in /usr/local/lib/python3.10/dist-packages (from keras-applications<=1.0.8,>=1.0.7->segmentation-models) (1.23.5)\n","Requirement already satisfied: h5py in /usr/local/lib/python3.10/dist-packages (from keras-applications<=1.0.8,>=1.0.7->segmentation-models) (3.9.0)\n","Requirement already satisfied: scipy>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->efficientnet==1.0.0->segmentation-models) (1.11.3)\n","Requirement already satisfied: networkx>=2.2 in /usr/local/lib/python3.10/dist-packages (from scikit-image->efficientnet==1.0.0->segmentation-models) (3.1)\n","Requirement already satisfied: pillow!=7.1.0,!=7.1.1,!=8.3.0,>=6.1.0 in /usr/local/lib/python3.10/dist-packages (from scikit-image->efficientnet==1.0.0->segmentation-models) (9.4.0)\n","Requirement already satisfied: imageio>=2.4.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->efficientnet==1.0.0->segmentation-models) (2.31.5)\n","Requirement already satisfied: tifffile>=2019.7.26 in /usr/local/lib/python3.10/dist-packages (from scikit-image->efficientnet==1.0.0->segmentation-models) (2023.9.26)\n","Requirement already satisfied: PyWavelets>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-image->efficientnet==1.0.0->segmentation-models) (1.4.1)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from scikit-image->efficientnet==1.0.0->segmentation-models) (23.2)\n","Installing collected packages: keras-applications, image-classifiers, efficientnet, segmentation-models\n","Successfully installed efficientnet-1.0.0 image-classifiers-1.0.0 keras-applications-1.0.8 segmentation-models-1.0.1\n","Collecting unet\n","  Downloading unet-0.7.7-py2.py3-none-any.whl (8.1 kB)\n","Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from unet) (2.0.1+cu118)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch->unet) (3.12.4)\n","Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch->unet) (4.5.0)\n","Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->unet) (1.12)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->unet) (3.1)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->unet) (3.1.2)\n","Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch->unet) (2.0.0)\n","Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch->unet) (3.27.6)\n","Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch->unet) (17.0.2)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->unet) (2.1.3)\n","Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->unet) (1.3.0)\n","Installing collected packages: unet\n","Successfully installed unet-0.7.7\n"]}]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":297},"executionInfo":{"elapsed":30356,"status":"error","timestamp":1696840208234,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"},"user_tz":-780},"id":"KP9eNozYVG30","outputId":"6cf5eeb6-6b98-4578-c8b9-dff27aca2127"},"outputs":[{"output_type":"stream","name":"stdout","text":["2.13.1\n","2.13.0\n","Mounted at /content/drive\n"]},{"output_type":"error","ename":"SystemError","evalue":"ignored","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mSystemError\u001b[0m                               Traceback (most recent call last)","\u001b[0;32m<ipython-input-2-1766418f2540>\u001b[0m in \u001b[0;36m<cell line: 61>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     71\u001b[0m   \u001b[0mdevice_name\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtest\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgpu_device_name\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     72\u001b[0m   \u001b[0;32mif\u001b[0m \u001b[0mdevice_name\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0;34m'/device:GPU:0'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 73\u001b[0;31m     \u001b[0;32mraise\u001b[0m \u001b[0mSystemError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'GPU device not found'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     74\u001b[0m   \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Found GPU at: {}'\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     75\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mSystemError\u001b[0m: GPU device not found"]}],"source":["# Note: Importing segmentation models library may give you generic_utils error on TF2.x\n","# When the error shows up, click the __init__.py link in the error message and change..\n","# keras.utils.generic_utils.get_custom_objects().update(custom_objects)\n","# to\n","# keras.utils.get_custom_objects().update(custom_objects)\n","# Then save the init.py file and restart runtime and run this cell\n","\n","\n","#Libraries\n","import cv2\n","import os\n","import glob\n","import warnings\n","import scipy.misc\n","import numpy as np\n","# # import nibabel as nib\n","# import SimpleITK as sitk\n","from scipy import ndimage\n","import matplotlib.pyplot as plt\n","# os.environ['PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION'] = 'python'\n","from matplotlib.widgets import Slider\n","from tqdm import tqdm\n","\n","# import keras.api._v2.keras as keras\n","import tensorflow as tf\n","from tensorflow import keras\n","# from tensorflow.keras import layers\n","from keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, Concatenate, BatchNormalization, Activation, Conv2DTranspose, concatenate, Dropout, Flatten, Dense, Concatenate\n","from keras.preprocessing.image import ImageDataGenerator\n","from sklearn.model_selection import train_test_split\n","from keras.models import Model, load_model\n","from keras.optimizers import Adam\n","from keras.callbacks import ModelCheckpoint, EarlyStopping\n","from scipy.spatial.distance import directed_hausdorff\n","\n","\n","import segmentation_models as sm\n","import keras\n","import tensorflow\n","print(keras.__version__)\n","print(tensorflow.__version__)\n","\n","from sklearn.model_selection import train_test_split\n","from keras.utils import to_categorical\n","from keras.models import load_model\n","from keras.callbacks import ModelCheckpoint, EarlyStopping\n","from keras.metrics import MeanIoU\n","from keras.callbacks import Callback\n","\n","import numpy as np\n","from matplotlib import pyplot as plt\n","import nibabel as nib\n","from tqdm import tqdm\n","\n","\n","\n","\n","if True:\n","  # Google drive\n","  from google.colab import drive\n","  drive.mount('/content/drive')\n","\n","  # WD for Data\n","  os.getcwd()\n","  os.chdir('/content/drive/MyDrive/Colab Notebooks')\n","\n","  # GPU\n","  device_name = tf.test.gpu_device_name()\n","  if device_name != '/device:GPU:0':\n","    raise SystemError('GPU device not found')\n","  print('Found GPU at: {}'.format(device_name))\n","\n","  # TPU\n","  # resolver = tf.distribute.cluster_resolver.TPUClusterResolver(tpu='')\n","  # tf.config.experimental_connect_to_cluster(resolver)\n","  # # This is the TPU initialization code that has to be at the beginning.\n","  # tf.tpu.experimental.initialize_tpu_system(resolver)\n","  # print(\"All devices: \", tf.config.list_logical_devices('TPU'))\n","\n","  from psutil import virtual_memory\n","  ram_gb = virtual_memory().total / 1e9\n","  print('Your runtime has {:.1f} gigabytes of available RAM\\n'.format(ram_gb))\n","\n","  if ram_gb < 20:\n","    print('Not using a high-RAM runtime')\n","  else:\n","    print('You are using a high-RAM runtime!')"]},{"cell_type":"markdown","metadata":{"id":"-TDSFKk1VG32"},"source":["Preprocessing Data"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"93yEBkprVG33","outputId":"fc92d26f-ba3e-4204-f126-0532bf296def","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1695640158075,"user_tz":-780,"elapsed":40225,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"}}},"outputs":[{"output_type":"stream","name":"stdout","text":["Number of Patients:  4\n","Number of Segmentation Classes:  5\n","Data Augmentation: False\n","\n","\n","['/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/msk_004_0000.nii.gz', '/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/msk_007_0000.nii.gz', '/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/msk_011_0000.nii.gz', '/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/msk_021_0000.nii.gz']\n","['/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/msk_004.nii.gz', '/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/msk_007.nii.gz', '/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/msk_011.nii.gz', '/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/msk_021.nii.gz']\n","\n","\n"]},{"output_type":"stream","name":"stderr","text":["\rReading in Training MRI Images:   0%|          | 0/4 [00:00<?, ?it/s]"]},{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/msk_004_0000.nii.gz\n"]},{"output_type":"stream","name":"stderr","text":["\rReading in Training MRI Images:  25%|██▌       | 1/4 [00:06<00:18,  6.07s/it]"]},{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/msk_007_0000.nii.gz\n"]},{"output_type":"stream","name":"stderr","text":["\rReading in Training MRI Images:  50%|█████     | 2/4 [00:10<00:09,  4.96s/it]"]},{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/msk_011_0000.nii.gz\n"]},{"output_type":"stream","name":"stderr","text":["\rReading in Training MRI Images:  75%|███████▌  | 3/4 [00:14<00:04,  4.75s/it]"]},{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/msk_021_0000.nii.gz\n"]},{"output_type":"stream","name":"stderr","text":["Reading in Training MRI Images: 100%|██████████| 4/4 [00:18<00:00,  4.71s/it]\n","Reading in Training Multi-Class Labelled Masks:   0%|          | 0/4 [00:00<?, ?it/s]"]},{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/msk_004.nii.gz\n"]},{"output_type":"stream","name":"stderr","text":["\rReading in Training Multi-Class Labelled Masks:  25%|██▌       | 1/4 [00:01<00:05,  1.72s/it]"]},{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/msk_007.nii.gz\n"]},{"output_type":"stream","name":"stderr","text":["\rReading in Training Multi-Class Labelled Masks:  50%|█████     | 2/4 [00:04<00:05,  2.52s/it]"]},{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/msk_011.nii.gz\n"]},{"output_type":"stream","name":"stderr","text":["\rReading in Training Multi-Class Labelled Masks:  75%|███████▌  | 3/4 [00:07<00:02,  2.76s/it]"]},{"output_type":"stream","name":"stdout","text":["/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/msk_021.nii.gz\n"]},{"output_type":"stream","name":"stderr","text":["Reading in Training Multi-Class Labelled Masks: 100%|██████████| 4/4 [00:09<00:00,  2.48s/it]\n"]},{"output_type":"stream","name":"stdout","text":["\n","\n","Total images in the original dataset are:  2199\n","Image data shape is:  (2199, 256, 256, 1)\n","Mask data shape is:  (2199, 256, 256, 1)\n","Max pixel value in image is:  0.9783952832221985\n","Labels in the mask are :  [0 1 2 3 4]\n","Training Images Shape:  (1759, 256, 256, 1)\n","Training Labels Shape:  (1759, 256, 256, 1)\n","Validation Images Shape:  (440, 256, 256, 1)\n","Validation Labels Shape;:  (440, 256, 256, 1)\n"]}],"source":["os.chdir(\"/content/drive/MyDrive/Colab Notebooks\")\n","from data_augmentation import DataAugmentation\n","\n","# Parameters to change according to experiment\n","n_classes = 5 #Number of classes for segmentation\n","training_augmentation = False\n","num_augmentations = 1\n","patient_index_training = [4,7,11,21]\n","\n","print(\"Number of Patients: \", len(patient_index_training))\n","print(\"Number of Segmentation Classes: \", n_classes)\n","print((\"Data Augmentation: {}\").format(training_augmentation))\n","print('\\n')\n","\n","image_names = glob.glob(\"/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/*.nii.gz\")\n","image_names.sort()\n","\n","\n","mask_names = glob.glob(\"/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/*.nii.gz\")\n","mask_names.sort()\n","\n","\n","image_names_train, mask_names_train = [], []\n","for i in range (len(image_names)):\n","  patient_index = int((image_names[i].split('_'))[-2])\n","  for x in range (len(patient_index_training)):\n","    if (patient_index == patient_index_training[x]):\n","      image_names_train.append(image_names[i])\n","      mask_names_train.append(mask_names[i])\n","image_names = image_names_train\n","mask_names = mask_names_train\n","print(image_names)\n","print(mask_names)\n","print('\\n')\n","\n","for image in tqdm(image_names, desc = 'Reading in Training MRI Images'):\n","  print(image)\n","  img = nib.load(image)\n","  img_data = img.get_fdata()\n","  if (image == image_names[0]):\n","    img_stack = img_data\n","  else:\n","    img_stack = np.concatenate((img_stack, img_data), axis = 0)\n","\n","\n","for mask in tqdm(mask_names, desc = 'Reading in Training Multi-Class Labelled Masks'):\n","  print(mask)\n","  msk = nib.load(mask)\n","  msk_data = msk.get_fdata()\n","  if (mask == mask_names[0]):\n","    msk_stack = msk_data\n","  else:\n","    msk_stack = np.concatenate((msk_stack, msk_data), axis = 0)\n","msk_stack = msk_stack.astype(np.uint8)\n","\n","print('\\n')\n","print(\"Total images in the original dataset are: \", len(img_stack))\n","print(\"Image data shape is: \", img_stack.shape)\n","print(\"Mask data shape is: \", msk_stack.shape)\n","print(\"Max pixel value in image is: \", img_stack.max())\n","print(\"Labels in the mask are : \", np.unique(msk_stack))\n","\n","\n","if (training_augmentation == True):\n","  print('\\n')\n","  print('-'*30)\n","  print('Data Augmentation Starting...')\n","  print('-'*30)\n","\n","  img_stack_aug, msk_stack_aug = DataAugmentation(img_stack, msk_stack, num_augmentations)\n","\n","  img_stack_aug = np.expand_dims(img_stack_aug, axis=-1)\n","  msk_stack_aug = np.expand_dims(msk_stack_aug, axis=-1)\n","\n","  print('Number of Augmentation per Input: ', num_augmentations)\n","  print('\\n')\n","  print('Shape of Augmented Images: ', img_stack_aug.shape)\n","  print('Shape of Augmented Masks: ', msk_stack_aug.shape)\n","  print('\\n')\n","\n","  if True:\n","      img_stack = np.concatenate((img_stack, img_stack_aug), axis=0)\n","      msk_stack = np.concatenate((msk_stack, msk_stack_aug), axis=0)\n","\n","  print('Shape of Training Image Data: ', img_stack.shape)\n","  print('Shape of Training Image Masks: ', msk_stack.shape)\n","\n","  print('-'*30)\n","  print('Completed Data Augmentation Stage!')\n","  print('-'*30)\n","  print('\\n')\n","\n","# Channel = 3\n","img_stack = np.repeat(img_stack, 3, axis=3)\n","\n","\n","#Split training data\n","X_train, X_test, y_train, y_test = train_test_split(img_stack, msk_stack, test_size = 0.2, random_state = 42)\n","\n","train_masks_cat = to_categorical(y_train, num_classes=n_classes)\n","y_train_cat = train_masks_cat.reshape((y_train.shape[0], y_train.shape[1], y_train.shape[2], n_classes))\n","\n","test_masks_cat = to_categorical(y_test, num_classes=n_classes)\n","y_test_cat = test_masks_cat.reshape((y_test.shape[0], y_test.shape[1], y_test.shape[2], n_classes))\n","\n","print('Training Images Shape: ', X_train.shape)\n","print('Training Labels Shape: ', y_train.shape)\n","print('Validation Images Shape: ', X_test.shape)\n","print('Validation Labels Shape;: ', y_test.shape)"]},{"cell_type":"markdown","metadata":{"id":"O-gbUvegVG39"},"source":["2DUNet Model"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"95KjH9rsmPYo"},"outputs":[],"source":["# Define U-Net model\n","def unet_model(input_shape, num_classes):\n","    inputs = Input(input_shape)\n","\n","    # Encoder\n","    conv1 = Conv2D(64, 3, activation='relu', padding='same')(inputs)\n","    conv1 = Conv2D(64, 3, activation='relu', padding='same')(conv1)\n","    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)\n","\n","    conv2 = Conv2D(128, 3, activation='relu', padding='same')(pool1)\n","    conv2 = Conv2D(128, 3, activation='relu', padding='same')(conv2)\n","    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)\n","\n","    conv3 = Conv2D(256, 3, activation='relu', padding='same')(pool2)\n","    conv3 = Conv2D(256, 3, activation='relu', padding='same')(conv3)\n","    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)\n","\n","    conv4 = Conv2D(512, 3, activation='relu', padding='same')(pool3)\n","    conv4 = Conv2D(512, 3, activation='relu', padding='same')(conv4)\n","    drop4 = Dropout(0.5)(conv4)\n","    pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)\n","\n","    # Bottleneck\n","    conv5 = Conv2D(1024, 3, activation='relu', padding='same')(pool4)\n","    conv5 = Conv2D(1024, 3, activation='relu', padding='same')(conv5)\n","    drop5 = Dropout(0.5)(conv5)\n","\n","    # Decoder\n","    up6 = Conv2D(512, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(drop5))\n","    merge6 = concatenate([drop4, up6], axis=3)\n","    conv6 = Conv2D(512, 3, activation='relu', padding='same')(merge6)\n","    conv6 = Conv2D(512, 3, activation='relu', padding='same')(conv6)\n","\n","    up7 = Conv2D(256, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv6))\n","    merge7 = concatenate([conv3, up7], axis=3)\n","    conv7 = Conv2D(256, 3, activation='relu', padding='same')(merge7)\n","    conv7 = Conv2D(256, 3, activation='relu', padding='same')(conv7)\n","\n","    up8 = Conv2D(128, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv7))\n","    merge8 = concatenate([conv2, up8], axis=3)\n","    conv8 = Conv2D(128, 3, activation='relu', padding='same')(merge8)\n","    conv8 = Conv2D(128, 3, activation='relu', padding='same')(conv8)\n","\n","    up9 = Conv2D(64, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv8))\n","    merge9 = concatenate([conv1, up9], axis=3)\n","    conv9 = Conv2D(64, 3, activation='relu', padding='same')(merge9)\n","    conv9 = Conv2D(64, 3, activation='relu', padding='same')(conv9)\n","\n","    outputs = Conv2D(num_classes, 1, activation='softmax')(conv9)\n","\n","    model = Model(inputs=inputs, outputs=outputs)\n","\n","    return model\n","\n","# Dice Coefficient Loss Function\n","def dice_loss(y_true, y_pred):\n","    smooth = 1e-5  # Adding a small constant to avoid division by zero\n","    # Convert y_true to float32\n","    y_true = tf.cast(y_true, tf.float32)\n","    intersection = tf.reduce_sum(y_true * y_pred, axis=[1, 2, 3])\n","    union = tf.reduce_sum(y_true, axis=[1, 2, 3]) + tf.reduce_sum(y_pred, axis=[1, 2, 3])\n","    dice_coefficient = (2.0 * intersection + smooth) / (union + smooth)\n","    loss = 1.0 - tf.reduce_mean(dice_coefficient)\n","    return loss"]},{"cell_type":"markdown","metadata":{"id":"WChXE7z8isMy"},"source":["3D-UNet"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"M4Ibu1G8d1K3"},"outputs":[],"source":["import tensorflow as tf\n","from keras.layers import Input, Conv3D, MaxPooling3D, UpSampling3D, concatenate\n","\n","def conv_block(inputs, filters, kernel_size=(3, 3, 3), activation='relu', padding='same'):\n","    return Conv3D(filters, kernel_size, activation=activation, padding=padding)(inputs)\n","\n","def unet_3d(input_shape):\n","    inputs = Input(input_shape)\n","\n","    # Encoder\n","    conv1 = conv_block(inputs, 64)\n","    pool1 = MaxPooling3D(pool_size=(2, 2, 2))(conv1)\n","\n","    conv2 = conv_block(pool1, 128)\n","    pool2 = MaxPooling3D(pool_size=(2, 2, 2))(conv2)\n","\n","    conv3 = conv_block(pool2, 256)\n","    pool3 = MaxPooling3D(pool_size=(2, 2, 2))(conv3)\n","\n","    conv4 = conv_block(pool3, 512)\n","    pool4 = MaxPooling3D(pool_size=(2, 2, 2))(conv4)\n","\n","    # Middle\n","    conv5 = conv_block(pool4, 1024)\n","\n","    # Decoder\n","    up6 = UpSampling3D(size=(2, 2, 2))(conv5)\n","    merge6 = concatenate([conv4, up6], axis=-1)\n","    conv6 = conv_block(merge6, 512)\n","\n","    up7 = UpSampling3D(size=(2, 2, 2))(conv6)\n","    merge7 = concatenate([conv3, up7], axis=-1)\n","    conv7 = conv_block(merge7, 256)\n","\n","    up8 = UpSampling3D(size=(2, 2, 2))(conv7)\n","    