{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.9","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceType":"competition","sourceId":13451,"datasetId":654585,"databundleVersionId":1188070},{"sourceType":"datasetVersion","sourceId":2170623,"datasetId":1303051,"databundleVersionId":2211890}],"dockerImageVersionId":30068,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# Load Data\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:14:09.442774Z","iopub.execute_input":"2024-12-08T04:14:09.443119Z","iopub.status.idle":"2024-12-08T04:14:09.446821Z","shell.execute_reply.started":"2024-12-08T04:14:09.44309Z","shell.execute_reply":"2024-12-08T04:14:09.445801Z"}},"outputs":[],"execution_count":16},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport pydicom\nimport os\nimport collections\nfrom tqdm import tqdm_notebook as tqdm\nfrom datetime import datetime\nfrom math import ceil, floor, log\nimport cv2\nimport keras\nimport sys\nfrom sklearn.model_selection import ShuffleSplit\nimport matplotlib.pyplot as plt\nimport PIL\nimport tensorflow as tf\nimport pathlib\nfrom tensorflow import keras\nfrom PIL import Image\nfrom glob import glob\nfrom keras.models import *\nfrom keras.layers import *\nfrom keras.optimizers import *\nfrom keras.applications import *\nfrom keras.applications.vgg16 import VGG16\nfrom keras.applications.inception_v3 import InceptionV3\nfrom keras.applications.xception import Xception\nfrom keras.applications import DenseNet121, ResNet50V2, InceptionV3\nfrom keras.callbacks import EarlyStopping\nfrom keras.utils import plot_model\nfrom keras.callbacks import TensorBoard\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom tensorflow.keras.callbacks import ModelCheckpoint\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau\nfrom keras.utils import Sequence\nfrom tensorflow.keras.losses import SparseCategoricalCrossentropy\n\nif 'checkpoint' not in os.listdir('./'):\n    os.mkdir('./checkpoint')\n\n\ninput_path = \"../input/rsna-intracranial-hemorrhage-detection/rsna-intracranial-hemorrhage-detection/\"\ntest_images_dir = input_path + 'stage_2_test/'\ntrain_images_dir = input_path + 'stage_2_train/'","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:14:09.448547Z","iopub.execute_input":"2024-12-08T04:14:09.448848Z","iopub.status.idle":"2024-12-08T04:14:09.465851Z","shell.execute_reply.started":"2024-12-08T04:14:09.448822Z","shell.execute_reply":"2024-12-08T04:14:09.465109Z"}},"outputs":[],"execution_count":17},{"cell_type":"code","source":"path = '../input/rsna-intracranial-hemorrhage-detection/rsna-intracranial-hemorrhage-detection/stage_2_train/ID_000012eaf.dcm'\nimg = pydicom.dcmread(path)\nimg","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:14:09.466862Z","iopub.execute_input":"2024-12-08T04:14:09.467137Z","iopub.status.idle":"2024-12-08T04:14:09.491233Z","shell.execute_reply.started":"2024-12-08T04:14:09.467113Z","shell.execute_reply":"2024-12-08T04:14:09.490491Z"}},"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":"Dataset.file_meta -------------------------------\n(0002, 0000) File Meta Information Group Length  UL: 188\n(0002, 0001) File Meta Information Version       OB: b'\\x00\\x01'\n(0002, 0002) Media Storage SOP Class UID         UI: CT Image Storage\n(0002, 0003) Media Storage SOP Instance UID      UI: 1.2.840.4267.32.337944818669776895705763408052798539612\n(0002, 0010) Transfer Syntax UID                 UI: Explicit VR Little Endian\n(0002, 0012) Implementation Class UID            UI: 1.2.40.0.13.1.1.1\n(0002, 0013) Implementation Version Name         SH: 'dcm4che-1.4.35'\n-------------------------------------------------\n(0008, 0018) SOP Instance UID                    UI: ID_000012eaf\n(0008, 0060) Modality                            CS: 'CT'\n(0010, 0020) Patient ID                          LO: 'ID_f15c0eee'\n(0020, 000d) Study Instance UID                  UI: ID_30ea2b02d4\n(0020, 000e) Series Instance UID                 UI: ID_0ab5820b2a\n(0020, 0010) Study ID                            SH: ''\n(0020, 0032) Image Position (Patient)            DS: [-125.000000, -115.897980, 77.970825]\n(0020, 0037) Image Orientation (Patient)         DS: [1.000000, 0.000000, 0.000000, 0.000000, 0.927184, -0.374607]\n(0028, 0002) Samples per Pixel                   US: 1\n(0028, 0004) Photometric Interpretation          CS: 'MONOCHROME2'\n(0028, 0010) Rows                                US: 512\n(0028, 0011) Columns                             US: 512\n(0028, 0030) Pixel Spacing                       DS: [0.488281, 0.488281]\n(0028, 0100) Bits Allocated                      US: 16\n(0028, 0101) Bits Stored                         US: 16\n(0028, 0102) High Bit                            US: 15\n(0028, 0103) Pixel Representation                US: 1\n(0028, 1050) Window Center                       DS: \"30.0\"\n(0028, 1051) Window Width                        DS: \"80.0\"\n(0028, 1052) Rescale Intercept                   DS: \"-1024.0\"\n(0028, 1053) Rescale Slope                       DS: \"1.0\"\n(7fe0, 0010) Pixel Data                          OW: Array of 524288 elements"},"metadata":{}}],"execution_count":18},{"cell_type":"markdown","source":"# Data Pre-Processing","metadata":{}},{"cell_type":"code","source":"def correct_dcm(dcm):\n    x = dcm.pixel_array + 1000\n    px_mode = 4096\n    x[x>=px_mode] = x[x>=px_mode] - px_mode\n    dcm.PixelData = x.tobytes()\n    dcm.RescaleIntercept = -1000\n\ndef window_image(dcm, window_center, window_width):\n    \n    if (dcm.BitsStored == 12) and (dcm.PixelRepresentation == 0) and (int(dcm.RescaleIntercept) > -100):\n        correct_dcm(dcm)\n    \n    img = dcm.pixel_array * dcm.RescaleSlope + dcm.RescaleIntercept\n    img_min = window_center - window_width // 2\n    img_max = window_center + window_width // 2\n    img = np.clip(img, img_min, img_max)\n\n    return img\n\ndef bsb_window(dcm):\n    brain_img = window_image(dcm, 40, 80)\n    subdural_img = window_image(dcm, 80, 200)\n    soft_img = window_image(dcm, 40, 380)\n    \n    brain_img = (brain_img - 0) / 80\n    subdural_img = (subdural_img - (-20)) / 200\n    soft_img = (soft_img - (-150)) / 380\n    bsb_img = np.array([brain_img, subdural_img, soft_img]).transpose(1,2,0)\n\n    return bsb_img\n\ndicom = pydicom.dcmread(train_images_dir + 'ID_5c8b5d701' + '.dcm')\nplt.imshow(bsb_window(dicom), cmap=plt.cm.bone);\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:14:09.493814Z","iopub.execute_input":"2024-12-08T04:14:09.494191Z","iopub.status.idle":"2024-12-08T04:14:09.69393Z","shell.execute_reply.started":"2024-12-08T04:14:09.494151Z","shell.execute_reply":"2024-12-08T04:14:09.693057Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}],"execution_count":19},{"cell_type":"code","source":"def window_with_correction(dcm, window_center, window_width):\n    if (dcm.BitsStored == 12) and (dcm.PixelRepresentation == 0) and (int(dcm.RescaleIntercept) > -100):\n        correct_dcm(dcm)\n    img = dcm.pixel_array * dcm.RescaleSlope + dcm.RescaleIntercept\n    img_min = window_center - window_width // 2\n    img_max = window_center + window_width // 2\n    img = np.clip(img, img_min, img_max)\n    return img\n\ndef window_without_correction(dcm, window_center, window_width):\n    img = dcm.pixel_array * dcm.RescaleSlope + dcm.RescaleIntercept\n    img_min = window_center - window_width // 2\n    img_max = window_center + window_width // 2\n    img = np.clip(img, img_min, img_max)\n    return img\n\ndef window_testing(img, window):\n    brain_img = window(img, 40, 80)\n    subdural_img = window(img, 80, 200)\n    soft_img = window(img, 40, 380)\n    \n    brain_img = (brain_img - 0) / 80\n    subdural_img = (subdural_img - (-20)) / 200\n    soft_img = (soft_img - (-150)) / 380\n    bsb_img = np.array([brain_img, subdural_img, soft_img]).transpose(1,2,0)\n\n    return bsb_img\n\n# example of a \"bad data point\" (i.e. (dcm.BitsStored == 12) and (dcm.PixelRepresentation == 0) and (int(dcm.RescaleIntercept) > -100) == True)\ndicom = pydicom.dcmread(train_images_dir + \"ID_036db39b7\" + \".dcm\")\n\nfig, ax = plt.subplots(1, 2)\n\nax[0].imshow(window_testing(dicom, window_without_correction), cmap=plt.cm.bone);\nax[0].set_title(\"original\")\nax[1].imshow(window_testing(dicom, window_with_correction), cmap=plt.cm.bone);\nax[1].set_title(\"corrected\");","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:14:09.69602Z","iopub.execute_input":"2024-12-08T04:14:09.696375Z","iopub.status.idle":"2024-12-08T04:14:09.970404Z","shell.execute_reply.started":"2024-12-08T04:14:09.69634Z","shell.execute_reply":"2024-12-08T04:14:09.96947Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 2 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAXcAAADHCAYAAADifRM/AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/Il7ecAAAACXBIWXMAAAsTAAALEwEAmpwYAACYmklEQVR4nOydd5gc1ZX2f7dS556ck0Y5BxA5iWhMthcwNjY44oC9jrtO67DBn8Puer1ep7VxwHjBYBsMBgwmBwECCZRzmtHkPD0dq6vqfn/cmtGMAhIggUK/j/rRdHV3xbdOnXvuOe8RUkoKKKCAAgo4tqC91TtQQAEFFFDAoUfBuBdQQAEFHIMoGPcCCiiggGMQBeNeQAEFFHAMomDcCyiggAKOQRSMewEFFFDAMYiCcT+CIIT4mRDia4f6uwdYzyQhhBRCGG90XQUUcDRACPF+IcSzb/V+HG4UbugjCFLKjx2O7xZQwLEEIcSTwO+klLe81ftyJKPguR8hEELob/U+FFDA4cC+RoWFkeLhR8G4H2YIIWYJIZ4UQgwJIdYJIa7wl/9GCPFTIcSDQogUcK6/7N/G/fYfhRCdQogOIcSH/fDJ1HG//zf/7yVCiDYhxOeFED3+bz4wbj2XCiFeEUIkhBC7hBDffHPPQgFHM4QQDUKIu4UQvUKIfiHEj4QQmhDin4QQLT7nfiuEKPK/Pxrq+5AQohV43A+FLBVC/JcQYgD4phAiIIT4DyFEqxCi2w81hsZt90ohxEqft9uEEBcLIb4FnAX8SAiRFEL8yP/uTCHEI0KIASHEJiHEtePWUyaEuM9fz4vAlDf1BL5FKBj3wwghhAn8BfgbUAl8Cvg/IcQM/yvvAb4FxIBn9/jtxcDngAuAqcA5B9hcNVAE1AEfAn4shCjxP0sBNwDFwKXAx4UQV72BQyvgOIE/orwfaAEmofj1e+D9/utcYDIQBX60x8/PAWYBb/PfnwJsR90L3wK+C0wHFqI4Xgd83d/uycBvgX9A8fZsYKeU8qvAM8AnpZRRKeUnhRAR4BHgdn/d7wZ+IoSY42/3x0AWqAE+6L+OfUgpC6/D9EJ5GF2ANm7ZHcA3gd8Av93j+78B/s3/+1fAt8d9NhWQwNR9fHcJkAGMcd/vAU7dz379APgv/+9J/nqN13OMhdex/QJOA3r35AfwGPCJce9nAHnUPN4opyaP+/z9QOu49wLldEzZY1s7/L//d5Sj+9inJ4EPj3v/LuCZPb7zv8A3AN3fr5njPvt/wLNv9bk93K9C3OvwohbYJaX0xi1rQXkoALsO8Nvl496/2ncB+qWUzrj3aZQ3hRDiFOA7wFzAAgLAHw649wUUAA1Ayx7cAsXPlnHvW1CGvWrcsj05O/59BRAGVgghRpcJlDEe3e6DB7mPTcApQoihccsM4DZ/O8Ye2x6/38csCmGZw4sOoEEIMf48NwLt/t+vJsnZCdSPe9/wBvbjduA+oEFKWQT8DHUjFVDAgbALaNzHBGgHyqiOohFwgO5xy/bk9/j3fajR5hwpZbH/KpJSRsdtd3+x8T3Xuwt4atx6iqUK2XwcNepwmHj/NO5nvccUCsb98GIZauj5j0IIUwixBLgcFbM8EO4CPuBPyIbxY5GvEzFgQEqZ9WOZ73kD6yrg+MKLKEfjO0KIiBAiKIQ4AxVe/KwQolkIEUWFOu7ch4e/T/ij2V8A/yWEqAQQQtQJIUbj879E8f98f/K2Tggx0/+sGxXnH8X9wHQhxPv8+8wUQpwkhJglpXSBu1ETuGEhxGzgxjd0Ro4SFIz7YYSU0gauAN6O8lR+Atwgpdx4EL/9K/BD4AlgK/C8/1HudezKJ4B/EUKMoB4Sd72OdRRwHMI3jpej5nxagTZUjPtXqLDH08AO1ITlp17j6r+I4vYLQogE8Cgqdo+U8kXgA8B/AcPAU+weKfw3cLUQYlAI8UMp5QhwEXAdakTRhZqsDfjf/yQqRNmFmqv69Wvcz6MSwp9gKOAIhxBiFrAWCBysd1RAAQUcvyh47kcwhBDvEEJYfkrjd4G/FAx7AQUUcDA4bMbdLzjYJITYKoT40uHazjGOj6ImhLYBLvDxt3Z3CijwuoCjBYclLOMXPmwGLkTF