merge8 = concatenate([conv2, up8], axis=-1)\n","    conv8 = conv_block(merge8, 128)\n","\n","    up9 = UpSampling3D(size=(2, 2, 2))(conv8)\n","    merge9 = concatenate([conv1, up9], axis=-1)\n","    conv9 = conv_block(merge9, 64)\n","\n","    # Output layer\n","    outputs = Conv3D(1, (1, 1, 1), activation='sigmoid')(conv9)\n","\n","    model = tf.keras.Model(inputs=inputs, outputs=outputs)\n","\n","    return model"]},{"cell_type":"code","source":["input_shape = (512,512,512,1)\n","model = unet_3d(input_shape)\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"l0a4-UXlj0gx","executionInfo":{"status":"ok","timestamp":1696840346355,"user_tz":-780,"elapsed":2294,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"}},"outputId":"79f96b17-4626-4382-c83c-80bd99adbbd6"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Model: \"model\"\n","__________________________________________________________________________________________________\n"," Layer (type)                Output Shape                 Param #   Connected to                  \n","==================================================================================================\n"," input_5 (InputLayer)        [(None, 512, 512, 512, 1)]   0         []                            \n","                                                                                                  \n"," conv3d_6 (Conv3D)           (None, 512, 512, 512, 64)    1792      ['input_5[0][0]']             \n","                                                                                                  \n"," max_pooling3d_4 (MaxPoolin  (None, 256, 256, 256, 64)    0         ['conv3d_6[0][0]']            \n"," g3D)                                                                                             \n","                                                                                                  \n"," conv3d_7 (Conv3D)           (None, 256, 256, 256, 128)   221312    ['max_pooling3d_4[0][0]']     \n","                                                                                                  \n"," max_pooling3d_5 (MaxPoolin  (None, 128, 128, 128, 128)   0         ['conv3d_7[0][0]']            \n"," g3D)                                                                                             \n","                                                                                                  \n"," conv3d_8 (Conv3D)           (None, 128, 128, 128, 256)   884992    ['max_pooling3d_5[0][0]']     \n","                                                                                                  \n"," max_pooling3d_6 (MaxPoolin  (None, 64, 64, 64, 256)      0         ['conv3d_8[0][0]']            \n"," g3D)                                                                                             \n","                                                                                                  \n"," conv3d_9 (Conv3D)           (None, 64, 64, 64, 512)      3539456   ['max_pooling3d_6[0][0]']     \n","                                                                                                  \n"," max_pooling3d_7 (MaxPoolin  (None, 32, 32, 32, 512)      0         ['conv3d_9[0][0]']            \n"," g3D)                                                                                             \n","                                                                                                  \n"," conv3d_10 (Conv3D)          (None, 32, 32, 32, 1024)     1415680   ['max_pooling3d_7[0][0]']     \n","                                                          0                                       \n","                                                                                                  \n"," up_sampling3d (UpSampling3  (None, 64, 64, 64, 1024)     0         ['conv3d_10[0][0]']           \n"," D)                                                                                               \n","                                                                                                  \n"," concatenate (Concatenate)   (None, 64, 64, 64, 1536)     0         ['conv3d_9[0][0]',            \n","                                                                     'up_sampling3d[0][0]']       \n","                                                                                                  \n"," conv3d_11 (Conv3D)          (None, 64, 64, 64, 512)      2123417   ['concatenate[0][0]']         \n","                                                          6                                       \n","                                                                                                  \n"," up_sampling3d_1 (UpSamplin  (None, 128, 128, 128, 512)   0         ['conv3d_11[0][0]']           \n"," g3D)                                                                                             \n","                                                                                                  \n"," concatenate_1 (Concatenate  (None, 128, 128, 128, 768)   0         ['conv3d_8[0][0]',            \n"," )                                                                   'up_sampling3d_1[0][0]']     \n","                                                                                                  \n"," conv3d_12 (Conv3D)          (None, 128, 128, 128, 256)   5308672   ['concatenate_1[0][0]']       \n","                                                                                                  \n"," up_sampling3d_2 (UpSamplin  (None, 256, 256, 256, 256)   0         ['conv3d_12[0][0]']           \n"," g3D)                                                                                             \n","                                                                                                  \n"," concatenate_2 (Concatenate  (None, 256, 256, 256, 384)   0         ['conv3d_7[0][0]',            \n"," )                                                                   'up_sampling3d_2[0][0]']     \n","                                                                                                  \n"," conv3d_13 (Conv3D)          (None, 256, 256, 256, 128)   1327232   ['concatenate_2[0][0]']       \n","                                                                                                  \n"," up_sampling3d_3 (UpSamplin  (None, 512, 512, 512, 128)   0         ['conv3d_13[0][0]']           \n"," g3D)                                                                                             \n","                                                                                                  \n"," concatenate_3 (Concatenate  (None, 512, 512, 512, 192)   0         ['conv3d_6[0][0]',            \n"," )                                                                   'up_sampling3d_3[0][0]']     \n","                                                                                                  \n"," conv3d_14 (Conv3D)          (None, 512, 512, 512, 64)    331840    ['concatenate_3[0][0]']       \n","                                                                                                  \n"," conv3d_15 (Conv3D)          (None, 512, 512, 512, 1)     65        ['conv3d_14[0][0]']           \n","                                                                                                  \n","==================================================================================================\n","Total params: 47006337 (179.31 MB)\n","Trainable params: 47006337 (179.31 MB)\n","Non-trainable params: 0 (0.00 Byte)\n","__________________________________________________________________________________________________\n"]}]},{"cell_type":"markdown","source":["2D UNet - Pytorch (nnUNet)"],"metadata":{"id":"BdxabQoTr6uX"}},{"cell_type":"code","source":["from keras.models import Model\n","from keras.layers import Input, Concatenate, Conv2D, MaxPooling2D, UpSampling2D, Dropout\n","\n","def conv_block(inputs, filters, kernel_size=3, activation=relu):\n","    x = Conv2D(filters, kernel_size, padding='same')(inputs)\n","    x = BatchNormalization()(x)\n","    x = activation(x)\n","    x = Conv2D(filters, kernel_size, padding='same')(x)\n","    x = BatchNormalization()(x)\n","    x = activation(x)\n","    return x\n","\n","def downsample_block(inputs, filters, kernel_size=3, activation=relu):\n","    x = conv_block(inputs, filters, kernel_size, activation)\n","    pool = MaxPooling2D()(x)\n","    return x, pool\n","\n","def upsample_block(inputs, skip, filters, kernel_size=3, activation=relu):\n","    x = Conv2DTranspose(filters, kernel_size, strides=2, padding='same')(inputs)\n","    x = concatenate([x, skip], axis = 3)\n","    x = conv_block(x, filters, kernel_size, activation)\n","    return x\n","\n","def unet(input_shape, num_classes):\n","    inputs = Input(input_shape)\n","\n","    # Encoder (contracting path)\n","    enc1, pool1 = downsample_block(inputs, 32)\n","    enc2, pool2 = downsample_block(pool1, 64)\n","    enc3, pool3 = downsample_block(pool2, 128)\n","    enc4, pool4 = downsample_block(pool3, 256)\n","    enc5, _ = downsample_block(pool4, 480)\n","\n","    # Bottleneck\n","    bottleneck = conv_block(enc5, 480)\n","\n","    # Decoder (expansive path)\n","    dec4 = upsample_block(bottleneck, enc4, 256)\n","    dec3 = upsample_block(dec4, enc3, 128)\n","    dec2 = upsample_block(dec3, enc2, 64)\n","    dec1 = upsample_block(dec2, enc1, 32)\n","\n","    # Output segmentation mask\n","    outputs = Conv2D(num_classes, 1, activation='sigmoid')(dec1)\n","\n","    model = Model(inputs, outputs)\n","\n","    return model"],"metadata":{"id":"XaMT4jHBr6CD"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["image_size = 256\n","image_channels = 3\n","\n","unet = Unet(input_shape = (image_size, image_size, image_channels),\n","            filters = [16, 32, 64, 128, 256],\n","            padding = \"same\")\n","\n","# call the build netowrk API to build the network.\n","model = unet.Build_UNetwork()\n","\n","# compile & summarize the model\n","if model is not None:\n","    unet.CompileAndSummarizeModel(model = model)\n","\n","\n","model.fit(X_train,\n","          validation_data = valid_gen,\n","          steps_per_epoch = train_steps,\n","          validation_steps = valid_steps,\n","          epochs = 10)"],"metadata":{"id":"tBvPa2AVb4rU"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["#2D U-Net Hyper-parameter Config\n","\n","activation='softmax'\n","LR = 0.0001\n","optim = tensorflow.keras.optimizers.Adam(LR)\n","dice_loss = sm.losses.DiceLoss()\n","\n","num_classes = 5\n","input_shape = (256, 256, 1)\n","\n","early_stopping = EarlyStopping(monitor='val_loss', patience=20, restore_best_weights=True)\n","checkpoint = ModelCheckpoint('/content/drive/MyDrive/Colab Notebooks/2dunet_best.hdf5', monitor='val_f1-score', save_best_only=True, mode='max')\n","model = unet_model(input_shape, num_classes)\n","model.compile(optim, total_loss, metrics=metrics)"],"metadata":{"id":"cCT2N-ZjIRRS"},"execution_count":null,"outputs":[]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"qdTaaVCUVG3-","executionInfo":{"status":"ok","timestamp":1695640159630,"user_tz":-780,"elapsed":1580,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"}},"outputId":"9461c762-1aa1-4dc3-dbee-fc7005f6e8f1"},"outputs":[{"output_type":"stream","name":"stdout","text":["Model: \"model\"\n","__________________________________________________________________________________________________\n"," Layer (type)                Output Shape                 Param #   Connected to                  \n","==================================================================================================\n"," input_1 (InputLayer)        [(None, 256, 256, 1)]        0         []                            \n","                                                                                                  \n"," conv2d (Conv2D)             (None, 256, 256, 64)         640       ['input_1[0][0]']             \n","                                                                                                  \n"," conv2d_1 (Conv2D)           (None, 256, 256, 64)         36928     ['conv2d[0][0]']              \n","                                                                                                  \n"," max_pooling2d (MaxPooling2  (None, 128, 128, 64)         0         ['conv2d_1[0][0]']            \n"," D)                                                                                               \n","                                                                                                  \n"," conv2d_2 (Conv2D)           (None, 128, 128, 128)        73856     ['max_pooling2d[0][0]']       \n","                                                                                                  \n"," conv2d_3 (Conv2D)           (None, 128, 128, 128)        147584    ['conv2d_2[0][0]']            \n","                                                                                                  \n"," max_pooling2d_1 (MaxPoolin  (None, 64, 64, 128)          0         ['conv2d_3[0][0]']            \n"," g2D)                                                                                             \n","                                                                                                  \n"," conv2d_4 (Conv2D)           (None, 64, 64, 256)          295168    ['max_pooling2d_1[0][0]']     \n","                                                                                                  \n"," conv2d_5 (Conv2D)           (None, 64, 64, 256)          590080    ['conv2d_4[0][0]']            \n","                                                                                                  \n"," max_pooling2d_2 (MaxPoolin  (None, 32, 32, 256)          0         ['conv2d_5[0][0]']            \n"," g2D)                                                                                             \n","                                                                                                  \n"," conv2d_6 (Conv2D)           (None, 32, 32, 512)          1180160   ['max_pooling2d_2[0][0]']     \n","                                                                                                  \n"," conv2d_7 (Conv2D)           (None, 32, 32, 512)          2359808   ['conv2d_6[0][0]']            \n","                                                                                                  \n"," dropout (Dropout)           (None, 32, 32, 512)          0         ['conv2d_7[0][0]']            \n","                                                                                                  \n"," max_pooling2d_3 (MaxPoolin  (None, 16, 16, 512)          0         ['dropout[0][0]']             \n"," g2D)                                                                                             \n","                                                                                                  \n"," conv2d_8 (Conv2D)           (None, 16, 16, 1024)         4719616   ['max_pooling2d_3[0][0]']     \n","                                                                                                  \n"," conv2d_9 (Conv2D)           (None, 16, 16, 1024)         9438208   ['conv2d_8[0][0]']            \n","                                                                                                  \n"," dropout_1 (Dropout)         (None, 16, 16, 1024)         0         ['conv2d_9[0][0]']            \n","                                                                                                  \n"," up_sampling2d (UpSampling2  (None, 32, 32, 1024)         0         ['dropout_1[0][0]']           \n"," D)                                                                                               \n","                                                                                                  \n"," conv2d_10 (Conv2D)          (None, 32, 32, 512)          2097664   ['up_sampling2d[0][0]']       \n","                                                                                                  \n"," concatenate (Concatenate)   (None, 32, 32, 1024)         0         ['dropout[0][0]',             \n","                                                                     'conv2d_10[0][0]']           \n","                                                                                                  \n"," conv2d_11 (Conv2D)          (None, 32, 32, 512)          4719104   ['concatenate[0][0]']         \n","                                                                                                  \n"," conv2d_12 (Conv2D)          (None, 32, 32, 512)          2359808   ['conv2d_11[0][0]']           \n","                                                                                                  \n"," up_sampling2d_1 (UpSamplin  (None, 64, 64, 512)          0         ['conv2d_12[0][0]']           \n"," g2D)                                                                                             \n","                                                                                                  \n"," conv2d_13 (Conv2D)          (None, 64, 64, 256)          524544    ['up_sampling2d_1[0][0]']     \n","                                                                                                  \n"," concatenate_1 (Concatenate  (None, 64, 64, 512)          0         ['conv2d_5[0][0]',            \n"," )                                                                   'conv2d_13[0][0]']           \n","                                                                                                  \n"," conv2d_14 (Conv2D)          (None, 64, 64, 256)          1179904   ['concatenate_1[0][0]']       \n","                                                                                                  \n"," conv2d_15 (Conv2D)          (None, 64, 64, 256)          590080    ['conv2d_14[0][0]']           \n","                                                                                                  \n"," up_sampling2d_2 (UpSamplin  (None, 128, 128, 256)        0         ['conv2d_15[0][0]']           \n"," g2D)                                                                                             \n","                                                                                                  \n"," conv2d_16 (Conv2D)          (None, 128, 128, 128)        131200    ['up_sampling2d_2[0][0]']     \n","                                                                                                  \n"," concatenate_2 (Concatenate  (None, 128, 128, 256)        0         ['conv2d_3[0][0]',            \n"," )                                                                   'conv2d_16[0][0]']           \n","                                                                                                  \n"," conv2d_17 (Conv2D)          (None, 128, 128, 128)        295040    ['concatenate_2[0][0]']       \n","                                                                                                  \n"," conv2d_18 (Conv2D)          (None, 128, 128, 128)        147584    ['conv2d_17[0][0]']           \n","                                                                                                  \n"," up_sampling2d_3 (UpSamplin  (None, 256, 256, 128)        0         ['conv2d_18[0][0]']           \n"," g2D)                                                                                             \n","                                                                                                  \n"," conv2d_19 (Conv2D)          (None, 256, 256, 64)         32832     ['up_sampling2d_3[0][0]']     \n","                                                                                                  \n"," concatenate_3 (Concatenate  (None, 256, 256, 128)        0         ['conv2d_1[0][0]',            \n"," )                                                                   'conv2d_19[0][0]']           \n","                                                                                                  \n"," conv2d_20 (Conv2D)          (None, 256, 256, 64)         73792     ['concatenate_3[0][0]']       \n","                                                                                                  \n"," conv2d_21 (Conv2D)          (None, 256, 256, 64)         36928     ['conv2d_20[0][0]']           \n","                                                                                                  \n"," conv2d_22 (Conv2D)          (None, 256, 256, 5)          325       ['conv2d_21[0][0]']           \n","                                                                                                  \n","==================================================================================================\n","Total params: 31030853 (118.37 MB)\n","Trainable params: 31030853 (118.37 MB)\n","Non-trainable params: 0 (0.00 Byte)\n","__________________________________________________________________________________________________\n","None\n"]}],"source":["activation='softmax'\n","LR = 0.0001\n","optim = tensorflow.keras.optimizers.Adam(LR)\n","\n","# Segmentation models losses can be combined together by '+' and scaled by integer or float factor\n","dice_loss = sm.losses.DiceLoss()\n","focal_loss = sm.losses.CategoricalFocalLoss()\n","total_loss = dice_loss + (1 * focal_loss)\n","\n","metrics = [\n","    sm.metrics.IOUScore(threshold=0.5),\n","    sm.metrics.FScore(threshold=0.5),\n","]\n","\n","num_classes = 5\n","input_shape = (256, 256, 1)\n","num_epochs = 10\n","batch_size = 4\n","\n","early_stopping = EarlyStopping(monitor='val_loss', patience=20, restore_best_weights=True)\n","checkpoint = ModelCheckpoint('/content/drive/MyDrive/Colab Notebooks/2dunet_best.hdf5', monitor='val_f1-score', save_best_only=True, mode='max')\n","model = unet_model(input_shape, num_classes)\n","model.compile(optim, total_loss, metrics=metrics)\n","\n","print(model.summary())\n","\n","# Define input shape and number of classes\n","# input_shape = (400, 400, 1)\n","# num_classes = 1\n","# batch_size = 1\n","# num_epochs = 10\n","# early_stopping = EarlyStopping(monitor='val_loss', patience=20, restore_best_weights=True)\n","# optimizer_adam = Adam(learning_rate = 1e-4)\n","\n","# model = unet(input_shape, num_classes)\n","# model.compile(optimizer = optimizer_adam, loss = 'binary_crossentropy')\n","# # model.compile(optimizer = optimizer_adam, loss=dice_loss)\n","# checkpoint = ModelCheckpoint('model(2D, nnUNet).h5', monitor='val_loss', save_best_only=True, mode='min')\n","# model.fit(x=images_train, y=labels_train, batch_size=batch_size, epochs=num_epochs, validation_data=(images_val, labels_val), callbacks=[checkpoint, early_stopping])\n","# model.summary()"]},{"cell_type":"code","source":["AFKRun = False\n","\n","history=model.fit(X_train,\n","          y_train_cat,\n","          batch_size=30,\n","          epochs=50,\n","          verbose=1,\n","          validation_data=(X_test, y_test_cat),\n","          callbacks=[checkpoint])\n","\n","model.save('/content/drive/MyDrive/Colab Notebooks/2dunet_final.keras')\n","\n","# Performance plots\n","loss = history.history['loss']\n","val_loss = history.history['val_loss']\n","epochs = range(1, len(loss) + 1)\n","plt.plot(epochs, loss, 'y', label='Training loss')\n","plt.plot(epochs, val_loss, 'r', label='Validation loss')\n","plt.title('Training and validation loss')\n","plt.xlabel('Epochs')\n","plt.ylabel('Loss')\n","plt.legend()\n","plt.show()\n","\n","acc = history.history['iou_score']\n","val_acc = history.history['val_iou_score']\n","\n","plt.plot(epochs, acc, 'y', label='Training IOU')\n","plt.plot(epochs, val_acc, 'r', label='Validation IOU')\n","plt.title('Training and validation IOU')\n","plt.xlabel('Epochs')\n","plt.ylabel('IOU')\n","plt.legend()\n","plt.show()\n","\n","\n","\n","if AFKRun:\n","  from google.colab import runtime\n","  runtime.unassign()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":653},"id":"1f_7ABls_G9r","executionInfo":{"status":"error","timestamp":1695640974183,"user_tz":-780,"elapsed":814556,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"}},"outputId":"46dddb0a-e302-47db-9fb3-e9a435f3e4d4"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/10\n","440/440 [==============================] - ETA: 0s - loss: 0.6583 - iou_score: 0.3538 - f1-score: 0.3544"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py:3000: UserWarning: You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.\n","  saving_api.save_model(\n"]},{"output_type":"stream","name":"stdout","text":["\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r440/440 [==============================] - 176s 341ms/step - loss: 0.6583 - iou_score: 0.3538 - f1-score: 0.3544 - val_loss: 0.6555 - val_iou_score: 0.3481 - val_f1-score: 0.3486\n","Epoch 2/10\n","440/440 [==============================] - 144s 327ms/step - loss: 0.6516 - iou_score: 0.3518 - f1-score: 0.3522 - val_loss: 0.6555 - val_iou_score: 0.3481 - val_f1-score: 0.3486\n","Epoch 3/10\n","440/440 [==============================] - 144s 327ms/step - loss: 0.6466 - iou_score: 0.3568 - f1-score: 0.3572 - val_loss: 0.6555 - val_iou_score: 0.3481 - val_f1-score: 0.3486\n","Epoch 4/10\n","440/440 [==============================] - 144s 327ms/step - loss: 0.6440 - iou_score: 0.3595 - f1-score: 0.3600 - val_loss: 0.6555 - val_iou_score: 0.3481 - val_f1-score: 0.3486\n","Epoch 5/10\n","440/440 [==============================] - 144s 327ms/step - loss: 0.6607 - iou_score: 0.3427 - f1-score: 0.3431 - val_loss: 0.6555 - val_iou_score: 0.3481 - val_f1-score: 0.3486\n","Epoch 6/10\n","193/440 [============>.................] - ETA: 1:15 - loss: 0.6510 - iou_score: 0.3524 - f1-score: 0.3529"]},{"output_type":"error","ename":"KeyboardInterrupt","evalue":"ignored","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)","\u001b[0;32m<ipython-input-5-db4de20d2f7b>\u001b[0m in \u001b[0;36m<cell line: 3>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mAFKRun\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m history=model.fit(X_train,\n\u001b[0m\u001b[1;32m      4\u001b[0m           \u001b[0my_train_cat\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m           \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m4\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     63\u001b[0m         \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     64\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 65\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     66\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     67\u001b[0m             \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_process_traceback_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__traceback__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m   1746\u001b[0m                             \u001b[0mlogs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtmp_logs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1747\u001b[0m                             \u001b[0mend_step\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstep\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mdata_handler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep_increment\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1748\u001b[0;31m                             \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_train_batch_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mend_step\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1749\u001b[0m                             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstop_training\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1750\u001b[0m                                 \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/callbacks.py\u001b[0m in \u001b[0;36mon_train_batch_end\u001b[0;34m(self, batch, logs)\u001b[0m\n\u001b[1;32m    473\u001b[0m         \"\"\"\n\u001b[1;32m    474\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_should_call_train_batch_hooks\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 475\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_batch_hook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mModeKeys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTRAIN\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"end\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    476\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    477\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mon_test_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/callbacks.py\u001b[0m in \u001b[0;36m_call_batch_hook\u001b[0;34m(self, mode, hook, batch, logs)\u001b[0m\n\u001b[1;32m    320\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_batch_begin_hook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    321\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0mhook\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m\"end\"\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 322\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_batch_end_hook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    323\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    324\u001b[0m             raise ValueError(\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/callbacks.py\u001b[0m in \u001b[0;36m_call_batch_end_hook\u001b[0;34m(self, mode, batch, logs)\u001b[0m\n\u001b[1;32m    343\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_batch_times\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch_time\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    344\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 345\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call_batch_hook_helper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhook_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    346\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    347\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_batch_times\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_num_batches_for_timing_check\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/callbacks.py\u001b[0m in \u001b[0;36m_call_batch_hook_helper\u001b[0;34m(self, hook_name, batch, logs)\u001b[0m\n\u001b[1;32m    391\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mcallback\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    392\u001b[0m             \u001b[0mhook\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcallback\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhook_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 393\u001b[0;31m             \u001b[0mhook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    394\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    395\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_check_timing\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/callbacks.py\u001b[0m in \u001b[0;36mon_train_batch_end\u001b[0;34m(self, batch, logs)\u001b[0m\n\u001b[1;32m   1091\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1092\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mon_train_batch_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1093\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_batch_update_progbar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1094\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1095\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mon_test_batch_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlogs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/callbacks.py\u001b[0m in \u001b[0;36m_batch_update_progbar\u001b[0;34m(self, batch, logs)\u001b[0m\n\u001b[1;32m   1167\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mverbose\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1168\u001b[0m             \u001b[0;31m# Only block async when verbose = 1.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1169\u001b[0;31m             \u001b[0mlogs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_utils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msync_to_numpy_or_python_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlogs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1170\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprogbar\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mseen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlogs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfinalize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1171\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/utils/tf_utils.py\u001b[0m in \u001b[0;36msync_to_numpy_or_python_type\u001b[0;34m(tensors)\u001b[0m\n\u001b[1;32m    692\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitem\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndim\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mt\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    693\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 694\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnest\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap_structure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_to_single_numpy_or_python_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtensors\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    695\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    696\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/nest.py\u001b[0m in \u001b[0;36mmap_structure\u001b[0;34m(func, *structure, **kwargs)\u001b[0m\n\u001b[1;32m    622\u001b[0m     \u001b[0mValueError\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mIf\u001b[0m \u001b[0mwrong\u001b[0m \u001b[0mkeyword\u001b[0m \u001b[0marguments\u001b[0m \u001b[0mare\u001b[0m \u001b[0mprovided\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    623\u001b[0m   \"\"\"\n\u001b[0;32m--> 624\u001b[0;31m   return nest_util.map_structure(\n\u001b[0m\u001b[1;32m    625\u001b[0m       \u001b[0mnest_util\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mModality\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCORE\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0mstructure\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    626\u001b[0m   )\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/nest_util.py\u001b[0m in \u001b[0;36mmap_structure\u001b[0;34m(modality, func, *structure, **kwargs)\u001b[0m\n\u001b[1;32m   1052\u001b[0m   \"\"\"\n\u001b[1;32m   1053\u001b[0m   \u001b[0;32mif\u001b[0m \u001b[0mmodality\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mModality\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCORE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1054\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_tf_core_map_structure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0mstructure\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1055\u001b[0m   \u001b[0;32melif\u001b[0m \u001b[0mmodality\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mModality\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDATA\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1056\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0m_tf_data_map_structure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0mstructure\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/nest_util.py\u001b[0m in \u001b[0;36m_tf_core_map_structure\u001b[0;34m(func, *structure, **kwargs)\u001b[0m\n\u001b[1;32m   1092\u001b[0m   return _tf_core_pack_sequence_as(\n\u001b[1;32m   1093\u001b[0m       \u001b[0mstructure\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1094\u001b[0;31m       \u001b[0;34m[\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mx\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mentries\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1095\u001b[0m       \u001b[0mexpand_composites\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mexpand_composites\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1096\u001b[0m   )\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/util/nest_util.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m   1092\u001b[0m   return _tf_core_pack_sequence_as(\n\u001b[1;32m   1093\u001b[0m       \u001b[0mstructure\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1094\u001b[0;31m       \u001b[0;34m[\u001b[0m\u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mx\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mentries\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1095\u001b[0m       \u001b[0mexpand_composites\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mexpand_composites\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1096\u001b[0m   )\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/utils/tf_utils.py\u001b[0m in \u001b[0;36m_to_single_numpy_or_python_type\u001b[0;34m(t)\u001b[0m\n\u001b[1;32m    685\u001b[0m         \u001b[0;31m# Don't turn ragged or sparse tensors to NumPy.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    686\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 687\u001b[0;31m             \u001b[0mt\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnumpy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    688\u001b[0m         \u001b[0;31m# Strings, ragged and sparse tensors don't have .item(). Return them\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    689\u001b[0m         \u001b[0;31m# as-is.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36mnumpy\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1139\u001b[0m     \"\"\"\n\u001b[1;32m   1140\u001b[0m     \u001b[0;31m# TODO(slebedev): Consider avoiding a copy for non-CPU or remote tensors.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1141\u001b[0;31m     \u001b[0mmaybe_arr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_numpy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1142\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mmaybe_arr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmaybe_arr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mmaybe_arr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1143\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36m_numpy\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1105\u001b[0m   \u001b[0;32mdef\u001b[0m \u001b[0m_numpy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1106\u001b[0m     \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1107\u001b[0;31m       \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_numpy_internal\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1108\u001b[0m     \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1109\u001b[0m       \u001b[0;32mraise\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_status_to_exception\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m  \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "]}]},{"cell_type":"code","source":["#Set compile=False as we are not loading it for training, only for prediction.\n","model_fname = '/content/drive/MyDrive/Colab Notebooks/2dunet_best.hdf5'\n","model = load_model(model_fname, compile=False)\n","BACKBONE = '2D-UNet'\n","pred_name = 'msk_001'\n","\n","n_classes = 5\n","\n","print(('Fined-Tuned Model: {}').format((model_fname.split('/'))[-1]))\n","print('Prediction Scan Stack: ', pred_name)\n","print('Number of Segmentation Classes: ', n_classes)\n","print('\\n')\n","\n","img = nib.load((\"/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTr/{}_0000.nii.gz\").format(pred_name))\n","# img = nib.load((\"/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTs/{}_0000.nii.gz\").format(pred_name))\n","img_data = img.get_fdata()\n","X_test = np.repeat(img_data, 3, axis=3)\n","\n","msk = nib.load((\"/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/labelsTr/{}.nii.gz\").format(pred_name))\n","# msk = nib.load((\"/content/drive/MyDrive/Colab Notebooks/nnUNet_raw/Dataset001_Tibia/imagesTs/{}.nii.gz\").format(pred_name))\n","y_test = msk.get_fdata()\n","\n","print(\"Test Images Shape: \", X_test.shape)\n","print(\"Test Masks Shape: \", y_test.shape)\n","print(\"Test Labels: \", np.unique(y_test))\n","print('\\n')\n","\n","\n","# Model\n","# preprocess input\n","# preprocess_input = sm.get_preprocessing(BACKBONE)\n","# X_test_processed = preprocess_input(X_test)\n","# test_masks_cat = to_categorical(y_test, num_classes=n_classes)\n","# y_test_cat = test_masks_cat.reshape((y_test.shape[0], y_test.shape[1], y_test.shape[2], n_classes))\n","\n","\n","# Prediction\n","y_pred=model.predict(X_test)\n","y_pred_argmax=np.argmax(y_pred, axis=3)\n","y_pred_argmax = np.expand_dims(y_pred_argmax, axis = -1)\n","print('Pred Mask Shape: ', y_pred_argmax.shape)\n","print(\"Pred Mask Labels: \", np.unique(y_pred_argmax))\n","print('\\n')\n","\n","combined_mask = y_pred_argmax.astype(np.int32)\n","# combined_img = nib.Nifti1Image(combined_mask, msk.affine)\n","combined_img = nib.Nifti1Image(combined_mask, affine=np.eye(4), dtype=np.int32)\n","nib.save(combined_img, (\"/content/drive/MyDrive/Colab Notebooks/nnUNet_results/Dataset001_Tibia/predTs/Transfer Learning/{}_pred.nii.gz\").format(pred_name), dtype = np.uint8)\n","print('Exported Prediction Segmentation: ', (\"/content/drive/MyDrive/Colab Notebooks/nnUNet_results/Dataset001_Tibia/predTs/Transfer Learning/{}_pred.nii.gz\").format(pred_name))\n","print('\\n')\n","\n","# from keras.metrics import MeanIoU\n","# Calculate Mean IoU\n","# IOU_keras = MeanIoU(num_classes=n_classes)\n","# IOU_keras.update_state(y_test[:,:,:,0], y_pred_argmax)\n","# values = np.array(IOU_keras.get_weights()).reshape(n_classes, n_classes)\n","# class1_IoU = values[0,0]/(values[0,0] + values[0,1] + values[0,2] + values[0,3] + values[1,0]+ values[2,0]+ values[3,0])\n","# class2_IoU = values[1,1]/(values[1,1] + values[1,0] + values[1,2] + values[1,3] + values[0,1]+ values[2,1]+ values[3,1])\n","# class3_IoU = values[2,2]/(values[2,2] + values[2,0] + values[2,1] + values[2,3] + values[0,2]+ values[1,2]+ values[3,2])\n","# class4_IoU = values[3,3]/(values[3,3] + values[3,0] + values[3,1] + values[3,2] + values[0,3]+ values[1,3]+ values[2,3])\n","# class5_IoU = values[4,4]/(values[4,4] + values[4,0] + values[4,1] + values[4,2] + values[0,4]+ values[1,4]+ values[2,3])\n","\n","def dice_coefficient(true_array, pred_array):\n","    true_array = np.asarray(true_array).astype(bool)\n","    pred_array = np.asarray(pred_array).astype(bool)\n","\n","    intersection = np.logical_and(true_array, pred_array)\n","    dice = 2.0 * intersection.sum() / (true_array.sum() + pred_array.sum())\n","    return round(dice, 2)\n","\n","def volume_error(y_true, y_pred):\n","    # mm3\n","    Voxel_Volume = 2.63671875\n","\n","    N_true = np.count_nonzero(y_true)\n","    N_pred = np.count_nonzero(y_pred)\n","\n","    volume_error = np.abs(N_true - N_pred) * Voxel_Volume\n","\n","    return round(volume_error * 0.001, 2)\n","\n","\n","tibia_seg_data_pred = np.where(y_pred_argmax != 1, 0, 1)\n","femur_seg_data_pred = np.where(y_pred_argmax != 2, 0, 1)\n","fibula_seg_data_pred = np.where(y_pred_argmax != 3, 0, 1)\n","pelvis_seg_data_pred = np.where(y_pred_argmax != 4, 0, 1)\n","\n","tibia_seg_data_gt = np.where(y_test != 1, 0, 1)\n","femur_seg_data_gt = np.where(y_test != 2, 0, 1)\n","fibula_seg_data_gt = np.where(y_test != 3, 0, 1)\n","pelvis_seg_data_gt = np.where(y_test != 4, 0, 1)\n","\n","dice_score_tibia = dice_coefficient(tibia_seg_data_gt, tibia_seg_data_pred)\n","dice_score_femur = dice_coefficient(femur_seg_data_gt, femur_seg_data_pred)\n","dice_score_fibula = dice_coefficient(fibula_seg_data_gt, fibula_seg_data_pred)\n","dice_score_pelvis = dice_coefficient(pelvis_seg_data_gt, pelvis_seg_data_pred)\n","\n","# print(\"Mean IoU: \", IOU_keras.result().numpy())\n","# print(\"IoU Score - Background: \", class1_IoU)\n","# print(\"IoU Score - Tibia: \", class2_IoU)\n","# print(\"IoU Score - Femur: \", class3_IoU)\n","# print(\"IoU Score - Fibula: \", class4_IoU)\n","# print('\\n')\n","\n","print('Dice Score - Tibia:', dice_score_tibia)\n","print('Dice Score - Femur:', dice_score_femur)\n","print('Dice Score - Fibula:', dice_score_fibula)\n","print('Dice Score - Pelvis:', dice_score_pelvis)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":679},"id":"Q_FoIY63A1mA","executionInfo":{"status":"error","timestamp":1695641084509,"user_tz":-780,"elapsed":47809,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"}},"outputId":"6af547c2-a884-4ce5-9e22-3fb078eaef29"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Fined-Tuned Model: 2dunet_best.hdf5\n","Prediction Scan Stack:  msk_001\n","Number of Segmentation Classes:  5\n","\n","\n","Test Images Shape:  (440, 256, 256, 1)\n","Test Masks Shape:  (517, 256, 256, 1)\n","Test Labels:  [0. 1. 2. 3. 4.]\n","\n","\n","14/14 [==============================] - 37s 2s/step\n","Pred Mask Shape:  (440, 256, 256, 1)\n","Pred Mask Labels:  [0]\n","\n","\n","Exported Prediction Segmentation:  /content/drive/MyDrive/Colab Notebooks/nnUNet_results/Dataset001_Tibia/predTs/Transfer Learning/msk_001_pred.nii.gz\n","\n","\n"]},{"output_type":"error","ename":"ValueError","evalue":"ignored","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)","\u001b[0;32m<ipython-input-8-646420893130>\u001b[0m in \u001b[0;36m<cell line: 82>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     80\u001b[0m \u001b[0mpelvis_seg_data_gt\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwhere\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_test\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0;36m4\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     81\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 82\u001b[0;31m \u001b[0mdice_score_tibia\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdice_coefficient\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtibia_seg_data_gt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtibia_seg_data_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     83\u001b[0m \u001b[0mdice_score_femur\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdice_coefficient\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfemur_seg_data_gt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfemur_seg_data_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     84\u001b[0m \u001b[0mdice_score_fibula\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdice_coefficient\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfibula_seg_data_gt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfibula_seg_data_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m<ipython-input-8-646420893130>\u001b[0m in \u001b[0;36mdice_coefficient\u001b[0;34m(true_array, pred_array)\u001b[0m\n\u001b[1;32m     65\u001b[0m     \u001b[0mpred_array\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpred_array\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbool\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     66\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 67\u001b[0;31m     \u001b[0mintersection\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlogical_and\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrue_array\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpred_array\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     68\u001b[0m     \u001b[0mdice\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m2.0\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mintersection\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m/\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mtrue_array\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mpred_array\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     69\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mround\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdice\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mValueError\u001b[0m: operands could not be broadcast together with shapes (517,256,256,1) (440,256,256,1) "]}]},{"cell_type":"markdown","metadata":{"id":"Rq6D4-hhMDs_"},"source":["Prediction Mask"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"executionInfo":{"elapsed":20852,"status":"ok","timestamp":1691885439773,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"},"user_tz":-720},"id":"Xz1vRP640A7D","outputId":"0c2b8311-16b7-40be-abf5-74e8c46b4acd"},"outputs":[{"output_type":"stream","name":"stdout","text":["imgs_test size (Scans):  (214, 400, 400, 1)\n","imgs_test_masks size (Masks):  (214, 400, 400, 1)\n","------------------------------\n","Prediction Made Using Weights From Model: model(2D, nnUNet).h5\n","------------------------------\n","1/1 [==============================] - 0s 455ms/step\n","Testing Image Input Shape:  (400, 400, 1)\n","\n","\n","Dice Similarity Coefficient (DSC) Metric Value for Specified Slice:  [0.00673236]\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stderr","text":["<ipython-input-5-34d36e556e56>:98: MatplotlibDeprecationWarning: The get_cmap function was deprecated in Matplotlib 3.7 and will be removed two minor releases later. Use ``matplotlib.colormaps[name]`` or ``matplotlib.colormaps.get_cmap(obj)`` instead.\n","  cmap_superimposed = plt.cm.get_cmap(cmap_binary)\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["<Figure size 640x480 with 1 Axes>"],"image/png":"iVBORw0KGgoAAAANSUhEUgAAAosAAAGzCAYAAABHK11KAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAC690lEQVR4nOy9d3hU1fb//55eM5n0RoBQQ0d6pEsJRRQBEUEpioqCBe4HlftV7GK59yo2sIJKUbAXkN6kKaAgvTchIaQn0zIz5/cHv73dc3JOCgRIYL2eZ55kTt1nnz1nv89ae62tkSRJAkEQBEEQBEEooL3aBSAIgiAIgiCqLyQWCYIgCIIgCFVILBIEQRAEQRCqkFgkCIIgCIIgVCGxSBAEQRAEQahCYpEgCIIgCIJQhcQiQRAEQRAEoQqJRYIgCIIgCEIVEosEQRAEQRCEKtedWOzRowd69OhxtYtx1Zk7dy40Gg2OHz9+tYtCEJcFjUaDZ599ln+v6jZ//PhxaDQazJ07t0qOV9N49tlnodFocP78+Ys+xmuvvYbU1FQEg8EqLNm1y9ixY1G3bt3Ldnx5/3i9t/GaDPt9MkpKSpCcnIz33nvvoo5XabH4119/YdiwYahTpw7MZjOSkpLQp08fvP322xdVAKJ6wxoc+xgMBtStWxePPPII8vLyrmrZ6tatG1I2tU9VPehefvllfPfddxXePisrC48++ihSU1NhsVgQGxuLDh064IknnkBRUVGVlOlyEAwG8Z///AcNGzaExWJB/fr18eCDD1aqzPJ2Y7Va0bRpUzz11FMoKCi4jKWvehYsWIA333zzahcjhLFjx0Kj0cDhcMDtdpdaf+jQIV73//nPf65CCcunoKAAr776Kp544glotaW7ory8PJjNZmg0Guzbt++SznXmzBk8++yz+PPPPy/pOFeCmlTWi4E0xD9cyXttMBgwZcoUvPTSS/B4PJXeX1+ZjTdt2oSePXuidu3auO+++xAfH49Tp05hy5YtmDlzJh5++OFKF+BKs3z58qtdhBrJrFmzYLfbUVxcjFWrVuHtt9/Gjh078Ouvv161Mr355pshAmbJkiVYuHAh3njjDURHR/PlN954Y5Wc7+WXX8awYcMwePDgcrfNyclBu3btUFBQgHvuuQepqanIzs7Grl27MGvWLDz44IOw2+1VUq6qZubMmZg6dSoGDx6MqVOn4sSJE1i4cCGeeOKJSpeZtZuioiIsX74cL730ElavXo2NGzeGvPVeCe6++26MGDECJpOpUvstWLAAu3fvxmOPPRayvE6dOnC73TAYDFVYyoqj1+vhcrnw448/Yvjw4SHr5s+fD7PZfFGdwpXik08+gd/vx5133qm4fvHixdBoNIiPj8f8+fPx4osvXvS5zpw5g+eeew5169ZF69atL/o4V4Kyyvrhhx/WaCvstaAhqpIr3S7HjRuHJ598EgsWLMA999xTqX0rJRZfeuklhIeH4/fff4fT6QxZd+7cuUqd+ErjcrlgtVphNBqvdlFqJMOGDeMC7IEHHsCIESPw5Zdf4rfffkOHDh2uSpnkoi0jIwMLFy7E4MGDL6urpiJ8/PHHOHnyJDZu3FhKrBYUFFTrdvjFF1+gWbNm+Oabb7ige+GFFy6qkxLbzYQJEzB06FB888032LJlC9LS0hT3Yb/Vqkan00Gn01XZ8TQaDcxmc5Udr7KYTCZ07twZCxcuLCUWFyxYgIEDB+Lrr7++SqUrnzlz5uCWW25RrcN58+ZhwIABqFOnDhYsWHBJYvFa4Wq9mFQVNVlDXAs4nU707dsXc+fOrbRYrJQb+siRI2jWrFmpmwwAsbGx/P+yxjnIxxExd9X+/fsxfPhwOBwOREVF4dFHH1V8K543bx7atm0Li8WCyMhIjBgxAqdOnQrZpkePHmjevDm2b9+Obt26wWq14t///jdfJ47JWLt2LTQaDRYtWoTnnnsOSUlJCAsLw7Bhw5Cfnw+v14vHHnsMsbGxsNvtGDduHLxeb6lrmjRpEubPn4/GjRvDbDajbdu2WL9+fany//HHH+jfvz8cDgfsdjt69eqFLVu2hGxTUlKC5557Dg0bNoTZbEZUVBS6dOmCFStWhGy3f/9+DBs2DJGRkTCbzWjXrh1++OGHUufcs2cPbrrpJlgsFtSqVQsvvvjiJb+ddu3aFcCFNsHIycnB//3f/6FFixaw2+1wOBzo378/du7cybeRJAnR0dGYMmUKXxYMBuF0OqHT6UJc26+++ir0ev0lu2wr0mYOHTqEoUOHIj4+HmazGbVq1cKIESOQn58P4MI9Li4uxqeffsrde2PHjlU955EjR6DT6dCpU6dS6xwOR6kOcuvWrRgwYAAiIiJgs9nQsmVLzJw5k6/ftWsXxo4di3r16sFsNiM+Ph733HMPsrOzQ47Dfk+HDx/G2LFj4XQ6ER4ejnHjxsHlclWovrRaLYLBYIjlT6vVQq+v1LulIjfddBMA4NixYwDK/q16vV4888wzaNCgAUwmE5KTk/H444+X+v15vV5MnjwZMTExCAsLwy233ILTp0+XOrfamMWlS5eie/fuCAsLg8PhQPv27bFgwQJevp9//hknTpzg9529iKg951avXo2uXbvCZrPB6XTi1ltvLeVGrYr7BAAjR47E0qVLQ343v//+Ow4dOoSRI0eW2r4iv1HG22+/jWbNmsFqtSIiIgLt2rXj9aLGiRMn0KBBAzRv3hyZmZmq2x07dgy7du1C7969FdefPHkSGzZswIgRIzBixAgcO3YMmzZtKrVd3bp1FX+H4nN+7dq1aN++PYALlhWl4SmLFy/mz4jo6Gjcdddd+Pvvv0OOOXbsWNjtdpw8eRI333wz7HY7kpKS8O677wK44F696aabYLPZuMAVqUjdl1dWpTGLwWAQM2fORIsWLWA2mxETE4N+/fph27ZtfJs5c+bgpptuQmxsLEwmE5o2bYpZs2Yp1n1ZzJkzBxqNBn/88UepdS+//DJ0Ol2pehOpqIZgVOTZDQDvvvsu6tWrB4vFgg4dOmDDhg2Xpa+vaJnYc23v3r3o2bMnrFYrkpKS8Nprr4WUp7x2uXXrVvTr1w/h4eGwWq3o3r07Nm7cWKpMv/76K9q3bw+z2Yz69evj/fffL7UNo0+fPvj111+Rk5Ojuo0SlXr616lTB5s3b8bu3bvRvHnzSp2oPIYPH466detixowZ2LJlC9566y3k5ubis88+49u89NJLePrppzF8+HCMHz8eWVlZePvtt9GtWzf88ccfIQ0wOzsb/fv3x4gRI3DXXXchLi6uzPPPmDEDFosFTz75JA4fPoy3334bBoMBWq0Wubm5ePbZZ7FlyxbMnTsXKSkpmD59esj+69atw5dffolHHnkEJpMJ7733Hvr164fffvuN19WePXvQtWtXOBwOPP744zAYDHj//ffRo0cPrFu3Dh07dgRwoSOZMWMGxo8fjw4dOqCgoADbtm3Djh070KdPH36szp07IykpCU8++SRsNhsWLVqEwYMH4+uvv8Ztt90G4IK1rWfPnvD7/Xy7Dz74ABaL5ZLuF+twIyIi+LKjR4/iu+++w+23346UlBRkZmbi/fffR/fu3bF3714kJiZCo9Ggc+fOIUJ6165dyM/Ph1arxcaNGzFw4EAAwIYNG3DDDTdckru2Im3G5/MhPT0dXq8XDz/8MOLj4/H333/jp59+Ql5eHsLDw/H555/z+3H//fcDAOrXr6963jp16iAQCODzzz/HmDFjyizjihUrcPPNNyMhIQGPPvoo4uPjsW/fPvz000949NFH+TZHjx7FuHHjEB8fjz179uCDDz7Anj17sGXLllIu3eHDhyMlJQUzZszAjh078NFHHyE2NhavvvpquXU2btw4PPDAA3j//ffxwAMPlLt9ZWAvF1FRUXyZ0m81GAzilltuwa+//or7778fTZo0wV9//YU33ngDBw8eDBk7On78eMybNw8jR47EjTfeiNWrV/M2VB7sDbtZs2aYNm0anE4n/vjjD/zyyy8YOXIk/t//+3/Iz8/H6dOn8cYbbwBAme1x5cqV6N+/P+rVq4dnn30Wbrcbb7/9Njp37owdO3aU6ugv5T4BwJAhQzBhwgR888033FKwYMECpKamok2bNqW2r8hvFLjg7nzkkUcwbNgw/uK+a9cubN26VVGEAhfu7U033YTIyEisWLEiZCiIHCb8lMoIAAsXLoTNZsPNN9/Mx83Onz//ooaUNGnSBM8//zymT5+O+++/n7/osmPNnTsX48aNQ/v27TFjxgxkZmZi5syZ2LhxY6l+JRAIoH///ujWrRtee+01zJ8/H5MmTYLNZsP/+3//D6NGjcKQIUMwe/ZsjB49GmlpaUhJSQFQsbovr6xK3HvvvZg7dy769++P8ePHw+/3Y8OGDdiyZQvatWsH4MJwkGbNmuGWW26BXq/Hjz/+iIceegjBYBATJ06scF0OGzYMEydOxPz583HDDTeErJs/fz569OiBpKQk1f0royEq2t/PmjULkyZNQteuXTF58mQcP34cgwcPRkREBGrVqlXquJfS11dGg+Tm5qJfv34YMmQIhg8fjq+++gpPPPEEWrRogf79+5d7r1evXo3+/fujbdu2eOaZZ6DVarno37BhA/fo/fXXX+jbty9iYmLw7LPPwu/345lnnlHVPG3btoUkSdi0aRNuvvnmMu9BCFIlWL58uaTT6SSdTielpaVJjz/+uLRs2TLJ5/OFbHfs2DEJgDRnzpxSxwAgPfPMM/z7M888IwGQbrnllpDtHnroIQmAtHPnTkmSJOn48eOSTqeTXnrppZDt/vrrL0mv14cs7969uwRAmj17dqnzd+/eXerevTv/vmbNGgmA1Lx585DruPPOOyWNRiP1798/ZP+0tDSpTp06pa4JgLRt2za+7MSJE5LZbJZuu+02vmzw4MGS0WiUjhw5wpedOXNGCgsLk7p168aXtWrVSho4cGCpsov06tVLatGiheTxePiyYDAo3XjjjVLDhg35sscee0wCIG3dupUvO3funBQeHi4BkI4dO1bmedj9OXDggJSVlSUdP35c+uSTTySLxSLFxMRIxcXFfFuPxyMFAoGQ/Y8dOyaZTCbp+eef58tef/11SafTSQUFBZIkSdJbb70l1alTR+rQoYP0xBNPSJIkSYFAQHI6ndLkyZPLLJ/I66+/HnJNFW0zf/zxhwRAWrx4cZnHt9ls0pgxYypUloyMDCkmJkYCIKWmpkoTJkyQFixYIOXl5YVs5/f7pZSUFKlOnTpSbm5uyLpgMMj/d7lcpc6xcOFCCYC0fv16vozdr3vuuSdk29tuu02KioqqUNmffPJJyWg0SjqdTvrmm28qtI8cebs5duyY9P7770smk0mKi4vj7Ubtt/r5559LWq1W2rBhQ8jy2bNnSwCkjRs3SpIkSX/++acEQHrooYdCths5cmSpZ82cOXNC2kdeXp4UFhYmdezYUXK73SH7i3U/cODAUr95SVJ+zrVu3VqKjY2VsrOz+bKdO3dKWq1WGj16dKn6udj7NGbMGMlms0mSJEnDhg2TevXqJUnShd9NfHy89Nxzz/Hyvf7663y/iv5Gb731VqlZs2ZlloFdQ1ZWlrRv3z4pMTFRat++vZSTk1Nu+Z966ikJgFRYWKi4vkWLFtKoUaP493//+99SdHS0VFJSErJdnTp1FH+T8uf877//rtgn+Xw+KTY2VmrevHlIG/jpp58kANL06dP5sjFjxkgApJdffpkvy83NlSwWi6TRaKQvvviCL9+/f3+p9lfRulcrKyuD2BZXr14tAZAeeeSRUtuW9/xIT0+X6tWrF7JMXm9KbfzOO++UEhMTQ65lx44dqmUWqaiGqOiz2+v1SlFRUVL79u1D2sbcuXMlAFXa11+MBvnss8/4Mq/XK8XHx0tDhw7ly9TudTAYlBo2bCilp6eXuo8pKSlSnz59+LLBgwdLZrNZOnHiBF+2d+9eSafTSUoS78yZMxIA6dVXXy21riwq5Ybu06cPNm/ejFtuuQU7d+7Ea6+9hvT0dCQlJSm6PyuD/O2GDXRdsmQJAOCbb75BMBjE8OHDcf78ef6Jj49Hw4YNsWbNmpD9TSYTxo0bV+Hzjx49OmQ8SMeOHSFJUim/fseOHXHq1Cn4/f6Q5WlpaWjbti3/Xrt2bdx6661YtmwZAoEAAoEAli9fjsGDB6NevXp8u4SEBIwcORK//vorjxJ1Op3Ys2cPDh06pFjWnJwcrF69GsOHD0dhYSGvi+zsbKSnp+PQoUPcFbBkyRJ06tQpZFxhTEwMRo0aVeG6AYDGjRsjJiYGdevWxT333IMGDRpg6dKlIWPLTCYTj2oMBALIzs6G3W5H48aNsWPHDr5d165dEQgEuHVhw4YN6Nq1K7p27YoNGzYAAHbv3o28vDz+tnUxVLTNhIeHAwCWLVtWKRdgWcTFxWHnzp2YMGECcnNzMXv2bIwcORKxsbF44YUXIEkSgAvDEo4dO4bHHnuslGtGtBaKlmCPx4Pz589zF7dYt4wJEyaEfO/atSuys7PLjUR+66238L///Q8bN27EnXfeiREjRpQKCjOZTHj66afLrwT8025SUlLwwAMPoEGDBvj5559LtRv5b3Xx4sVo0qQJUlNTQ+4dc2Oze8eeD4888kjI/vJgFCVWrFiBwsJCPPnkk6WGBVxM8M3Zs2fx559/YuzYsYiMjOTLW7ZsiT59+vCyilzsfRIZOXIk1q5di4yMDKxevRoZGRmq1r+K/kadTidOnz6N33//vdzz7969G927d0fdunWxcuXKEG+DGtnZ2dDr9YpW2l27duGvv/4KCXy58847cf78eSxbtqzcY1eGbdu24dy5c3jooYdC2sDAgQORmpqKn3/+udQ+48eP5/87nU40btwYNpstZNxo48aN4XQ6cfToUb6sonVfGb7++mtoNBo888wzpdapPT/y8/Nx/vx5dO/eHUePHuVDbSrK6NGjcebMmZA+d/78+bBYLBg6dGiZ+1ZUQ1T02b1t2zZkZ2fjvvvuCxkmM2rUKNV2eLF9fWU1iN1ux1133cW/G41GdOjQIaRNqPHnn3/yoSTZ2dn8XMXFxejVqxfWr1+PYDCIQCCAZcuWYfDgwahduzbfv0mTJkhPT1c8NquXyqa8qnTqnPbt2+Obb75Bbm4ufvvtN0ybNg2FhYUYNmwY9u7dW9nDcRo2bBjyvX79+tBqtdzdeejQIUiShIYNGyImJibks2/fvlKDY5OSkioVRCBWNPCPgEhOTi61PBgMlvqBycsPAI0aNYLL5UJWVhaysrLgcrnQuHHjUts1adIEwWCQj3t4/vnnkZeXh0aNGqFFixaYOnUqdu3axbc/fPgwJEnC008/Xaou2EOD1ceJEycUy6ZUjrL4+uuvsWLFCixYsACdOnXCuXPnSrmyg8Eg3njjDTRs2BAmkwnR0dGIiYnhbmZGmzZtYLVauTBkYrFbt27Ytm0bPB4PX9elS5dKlVOkom0mJSUFU6ZMwUcffYTo6Gikp6fj3XffrfRDVE5CQgJmzZqFs2fP4sCBA3jrrbcQExOD6dOn4+OPPwbwj1u2PJdMTk4OHn30UcTFxcFisXABBkCxnPL2zB4Qubm5qudwu9145plnMH78eLRr1467PG677TYe9X7o0CH4fD4+ZKI8WLtZu3YtDh8+jN27d4e8VAHKv9VDhw5hz549pe5bo0aNAIS2b61WW2pIQEXad0XrvqKcOHFC9dxNmjThD3uRi7lPcgYMGICwsDB8+eWXmD9/Ptq3b48GDRooblvR3yiLfO/QoQMaNmyIiRMnKo6VAoBBgwYhLCwMy5Ytg8PhqHC51Zg3bx5sNhvq1auHw4cP4/DhwzCbzahbty7mz59/yccXKeuepaam8vUMNiZQJDw8HLVq1Sr1ghEeHh5yHyta95XhyJEjSExMDHk5UWLjxo3o3bs3H0cbExPDxwZX9tx9+vRBQkICvxfBYBALFy7ErbfeirCwsHL3r4iGqOizm90feXvX6/WqQY4X29dXVoMotYmIiIgK/baZoWjMmDGlzvXRRx/B6/UiPz8fWVlZcLvdlerjmaGisi/EFz1i3Wg0on379mjfvj0aNWqEcePGYfHixXjmmWdUCxEIBCp8fPkx2ID7pUuXKkY0yt9QKzsmTy1KUm05q/DLQbdu3XDkyBF8//33WL58OT766CO88cYbmD17NsaPH8+DU/7v//5P9e1BrbO4lDKxMUiDBg1CixYtMGrUKGzfvp2/Lb/88st4+umncc899+CFF15AZGQktFotHnvssZCAGoPBgI4dO2L9+vU4fPgwMjIy0LVrV8TFxaGkpARbt27Fhg0bkJqaWurBXBkq02b++9//YuzYsbzOH3nkET5+VmncS2XQaDRo1KgRGjVqhIEDB6Jhw4aYP39+iIWiPIYPH45NmzZh6tSpaN26Nex2O4LBIPr166cYrHQx7Xbfvn3Iy8vjFku9Xo+vvvoKN910EwYOHIg1a9Zg4cKFiI2N5WNny0NsN2oo/VaDwSBatGiB//3vf4r7yB/sNZWqeL6YTCYMGTIEn376KY4ePRoSQCinor/RJk2a4MCBA/jpp5/wyy+/4Ouvv8Z7772H6dOn47nnngs55tChQ/Hpp59i/vz5FR7jGhUVBb/fj8LCwhCBIUkSFi5ciOLiYjRt2rTUfufOnUNRURH/7ZbV11Rl5DvjUvqJitZ9VXPkyBH06tULqamp+N///ofk5GQYjUYsWbIEb7zxRqXPrdPpMHLkSHz44Yd47733sHHjRpw5cybEilYRytIQle3vK1v+yixn97CyZbqU3za7J6+//rpqSh273a4YgFMeTKyW91yWc+nhjQAfRHv27FkA/7wdy5M2y9/SRA4dOsQtJcAF61kwGORvB/Xr14ckSUhJSeHWheqEksv44MGDsFqtXPBYrVYcOHCg1Hb79++HVqsN6QAjIyMxbtw4jBs3DkVFRejWrRueffZZjB8/nruxDQaDajQho06dOoplUypHRbHb7XjmmWcwbtw4LFq0CCNGjAAAfPXVV+jZsye3mjHy8vJKNcyuXbvi1VdfxcqVKxEdHY3U1FRoNBo0a9YMGzZswIYNGyo3+FaByraZFi1aoEWLFnjqqaewadMmdO7cGbNnz+YpO6oiL2C9evUQERHBfyvMIrZ7927Ve5mbm4tVq1bhueeeCxlsrTZM4WJh1ydG9tlsNixZsgRdunRBeno6PB4PXnzxxUrnKqws9evXx86dO9GrV68y671OnToIBoM4cuRIyJt0Rdq3WPdlvVxV9L7XqVNH9dz79+9HdHQ0bDZbhY5VWUaOHIlPPvkEWq2W/x6VqMxv1Gaz4Y477sAdd9wBn8+HIUOG4KWXXsK0adNCXLavv/469Ho9HnroIYSFham6wEVSU1MBXIiKbtmyJV++bt06nD59Gs8//zyaNGkSsk9ubi7uv/9+fPfdd1yYREREKE4OcOLEiZDhPmr3ULxnbIgD48CBA3x9VVDRuq/Mc6Z+/fpYtmwZcnJyVK2LP/74I7xeL3744YcQq5rcbVoZRo8ejf/+97/48ccfsXTpUsTExKgaLiqCXENU9NnN7s/hw4fRs2dPvtzv9+P48eMhbetSuRwaRO1es2eTw+Eos4+PiYmBxWKpVB/PMlHIf1/lUSk39Jo1axRVMRuLwx7WDocD0dHRpVLHlDXNDEs/wGDZ3Pv37w/gQtSfTqfDc889V6oMkiSVSiFypdm8eXPIuJNTp07h+++/R9++fXl+t759++L7778PSd2RmZmJBQsWoEuXLtyFI78Wu92OBg0a8LeI2NhY9OjRA++//z7/cYlkZWXx/wcMGIAtW7bgt99+C1l/qe6cUaNGoVatWiFRmzqdrtS9Wbx4sWIqha5du8Lr9eLNN99Ely5d+I+ma9eu+Pzzz3HmzJlLGq8IVLzNFBQUlBqD2qJFC2i12pA3N5vNVuFZa7Zu3VrK5QgAv/32G7Kzs/lvpU2bNkhJScGbb75Z6tiszOwNVX4NVT2rSIsWLRAXF4d33nknxKUSFRWFOXPm4Pz583C73Rg0aFCVnleJ4cOH4++//8aHH35Yap3b7eZ1y54Pb731Vsg2Fambvn37IiwsDDNmzCiVpkusa5vNViFXXUJCAlq3bo1PP/005F7u3r0by5cvx4ABA8o9xsXSs2dPvPDCC3jnnXcQHx+vul1Ff6PyZ5DRaETTpk0hSRJKSkpC1mk0GnzwwQcYNmwYxowZU6Hx6yzHppjeBfjHBT116lQMGzYs5HPfffdxqzyjfv362LJlC3w+H1/2008/lUplwkS6/DfWrl07xMbGYvbs2SG/9aVLl2Lfvn0VjqqvCBWte7WyKjF06FBIklTK2guU/fzIz8/HnDlzKlV+kZYtW6Jly5b46KOP8PXXX2PEiBEVSq1VUQ1R0Wd3u3btEBUVhQ8//DDkGT5//vxKDeWoCJdDg6jd67Zt26J+/fr4z3/+o5g6jvXxOp0O6enp+O6773Dy5Em+ft++farje7dv3w6NRqOa51aNSlkWH374YbhcLtx2221ITU2Fz+fDpk2b8OWXX6Ju3bohg9THjx+PV155hY9/Wr9+PQ4ePKh67GPHjuGWW25Bv379sHnzZp4Ko1WrVgAuPBRefPFFTJs2jYfGh4WF4dixY/j2229x//334//+7/8qdfFVSfPmzZGenh6SOgdAyI/4xRdfxIoVK9ClSxc89NBD0Ov1eP/99+H1ekPyLzVt2hQ9evRA27ZtERkZiW3btuGrr77CpEmT+DbvvvsuunTpghYtWuC+++5DvXr1kJmZic2bN+P06dM8d9fjjz+Ozz//HP369cOjjz7KU+fUqVMnZBxkZTEYDHj00UcxdepU/PLLL+jXrx9uvvlmPP/88xg3bhxuvPFG/PXXX5g/f37IGz4jLS0Ner0eBw4c4KlogAtuS5b/61LFYkXbzOrVqzFp0iTcfvvtaNSoEfx+Pz7//HPodLqQAdtt27bFypUr8b///Q+JiYlISUlRHbv3+eefY/78+bjtttvQtm1bGI1G7Nu3D5988gnMZjMfL6TVajFr1iwMGjQIrVu3xrhx45CQkID9+/djz549fBwYS9VRUlKCpKQkLF++nL8hVhV6vR7vvPMO7rjjDrRo0QIPPPAA6tSpw8vdokULnD59Grfeeis2btxYJePT1Lj77ruxaNEiTJgwAWvWrEHnzp0RCASwf/9+LFq0CMuWLUO7du3QunVr3HnnnXjvvfeQn5+PG2+8EatWrcLhw4fLPYfD4cAbb7yB8ePHo3379hg5ciQiIiKwc+dOuFwufPrppwAu3Pcvv/wSU6ZMQfv27WG321UF8+uvv47+/fsjLS0N9957L0+dEx4eXqZ7+FLRarV46qmnyt2uor/Rvn37Ij4+Hp07d0ZcXBz27duHd955BwMHDlQcl6bVajFv3jwMHjwYw4cPx5IlS0pZ6kTq1auH5s2bY+XKlTywwOv14uuvv0afPn1UE3XfcsstmDlzJs6dO4fY2FiMHz8eX331Ffr164fhw4fjyJEjmDdvXqkxrPXr14fT6cTs2bMRFhYGm82Gjh07IiUlBa+++irGjRuH7t2748477+Spc+rWrYvJkyeXW6cVpaJ1X1ZZ5fTs2RN333033nrrLRw6dIgPS9mwYQN69uyJSZMmoW/fvjAajRg0aBAeeOABFBUV4cMPP0RsbKyisaGijB49mve5FXVBV1RDVPTZbTQa8eyzz+Lhhx/GTTfdhOHDh+P48eOYO3cu6tevX6WzRF0ODVLWvf7oo4/Qv39/NGvWDOPGjUNSUhL+/vtvrFmzBg6HAz/++COACxrjl19+QdeuXfHQQw/B7/fzHKlKffyKFSvQuXPnkPRlFaIyodNLly6V7rnnHik1NVWy2+2S0WiUGjRoID388MNSZmZmyLYul0u69957pfDwcCksLEwaPny4dO7cOdXUOXv37pWGDRsmhYWFSREREdKkSZNKpbOQJEn6+uuvpS5dukg2m02y2WxSamqqNHHiROnAgQN8m+7du6umfVBLnSNPm8LSbPz+++8hy8V0EQwA0sSJE6V58+ZJDRs2lEwmk3TDDTdIa9asKXX+HTt2SOnp6ZLdbpesVqvUs2dPadOmTSHbvPjii1KHDh0kp9MpWSwWKTU1VXrppZdKpRc4cuSINHr0aCk+Pl4yGAxSUlKSdPPNN0tfffVVyHa7du2SunfvLpnNZikpKUl64YUXpI8//rhSqXPE62Xk5+dL4eHhvD49Ho/0r3/9S0pISJAsFovUuXNnafPmzaXqnNG+fftSaX1Onz4tAZCSk5PLLJcS8tQ5jPLazNGjR6V77rlHql+/vmQ2m6XIyEipZ8+e0sqVK0OOs3//fqlbt26SxWKRAJSZRmfXrl3S1KlTpTZt2kiRkZGSXq+XEhISpNtvv13asWNHqe1//fVXqU+fPlJYWJhks9mkli1bSm+//XZIvdx2222S0+mUwsPDpdtvv52nQFD6PcnvlzxtTFmsX79eSk9PlxwOh2QymaTmzZtLM2bMkFwul7R06VJJq9VKffv2LZXGRKSsdiNS1m/V5/NJr776qtSsWTPJZDJJERERUtu2baXnnntOys/P59u53W7pkUcekaKioiSbzSYNGjRIOnXqVLmpcxg//PCDdOONN0oWi0VyOBxShw4dpIULF/L1RUVF0siRIyWn0ykB4Ok01FKErVy5UurcuTM/3qBBg6S9e/dWqH4qep/E1DlqqKXOqchv9P3335e6desmRUVFSSaTSapfv740derUkHpXugaXyyV1795dstvt0pYtW8os3//+9z/JbrfztC5ff/21BED6+OOPVfdZu3atBECaOXMmX/bf//5XSkpKkkwmk9S5c2dp27Ztis+c77//XmratKmk1+tL3bcvv/xSuuGGGySTySRFRkZKo0aNkk6fPh2yv1qdq7XhOnXqhKRAq8zzUa2s8tQ5knQh/dbrr78upaamSkajUYqJiZH69+8vbd++nW/zww8/SC1btpTMZrNUt25d6dVXX5U++eSTUm2tIqlzGGfPnpV0Op3UqFGjUuvUqIyGkKSK9feS9E/6NZPJJHXo0EHauHGj1LZtW6lfv358m6ro6ytaJrU2oXT/ymqXf/zxhzRkyBD+O6xTp440fPhwadWqVSHHWLdundS2bVvJaDRK9erVk2bPns3LL5KXlycZjUbpo48+KlW28tBI0mWM1KgAzz77LJ577jlkZWVVesBldUGj0WDixIl45513rnZRCIIgagT5+fmoV68eXnvtNdx7771XuzhEJTl//jwSEhIwffr0CqfSulIEg0HExMRgyJAhikNZrlfefPNNvPbaazhy5Eilg4ArnTqHIAiCIC6V8PBwPP7443j99dcvazQwcXmYO3cuAoEA7r777qtaDo/HU2oM4WeffYacnJyQ6f6ud0pKSvC///0PTz311EXN4FYl0dAEQRAEUVmeeOIJPPHEE1e7GEQlWL16Nfbu3YuXXnoJgwcPVs1neKXYsmULJk+ejNtvvx1RUVHYsWMHPv74YzRv3hy33377VS1bdcJgMIQEwVQWEosEQRAEQVSI559/nqcWY1lLriZ169ZFcnIy3nrrLZ5CaPTo0XjllVcqNTEHUTZXfcwiceV599138frrryMjIwOtWrXC22+/HTIdIEEQBEEQBIPGLF5nsBQgzzzzDHbs2IFWrVohPT291FRFBEEQBEEQAFkWrzs6duyI9u3b88jtYDCI5ORkPPzww3jyySevcukIgiAIgqhu0JjF6wifz4ft27dj2rRpfJlWq0Xv3r2xefNmxX28Xm/IzAbBYBA5OTmIioqq0oSnBEEQxOVHkiQUFhYiMTERWi05F4mKQWLxOuL8+fMIBAKIi4sLWR4XF4f9+/cr7jNjxgzFqaQIgiCImsupU6dQq1atq10MooZAYpEok2nTpmHKlCn8e35+PmrXro3JkyfDZDJdxZIRBEEQlcXr9eKNN95QnLaRINQgsXgdER0dDZ1Oh8zMzJDlmZmZiI+PV9zHZDIpikKTyaQ6fytBEARRvaFhRERloAEL1xFGoxFt27bFqlWr+LJgMIhVq1YhLS3tKpaMIAiCIIjqClkWrzOmTJmCMWPGoF27dujQoQPefPNNFBcXY9y4cVe7aARBEARBVENILF5n3HHHHcjKysL06dORkZGB1q1b45dffikV9EIQBEEQBAGQWLwumTRpEiZNmnS1i0EQBEEQRA2AxiwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmLxGuLZZ5+FRqMJ+aSmpvL1Ho8HEydORFRUFOx2O4YOHYrMzMyrWGKCIAiCIKo7JBavMZo1a4azZ8/yz6+//srXTZ48GT/++CMWL16MdevW4cyZMxgyZMhVLC1BEARBENUd/dUuAFG16PV6xMfHl1qen5+Pjz/+GAsWLMBNN90EAJgzZw6aNGmCLVu2oFOnTle6qARBEARB1ADIsniNcejQISQmJqJevXoYNWoUTp48CQDYvn07SkpK0Lt3b75tamoqateujc2bN6sez+v1oqCgIORDEARBEMT1A4nFa4iOHTti7ty5+OWXXzBr1iwcO3YMXbt2RWFhITIyMmA0GuF0OkP2iYuLQ0ZGhuoxZ8yYgfDwcP5JTk6+zFdBEARBEER1gtzQ1xD9+/fn/7ds2RIdO3ZEnTp1sGjRIlgslos65rRp0zBlyhT+vaCggAQjQRAEQVxHkGXxGsbpdKJRo0Y4fPgw4uPj4fP5kJeXF7JNZmam4hhHhslkgsPhCPkQBEEQBHH9QGLxGqaoqAhHjhxBQkIC2rZtC4PBgFWrVvH1Bw4cwMmTJ5GWlnYVS0kQBEEQRHWG3NDXEP/3f/+HQYMGoU6dOjhz5gyeeeYZ6HQ63HnnnQgPD8e9996LKVOmIDIyEg6HAw8//DDS0tIoEpogCIIgCFVILF5DnD59GnfeeSeys7MRExODLl26YMuWLYiJiQEAvPHGG9BqtRg6dCi8Xi/S09Px3nvvXeVSEwRBEARRnSGxeA3xxRdflLnebDbj3XffxbvvvnuFSkQQBEEQRE2HxiwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEYg1h/fr1GDRoEBITE6HRaPDdd9+FrJckCdOnT0dCQgIsFgt69+6NQ4cOhWyTk5ODUaNGweFwwOl04t5770VRUdEVvAqCIAiCIGoaJBZrCMXFxWjVqhXeffddxfWvvfYa3nrrLcyePRtbt26FzWZDeno6PB4P32bUqFHYs2cPVqxYgZ9++gnr16/H/ffff6UugSAIgiCIGoj+aheAqBj9+/dH//79FddJkoQ333wTTz31FG699VYAwGeffYa4uDh89913GDFiBPbt24dffvkFv//+O9q1awcAePvttzFgwAD85z//QWJi4hW7FoIgCIIgag5kWbwGOHbsGDIyMtC7d2++LDw8HB07dsTmzZsBAJs3b4bT6eRCEQB69+4NrVaLrVu3qh7b6/WioKAg5EMQBEEQxPUDicVrgIyMDABAXFxcyPK4uDi+LiMjA7GxsSHr9Xo9IiMj+TZKzJgxA+Hh4fyTnJxcxaUnCIIgCKI6Q2KRKJNp06YhPz+ff06dOnW1i0QQBEEQxBWExOI1QHx8PAAgMzMzZHlmZiZfFx8fj3PnzoWs9/v9yMnJ4dsoYTKZ4HA4Qj4EQRAEQVw/kFi8BkhJSUF8fDxWrVrFlxUUFGDr1q1IS0sDAKSlpSEvLw/bt2/n26xevRrBYBAdO3a84mUmCIIgCKJmQNHQNYSioiIcPnyYfz927Bj+/PNPREZGonbt2njsscfw4osvomHDhkhJScHTTz+NxMREDB48GADQpEkT9OvXD/fddx9mz56NkpISTJo0CSNGjKBIaIIgCIIgVCGxWEPYtm0bevbsyb9PmTIFADBmzBjMnTsXjz/+OIqLi3H//fcjLy8PXbp0wS+//AKz2cz3mT9/PiZNmoRevXpBq9Vi6NCheOutt674tRAEQRAEUXPQSJIkXe1CEDWHgoIChIeH48knnwwRogRBEET1x+Px4JVXXkF+fj6NQScqDI1ZJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFQhsUgQBEEQBEGoQmKRIAiCIAiCUIXEYg1h/fr1GDRoEBITE6HRaPDdd9+FrB87diw0Gk3Ip1+/fiHb5OTkYNSoUXA4HHA6nbj33ntRVFR0Ba+CIAiCIIiaBonFGkJxcTFatWqFd999V3Wbfv364ezZs/yzcOHCkPWjRo3Cnj17sGLFCvz0009Yv3497r///stddIIgCIIgajD6q10AomL0798f/fv3L3Mbk8mE+Ph4xXX79u3DL7/8gt9//x3t2rUDALz99tsYMGAA/vOf/yAxMbHKy0wQBEEQRM2HLIvXEGvXrkVsbCwaN26MBx98ENnZ2Xzd5s2b4XQ6uVAEgN69e0Or1WLr1q2qx/R6vSgoKAj5EARBEARx/UBi8RqhX79++Oyzz7Bq1Sq8+uqrWLduHfr3749AIAAAyMjIQGxsbMg+er0ekZGRyMjIUD3ujBkzEB4ezj/JycmX9ToIgiAIgqhekBv6GmHEiBH8/xYtWqBly5aoX78+1q5di169el30cadNm4YpU6bw7wUFBSQYCYIgCOI6giyL1yj16tVDdHQ0Dh8+DACIj4/HuXPnQrbx+/3IyclRHecIXBgH6XA4Qj4EQRAEQVw/kFi8Rjl9+jSys7ORkJAAAEhLS0NeXh62b9/Ot1m9ejWCwSA6dux4tYpJEARBEEQ1h9zQNYSioiJuJQSAY8eO4c8//0RkZCQiIyPx3HPPYejQoYiPj8eRI0fw+OOPo0GDBkhPTwcANGnSBP369cN9992H2bNno6SkBJMmTcKIESMoEpogCIIgCFXIslhD2LZtG2644QbccMMNAIApU6bghhtuwPTp06HT6bBr1y7ccsstaNSoEe699160bdsWGzZsgMlk4seYP38+UlNT0atXLwwYMABdunTBBx98cLUuiSAIgiCIGgBZFmsIPXr0gCRJquuXLVtW7jEiIyOxYMGCqiwWQRAEQRDXOGRZJIjrDI1Gc7WLQFQzxDZB7YMgCDkkFgniOqMsCzVBUPsgCEIOiUWCIIjrHBKIBEGUBYlFgiAIgiAIQhUSiwRBEARBEIQqJBYJgiAIgiAIVUgsEgRBEARBEKqQWCQIgiAIgiBUIbFIEARBEARBqEJikSAIgiAIglCFxCJBEARBEAShColFgiAIgiAIQhUSiwRBENcRNPczQRCVhcQiQRAEQRAEoQqJRYIgiOsImgeaIIjKQmKRIAiCIAiCUIXEIkEQBEEQBKEKiUWCIAiCIAhCFRKLBEEQBEEQhCokFgmCIAiCIAhVSCwSBEEQBEEQqpBYJAiCIAiCIFTRX+0CEARx5ZDP3kE59wiCIIjyILFIENcRJA6J6ohGo6G2SRDVGBKLBEEQ1xGidVlJoLH1lyrelOagVjsmCUWCqN7QmEWCIIjrEEmSFAVdZajI/pIk8Q9BEDUTEosEcR2h0Wj4h6j+yO/T5bhvl3LMsgTgxQpEapsEUf0gsUgQ1wnUCdc85GKrPPFV0Xt8OUReVUEWSIKofpBYJIjrBFEEUIdcc1GzDF/My8DlFIb0ckIQ1w4kFgniOoOE4rVHZYJSKrLNxQg9SstEENcuFA1NENcR5UXCEtUfpft2Oe5lZdPZUHsiiGsXsiwSBEEQBEEQqpBlkSCuI8j6Q1QEaicEQYiQZZEgCIKglEoEQahClkWCuE6h8YsEg0QiQRBlQZbFGsKMGTPQvn17hIWFITY2FoMHD8aBAwdCtvF4PJg4cSKioqJgt9sxdOhQZGZmhmxz8uRJDBw4EFarFbGxsZg6dSr8fv+VvBSimkFCkRDbAAlHgiDkkFisIaxbtw4TJ07Eli1bsGLFCpSUlKBv374oLi7m20yePBk//vgjFi9ejHXr1uHMmTMYMmQIXx8IBDBw4ED4fD5s2rQJn376KebOnYvp06dfjUsirjJXO/kyUb2gtkAQhBoaiZ4QNZKsrCzExsZi3bp16NatG/Lz8xETE4MFCxZg2LBhAID9+/ejSZMm2Lx5Mzp16oSlS5fi5ptvxpkzZxAXFwcAmD17Np544glkZWXBaDSWe96CggKEh4fjySefhNlsvqzXSBAEcbmobGqgawWPx4NXXnkF+fn5cDgcV7s4RA2BLIs1lPz8fABAZGQkAGD79u0oKSlB7969+TapqamoXbs2Nm/eDADYvHkzWrRowYUiAKSnp6OgoAB79uxRPI/X60VBQUHIh6iZUAADQfzD9SgUCeJiIbFYAwkGg3jsscfQuXNnNG/eHACQkZEBo9EIp9MZsm1cXBwyMjL4NqJQZOvZOiVmzJiB8PBw/klOTq7iqyGuNCQYLw8kxms+dP8IQhkSizWQiRMnYvfu3fjiiy8u+7mmTZuG/Px8/jl16tRlPydxeWBjFMmiQhDK0G+DIJSh1Dk1jEmTJuGnn37C+vXrUatWLb48Pj4ePp8PeXl5IdbFzMxMxMfH821+++23kOOxaGm2jRyTyQSTyVTFV0EQ1x4kNAiCuFYhy2INQZIkTJo0Cd9++y1Wr16NlJSUkPVt27aFwWDAqlWr+LIDBw7g5MmTSEtLAwCkpaXhr7/+wrlz5/g2K1asgMPhQNOmTa/MhRAEUa0hVyxBEHLIslhDmDhxIhYsWIDvv/8eYWFhfIxheHg4LBYLwsPDce+992LKlCmIjIyEw+HAww8/jLS0NHTq1AkA0LdvXzRt2hR33303XnvtNWRkZOCpp57CxIkTyXpIENcYFxvte71YSJkovl6ulyAuBRKLNYRZs2YBAHr06BGyfM6cORg7diwA4I033oBWq8XQoUPh9XqRnp6O9957j2+r0+nw008/4cEHH0RaWhpsNhvGjBmD559//kpdBkEQVwgSQWVD9UMQFYfyLBKVgvIs1nyu1/xyRGnKsq6V1U6uN6vctfSboTyLxMVAYxYJ4jrjWun0iEtDaWxiZdL/UDsiiOsHckMTxHWKKAqo4ydEyhOM11t7ud6ulyDkkGWRIK4jmOVI7lajCNjrl4sVQpejzVA7JIjqCYlFgrgOEQUCJeq+/mAvC/L7Lm8XZaE2zvFSoHZIENUTEosEcR1Rljggaj6XOuWgmoisKNSeCOLahMYsEsR1BnXo1y4VvbdlDUG4liJ/CYKoGsiySBAEQYRwsdbJS7VsKp2/osej8Y4EcfkgyyJBEMR1gJrF8FKsiEr5FquDVZKsowRRtZBYJAiCuA64HOLpco2BvRjxSeKQIC4f5IYmCIIgCIIgVCGxSBAEQVxTkJWRIKoWEosEQRDXOWKy9upKVZevqgNxCOJahsQiQVxnUAd37XGlhFR1aztXuzxkwSSuFyjAhSCuQ9SiRSmKtGZyqfesqoNIlKKkL5WqjuSuju38ctQbQVQFZFkkiGuAqrAsXW0rDVF1VMUsLpdyDvksMJVtnzW5LV5K2WnqTaK6QpZFgqhBiB3RpeS2q2orDXF5qYzFqSJiRTye/NiVaQdyYanVaqHRaBAMBit9LBFqiwRRvSCxSBA1hIoIBrHz1mq1pbZVE5vlHYu4ulTmPlTGVcy2VWpb5d1/tRcO8ZharRbBYPCytqPq5rqtLuUgiKqExCJB1BDUxhgqoTTfr9pxqspaSdQcRFFXVnuoivOILujL4WaldkoQlx8SiwRRA5BbT8qzpsg7ZbnFSPxLXL8w66Eo6sQ2ptRG5G1QbfnlFKHXA2TZJ6oTJBYJogZQmWnVKtLJiCKBuD4QRZx8bCFbz5ZVpL2piUG1fSv6okMQRPWDxCJBVFPULDfloWT5kS+Ti4TyzlOWhYmoXpR3P+UvCmVZ/NTue0XGM6odl9pNxaB6IqoTJBYJohqjFnhQGZTcipcSpUruxKuLklCryD1Ruuc6nU7x+GWdUy0wRmwb1EYI4tqCxCJBVCPKsgpdrEgU91Xq8NXGqFGwS/VDTcgpBZCIwk0pPQ5zOSsJQXlbOHLkCBwOB6KjoytcrurI5R4HSOMMiWsVEosEUY1Qs9xV1iJYXkJktTGLFTk+zfxydRDvodpLhSj01PInljXMQM01rdfrodPpKlwGpfVq576SXO7zX+3rI4jLBc3gQhDVmCNHjmDPnj1c2K1YsQIulwvAhY7pm2++gVar5Z+yUuawfeQWJzVxURmu107ySlnUyhL3ahbkYDAYEqyi0Whw7Ngx7Nu3j2/H2hO7/4sXL8aSJUug1WqRlZWF33//HVqtFnXq1MG+ffvwxRdfYOHChXC73fjyyy/5+QsLC7FmzRqeW3HXrl04duyY4ktLZWdzqWj9EARx+SDLIlHtICvVBSRJQmxsLAKBAF/WokULmEwmXj8dOnQI2ae8TlNtjJl8vdihy12V5R3/cubUq25cietTsuYpiTB5Chz5MSRJQkxMDPx+P4ALSdvbtGkDq9XKk2ffeOON0Ol0CAQCCAsLQ7169QBcsCw2a9YMKSkpkCQJVqsVXbt2hV6vh0ajgd1uR8uWLfm+tWvXhtFoLPNa5NdxKVzr7YwgrjZkWSSqFdezhUDs5DMyMvDjjz8iLCwMTqcTwIUOMSEhAQaDAXPmzIHRaERKSgq++OIL2Gw22O122O122Gw2/lm6dCl8Ph+MRiMMBkNIQAOzRGo0Guh0Ot7xazQafPTRR/D5fCFpVtREiJJArEmdd01oc+W5eCVJwrfffovc3NxS1kVxH6fTiejoaGi1Fx79MTExAC68EOh0OqSkpCA5ORl6vR42mw0xMTHcQhkZGYlatWqhdu3a0Ol0SE5O5vtqNBpERkZyIRoZGQmHwwG9Xg+9Xs/PV12oCfecIKoTGqkmPdWJq05BQQHCw8Px5JNPwmw2X+3iXBLVyYIpWoeACx19IBCAwWDgHbnJZILZbIbBYIDX64XdbodWq4XH44HFYgmxBDLB5na7+Xgztq6kpASBQAB+vx+BQACBQIALC4bX68V7772Hxx57jJeLiQKl4BjiyiBvs8ztCwAulwtGoxE6nS7kfovs3LkTxcXF6NatG7799lt07doVsbGxvL0wscfajPiXHVs8J2tPfr8/pD35/X74fD4Eg0EYDAbo9XpIksTbHmtHrHxX8rcoiunq9Ay4Ung8HrzyyivIz8+Hw+G42sUhagjkhiauS6qTZYF1nC+//DImT56MOXPmYOLEiXx5eHg4rFYrTCYTdDodJEmCyWTiotBoNPJOHvhHIEiSxLdn/2u1Wm5BFLcvKSlBSUkJfD4fP9bDDz/MBecnn3yCiRMnlio7Ew0kHq9MsmlR4LD2sWLFCmzevBmjR49G3bp1MXPmTEycOBF6vR5erxcffvghJk2aBK1Wi/bt2/M2cfPNN4e0Db1ej2AwiFmzZsHhcMBqtcJsNkOr1aJ///44dOgQ9uzZAwCYOnUqLBaLqlB0u93weDzweDwoKiqC2+2GwWCAwWCAVqvlLyjy+iur7qrKhX0lovyvRxFKXNuQZZGoFGRZrLpjMgsLswKxIJVgMAitVsvdysyiEwgEuKATRR2z0AQCAe4yDAQCIYEvrJMWxymaTKYQq6PotmTikVmC2IcJUdGtyMpb2chq6lBDEUWg0jq23O/3KwYzse2AC/dHtDCytsNEmtlshtlshs1mg9PphM1mw9tvv42nn34aAJCdnY01a9ZgxIgR3ELo9/sxe/ZsDB48mLucX3jhBTzxxBMoKSnByZMn8fvvv+OOO+4A8M+QBL/fD4/Hg5ycHLjdbl5WubWajc2Vv4DIr03cn6g8ZFkkLgayLBLXLZejs6loEAiLZD5x4gQefPBBREREALjQqZtMJoSHh8Nut0Ov18PtdqO4uBg+nw8lJSVlpsVh7usVK1YgOTkZjRo14gIUuCDsioqKsHDhQtx///1cUDDxodPpuAXI7/fD6XTyY7Lzsw8bzyhaL+XlKqs+qLMPRa0+xHtcXFyMBQsW4L777uP7+P1+ft/YywFb7vP5+HYWiwXHjh3Dpk2bEB4eDovFwscVSpKEZ555BiUlJXC5XJAkCZ07d8bhw4dDxOKpU6dw9OhRvPzyyygsLEQgEMDevXvxxRdfoHfv3jh37hx+/vlnGAwGdOzYkZfLarUiEAggPDwcubm58Hq9IS9KLNK/QYMGqFevXrVMu0MQ1zNkWSQqxbVkWbwayK1HYocZDAYRFhbGA1kkSYLH48GqVaug0+nQqFEjFBUVISoqirukgVArHxMJoiWJLT9//jycTidycnIQHh6OoqIiOBwOSJKE4uJi6HQ6WK1Wnprnm2++wUMPPQStVovCwkJERkZya5Df7+ei8fz583z8pDzFi1zIEmWjlu8wJycH0dHR/P4WFxcjMjISWq0WK1euRGxsLJo3b47c3FzodDpuOUxMTERGRgYWLVoEh8OBm266CQ6HAzabDYcOHULbtm3hcDhQXFwMl8sFt9vNXch+vx9FRUW8vXo8nlKWbkmS+JhEZiVk42oBcOu3wWDARx99hAkTJkCr1cLn83H3tNfrRSAQ4M+TvLw8hIWF8ZeQq8W1avkmyyJxMVSvEDWCuMYRx5oxocjcuFFRUSgsLMSmTZtQUlKC3NxcZGVloXHjxmjQoAFycnKwYcMGHjQgF2darRZGoxE2m41HUTMXo8lkwi+//MItOF6vF9u2bYPJZILBYMDBgweRlZUFs9mMDRs24Pvvv8ddd92FgoICZGVl4euvv0ZRURE8Hg8CgQCPlrXb7dixYweAC0ERDCXL4uXIr3etIRfa7PPzzz/ztuP1erF169aQKHWr1Yq4uDicOnUKBw4cwLJly7Bnzx7ExsZi165daNSoEdq0aYPWrVsjKSkJer0edevWRWZmJpYtW4b9+/dj3bp1OHv2LPLy8rhF8ty5czhy5AgOHz6MhQsXIj8/H1arFRaLBXa7HeHh4XA6nYiIiEB0dDRiYmJC/kZGRsJisSAQCODuu+9GUVERDh48CABwu92w2+04ceIEDh06xF961q9fD7fbjZMnT16dm/D/cy0KRYK4WMiySFQKsixeHPJceeLYMqPRiKioKFitVnz//ffo0aMHdu/ezaNUTSYTTCYTNm3ahGbNmsHpdGLfvn1o2LBhyDlY8ApzRbLxiKIlkLmS2fbAP6lPWLS1Tqfj48z++OMPNGjQAJIkwefzITs7G7Vr1y41o4dOp8P+/ftRr149HvSgFPRyrVprqorz58/zFwd5m2FiXKPRwOfzobCwEE2aNMHmzZthNBrRq1cvbilavHgxBgwYwINMvF4vvF4vbwMnTpxAWFgYbDYbfvzxRwwYMAA///wzbr/9dgAX2gSzMtapUwcAsGnTJjRu3BixsbH8RUccG8nKaDQaYTabYTQaodFo4Pf74XK5UFBQgPz8fHz55ZdIT0/Hxo0b0bhxY1itVu6WjoiIQDAYxKFDh7B48WI8+eST1S7tTk2HLIvExUBjFgniCiB3PTNBZ7VaERkZCbPZjJKSEthsNpw9exaHDh1CbGws7HY7d8n16NEDHo8HW7ZsQUZGBmrXrh0S6KDRaHDmzBkUFRWhbt26MBqNPL+iwWDgnbjP5+PCgQWusE4/EAhg9+7daNy4MfR6PbKystCsWTMEAgG4XC5kZWUhKSkJJSUlvBNnLs+srCw0atQIALgLUQy8qWn5F68GhYWF0Ov1yMnJQa1atXhnziKWzWYzwsLCEAwGkZmZicTERDRr1gyHDx9GdnY2tm7dipSUFLRu3RpHjhzB5s2b0aRJE+zfvx/NmzeHJEk4e/Ysjh07hlatWsFkMmHo0KHQarUYOXIkdDod/vzzT9SvXx+7du1CZGQkEhIS4Pf70aZNGxiNRt5eWGAVy8fJYGmebDYbd3kzC2ROTg5Gjx6N3NxctGrVCmvWrEEwGESdOnWQmJgI4MJLzM8//4zWrVuTUCSIagL9EmsIM2bMQPv27REWFobY2FgMHjwYBw4cCNmmR48eIa4rjUaDCRMmhGxz8uRJDBw4EFarFbGxsZg6dWpI2pXqxLXgshSFnPyv3W5HbGwsrFYrPB4PsrKykJWVBa1Wi86dO8Nut8PpdPJAF+AfN2Xfvn2h1+uxbt06Ljxzc3Oxe/dubgXctGkTTpw4gby8PLhcLgQCARiNRu6iDgsL4+PLDh48iBMnTsDlciE/Px/FxcVYsmQJt0quWLEC27Ztg9FoREZGBlasWIHTp0/zcY52ux0333wzNBoN3G43li9fju3bt8NkMsFoNJaZ2Pt6R6PRICcnBytXrkQwGETdunVDrLYbNmyAw+FAQkICTp8+jdq1ayM5OZmPUbTb7WjcuDHWrl2LDz/8EHPnzsX8+fORl5eH77//HsuWLcO2bdtgNpthsVhgMpnQrl071KpVi1uI2fjXZcuWwePxwOfzwWq1omHDhnxMIWtnbNuSkhJ4vV64XC4UFxejsLAQeXl5yM7ORkZGBk6ePInTp08jNzcXfr8fYWFhSE5ORkpKCmJjYxEREYGuXbsiKSkJgUAAFouFj3Xs3r07+vXrR+2FIKoJZFmsIaxbtw4TJ05E+/bt4ff78e9//xt9+/bF3r17YbPZ+Hb33Xcfnn/+ef7darXy/wOBAAYOHIj4+Hhs2rQJZ8+exejRo2EwGPDyyy9f0eupCDXdCiUKQ3lAS1hYGKKjo2EymVBcXIzz58/D5XKhbdu2XEgyiyPwT12wXHnff/89Bg0ahPj4eG7B0+v1qF+/PmrVqoWSkhI4HA5otVp4vV74/X54vV4YjUZYrVYuGm02G3w+HxISErilqGXLlpAkCZGRkTwVT2xsLPLy8rB3716kp6cjKSkJBw8eRHh4OBISEmCz2XjKHbfbjcjISFitVpSUlHBLE3OFs3qo6ff3YhGDWJjwMplMSEhIgNPphF6vR2pqKk+f1KZNG9StWxcWiwXZ2dnIy8tDQUEBXC4XT6O0adMm+Hw+BAIBxMbGYvXq1Rg0aBBsNhuSk5ORn58Pg8GAQCCAxMREaLVarF69Go0aNYLT6cQPP/wAv9+Phg0bonnz5tBoNLjhhhtChD4LbJEHUfn9/lIplZgbW5xBJjY2Fk6nk08vyCLqIyMjkZWVxcfAFhYW8t+BPGn39dxuCOJqQmKxhvDLL7+EfJ87dy5iY2Oxfft2dOvWjS+3Wq2Ij49XPMby5cuxd+9erFy5EnFxcWjdujXPk/bss88qzuVa3agpnQXLGzdv3jw4nU4MHjw4RChGRkbCYDCgqKgImZmZITkTmWvabrcDAE9dwqyKwWAQzZo1439Zp200GhEXF4eSkhL89ttviI6OhtVq5alv2HZFRUUheRztdjtMJhPy8/Ph9Xq5OGjbti3fr2XLljh9+jT+/vtvREREIDw8HFlZWdwqunTpUmi1WowaNYoHzRQXF/PjsYhZJhLk803XlPt6scivlc3K43K5sGLFCtx6661o06YNrxeW/zA8PBwNGzaEJEnIy8vD4sWLAQC33norzGYzYmNjYTAYuFDfuXMnWrdujfr162PRokUIBoM4evQo+vTpA7fbzdvPpk2bYDabudV63759GDJkCFJSUqDT6biVz2Qy8STaLPk2O5fH4+H3kiGfQhK40H49Hg9/oTGZTIiOjobb7UZJSQny8vIQExODv/76C6mpqYiKikJBQQEP2hKPfy23EYKozpBYrKHk5+cDuDAHq8j8+fMxb948xMfHY9CgQXj66ae5dXHz5s1o0aIF4uLi+Pbp6el48MEHsWfPHtxwww2lzsMGxjMKCgoux+Vck7CZL9iMKTqdDna7HdHR0TAYDCgsLEROTg6PPA0Gg9yiaLfbeaCJKBKBCx0mCzoA/rFWsjQ5O3bsQElJCeLj40OSHvv9fh50wIIXJElCVFQUwsLC+FhGn88HvV4fkm+xpKQEiYmJGDRoEM/jx9peXl4e2rdvj8TERERFRfHpCFkwTTAYhNfr5cc0m808qpodq6wcgzVVIJRVdmaBM5lM6N69OzIzM7F7924MGDAAMTExcDqdMJvNCAaDKC4uhtvtxssvv4w+ffrAaDTCZDKhdu3aqFevHgwGA6Kjo3HkyBHo9Xp8/PHHMBgMyMjIgE6nQ7du3RAVFQUAPPDE7/dj165daNWqFRYtWoQxY8YgJiaGj2vVarVc9IszsrDIfZZ3U0z7xESwaF1kwpKtZ/Vis9n4WEjgQgS0RqPBunXrkJmZyV9qHnroIV6POTk52LhxIwYNGnRJdU8QROWhMYs1kGAwiMceewydO3dG8+bN+fKRI0di3rx5WLNmDaZNm4bPP/8cd911F1+fkZERIhQB8O8ZGRmK55oxYwbCw8P5Jzk5+TJcUcWpLh1ARcZSabVaxMXFITo6OiTq+bfffsO2bduQnZ2N4uJilJSUQKPRwOl0Ijo6mge0sMAQcSYWFhzz7rvvIhgM4q233gIAnt5Gp9OhZcuW6NChQ6lo9f/+979wuVw8f978+fN5GZhb2mQycVcyG+Nos9lgsVjgdDpRq1Yt2O12voyNeYuIiEBYWBiKi4uRl5eHmTNnAgDOnDmDFStWQKvVwu/3Y9GiRTh69CgXPGJ9Xssotds33ngDRqMR0dHRPJ9hZmYm5s+fj5MnT6KwsBAZGRl45plnkJubixMnTuDTTz/F119/DY1GA4PBgO3bt+OVV17B66+/jpkzZ2Lo0KG49957MWrUKEyePBmPP/44GjZsiJiYGMTHxyM5ORkJCQmw2+1wuVyYO3cubrrpJsTExECv18Nut3OLo8Fg4FHXRUVFcLlcPLqatVkmDMXofmY9NBqNXOwywcgs1cy6mJSUhPj4eNx44404c+YMEhISUFRUhOzsbNxzzz0AgLfeegsajQaRkZHo27ev4m9PKTk9QRBVB6XOqYE8+OCDWLp0KX799VfUqlVLdbvVq1ejV69eOHz4MOrXr4/7778fJ06cwLJly/g2LpcLNpsNS5YsQf/+/UsdQ8mymJycfM2lzqmsJUItebII60iZyIuNjUV0dDRcLhfOnj3LLW9sxhY2qwZzYYsWRY/Hw926wWAQL7/8Mv71r39xYTd//nyMGzcOer0emzZtgsFgQLt27UKm4mNWytmzZ2PatGmQpAvzPjudTiQnJ8NgMCAnJwfnz5/nOfAiIiK4JYrldwRQKpKaRV0zt2JWVhYyMzOxZs0a3H333Vz8+ny+kJliWBoY0S19NR5JV8ISpZR7krmQo6OjebBTcXEx8vPzMXPmTKSnp+Pzzz8HAD4G8JFHHoHNZoPNZsORI0cAAJmZmWjVqhXq1avHZ25hY1+tVit0Oh2/Rz/++CPOnz+P33//HX369EF8fDy8Xi8cDgfCwsJgMBi4NbigoADFxcWlXMGiOGTLGGIqHdZG6tSpg5SUFJ5I3Gw2w2Qy8d/C8ePHcebMGd5OPB4PwsLCeLs3m80IBAKKswWJ5Sqv/q9E25I/G6oblDqHuBjIDV3DmDRpEn766SesX7++TKEIAB07dgQALhbj4+Px22+/hWyTmZkJAKrjHFmOP6I0YmcgF43igHyNRoOwsDBEREQgEAggLy8PixYtQps2bZCYmMjToYgD/0X3MTueaFlk0dEsncq9994LSZKwY8cOrFixAunp6ZAkCXPnzsXff/+NyZMnw26348UXX+TBJlarFQcOHMDatWsxevRo7v4MBoMoKCjgiZeZO5SdTxSe4oeNadNoNHA4HLBYLLj77rt5/TChyY4lujFnzpyJRx999KpZh6r6XGoJySVJwn//+19MnToVJSUleO+99/Dqq6+isLAQK1euRI8ePfD5558jLCwM2dnZePPNN/m4wX//+98h83/7fD40bdoUYWFhCA8P59HtbB2AkHyHzNIHXHgJHDFiBCIjI7kFmb2ssCkh8/Pz+Ww+4thBUQyxlxHRHc3arl6v5x9miWbDIdxuN8/tGRsbC6/Xy88pDlVgqXrYPOrs2OyFqH379hW+HxW9V5dKdRWJBHEpkGWxhiBJEh5++GF8++23WLt2bamEzEps3LgRXbp0wc6dO9GyZUssXboUN998M86ePYvY2FgAwAcffICpU6fi3LlzFRKFlJS7bFin5PF4uPgzm81ISkqCyWTC+fPnsXjxYsTFxaFRo0YwGo2IiYlBeHg4j1ZlQoxZbdgyr9fL3cNMnLlcLsyaNQv33nsv79BZoBIbMyaOWTSZTAgEAsjJycHq1avRqVMnHDp0CLfeeiuSkpJgs9ngdruRl5cHrVbLZ4ARo7FFQSCeh5WTrfd6vSguLuZuSAAhQlMU1Hq9vtTYNrb91eBSBYQoqJhFrKSkhKcqYnkqU1JS4PP5sGzZMtSuXRu7d+9GUVERduzYAUmScN999/HfKhsqwNLfMOscS4nDjs0seiyghN1/ZiE+evQojh8/zl9SioqK4PV6eRssLCxEVlYWiouLQ8bDsjGx4rWJrmhmTWRR3ux5YrFY0KBBAyQmJkKv1/OobYPBAJvNBoPBgPPnz+PgwYM4evQo3n//fYwYMQI2mw2vv/46Jk+ejHfeeQeTJk1StEBfSUvetTAWkiyLxMVAlsUawsSJE7FgwQJ8//33CAsL42MMmTXgyJEjWLBgAQYMGICoqCjs2rULkydPRrdu3dCyZUsAQN++fdG0aVPcfffdeO2115CRkYGnnnoKEydOJOthJVCyGon/azQa/O9//8MzzzwDnU6HmJgYWCwWFBQU4JdffoHRaESzZs2g1Wr5WD/m+mNCEAhNl8Pm3mWuXOYSttlsuPfee7F48WJ07twZhw4dQv/+/UNSlrBjffDBB5g4cSIXE0ePHkVGRga8Xi8iIyN5hC1L4M3SsrAoZmZFYtcvJkxmgo9NQ8hc3x6PB4WFhSgsLITb7YbP5+PHEt2ZzCIpBupcC+MYWdBG/fr18dtvv+GWW27hida/++47TJs2DX///TeysrKg0+lQVFSEvn37om/fvvweW63WkMTWbPpGMfKYwdzP7NxMuAPgwSY6nQ7x8fGw2+0IBAJ8XnC9Xs+/u1yukKAVAKWCWdg6dr+Af4ZcMAt0IBDg7m3WjlhbZu5yg8EAh8OBmJgY5OXl4Z577kFBQQGMRiOeeOIJABc8KmWlzlFadi0IO4KoLpBYrCHMmjULwIXE2yJz5szB2LFjYTQasXLlSrz55psoLi5GcnIyhg4diqeeeopvq9Pp8NNPP+HBBx9EWloabDYbxowZE5KX8Xqmop1LWduwjjo5ORlnzpxB48aN4XA44Pf7kZGRAY/Hw6c0czgcCA8Ph8lkCol2VhrAz9LPMLHIrDfM5Tty5Eie0Dk/Px/5+fk8ovbcuXOIjo7Ggw8+iEAggDNnzqC4uBhJSUnQaC7M+gL840JkQS1smd/vh16vDymj2nWLKX6Y+5HN5lFcXIyCggIUFhbyAAkmjjUaDc6dO4fY2Ngyx6VdKS7m3GL7YYEgERERaNu2Lex2O/cGhIeHIy4uDk888QR8Ph/OnTuHs2fPIikpiee21Ov13L0cGRkJh8MBq9XKBRc7l9hmxJcNJthES3BJSQkXi06nE0ajEfn5+dzyyYKQmBVYLg6V6ke+nI1FZaLfarUiJiaGtydWPhZR7Xa7edtm80sXFhZi/vz5GDt2LEwmEwoLC/