6F4C3i2lXH/IN1ZAAW8SCrwu4GjC4fLcTwa2Sim3+5OKvweuPEzbKqCANwsFXhdw1OBwGfc6JhYNtLG7cKeAAo5WFHhdwFGDw1Whuq8CmQnxHyHETcBNAJFI5MSZM2fu4ycFFHBosGLFij4pZcUbXM0BeQ0TuQ2c+Aa3WUABrwop5T4LEg+XcW9jYkVYPSr/dPwO/Rz4OcDixYvl8uXjK+0LKODQQghxKErOD8hrmMhtIUQh17iAtwSHKyzzEjDNr16zUMUF9x2mbRVQwJuFAq8LOGpwWDx3KaUjhPgk8DBKCOhXUsp1h2NbBRTwZqHA6wKOJhw2VUgp5YMcvKpbAQUcFSjwuoCjBYUK1QIKKKCAYxAF415AAQUUcAyiYNwLKKCAAo5BFIx7AQUUUMAxiEKbvQIKKOAQQRv3Gn0vAG/cy31rdu04RMG4F1BAAa8TBqrJVxkQByKAiTLiADoIC6QD2Kg+MyNAAtWgLIXqgFcw+IcDBeNeQAEFvAaYQBCoRBXoOiiDbaOUGEYLcn2vXY568S6QV8soBmr8344a/Yy/noz/vUJh7xtFwbgfQqTSObLZPGWl0QN/uYACjngIIAyEQC8DEQdRBp4ANwn0oLrr5VGmxEJ1tjPVb8a63LnsDs9kx/1m1GMP+a9y/3t5/ztplHefZffDo4CDRcG4H0KYpo4Q+9Tw2S88T/Kr259h8YJJNNaXUlIcmbAOKSVDiQx528FxXIqLIwQDBkKI17ytAgo4OGgoQ1uPCrcIwATPBm8IZXBHUB58xP87gPLIi8AIgxECBFrYAtdFehKZtSHvtwDWhP+SaMJFyDyuk1MhHOmijH0M9UCQKAM/Agzw+toIH38oGPdDCMs0sMx9f5bPu3ieR3I4zbb1rTjpLEUlIdyMjdzSyoqNO1hpGkye30ikKEr/UIaU7eDoBnc++DL93cOYnktVWYz68hgz5zURjAaZO38SlZVFlJfFCsa+gEOAEDAFKEEZ8Q7ABVdHGfMK///xsfJahIgRDBRTX11KZUWUoniQqniY2uIwEVMn67q09I2wq32Q/uEcKQED6TxpKYmYOjFTwwBCAoazNul0hpFUAttOId0EysBHUQrLPUA3BSP/6jgiGmQfq6qQUkqyGZvWLe1sWbmV0tIITQ0VREqjhMMhtLCFZlmIsewCiec5eGkbO50hOZxgsD3B9p4+Ej0piqpLMYMWBALkPUlX5yAvrtjOyEiGy648mQvOn09ZSaRg5PcBIcQKKeXit2C7b/0NdtAoQxl2EzXpmWF35ouLMuo6ykvXMXSTSTW1vP3sE5g3r5ETFk5m0oxaYrHIQXF7oG2YHT39dLUOsHJ7H+s3dLC9c5hEIo1lCgzTRDd0+hIpksODkB9EhWpGHyodQN+bdG6OXOxP8rdg3A8xpJQgJYmBBOneIdLJNOW1ZcSrSkE3lCD4azK+cvQfSA8nnSPRP4xlCNI5F9MwGHE8zGCAXV1DJFM55s2qp6IsWjDy41Aw7q8GgfKIG1Heeg7FOAMVdtEYTWMUIkNlSQMXnHEy1/7dGZx29lzKGyoPCbfzqSx9XQOsfHkrTzy9huUvbWbdtj4GMy6OGQQpITMMTq+/nxrKg+8+ROfh6ETBuB8GeFJi5xw0TaDrgoHuIfLDCTRdo6gsjhWLoJumIvzoeRYe6mYS4DqM9I3guJJ4eQzNNF+TQZZS4to2qYEEyaEU8aII3ak8LZ1DRKNBTl7UXDDwPgrGfX/QgVpUjH00o8UAikGPAkGE1KgoMrng9ClcetmJnHnuCdQ114xxW3oe2ZyNCtUItU7PZqR3BNeTlFaXYoVCr5nbdiZLx44unn5sJXf+6TmeXdlKWlhIz8NLdoJMoCZaO4D+Q3pWjiYUjPshhpSS225/mnv/+DwzGkv5yHWnEa0soayhEjFqpKUE6SmDbntgmKBLxhv35GAK15WkszksXEobahDaay8cllLi2TZDnQPkbQeiEapqSgrG3UfBuO8LOtCMmrjMorJdwiCKiZdXUVUSoToe5Mrz5/CO686kaXbTmAOiQo4ZHnn0CR788308v/xl8k4CFdIxwUuTHEjiepLmyTP5py/+I297x0Wvm9v5TJZVL2zkRz96kLuf2EDSdiHTBXIANaroQE22Hn8oGPdDCCkljuPxD5/7FY1elvd/8hJKpk/am7h5GwwdhO43aNu/oZVS0tPSRUlpBCse3/PTcf+NXi+xz3VKKfHyDn0tnWiGQbymgkBwP7O8xxEKxn1PCFQYpgLl/QZQaY8BMIuY1lzJxy6YsU9uS2DVSyv4zD98heeee4q8Yx9wa/NnnM5zS/9CpKx0j09eG7ddO89zj77MN/7fvTyzaiduahu7Uy03AcnXchKOCbzZbfaOWQwnMtzyq8dwWju57rRGFl92OkYsqrjlemSGUwSFgzA0CIV9w35g71kIQcQQ6No4WyAlUrrI4SGSLV1kuvvZubOfvBQ0T6ui5qRZaLHiCesXQqBbJlVTG8gMDrPhmdXMOHMuoVBg740WcByjCKhGhVJiQBysKMWlMc6ZUs5nPngWZ159zhi3c+kcjzzwCKtffI6pMxfwT9/6Glt2bD3orVXG45jGuPtgH9zesb2fVN5h5pz6/XLbCFicfckp3HvSdP7li7fxX79N4Xk9/nFMArZQyKJRKBj31wDPk2zc3MHWJ1fytc+/nZrTFyB0Q3nLyQy6pRMsisB4D/4gwyJSSsLRIFrE99qlh9exk62PreHFzf2s7hhh3cZ2qmY1csP7lnDzd+/m8qnLufq9ZxA/YS7CsCZuSwhCJUVMW9jMzpXbmHnqrEKIpgAfAqhCpRaGAA+EiRGLcsX8Or79T1dO4PZAWyd///kv86d77iSXz6FpFp53YG9999Y0rr/hGqx4sVrgc3vLo6v5v4c2sGz7AALJhv4M/WmbGRURPnH25FfldryihK9/+3peWdfG4y+5QC8qzDQN2IbK9Dm+UTDurwLPk3ieRzpj89ILm1n9yjbSm1r45levpPLEOQjNj6t7LrYrCZnW6zegjrM720BKZHKIFXcsZWk2wA2fu5YrLZ17H3yZP96/gobmKnZmXf7cmaPr589w/cU9NF25BGEFmTCUFYJweTG9T7xM1YxGSgppkgUAyqDXgFGKMAPEwzql0QBXLqzjS199xxi3pZSsWbWOD73/o6xY9dxY0OS1GHaAWDjE2WcunsDtpb95kk/e9jJrWoeRusAKW2imRtbxWDuQ5kv3b+CFTT185SPdTLry3H1yO1ZVyo3XLubJDV14KQ9kL2reYDbHa4hmPArGfT/IZm2+/8MH2bBqB8WeS39HPyfVxvn0Fy8numA2CE0Z9mQSYZqEisLsGSP0PE9NnR7EJJKLoK+jj4qghW4KOh9/kcGmZj5x1alYprpM177jFB55ZiP/9K9/oL9zgG98/gpOmN/IQ799nLf/9VkaLz8XtImXVCCoriwi77j8+o5nue4dpxAOWYfqNBVw1EEDbSpF5ZOoKArTFA9SFjQ4taGYj4zjtpSS1c8t49rr38Pmlh17rUUIE0PXyTvZA24xnbN5/JGlNM6YimEJOh5bxid/+QKr2xJKe8bTsEdyGMVBIkGDiKkzmLL5zYp2tvU+wi2azuR3nL9Pbhu6eghpxVV4wwK8HtSk7iJgJaqq9fhEQc99D0ipioP+/Z/vZO2Dy4h195HrGeSE6ijves9JRObNUIYdcLNZHN2AQIB9TZZ2dQ6SHR5huG8QmbORjsv+JrAN0yBWX0PXi2uQiVa6WgZomt88ZtgBdrUPsPz5jWx9aTNTohb33PMCNTUlvPdzV7FifQ/eyPDex5O36XhpC4P9Cd523lwMvXDJj1/omNZc5k45lbdNr+TCxmImFwU5qS6+F7dH+gb4yM2f36dhB6iumswffncXX/rclzn9pDOIhsYnAfjpkD4cN89nv/417vqPXyMTrWzf0MWmzgFwHf+rAmHqVIRNZhaHmFUSojRk4iRSPLlmF7+646X9cjvYN0zI1PEcCeEyEKMpnaMGPnyIzt3Rh4LnPg5SSpY+v4nbfvko23d0kxjKMq8szA3nTeOUq07Emj4VMeY9SIba+ihqqNpvXL28PI5h6AQ1AZ4H6TTpZJqwK5ECuvpTVM2ehG6oGyEcCyOLi5FGCLMoQkN92YT1/fHeF4k5DkFDx9IEdTXFmIaOaeiUT23A7h0kWFTK+AeN2z/IjnVt/H71H/nPn30Cy1JxVClB0wohmuMHJsHwidTXLsQzTHaO2MQsY7/c3vLKetasf/lV1udy5gVnc8W1l5HL5Ni8aj1/uusvdG7eidQirNvSx7LNT+HJLgCS2X6WPvcK133mcobzHk4+Bxjg5sGxCZQX0RANENI1LE3gOS44aSQey7Z075fbw+2DzKovZsXmbnDyYBZD3gE5jDLs81Ee/IFHGMcaDmjchRC/Ai4DeqSUc/1lpcCdqOnpncC1UspB/7MvAx9CPT7/Xkr58GHZ88OAFSt3sm5DO1/95nVICV/5zC38/RUzmXfteYjQqIiRDwmmlyGXyWEE9x3mGO4fprSiGE03QNchFiMcjYDjIfCIDg0y2NpN+eTa3at1HYQVI1AURtvjoWFn87hS0pPN40j46MnTx2LoWnGckb5hglMYx39JpnOALX0pshmXV17ZzplnzgKgfzBJRVnsEJ25oxPHD7dD6OFT0ENNbG/tQ5gBFk0p5+/fd9J+uR01IWDEyOb3bRQXzp1BUSyMEIJgOMj8005g3qkLwVFNOXpWbeC8v+thfWuX/wuNonjc53YIjSyuJ1HCZA4GEs/ndt6VJJIZlNSAYGvPEMM9g/vl9rTiEBuDglRiEJwohCshZQODqArbecAGjrcY/MGM0X8DXLzHsi8Bj0kppwGP+e8RQswGrgPm+L/5iRBC5whH3nF55Ml11FQX86H3n0tDfRmG5/KFK2Yx79olSFcytGIVww8+juzYAU4a8AhXFzHY0o7MZPYKtwz0JUiPpNCMiYcvhIYwDYRpEZs5jezAAJ1b23BTGYY7+0kJEGaUkupiEn2JCb/NOS45V5JyJVo4yKknTR37bMasejzPmfB9KaFteyctiRwRDW6/7UmyuTxCiOPesPv4Dcc4txFF6NFzcb1KUv39ePYIUeHw1avnvyq3Jy+aznf/6evMnbYQIUZ9QB3QCAWK+PAHPohu7hEDH8ftykVz+LcvfZRF08+gIt7E1Nr5XHX9pQgzyuTZ9RRFwihjawMWLoKcKxnOuQxkHex0mlFp4GQ6Szoz8SEzntulQYOqihLQY+ANQ2YIrCqU55709/sElBja8YMDeu5SyqeFEJP2WHwlsMT/+1bgSeCL/vLfSylzwA4hxFbgZOD5Q7S/hxxSSjZs6mDB3AYqymJIKdmxrYvVtz3MpZdOofPpl7n9vrVsGcgx1c5y7YmtlDWVYjZXYp10AnULKpH9gwhNh8BuD166HsVhCxwHzP0UEWk6lVMaGBrqJbd+DWZpGUXzZ4KmEW+oYdXqnVQ2VgBKK37r1i7ynsTVNISpEwjscfn2jKfbNs8+txlPKqmE9g2tbNjUzsJ5TYWsGY59biOqEJHT8GwD7CQIk3Aowj9ePJdL3zaNzqdf5he/X8ETa7u4tLF4L27f9OWbOefcszj9gksYTHegMlEkhlbE048u5dwLl1BSsWdR0ui2Nd529YVMXTSFxJotTD5xDtUL54CmUTermRl1FfQlOoEUBGKYQYO8J8m6HjnP89U61ChACIE4ALcnl4Ro7S/BGXKUgXcArQK8HMrAR1Ahmk1AF8cDXm/MvUpK2QkgpewUQlT6y+uAF8Z9r81ftheEEDcBNwE0Nja+zt14YxgaTpPN5Zkzsw5NE3T3DPPAHU9Tt6udcypDPH37Sm5b1cmWEZtI0CQWNfjr6i5GVnRghQO8vXWYqefOp6dzhKqFE72CsqpipCzCS6bQDWOfcXnZ24eHjhGrQKusY6itm6DtoAcDmPEIWiaN50k0TbBtezfrX95GSUAnn3GIhyzMcaOCzu2dTK4u2j1slZKB1Zt5duUuSgI6WVcSF/Cjf7+Hb3z7Bhr3iOcXMIZDyu23DFoDBE5Cph3wsujBGLPqS/nsSQ28Y0HNGLfXD6QxNEF32lbcXt6OIwRXvGOAWRcuYumjzzCU7vFXqnLHRzKt/PDXP6Bxcg2f++rn98ntzc+v5H0f/CSbu3bi5T3e986r+Y+ffIdQPIpVFGVmfQVLNxhABtOQ1EQsxW1PMpDNk9INyCt+15ZEKasue1VuV4VNZtTE2JBz8DIOeAnVWERUguxAqVw6wCyU2Ws7rKf/SMChTp3Ylzu4z/QQKeXPpZSLpZSLKyoqDvFuHBieJ2ntGKC0JIKmCZ5bupF///TPaV6/hWnC466X27l9VSdSShaWBJkTMagImawdyuKdOJNLvvE+hmsaWP7jh9m5bOs+s2CEECpLxvNUA4LR70hPKUemc8hwiNLyIoKREFVTG9AGVVaAsIIkOvtxXSVvqgNNUYuyoEF5ZZyuvgTbW5TcqZSSkc5eglUVjF4C6bo8/deX2T6UJWRoNEQsPCnp3drJl750G339I/vN3Clgn3hd3D7M+7RviAawToJsHjxJtKSUKxc18oMlUzinNj6B2ydVRjmlMkpFyGRVX5qfLG/lnx9exRVf+iMPfPMuVj++bp8HKfFYtfwFPNfdJ7fTts26lo0MJzoZyXTzi9//mpWPqUGOsILMqC8FEQA0TB2a4wHKggZZ10MCwtBRp9xg4dQqwjVVvDq3YXJRiNrqOARKgRjIDBhFICpQo4AEMIQy8A2H8QIcGXi9xr1bCFED4P8/+mhvY+JZq0cp+hxxEALmzazDNHRWvLyd+37wZ26sDKAJ+P2WPl7sSaEJqAmbzC4OcmJ5hFTew5zWwGe+cBXTptWw+Jy52LOnMNlLMbhz37KjIhLBcxwY6oS0H0PP9IN0KSqLExxXki00DZHNqzeGTklREOETOhIPMaLpjNgul11+Ep/++MU0N5YDkM3mCUoHLbq7vZ90XFZt6UUC7ak8WdejPGgQNzU2rWnhvTf9lNXr2/C8cRNpBcBRz+0yEPMhmwTpEYwXc/X8Wr6xuA5de3VuP9E6xM72DnLpLrZ37OQnz23n5gtPZEb1rH1uadmajaRHUvvkdvO0SZQW704UcD0bO+GnMxo6pSVhhDABnZzt0pa0GbFdBpM5UlkHmbcBD6EFOOOESQfN7fKISVFlHBEtB2GAM6xaBFKMMndJlJGfjerjeuzi9Rr3+4Ab/b9vBO4dt/w6IURACNGMqgV+8Y3t4uHBaJu6/t4Em+5+mk/PLSfvwdOdSdKOR5GlUxwwKLIMwoaOqQl6MnmMWJhAwBxbx6xzFzDsCXqeW0k+7+y9HUMHJ4/Xnya/dquq0OsZRHZ1qy5Mzm7jKiVkXPVeaBpGJDT2WXVVMZXT6hjKe6SGUnzo+rMpiqvPM+kchqWpuP+442soCmIIaE3mSOY9PAkbhrL0Z/K0bevit79/lh/89GEct2Dgx+Eo5nYQxALwUoCHFYry0dMm8a0lkw+K231p229orfTbn93WSWfK4eaLL/UN8US0tu9i+5ad++F2Di+3W+NF4pHxBcaEpmGEgwipPHPXE2wbzjKYc4mYOvmsA3Ya0NA1i6lTKw+a24M5l/KwSTAeIlzqR9TcLErSOIbKfx/tzToHZfSPTRzQuAsh7kBNGs0QQrQJIT4EfAe4UAixBbjQf4+Uch1wF7AeeAi4WUrp7nvNbz1yuTw7n3qZKy6aRKAyyrKeJAnbwZUSUxdoAlwpSeQdOtI2PXmPCy9cMGEdpVXF9JRXkd/aSTaR3msbnpRIx8HOOWxbuhFp57BTLi33PQdemsSuDgZ7BlWIRMCIafrhEo1INDgWzgxYBj//wQc45dx5PHT/cv73pw+NbUMIMK09snJMncZJpSTyakIq6biUBHTmlYY4uybGJRfOJxIOcMedS3n6+U3HZYjm2OP2VN8459G0ADeeM41//fK5B8XttpRNImWjAoBKbyaZHuS7969heqCMWLB6r60Zuo4hvH1yOxz0uOrciyiL1wECKT2eWb99jNvRWNjXYNJACjJJm5bhLFXxANXxAMg8YCJwMF4jt/OOhyclsaIwWrTC78mqowx50F9LDmXk57C7kfexhQMadynlu6WUNVJKU0pZL6X8pZSyX0p5vpRymv//wLjvf0tKOUVKOUNK+dfDu/uvH54n2frCOmYsaiQ6bwZrtw/QkbIJ6JrKSPEktqtefVmHlqRNZXM1Z58xc8J6hBA0nz2f/rxH4qV12PZu791zPQZWbiKbs8kNp3lxZRvJjduxXY/b/7aRtodXENOSyK5t9G3egXQ95Y3nbUCQHEnT3TM8tp3ieJh//7f3cOZZs3hl6Xp6etVQODEwQiy6p/aGRu30WiWT6kmSeZcOWxIujxO3dKygxU03LOH233yKBx5eSTrz2vRCjgUcW9yOgqhHhR0MLj99Ft/7wY0Hze32kRz5VJYxPXYAsjy2YTu9WZebL7gMbZz3rgmD68+5iuraqn1yu/vxlfzw2x/h6T/cwjXnXY2pB3n6ySfIpzOAoKQ4hK4ZgA6uB3mXxECaZNZhUkkIzYwCNpGgRmX5aJNuH/vg9rbhLH3pPHFLJ+9K8tk8PV3DWJGQ36w7B1oRKmvGRE2XjHZzmjlx/ccIjtta9ERXPzXVcaJTJpPZ3s3GtmFSjprMCegajnKksT2PrnSebYksTbMbCFh7JxjV1JQQXjCNqJUh0dY55gUPtHTT1jVCqr0PkzzJrMOLf3gWe91WelI2f31wPcm/rKLU8yipLSbV0U12ODE2NxUrDiP3CPXEYyHe/6EL6BxIsaOlF4DcQILi+oqJ/BSC+ik1TCsJURkyCRs6iy47mUvfdz5RU8d+eRP/+x9301BbSsDU+Z9bHj0uvfdjB3W+tyuZVF3Ff/77DRRNn3JQ3N46nKV9OAtOFjQB2qh362DnR7h7XQef+cSVXHDKkrGtNZY0sXV7Nz/51k9elduzK0u59Q8/4j++9h1OmD1/rDCvuq6EkCkAqTx4x0Om03R0DZN2JZppAjaNZSXUTq9/VW6HDI0ntvXz4o4+IobGdTPKWVgVRWZT6J6LURQHDDB1sMpRnnoelUc/hJI+Pvayx45L+YG8nSfV2UPtwunguXQs38ZQVhnRZN5FAJafV5vMe3Sm8/RbAa659oyxLjS27UyIvRfPaaZl9RpmzDHGctu9VIrixgpCAQ0t4OEJeHpVB/HhDFFDoyNls64/w2m1VeiWRSDkkOwdQshyEFA+qYbBtCreGE5k0HWNaCTAgnlNXPauM5k+tVqJJg0MEJk7lz29j2hNOWc1l9LZm8KRkof/tooyPKaaGjOLg6zc3sETj6/mS5+9nNy4EcdIMksgYEzQtSngSIYOog5kBl2z+OwHL2Ly4lkHze1VfWn6B1OMtdjTdb9g1QPyPL6xla27kvz7d7/JiitW0T/cQ3P1FNqGdjAy0oRWHHtVbgcjYW54/zvZtXkHnueCgKopdZTHwiTSCQgYKpxk57EzDpv7QjiOAxhcfNI0onWVHIjb0WiAyUVFxCydmcVBdATbu4cZ6h+ESAy0ANhZiBaBUwSerY6VHJAAbRZ4S5lQqXuU47jx3NUQTl24zm2dlDRUIXQD0kk2rO8g43o4niTjeNieZDjnkHU8Mo7HiG7w8ZvfzpRJlWPryu3hUU+ZUUdHwkNzXWQq5TfKdimJ6OjxIGZlJWlNsCORYzjrUBOxMITglW399Nz2FEu/dydrn91ExjZw+gYBCJYUkxkYRkpJJmeTs1UmjWHofObjb6O4KMJA9xDhuAWhKHtCKy7m6utO4ZSGIgK6oDKVIp9IsXEww+r+DNMiJtv/vJS1r2ynbJwccCioFP8KOFoQAaMYMJg3pZkbP3E5wjg4bu9K2nQNpPAyI6hq0bxqB4mBMnQOw8l+brlzOTOnNHDdFVcBsOSc+XzlC5/hyndffVDc/tT7/4cvfPFW+raq/PJ4VTnT/AI9XAd033h7NtnhFHhQFC7lXe8+46C4fXZdEeUhc4zbc0tDfGhxE+XxMCRT6nikB5kUhEazZwL+caZAFKmc+GMIx5Vr9tyLWznjpKnodpZQeT0AzkiGlr4UOdcj63ok8i6uB2nHI+9J0sBV1y/hvdectlvHRdOIR0MT1m0YOrFpjWz628tMu+QkejcMEU4lSQeKMXQNW3rMaSwhAiw8vYmm9mFe2tRLRdBEJrJMm1dLbF4F2b4+dm3uY1JlGUYsAv6DorqiiOeXb2PBHItwyMIwdKSUtK/bzqwTJo+lTI6H0DSqLzqdS6bXM/O5jaQ7+lmzqYendgzQk8mjCZhjaKz/5YP0dg5SPbWGExc2YxgFw35UQcTQwmFkIsiN1y0hXqNSZA/E7cGcw47+FM7wMMgRwAHPUAYQPyUXF8jyyJo2Njy8go9+5AaeXfoKi6fNZjhqsX7LDuafMOOA3P7R1afS39pJX2s71bObMWIRzlk8lYdf2gi2jYhEkIYJTg5yWRA6Z86bxtwlJ7xubp9SHaNuyQx+8OIu2lJ5vKRU8gpSgFkGeRXGAhvcBOgzwO31j/nox3Fj3POOy/r1u5hZX0I4Pq5phSboyzm83JemPGiQ8iAXDJLIu8yYWcffXXUKl1y0AO0gNNlrmqu58zd/43NnTiNu6nT3JqlfMBdN19j05HLOn1+Fdk4z5rknU9o/Qu3S1ZjdCcymYux4gPYt/ZQvmomezDG4s4OyaZOwLJ3BvhHC8RBr1u1i+/Yurr/2DHVMtoPIpDGKivajTCkQuok5eTIzJk9GOnnm9vQS/83j3PLAGnr8nPrTq6I8fduj/Kl9hHe9+yzee83pTG3etxczGpcvyBccSYgSDFjEyyq56p1n7pfbgzmXXSM5hm2XrO2SHMmQT6bAG0IZc4ny1m1UNadgNC2yazjB7feu4l/+81qeePC3/ODrP+Pbf/o5nnRZ+9xNfOeKc/fL7VwswPe/92d+ev9DpHOS++/4DqddcgbnnTuX0K+eIONZmLqGFouSHUyCdBBC58oL52MWv3Fuv3dBLb/Z1EePpeMmdGQ2A9JAee+u/0qo4i9R5Ve0Hv04boy7oeusWbWTEvL83XvOGSOMEYsSqylh5pQmenf1ccM7TuGity1SPU3D1mvyYpsaKwjMmMTqJzcx96ozaVxSSyAcACkJlhTjlmoEZ9dBsAhRV0LknZXQthNCBrmdfcSnTCFeXUZMSoa3tyGlR0ltKW3bO7nrifXc/ZflXLpkDu+55vSxHP1QOIAQ4x884ydF/ZvCP1ZhWph1tVz5hWuYM7eBH/3vE2xL5KiPWJxWGaFLM5g7s47BoRQbNrVjmQZTJldNOEYpYUdrL82NFQXJ4CMGJtGgwWlzG6mfUTeB207IYlnXCGVBk4HBEYaHU0jpKs0VL8OY54qDShccvabKqI9Gbh17hPvWdvF3T26i9qx53PLYn8m7KvPl5Q2bcb/w3v1ye3BdO/9z79/oGnwOMPnzPY9w6sWnMX1+Ew0VZbTmJGbQIGAKsoMGIAhZsHjxlEPC7dOroqzsS/PIUBphWei6AVLipHVUq0EHyII7ggjOR2Z62T1yOXpx3Bj3dCZHa0sPy9Iprr7xgt0fhMOcd85MmNTEnAXNmKb+ur1SXde48eNv5/m7n2H21p0ETz4BKSX5/kHqq4NY5XXIUNgnrAAzBJNUamUoH8D1RwdCCIKVZWQGR4jXVtDxzLNsWddKdmCEV9a0kMnmVWgGSay6dIzn0nVJbmuld+1OgqEAoZIwsan16CUlqhuUEIBABAJMvexMvlAU5of//TAv9aY4rSpKY1GIt507l1gsxKOPrmbb9i6m3HTRhGPUNEHrrn5cx2P61L1znwt4s2GAiBI2dZqqi9GscfLT4TBvv2geP3tsK9sHhiHVg0qVVLH03ZOHOsp7lf7LRU005lB54QbINJt3dfPd25bxiWQP3YOdAJw650x++P2voE2fjgzH9snt4JBEEyl/ezl+d9+tfPBT1zJ1SgPnntDEX9Z0EbJ0kllU5oxnEw5GKakvP2Tcrg4ZuMMDeE6ScEktphVgMD3sH3sYsEEmMLQKXGsqnr3hMF2vNw/HjXG3cw56KkOfKZH5POjq0AWCeRedxCO/f5q5C5rfcLihrDTKSZeewopfP8jC+gaiNRUkE1lErIiu9e3U1sYI1tTtdpD87ZnhCCWh3V1jAtEQ+YE8IhiiEptoRw8Ly8J0p7LkbIdQ0GTjyq2cdOp0kKor1Nq7n+TBP68gkcpRHDAIGxqReJBTTm5mypL5BCY3IAxVsCF0g/pzFvPF0iL+7wf30zmQJKi7LH9uI0suWsg558xh1uz6fR7jqSdN4d4HVtDUWEbA2o/iZQFvEorRRZzaqMVAIrUXt0+58gw+/Mg6vnf7MuTY7Z73Xx6KiKOdi0a9+BATOxipwiMvn+TBF3dydlWA+c3zWLV9A4mhJFe9/xMsaJ7Lrbd+m+Lm5r24LcwgyN1a6h29LXzn377DLb+7hY9eMR93RFWWLutOgm6CJ5gzrZaqxppDxu3JRUEqiyN09XWSHO5ARGpBuCBt/9hDwDD5dA/Botnk8q1ImTr0l+tNxHGTLaMLKA6aVDVUMdI7tPsDITDicU45dw4tq7cdEq2VyuoSSk6chpccxrXzlE6upaSilKaF09nRNqxuwFGxJc9RZduxENKaWGJtxMJkRzLMXtzMOyaXMr8sRER6DCfStLf0EDMkgdJivEyWZ3/xAD/+9TPsHEiT92Aw57A9kWPlriH+9MBa/u/f7qbllvvIvPAScrgfPBchNMrnTecjX/07iquL2DSQZtmtf2P1y9sxDI3KiiJa2/r3yn8PBS1KYiFeWb6tkBv/lkIAdei6SdwyWLmlj6GuwXEfK25/5otXcfrcapSRDqKke0c9/FFP3fNfKZRXH0Hpn8dQWSURwCWbTbMm5fLjf/8XgqbG+vZXaGlfz/1L7+Xr//pTMiOpvbhNPIwWnOhH3vvwA2xcu4k547hdFTYRukVJcZwv3XwBwbJDx+3tiRzvPWEyxfF68FLIbAoRDKNGJ6Di7ybIAUx04vH5h/5yvck4box7a3s/pZOq+Id/fCf5kSwT4ndCUDKtmZKoybKHl+M4Bz9bLqUklc4xMJQik7WRUiKEoKSxGtnaix7Y7dnqhs6ME2dBOk1uwybSW7bSs/RFdi1bgxQGA+0TDakwDETIRFgWcUunORaguSyKyDtkWzqYt+QEZDbLS796gN/d+zJJ28XQVGl51pEM2S5pxyNhO2ztT/GrB9Zz+48eY8337ya3fpO68YQgPLmJ9//T1Vy4sJYK6bLs7qXk8y66vv9RzMknTeWPv3+GxPDekgsFvFmIAVE0Q2dnIsvWHX3s3NTOntyumjOV3/78Y5x3whSE8FDGOoryVke1ZEA9LBxUU2l/wtGoQpiVCLOE0YH+0tXtbH78RdJ2Zmwznszxk9/+kC9+6ssMvbx6ArcjsSiL506s7B4cGeLpZS9M4HZ5QCdi6nz702/jwnede8i5PbM0zLkzJiFEAPL9ICzUCGX04RYBPFLJfqrLZqHrR3dzj+PGuG/d0Ma27T3kXEnXwBB7OpxCCEpnNDN7dh1tq7aoHo4Hgbzj8skv3MrVV32Hr33l/8bkB6IVJbRt7SK9h96MpmsQL2JdS5IX7n2eUERH9gyR7BlAy6UmbldAIGDi5GxW9qXpTOepyudY+YfHaTpxGpqhsfnPT3HH/atI5V10ITCEGg17qNJsT4ImBBlX0p912DKY4U+vdLDq7heQqZGxmyBUV8c7P3slC6dWUNrZw4aV2xFC0FhfhuN4DI9kJhxHcXGEWfOaePqxVQXv/S2BQHUCFBRFIpi6Ri6bZsvOjn1yu/nkOdz5+y/w3refjq5LVCiiSmWHEGX3ZKpAhWwSYBrEq0uYObWOxrpSP8zi0Nqfg2yAWGhiNy/Xs/nxbT/jHTd8jWfvfhbHy3HvL+9l+VMvcNVFF2Bq4Qn7ZAWsCdw+qSrKDz+xhA9+/h2Hjdt/N72SqpJKIIlMd4FZBEYMZeDVA89z+hlK5qgpO4GjWZbguDHu6zd3MG1uI+VlMYJCA2+cEZUSN5Uk39NDvKGGuum1bHthLclhlWPe0tbPT37+CGvWtuJ5E+8c09A546QphHNZBlZt5fe/fRIpJVY4QFd/klxX/177IjTB5JNnEWxowGqaTsNlZxKpLKd4yqQJbfmGugfxsnk6tvTwePswG4YynDm5jMtuPB8jHGbLo8v53q+WsmUoi+1JHCnJupLejEPK8dA1gSclOddj2HbIuh5DOZeOlM1Tq9rZ9fALSDs3dhNYDfUsuPF8zmwuoedPT/Hi0+vwPI+RZJYXXto68RiE4Jp3nclzz21i166+Q3uxCjgIFKFCCVk0M0hPMofrJFm5bON+uV02pYGf/vbz/PPNVxMNaiA8iFUTrZiGFapBGXyHsdh7fhBh55kUD3JWYwkN1TWAS9Z1STs6Myr3brLjSYfnt77ALfc+ytve/yk+/ct/49zLL+YTX/sSeW93q7zZU+Zy1aVvn8Dtc6ZVcMNnrsCIHD5unz+jgq8tmU9t2WQgjxAeejjG7hFMCLDp7e8gHG3GsvY973Q04Lgw7rbtsLOlj+uuO4tg0MQ1LNI7diCH+nC2bWHXA0/z0y/8kk9+6Kdseuh5dN1g8uIZdK3fRuuGVqIhi2cefpmffPk3/PmPz9HTm5iQ7331O09jwemzKbV0nrnnOR5/Yi2elOzsTlK0n9BGUWmUU69dQqBMzfbrpoHQjQkTulY0xNBIipH+BHFTZ2F5hBNnV6OVFZPa3sr//uwROkbUDWO7HgIYybtjgkogMTVByvFU71XHYzjv0p3Js6Inxfd+/gzP/vcfyXd1jd0ExpRJVF1zOgtD8OIvHmTzpnZKisNcuGTuXscQi4W45vqzue8PKoxTwJuFUbErCUJHs0wGh1PgjfDI02tIbd8/t0OhIF/8zof53f/czNxJ5Wi5HM3lcd5xwkyqq6ejGVWM9kqFDIn+dlr6k1SGDE6aVEGkqByJpKUnRZlVvs+9y9kD/OGF37N25zo8aZPL50hnhxlf2t/e20HLrra3hNvXzKvmY6fNIRStR9o53JFhxqpziQJhPLeftp5+GqpPYff8xNGF48K4Dwwm6W/tIZNWkyfx6jI2/f5ZNv/gHh7+zn387KePs2VbL0NDGf7jPx/k1q/dSmpnO1NOmUNR1KRzxToWlQSYZMC9P7mfr3zh16xY1YLr66AXF4X5x6+/i9pFU0knM3znn+9k67ZuupI5tq/b29sH9VA4UJ54OBJEz+dpmFrFZ8+cxIcvmEqqe5j0ky/wxC0Ps6svRbFlEDU1LE0j7XgYQlAWNAkbGqYQ5D1J2NAoDRhYusAQQolHeZLhrMNvH1rPwz97UBFcShAaTJ9O0SWLmVkc4P5bH2dkJLPPfRVCMH/+JPoGUqxbs/ONX6gCDhKlKK/dRjei1MVC6NIGUmzt7mfFLx99VW6nW9q54oOX8Njf/pWffPlSLp5ZwaKKCBfOqGX65Olo4WYQquRfuik2tezipY5hLF1jWn0ZeihEV9KmrqycfYctRouh9o+h4T7uu+vut4zbpzaVcNLkKoSOX50bUPssAigRMY10qgspiolHph2qC/em4rhIheztG6FqWh0LFkwCIOdJfvlCK/WGwPGU7Gl50GBSTGMk77JmXQf6f97LOz99OUVzplJUX8X0BZPZ9fQq/vLASh7e2MZ///ivlJTF+No/XEl5aZSiojAf+uLf0evC+r+t5PFnNzCQ9yg2smQGE4RL4685zVIIQTQeQz91LqXzK8k8t5knntlJZGs/L3QniZo6QV1g+xKuEtA1gaULpP/c7ss62K4kZGgUmSrkk3HVcRdZOmnH4/dPbkUL/oW33Xw5eqwIoemYJ87j7FyWxG+Wct8flvLuD5yPvo8qXcPQef9HLuQPdzzNnHmTMM2CdMHhhQZMQYVP8ggjwo7hLNn0CCDIuAa/eK6FOaXhA3K7Ys5Ubvra9eR7+9n19CoCD6ykN+vQmS3FzkXJDvQh88O4+WGe27iduto6QmELPWLRZzv8vw9dyTPtK9iya9vrOpI/3XMvn/nMJ5j/FnH7U2mbXQMj7GjbjsqacUDkIVAG2RzIAdq6O6kpn8dIegdSHl3JA+JImAxbvHixXL58+WFbf85WKVmWpcIemazN5z77a9IbdqoCa6HUKypDBn1Zh16fNBfMqOCmr19DZMokhADpSZyhIbrXbOPF5zfz5Is7SJoBLr/6dM67aCHxeBjHcfnJLx/n6ec2oiVSfOd9i9EXzsEQgur6Cox9SAa/GqSUJNvbiHrD9P95Jfc930pXOk9v1kEX4EpI+JkEYUPD9r2ZVN4lqGskHY+ALgjp6rOAJnClVGUsniTvSbrSeWxP8pnL53L+zZejFZWAAGnnGL77Me54aAOXfP19NDZX7vMBJaXk/vuXY1gGF1+08IiUJhBCrHgrepoKIQ7xDVYCLEBNANoQagLbA7cTGAKtlvqmKZzXWPy6uf380k089eIOlu/op6V7iN7+XlwnA1qEQHEZZjhAc1GAe/75craFDL721X/ilXXryOeHX9ORaELn1v/5Kddfftpbxu0f37Gcbz+2mlSqg7FU0XgjJBPgtQKCopLp5J3tpEeOsMZbPqSU+7zhjouwTMAyCATMMaMTDJjU1pXSn3XoTOdpT9mYuqAsaGBogh0jOYZshwc2dPOXXzwCtmqeITQNs7SE+rMX845/vI7v3/IJ/vljS4hu2srvvnEbf7n7eXa1DXDReXNJDozQ2drL809tpLEsSDBgkBgaeV37nxux8TSPnpEcnek83Zk8liawfFILAY6UBHWBLiCkawgEhiYoMnV0IdD9mzwvlacT0DR0fxhbHjRwPcn/PbqJ9kdeRPrFLcIMUPS2Uzh/ehl/uuVh7HFx9f7BJImkyqARQnDxxSfQP5gilT7+mn68uWgAMv4rDLkcuMOo/HQbPBvbdt4Qt6/+0rv5wa9u5g8/uJ7ffGIJHz3vBOqqGjB0i3w6R1FAJ24ZPP/URi44fQF33HEbVaWvXQ/dky5/vuuet5Tb15zcyImT60DEUXMNaSVeZoVR4a88w0M78IxmEKWH6Bq+OTguwjL7wpSpNTwWsIjFwwx19GMINQTMuZIzqqJ0ZxyGbYd1W7vxkgn0gC9PilD/hI5RWkrDkhLqz1zAWV29dG7pYutzK9m8ro1pwkErD7N6ay9n//V5wifNpqi66XXtq2cFIBJnc0+KYdslbOg4UqrRiCaImybDtkPGkYrsGli6iklamqA8YKjOOx7kXImGatwQMzUVHZWSqrBJKu/y0rLt1F+Wg1AYhEAUl1J33jy6v/NXnnxyLRdduAAhBJ4n+eEvHuVLn7oEw9AxTZ0rLj0RqxCWOYwIoDz3PtQEoA7eaBHSaO2GRsZ22ZHIkXO9MfndN8Ltc7p6+dymDtbu6GLzuja2b+nGzDtj3H62dxftPTtfx/EIJs+aBZGat47b589j0TM7WNFeQ2qgD+gHO4leUo3rlIKTAjlANlEMxizIP8/Rovl+XBp3IQSXXXoiS5bMwbIM/v5jPyOWHGEbBsULG0iu20GxpRMyBDHL8Hs9oipJPRvZ242XyiBME89x8fJgVZQx6az5TDIMLnBdMm1d/OG/7+Nv24dY/fJOzl+y8HUJbeXTOXRNRxMaSGhJ5iiyDIK6wNI05anoAl0zxjwYpGqoIyWEDA1TE+Rc1UQ4Ymoq6UsIdE2QtD0CukZJQKALl86eEWQmjRiVQhCC8MLZvG/JZn552+Ocesp0iorClJdGOWlhMy27+qksjxGNBonHQq9yJAW8cdT6/yvBLhV3t1HGJsNoOt9IIscG21MGsjZOzNR4qmOEjQNpzq0vel3cnnzOQiafb4DP7Tv/68/875NbOWvFTp5qXYuUr93ghc0g73rXtW85tz988WbW9aV4LOMgM4CTRrouWjgE2Ro8ewjcXai6gmrg6FCNPC6NO6h2dfFYCCkls2fWEVu/nc39ac4/eRovSMnO5Vso1gWnLqhHi/rFGp5D9pllPHv3SnqHs4RNjUzeI+961JaGKa4rpfHEKZTMaSZUU8HbP3AeMwfyOGs3MJxIsY8ewweG51EcNiAe56TTJvPC1j6kVN6LqQlChkbU0HF9T8eRSq/bk6oBct6TuHkXgYpNOlJiS4lAIoSGpoGlCQK6IGG79CVzOJksei5LZihJpLIMEQgx64pTOHvTffz+tif4yCfejqZp9HcO8PN/u5Ppkyv5x+99gJKSvZsqFHCooAH1QAKVsmeiPHYdNRnooW5nC3I5pJMH08JxParDFpBmOOvwSOswc8vDVIXMN8Ttc647i3+5Zw3ZgEF9/eur5IyESqmrLH1LuJ0aSBCrrhjj9sc2dLGlL0VLaxqkTZEuWdRcjvBKeXJND67TAW4X0Az0oB6sRzaOW+M+HpFcjinxALuSOX73w78Qqq/g3GvOJL5hK6e/93yEoUSVZF8PGx5cy4stg3gSJFJVAwroTefJtAwin9tGVTxIcW0xJ82tYfv2BEW1RZSXhPBcD/01SAhLKenf3kbF5DJEdxtlRRZzS8P0ZPIM5VzChkZI1wjqGlnXI2LqeFLl/+oChm0XT0LQEAT8dLK042JpGinHQ0MQNzU0oQpCKkMGriPJD6fIagbt69uZfqKFXhxDb2rinEvm8/3fvMCqM2axaNFkFsyfxAulEVKpHOvXt3HGHs3DCziUCIMe95tJ+KQbCw+MznPogC8cJoC8y+RYgCnxAPNKQ0hg81CG5Z0jfO/SWW+Y22+bVsbSrf1cfNU8DN3CcV/LfIvBeSeeR1lDyZvO7TQan//Ij/nuj2+mvLkGvamJcy9bwJU7B7llMEU6kSKXThMzNFJ5SSBYSjrZg5rXCKC89z1kHo5AHNC4CyEagN+ijsgDfi6l/G8hRClwJ2qsshO4Vko56P/my8CHUK7F30spHz4se/86Mb4AKTGSxRhOYghBVcikP+dgDg6x/YmVfOET52LW1aiaZylxd7bR3p8iYqgu8o5UaVfDtkPWUZM/I7bLQNahp2WQVWs7sHSNkVc0Tj+xmoH2JM1zpoJpHFRGSX/3ECKXRg/WwzPLYTBFRyaPLpUQWjLvqfxfTU0wDeUcyoMmQR1MTahqcYlqiCwY84YEYqxRsStVLDNsqGFw2vHIDwxRNGMKPLqCVLFG/IQFoOuULFnMhct38uwjK5k3r4lpM2r52k8+QV9fgv/75SOUl8eYPr32iMyW2ReOLm4bSohrTHd9tKIyy27t8RCIEOgaSIkwdKaVhMa4XRdxaIxaZDzJBe886Q1zuzps0TuUYfGUSXzo2hu4/Z4/MJI9uIyZeKiZL3zqBoxQGJ5d8aZz+yNvX4DW3QGTqse4/c7lO3hkWz8bRnpIp/q5f6WGaQim1NWzbVeebKYdSLO7mXYHR3L8/WCyZRzg81LKWcCpwM1CiNnAl4DHpJTTgMf89/ifXQfMAS4GfiKEOGJm2fJ5l//5xaO0tg8AkEikCWVzRP2nfIllUBMy+eiFM2g858RxNRoS0rkx3Q7N17pwpcT2JCnHZSSvXoM5B9uTZF0Px/NoNAVmOk/zrApyO7fhuQdHiJh0KS0zEcPtEDHIZvIs7RyhJ5sn4Dc5Tjme77V4uBL6sir1CyBi6AQNjZBfJZv3JMm8arHmSYnjSQRqcmok79KX9dX2HlkDOzZRMzRMND7atEEgonFOuf4ctE072bC2FdPQqaiIM2NGLZe88zReXrmDkZEMHS09dLb20NM9dKTrzhxF3A6AHNVgN2CCfC+oJtlxrNIyJQ6WH0bHpSkWmMDtuojFl6854ZBw25WSGfEAIVvyo1u+xU+/+a/o2sHNuzQUVzNzVuVbxu2ZOBSXmUzk9hLef1IDsVgJYOPmUmQzDjs7hzCDFWjBmcSLJlNc1IxpzQGaOJK1Zw5o3KWUnVLKl/2/R4ANQB1wJXCr/7Vbgav8v68Efi+lzEkpdwBbgZMP8X6/bkgksUiAnbv6GE6k6ekcoDmo1OjaUjaulIQsnebzFiKsAOPEqdGnNzBvSimN8QClQWOMOHlPkrBdhnIuWVeSdjxsVzKUc8k4kqzjMbi6BdwMeWw6tx7chMywC+3PbEK2dCEro4SKQ5xbF8cQwtfa8ECqsuy045JyXBz/fSrv4klJScAgZGjETJ2asIntSjU6GSsIUQUiUqojDeiCl9d10nrbUrIpG1FVDa7faEEIAlOb+btrTuLp25+gp1d5aZqmcfrpM7n26tO47X/u52+3P8mGZZu59Rd/Y+OWzsNwFQ8Nji5uB/z/fZeV0WfKqCa7AGEqNzYahmAxkWiIOaXhN4Xbusxx0dtPY1LFfA7GZ+wc6WXzX1854rh9w41n8va5jehmkf+jIKmRBCNDvSyeVMEpTeVMLtVori1HDy1i9yT3kYfXlOcuhJgELAKWAVVSyk5QNwkw2nSzDtg17mdt/rI913WTEGK5EGJ5b2/v69j11wfLNPjA9Wdz9qnTCQRM7n14FV1+Q926iEXI0BjUdUJ1VWPNBvwdRtQ2MOmD53PZu06gsThIW8omYbsqHxfIOJ4/gaNRZKmULscfGg5uH4B1O4nUFGHvbCWXOXB8sry2jHxFDY5pkNw+wNOPbmVKLMBZ1TEaoxaOpzyr/qyDJyGga3hS7YsQQnk9eZecKwnpGnFLpy5iknM9RvIuGdfD8cDUfMFTQ6MqZCI92NCeIFwchPWbkMP9SM9F+jrZVecu5tzmOL/7j3vIZlVeted5ZLN5GEhw9ccv4dyrz+DzX7maGVNrDtelPKQ4XNw+dDu4ZwR1NOY+6s0L8DLY/X3IoUFwsniWTmfaHuN20NAY1A4ft8uaK3j/RRdjaAe+5gPJNv7rjy8dkdz+xntP5txZU9E0S50nLYxuxJhcHGLpxr/y8o672bzzD7iZJ1ET3EcmDtq4CyGiwJ+Az0gpX+2I9ic2MXGBlD+XUi6WUi6uqKjYx08OL4QQBCyDc06bjq5rVAQNJsUsItMbOe38eYhIZPzeMirSJKqb0BbOYO1QlrwniVk6MVOnImQSt3QCusDSVNFIaUDdkP05hy19KexX2hH9g9ROj9D69HLs7KsbeE0TxGY1k3KCmA21tCVtWkdylAUNTmssZkpxCN2PN5ra7uGpLgRSKknUvqzjK30oBb36iEVt2GQw5+L6RSI5Vw1j046HJiCRd1mtB9kmDfqWt0FWIJMJcitWAhJhBZl57RJOC3nc+sP7WbVuFznbJRwOUL9oKkOJjK+dox0VfVYPJ7cP1T4iNXZ76+M3ORris1Ct4pKqWtVpRWTSCKAiaNAUtXihLUHt9JrDyu3Pff0KPv9378XSa3h185Ll0fUb6EmIN53b/7ehmwc3dtH1Qst+uf21y+aycGotWsgES8fNp1jVOYwc6+lqAwMo7fsjEwdl3IUQJor8/yelvNtf3C2EqPE/r0HlB4HyZhrG/byeIzQxVAjB2WfPITmpDte/X+JlUU47c5bqyzgecgSVBCsZ2rCLtqEMtRGLqpBJzNQwhCBu6ZQEDIoD+thE0Kia3a6kTfvWfrxntxOMBmhaWM7Q6g149qs34o2Vx+lNuARmTOfcC2