nLi3h+0cKo9NutTkKRhCtR0yGxWEMo70GTnJyMdevWlXucOnXqYMmSJVVVrGuGqniYix3nuHHj8O2336Jz587Q6XQ4e/Ysz23XtGlT7gJk48hES6A4lZpYJnEeXmbNYWPCREvP0aNHsXPnTnTt2hXJycnYunUr+vTpw8ezrV27Fg6HA/fffz+OHj2KOXPm8DKwsWFsiIE4x7MoHsS/rGwM5rJkIoTllrRarbBarTAYDMjLy+NjFgOBALxeL7Zv347+/fvXyNx6ctGUnZ2NM2fOoEOHDjhy5Ahq167Ncyey3IjM3QwACQkJaNq0KYLBIEwmEyIjIxEZGcnrjbmXxVQ0YiJsdm/KCv5gibTZ/M0ajYYLSNYOxXbFBJ04LlV0O8sxGo3cRc6EXUJCAqKjo/nxmbVRHHtZVFTEra1xcXHIy8vDXXfdBUmScPToUZ4Avm7duqWurTyXdFW7qC/2ODWhDRNEWVDqHKJacqVdkJWNhBY/AHD06FEUFxcDAJ9fd8KECXwM4MGDB3Hs2DG0b98eWq2Wz54i5hmUu43lIpKlSzGZTCGD/TUaDQ4fPoyCggIcO3YMzZo1w8iRI3nak5tvvhkmkwl//PEH9Ho9Ro4cifT0dGzbtg0HDhzggoBZEUXLkmiZKgu2jXwmj5KSEvh8Pvj9fn7dcXFxiIuLg81m4+LDZDKFCEX5nNc1AfE+1apVC/Xq1cPZs2fRsWNHJCUl4ezZswgPD4dWq8XatWuRkZGB3377DXa7Hb169QIA2O12JCUloVatWiFJ1T0eD3fji0MVRIuuaGWUDxEQU9wwl7NonWQuYTYcQMyzqWQ9ZG1DvG4mFpllODIyErGxsfwlhbVl0frMxK/X6+UpmGJiYmC1WuH1erF3715otVocPXqUB0gp1XlZ38vzBNSU9kUQVxMSi0S1pCa9iWs0Gj5/LsPv9yMiIgJerxfLli2D0WhEq1atAIC7ZVmnypD/L3asYqoSFqHOtmHJu1mKHTZm0Ov1huxbWFgISZKwceNGeDwebNy4ESaTCV27dkWdOnVCkimLM8qIkc6iUJHD9hMDYMRZPFhwDpuXPC4uDg6HA0ajkU8lx4SiXHRW9w5dKfKZTYWn0Wj4HN+bNm1CZmYmPvnkExQVFaFbt27cAhsVFYU6deogPj6eJ9Jn40aV6l7+wiIKdmYlZPuxZUpR7Cx6mrUX1j6ZJZgl6Wbbs2OK5TGZTLBYLNBqtXC5XLBYLKhVqxacTicA8PbD2hWzhjLRylJ0mc1mxMTEIDIyEnq9HjfddBOMRiMGDBgQkrpJrIOy7kVl7l15EdOVWU4Q1xrkhiaISiDvHA4fPgydToemTZvi119/Rdu2beFwOHDbbbdBr9fjzJkzWLZsGR588EGEh4fzMYZmsznE6qFmEZG7AAHwSFM257PBYECnTp1QWFiI8PBwHDx4EHq9Hk2bNg1xT3fv3h3BYBCbN29Gt27dkJaWBp/Ph06dOsHhcPAp+cRrlLuXRSuVkqtPFLisrKKYYTk7matVo9EgNzeXzw7CxtaJlkwxalqprqoDYp3l5ubi4MGDuPHGGwH8M0YxMTERa9euxWeffYYePXrwuZFNJhNPmm2327n7Vxzfxz7ylwe5YBTvgbhOHN8oWvbYOjYkgEVXM5i4A8DvkTygCwDP58giqFkyeqPRGOI2Z9cjHw/J0uno9Xo4nU7ujs7Ly4PH4+EBYErjJxllBcDI75XS766s/S6lzdF4ReJagMQiQVQAeboQRlRUFP9et25dmEwmPt8yS1DNBJIkSXxsFos8VbIUKY3BkpeFuaNdLhck6cK8wZs2bcKNN96IiIiIkDQmALhlSKPR4Pbbb4fRaESTJk2QlZXFj8UCE+TnEgMq5MiXie5jueuaLWcRu2x+apbYW0wxU1RUxMe9yYVQdel8le4NS5VUu3ZtBINBWK1WPgVibm4utm7ditq1a6NJkyYALuRBjI6O5m55JtxERAEoPxcrh1hHrD6VjgEgxIUsztft9Xqh0VxIscPyeLIyihZL1kaYCGQJwpnoczqdiIqK4m1cFL7s/im1DeYKZ7O75Obm8qTzTGCyMZfiWFq5eGbL1FBap9amqqKtVYe2ShCXCrmhiRrF1XD7KAnFv//+G2vWrEFkZCQiIiKwcuVKmEwm6HQ6OBwO6PV6Pp8u6xwNBgOfUk9EtB6x76IFRm4JYa5nlk/R6/XCYrEgPj4en3zyCY4ePQqn0wlJkvD999/j/fffh8fjwYcffog5c+agXr16OH/+PH766SfExcXxgAcW8SyKk7IitMW6Eb/LrV2s3CJsLCMAnvzbarWGJAJXOq7Ssa4W8rGmJSUleP/997F06VIkJibCaDQiIiICJpOJT2G3b98+pKSk8CAiJhStVit3B8stuCwCXu5Clrub2Ud80RA/SgFTLEAK+GeoAJvOj1nxWJJsNvyBTfPIIuctFgv8fj+ys7Oh1WoRFRUFq9UaUm75sAKx7KytB4NBPlQhLCwMsbGxiIyM5NMOMre1XCjK/8qtrhW9l5VZXtH1BHGtQJZFosZzpSxNYscTFxfH3agAkJeXB7/fz2cu8Xq9mDFjBkaMGIGxY8cCuCCKlKbzE48tWgJFC53o3mXWHdZxs+VNmzZFUlIStxZJkoRevXrxTn3YsGHcehgWFoZevXrxYAYxXY3otmQduVi/oitQtIYyRLEr1p14vaJliaXYYWP8WFodANz9yMb+MVFR0Xt+uduGWA8sR+Fdd93FE5qHhYXB5/Phk08+QWpqKu655x5YLBYYDAZER0cjJiYGdrsdAELyS5YlXti9EduIuJ9ouZMHu7Axh8y6yMaVsnvMXOOSJPG2wo7BLIqBQIAHQZlMJrjdbhQUFPCcomFhYfw+ie1cDJhiglgso0aj4WMnrVYrIiMjkZ+fj8LCwpBZXADw8a3i70f+e5LX4dWySFcXSzhBXApkWSSqPWVZqNSWXW70ej2PVF22bBmaNm2KVatW8TGExcXFOHbsGN566y0eAWu322E0GhXHI4puRiWLiNL2TPSxIBE23ovl42NWzvDwcAAXxs4xt68kSTx3HwuWEccKyiOx5WVRim6Vl10pHZB8OVvHLFQsmEJcxyJyKxLsolRvVY3c5cn+Wq1WPProo1wksuEA+fn5OHv2LEpKSuBwOKDRaLhQZK5ncVYbIHTaPBZ9DPwzmw8TXGr3SNyWbcfqg4lvcV5vZl1k40pdLhdcLhfPF+nxeOD3+3mSdWbpKygogM/n4wEtcXFxfIo+Vk6ldi7OCCPWKwvSYoFQ4eHhPEcjOycLcmH1VRlvg9J4yyvN1TovQVwKZFkkrhoVfeO+mm/losVPHPcnWuHS09MBAH/99Rcfu+VyueD3+/Gvf/2Ld8gsVQ7rJEULHOtE1YSxkpWRuaKZmGCpVUQrnJikmQkPdiy9Xs/z4sld3ayzV0qQLV6/PBBFFFByN624XLSMiS5KFvjDpglk4xhFV2RZEdlXuq3ILa+sfiMiImAwGPDDDz/A4/Hgjjvu4HUZFRWF2NhYWCyWEIuZ3IKrVpeiqBS/i8MYRBEpL6NY/2wWILfbDbfbzV3ZJSUl3ILI2gNrEwD4kAWTyQSn04n4+HhERkby+8csj+IsM+w4YjlESzO7Bp/PB4/HA4vFwue8Pn/+PP7++29s3LgRt99+e6lhCfL2qyTI5G1Dvt/lgqyKxLUAWRaJq0ZNe4iKndHx48cxY8YMrF69GpIk4auvvsItt9yChIQE+P1+vPjiizCZTHyQv2hVBP4RAmysYnnjAeUCTbTs6XQ6WK1WhIWF8bF/JpOJW+tYwM17770Hi8XCrZEs16PZbOaWSHFMmbysav+Lnb7cFSiK3LLqlQkRjUbDRYLVaoXf78cnn3yCrKwsvPPOO3z2GrkwvVLIBRwrk0ZzIVXOhx9+iMjISFgsFmzcuBE//vgjvvvuO/z999/QarU8bRCzSoviSbynogVQtA7K61kc+ycKOjHVjlyws/OyF46wsDBER0cjOjoaERER3DJqNpv5dbKUTQ6HA06nk0cs165dG8nJyYiOjobdbudWP9FKzhDd0uJLgzxHJ7MuAuCz2FgsFsTFxWHUqFEhrmi5uJZbGsuzPCq18ctNTXvuEQRAlkWCKBcli0VKSgr+/e9/4/fff8dff/3FRZlGo4Hb7cajjz6KvLw83gGyWThEq6L8HKKVQ56eRhQH8mAYZjFkos9kMoWIDiZGX3zxRQD/RMCK1iilYBoWUCDvlAFld6/cOioXVkpWSDHpNxNHbD5kh8MBr9fL0/n861//4vNiy8XP5UJpPKZ4bY8++iifx9hkMuGRRx6Bw+HAwYMHsXv3bjRv3hwRERFITk6GTqcLEYpiGhy5tVCsU6XgJ7EO5e2TiUFA+V6LwpxZvdkc5Uxw+nw+FBQU8Kh0g8EAi8UCm83Gx1xqNBfGu5rN5pDhFWL9yOtObI9i2Zl4FcdOspll2Cw2RUVFkCQJZrMZHo+H54WU15m8PuV1pdZeroSVkcYvEjUVEotElVETHoQXW0YlcaTRaNCpUydotVqkpaVxq2JRURG8Xi8WL16M8ePH88TG8o5ddA/K3bryzla0pojWSFGQaTSaMnMligJCPjZOnoNPzO0nrzf5/8yVLFo61aaEY+WR1yc7JgtuMRgMsNvtcLvdGDlyJLKysiBJF4IuxCCMS0FJ0MhRWidahSVJwqJFizB+/HhotVqEh4fziN1Dhw7B4/GgW7du0Gg0CA8Ph8Ph4HMwi/dA7lYVzyW30KqVSfwojWkU17PxhKy9sBlb2L0JBAJ8iILb7eaR/Ey4sWMA/7Qn5k4Xr0O0JIrXJqZokqR/kr6zMgQCAZ5f0Ww2w263Iysri2+jJErVBKpaWyvvPsuPr7YvQVwPkFgkqoyr9RCtyAO8Mg95tc5FFGYulwuZmZlwOp2IiYnhbt/Dhw/j2LFj8Pl8eOCBB+DxeHj6D3mgQVnjqkQBKY43Ey2AauUWrUhsH7kAEa1NTHyJlj/xPEouRfl55cJHbhlV2pZtL79+FnjB5s/2er3YuHEj+vfvD7vdjgMHDiAlJUWxLJVB7R7IEbeR1+PRo0cxfvx4AOBWsEAgAJPJhIEDByImJoYvj4qKgslk4i5iMWhFHrEsF13iWFUg1PIsr1N271j7YSJO3JYJNHY9zALJrotZDNnwCWbtNZvN/NiipU7Jgii+gMitiaLlm20jHoPNF86GVLC/Xq83JPBHPv5Xfn/k96wiiPvJ28ilPuNIaBI1FRqzSNR4KvIAlrurLgZRjGVkZOCnn35CRkYGNJoLiYy1Wi127dqFzz77DDt37uSdpZguR2ksoLxsau4ztetSioqVRyuLnbM8UlUpalbN9Sl+l0c7i/vIxYBcKMjLJG7H1hmNRp7EfNiwYTyoYu/evYp1dDGU1R7KE+SSJPG5tfV6PcLCwmA0GuHxeHDkyBFs27aN5zIUx6wya5sYESyOTxTbA7MQsryUSmM/RdEmWobF+Z/FczHLL3M3s2CWYDDI3b9s+ko2VpENcQD+yZEpD34R25E47SO7PrGs4j5iuURYfbDMA2x4RUlJSciQCXnbVxOJF2uNJoFHEGRZJC4Tl+ruvVRRVxUWAFEYKJ2jdu3aaNGiBR8nKEkSbDYb2rdvz/MbinPrMtej3KUlFwByISQKKrX9RStkWePF5OKNWXCYpUvu3hbH1cnrR14uMapb7lqV7ytep9xyy6xebBwmc0ezcg4dOpTPilMV7UUJtbIxdu/ejdzcXPTp0webN29G7969ERYWBrfbjeXLlyM7OxuNGzeGTqfj+TVZpC+DWdxY+cXvYpuQpzESo/LZvnIrmJgfUclSLrqORfElvtQwi6SYuFtu4RTFr7zulNzr8nYob1/iOhaVzVIqmUwmXjYxWIy1e4bS/arMM6G8FwgSj8T1CFkWiSqnMlaessTExVLV+5fnijp48CCys7OxceNGFBQUoHv37nzaOjb4Xx7JKj8W61TFqfVES6A8YbNc+LFjqbkF5evLsvKxbcVp2sqrH1FEsGnb5InH1epaXgcA+LlZeh8WVMFEihi4cSWQn8dgMPAZdMxmM2w2G0wmE/Ly8rBu3TrExcVxschmpBEtbfL7JH4Xt2OIkcRya7H8fyVrGzuGOJsKS2wtzg4jbwvMQimWQTw2OyZLqK50XtaW5JHdYrnk4hH4Z+YaSZJgNBp5miggNCWP+JGj1PaU2ltFuFJtjSCqIyQWiSqnMu6e6vqWLloQxL9KFrbo6Gg4HA5ER0ejRYsW+Pnnn3kdmEwmxXl6lb6XJRZZJ8u2k5dVfjy5+BO3k3eucmukeF5xf1GwiMeTi1TmKpS7OMVyiGJVLirFgBwmFJh1KRAI4Msvv4Tf7+f1rFQHci7GVS231on1lpqaivz8fHz99dfo0KEDT/OzePFiGI1GNG3aFBrNhSn9mGVZrB+1cisJRfn9VPrIjyEX+sxay6b083q9ITkVmWBk+8ndxqKbnK0X77PoPlcri9gWlMqsJKDZ+dgYSiZcmcVTHkwlWrgvBrU2IrdgX8rQB4KoiZAbmriiVMRteLlcPZU9rpIIk7uBmTva6XTCYDBg5syZaNmyJR/HyMQiixyVCxB5eeTCRDy3WkfFjqckcNWOJz+ffHyikoBViqwV92FjFuVj5dh+YhS2WjnFczJBIrpyi4uL0b59exiNRrRt25aXg7k8lYSs0jWrLZfXtRx2ncFgEG3atEFxcTEMBgNPbN6hQwe0aNGCH8tqtYYkEmfCCwgdoye/f8A/6WSY2FJKOSN/gZHfO4ZoVVSyGLPlYvCUKBTF/8X2IKa8kb90sPGPGo0mJFhKbDtKdS4KVfHaTSYTj4Zn9cfGTV7MM6Msq6PScrXfT0XOS+5roqZDlkWiWlEVD9SqeOMXRd3777/PrShvv/02Fi5cyJMRb926lbsjS0pKcObMGdSqVQuSdCHNC3OdyqOg5W40JYuT3AIolknpIwaYiPWgJC7FIARxe9GaI5ZTrUzseOIxmHhiufjk7k3R9c32UZrnmNW5RqPh82AbjUYkJSUBAM9dKCIvm1h3SoJMCbmQUTret99+C6PRiOTkZBiNRnzwwQcoKSmB1WrF+vXreZnF6GHRYisf8ycGFon3gVnj5OvYvmpWR9EaLQaysA8bO2m32xEeHg6TyRRyjUrJ4pVeOMS2JxenPp8PRUVFcLvdIeVn69l1y/eXWxbZWF82dlL8HahZWpVe9Mq615VF/rJT0e3VIEslUd0hyyJxRanIw/VSBWNVCk5JkjBmzBievPiee+7huenatGnDLWmSJGHOnDkYOnQod0mKgQFK1ipRGCpFuapZ8dTKW176FSYsmFWJufHE3IWiiGOCQS4Gxb/y/xli5y+fA1huoVKyMjFEqyQT3y6XC16vt9QcwWr1I4qK8lATGvJlgwYN4nMqh4WFYfz48dy9KyaPFq2sorATLbWiYBJd8KJIZOlwWJ0o1bccuSAVrdsAYDKZEBMTA7vdDq/Xy+d8ludLFPdRsnDLUzmx9eKYw2AwyH8L8vKJYlG0vIpR4+y3xMZZyqOsy0LpBaGslwa2rrL7XQpkdSSqO2RZJKoFai6eq4H8vGzGDa1WyxMVHz16FDNmzMCvv/4KvV6PxYsXo2PHjoiLi8Obb77J5zFmgqY8UaT0nS1TshqKnaq4rCw3mihAWOAIm3uXWUDV5l1WG2cnt3TKBSebBUZJZMq/y9PuyC1p7BxWqxVGo5FbnZSOK6cinbyaKBYtVqtWrcILL7yAjIwMHpXL0rpkZ2fjk08+wT333MPFEXOlipZVdh1yizP7y+4DqxMmkpQsaXJrrVLZRdevKDxZ/seEhATUqVMHcXFxfA5uNg5RzSIsH1spXy9JEm//YpS80kuMPKhGHgwmptbR6/WlxjzKra3y+17Rey5fpvSSUFnIWkhcK5BlkagWlPXQvpznKGtbJQsDG9cVCATQpEkT9OzZEytXrkTjxo0RHh6OwsJCTJkyBW63m3f08k6V/ZV3ikplZJ0NO6foxpNvI4oIOaxDFqdts9ls0Ol0KCoqgsfj4e5CZi2SizWlOmLr1IJ4mEBREmLsf3mZxWOK94B9WAL0goICPsuHkmgsTziUZ60Vy8f+DwQCGDRoEGrXrg0A3M3scrnwn//8B5MmTeKWZ/k8yew65dclr092r8p6wVByRzMBygShKNjZ/ZQkiYtAj8eDgoICREZGwul0IhAIIC8vD/n5+YpiXTyPvPyiUGXth6ULYtfCyiYXtex6mYVetDqz87JjMuuqeG41S7DSy82loNaGy+NyWSMJ4kpClkXiqlPd375dLhcAwOfz4YMPPsCpU6fw9ddfY//+/di8eTP69++PgwcP4tChQ/joo4/gcrl458Y6QtG6JFpR5NHFosVQ/l2M/BQ7SlFUiNYbhmhdstlsqFWrFurXr4/ExERYLBZ+ftYZGwwGVUuW/COWRf6/HCXrl7yM4nHkljHmhtbr9Tx4SO7aFI+n9L/SuZVEmbyO2V/RHczGUQKA2+3GlClTeKALK6t8DKncvSsvo/z+i/VWllVP6RrF9qLT6ULqKxAIoKioCGfPnsWpU6eQm5sLSZJCBJu8HsQXHLH9KlkeNRoNt1yzpPSi1VQUw/LfhLxelNo0Q2nqS7E+5XWvtl5ORV4kKkJZ1n6CqEmQWCSuCFdSEFb1uebNmwdJklBYWIgxY8Zg48aNGDFiBJo0acLn/e3RowdWrFiBoUOH8lQpDLFDVerE5JYz+XWwDpaJlbJEh1zYAKEWIZvNhoSEBCQlJcFsNqO4uBgFBQXw+XzQaDR8HJ7YucuFl5IbUI6SlVMuhJSsanI3pXjtLLchGwsnn+1EqS7Kqyfxf7mbn/2ViyVWN8x6yKx0WVlZ/P4wwa0UuKFkCWbHFlMkieVh9aCUekZ+fXKXrlycMfx+P/Ly8nDmzBn8/fffyMnJgcfj4eVguRPZC4344qNWFnZ+cT8R8ThyS6rcgikXoHIRqyYgWZ2ILxzisopwuQRedX8xJgg1SCwSV52qfjCrCQfxrxriduw4/fv3h0ajwZIlSxAWFoYRI0ZwMcam+du6dWtIombRAsWOx/YRP6JrTRR4YhnUpgmUX6/YQSpN18c6cRaEkZOTg3PnziE3Nxder5eXRz7GjF2PkmVGbn1k2ypZ1MTOXkn0ytfJz8USMweDQRQWFsLj8YRcn5yyxIRS/cn/F5FbH0XrYSAQgMfjwc8//8zXi4JbrZ7kxxfFEVumViY1ISwXiOJ9F6cTZG1EkiQUFRUhKysL586dQ1FREd+G5WX0er0hwlE+H7O8TIFAAC6XC/n5+SgsLOQz78hFoJjCh7VzNQu80kuKWEfloWYJv1jIYkhcb9CYReKKcCUerGWNDbqU83/++ed44okn0KZNG+zduxfABbdjUlISd9f27NkTJpMJp0+f5gEjYgJhUWiIU6uJIkKpzGKwg1JCbHFbUQCw9WKHHAwGkZ+fj5MnT8JsNiM3Nxd5eXl8ujd5RKp4TKVEx0piRsl1y44hdv5KQrosJEni4hwAF4rirC5q+6ktV3NLKt2TgoICuN1uJCQkwOl0cle4RqOBz+fD7t27MXLkSD7eTnTjy48p3ncxWbe8HBUVifJ95dZQdj+Z6GPtQXyZKC4u5mMZxaEOSsJVPL+SVZyJZzYOkVlZla5JrCNxbKeSRVv+Xc06LW9L8rq/GJTu5cVAApOoqZBYJK4rynpYiy5h8Xu7du2g0Whw8uRJ+P1+7Nu3D71790aHDh1CrGIrV66E0+lEw4YN+Vy2SilNlMSRXFDKZzERO2Im7ESRJE+zwsrEZs5gx2eWI51Ox125TNjKy6okTOT/K4kspfpmx5ELO7X7oSQAmdBm185EmShs1QSGXNxUluLiYuTl5aFly5a8DOxloKSkBMeOHUPDhg1LWWLVhKw86EVtO7X6VROYSvszF7TS7CxismzR3a90ToaSu17+ksGsmWp1Ib7UsHVyIc22V7Oqq70wlYVSeygPNUt+RbgUYUkQ1QlyQxPXDOUJQfFvWfuzv1u2bIHX60WfPn2g1WphMBjQo0cPhIWFoV69eti9ezff/s8//0R+fj569OjBk1EzyxNQeko9+TlFYSZa88QcdkpJmkVRKaY7kbv4xHN6PB4UFxdzi6LRaCwVjCG6ypXqVm45FK9NPr1fefUsHlMuBuR1piayy+uU1Sy3FXUnsntx+PBhnD17lg8fYKKob9++/JhK4kJtphO2XsnFWpbrVCy7vA2pbSMOe2B5C8X8heK1ilPpiZZwIDTgRrw+1q48Hk+I1VQ+flHepuTtXm5xl49plL9YlTVEg6Fmja2IVVvcvrKQUCSuFUgsEtWOylp+ytv+Yo8XHR0d0onGxsbCYrGgd+/eyMvLw4EDB/i2DocDvXv3RlhYGN+ezdzBjikXP3KrkdhBsnWsY5ckCV6vFy6XC263myfRZsdiFkR5bjxxHCITvMySKAoFJaGmFGVaVn0quW/VKOvalepLLlSA0ul6KmpVUiufknWSYTabERYWhuPHjyMrKyukzEwIlZSUYNmyZSHHYx8xKbZcLLJl8hcK+UuFmqBk1y7uKw+oYvdTdAuztiW6iQGUEmesfOKxxbGFfr8fxcXFyM3NRXZ2NgoKCviUfMFgkLdLhtJLgLzOlLZTqhPxnqrVnRoVFXIk+AiCxCJxDVDew1zuKqsoDRo04NZBjUaD5s2bQ6/XIyoqCsuXLwcA7N69G/v370ft2rVx6tQpPpZOqaMTl4nuZblwYB0wG/PFcjX6fD7uDs3Pz4fH4wmx2shdrSwNjslkChGMcqGoFGyiJDiU6lV+DRURbErRr2KkrVK0r1hvolCuCGWJW6XyKREeHo68vDzs2bOHi3DRcvb555/DYDAgNTWVH0NJdInWMiUxV5ZlUOkjL7fcGifWn5LVWn7/5el5xOMBoYnTRaGYn5+PvLw85OXl8Zlg2P0sS6SL16KUQqcswSi/Rnl7lIvJss5PEETZkFgkrikqakWsjLXxo48+4uO+XC4Xli5dinbt2gEA6tWrxxM0nz17FiUlJWVGAwOh1hmljkrclgk6cd/i4mJkZWUhLy8PRUVFPO2NKP5EQSAG26gJlLLcnHIxqFR3ohARXedqQkAUJEwAMhe7klWL1YHohpcLTqXyyJfJ15UnJNnfI0eOYMmSJcjLyyt1rpKSEqSnp6OkpAQrV64sJVBEgSZaIpUEkRplWdRE66Wa4JYjt2KWVZcirH35/X64XC4UFhbyiGd2bq/Xy7+LolRuiZX/HtgLknw5qz8gdCxreaJSqe4Igrg4SCwSVU5l3b5X4/wV6UDYce644w7eGVksFtx2222IjIwEAFgsFlitVvz44484c+YM309JkMg7SPEv20atc2VWRqPRyJcxa05xcTEkSQrJ7ad0bPFYavVQUXGoVJ9ycSSeW4zqrogFTSybGCDBxmWy5XKxW1GXudo2atvXrVsXEyZM4C8JDCZmYmJioNPp4PV6+VhGsVyiWJSnhFGqSzXxptaW1F5AlP6Xt0+1dDXy84jR8j6fDwUFBcjPz+djX5kFnAl/8T6JUz6yepO3Q7GNiO2GfVcTj2K7I2FIEJcHEotElVOZB3Z5lqqqOrdcOFWkXIzZs2eHdFpWq7VUpOagQYPw73//G1FRUSGWNXZueacrijr5ecWIX5YbLxgM8g551qxZKCkpwfPPPw+Xy4Xi4mIeyarUIYtJlNWEWXmiS61OldyCctHIhJ4kSSFWT9H6KY6dE0WJKF5Z3j8192pF76e8/Erbye+fXq+H3W7HgAED0Lx585A6ZtdltVphsVh4sJG8PuXWZnkdyi1qauvUXjTkdVzW/VJ6SZB/5GVg31kwi9vtht/vh16v59MeMuu2vO3KLcXyHKDyMindL9a+5EJSjMCW76v08nC1X2YJoiZCqXOIq45SxwWUdt9e7PHE5RXtKMRt//Wvf0Gj0eCFF17goi0lJQV3330376iMRiPmz5+PU6dO4f/+7/9gMBgUyyG6a+WIVhNJuuByFVOQMCHw0EMP4dVXX8XUqVP5mMWwsDCeVkc8j+jiA5SDK8QyiZ2xkptSPh6MlUm+rXyZmNtPXMf+KolnUcgya5bP5yv3hUD+f1nLykOSJJw8eRLz5s0DAPTu3RudOnUKETcvv/wyfD4f/vOf/+Cuu+7CO++8g8mTJ4eILfkLhFy0yMUSE0ZqAlN+DHGZKLbLqhvxvpdXN+zes5cPlrhbr9fzFFHHjh3DmjVrMHTo0JDhBcxtrdTulayo8rpg+7C2rtFoeBnEBOFiHZV3LQRBVA6yLBJXlbIe3NXloc461SeeeAKRkZF4/PHHMXLkyBCrCeu0HnroIXz88cc8+EQpXYoouMTOHQh1x4mdIQB8+eWXOHr0KN588008+OCDePfdd0Pm+hWPzRAFnTygRek65eJEzWWs9F1tO6VgC6XyKVkJWSAOm8tYDCASj10Zi5G8zEpCSlxWu3ZtPPXUU3jqqafQvn37EEuWRqPBtGnTYDAYMGPGDPz3v//l94RZQeUWUrF+lcot3n+ltDBK9VdWMI3StctFmigcxchoJcQXByYECwsLUVJSEpKIXrT2Kc3OIpZJqa2Jvx1JkkLEIqubyloJq8szhSBqGiQWiWpNVT3cK+tiVcJoNGLcuHFYvHgxTpw4gR9//BGSdCHgZMmSJXC5XACARx55hHdu4rmVchaqWYTYcuba02q1uOWWW7By5Urk5eXhjTfewL/+9S8EAoGQ+ZyV3JvsOGL0qyhg5duKQlYucOXf5R28XPSKwkLp/OJ+SqlwWHBOSUkJioqK4PV6QyyUotVU7dqVRJO8/pW+Kwmv1atXY8+ePfy6mAv28ccfx4QJE2CxWDBmzBhIksTzDcrLoiYAxfahNPZQLmTlwk/Jda10bvnQBLnQVLIos498TuiSkhJkZ2fjgw8+QFRUFAYOHAiDwQCz2RySu1O+n3ht8nYkCnh2n/1+P9xuNwKBgKJVXv7CJbe4VoYr4aYmVzhR0yCxWEOYNWsWWrZsCYfDAYfDgbS0NCxdupSv93g8mDhxIqKiomC32zF06FBkZmaGHOPkyZMYOHAgrFYrYmNjuRvzekDJvVWRfeTf7XY77rjjDpw/fx5utxu5ubnYtm0b2rRpg9GjR8NmswH4J7+ceG7R2sLEk7yDE4UamwvZYrHAZDIBAIYNG4YGDRogNjYWfr+f5/9j69U6ZVEcimMm5ePd1OpMLB/bRy76lKykYn5BcR5shri/aG0Sj8eEl8vlCnHVywNGxP0v5eVAzSJXVFSEgoICXlYWdGQymXjwDcvNWVhYiIyMDH5+UTSLgShK1kAxCEktulxJCCttIz+2mstXFIxKgk6+v5jSSavV4s477+RlFdssc1GLruuK1D+7fvYS5PP5+BSCSil/lI7BqIzVWb7v5YIsnERNg8RiDaFWrVp45ZVXsH37dmzbtg033XQTbr31VuzZswcAMHnyZPz4449YvHgx1q1bhzNnzmDIkCF8/0AggIEDB8Ln82HTpk349NNPMXfuXEyfPv1qXdJloSre2OWdqdgJ+/1+7N69Gzt37kRmZiYOHTqEunXrIi4uDkuWLEF+fj6OHDkCrVYLn88Xsp9YPqWxZaJYBBCSD9FqtcJms8FkMmHs2LGYNGkSbDYb7HY7rFYrd9WKORflFkS5UJS7fpWEiFx4yutXfg4xmhv4Jy+i6E4X61jtnjExzeqRpQgSty9L2IjnudiOWbwXhYWF+OOPP3Dq1Cl+XeL0eOya77jjDgDAuXPnsHfvXr6NeEylcYisrCyKWLyHlbHwqglQpZQ6SsdXsgjLxZZOp4PJZILdbofFYuFR+jabDWFhYbBarTCZTDCbzbBYLCEzGYnDBphlWP5Sw+oXAHdrezwefv+V5hVXusfydk3WPIK4eCjApYYwaNCgkO8vvfQSZs2ahS1btqBWrVr4+OOPsWDBAtx0000AgDlz5qBJkybYsmULOnXqhOXLl2Pv3r1YuXIl4uLi0Lp1a7zwwgt44okn8Oyzz8JoNF6Ny6p2KHU8Ykfj9/uRl5eHXr16YefOnWjRogXOnDkDs9mM5s2bw2g04s8//0Rubi7CwsK4JYQFq6iNO2Mw4SWPbjYYDAgLC+MuOXYMJlTYeZTcw0puYvl3NRen0r5qna5oFZVbC5VESVnHYvkhJUmCy+Xic1qL49f27t2Lpk2bKgqGqrbcFBYWIjIyEn379oXT6QwR0mwsqNvtxsGDB9GyZUskJCSgTp06cLvdIeJZLpLEOhDFnHzIglzgyWF1oJR+hu2vNnZUbpEU75n8+OwjDn1g18+EHbMusuET7HpYu5UH7sjPx8rAxtkGAgG43W7u1tdoNGXmklQTjwRBXDxkWayBBAIBfPHFFyguLkZaWhq2b9+OkpIS9O7dm2+TmpqK2rVrY/PmzQCAzZs3o0WLFoiLi+PbpKeno6CggFsnlfB6vSgoKAj51HTK6khEgaQ07slsNqN79+78+/HjxxEWFobExER069YNdrsdZrMZxcXFfCYL1mkqdeLiecVOU2kMlslkgs1m4ylazGYz77Dl6WgY8k5eHK8mt5rKXZqilVBunZRbm5TcwKJbUj6lXHlWHmatCgaDKCgoQGFhIRfQ69evh0aj4SmDlMp/Mcjvu3iNiYmJaNasGZo0aYLExETs2LEDeXl5CAQC/P6uWbMGq1atQkFBAXbu3IkTJ05gz5493CIm1otoBZRb8tjwAzbNo/yayrpngPqUiOL1yM+rdN1yK6P8fPL7K04lKbrOtdoL00wajUYulMUAHgY7rphhQK/X82eQx+MJeQmRi8Wy2hRZFQni0iCxWIP466+/YLfbYTKZMGHCBHz77bdo2rQpMjIyYDQa4XQ6Q7aPi4vj46YyMjJChCJbz9apMWPGDISHh/NPcnJy1V5UFaPWsV7KMZYuXcoDKb7//nusWbMmpENj1hO9Xo+1a9fCaDSiS5cu+OGHH3gHx8Z3MeRj0sROXRyPJ7c6sun7zGYzzGYzHxcmdthq0c7y4AYldyWrM6WPXEirWbnYsZjViZWPicXyRJ0YkevxeFBcXAyv18vP5XQ6YTQa0aFDB16PFyMSlQSv0jY5OTnYtm0bjh49ih9++AGnT5/muTaZtdNkMiEmJga9evVCQUEBdu/eDb1ej0OHDuHgwYOKQlp+j1l9MbEojgVVeoGRu5aVXNziRy785WJQrHslS7C4DfuIAlE8r9jWlF6CmGWWvQCw5aJllbmv3W43f1lgAlrpGuUoeQgIgrg4SCzWIBo3bow///wTW7duxYMPPogxY8Zg7969l/Wc06ZNQ35+Pv+wMVs1hfLcnRXZv3HjxrxDq1u3Lvbv34/4+HjEx8fjzJkz3C25bt06JCYm4vDhw/D5fNi5cye3fonWFrHjF8f6iZYYefAGW87cs0ajkQtFJsaYhYt91MYmitZHtfFrclGilPKkLDHC9hWXi+5B+T5iWVhd+Xw+FBYWoqioiLvZAaBVq1YAEOKqVxMM5d1bJQEhd/1arVbUqlULERERaNKkCcLCwtCwYUNeRo3mwsw+HTp0QHJyMn777Td069YNkZGRSE1NhdlsVhyzqlR/cquc2jWpWRzVXjTYejXBKBedchEtij6xnOzlRWx/4nHlbVje1uV1AYDfaxYFX1hYiOLiYn5uUVCqWVnldUdCkSAuDRKLNQij0YgGDRqgbdu2mDFjBlq1aoWZM2ciPj4ePp8PeXl5IdtnZmYiPj4eABAfH18qOpp9Z9soYTKZeAQ2+1wuLqerqLKiUexc6tevzzununXrAgDy8vKQm5uL+vXrIxAIYMmSJUhJSUHr1q1x8uRJnhOOuc9E64s8wlUpElXuWhaFpFxUiMcRO3UlN6WaeJO7nOXubKXOWOnY8vLKBaFcHAEIKTMTH5IkobCwELm5udyqKNaBWtBCefe3suslSYLZbIbb7ca+ffvQsGFDhIWFQaO5EKHrdrv5NpIk4dtvv0WXLl2QmJiI/fv34/jx47BYLHyuZNGqJreKsjoRxbbSp6wgFfYRI67l1ydvV3LBKG+PYjnlLzisLbKPmC5HqT2XZ5lm5TWZTNDr9XC73SEuaK1WywOmlOpGbgEnCKJqILFYgwkGg/B6vWjbti0MBgNWrVrF1x04cAAnT55EWloaACAtLQ1//fUXzp07x7dZsWIFHA4HmjZtesXLrsSVeshf7Dk0Gg1sNhvuuusuuN1ueL1eOBwO+Hw+tGnTBs2bN4fdbsekSZOg0+kwadIkeDweFBUVAQi1irDvcguL2MkrWevkIg5AqY5dbilSGtfG/hc7frXIabmbXNxPSciUlYZHtEzK3eEGgwEWiwVarRYulwu5ubk82bNOp+OCnbn0lVK9lGdBqoiFSbRWMWrVqoUbbrgBGzZswJtvvolTp07hs88+Q25uLvx+Px8akJ+fj6ioKADg41a9Xi/y8/N5nkAla6jS0AC5hU/JJSyvX4Z8rKG4P/tfFHtKglP+AlBeuhq5cBVdzUpDHOQWbnYvmdWcJftmc5+LCejl91w8Z1n1dKUgsUpca1A0dA1h2rRp6N+/P2rXro3CwkIsWLAAa9euxbJlyxAeHo57770XU6ZMQWRkJBwOBx5++GGkpaWhU6dOAIC+ffuiadOmuPvuu/Haa68hIyMDTz31FCZOnMhz9BHlo9FcGEO1efNm3HHHHZAkCcuXL0erVq1Qu3ZtWK1WOJ1OuN1u2Gw2vPnmm5g+fTry8/Oxe/du9OvXr1QaGbVI4YrArGys81WyJInHVLIGqiF2wuKx2XfRUibuo3YNorCTj9FkiZy1Wi2Ki4uRk5OD/Px8+Hw+LFq0CKdPn8aECRO4y18eUVvZemPXUdY+4no2Ni8tLQ0dOnSAwWCAy+WC2+2G2+2GyWRCZGQkHnnkEfz999+YN28eJEnCjTfeiKVLl6Jhw4bYvn07fD4fnn76aYSFhQEAH/coDzpSEopyN774V379cjEvWvGU7r9o+VUTdkptRcn1y4S9uL08pZO8vOw7G/+p1WpRWFiIvLw8Pg/1V199hbFjx/LtxJcPeV0p/Q7IFU0QFw+JxRrCuXPnMHr0aJw9exbh4eFo2bIlli1bhj59+gAA3njjDWi1WgwdOhRerxfp6el47733+P46nQ4//fQTHnzwQaSlpcFms2HMmDF4/vnnr9YlKXKpD3n59kpiqTKuaPF4knQhMfO3336L8ePHc8HE8gB+9NFHGDJkCAwGA6ZPn45p06Zh/PjxePXVVzFjxgwMHjwYknQhl54oeJTcqmLkMDuP0nUodfgM+fhCuZATBQgTfnLXOOv85dYa+bHl9SZ3YcutTuy6mKWQRUu7XC5kZ2fj/Pnz3KJ055138nmvdTpdyLRvlyoAlASYvNzi/8wS99lnn+H8+fP83tpsNpjNZjidTmg0GkydOjUkaOPLL7/E/v37YbPZUFRUBKvVykWVXMArjTmUt1u5pVdEbiVk90pM3SQeU2xLbDt5+yrLQqkkPuXnZ8dUG4/JjsGsnEVFRTh37hzPKOB0OnHfffehuLiYzzMtv1dieZSE6JWEhClxrUFisYbw8ccfl7nebDbj3Xffxbvvvqu6TZ06dbBkyZKqLtpl43K5ci72QS5JEhwOB+677z6cOHECX3zxBTp27Ait9kLi6OHDhyMmJgYAYLFYeMdVUlKC8+fPIywsDHa7HQAUx5PJOzn5OD+5RVJ+LWInL66Td6Byi5xS5y2el+3DRKsYbKJ0PNHqJ1p+mNBj1yZamFggQ15eHs6fP4/CwkKsXr0a27Ztw7Bhw1CvXj289957ePDBB/k5mRCpqo65rBcJubDR6XR44IEHsHDhQrhcLuTk5MDpdGL+/PlIS0vDypUrkZqaiuLiYtx4440YMWIEZs+ejTvuuAPTp0/H9OnTYbPZSolQ0TInDyiSu1zl4kwuOEVrsJo1We0lSs1iKd9WTbQpWaHly9l3to5FgXs8Hpw/fx55eXn8mlmu0hMnTuD3338vlXdWrawXw8VY+AniWkcj0S+CqAQFBQUIDw/Hk08+CbPZfLWLUy4VefCXZaGSW+TcbjfMZjO8Xi+sVis2btwIk8mEzMxM9O3bF2lpafB4PDh27BiKiorg8Xjw7rvvIiIiAo8++ihSUlJgNptDxnSxY8utWEppaZRceEoikqEmHuWIEcnieDAmXgDwvHjiWDPR3QmEWjPllsSSkhL4fD6+TWFhIex2O7TaCzkoi4uLkZeXxy2KzNo4f/589OrVC7GxsTy5uVrEb1UjWt4YknRh+kE2ti4nJweLFy/GK6+8Ap1Oh4yMDGRkZHC3us/ng06nw7x583DTTTdh/vz5sNvteOyxx+DxeBAXF8ctjSxQREkMKwl+NWuokpWY7SePIhavVQ2l9llWPYnlFK2bSvsAF4QiS0d0/vx5nD17lluTWW7XL774AiNHjqzUGNXKcL24qj0eD1555RXk5+df1oBF4tqCAlyIa5qKPPzL2kZc5/P5MHv2bOTl5fFgIpYk++abb4bD4eDzBzMRZLVaMX78eHi9XixatAi7du3CkSNHeEodNh0em+KNpSNRinQWO31REIgzaDBXrfi/KBDYMqWgGbUgFgZzGau5QOXWIxYUAfwjNNl1uVwuzJo1CxkZGcjLy+MJ310uF3djMxF5++23Izo6mrvvRfft5UZuKWN/V65ciby8PASDQSxevBj33Xcf8vPz+f38448/oNVqUVBQgBUrVuDvv//GmDFjsG7dOjidTkyYMAFFRUVYuHAhvF4viouLYTQa4ff7+UuGKMzFABOllEisbGW5k9nLiRj1LKKUfFu0cCol6AZKpwOSB0bJ25KY61Oj0fBpAYELL6NZWVn893H8+HGejP6uu+4qc+aWqrrXci6Xh4MgahJkWSQqRU2zLFYlfr8f3333HW6//XaeKJglNmcdSnR0NDZt2oTmzZtDr9ejqKiIW8H27NmDNWvWoF69emjbti3atGkDm83G0+qIwkAUXGpWFNFaxJCLB/k+Su5FJVGqFKkqFx3s3ErpUZhYKCkp4eLHbDZzS8b58+eRmZkJn88Hs9kMnU6HwsJCnDlzBgkJCXwbg8EAp9MZYj0ty5J6JWF1werAYDDA7XajefPmKCkpQU5ODjZu3IjCwkK0atUK+fn5SExMhE6nQyAQwJEjR1C/fn14vV6cOHECXbt2RX5+Pp+Zh829rGRNVrvH8vsvbiummxFFnLitUptQGr4gF4hA6JhIJXezaIVmwxFYnlA2jWZWVhYKCgp42/7yyy/Ru3dvxMbGlrJ6X4muq6pc0tXJakmWReJiIMsiQVQQvV6PYcOGAbjgQj116lRIp3X48GGsX78e8fHxOHLkCGJiYmAymXgnGhkZiWbNmqFTp044f/48jh49yq1TLPWKONMJs1IxSwxQ2nojD2ZQQy4M5MeTbydfxsrAgkuAUJe4aBll1+D3+5Gfn8/dsgUFBQgEAiEWxz/++AMejwc7duyA2+3GsWPH+PnOnj2LwsLCEAuXmgv0asDKwu5vUVER5syZA7fbDaPRiPDwcHTq1AlWqxWFhYXYv38/vF4vt/wuWrSI3/uGDRtizZo12LBhAzZu3Ihff/0VmZmZ+OOPP7B9+/YQgaxUH/Lxi/KPvL2I9SaOcVSySsuXiZZNsTxAqNVQnlBenM2HCWyv14vc3FycOnUKJ0+eRGFhIXfv7927F/fffz/++OOPUjkgaxrVRSgSxMVCAS4EUUkkSUJMTAxiYmJw6tQpnDhxAk2aNMGGDRtw8uRJWK1WjBs3Dnv27EF2djbq1auHQCDAxeDevXvRuHFjmM1mrFq1Ct26dQNwIUiJWRmVcsqJnaToplayAJVlbRKPJ6YgES1HojiRj52UW6XY8ViUKkuazJJqFxYWAgB2796NoqIibj0sKSnBuXPn4PV6sXjxYvTp0wedOnXi527ZsmWp61YSCle7I2ZWoy1btiA/Px9r165Fy5YtUVxcjKSkJHTu3BlutxtxcXHQaDTYsGEDAKBbt27Q6/UIBAI4duwYNm3aBIvFggMHDqBJkybIycnhAuvMmTPo0aMHtm3bxtNhiSIQKHv8odzyK7cwK7mURQueaFVWG1+rlF5HHhXv9XpRUlKC4uJi3k5cLhefpYdFlbtcLvzyyy9o27Yt+vXrx19GxGOJ5b1cbeBqty2CqC6QWCSIMijPfSQmNe7YsSOaN2+OVatW4YsvvkBycjIGDhyIyMhIZGdn830OHjyI06dPIz09HRs3bkRqaioAYPXq1bDb7Rg0aBCfwYLNjwuUtigpuRkBhIg49l2pU1USieI4RnGZvB6CwSC3evp8Pj7GDrjgrvf5fHC5XDh9+jROnz6NTp064fjx4wAAl8sFq9UKrVaLnj17QpIk9OzZs1R+vrLczdXFrScKKYPBAEmS4PP5kJubi5MnT+LAgQNo3LgxIiIiuEBiAr1z586lXLcNGzZEw4YNUb9+fZw5cwb169eH3W7Hjh07cO7cORQUFCAnJ6eUxY+1ByXrn9xaXFZ7qMx3NtxA/jIht4wzi7Tf7+fjM30+HyRJQmZmJk6dOoUmTZrwtu7xeOD1etGjRw+43e5SKYbk9746tAOCuNYhsUgQZVBeR5SYmIjExEQAQGRkJDQaDSIiIrBo0SJ07twZbdq04R0mAKSmpuL06dM4dOgQfD4fOnfujOXLl2PIkCFYv349Ro4ciRMnTmDr1q24+eabuaWFzb0rt/gwxOASeaSs3EWpNPZM3E90b8pnh2HX4vP5uJWIfdiYOPZ/MBhETk4OF8Ht2rXD1q1b0bhxYy6YFi1ahNtvvx3t2rVTrX8lYVydYHWVlpaG+Ph4NGzYEADg9XqRnZ2NTp06wel0Yv369WjdujXS0tIwf/58nDx5EkOHDuX1GxkZiQ4dOgAANm3ahIYNG8JiscDv9+PAgQNo2bIlGjRogNOnT2Pbtm3o3bs3t0Cz+8+Sh3/zzTcYPny44hSOzCUsHyerdF1AaJsR82+KbaekpARer5dHMLM2wiyCzD3t9Xr5FInsuDk5Odi9ezdatmwJt9uNZcuWoVOnTmjTpg2AC1H0YnlIKBLElYfEIkFcAmKHyv5v0KABNBoNoqKi8Prrr+Phhx/m4xfNZjOioqIQGxuLhg0bIiEhAStXruTTB/7222/cssTyDbJxXmazmbuq2Ry8otWICVL5vM/APwJQDKBhHxapLBeEYgfPrEQej4dbicSACQD47LPPMGrUKMybNw9DhgzB8uXLMWDAAAwfPhx///03dDodGjduDJPJxCNhO3bsyOtPRMzNVx7VwcrI6rZBgwZcTNWtWxf16tXDxo0b0aRJE7Rv3x4REREIBoPo168fn5lk+fLl6Nu3L8LDw3m9sDmogQt1ceTIERiNRkiSBKPRiEaNGuHgwYPIysriAnPJkiVIS0vDihUrcOONNyI3N5fvL1oBNZoLEfQWi4W3JTECX2kIA2s/8jmtWToksW2w9sVeJkTrJ7MosmNaLBa0atUqZEhEy5YteT5SpeTv5d3r6tAeCOJag8QiQVwCoshZvHgxMjIycN999+H+++/He++9B5fLhbNnz8Ln82Hfvn3o06cPhgwZApfLha+++gqdO3fG6NGjMWvWLHi9XvTs2RN5eXmYP38+kpKScOutt8LtdnM3J/sYjUYYDAbe8bMp0gDw5WKnLiYBZwKRuYv9fj93KQP/BCmw/cTp6ESBKI6Z02g0OHPmDGbNmoWRI0ciEAhg165d0Gg0GDJkCI4dO4aMjAwkJydj8eLFOHv2LABg0qRJXPiKFszyIp6rm3VJFCjnzp3D1q1bkZKSgrVr1yItLY2Ls7lz5+Luu+9GkyZN4HK58NFHH2HYsGEICwvD7t27cfz4cbRv3x5RUVFYvHgxMjMzMX78eEyYMAGSJPH9ExIScODAARQWFvI5x7t06QK73Y7+/ftjwYIFKCkpwUMPPRRSRnGYgcvl4tZFZoFUGwPL9mPRyZGRkfD5fHC73QgGg3zs5b59+3D27Fl069YtZJwheyEJBAL46KOP8MADDyAjIwO///47brnlFmzduhUOhwMnT57k4pcJZ1aW6mhVJojrBUqdQ1SKy5U6p6ZaA8QOjI3bs1qtkCQJzz33HOx2Ox5//HFkZGTg4MGDuOeee6DRaPD111+jVq1aqFu3LgDweZC1Wi1mzpwJu92OcePGwWQy8Xr55ptv0KNHDyT8f+3de3QU5fkH8O9ukl0SwmYTcjchIpcg5GKLSKP9gafcRcRClSJVqggFwVqxKPFYb7XCES2oVVpsFf9QqFqRA9UiEBKrhgiUGCSSAwEE24QImIsJue2+vz84M85uZnZnk83ObPh+zsk52Z3LPvPOJPPse5u0NI/aGqvVivr6ehQXF2Pu3LkeNURSAvb8889j8eLFcr86KUFU1hJ6T8Wzdu1aLFu2DC+99BLuvPNObN++HbfffrtcC+Q9UEIapBAdHQ2XyyX3Nzt+/DjOnDmD8ePHw2az4bXXXsPUqVMxcOBA9O/fHy6XCy+//DLuuecej9HWvsrabNeK8vqVamcjIyPR0dGBPXv2YMSIERg6dChefPFF3HvvvXA4HLBarejo6JDn5Pz888/lcmpvb0dDQ4M8+bvb7cZzzz0nP8tdaoq+6aab5GRbOi8RERFyEif9jUpzXErnVnm+ldT6M0q1khbLxfkxbTYb/vSnP+FXv/oV1q1bh+XLl8u1ni0tLfIIb+UXCuWXldbWVsTExMifITW1Axeb7qXP9O4WQcHBqXOoO5gsUkB6c57FcE0YAc/YrVYrnn76aTz44IMALpbZ9u3bcccdd8But6O0tBSXX3458vPzYbFY8OKLL2LZsmXydDNNTU1obm5GZWUljhw5gptuugkWi0Uebaxsfn722WexcuVKuRnae8oUAPIgFOWTQQD1hEGqqVy7di3uvvtuREVFobm5GRs3bsR9992HyMhI7Nu3D42NjRg3bhzcbjdeeeUVzJ49G3FxcXC73VizZg0KCwthsVjw1VdfoaKiAjfffLP8+UIIua+dlLS2trZ26WspUdYqKZNgM1FLsKRYpfPy6quvYvbs2XA6nR7nUHrMnfdIeGlASHt7O5566iksX74cLS0tePbZZ5GZmYl58+YhIiICu3btQkpKCnJzc2GxWLBu3TosW7YMNpsN7e3tePXVV7F06VIAQHl5OZqamnDttddCCIFXXnkFt956K5xOJwBgzZo1WLFihXxcyi8Q//jHPzBmzBhcdtllcLlcWLduHVasWCE/ZWXr1q2YO3euvL6y2Vv60iIlnspnREvHqdY31YznOtwxWaTuYDM0mUY43xS8m0VXrlwJ4OJN0+Fw4Be/+IXcZ6u+vh61tbVIT0+HxWLBXXfdBQByTeFbb72FBQsWICkpCT/+8Y/R0tKC1tZWed/KUcdNTU0oLCyUEwzg+8mRrVYr5s+fj8zMTDz33HO4cOECgIsTId95553YsWOHXFNYXFyM5ORkVFZWYtKkSfKj6KSaS2lOvI6ODlx55ZXyFDkWiwULFizwGInbv39/2O12REREYPjw4fJobyl+KTmUBkJIgyLUytLXNC9mp0yOAODuu+/uklS63W60trbK51eaY1BKHvv374/Y2FgMHDhQforN6tWrAXw/8OOGG27o0n9U2Vfw7rvvlrsySNeSci7E9vZ2tLe3y184pMcTVldX49ChQ7jxxhvlLytSDWBkZCQefPBBj9HJ0sAZ5VQ6UsKoXK+jo0N+Uo/3uZbKJlzOMdGlgjWLFJBL+QkuengnAxcuXMDmzZsxZcoU7N+/HzNnzoTVasU///lP5OXlYffu3bjlllvkJ7m0tbUhOjoab775JrKzszF79mx5EIF0s1aOPm5ubsZf/vIXLFmyRI5h7969sNvtGD16dJcktrOzE2vXrkV8fDwWLFgA4Ptm5+3btyM3Nxe7d+/GnDlzsGHDBvz617+GxWJBQ0MDtm3bhuuuuw7V1dWYMmWKRzIAXEx2X3jhBdx7773YsGEDZs2ahV27duGWW26R+6wBnqOtlWWlt0y13jM7KfFtbm6Wm2GVyfDhw4dx9uxZdHR0ICsrCzk5OXLSKNXQtba2elxPN910E4QQ2Lp1K0aNGoWMjAy4XC48+eSTePDBB+F2u+Vzd+211+LLL79EZGQkEhMTcfLkSVx33XV477330NjYKCf+mzZtws9+9jMUFRUhOzsbRUVFsFqtmDlzJvbv34/p06fD6XTKT61pa2vDG2+8gQULFnSpYZcGugCeg1WUTcta5zLQ90kf1ixSdzBZpIAwWfRN2fyoNt2L8s9NSrK+/fZbJCUlQQiB9evXY86cOUhNTUW/fv3kpErq19bQ0IABAwbI/cCkRFI5ebdy1KoyQVOqr6+Xm0OlGJV9Bevr65GcnCwPnjh//jxsNhuio6PR2NiImJgYxMbGoqmpCe3t7XA6nfK6ygExyuZH6VjUmpID7YIQrgmDxWLBhg0bsHDhwi4TVku1c8puAlJ5ffvtt0hJSekyj2JUVJQ8UKVfv35yOb788stYuHAhXC4X6uvrER8fDwDYt28fduzYgRtvvBE5OTloaGiQry23242nnnoKDz/8MCIiInDixAmUl5dj1qxZsFgsaGxslEdQeyf80uAV72lulE3QyjJQHrfyPT3XhJn7roYDJovUHXzcH1EQafW78qbsV7hjxw60tLTA5XJhwYIF2L17N7777jscPXoURUVF2LZtG+rq6lBXV4cNGzagtrYW7e3tACCPsh0wYAAcDgccDgecTicGDhyIhIQEJCQkID4+Hk6nE3FxcXA6nbDb7di3bx8GDBiA2NhYOBwOxMbGIi4uDi0tLbDb7fjkk09gt9sRHR2NiIgIfPjhhygtLUVdXR22bduGqqoquFwu/Pvf/8amTZtw9uxZtLS0yM2cUk2isvlRWRbKvpdqZeTdbzEcmqO1Rut6v79o0SKP6WikdZQjwqXHIkrHvW3bNnmOwubmZjQ2NqKxsRH19fX45JNPcPjwYbS0tMhTMN11113yfvbs2SMnl06nEzNmzMCgQYPQ2dmJTz/9FJ2dnfIo+6FDhyIyMhJnz55FbGwskpKS5Dj27duHs2fPyl8EpMnYpZ/29nb5C4ryOLy/qHhfC9Lv/hJD73XNdv6J+jLWLFJAWLPon6+aD++pQKTXlZWVuPLKK2G1WtHW1oaysjIcOXIEOTk56OjoQGJiIjIyMvDZZ58hJSUFV111lVzDI03YLO1P+Qg4tc+Uah4l0mCDzs5OFBUVIT8/HwMGDJBrG6XERXnzP3PmDCIjIxEfH6/ax9A7afYe+CHF451MqsWs9Tpc/nX5+9KgXKaWHKldM83NzTh37hwyMzNV162srMSIESNgs9m6LP/mm2/w+eefIycnB2lpaR77d7vdqKioQF1dHSZNmuSR0Lrdbhw/fhyXXXYZoqKiuhyT2rntiXA6x+GENYvUHRzgQhRkWgmQ2nqSr7/+GldeeaWckDU1NSEzMxMOhwM2mw3V1dVITk7GpEmTUFJSIjc9d3Z24uTJkxg8eLB8o1aONAUu3nQPHDiA0aNHY//+/bj66qtV+/8dPXoUw4cPl5s2pRjVagfr6+vRr18/eRStVpKgHMXsfcxqNUxqZaMs02ALRULia/++jtM7wVY26V64cAHffPMNMjIyuowUB4DTp08jOzvbYyoaab26ujoMHjwY8fHxaG1tlQfhSF8Y6urqMH78eHlb5fZ1dXVISkqSB7J4x66VEOvpl6pWFkRkDqxZpICwZrFnfPXXkt5TS7C8a23U9nH+/HnU1NRg1KhRXT63rKwMY8aMQVlZGa699touy4UQqKqqQnJyMhISEjz2rfZ5asejto5WgheMWqdg7ccs/wK9z7f0u/dyidr1o7dcpOVlZWW46qqr5AE3yuXK8x/qfoJ9vV+ikdcdaxapO1izSBRC3rVFvpIv5aAH5bbe60rv22w2OBwO1aZa6akYP/rRj7o821eSnZ2tmaSo9TtUi0nreHvKuyk7WDWNZkhE/CXcvt5Tvq/VN1TttfT7wIEDAcCjW4JWIuPrS4uv7Xwt85c0meH89Ia+elzUdzFZJAoCfzdKoGuSpdXcCHSdZkRtf8rXFsvFEdP9+/fXHVegyZ+vPoa9TStGM9UMdlew4vc+N76uO2nZsGHDPNZRu7bUYgwkmfW1LND3g6kvXDtEocJkkSjIvG9CempUlINCfNWY+RpA4KuZUrm+Wu2QWu2hnuRWz/EFq8mY/NOT+Pu7xnztI9BEXc/gJb3Lgo3XI5F+TBaJgiCQplmtdbybCNWSLX/bqX2OnqRULTnszjForeedjGo1dwdyA+fNXj+1/pBqy6TXehL9nlwjvj7L+3e9n0VEvYfJIlEI+Oo7pva+WoLory+Zcj++YtAbr/d+9X6O2vJgJp/hpKdNnd2pafM3qEjZXO1rcEwwa/n8feHx/hy1hLYvXh9E4YLJIlEvUGuKVtau6Um2Aql1896/VjIghOdTQrRiUm7rnTQE46bdV2/8WjVl3eUv+e9JEu7vWuzpOdIaFKXnM9Rqvo3AJJXoIiaLdMnqzRtBT5rt1OLS27/L++astp3b7faYtFur+dnXMfAm6l9vl09PkjzvREzPF5lAkrdgJcpGX2e8xokuYrJIlyyz3ggCjUtPX0floBZ/TXx6ahLNWnZGC4dysVgsXZ7VrDXoSfk6kBrTYJVDT/q0ElHwMFkkCkN65rRTq530vtFLj/HzXk+5L1/vcaSzp0ATmlAnQL76vertZ2rEuWaiSGQsq9EBEFHgvG+cWiNcvbdRPusXgPxaq/nRX7OkcuCLnhj6ukATmlAnQGrXjXfNohnPJRNFImMxWSTqJd25wXrfuPXy7mvYndHKPUkQ1AbkkLlpNTMHUstIRJcGJotEvUQtAdOzTTCmSVHbr6/P0KqJ1Hrfe59a6zBpDEx3v2B0Z13ldcBkkIh8YbJI1Iu6exPWu11P9q82XY7e/esd2c0kRL/uJtaB1Oh2Z7ASE34i4gAXohAwYwd9t9vdqxMxU2CMnL/S33Q5Zrx+iSh0WLNI1MuCXTMT6P58re+v9q87/Scp/JhhUIva5/PaIzIH1iwS9TK9NTKB1N4E+nQLrbkUtbbvKzdp1ohdFMj5NqofIwdIEZkXk0Uik9A7AXGgg0e09mO1WnWNiu5p0hDs/XX3c83AqOTV39NQujMYq7eY4TF/ROSJzdBEJqKnz6DWo9m0bva+mvd8PTKwJ9RG3YZ6wIsZB9gYHU9PEkJf15dZEs3uCvf4iXobk8UwsX79euTl5cHhcMDhcKCgoAAffPCBvPz666/vMsHu4sWLPfZx6tQpTJ8+HTExMUhOTsaKFSvQ2dkZ6kOhHvKXSPaEnkf9+dueN97QClZ5q9VY65n3M9hJuVEJNa9bIm1shg4TGRkZWL16NYYNGwYhBF5//XXMnDkTBw8exKhRowAACxcuxJNPPilvExMTI//ucrkwffp0pKam4tNPP0VNTQ3uuOMOREVF4emnnw758fRVPR1N3JMpc/ROc6NMCvTMlRgIo2vOLjWBNGt7NzUrr1V/j240+kkzofg8JotE2pgshokZM2Z4vP7DH/6A9evXY+/evXKyGBMTg9TUVNXtP/zwQ1RWVmLXrl1ISUnBVVddhd///vd46KGH8Pjjj8Nms/X6MZC58Ckd4a+njxfk5Onf4/VPpI3N0GHI5XJh8+bNaG5uRkFBgfz+G2+8gcTEROTk5KCwsBAtLS3ystLSUuTm5iIlJUV+b8qUKWhsbMThw4c1P6utrQ2NjY0eP6TN6H5y3XlEX6jj7WuJSTgdT6CDR4y+nonIHFizGEYOHTqEgoICtLa2IjY2Flu2bMHIkSMBALfddhuysrKQnp6OiooKPPTQQ6iqqsK7774LAKitrfVIFAHIr2trazU/c9WqVXjiiSd66Ygo2PyNelVSWy8Uo3WZfBhHa8R9INcNEV16mCyGkezsbJSXl6OhoQHvvPMO5s+fj5KSEowcORKLFi2S18vNzUVaWhomTJiA6upqDBkypNufWVhYiOXLl8uvGxsbkZmZ2aPjoN6lt8bImzJZ4JNc9AvXMmI3BCLSi83QYcRms2Ho0KEYPXo0Vq1ahfz8fDz//POq644dOxYAcOzYMQBAamoqzpw547GO9FqrnyMA2O12eQS29EN9g79HvBlFa/Str1G5gWyjZ4RvMPTGk3uMPjdEdGlishjG3G432traVJeVl5cDANLS0gAABQUFOHToEOrq6uR1du7cCYfDITdlmx1vlMHlnTQZOWWJ97yP3u9rra987evHarXqWk/Pj6/YQsH72K1Wq3x8auvqOR7lusGMM5RlFOp5IP3tk8k99SVshg4ThYWFmDZtGgYNGoSmpia8+eabKC4uxo4dO1BdXY0333wTN9xwAwYOHIiKigrcf//9GDduHPLy8gAAkydPxsiRI3H77bfjmWeeQW1tLR555BEsXboUdrvd4KPTx4hkRq1pVsnXMrWJqZXvGz0Qxl+iGKr4Ap0Q3Ffzqb8y1nOc3ue8u2XTW+WnVV6BfJ6Zm5z19KX1Pr/eXzZ8dbPQ2lbv4wa9E2w9j8v0NTWRr/8rRGbBZDFM1NXV4Y477kBNTQ3i4uKQl5eHHTt2YNKkSTh9+jR27dqFdevWobm5GZmZmZg9ezYeeeQRefuIiAhs374dS5YsQUFBAfr374/58+d7zMtoFqHsaO8vGVQKZC42s/cH8zXpttlilQQyJ2RP5o8M9tNsgkXvPJrey/T+PQX7WIM516i/89vT892TGkA9X/7UEkx/CamebiJmuj6pb2OyGCb+9re/aS7LzMxESUmJ331kZWXh/fffD2ZYPaKnFqC39bRWy9f73bm5h5JZ4qDe1ZfOczD+L3QnGdW7LNjrBHM7op5gn0UyjNYcbvxnSERqzPy/gf0TqS9jskimpLf/UF/VF4850GPSGsVMZEZmTmSJeorJIpnepfhPOBTHHKwpZPTuI5CpevQOMLiU6S33cC+vcI+fqC9gn0WiMNCbfTh7ow9YT7dn9wT/9JZHuJdbuMdP1BcwWSQyud6qWeFNmHrCDFNAEVFoMFkkMrme3Ix5Q6dg8a7d5jVFdOlgn0WiPkxrxDmFL6P68PE6Irp0MVkk02MHd1K61K+HniZtl3r5EVHgmCwSUVjpCzVcRiZs4Vh+nDaJyFhMFsn0wvHmFk54Iw69nj5ijogolJgsEl3CQjEAhkmROrOUeTh8WWDfWyJjMVkk0kHvzTSUN92e3uSVk3L3Zty8yYeerzJXnu/unnezJ5dEFFycOocoyHpzAm2lQD9DLS5/j1UM50SvL0wbpPdaCuSa8/ckHT37CecyJaLAMVkk0sHMN8fuJqdSvzl/SaQZdOcYzXYM3RFoAhhoOfWFMiKi3sdmaKIgMqJvVU9rlKSYzZw4mDk2M/OuLQ6H/olEZD6sWSQKQ8FqYjV7jSIFxt/55Pklou5gskgUhnjTJyKiUGEzNBERERFpYrJIRERERJqYLBIRERGRJiaLRERERKSJySIRERERaWKySERERESamCwSERERkSYmi0RERESkickiEREREWliskhEREREmpgsEhEREZEmJotEREREpInJIhERERFpYrJIRERERJqYLBIRERGRJiaLRERERKSJySIRERERaWKySERERESamCxSt7z++utGh0BEREQhwGSRuuXWW281OgQiIiIKgUijA6DwIoQAAFitVrS2thocDRERBaKtrQ3A9//LifSwCF4xFIDjx49jyJAhRodBREQ9cPr0aWRkZBgdBoUJ1ixSQBISEgAAp06dQlxcnMHR6NfY2IjMzEycPn0aDofD6HACEq6xM+7QYtyhF46xCyHQ1NSE9PR0o0OhMMJkkQJitV7s5hoXFxc2/xyVHA5HWMYNhG/sjDu0GHfohVvs4fRFn8yBA1yIiIiISBOTRSIiIiLSxGSRAmK32/HYY4/BbrcbHUpAwjVuIHxjZ9yhxbhDL5xjJwoER0MTERERkSbWLBIRERGRJiaLRERERKSJySIRERERaWKySERERESamCwSERERkSYmixSQl156CZdffjn69euHsWPH4rPPPjM6JA+PP/44LBaLx8+IESPk5a2trVi6dCkGDhyI2NhYzJ49G2fOnAl5nB999BFmzJiB9PR0WCwWvPfeex7LhRB49NFHkZaWhujoaEycOBFHjx71WOf8+fOYN28eHA4HnE4nFixYgO+++87QuH/5y192Kf+pU6caHveqVaswZswYDBgwAMnJybj55ptRVVXlsY6ea+PUqVOYPn06YmJikJycjBUrVqCzs9PQuK+//vouZb548WJD416/fj3y8vLkJ5sUFBTggw8+kJebsaz1xG3GsiYKBSaLpNvf//53LF++HI899hj+85//ID8/H1OmTEFdXZ3RoXkYNWoUampq5J+PP/5YXnb//fdj27ZtePvtt1FSUoL//e9/mDVrVshjbG5uRn5+Pl566SXV5c888wxeeOEF/PnPf0ZZWRn69++PKVOmoLW1VV5n3rx5OHz4MHbu3Int27fjo48+wqJFiwyNGwCmTp3qUf6bNm3yWG5E3CUlJVi6dCn27t2LnTt3oqOjA5MnT0Zzc7O8jr9rw+VyYfr06Whvb8enn36K119/HRs3bsSjjz5qaNwAsHDhQo8yf+aZZwyNOyMjA6tXr8aBAwewf/9+/OQnP8HMmTNx+PBhAOYsaz1xA+Yra6KQEEQ6XXPNNWLp0qXya5fLJdLT08WqVasMjMrTY489JvLz81WX1dfXi6ioKPH222/L73355ZcCgCgtLQ1RhF0BEFu2bJFfu91ukZqaKtasWSO/V19fL+x2u9i0aZMQQojKykoBQOzbt09e54MPPhAWi0X897//NSRuIYSYP3++mDlzpuY2ZohbCCHq6uoEAFFSUiKE0HdtvP/++8JqtYra2lp5nfXr1wuHwyHa2toMiVsIIcaPHy/uu+8+zW3MELcQQsTHx4u//vWvYVPW3nELET5lTRRsrFkkXdrb23HgwAFMnDhRfs9qtWLixIkoLS01MLKujh49ivT0dFxxxRWYN28eTp06BQA4cOAAOjo6PI5hxIgRGDRokKmO4cSJE6itrfWIMy4uDmPHjpXjLC0thdPpxNVXXy2vM3HiRFitVpSVlYU8ZqXi4mIkJycjOzsbS5Yswblz5+RlZom7oaEBAJCQkABA37VRWlqK3NxcpKSkyOtMmTIFjY2NHjVPoYxb8sYbbyAxMRE5OTkoLCxES0uLvMzouF0uFzZv3ozm5mYUFBSETVl7xy0xc1kT9ZZIowOg8HD27Fm4XC6Pf4IAkJKSgiNHjhgUVVdjx47Fxo0bkZ2djZqaGjzxxBP4v//7P3zxxReora2FzWaD0+n02CYlJQW1tbXGBKxCikWtrKVltbW1SE5O9lgeGRmJhIQEQ49l6tSpmDVrFgYPHozq6mo8/PDDmDZtGkpLSxEREWGKuN1uN37zm9/guuuuQ05ODgDoujZqa2tVz4m0zIi4AeC2225DVlYW0tPTUVFRgYceeghVVVV49913DY370KFDKCgoQGtrK2JjY7FlyxaMHDkS5eXlpi5rrbgB85Y1UW9jskh9yrRp0+Tf8/LyMHbsWGRlZeGtt95CdHS0gZFdGn7+85/Lv+fm5iIvLw9DhgxBcXExJkyYYGBk31u6dCm++OILj76s4UArbmV/z9zcXKSlpWHChAmorq7GkCFDQh2mLDs7G+Xl5WhoaMA777yD+fPno6SkxLB49NKKe+TIkaYta6LexmZo0iUxMRERERFdRiyeOXMGqampBkXln9PpxPDhw3Hs2DGkpqaivb0d9fX1HuuY7RikWHyVdWpqapeBRZ2dnTh//rypjuWKK65AYmIijh07BsD4uJctW4bt27djz549yMjIkN/Xc22kpqaqnhNpmRFxqxk7diwAeJS5EXHbbDYMHToUo0ePxqpVq5Cfn4/nn3/e9GWtFbcas5Q1UW9jski62Gw2jB49Grt375bfc7vd2L17t0d/HrP57rvvUF1djbS0NIwePRpRUVEex1BVVYVTp06Z6hgGDx6M1NRUjzgbGxtRVlYmx1lQUID6+nocOHBAXqeoqAhut1u+gZnB119/jXPnziEtLQ2AcXELIbBs2TJs2bIFRUVFGDx4sMdyPddGQUEBDh065JHs7ty5Ew6HQ26mDHXcasrLywHAo8xDHbcat9uNtrY205a1v7jVmLWsiYLO6BE2FD42b94s7Ha72Lhxo6isrBSLFi0STqfTY+Sf0R544AFRXFwsTpw4IT755BMxceJEkZiYKOrq6oQQQixevFgMGjRIFBUVif3794uCggJRUFAQ8jibmprEwYMHxcGDBwUA8cc//lEcPHhQfPXVV0IIIVavXi2cTqfYunWrqKioEDNnzhSDBw8WFy5ckPcxdepU8YMf/ECUlZWJjz/+WAwbNkzMnTvXsLibmprEb3/7W1FaWipOnDghdu3aJX74wx+KYcOGidbWVkPjXrJkiYiLixPFxcWipqZG/mlpaZHX8XdtdHZ2ipycHDF58mRRXl4u/vWvf4mkpCRRWFhoWNzHjh0TTz75pNi/f784ceKE2Lp1q7jiiivEuHHjDI175cqVoqSkRJw4cUJUVFSIlStXCovFIj788EMhhDnL2l/cZi1rolBgskgBefHFF8WgQYOEzWYT11xzjdi7d6/RIXmYM2eOSEtLEzabTVx22WVizpw54tixY/LyCxcuiHvuuUfEx8eLmJgY8dOf/lTU1NSEPM49e/YIAF1+5s+fL4S4OH3O7373O5GSkiLsdruYMGGCqKqq8tjHuXPnxNy5c0VsbKxwOBzizjvvFE1NTYbF3dLSIiZPniySkpJEVFSUyMrKEgsXLuzyZcKIuNViBiBee+01eR0918bJkyfFtGnTRHR0tEhMTBQPPPCA6OjoMCzuU6dOiXHjxomEhARht9vF0KFDxYoVK0RDQ4Ohcd91110iKytL2Gw2kZSUJCZMmCAnikKYs6z9xW3WsiYKBYsQQoSuHpOIiIiIwgn7LBIRERGRJiaLRERERKSJySIRERERaWKySERERESamCwSERERkSYmi0RERESkickiEREREWliskhEREREmpgsEhEREZEmJotEREREpInJIhERERFp+n93Anlp0EaEfwAAAABJRU5ErkJggg==\n"},"metadata":{}}],"source":["# model = 'model(Baseline 125 Epoch).h5'\n","# model = 'model(2D UNet, 9 Patients, Tibia).h5'\n","# model = 'model(2D-UNet, 5 Patients, Tibia, 256x256x1).h5'\n","# model = 'model(2D-UNet, 3 Patients, Tibia, 400x400x1).h5'\n","model = 'model(2D, nnUNet).h5'\n","pred_img_idx = 50\n","MaskStack2D = False\n","\n","from writeout_dataset import ReadInDatasets, ReadInDatasetNPY\n","# imgs_test = ReadInDatasets('/content/drive/MyDrive/Colab Notebooks/Test_Data_Tibia(Collab Sample)', 0, 10)\n","# imgs_test_masks = ReadInDatasets('/content/drive/MyDrive/Colab Notebooks/Test_Masks_Tibia(Collab Sample)', 0, 10)\n","imgs_test = ReadInDatasetNPY('/content/drive/MyDrive/Colab Notebooks/Test_Data_Tibia(Collab Sample)')\n","imgs_test_masks = ReadInDatasetNPY('/content/drive/MyDrive/Colab Notebooks/Test_Masks_Tibia(Collab Sample)')\n","\n","# imgs_test_masks = (imgs_test_masks > 0).astype(np.uint8)\n","# testing_scans_processed = np.reshape(imgs_test, (len(imgs_test), 512, 512, 1))\n","# testing_masks_processed = np.reshape(imgs_test_masks, (len(imgs_test), 512, 512, 1))\n","print('imgs_test size (Scans): ', imgs_test.shape)\n","print('imgs_test_masks size (Masks): ', imgs_test_masks.shape)\n","\n","def superimpose_images(image1, image2):\n","    # Normalize the image intensities\n","    image1 = image1 / np.max(image1)\n","    image2 = image2 / np.max(image2)\n","\n","    alpha = 0.5  # Opacity of raw scan\n","    superimposed_image = alpha * image1 + (1 - alpha) * image2\n","    return superimposed_image\n","\n","def dice_coefficient(y_true, y_pred):\n","    intersection = np.sum(y_true * y_pred, axis=(1, 2, 3))\n","    union = np.sum(y_true, axis=(1, 2, 3)) + np.sum(y_pred, axis=(1, 2, 3))\n","    dice = (2.0 * intersection) / (union + 1e-7)  # Adding a small epsilon to avoid division by zero\n","    return dice\n","\n","print('-'*30)\n","print(f'Prediction Made Using Weights From Model: {model}')\n","print('-'*30)\n","\n","# Prediction\n","best_model = load_model(model)\n","# best_model = load_model(model, custom_objects={'dice_loss': dice_loss})\n","prediction = best_model.predict(np.reshape(imgs_test[pred_img_idx], (1,imgs_test.shape[1],imgs_test.shape[2],1)))\n","print('Testing Image Input Shape: ',imgs_test[pred_img_idx].shape)\n","# print('Prediction Mask Shape: ', prediction.shape)\n","print('\\n')\n","\n","# Evaluation\n","rounded_array  = np.round(prediction, decimals=3)\n","binary_pred = np.where(rounded_array != 0, 1, 0)\n","DSC = dice_coefficient((np.reshape(imgs_test_masks[pred_img_idx], (1,imgs_test_masks.shape[1],imgs_test_masks.shape[2],1))), binary_pred)\n","print('Dice Similarity Coefficient (DSC) Metric Value for Specified Slice: ', DSC)\n","\n","if (MaskStack2D == True):\n","  DSC_stack = []\n","  pred_stack = []\n","  for i in tqdm(range(len(imgs_test_masks)), desc=\"Evaluating DSC on Paitent Scan Stack\"):\n","    prediction_patient = best_model.predict(np.reshape(imgs_test[i], (1,imgs_test.shape[1],imgs_test.shape[2],1)))\n","    rounded_array  = np.round(prediction_patient, decimals=3)\n","    binary_pred_patient = np.where(rounded_array != 0, 1, 0)\n","    pred_stack.append(binary_pred_patient)\n","    DSC_patient = dice_coefficient((np.reshape(imgs_test_masks[i], (1,imgs_test_masks.shape[1],imgs_test_masks.shape[2],1))), binary_pred_patient)\n","    DSC_stack.append(DSC_patient)\n","  print('Average Dice Similarity Coefficient (DSC) Metric Value for Patient Scan Stack: ', np.mean(DSC_stack))\n","  np.save('ManualSegStack.npy', DSC_stack)\n","  print('\\n')\n","\n","# Visualisations\n","cmap_binary = 'white'\n","cmap_segmask = plt.cm.colors.ListedColormap(['black', cmap_binary])\n","bounds = [0, 0.5, 1]\n","norm = plt.cm.colors.BoundaryNorm(bounds, cmap_segmask.N)\n","fig, ax = plt.subplots()\n","ax.imshow(binary_pred[0, :, :, 0], cmap=cmap_segmask, norm=norm)\n","ax.axis('on')\n","plt.title('Model Outputted Segmentation Mask')\n","plt.show()\n","\n","fig, ax = plt.subplots()\n","ax.imshow(imgs_test_masks[pred_img_idx, :, :, 0], cmap='gray')\n","ax.axis('on')\n","plt.title('Groundtruth Mask')\n","plt.show()\n","\n","fig, ax = plt.subplots()\n","ax.imshow(imgs_test[pred_img_idx, :, :, 0], cmap='gray')\n","ax.axis('on')\n","plt.title('Raw Test Scan')\n","plt.show()\n","\n","cmap_binary = 'YlOrBr'\n","superimposed_image = superimpose_images(imgs_test_masks[pred_img_idx, :, :, 0], binary_pred[0, :, :, 0])\n","# Define the cropping ranges\n","x_start, x_end = 200, 400\n","y_start, y_end = 200, 400\n","cropped_image = superimposed_image[y_start:y_end, x_start:x_end]\n","fig, ax = plt.subplots()\n","cmap_superimposed = plt.cm.get_cmap(cmap_binary)\n","ax.imshow(cropped_image, cmap=cmap_superimposed, vmin=0, vmax=1)\n","ax.axis('on')\n","plt.title('Superimposed Prediction Mask (Orange) & Groundtruth Mask (Black)')\n","plt.show()\n","\n","fig, ax = plt.subplots()\n","superimposed_image = superimpose_images(imgs_test[pred_img_idx, :, :, 0], imgs_test_masks[pred_img_idx, :, :, 0])\n","ax.imshow(superimposed_image, cmap='gray')\n","ax.axis('on')\n","plt.title('Superimposed Raw Test Scan & Groundtruth Mask (Manually Segmented)')\n","plt.show()\n","\n","fig, ax = plt.subplots()\n","superimposed_image = superimpose_images(imgs_test[pred_img_idx, :, :, 0], binary_pred[0, :, :, 0])\n","ax.imshow(superimposed_image, cmap='gray')\n","ax.axis('on')\n","plt.title('Superimposed Raw Test Scan & Prediction Mask (Automatically Segmented)')\n","plt.show()\n","\n"]},{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":330,"status":"ok","timestamp":1689137095066,"user":{"displayName":"Asif Cheena","userId":"14143847646622962473"},"user_tz":-720},"id":"Ffuc-3G1VG3_","outputId":"6fc82505-3ec9-46f5-cb9f-e45ff0c16f45"},"outputs":[{"name":"stdout","output_type":"stream","text":["Dice Similarity Coefficient (DSC) Metric Value:  [1.43042052e-05]\n","\n","\n"]}],"source":["def dice_coefficient(y_true, y_pred):\n","    intersection = np.sum(y_true * y_pred, axis=(1, 2, 3))\n","    union = np.sum(y_true, axis=(1, 2, 3)) + np.sum(y_pred, axis=(1, 2, 3))\n","    dice = (2.0 * intersection) / (union + 1e-7)  # Adding a small epsilon to avoid division by zero\n","    return dice\n","\n","def assd(y_true, y_pred, spacing):\n","    surface_distances = surface_distance(y_true, y_pred, spacing)\n","    avg_surface_distance = np.mean(surface_distances)\n","    return avg_surface_distance\n","\n","def surface_distance(y_true, y_pred, spacing):\n","    true_surface = find_surface_points(y_true, spacing)\n","    pred_surface = find_surface_points(y_pred, spacing)\n","\n","    if true_surface.shape[0] == 0 or pred_surface.shape[0] == 0:\n","        raise ValueError(\"One or both surface point arrays are empty.