dz6owKaieXMuXGM5gzsxLNr8QzNUFQ1/D8dLG4pfahNGigC7BdiSbUcHVaUZDqsInhZx5ETZ3KkMm0oiBeSRy3uY6LPn4pk6+9iPwZi3GjxWiaRrAihNLfAK20jIVXn87QS+v53x8/iOu6fpOSSl5YtuVwXK7DgqOH24Psjre7THzOjFYOB1BG3gEGSQy18vv1Xbh+WCIrJZdevviwcjscD/HNH3yAb3747wkH9pYE3g2HgeQutreNvGnc3jKQ5q9be/jTK0v58M9+xft/+zcyVmyf3F583ZlcM6+ahpIQuGp01DqQJhSZfAiu5ZuDg8mWEcAvgQ1Syu+P++g+4EbgO/7/945bfrsQ4vuogNQ04MgUZQAMQ+Osd57O9p/cQ8uITdsrWyi9+eJxw1YJ0oORXugdxs0brP7rSopNHcMvrAjoGnkhMTyImbo/ASTRBAQMdSOZmmDncJbSlkGij29CNJRSPnc6/es2UzJ3JsY+KjulJ9m4cjuVTgZhBWh6z9tostMgJAibSbVxppaGaUtkcSQsbiqmrCIK4SCJrmGWb+nF9VRJtuNJgrqGqUFlyCRs6OQ9yUDOYedIjqlFQWZXxTjpxkuYOX8SQgg1uglZbHppLaWeTbTUIrBlB1plDXpRjNCsqVxx6QL+43fLeOyRVVxx5clMmVrDn+55gavecQrGa0j7fCtwdHE7iTLRBrsbWcNY+iN5dmfQSMABmealli42DDbSkrQ5fWo5TdMbDju39YZS/uHbNyB1j6/99P/h7bMXqUV9+RQqo9qbwu2pxUG+8MAG+hLrUZE1g6fWuvzuF/dzYlMxNU1lOK0jVM2dgVVSRGjWVK68dAEbelP8ZTDBYH836YxBPF6P0nzP7OOYjiwcTJ77GcD7gDVCiJX+sq+giH+XEOJDQCtwDYCUcp0Q4i5gPcqFuFlKecSKfQsh2LW9i7CU9GTyzJhaiREdN+PvOciunbBlF3Qm6N0+wLodAxRbOkO268ciNcKGhiZ2p2kFNQ2JpCxo4HpKE6M367C5YwStK0l3bhunX+1RvGgmTkcXWn2N6tIEeJ6Hk84xuH0X1dowdWdMAi+BMEJgFDE6qdbw7gv5wNuGSbb3g+dQNKsZEQuDHoB0mtlrt9D/wiZ6dvTTNZKlNGCgCUFdVZSqKaXQl+a5jb0sc3TK5k+ls7GMi2c1qFG6PxQOhAJMPXk+jp1n+XMbOOW0OmQuh+7aCN1i2mWnccqzm/nLzx+iorKI8soiOje1sfaV7SxYPPVIT4s8irjtKsMng8AwKiww3osfjb+P/yxESShIxNTfEm5/6kvvZcPWzdzx6J24Y406dIojtVx62kV86e+vYfr50w8rt3+3sYffr22nSPfoH2n3z48B5Mnlu7j569/A0uPUVS5kYGgts5tL+f7P/53Fpyxi2mWnccazmxnJOfwtlyPrwuTyMvLJGfQNr3wTrvkbwwGNu5TyWfaf73P+fn7zLeBbb2C/Xjcc10M7CK308aiqKWFQCIKGRkVZFKGPOy2ZFNm/rGDn1n6ipk77cBZPgqmrvNqIoe32oYQ+lmFgGYKIoWNpGq6QBHTBcM5hh4TyoMGmgTSDd7zEu6Y3YpWVkti0Bb24iJGsjZVMEQh6lDdVwDC4a3aiOS7SMsllPAI1leiTpyBixZixEkqaxmnWSBhZuQbPzlN06iJiJ8ymcWcb2Q078QZHCJRFME+YjJdM8NiPnmXQg8989RoWnjAZKWHVi5sJBUxmLlLDz1HvPZHM8tzSjUxdOIW6mjJGOnqIVpail5VywTtPYeiWJ3jo9qcITqrGymRZfscTTJ5eS7xofHz3yMLRxW0XVYkaRHnrHspLH82Wcf3XaB68BQRJOy5Zx3truP2NRn762+9y7i9O4r6nluJ4LucunMfbLj6dmSfNQSSGDyu3W4YyrN2xmZHkOnahU122AEEpnf1L/fM0gOOmkKKZYCjGQFeYZ9Y8zb133M0JJ87fze2BJ+hN1/JKb4q6WIB5C87hl891kHd6OJJxzFWorlu3i1DYYvpryNJoa+0j6LjkXI/iaGDi7R4IkDMNXukcIZl3x4aBIUMpz0VNVfTRk8kT9BsFBDRBxB+yDuQcIobS0m5N2tSEJZVhk6zrqekxCVq0iKJZGjgeUdtAWjkSG3fx7B9f5MlX2hlJ55lZEsJxPTb0Z5hdE+Pii2dTfepcrPo6hGFMGGrrsQjCA9AQgTD69GlEpk9VsUNNA6GhDfdw6kcvpW0gReO0Gj8MAzPmT8LahyxxSUmE93/iEiXsgeoRKweHEUUxJi05gXNe2c5dL7Zw3Scvo7okwra/PM8Ttz7KkhsuIF4UPtI9+KMCgaiFawdxcp3sNuoaSopgtJNQHGXkTSBIOBBCE7xl3I5WVvKBr76P9//j9WA7MDRIYuMulv7kwcPO7eyLW9Af+gWjCU49g/1Ib3zRF0AO11nBxpYBENWAzg9v+Snkbb7y7X8a4/aWoQwvtA7zeMsQ751VycVzr+ChdQ+Sz3dypFaqHnPG3U5l6ekafE3G3TMNdiRtpZ6XdydeK80gUBbBkarjuiMhbunYroepCTQEWUflAGtC+kUUoDuealTmekQMjZakTVc6zwnTKjjpmlOxH3yFeac0YzQ0gHARUuK27WTTfWt5eNkuNvUkWT+QoS1lk3UlFSGDmKkzkHN4vnuEpS2DVN2xgksunMM5H7kMLRhU+ysE4alTJh6g8POgjd3twkRxNfHiamZ6HvmR3U0IwuEA+4Jh6NTU7pY8FaYJZaWAg2aGOOHaM9i2rYe/3PMCn/uHq3hhWi1L732e5778W770/95X0J05BAgHdDwjynDOz4wBxnLcxwy85/+vmnkkbI9tidxbzm2v/c3n9mWzp/C+ZZfwP7/4KQCet7/MliR5extKcdMkkR7g2//7fUqmNfPZz3yME649gyVbu/nrzkHa+9P88qVdnNRYzAnTrmD51tW49k5UuCfNkWTojznjbumCLWt2cuFFCw/q+zk7z8x5Tay5O0BV2MVJ+U11RyF0AtNqqYhuoCOVJ+9JSgI6Q55EF8p7Gcg5eFIVdGQcj6ipo6uqbn8mH78rTp66qTVETjuBixbNgoClhslyCNnfx/O3vsQPHtvGDlegpTJUhUzmB8N0pGwiphJQqg4pz2hVf5p8b4qXu1+gYXYDU847eaJ3LD3IjUAgPjGneQ9oQmDFwvv9fH+QUpLJ5Ojc3snkOU0YzY3MmFfH/Y9voLNrCWeeNYuTTplGZ8cA4Uhgwu+Agif/miEJeBmKipoYHgyivE8DZdhT7C5uMlHhGw10nUFHsqInyeyy8FvO7e8/soVl3SlqI+abw21NUNO0VxnCfpADVqAMNIDJyufWIv9eYjQ3MnN+PU2vdNDRn2ZkeJgn1mzANDRcZ/SBMcm/BpuYODJ463DMNetwhEZX+8BBN2y2TIOa6hKkZRI3dUKug3THXRwhEJMnM31mJaUBnYihkcqrhr05P5c243gENNUZxpNq4mlUwKgnk0f6KnauhJqmUhUCCUcQuqmkVlPDtP11Nb9+egctDnzkpotwwkFcCZNiAU6tijIpFiDsS6BmXVXBl3E84k3VPPz8drpXb9pDdlWS3tVC55pNSHv/+fQS6Gvve80yAcM9Q2x88GnMVAY3l0VqOsXzp9CbyPDlf74Lx/UIBkyam6sIWObY79IZm+df2nakyxIckUjZg4RDFogwuzNngigvfbSYSUM1eQ6Am8VN5UjknCOC2yv70vSkbTpSeVwpD8jtdb0pPvev99L5yoa9uD2ycyerHn8Jz87t93x5UrJpbctBnl0X9ZCUVBbV8d+f/jpDO7q57Te3j3E750nCsQCIIaT3Crb9AnjrUNmwG0CTaMGFHCmSBMeccZ8ytZqB/gSJxMH1OxRCkEplyWVsphYFcZI5ZHo8YQQiEKXh3HnMrokDfgm0o8iW84eweSmJGBohQxVd2J5HkaVz5Zwq5tQXURMN8MElU6k/54QJ117mM7Tf8wo/vnM1q/vT7OpJ8Mf7VzBtThP50jgdGdUWzfUkcVMfkzs1hSCP4Ib3n8dZ7ziT//zJo2z86/N4uVHvTMOqbqbEtJCZVz8XjufipDKvyeCGo0HmLVlM/UkzcaUOEkqm1POFf7yKiy9agG3vWxI1FLLYta2Tjo7Bg95WAQqZ7CABXUM3YqjHsgtEUJOnur8s67/XUOl6eUxDOyK4nXI8NE3Qm82zdiBDazK3X25nHI/elM0Dqzr44Kd/uxe3zaom9IyDTO8/JVEIwbXXXs2k6ubXdJ6zOckv7v4LD7z8KP/2rf8gOZKmZEo9A8Npspk8iDR7e+ceeFsoidZiGG9+Uea+cMyFZWLxMJXVJezY3kVZWeygflNeFmPR6TOxX9moKuDsDKq7vA8B5rzZnPoRner7XmJ7+zA528UAutJ5QqZD3vEQQinpVYVNqiMW9U0lzL7+LEQ0zpl9IwTqKtBicXbfAZLs9nZ+/qc1/LVliGHbxdQEq1fu4MLz5rHolOmsWraZ7FACQxPjtKzB1nUi0uHL/3Q7rucRkx79Wzu5ZsVW5py/kOrZzZhFMYxZr34OhBBUN1Yz1NlHNJ/HKD64Rt5WJASREHk7z9D2VipnTSZeVcoJWYchK0Bn9zBTmyv3+p0mBLNm15NKpKDu6Gpb9lbDcQbI5FKEQnGSeZPd3Zd0dmfQjBodAThgD9M+lMF2vbec25YmiFo62bxHbzrPy70p5peFJ3BbKVG6xC0dogE8oHsow7//54MTuB0oLmLuZae/6vkSQvD2Ky/kt5Ff8S/f+B6PvvAoBxMySWQ7WNXSga4F+OBVf0ckHEBapcysibJzdRfCMJSG216wyWU7CAVrGUm+9Zk0x5xx1zTBiafO4KXnN3Hia8izdlDVbFuSObLJDJGq8Z8KhG5gzJ7NlLoipuQcpAMyk8OzHZyOHlIrd5FO5+keyDB7yRSCzXVokydBNIYQGqGKqr036nlseGYdj7Ql6LM97LxqM6ZLj6efXocmJUJCcUBVB46WVEctHaskRm/nIKZf4ZpHsqo3xaa7V5K462UWTirjo+85nVMuORkjHvNDk/s+F0IIimvKGdq4AydpU9Fw8J6H0DRSfi9VPWDS3T9E08LprzowrSiPs+ylrUyf1fAq3ypgb2TpS3RSGq8lmQih4sOjjTtGwzJpIOz/rbx52/UOCbe7BtLMWTL1NXH7ge0DdKbySCRhQ8fSBIal/pcIWpP2BG5HDI0R20UXgsqQCuc5ciK3F0wq46brTuO0y045MLc1wZkXnsNPI8WccWkfPcMreHWZ3tEiMInnORTF4miaBgGN2fOb+OvKTpD7L85z7AGsSMFzPywQQjBjTiN//eNSBt57DmWlB/beHcdl85oWaqXECFlYRUX7WrP6V6w0M4SfpaAj8QIBdj6xmYpF0xjsSxK+8BREuPRVJ3sA3GSSh17YwWe+fDW/vONZXlqxDdvzy6uFIOVIXJQuRkD30P0CkpgmSA8kiFk6SFV6PWS7ZF0XDw0pJTvSHnev6uSP9/2Uj12zmLqGSnTLwCqNoJeVIYIhP61RjB4dsWKLltVbGWjtxqgoZdLkqn02F3Edl64VmyitL0fEwgRjfk9KTRDKOliGTiBg7vW7UeiaRnNj+QGvSwF7QjI0spPF06fT3lWO67Si4sSgrqCOMvIZxiZbhUZ5JIDjvX5ub39sE8+1ddOecTjpwusPmtv3PLmJDX0p0DUsXezBbVXpuie3iyzDDwWxX24/tr6Lv371bt53/8sHze1JzeX847uv5v5na1i+bT2pTAeSNLsnotV3dVHDhXNOomtkB32ZBOU11WPcnt9QpQTkPZPdNQYToQmBcI+MLk3HnHEHqKwpwTJ0drX0HpRxT2dsQo7D9AXVLFqyEKO0ZNyno3HoUbL4p8xzfT5odLYOsK6mnmvedjra0hXg6QckP0iGWjqxy0o5b8kc4iURPv6ZX0PO9ru3g2bqShPEVeTXhCCZdwn6ecbSV+XTBVSHTPKeIpujwWDXAHfd0weepKd9kMUVEYoCBuURi2BJmKoZddQsmEz5jEa0aFR1lK+uo7m8ksG2HlY+vQqZnkZlYyVdW3cRKCulaYpKL9U0DTMWhoFB0G1qpjf5eiWSztZegv0j1NW+SshFQDz+2jN0CoBMthsdj2AoTmpERxnyMCr2nvS/NVqhCkLXqYoGmD739XG7dVsPN/1hFRtbH+c7N777NXH7/jVdZGwXDImlGwR07ZBw2w3AkO3wx+WtB8/tmjo++8PPcOOud7P0oeV87+d/YOPOF7no9HN47IVn6R3cCghc2Ul/qoXTp8/nY1/7CDMWLx7jdixooAdM3EwIJUGwt6yCp+t4zv4ned9MHJPGPRoJUN5QzppVO1mwsPmAoZlwyCJnmUTOO4HgzOkTySsleDYSEzxvd1HFUC/09SMbmoiXFrPkjFJ6tu2kav4UiO7LO5oIKWHLK9vJWRZ/fmAFjy/dRFgDw9QJGRrDtiqqCuiCnKt0MgK6hqWpzjIagow/4aULKLIMArpgMOf4Lcg0lU0TNNCEElyS0iGTdxnoTiI29jDypxUsmlzG1Jk1GOVF1DZXU9xYRUltOee97yJSQ0k8x2HK/MkM7uxGui5C1xGaoGxGI8n+IeLxoMp5V0eFnUzw1JNrec97zt7vsceKIoQiwYO5lAXsAc9L0jsySDQcITUSQBlyC0QJyC6UgddQ4RoX6dr0Z/Ovk9uN/PxXDxEN5PnKp27i+o++8zVxuz2RxTQ00JVHHj9U3DY1cq6S+X2t3C6tq+CKj13Bme84k86OAWbNaeQH//xDvvLv38B2lVF+accqiuorKaqqwQqNyjVI4gGPWCzAUAagBiXnPxHZnENOjM9OK0FNfL/50sDHpHHXNI3TzpnLgw+uAM494Pd1XSfQUEnfYJr6saW+V+N50Lqd1u2DEArRdNoitby4HAwTz05RNKmWWCaHXhxFCwQOwrMBmcuycWc/H73p7Qwl0jzwt1WUWzqmKRjKuSRs168slAR11TrM0gQxUyegqbLwgBRETaWQFzWVznbWVR3fezJ5tJBJY9TC0lQvSldKerMuxZZOsWWQl5LergQbdw7wUl+KgK7RUBKitraY6bUlnHzOTKqnN6DldEqbqunY0oYmBdUzGnBsB+kPV1U3BOX9lRfHKJ7y6p3AQyHrVT8v4NVg0znQSnHJbLqJomRnTbCikAugJllHG3F4ICWrupOvi9v9Pd08uOw+pjdM48v/+gnMUOiguX3/4xvoH7GRAkKmTm3YJGxqRxS3Z05vQMvZfOorN7OrZ5BHH36c9e0vY+gm17zrerr7eiivryccDgKCsqIYup1RKppUAi3sNUHrJpEU++e/GMRikFsoGPdDiFPOmMVzz28imcwSi7166y9NE8w5cSqb1+2i7rSFakQqJWRGIBSH+ik0VDrjPFRAMyBWipbJQCiEGwhgp5IEgwfhkUpJtr2LHb0p7CfXcuttT9HfPUSxBiFLJ27pWLrKTnCln7ls6kRMDQEUWaroI6OBoQk0sbsbfGlADX+LLZVahsDXvs6rYnWhbibXb0WWc5XuSFPUoi1p88KuIbI7B8m625j36Ho+NKeKExpLqLjkBCpmTKPr5S1IWU8gZBIIFqvj8c8BQqCZBoZxzGXYHlEYTGwiUjQd9Ai4/UAWckmU0Q4yKj0wqjHTPpxl9cs7XzO3H7zjETa2rKOlu4UNq9Yy/7SDaDrlc3v55m40SyceNIhbOhLGpIOPRG5/94df47+/GOPLP1lN3s3y8b//CLou+MH/+3c+/vmbVX8C0wDPV+AU5SCrUCrQE64OSjB0EVAEsgfoet3X+o3gmDXuoZDFTZ94O9arTOyNh4PgxdUtnOs4YPqTUcGoP09loAUccFKMTyOTnkvWtgmFw2o74uBCDdJz2fLkKh5dsZNtj6xH5h0CusC0DIosncaoRdZVinydaVt5NH63GfB9srFOOOomAAjqGkWW6hsZNUwsXTCQczH8m6DY0on60sKulIQNjYStemPWhE1qwxabhjPsSOQYsh22DmdZ0TmCcDxm3PcSzTdXUz6jwQ9zid0JCoFRT1wiLYuqusJk6eGE6/bS2vEyiCYghqquHERNpsZRjbIt0CLgSbKu5KV1u3j7QXJbSkkuk+WFF5fhSZesnSRl70u2d2+Mcrt1OEvY1353pSTleEc8t9vtEaRUnrjn5fA8+Omvfs0NH/0A0ViYXX0pEumkOs+aBFEPzp7G3QbWoOZB8uxOV33zccy6WEIIKsrjBPYhgrUvVJTHeX5DFyNtnWAnITMIQmNsNl0PQUBNzkop8fIqrpZxNDzPD0sEDmaSUOJ0dXLXg2tp608SlB4hQw0tK4MGEVMNS0sDBiFDUGwp3Q13tMUYEDI0DE01PB4d0kYM3fd0fIsrlEdUbOmUBgwihkZp0KAyZPhNGHTChkZJQKfI0sk4St1vZnGIheUR5pSESDsez3cn2ZWy6epJIts60KTNrvU7yKayuw8p7ReXeBKtIk5l1YHjsgW8EXhIexU4K9id7ZFit/yvptL19CCIAK4neXJl20Fzu2PXLq591wf4ze1/QY0CTLAO5pru5vaI7VJsGUcVt7/2xZtYOPUiAsZu56SxvAJd08CTvLi1nXx+ECXV2qVmd/eZgumgwjAZ3kqtmWPWuL9WLJrXyAVXnsayh19G6gEIjFPQ0wx1MwiVepjqT5BJ2whNp6QsdjBhyN2Qki3PrOXhrarkP27qlAR0JscD1IRNDKG8E9uVpPIenpRqmOp4JPMuYpzDHDHVjWD53WocTyKlGv66noppqmGtGrJ6UrUqC/uqf7YrKbJ0qkMm5UFDDep1QXnQYEo8SG3YJO149GXy5B2P/FAGW0Jnd4Kd28YNNU3VmFl6HoODqYJuzJsCFyU1v4XdA3AN5Tnm1Od5B6SNHBlk5c5+nrn/xVfldiad5Xe33MrFF13CX+6/k0y2BWWoRqWEDwAp2fK04rYQKsRyNHFbDwZwZRXR0Gjevsa73ncjoXAQ6Xn09Q7758F/KIoQR3Lw47g07lJKHMfFybsMJ9IkU1l0XeNjN12IEy8i1dYN2qh+x+7fZIaSSM8hUhojHI+o/Ff/JaXEcw+sZ+Nls9z75GaSukFF0KQ4oBMzdDShMgTyfkPinOfhSElA13CkJGIqkrueuiF0oXQ4ALKOR9b1SDsew7ajsgeQDGQdpE962/MYyjkM5lwGcw492TwJX58763qqF6VkrDlDdchkelEQBGwYyqruO5ZBpLSMKZNKqPW9cyklUriAxMnmkGJ3XryUkk1bOws6MocVo308g0AItBLliYscmEKFYbwUQz29/MetzzOyq2uf3O7Y2caNN3yYD378I6zdtM7/xGG0AlZ6B35ge9ksd/1tPe0p+6jkdryiku9/70aKoqOTpJK777mL4cQITjbHjtYB1DyGCUQQ4RL/7yMTR+5j5zAi77j897f/RHUiwc7+FIPhEF/46jXU1pZy4vmLWP7nJznng5UIc7eaoT0yQn/vMHVF9WPG3LUdhJRg6rh5l1RimOKKMvYrHCQl/VvaeGFdJzHXwQNSeZUSlrBd8r6XYnsuMVNTXW5MQSLvYQqBK8F1JRnXodgyEEDe8zCEYCTvUWwZOBIyjkulYeLgkXVV/NJ2PXK6umEcf4JK3UQeIV0jpAsMAQFdIIRGGo/GaABNCDpSNh2ZPKIojG4YlNZX4eQlSEkmmSKfzBAqEmT6hmiasbvqVAK2fcQ24TpGIIFOoArQwQgwa1IFF9XF6c+7rOhNsXmnxM2leW59B/ff+jjv/sq7J3A7PTjE9dd9iCeXPTK2zNIjGLpH2s6iI1nz8jpOP2MxB+L2K1t7qY9YePIo5LZpEK8KkcoOIITOu9/9UbxkHx0tHZRaQdZsaWO3524gdB15hIiE7QvHpXHPZPJ0be3gqgqT8ystHm8f5Jff+SPnXXsWVsjiqSc2csa5szCnjeYFS4Y6e9ED0bGQgz2Sxu7pQ7csMp6H50FFWXzCdsbkbUGFLfJ5/nbXUpJZ1fzA0oWfk44vzKSp/F9NxfIMTdXAWX68MZF3iRgaMVMn53skAjVk9WBs6Gm7YHtSpYn5DRhGPaO8JzH997pQ3wsZGhrQmclj2y4xX9a1LGhgaErEafVglqsDEQxA08EKBPE8iZOziVeVgNBo7R6kbt60seMXQFND2WG+mgWo3HYJRMCD+liAmxfVEjE0Hm8b5tchk+U7+8g4kleW7+SaHTsncLu/rYtNm1v9dQkaKqfxs+9+l4amSp55cRnNzVM49ZTFE7Z4rHL7z/fdTfdgH7pmcs1Vb+eKd7wNoen8/if30tnfiZogVS0NPcflSNJv3xPHlXGXUuJ5kngsyCe/9i4e+tmDlAwlVQwuO8Jj//lHdmZdzi8PIlrbYeokEBZSQpnpMtI/gGyqZHAohZPNUdJQgxkwCY0V+u3xFHcd3J3tGFOakFLS9/IG1q5qoSJo0J1xCGgaEUMNT2Om7nd5V3HJnOtREjDIOB6uhMGcQ1vKpsjSqQqZOFKiodqheX4Zd0lAXc6ArqkbwBCM5F10wVgXeUMTeEBACGw/jpl2VMGIlOqGcKVLQBN+XrGgIWqRkRJ31Evxs2WE52EFLIRm4KQzlFaUEByXw97Xn+Tnv3yUL33hSnT9yPVwjn64oGXBqAM7x7Kt3fxL0ODUmhgLyyN89aR6Hq+Ns2Eww4KivbldFRKcNXUxd73UiqY1M2XGDC647u1YQYu5S04D2Hse5RjlthQqUh0wTWpqKtAMk9xIitt+/xiul2DUa9fMOPF4gKF0wbgfEUhnbNZv7uSkhZOYNLWGD337/fT0DPPKQ8uJr1jPaeUhFjmS6rBJZlMX0VNGyDs6sneQlK0Rm67KQIriYTKmTm9HL7F4lGjpvpUUhW5gTG4EILOjnYdufYKhTB5Hql6TpiaoChm+VrZKFzOEwPHzdDOup7IE/BtAE4KAro2p5lUEDTypmiqASiETaOQ9T+URexLbU4UirqfIbWqCsCFUZx7XIy/Vsoyjfi+R5FyJITQMP/YpBAhX4qSUQJibAy0oGR4cIV4UBSnp2tpGrL56wnnIZW1qy2Po+nE5tfPmQuQgYICdJDGc5P9eGOAuI8epkybx9bNmcU5tjFMqoxO4nUx7rHj4RX72yzv529qngBye18rzy1r5yhe+yac+/TEapzYeV9wuK5qEEBqnnHQ6CxbNBylZuXQtT6/YgJqotgET3TQJyAy7O2IdeTiujHs4ZLF4QROu67FmTQuzZtVTX19G5Q3n87AQiOfX0JOxGbQd2l/p4NIL+7FLyrDq6ygJWWMk13VBNBoiEqmlp60P3UipCVYmqnWMevL5tk7u/8Gf2bxrkLqIRVBX6WEpx8V2JcLPItBcj1ReTSCN9qyUfhFHYzRAMu8yozhIVyZPRdAk7A91h2xF6pwr8aSSDXalGs6G/YKinOeRcyXJvAQMJA66EHhSEV4X+O8BoXKjdd+D0hBYGoi8b9w9F7e9i3g8gjB1vLxNT9cgNXMmtkBzPMnpZ80+vBe1AAU3Adk8aCbBUJhcugU7t5qnN6/iG16WL5y+gP6sM4Hb67tGuOSmm8jkelAZMQBJcjb854+/yxNPPc79D95DdX2NaryB2J3Rcoxy+4MfvJrqgMfJS84iEA7i5W1u/92TpLKjCpyqIYorYXCkc9x5O/JwQJdKCBEUQrwohFglhFgnhPhnf3mpEOIRIcQW//+Scb/5shBiqxBikxDibYfzAF4LRjNb1q/fxZ3/cjuP/PkFpJRYlsHF7zuPkWmNLOtNsX4wQ386jzeUIKjpaK6zz9CaEIKKujLSiRGGOvtxszYDfQn6X3hF5RNLD5keYeudj9PZMeR3sRHUhk1fAlVD9xsOB3Q1dAybqqCjPGSMpYjlXI+yoEF12KQ749AQsagKmQR1jYCu0Ri1CBkaQrA7BinB8B0uSxPoQpV3R0wNz58GUmFTQc5T2Qj9OYeUo7IaUo5L1pFjw9eaWACruFitLxrGrK9Gi8cQQjDU0kX1tMYJHrqUkvraEqZPO/hetm82jiVuwyDkRwiGQ3zg1ClMq60FbJD9PL/1IX61evte3J5SV05pdDS7ac/euZKX1y7n1lt+y9oXV3HtO6/lysvfy9p7Hj2muV1SVc57Pvtxpi2aixCCtnU7+cNDLwFD7JZVDuJ5OnZmx2G+pm8MBzNezgHnSSkXAAuBi4UQpwJfAh6TUk4DHvPfI4SYDVwHzAEuBn4ihNi/APJbgKbGck5sKKFrxRZVgASYlsGCS08mGDCREs6YWYE1uQG9KEbHs6sYaN23+L6maZjhCAFDRwtalJiC4rlTVMZUpofMk8tYs6aDgC6YHAtSEzYpDhhjHk5pQEcXgpCuETV3xxiVUp5SzasJW8RNJUuQ84ezACFD6W4EdFX0UWzpBA0N2/VUNo9UzyRN+AltAgJ+OljEUOsLGRpBTU2AxUwdIRgrPAkZgpKAEm2aVBMnUF0+5rEJIcZy27t39VJeN3HitLtnmEefWnek57wfQ9weBl7EyW2hOWJyamMdo2l6nhzgiU3P43neBG4X19fwzzd8lobiGex7YtDj+//zI9597fX88d4/ke3roPH0eccVt//2wEt0D3agdPJdIIBmVWNYGZB9h/mavjEc0LhLhVEtUb9cDQlcCdzqL78VuMr/+0rg91LKnJRyB0o67SBEKd48xOJh4jMaiZVEJ8yBVtWUckJdMYvKw9TMrkGUluM4DsHmWuK1+8/6iJfGCFYU4+RdOvuT6NE4MpPGe3YNXc9tI2k7ZByPvKeqUWOmTmXI9PN7NYoDuh8v1KiPWIQNDduVlAVNZhaHlFqeL540qquh+WXXoBoVO35+sCkEuqbilxLl2eArdAd0NaYO+IQXwp9kRpV3lwUNikzVMi9iaIQNVelXGjA4YVEThCN7HXu2f4ik1DHN3RE+KSWP/G0VRdEjW/nx2OK2BHpx8it5qa2VtD0aQlDI2u1Mj5sTuO26Ls9uX0f78Fb2FzvuHWxnXet2dM3iw5/4NPGqquOG2+m+QW79w7N43qi0gweEicfLMNzRtMgjFwcVc/e9kxXAVODHUsplQogqKWUngJSyUwgx2lOtDnhh3M/b/GV7rvMm4CaAxsbG138ErwNCCCafM49k2lZdVnyUFEeYNLmKu59Yx+yhHPOFhkxlKWmuwzyAjMHmx1cQry+lqr4acgmyD73Iyqe3s3MoQ8JW8Ufbk/Rm1PDQ0lQMcFTP2tQEHhqGn6aVznsEdTUBVWoZjNguZUFjzDOSqAKPgK5uoMGcSzLvYmiK7BFDA6FaL4xWAgoh0FATSyrTQGUkZBw1mB3MOWNZBromGLFdso5HRdgkPrUWISb6AlJK+nd1M/PE6RM89FQ6R2tbH9de++pt0I4EHG5uv/mweWrbZlSb690G23EzJHM2z3V7Y9z+0+/u5/YH7sCTrzYpqHP92e/hlItP5JJLzj6uuP3ik6tYvnE7aoAHYIAWx7Q0hvtbOdJxUMZdSukCC4UQxcA9Qoi5r/L1fY3D9xrzSSl/DvwcYPHixW96PtHUOU17LROaIBow6Ms65P1WWulMjqLS/etqSM/DS6WI1ZVQM30S0sthL13Fymd2sKk/TUfaxvWUZzGQczA1NVGU92DYdnF8F2XYdrF0DaEJ34ORGEJ5IC6qii/t3zh5vyXZqHcT0DVc6RA2NCxdeUaan8OcdVV2gSr79ohZOlIqr2dUbc/xJAlb3TzJvIvrMTbxlfU8SvUAoabqvVI9vUwW3bSIFk3U1Glt6aWuqgjrIHV93kocbm4LId50bvcMb0CFEcZvWuV8b03s5nY+nyTvZPe1CgBMI8Bpi87i/Z++jgvecb7P7ZeOC247qQy/+OXDZO0edmvEhAgEihDuEFIOH6Krdfjwmu4+KeWQEOJJVLyxWwhR43s2NcBoULoNGN8csx7oOBQ7+2ZgMOfSk8kzPDiClB6h4P61xzOJJCKfJxAPUzN9Et7wMJm1m3jmrpdp6U0hUJNAozP1noSE3wR7tKDDkyoPN2Qor8LxJBII+2JJQV1NAus+oS1dNRMOGjpBQyBRs/6GUCp5FUFBxNRwfU1UQ1PD3LE8YClxvNEbAHKOR08mr5T5TF2ty2+2Y/ge2KypFRjlE8NS0nVoX7WFirnTJnjtUkoefWw1p5487UiPt0/AscNtgcrq2CNkIGEok6cn441xO2/byP0U4dRWTOWf/+krvO+D12CFQ8cdt+/91V+596kXUQJgo4JsYWKxYjLpdbx6H9YjAweTLVPhezUIIULABcBG4D7gRv9rNwL3+n/fB1wnhAgIIZqBacCLh3i/Dxua4wGipk5rXwocDyNo7dNISSkhkyVQUoTMZNlxx8M88LXbuPVHj7OlO4kmVJ/IUa1q19fSkEhFbEMb064ezQLQhWpQELdUFd2oNGrO91BUIYimljnqxjJ8IkdMDU2o8mvDX551PaKGNvY7pe3hxyPxc38lxEydkN/wQKLWkbBVWUd9LMC8C+YjrInZFMM72shaIUJ7aOXn8y59rT00TarkSMexye0YKsI0BRjnmAhoLgpO4PbajWv2sw7BB69/Hx/65I2YnnvccbtvUwtf/487Sef6UA9JHQiAFqe6KEwmc4Q9z/eDg/Hca4Bb/dikBtwlpbxfCPE8cJcQ4kMoebprAKSU64QQdwHrUWfmZn/oe8TBdT127eqjqalizIBXhk0ubyrGS+fB9cgNjhCKhPcy8NLOo6OGkJ2PvchD975CzNSw8+pQHSHpSOfHCjpKAgZ5T455OIam2lHmPYmD6gyfkX6MUhcEdINk3mMg51AVNtFQxJSoTIJk3iOZ99CEyvd1pfrf0rSxzAOl5SEJ+SmKSUfFJPOeJKhLgoZG1vGImhpSquGz6nyj+4UhHifPqyV+wqwJw1bpunS19DL5zIV7ndOWlh5cx6P0IHrXHgE4BrntZ8lotViBUuzMMka9zIqwyeVNoTFux3TVYWjPyFIsVMp7r73iuOX23Xc+w+b2TtQlHtWSCRMIlCHI4ThDh/MCHjIc0LhLKVej2orsubwfOH8/v/kW8K03vHeHAWOaGL7417MPrSBy5SlU1KiGzo6EU6uiDOoCmcuCaeFkcpjhiZkfLpB1wZIgU1k/1UvJjzpSknRcXE9JmxYH9LFhbMTQfMEwF8dTebeWpjrDj+ps6EINRaUxKpMuCZs6qbw3Jnvak8n73pCSRtUFlAQMpISUoxTxPA+ifjxTCJUulve9pFEYvufjSumXZytJ1qAhaCqLMO2K0yA4LqYuJcNtXYxo1j4nmdetbWXB4qlHRTemY43bEARRC/JlkB7Tqi9nZ2cHqWwLSInrehO4fd0NN/DD39xCIjOxBZydT9ObGGbGccrtn9+5DNfTUM/70UzXOJFYKQMjPeyeYD2yceTfgYcYQ8Npnnp2A1JKDEPntLPm8LfbnySdzinp00SW4ZyLncyRaukkXBrBTe3dhcawTHKOgwTKZ9dTGwug+xNCaUd5HqY/fEw7HinHVXKmPvkCujY2dNSFIKCpoaVElVarJC8wNUjm1dBViN1yqZ6EvqxqGJz1izNyrvLQkraq2HMZjXFqZJzd29JQcU+VEqZyiQ0hVLqYpfKBZ1ZGeecHziE4a8rEmLrn8uxfluGEQ/sMV7308nZmzm06quLtxwqEVoIVL0UVLw3TO7CWU6ecg6ZFAI3OVH4CtyfPbuaic97JbgOmkHMy3Hvfg8cltx/947Os60kzKg6mirtKgSIM02AgsYsjWSxsPI47497T1s/zD7zkV7BB04w6QtEQzz24nJ6eYf740g6eGsgylHMYWteCNEwCZcV7rUcIQTgSwsvnsGZNY/7JTURMfaxYQ0qV9hUxNUwhEIix2X1dqFigpSvvRAIekpKA7mftquFrxNTHyrcHcg6en+87kleqeYYGPRmH7kx+TGLVk+pGKbZ0YqbqXZmXfgm2JrB0NYwe1fGKGKrrfMjQCOkaZQGDhbVxrvrwuZSctRihTdRn71+7hc1dKU5YNHmvc5LN2mh2nsmTq/b6rIDDj+JwCQtry1Et3qBneB2ZvM3c+gswrRmsTbjc3zLIUFZxOxiNctX179jnuh59/AkyIyPHHbd/dtdL5BKjGvkuEAFCCE2nOKBh596afqivB8edcY8YGvmWLna0qAQIw9A5/9qzWLZ8K3//6V8SXTSNa/7tRlbrQR5/cgPZ/gESyRyOs3doNRQwSbV1k856VFx9LhfdeAYnTisnoGuUBlXxRonfF1Xzq+M0oYa3QV1QZBmUBQ2ifrOC0ZtkJD+mUUfU0KgKmdiuyiNO5l2Gc47fmkzdHP1Zh8GcM6ZjrQn8whL1eylVTDOka2NFHqNCTY5UDyrTnwhb1FjMpR85j6LTT0Do4z06iTM0zBOPruWK91+AZe5dmLltezfxeJhw5MguXjpWETUtFtcUY1iT/CV5lu94BiNURW3Dqdy/tZ//enoD/7epd4zb4ag+odZjFIP9vfRv30UylT9uuP297/2FZ9bsALcbJe3roNoXDmNaFo6bwnWP/BTIURx3xj0vJfz/9s48Oo7qyv+fV129d2vfN2+SwRvY2BgwxmCC2WwgEMKSCSEJCQSYIQknYchwMkvmZM9vhskwmRMmmYRJJqzJBMzAsIXYgMFYgPdNtuVF1r601FLvVe/3R1VLbSzb8iJLar/POX26VKqqfq/69rdv33fffdEE7Qe7Bvfl5gf4yjdv4uLL5nDTzYuoratg2Rev5KW2KPX/V4/f50KaklRyKL1MSsnBnc10dkZJ9MdIxgzc55/DvLsu44JJeeh2vYtclwOnw/JZPA5tMHUsZC/e67RTsoDBOtYpexmxuCHpTViry+iaQMLgJIy4YdISSdCbSNHQF2NzT9Sa5GGnhkmscqctESsVrNrvwm2nmiXtlDSvQ7OnbQvK/E4umVvJvHuvwT3/3EO8GpDIeIK3n/oTZfNnUFtbPmzYZdvWA5wzbyqapkIyY0HMSJHvcRIMTgECACSSzazfvZqO3n7aegaIDfTyf1ub+OmaRupfrufKZUu5956v43YdOlchz1XKrbd+ncUXfoLHf/40jnmzstq23/zNa/zy1c0kouma7fZShcQBDZ8vQKivifFcBfLjnHHiXlxVhFlVQmt7H6HQAIYdyyssDPLVe6+ioiyfVMpg0aKz+MnP7qHf46dn5340AcIYKs7ffqCND1ZtpGTGJPKrS9ALCmjasgetspjzrp6Fz+UgYVqlThOGFavsSxhEU9bP1/Zokv6kMTggZEps45fETcvDCSeNwVSw9Aeozz5HSmsAqSOWIhQ3aB5I0hFNIrCWEws6rbKpeW6dhGHSlzRxCEGJV0cTDK5MUxlwsbC2kCtuWci0e65DnzIFkenJSYnR18fWp17jpXf3ce78aR+/pQCkUgbvr9vFjNmHTw5TnB66BzpZ09SFcAZxuOYBXkBipnYS6axHmiZoTiLhfaxv2M+DP3qR1k2N/L9/+g6fufVzg9eZMW0W58+4kPrGD9m4+yP+6ltf5yff/kFW2/ZjT66jJ9SNJeyZ8wR0ELl4fT7CAwdOzxt5ihj/UwhPMf6Ah2/84E5efPlDvvq5f+bqWxZzy+1LcDg0pJT8+ldvcPkV5zK9rpzqykIqP7WYHWu34m7vJFich4wnEW4XReX5LLmgiv7dB/CfWwcCKupqwJlL8LILufxgH0+u3EQ4aeDTNcIJY3BlmIRhEDcsD6Mnbgx6IwFdI4KVMWDFHw0Cdp5uvlsnZdevHkhZOb5d8RRuhzVzb3qBl6vOq+aSeVUYkQShjj7CnQN09sXojqXsn9EO8jw6QhOUFfopm1JIzlmVOGdMhYIiawp2pkcuJanONl781/9lc8JJ/sxJBI9QLybUG0HXBBUV+afjbVQMg2G0sWrLSrw5C7h09gK2NBXS1v4mVlGxg5TkL6Cn20Ey3o+ZSFC/pYd7v/YLnn7mm9x26yd5/o+/ozsc5p77v8bt581gf9tWXt/8J8CkbFo1OPOzzrZ//5Pn+eELmznQn0AaKSxhj2J57VZ+u6bn49AMksm20/yOnhxnnLgLIQgEPCw8v5aVz7/Pm2t2Mn/hdKZPryAUGmDjmxu44hNzBo/XNMGUeXV89OK7nH/VeYi4QaQ/ht/roH3AJLFxC/kleRDwo/vsfHi3j5qbl7K8K8xLa/YSThqkpL2YgEMbrL2RnqgBVt5tSkrybK8oHWM0paTX9nLSMU2/rnHHhTV4ppWRcDvJyc+ncFIRwZpyNLcbJMhUAtnbR+JgO8neXkga6G4d3edDyw2iFecjAgFwuA5fQQpAShItzaz86UritVP55h1L6ezpP/w4rBDVqjc3U11ZqBbmGFMkprGfWL+HXT0lSG8pLs8UErH1OBxu5lUU8Hb/AMm4wFqaT+ONdRt47Pu/5+Ef3smTv/hPHvnuP1EYLGDl6l3cd80N3H3/5+lOJLjjC7dknW2/8C8v8O2nPqKhqQf8XpAJrBh7jKH8fy+5uYUY8S6QkdP1Rp4SzjhxT1NVWcBjj32ZcDiKQ7dicKZpUuwQ9PYcmvrodjvxT6ti9TN/ZsktS3HqToRDUD1jEmLOVNylJekVDKwThEDLyWXmX3yC3p6VfNTQSV/SSusypDWLL+h0DBp0Skq8ulURz6trCHuleK+wSpzGUpL2aApp18u485IpnHvvNThKKw55zUyEw4so8eIpKcGTmbklDtv4GBJpmES2bOflp9+lb+oUbrhpEf/5m1Xk5ge4/aYLDj9DwvvvbueTN16gUiDHAUayg/379+BwFyBTliAJYVAdcOF2uhhAx/JMBzBNg0effpfpkwv51H3X89qyK/E6HfQ1t+EJeAiWl2Wlbf/6sVf44Ss7aeqI4MsPEk8lMOjH8tzTOe464KMwx09X1zYmSgpkmjNW3F1OHVeeTn7eUKnPvLwAddPK+PDtrcw7v25wYFAIwZy5U/kgYbDqube54Mq5uCtK8VelF6IYxpiEwFFRwUVfvALPL16l4WAf4aT1kzVpStyaVZPaISC9gromrIJHDiFw6RpRw8QwBQmsFeIjpmT57DIuuedqHKWVw3slhzfkyLb+caREJhMcePU9nv3tO/gWncOll87me9//PeHOPv75sbuHFe+29hB97SGmTCsb4QspRpceMFZhRPKAbgBSqQGMZISqvCDd3Q6smLK1bFx3z37u/eGL7N7XzX0P34Srupzi6ZPta2Wnbf/r2gM0h6KUlgbJcznYsbvJum9WdXj7JC+aM598n5P9TcOv5zCeOWPFfTg0TVA6r5bVz75F04FOaiYVD/5PCMH8hXXE5kyifXcziYG95FSWoPt8RzQwIQR67VTmfmYx5m/eYmdLH9FUipS0sgX8ujW5A0Ai7bijhqbZEzKENeLvd1r1p6sKvCz/wqXolVVHMP60Z3EC3rOUmKFudv1+Nf/1wkb29kbxvrGB1/63nrbOMH/zndvx+YYvorZq9VY0p05hUc7xv65ilIgDbYf8/e6+bVxcu5CdzcXEYulZqQbQQU9PhL/9jxArV2/ibx++iU/ccDGugD9rbXtmiZ+KPA+GhO3725FGJ5bXnn4tDfDiD+aTSERIJMf3whzDocQ9AyEES5YvoKG+gZd/92duv385weDQTEwhBF6fm5rZk0lGE7yzcg1Tq/OoPG+GFQ8cziiFhnPOLObf7aXg9++wvaGDrliKiL1wsFOzlgLzOhx2aVRB3LBSwib5XcQNSZ5bZ3JFDrU3no9z7mwQR4prW9XyRo41IUX2hYhs3EnbW1tZs7kVF5JCt04JKXwyReUF01l6+TlHLKC2ZX0jFy+Zia6Pk0WJFMOys6We6aXTOHfKZOobohipdD635cEbqRTvbenl5i/t57PPreWr9y3j7CVz0dyerLPtGXle2qNJXtzTTV9vK0OTltKeuwCcFAS8hMItIKPH8drjA5GutTKWLFiwQNbX1491MwBLrLq7wrzy1Gpa97Xzma/dQGlFwbDCFo8n6W7uIrJ1FxXTy/FMrkboziMO4sjebvrfrKfxvd209UTpjqXQBcQMq9pd1Bj6UDg1QaXfRYHfRc3MMgJXLoCqao6+qtuxvBsrJ81MxpGJFEZvH5Ede1n/2kY27OqkyK3zp+Y+XHZNjoORJA6fm/u+fRuXLJ4x7BUj0QR/dde/ct/Xrmf+wrqj3tuxRAjxgZRywRi87th/wDJw6sWcO+UKigIlrN6xi0hkL1btd4HluXqAUhD5lOYH+IcvLOGOe5bhzQLbfv1gHx6HZdsH+hP0JVKs2dnEQN9GrNK+aTSs4ms1zD1rDnub3iUU/uD4bvRpREo57E1R4n4EDMNk/VtbeOGp1Vz72aXMv+hs9CNkgvR2h3nzideY4ZdMuehsnNOnIlzDeTsSDAPZ2UGy8SD9e9uJtPYw0Buzpu4DmkMj6HXiyfGSU5WPq64SMW0ywhMYYRxyGEyTRLifgY5uevZ3sGN3Kxt3tDLQ2EpQWh+X1kiCfuFg5nUXUv/mRrwOwaLrLmDa1FIuvnD6EQdK29p7eeSB/+D7P/0yxSW5J9a+04AS9wyEh2kli6itnMOH+1ro6NqNJW5pkfdhTYIK4HEX8OmFdTx06wKmL5k1bm27c18LG97bwao1O2kPRalycIhtt0aSrNzdxbR8H36H4MODvaQSSRLhBqwy/en67OliYT4051QWnFXH+p0vkEjsPbH2nQaOJO4qLHMEHA6NeUtmU1hZyG8efYH1G/fxhS8tw2nXxMgkJz/Atfdfz9uvrWfNr97msmmbqVl+AVpN9cfyawU4dERpGa6SMgouMMlPpiCVgGQcDNMqqqE7EbobnE5AOzRbYaRIiUzE6W/poKe5C+n24inMo2DeDD58p5GGzQcJmikSujWJ5IDQ+Yt7r2XFivmEbl8MEvLz/UfNfpFS8n+vricWTeDxHnlRE8U4Q8bY3baKrkgnF9UtYYPTTXPbXqwFn61qMNbgYohYPM5v3+5l1Y6D3DJvE/deN5tJ48S2ew608vIf1/LbZ9eyYVcznf0JSipKWFCWgz/oGrTtde0DfLSvg3Cojw2dGpgGJj5I9WHNAUiHfNLOmwMI4A8W4hAGqdTEKTmQifLcj4GUkoP7O3j075+ksKKQv/jK1dRUFx3x2KaDXTz3H69S2d/LRRfXUnHpeTgKCk7cMzlyy4bfJSUyGafzo+3Ur9vDvoRGfkURXodV/zoeGmDTS2uZ6nPSMpCgM57Cnxtg0R2f4LrrFhxXKmMyafDAfT9nUmU+D/3tbeO67IDy3IdDEPBM5fzpy+iJCTbta8eIh7A82ShWmMYH5ABudFcp86ZVc8f8Km745HlUXjZ2tv2rJ1bzzJq9HGjtw+sUJJJJ8v1ultWWMLPAN2jb4XiKP27cS2+oCWu2qR80F2gSknuxsonSs1HTKZA+ENXUTatDN3rZ1vgsQ4Ot4w8VljkJpJTs39fB//zyVfY0h/i7H37uqJkhKcOkoy3EOy++T/+W3SxbMY/yi2aj+QNHGTA6ZiuQhokRGaC/I0RvVx9GOMZAXwRdmgRcApcw6TgY4kBTF4+93kBefgCfNElG4tTluAk6HbgdglKvkwK3Tms0yQ7dzW0P3cy06ZXHLc6Nje088pWf8cDf3MyFlx5t6dGxR4n7kXG5KllYdw1RvKxv2IuR2I01mSeJ5dE6gFwgCMKN253LnJoy7lxcy423XXRKbbu3tZuW/e10NYfwu3T8Lm1Y2+6PJSn2OPE7Nabneg6z7ZZIkhd2d7Jy4w7CA81Yv0ZKQQuCDIPcb/dRMjSQCtbqVQU4fdNYOquGDXvW0da1+iTu7uijxP0UEBmI8cSjL9Dc3ssD376V4mOk/hmGyZYt+3l/5VpK+3u5aFEtBTNqEH4/pgQjZSDcTvSA/cFwOsChgXBgxTBTyFiCaE8vnU0ddLT3ETUtT7x8chnSofGjH/yByIZdzMr3Ejclm7sjdMZSdMdTLCkPUu51src/QYXPSYnXicdhTf9uNwWuc2tZfsflFBXnHPfkI8Mw+bd/e4kNb27kx798gIKCwEnc2dFHifvRcThKOL92OYbmo37nVqTRhCV+g0dgxeF9WIOuXry+fBbVlnPXpbUsWzbrhGw70h1i+4ZG3lq1jVXr9rL5QA9tbd1Ek0mqK0tZXlt43Lbd0BvjjzvaWbdrH8lkF5aw61i/QCJAC0PCnvmFJKw+ikpKKqYwp8TLnzc9h5Ea38vqKXE/RfR0h/nHB39J6aQS7nrgOooKj72cXCplsHNbEx+8uJbA/mYq3Q5aIgkO9ifQHBp5OV58LgdnVeQQcWj4/H76YgkOtPeyals7JWdXc8WKhUQSKf7wzDu4PC7mz5tCqD/Grlfqme4WTAq46Ywl2dkbozdhUOTRqfS5KPc7B2cHGqbkYMygraiAZZ9dytx5U0+oXICUknXrdvGdh37NTZ9Zwhe+fOW4n5mqxP3YOJ3lLJ5xAx0Ryba9OzFSB7C89/QC0SZWMbJc+9kFQifH7+OS2mpunV3BWYX+47LtdXu72L6vm4QpKcn3YQhBPJYkaZhcf3YJF5QGRmzbjeE4f9jZwZo9nfSHo3a5gHQRsAEsIY8wFGeHQwXeCZThzZnM/Gml7G3ZRVPrS3b/xy9K3E8RUkqa9nXwm+89jZ7j5/PfvIniktwRiVsqZbB9WxNrXlhLx7Z9OPqjBJwamhCUenVKvU40IehPGjSG43THrZ+LTVEDt66RMk2CmlXaVBOwL5xgXpGPUq+TUq/1E9UhrLrZ+W4dw5QUe3VihmRvJMn2YC6LPnkR8xbW4fWc+ABoS2uIr3/l35lVW8aD/3A7/glQv12J+8jwe2pZMXcFXVGTVdt3kowfxBLG9FqiEssL9mN58U7SOeGBQCHzJpUxpyxIVcBllyE4um039sUHS/4WuPUTsu2doRi/3NTM2sZmunpDgBekhjUoHGaoNnv6rYhjfVGlP7PpUgMFaO5qzq2txGnGqd/5PKYx/ouFKXE/hUgpaW/q5KkfPMue7gHu+fZtzJhRNWLv1TQlra09rH17K2+9/AGR0AB50sQvDfy6hgb2mpVQ5HGS43LQFUta0UGJVazJlGzriXJBSYCgy0GhWyfH5aDM56Q/adAWM+h06PirivFPLaeotpKz5kzG7dZP2MuWUtLZFea73/4d0a4+vvWjzzN5cskJXet0o8R9pAjy/GfxqfNWcDBi8udtu4lFGrFSJdPx6bT9eLCWoAtiiaMOwonT46WowM/0Yj9+p4NJOW7KfS78zpO37XDCoCWSZEvXALu6+9nQ2k1DRxedva22p+7GCr8kgC4sIU9hCXjaSzcz9qUfuWjOSZw9tYoSr8aara+SSOw4HTf8pDlpcbdXiK8HDkopVwghCoCngcnAXuAWKWWPfey3gLuwLOEBKeUrR7v2RBN3GBL4J7//DCHdyV/93e0UjiBE83EikTjJlEFbWy/vrdlO18FOPnp7K65YHI9dZS/XrqZX5NEJOh10xVMIoCWSZFLQjSMvQP9AHJeAmpoi8mZOpmzWZKqmlBLM8Z6ymaMdnX38/SP/TexAO3d+4yYuWTp73Idj0hxJ3EfTru1zJpi4AwjyAjO5ce7V7O5LsWb7blKJ9ABk6mPHurEGIYNAkb2dsB6aDkLH6dTJC+ZQFPRQU+ijKuAakW1XB1w091uLY3h1jUQyydqmTra2HKSnv5NUagArq8fMaItuv36mp5720sUw+6y2a84qptVUMrs4wOpt79LV+27Gdcc3p0LcHwQWADn2h+BHQLeU8gdCiIeBfCnlXwshZgJPAguBCuB1YLqU8oiBq4ko7mAJfMv+Dn7+nacYcDj47P3LOfeck1scOpFM8aW//AWN63ZS6NGJGSbRlEmxx0mpz4nX68JdECSvJI/ac6bgCnq5aPFMBuwFvsvL8tGHycU/GQzDZOeuFn75Lyvp3HGAO79xE5dedd64Tn38OEcR91Gza/v6E1DcAQQ53rO4fPaVtMbgoz1NxAf2Y3nwmdklmcLpA/KxBl77sLxmsIQ/H1xuckqCzCn2UzSMbZumpHUgTiiSoDkcp3cgRldvGISJRj/JZCfSjGDFzVMMlQlIZ/S4GAofZZYSyJzdqmU8u4B8dG8psyaXMbPIz9sNmzjQ+joTacWlkxJ3IUQV8ATwXeBB+0OwA7hMStkihCgH/iylPMv2bpBSft8+9xXg76WU7x7p+hNV3GEoBv+zf3iS7t4IN997DZdffs4J1zWXUrKrsZ0t25qshQ4Mg337O5lRW07KlEyZVkpZeT5+nwchGDXPWUpJPJFi1+5Wnnv6Hda/tZkyr5PFNy7i03dchtvtHJXXHS2GE/fRtmv7uAkq7gACn6eWpbOuwhQu3tnVTF9oP0O54WkvPlPgNSxxL7C304te+MDhQTgFTl3DJUx0pwvd5YJUnFQyTiwZJx6LIk2wBDmJNfiZLsWbZGjeZfo7NS3eDg4V+/RkrHQ83S4pkG6L5kf35FBSkE9dSZAyr5N1extobH4NKYdft2C8crIzVB8FHsL6Ck5TKqVssS/eIoRIB18rgfcyjmuy92UlQgiqJhXzte9/jlefeJ1nfvIHWpu7ufHmRQROYKBRCEHd1FLqppaOQmuPTSplkEqZfLC+kSd/9QZN2w/gE3B2XQUr7ljKxZfMnDChmBHwKMquj4IkEmvg9U1RLptxDctnT+JPDW7aO/YjzXYO9eCxt1NACMtrT6dN6sAAGANII0mCJAlSWBk3TixP3GBo6r+BJegRLA/awPKydYbEOy3gmeINQ5I2VPxrMHSkBcHhwunxMrUsj+pcD/lunY5whFc21RPqW4c1+JodHFPchRArgHYp5QdCiMtGcM2j1evMvO7dwN0ANTU1I7js+EUIQWlZPp/6y+sIpyTvPbWKPdsP8uDf3Eww6B3r5h3Gx3+tGYZJqDfCth3N/PH5tTTuOEh/V5hCj86scyZz+YrzueiSmXi9rqwR9tGya/vag7adDcQTTbyx+Q/Mn3Yl186YxLsBLzv3uTBTLVgibHL4rYjY/3NhiSv2djrnXLe306mWMfs5mrEvLfbpUEpmWEW3/6cz9CVhMuidC5f1rLnA4cbpdpGb66Mo4CLH7aDApdPVH2FD4wG6QpsxjQOM95TH42UknvvFwPVCiGuxvoZzhBC/BdqEEOUZP1/T1eybgOqM86uAw2YBSCkfBx4HKyxzEn0YN/j8Hu76xo2snlXDS0+8wWPfe5bb7rmayZOKx0wUpZTEYknefb+BadPK2Le/gw0b9hLuixIKDdATjpKMJdnd0EwslqQg10ftlBKW3LaYCy46m6rKAhwOLWtEPYNRsWs41LYndlhmiJTRxdqG5+kOL2bhtHMJuutY3+glGU0vcpHg8AFLGIqBmxwax85cFCMt5unjTYY8b0/GNVz2324GPXKHF1cgl2TCwOHQ8HndaLqGU3dYC4foGgG3bpW+sSdX7e7u4aPeJpKJ3SDbGM+lBU6G40qFtD2cb9ixyR8DXRkDTwVSyoeEELOA3zE08PQGUJeNA6pHwjRNdm1r4hffe4aBeIqb7l/B5ZfNOu0CaZqSP7+9ld/+5xts3rgPb2EOqVCYoEPD5XIgnTqBolzOnlVNTU0xiy4+m4ryAtxuHZczu2rKHS0VcrTs2r52Voj7EA4KgrNZOvMyYlLnT9sPEu3bC6QXu8j04tMFuRwZ22AJucGh4ZTMzJRM7z4djvFiibrHejjcOANeaoqDBD06bZEkFX4X+W4dkPQnDLojCfpiSWLxOOFwL2ayD2l2g2zG+kLKDk99NKpC/gB4RghxF7Af+LT9QluEEM8AW7G+cu8/1gcg29A0jbqZ1Xz9x1/kqZ+u5Df/9r/UVBVSW1t2WgU+kUyxvaGVq66ex1VXzSOSMtE1QUlxDmfVlaO7nJSW5OBwOCZU5ssoo+z6qBh0hzfy4vpeFk+/ijmTSlm/2yARAUsw0+EVGBL09N9axv70gGfa20976mlBdzOU2pgeCHUxGGP3etCcOr39UXrDKQZiMQa6DUyZJJXoJ5nswzD67e8ZE2sQOIz1BZRl37dHQE1iGkWklIRCA/zku8/S0tTFX3/nM0yvKz9tAp9+b7MwpHLcqElMpx6Ho4Tpk5bh8xawqbGdRKQVK4qVxArBpMU9M5sGDhXX9AxXN0Oxc7u0weBgqZFxDZNDQz4RrLTLmP0YsB+Z37uZ4aLsQ81QHUNisSQvrXyfXz/1DnfeuZQbVyxQnvJpRon76CBEHiVFS9D85XR195MId9gzRfuwBD4txukZojCUxZIOy9iDn/gZSmlMD5zCUBpkOjsmheWFp19ngKGYfrq0wJmDEvcxRkpJ/YeN/PvPX6GsJJdFi87mymXn4NRP7YQjxfAocR9NPOieeRQVz8TEQTgcJdrXA2a6bHA6Dp+OvaezWpwcOrCa9uJlxn6DoYHYtPceBlqx4vwxstkrHwlK3McBUkrC/TFefW0Dzz23BnfAy/kLavny55fidmXXAOZ4Q4n7aKOBVkkw51zy8iroT1pZWtG+iLUS0yHedDrNMV3nRQ5dYzCUkznTNB3iCWOFfTqwPPQz5NYeA7XM3jhACEFO0MunbryA5decx45dLXy0Ye9heedpEskUAoHTeWpqwygUo4cJ5gHCoXbCfVXo7lqcvhLweSCmW1XBpF0xzDRACGvbMMA0QaY99nRaZDoUE8fyznuwRD0yVh2ccChxHwOEEHi9LubOmcTcOZOOeNxb7zUQiye54pIZE266v+JMJQ7mblLRA6SiRUAxiDzQAuD0gcMBUiB0HRwaMiEglYJEP8h+rPh5CEvEo9b1DsmDV4wUJe7jmMsXnz3WTVAoTpAE1hyvZpAOMJxgpDNgQA7ONjU51FPPzIZRnAxK3McxaqBVkR2kJy1lT92WicCJrmirUCgUinGMEneFQqHIQpS4KxQKRRaixF2hUCiyECXuCoVCkYUocVcoFIosRIm7QqFQZCFK3BUKhSILUeKuUCgUWYgSd4VCochClLgrFApFFqLEXaFQKLIQJe4KhUKRhShxVygUiixkROIuhNgrhNgkhFgvhKi39xUIIV4TQjTYz/kZx39LCLFLCLFDCHHVaDVeoThZlG0rspXj8dyXSinnZqxD+TDwhpSyDnjD/hshxEzgNmAWcDXwMyGEWidOMZ5Rtq3IOk4mLHMD8IS9/QTwyYz9T0kp41LKRmAXsPAkXkehON0o21ZMeEYq7hJ4VQjxgRDibntfqZSyBcB+LrH3VwIHMs5tsvcdghDibiFEvRCivqOj48Rar1CcPKNq26PYboXiqIx0mb2LpZTNQogS4DUhxPajHDvc2nDysB1SPg48DrBgwYLD/q9QnCZG1baFEMq2FWPCiDx3KWWz/dwO/A/WT9E2IUQ5gP3cbh/eBFRnnF6FtVKuQjGIaZr0toeIN3cQj8THrB3KthWnHo3inBrmVC3G4ywfw1YcAyGEXwgRTG8DVwKbgReAO+3D7gSet7dfAG4TQriFEFOAOuD9U91wxcQlHkvQsaUBs6sNoiHaNjaMSTuUbStONQ7NzZeu/xxrXnqGNa89zvUXLhmztggpj/6rUQgxFcujASuM8zsp5XeFEIXAM0ANsB/4tJSy2z7nEeCLQAr4mpTy5WO8RhjYcTIdmWAUAZ1j3YjTxHjp6yQpZXHmDmXbo8J4eb9PB+Ohr4fZdZpjivvpQAhRn5GGlvWcSf09k/o6HGda/8+k/o73vqoZqgqFQpGFKHFXKBSKLGS8iPvjY92A08yZ1N8zqa/Dcab1/0zq77ju67iIuSsUCoXi1DJePHeFQqFQnELGXNyFEFfbFfZ2CSEeHuv2nCxCiGohxJtCiG1CiC1CiK/a+7O20qAQwiGE+EgI8aL9d9b29XhQtj3x3+8JbdtSyjF7AA5gNzAVcAEbgJlj2aZT0Kdy4Dx7OwjsBGYCPwIetvc/DPzQ3p5p99sNTLHvh2Os+3GcfX4Q+B3wov131vb1OO6Jsu0seL8nsm2Ptee+ENglpdwjpUwAT2FV3puwSClbpJQf2tthYBtWcamsrDQohKgClgO/yNidlX09TpRtT/D3e6Lb9liL+4iq7E1UhBCTgXnAWk6y0uA45lHgIcDM2JetfT0esrqvyrbHf1/HWtxHVGVvIiKECAC/x5qi3ne0Q4fZNyHugRBiBdAupfxgpKcMs29C9PUEyNq+Ktse/pRh9o1pX0da8ne0yMoqe0IIJ5bx/7eU8g/27jYhRLmUsiWLKg1eDFwvhLgW8AA5Qojfkp19PV6ysq/KtidQX8d4sEIH9mANQKQHnWaNZZtOQZ8E8F/Aox/b/2MOHYj5kb09i0MHYvYwwQad7H5cxtCgU1b3dYT3Q9l2lrzfE9W2x8ONuxZr1H038MhYt+cU9Gcx1s+xjcB6+3EtUIi1HmeD/VyQcc4jdv93ANeMdR9OsN+ZH4Cs7utx3BNl21nwfk9U21YzVBUKhSILGesBVYVCoVCMAkrcFQqFIgtR4q5QKBRZiBJ3hUKhyEKUuCsUCkUWosRdoVAoshAl7gqFQpGFKHFXKBSKLOT/AwxtAiLbJHKkAAAAAElFTkSuQmCC\n"},"metadata":{"needs_background":"light"}}],"execution_count":20},{"cell_type":"code","source":"df = pd.read_csv('../input/rsna-csv-files/RSNA_DATA/good_slices.csv',index_col = 'Unnamed: 0')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:14:09.971849Z","iopub.execute_input":"2024-12-08T04:14:09.972214Z","iopub.status.idle":"2024-12-08T04:14:10.641579Z","shell.execute_reply.started":"2024-12-08T04:14:09.972175Z","shell.execute_reply":"2024-12-08T04:14:10.640823Z"}},"outputs":[],"execution_count":21},{"cell_type":"code","source":"from tqdm import trange\ndef get_partition_labels(df):\n    partition = dict()\n    labels = dict()\n    for i in trange(len(df)):\n        id_ = df.Image[i]\n        label = df.iloc[i,1:7].to_numpy(dtype = 'int32')\n        labels[id_] = label\n        \n    df = df.sample(frac = 0.1)\n    training = df.sample(frac = 0.8)\n    \n    validation = df.drop(training.index, axis = 0)\n    test = validation.sample(frac = 0.5)\n    validation = validation.drop(test.index, axis = 0) \n    \n    partition['train'] = list(training.Image)\n    partition['validation'] = list(validation.Image)\n    partition['test'] = list(test.Image)\n    return partition,labels","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:14:10.642635Z","iopub.execute_input":"2024-12-08T04:14:10.642863Z","iopub.status.idle":"2024-12-08T04:14:10.649149Z","shell.execute_reply.started":"2024-12-08T04:14:10.64284Z","shell.execute_reply":"2024-12-08T04:14:10.648206Z"}},"outputs":[],"execution_count":22},{"cell_type":"code","source":"partition,labels = get_partition_labels(df)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:14:10.65025Z","iopub.execute_input":"2024-12-08T04:14:10.650512Z","iopub.status.idle":"2024-12-08T04:15:13.41603Z","shell.execute_reply.started":"2024-12-08T04:14:10.650489Z","shell.execute_reply":"2024-12-08T04:15:13.415243Z"}},"outputs":[{"name":"stderr","text":"100%|██████████| 315084/315084 [01:02<00:00, 5025.44it/s]\n","output_type":"stream"}],"execution_count":23},{"cell_type":"code","source":"len(partition['train'])\nvalues_view = labels.values()\nvalue_iterator = iter(values_view)\nfirst_value = next(value_iterator)\nprint(next(iter(labels)))\nprint(first_value)\n\n\nvalues_view2 = partition.values()\nvalue_iterator2 = iter(values_view)\nfirst_value2 = next(value_iterator)\nprint(next(iter(partition['train'])))\nprint(first_value2)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:15:13.417381Z","iopub.execute_input":"2024-12-08T04:15:13.417658Z","iopub.status.idle":"2024-12-08T04:15:13.423967Z","shell.execute_reply.started":"2024-12-08T04:15:13.417629Z","shell.execute_reply":"2024-12-08T04:15:13.423109Z"}},"outputs":[{"name":"stdout","text":"ID_896989c9d\n[0 0 0 0 0 0]\nID_578149bb2\n[0 0 0 0 0 0]\n","output_type":"stream"}],"execution_count":24},{"cell_type":"code","source":"def _read(path, desired_size):\n    dcm = pydicom.dcmread(path)\n    \n    try:\n        img = bsb_window(dcm)\n    except:\n        img = np.zeros(desired_size)\n    \n    \n    img = cv2.resize(img, desired_size[:2], interpolation=cv2.INTER_LINEAR)\n    return img\n \nplt.imshow(\n    _read(train_images_dir+'ID_5c8b5d701'+'.dcm', (256, 256,3)), cmap=plt.cm.bone\n);","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:15:13.42583Z","iopub.execute_input":"2024-12-08T04:15:13.42609Z","iopub.status.idle":"2024-12-08T04:15:13.589729Z","shell.execute_reply.started":"2024-12-08T04:15:13.426064Z","shell.execute_reply":"2024-12-08T04:15:13.588759Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}],"execution_count":25},{"cell_type":"code","source":"type(_read(train_images_dir+'ID_5c8b5d701'+'.dcm', (256, 256,3)))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:15:13.592155Z","iopub.execute_input":"2024-12-08T04:15:13.592453Z","iopub.status.idle":"2024-12-08T04:15:13.610334Z","shell.execute_reply.started":"2024-12-08T04:15:13.592425Z","shell.execute_reply":"2024-12-08T04:15:13.609152Z"}},"outputs":[{"execution_count":26,"output_type":"execute_result","data":{"text/plain":"numpy.ndarray"},"metadata":{}}],"execution_count":26},{"cell_type":"code","source":"\n\nclass DataGenerator(keras.utils.Sequence):\n    'Generates data for Keras'\n    def __init__(self, list_IDs, labels, batch_size=64, dim=(32,32,3), n_channels=1,\n                 n_classes=10, shuffle=True):\n        'Initialization'\n        self.dim = dim\n        self.batch_size = batch_size\n        self.labels = labels\n        self.list_IDs = list_IDs\n        self.n_channels = n_channels\n        self.n_classes = n_classes\n        self.shuffle = shuffle\n        self.true_labels = []\n        self.on_epoch_end()\n\n    def __len__(self):\n        'Denotes the number of batches per epoch'\n        return int(np.floor(len(self.list_IDs) / self.batch_size))\n\n    def __getitem__(self, index):\n        'Generate one batch of data'\n        indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]\n\n        list_IDs_temp = [self.list_IDs[k] for k in indexes]\n\n        X, y = self.