\")\n","\n","    try:\n","        surface_distances_true_to_pred = directed_hausdorff(true_surface, pred_surface)[0]\n","        surface_distances_pred_to_true = directed_hausdorff(pred_surface, true_surface)[0]\n","        surface_distances = np.concatenate([surface_distances_true_to_pred, surface_distances_pred_to_true])\n","    except ValueError as e:\n","        print(\"Error occurred during Hausdorff distance calculation:\", e)\n","        raise\n","\n","    return surface_distances\n","\n","def find_surface_points(mask, spacing):\n","    mask_padded = np.pad(mask, 1, mode='constant')\n","    mask_padded_diff = np.diff(mask_padded.astype(int), axis=0)\n","\n","    surface_points = []\n","    for z in range(mask_padded_diff.shape[0]):\n","        surface_indices = np.where(mask_padded_diff[z] != 0)\n","        if len(surface_indices[0]) > 0:\n","            surface_points.extend(list(zip(surface_indices[0], surface_indices[1])))\n","\n","    surface_points = np.array(surface_points)\n","    surface_points_phys = surface_points * spacing\n","\n","    return surface_points_phys\n","\n","def volume_error(y_true, y_pred):\n","    true_volume = np.sum(y_true)\n","    pred_volume = np.sum(y_pred)\n","    volume_error = np.abs(true_volume - pred_volume) / true_volume\n","    return volume_error\n","\n","predictions_single_scan_binarized = np.reshape(predictions_single_scan_binarized,(1, 512, 512, 1))\n","DSC = dice_coefficient(testing_masks_processed, predictions_single_scan_binarized)\n","print('Dice Similarity Coefficient (DSC) Metric Value: ', DSC)\n","print('\\n')\n","\n","# VError = volume_error(testing_masks_processed, prediction)\n","# print('Volume Error (VError) Metric Value: ', VError)\n","# print('\\n')\n","\n","# spacing = 1\n","# ASSD = assd(testing_masks_processed, prediction, spacing)\n","# print('Average Symmetric Surface Distance (ASSD) Metric Value: ', ASSD)\n","# print('\\n')"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"7wSwJj5eVG4A"},"outputs":[],"source":["# from keras.models import Model\n","# from keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, Concatenate, BatchNormalization, Activation, Conv2DTranspose, concatenate\n","# from keras.layers.core import Dropout\n","# import tensorflow as tf\n","# # from tensorflow.keras.models import Model\n","# from keras.layers import *\n","# from keras.optimizers import Adam\n","# from sklearn.model_selection import train_test_split\n","# import numpy as np\n","\n","# # Define U-Net model\n","# def unet_model(input_shape):\n","#     inputs = Input(input_shape)\n","\n","#     # Encoder\n","#     conv1 = Conv2D(64, 3, activation='relu', padding='same')(inputs)\n","#     conv1 = Conv2D(64, 3, activation='relu', padding='same')(conv1)\n","#     pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)\n","\n","#     conv2 = Conv2D(128, 3, activation='relu', padding='same')(pool1)\n","#     conv2 = Conv2D(128, 3, activation='relu', padding='same')(conv2)\n","#     pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)\n","\n","#     conv3 = Conv2D(256, 3, activation='relu', padding='same')(pool2)\n","#     conv3 = Conv2D(256, 3, activation='relu', padding='same')(conv3)\n","#     pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)\n","\n","#     conv4 = Conv2D(512, 3, activation='relu', padding='same')(pool3)\n","#     conv4 = Conv2D(512, 3, activation='relu', padding='same')(conv4)\n","#     drop4 = Dropout(0.5)(conv4)\n","#     pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)\n","\n","#     # Bottleneck\n","#     conv5 = Conv2D(1024, 3, activation='relu', padding='same')(pool4)\n","#     conv5 = Conv2D(1024, 3, activation='relu', padding='same')(conv5)\n","#     drop5 = Dropout(0.5)(conv5)\n","\n","#     # Decoder\n","#     up6 = Conv2D(512, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(drop5))\n","#     merge6 = concatenate([drop4, up6], axis=3)\n","#     conv6 = Conv2D(512, 3, activation='relu', padding='same')(merge6)\n","#     conv6 = Conv2D(512, 3, activation='relu', padding='same')(conv6)\n","\n","#     up7 = Conv2D(256, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv6))\n","#     merge7 = concatenate([conv3, up7], axis=3)\n","#     conv7 = Conv2D(256, 3, activation='relu', padding='same')(merge7)\n","#     conv7 = Conv2D(256, 3, activation='relu', padding='same')(conv7)\n","\n","#     up8 = Conv2D(128, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv7))\n","#     merge8 = concatenate([conv2, up8], axis=3)\n","#     conv8 = Conv2D(128, 3, activation='relu', padding='same')(merge8)\n","#     conv8 = Conv2D(128, 3, activation='relu', padding='same')(conv8)\n","\n","#     up9 = Conv2D(64, 2, activation='relu', padding='same')(UpSampling2D(size=(2, 2))(conv8))\n","#     merge9 = concatenate([conv1, up9], axis=3)\n","#     conv9 = Conv2D(64, 3, activation='relu', padding='same')(merge9)\n","#     conv9 = Conv2D(64, 3, activation='relu', padding='same')(conv9)\n","\n","#     outputs = Conv2D(1, 1, activation='sigmoid')(conv9)\n","\n","#     model = Model(inputs=inputs, outputs=outputs)\n","\n","#     return model\n","\n","# # Dice Coefficient Loss Function\n","# def dice_coefficient(y_true, y_pred):\n","#     smooth = 1e-5\n","#     intersection = tf.reduce_sum(y_true * y_pred)\n","#     union = tf.reduce_sum(y_true) + tf.reduce_sum(y_pred)\n","#     dice = (2.0 * intersection + smooth) / (union + smooth)\n","#     return 1.0 - dice\n","\n","\n","# # Reformat image data structure\n","# training_scans_reshaped = np.concatenate(preprocessed_images, axis=0)\n","# training_scans = training_scans_reshaped.reshape((-1, 512, 512, 1))\n","# train_mask_tibia_labels_reshaped = np.concatenate(preprocessed_masks, axis=0)\n","# train_mask_tibia_labels = train_mask_tibia_labels_reshaped.reshape((-1, 512, 512, 1))\n","\n","# # Split the data into training and validation sets\\\n","# images_train, images_val, labels_train, labels_val = train_test_split(training_scans, train_mask_tibia_labels, test_size=0.2, random_state=0)\n","# unseen_scan_model = np.array(training_scans[2][100])\n","# images_train = images_train.astype('float32') / 255.0\n","# images_val = images_val.astype('float32') / 255.0\n","\n","# print(images_train.shape)\n","# print(labels_train.shape)\n","# print(images_train.dtype)\n","# print(labels_train.dtype)\n","# print(images_val.shape)\n","# print(labels_val.shape)\n","# print(images_val.dtype)\n","# print(labels_val.dtype)\n","# print(unseen_scan_model.shape)\n","\n","# # Expand dimensions for the channel (grayscale) dimension\n","# # images_train = np.expand_dims(images_train, axis=-1)\n","# # images_val = np.expand_dims(images_val, axis=-1)\n","# # labels_train = np.expand_dims(labels_train, axis=-1)\n","# # labels_val = np.expand_dims(labels_val, axis=-1)\n","\n","# # Create an instance of the U-Net model\n","# input_shape = (512, 512, 1)  # For grayscale images\n","\n","# # Create an instance of the U-Net model\n","# model = unet_model(input_shape)\n","\n","# # Compile the model\n","# # Binary Cross Entropy Loss Function\n","# model.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy'])\n","\n","# # Dice Coefficient Loss Function\n","# # model.compile(optimizer=Adam(), loss=dice_coefficient, metrics=['accuracy'])\n","\n","# # Train the model\n","# # Hyperparameter tuning -> batch_size\n","# model.fit(x=images_train, y=labels_train, batch_size=32, epochs=1, validation_data=(images_val, labels_val))\n","# # Evaluate the model\n","# loss, accuracy = model.evaluate(x=images_val, y=labels_val)\n","\n","# # Perform inference on new, unseen MRI scans\n","# predictions = model.predict(unseen_scan_model)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"rKIt44NrZt83"},"outputs":[],"source":["# # import tensorflow as tf\n","# # from tensorflow import keras\n","# # from keras.applications import MobileNetV2\n","# # from keras.models import Model\n","# # from keras.layers import Input, Conv2D, Conv2DTranspose, concatenate, Activation\n","\n","# # from keras.applications import VGG16\n","# # from keras.models import Model\n","# # from keras.layers import Input, Conv2D, MaxPooling2D, Dropout, concatenate, Conv2DTranspose, Activation\n","\n","# # def create_unet(input_shape, num_classes):\n","# #     # Load pre-trained VGG16 model with 'imagenet' weights\n","# #     base_model = VGG16(input_shape=(input_shape[0], input_shape[1], 1), include_top=False, weights='imagenet')\n","\n","# #     # Encoder (downsampling path)\n","# #     inputs = Input(input_shape)\n","# #     encoder_blocks = []\n","# #     x = inputs\n","\n","# #     for layer in base_model.layers:\n","# #         if 'conv' in layer.name:\n","# #             x = layer(x)\n","# #         elif 'block' in layer.name:\n","# #             encoder_blocks.append(x)\n","# #             x = MaxPooling2D(pool_size=(2, 2))(x)\n","\n","# #     # Decoder (upsampling path)\n","# #     encoder_blocks = encoder_blocks[::-1]  # Reverse the encoder blocks\n","# #     x = encoder_blocks[0]\n","\n","# #     for block in encoder_blocks[1:]:\n","# #         x = Conv2DTranspose(512, (2, 2), strides=(2, 2), padding='same')(x)\n","# #         x = concatenate([x, block], axis=-1)\n","# #         x = Conv2D(512, (3, 3), padding='same')(x)\n","# #         x = Activation('relu')(x)\n","# #         x = Conv2D(512, (3, 3), padding='same')(x)\n","# #         x = Activation('relu')(x)\n","\n","# #     x = Conv2DTranspose(256, (2, 2), strides=(2, 2), padding='same')(x)\n","# #     x = concatenate([x, encoder_blocks[-1]], axis=-1)\n","# #     x = Conv2D(256, (3, 3), padding='same')(x)\n","# #     x = Activation('relu')(x)\n","# #     x = Conv2D(256, (3, 3), padding='same')(x)\n","# #     x = Activation('relu')(x)\n","\n","# #     x = Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(x)\n","# #     x = concatenate([x, encoder_blocks[-2]], axis=-1)\n","# #     x = Conv2D(128, (3, 3), padding='same')(x)\n","# #     x = Activation('relu')(x)\n","# #     x = Conv2D(128, (3, 3), padding='same')(x)\n","# #     x = Activation('relu')(x)\n","\n","# #     x = Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(x)\n","# #     x = concatenate([x, encoder_blocks[-3]], axis=-1)\n","# #     x = Conv2D(64, (3, 3), padding='same')(x)\n","# #     x = Activation('relu')(x)\n","# #     x = Conv2D(64, (3, 3), padding='same')(x)\n","# #     x = Activation('relu')(x)\n","\n","# #     x = Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(x)\n","# #     x = concatenate([x, encoder_blocks[-4]], axis=-1)\n","# #     x = Conv2D(32, (3, 3), padding='same')(x)\n","# #     x = Activation('relu')(x)\n","# #     x = Conv2D(32, (3, 3), padding='same')(x)\n","# #     x = Activation('relu')(x)\n","\n","# #     # Output layer\n","# #     outputs = Conv2D(num_classes, (1, 1), activation='softmax')(x)\n","\n","# #     # Create the model\n","# #     model = Model(inputs=inputs, outputs=outputs)\n","\n","# #     return model\n","\n","# # def get_unet(scale = 1, dropout_rate = 0):\n","# #     inputs = keras.Input((512,512,1))\n","\n","# #     # Encoding Path of the UNet (32-64-128-256-512)\n","# #     conv1   = Conv2D(32*scale, (3, 3), padding=\"same\", activation='relu')(inputs)\n","# #     # conv1 = Conv2D(32*scale, 3, activation='relu', padding='same')(inputs)\n","# #     drop1   = Dropout(rate=dropout_rate)(conv1, training=True)\n","# #     max1    = MaxPooling2D((2, 2))(drop1)\n","\n","# #     conv2   = Conv2D(64*scale, (3, 3), padding=\"same\", activation='relu')(max1)\n","# #     drop2   = Dropout(rate=dropout_rate)(conv2, training=True)\n","# #     max2    = MaxPooling2D((2, 2))(drop2)\n","\n","# #     conv3   = Conv2D(128*scale, (3, 3), padding=\"same\", activation='relu')(max2)\n","# #     drop3   = Dropout(rate=dropout_rate)(conv3, training=True)\n","# #     max3    = MaxPooling2D((2, 2))(drop3)\n","\n","# #     conv4   = Conv2D(256*scale, (3, 3), padding=\"same\", activation='relu')(max3)\n","# #     drop4   = Dropout(rate=dropout_rate)(conv4, training=True)\n","# #     max4    = MaxPooling2D((2, 2))(drop4)\n","\n","# #     lat     = Conv2D(512*scale, (3, 3), padding=\"same\", activation='relu')(max4)\n","# #     drop5   = Dropout(rate=dropout_rate)(lat, training=True)\n","\n","# #     # Decoding Path of the UNet\n","# #     up1     = UpSampling2D((2, 2))(drop5)\n","# #     concat1 = concatenate([conv4, up1], axis=-1)\n","# #     conv5   = Conv2D(256*scale, (3, 3), padding=\"same\", activation='relu')(concat1)\n","# #     drop6   = Dropout(rate=dropout_rate)(conv5, training=True)\n","\n","# #     up2     = UpSampling2D((2, 2))(drop6)\n","# #     concat2 = concatenate([conv3, up2], axis=-1)\n","# #     conv6   = Conv2D(128*scale, (3, 3), padding=\"same\", activation='relu')(concat2)\n","# #     drop7   = Dropout(rate=dropout_rate)(conv6, training=True)\n","\n","# #     up3     = UpSampling2D((2, 2))(drop7)\n","# #     concat3 = concatenate([conv2, up3], axis=-1)\n","# #     conv7   = Conv2D(64*scale, (3, 3), padding=\"same\", activation='relu')(concat3)\n","# #     drop8   = Dropout(rate=dropout_rate)(conv7, training=True)\n","\n","# #     up4     = UpSampling2D((2, 2))(drop8)\n","# #     concat4 = concatenate([conv1, up4], axis=-1)\n","# #     conv8   = Conv2D(32*scale, (3, 3), padding=\"same\", activation='relu')(concat4)\n","# #     drop9   = Dropout(rate=dropout_rate)(conv8, training=True)\n","\n","# #     outputs = Conv2D(1, (1, 1), activation=\"softmax\")(drop9)\n","\n","# #     model   = Model(inputs, outputs)\n","\n","# #     return model\n","\n","# #   import numpy as np\n","# # import matplotlib.pyplot as plt\n","# # import tensorflow as tf\n","# # from tensorflow import keras\n","# # from keras.models import Model\n","# # from keras.layers import Input, Conv2D, MaxPooling2D, concatenate, Conv2DTranspose\n","# # from keras.applications import MobileNetV2\n","# # from keras.optimizers import Adam\n","\n","# # # Define the U-Net architecture\n","# # def UNet(input_shape, num_classes):\n","# #     base_model = MobileNetV2(weights='imagenet', include_top=False, input_shape=input_shape)\n","\n","# #     # Get the output layer from the pre-trained model\n","# #     base_output = base_model.get_layer('block_16_project_BN').output\n","\n","# #     # Contracting pathg\n","# #     c1 = Conv2D(64, 3, activation='relu', padding='same')(base_output)\n","# #     p1 = MaxPooling2D(pool_size=(2, 2))(c1)\n","# #     c2 = Conv2D(128, 3, activation='relu', padding='same')(p1)\n","# #     p2 = MaxPooling2D(pool_size=(2, 2))(c2)\n","# #     c3 = Conv2D(256, 3, activation='relu', padding='same')(p2)\n","# #     p3 = MaxPooling2D(pool_size=(2, 2))(c3)\n","# #     c4 = Conv2D(512, 3, activation='relu', padding='same')(p3)\n","# #     p4 = MaxPooling2D(pool_size=(2, 2))(c4)\n","\n","# #     # Bottom\n","# #     b = Conv2D(1024, 3, activation='relu', padding='same')(p4)\n","\n","# #     # Expanding path\n","# #     u4 = Conv2DTranspose(512, 2, strides=(2, 2), padding='same')(b)\n","# #     u4 = concatenate([u4, c4], axis=-1)\n","# #     c5 = Conv2D(512, 3, activation='relu', padding='same')(u4)\n","# #     u3 = Conv2DTranspose(256, 2, strides=(2, 2), padding='same')(c5)\n","# #     u3 = concatenate([u3, c3], axis=-1)\n","# #     c6 = Conv2D(256, 3, activation='relu', padding='same')(u3)\n","# #     u2 = Conv2DTranspose(128, 2, strides=(2, 2), padding='same')(c6)\n","# #     u2 = concatenate([u2, c2], axis=-1)\n","# #     c7 = Conv2D(128, 3, activation='relu', padding='same')(u2)\n","# #     u1 = Conv2DTranspose(64, 2, strides=(2, 2), padding='same')(c7)\n","# #     u1 = concatenate([u1, c1], axis=-1)\n","# #     c8 = Conv2D(64, 3, activation='relu', padding='same')(u1)\n","\n","# #     # Output\n","# #     outputs = Conv2D(num_classes, 1, activation='softmax')(c8)\n","\n","# #     # Create the U-Net model\n","# #     model = Model(inputs=base_model.input, outputs=outputs)\n","\n","# #     return model\n","\n","# # # Load pre-trained weights for the U-Net model\n","# # input_shape = (512, 512, 1)  # Replace with your input shape\n","# # num_classes = 2  # Replace with the number of segmentation classes\n","# # unet_model = UNet(input_shape, num_classes)\n","\n","# # # Load the pre-trained weights\n","# # weights_path = 'path_to_weights.h5'  # Replace with the actual path to the weights file\n","# # unet_model.load_weights(weights_path)\n","\n","# # # Visualize the segmentation results\n","# # input_image = np.random.randn(1, 512, 512, 1)  # Replace with your input image\n","# # predictions = unet_model.predict(input_image)\n","\n","# # # Assuming predictions.shape = (1, height, width, num_classes)\n","# # segmentation_mask = predictions[0]\n","# # predicted_class = np.argmax(segmentation_mask, axis=-1)\n","\n","# # # Plot the segmentation mask\n","# # plt.imshow(predicted_class, cmap='jet')\n","# # plt.colorbar()\n","# # plt.show()\n","\n","# print('-'*30)\n","# print('Loading and preprocessing train data...')\n","# print('-'*30)\n","\n","# images_train, images_val, labels_train, labels_val = train_test_split(imgs_train, imgs_mask_train, test_size=0.2, random_state=0)\n","# print('Training Image Input Shape: ', images_train.shape)\n","# print('Training Mask Input Shape: ', labels_train.shape)\n","# print('Validation Image Input Shape: ', images_val.shape)\n","# print('Validation Mask Input Shape: ', labels_val.shape)\n","\n","\n","# print('-'*30)\n","# print('Creating and compiling model...')\n","# print('-'*30)\n","\n","# # my_callbacks = [\n","# #     tf.keras.callbacks.EarlyStopping(patience=PATIENCE), # early stopping\n","# #     tf.keras.callbacks.ModelCheckpoint(filepath=MODEL_FNAME_PATTERN, save_best_only=True) # save the best based on validation\n","# # ]\n","\n","# input_shape = (512,512,1)\n","# model = unet_model(input_shape)\n","# # model.compile(optimizer='adam', loss='binary_crossentropy')\n","# model.compile(optimizer='adam', loss=dice_loss)\n","# checkpoint = ModelCheckpoint('DiceLoss(batch_size=4,epochs=50,train_size=50,aoi=tibia).h5', monitor='val_loss', save_best_only=True, mode='min')\n","# model.fit(x=images_train, y=labels_train, batch_size=4, epochs=50, validation_data=(images_val, labels_val), callbacks=[checkpoint])\n","# model.summary()\n","# # best_model = load_model('best_model.h5')\n","\n","# # unet = get_unet()\n","# # unet.compile(optimizer=OPTIMISER, loss=LOSS)\n","# # unet.fit(\n","# #     x=images_train,\n","# #     y=labels_train,\n","# #     validation_data=(images_val, labels_val),\n","# #     batch_size=BATCH_SIZE,\n","# #     epochs=N_EPOCHS,\n","# #     callbacks=my_callbacks,\n","# #     verbose=1)\n","\n","# # unet.summary()\n","\n","# # unet = get_unet()\n","# # unet.compile(optimizer=OPTIMISER, loss=LOSS)\n","# # unet.load_weights('model.h5')\n","\n","# # input_shape = (512, 512, 1)\n","# # num_classes = 2\n","# # num_epochs = 10\n","# # batch_size = 8\n","# # model = create_unet(input_shape, num_classes)\n","# # model.compile(optimizer=Adam(lr=1e-4), loss='categorical_crossentropy', metrics=['accuracy'])\n","# # model.fit(images_train, labels_train, validation_data=(images_val, labels_val), epochs=num_epochs, batch_size=batch_size)"]}],"metadata":{"colab":{"provenance":[],"machine_shape":"hm"},"kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.9.17"}},"nbformat":4,"nbformat_minor":0}