__data_generation(list_IDs_temp)\n\n        return X, y\n\n    def on_epoch_end(self):\n        'Updates indexes after each epoch'\n        self.indexes = np.arange(len(self.list_IDs))\n        if self.shuffle == True:\n            np.random.shuffle(self.indexes)\n\n    def __data_generation(self, list_IDs_temp):\n        'Generates data containing batch_size samples' \n        X = np.empty((self.batch_size, *self.dim)) \n        y = np.empty((self.batch_size), dtype=int)\n\n        # Generate data\n        for i, ID in enumerate(list_IDs_temp):\n            # Store sample\n            image_dir = '../input/rsna-intracranial-hemorrhage-detection/rsna-intracranial-hemorrhage-detection/stage_2_train/'\n            X[i,] = _read(image_dir+ID+'.dcm',self.dim)\n            #print(X)\n            # Store class\n            \n            y[i] = np.argmax(self.labels[ID])\n\n        return X,y","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:15:13.611801Z","iopub.execute_input":"2024-12-08T04:15:13.612171Z","iopub.status.idle":"2024-12-08T04:15:13.621811Z","shell.execute_reply.started":"2024-12-08T04:15:13.612136Z","shell.execute_reply":"2024-12-08T04:15:13.621105Z"}},"outputs":[],"execution_count":27},{"cell_type":"code","source":"params = {'dim':(224,224,3),\n         'batch_size':64,\n         'n_classes':6,\n         'n_channels':0,\n         'shuffle':True}\n\ncallbacks = [\n    ModelCheckpoint(filepath='./checkpoint', monitor = 'val_weighted_loss' ,save_best_only=True,verbose = 3),\n    ReduceLROnPlateau(monitor= 'val_weighted_loss', factor=0.1, patience= 3, verbose=1,mode='auto', min_delta=0.0001)]\n\n# Generators\n\ntraining_generator = DataGenerator(partition['train'], labels, **params)\nvalidation_generator = DataGenerator(partition['validation'], labels, **params)\n\n#RESNET50V2\n# Design model\nmodel = Sequential([\n    tf.keras.applications.ResNet50V2(\n    include_top=False,\n    weights=\"imagenet\",\n    input_shape=params['dim'],\n    pooling='max'),\n    Flatten(),\n    Dense(256,activation = 'relu'),\n    Dense(6, activation = 'softmax')\n])\n\nmodel.compile(optimizer='adam', loss = SparseCategoricalCrossentropy(from_logits=False), metrics=['accuracy'])\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:15:13.623203Z","iopub.execute_input":"2024-12-08T04:15:13.62359Z","iopub.status.idle":"2024-12-08T04:15:15.308303Z","shell.execute_reply.started":"2024-12-08T04:15:13.623553Z","shell.execute_reply":"2024-12-08T04:15:15.307563Z"}},"outputs":[],"execution_count":28},{"cell_type":"markdown","source":"# Training & Evaluation","metadata":{}},{"cell_type":"code","source":"# Train model on dataset\nhistory = model.fit(training_generator, validation_data=validation_generator, epochs=10, callbacks=callbacks)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T04:15:15.309491Z","iopub.execute_input":"2024-12-08T04:15:15.309719Z","iopub.status.idle":"2024-12-08T05:24:37.39266Z","shell.execute_reply.started":"2024-12-08T04:15:15.309697Z","shell.execute_reply":"2024-12-08T05:24:37.391065Z"}},"outputs":[{"name":"stdout","text":"Epoch 1/10\n393/393 [==============================] - 782s 2s/step - loss: 0.0647 - accuracy: 0.9888 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 2/10\n393/393 [==============================] - 511s 1s/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 3/10\n393/393 [==============================] - 388s 987ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 4/10\n393/393 [==============================] - 362s 921ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 5/10\n393/393 [==============================] - 353s 899ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 6/10\n393/393 [==============================] - 356s 907ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 7/10\n393/393 [==============================] - 355s 902ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 8/10\n393/393 [==============================] - 351s 892ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 9/10\n393/393 [==============================] - 351s 893ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\nEpoch 10/10\n393/393 [==============================] - 351s 893ms/step - loss: 0.0000e+00 - accuracy: 1.0000 - val_loss: 0.0000e+00 - val_accuracy: 1.0000\n","output_type":"stream"}],"execution_count":29},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nacc = history.history['accuracy']\nval_acc =  history.history['val_accuracy']\n\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nepochs = range(1, len(acc) + 1)\n\nplt.plot(epochs, acc, 'r', label='Training Accuracy')\nplt.plot(epochs, val_acc, 'b', label='Validation Accuracy')\nplt.title('Training and validation acc')\nplt.legend()\nplt.figure()\n\nplt.plot(epochs, loss, 'r', label='Training loss')\nplt.plot(epochs, val_loss, 'b', label='Validation loss')\nplt.title('Training and validation loss')\nplt.legend()\nplt.figure()\n\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:24:37.393968Z","iopub.execute_input":"2024-12-08T05:24:37.394226Z","iopub.status.idle":"2024-12-08T05:24:37.67443Z","shell.execute_reply.started":"2024-12-08T05:24:37.394193Z","shell.execute_reply":"2024-12-08T05:24:37.673587Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 0 Axes>"},"metadata":{}}],"execution_count":30},{"cell_type":"code","source":"from tensorflow.keras import backend as K\n\ndef weighted_log_loss(y_true, y_pred):\n    class_weights =  tf.Variable([2., 1., 1., 1., 1., 1.])\n    eps = K.epsilon()\n    \n    y_pred = K.clip(y_pred, eps, 1.0-eps)\n\n    out = -(         y_true  * K.log(      y_pred) * class_weights\n            + (1.0 - y_true) * K.log(1.0 - y_pred) * class_weights)\n    \n    return K.mean(out, axis=-1)\n####\ndef weighted_log_loss_V2(y_true, y_pred):\n    class_weights =  tf.constant([2., 1., 1., 1., 1., 1.])\n    \n    eps = tf.keras.backend.epsilon()\n    y_pred = tf.clip_by_value(y_pred, eps, 1.0-eps)\n\n    out = -(         y_true  * tf.math.log(      y_pred) * class_weights\n            + (1.0 - y_true) * tf.math.log(1.0 - y_pred) * class_weights)\n    \n    return tf.reduce_mean(out, axis=-1)\n\n\ndef _normalized_weighted_average(arr, weights=None):\n    if weights is not None:\n        scl = K.sum(weights)\n        weights = K.expand_dims(weights, axis=1)\n        return K.sum(K.dot(arr, weights), axis=1) / scl\n    return K.mean(arr, axis=1)\n\n\ndef weighted_loss(y_true, y_pred):\n\n    class_weights = tf.constant([2., 1., 1., 1., 1., 1.])\n    eps = tf.keras.backend.epsilon()\n    y_pred = tf.clip_by_value(y_pred, eps, 1.0-eps)\n\n    loss = -(        y_true  * tf.math.log(      y_pred)\n            + (1.0 - y_true) * tf.math.log(1.0 - y_pred))\n    \n    loss_samples = _normalized_weighted_average(loss, class_weights)\n    return tf.reduce_mean(loss_samples)\n\n\ndef weighted_log_loss_metric(trues, preds):\n    class_weights = [2., 1., 1., 1., 1., 1.]\n    \n    epsilon = 1e-7\n    \n    preds = np.clip(preds, epsilon, 1-epsilon)\n    loss = trues * np.log(preds) + (1 - trues) * np.log(1 - preds)\n    loss_samples = np.average(loss, axis=1, weights=class_weights)\n\n    return - loss_samples.mean()\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:24:37.675747Z","iopub.execute_input":"2024-12-08T05:24:37.676117Z","iopub.status.idle":"2024-12-08T05:24:37.687497Z","shell.execute_reply.started":"2024-12-08T05:24:37.676068Z","shell.execute_reply":"2024-12-08T05:24:37.686571Z"}},"outputs":[],"execution_count":31},{"cell_type":"code","source":"#Evaluation\nparams_test = {'dim':(224,224,3),\n         'batch_size':1,\n         'n_classes':6,\n         'n_channels':0,\n         'shuffle':False}\n\ntest_generator = DataGenerator(partition['test'], labels, **params_test)\ntest_pred = model.predict(test_generator,verbose=1)\npredicted_classes = tf.argmax(test_pred, axis=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:24:37.688879Z","iopub.execute_input":"2024-12-08T05:24:37.689217Z","iopub.status.idle":"2024-12-08T05:26:01.302904Z","shell.execute_reply.started":"2024-12-08T05:24:37.689178Z","shell.execute_reply":"2024-12-08T05:26:01.302108Z"}},"outputs":[{"name":"stdout","text":"3151/3151 [==============================] - 84s 26ms/step\n","output_type":"stream"}],"execution_count":32},{"cell_type":"code","source":"print(len(partition['test']))\npredicted_classes = tf.squeeze(predicted_classes).numpy()\n\nprint(predicted_classes.shape)\n\nprint(len(predicted_classes))\n\nprint(type(test_generator.labels))  # Debug: Check the type\n#print(test_generator.labels.keys())  # Debug: Check available keys\n\n# Assuming labels are stored in a dictionary\ntotal_list = np.concatenate(list(test_generator.labels.values()))\ntotal_list = total_list[:-1]\nprint(len(total_list))\n\nprint(total_list.shape)\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.metrics import multilabel_confusion_matrix, classification_report\n\naccuracy = accuracy_score(total_list, predicted_classes)\nprint(\"Accuracy:\", accuracy)\nconfusion_matrix = multilabel_confusion_matrix(total_list, predicted_classes)\nprint(\"Confusion Matrix:\")\nprint(confusion_matrix)\nclassification_report = classification_report(total_list, predicted_classes, target_names=['Any', 'Epidural', 'Intraparenchymal', 'Intraventricular', 'Subarachnoid', 'Subdural'])\nprint(\"Classification Report:\")\nprint(classification_report)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:43:52.698444Z","iopub.execute_input":"2024-12-08T05:43:52.698757Z","iopub.status.idle":"2024-12-08T05:43:52.826515Z","shell.execute_reply.started":"2024-12-08T05:43:52.698731Z","shell.execute_reply":"2024-12-08T05:43:52.824808Z"}},"outputs":[{"name":"stdout","text":"3151\n(3151,)\n3151\n<class 'dict'>\n1890503\n(1890503,)\n","output_type":"stream"},{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)","\u001b[0;32m<ipython-input-38-eead8ac2c356>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     18\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmultilabel_confusion_matrix\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mclassification_report\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     19\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 20\u001b[0;31m \u001b[0maccuracy\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0maccuracy_score\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtotal_list\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpredicted_classes\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     21\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Accuracy:\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccuracy\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     22\u001b[0m \u001b[0mconfusion_matrix\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmultilabel_confusion_matrix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtotal_list\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpredicted_classes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36minner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     61\u001b[0m             \u001b[0mextra_args\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     62\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mextra_args\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[0m\n\u001b[0;32m---> 63\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mf\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     64\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     65\u001b[0m             \u001b[0;31m# extra_args > 0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.7/site-packages/sklearn/metrics/_classification.py\u001b[0m in \u001b[0;36maccuracy_score\u001b[0;34m(y_true, y_pred, normalize, sample_weight)\u001b[0m\n\u001b[1;32m    200\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    201\u001b[0m     \u001b[0;31m# Compute accuracy for each possible representation\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 202\u001b[0;31m     \u001b[0my_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_check_targets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_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    203\u001b[0m     \u001b[0mcheck_consistent_length\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    204\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0my_type\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstartswith\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'multilabel'\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/opt/conda/lib/python3.7/site-packages/sklearn/metrics/_classification.py\u001b[0m in \u001b[0;36m_check_targets\u001b[0;34m(y_true, y_pred)\u001b[0m\n\u001b[1;32m     81\u001b[0m     \u001b[0my_pred\u001b[0m \u001b[0;34m:\u001b[0m \u001b[0marray\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mindicator\u001b[0m \u001b[0mmatrix\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     82\u001b[0m     \"\"\"\n\u001b[0;32m---> 83\u001b[0;31m     \u001b[0mcheck_consistent_length\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_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     84\u001b[0m     \u001b[0mtype_true\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtype_of_target\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     85\u001b[0m     \u001b[0mtype_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtype_of_target\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36mcheck_consistent_length\u001b[0;34m(*arrays)\u001b[0m\n\u001b[1;32m    261\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muniques\u001b[0m\u001b[0;34m)\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    262\u001b[0m         raise ValueError(\"Found input variables with inconsistent numbers of\"\n\u001b[0;32m--> 263\u001b[0;31m                          \" samples: %r\" % [int(l) for l in lengths])\n\u001b[0m\u001b[1;32m    264\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    265\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mValueError\u001b[0m: Found input variables with inconsistent numbers of samples: [1890503, 3151]"],"ename":"ValueError","evalue":"Found input variables with inconsistent numbers of samples: [1890503, 3151]","output_type":"error"}],"execution_count":38},{"cell_type":"code","source":"print(len(partition['test']))\nprediction_with_treshold = []\n\ntreshold = 0.1\n\nfor sample in test_pred:\n    prediction_with_treshold.append([1 if i>=treshold else 0 for i in sample ] )\nprediction_with_treshold = np.array(prediction_with_treshold)\nprint(len(prediction_with_treshold))\n\nprint(type(test_generator.true_labels[10]))\ntotal_list = np.concatenate(test_generator.true_labels)\ntotal_list = total_list[:-1, :]\nprint(len(total_list))\n\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.metrics import multilabel_confusion_matrix, classification_report\n\naccuracy_score(total_list, prediction_with_treshold)\nprint(multilabel_confusion_matrix(total_list, prediction_with_treshold))\nprint(classification_report(total_list, prediction_with_treshold, target_names = ['Any', 'Epidural', 'Intraparenychemal','Intraventricular','Subarachnoid','Subdural']))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:26:01.41405Z","iopub.status.idle":"2024-12-08T05:26:01.414613Z","shell.execute_reply":"2024-12-08T05:26:01.414332Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.metrics import average_precision_score\n\naverage_precision_score(total_list, test_pred, average='micro', pos_label=1, sample_weight=None)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:26:01.416053Z","iopub.status.idle":"2024-12-08T05:26:01.416609Z","shell.execute_reply":"2024-12-08T05:26:01.416328Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def sigmoid_window(dcm, window_center, window_width, U=1.0, eps=(1.0 / 255.0)):\n    img = dcm.pixel_array\n    img = cp.array(np.array(img))\n    _, _, intercept, slope = get_windowing(dcm)\n    img = img * slope + intercept\n    ue = cp.log((U / eps) - 1.0)\n    W = (2 / window_width) * ue\n    b = ((-2 * window_center) / window_width) * ue\n    z = W * img + b\n    img = U / (1 + cp.power(np.e, -1.0 * z))\n    img = (img - cp.min(img)) / (cp.max(img) - cp.min(img))\n    return cp.asnumpy(img)\ndef get_first_of_dicom_field_as_int(x):\n    #get x[0] as in int is x is a 'pydicom.multival.MultiValue', otherwise get int(x)\n    if type(x) == pydicom.multival.MultiValue:\n        return int(x[0])\n    else:\n        return int(x)\n\ndef get_windowing(data):\n    dicom_fields = [data[('0028','1050')].value, #window center\n                    data[('0028','1051')].value, #window width\n                    data[('0028','1052')].value, #intercept\n                    data[('0028','1053')].value] #slope\n    return [get_first_of_dicom_field_as_int(x) for x in dicom_fields]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:26:01.417676Z","iopub.status.idle":"2024-12-08T05:26:01.418205Z","shell.execute_reply":"2024-12-08T05:26:01.417923Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# SUBMITTER UNIT\n\ntest_csv = \"../input/rsna-intracranial-hemorrhage-detection/rsna-intracranial-hemorrhage-detection/stage_2_sample_submission.csv\"\ntest_dir = \"../input/rsna-intracranial-hemorrhage-detection/rsna-intracranial-hemorrhage-detection/stage_2_test\"\nTEST_DIR = \"stage_2_test/\"\ntest_df = pd.read_csv(test_csv)\ntest_df.head()\n\ntestdf = test_df.ID.str.rsplit(\"_\", n=1, expand=True)\ntestdf = testdf.rename({0: \"id\", 1: \"subtype\"}, axis=1)\ntestdf.loc[:, \"label\"] = 0\n\ntestdf = pd.pivot_table(testdf, index=\"id\", columns=\"subtype\", values=\"label\")\n\ndef preprocess(file,type=\"WINDOW\",DIR=test_images_dir):\n    dcm = pydicom.dcmread(test_images_dir+file+\".dcm\")\n    if type == \"WINDOW\":\n        window_center , window_width, intercept, slope = get_windowing(dcm)\n        w = window_image(dcm, window_center, window_width)\n        win_img = np.repeat(w[:, :, np.newaxis], 3, axis=2)\n        #return win_img\n    elif type == \"SIGMOID\":\n        window_center , window_width, intercept, slope = get_windowing(dcm)\n        test_img = dcm.pixel_array\n        w = sigmoid_window(dcm, window_center, window_width)\n        win_img = np.repeat(w[:, :, np.newaxis], 3, axis=2)\n        #return win_img\n    elif type == \"BSB\":\n        win_img = bsb_window(dcm)\n        #return win_img\n    elif type == \"SIGMOID_BSB\":\n        win_img = sigmoid_bsb_window(dcm)\n    elif type == \"GRADIENT\":\n        win_img = rainbow_window(dcm)\n        #return win_img\n    else:\n        win_img = dcm.pixel_array\n    resized = cv2.resize(win_img,(224,224))\n    return resized\n\nclass DataLoader(Sequence):\n    def __init__(self, dataframe,\n                 batch_size,\n                 shuffle,\n                 input_shape,\n                 num_classes=6,\n                 steps=None,\n                 prep=\"SIGMOID\"):\n        \n        self.data_ids = dataframe.index.values\n        self.dataframe = dataframe\n        self.batch_size = batch_size\n        self.shuffle = shuffle\n        self.input_shape = input_shape\n        self.num_classes = num_classes\n        self.current_epoch=0\n        self.prep = prep\n        self.steps=steps\n        if self.steps is not None:\n            self.steps = np.round(self.steps/3) * 3\n            self.undersample()\n        \n    def undersample(self):\n        part = np.int(self.steps/3 * self.batch_size)\n        zero_ids = np.random.choice(self.dataframe.loc[self.dataframe[\"any\"] == 0].index.values, size=5000, replace=False)\n        hot_ids = np.random.choice(self.dataframe.loc[self.dataframe[\"any\"] == 1].index.values, size=5000, replace=True)\n        self.data_ids = list(set(zero_ids).union(hot_ids))\n        np.random.shuffle(self.data_ids)\n        \n    # defines the number of steps per epoch\n    def __len__(self):\n        if self.steps is None:\n            return np.int(np.ceil(len(self.data_ids) / np.float(self.batch_size)))\n        else:\n            return 3*np.int(self.steps/3) \n    \n    # at the end of an epoch: \n    def on_epoch_end(self):\n        # if steps is None and shuffle is true:\n        if self.steps is None:\n            self.data_ids = self.dataframe.index.values\n            if self.shuffle:\n                np.random.shuffle(self.data_ids)\n        else:\n            self.undersample()\n        self.current_epoch += 1\n    \n    # should return a batch of images\n    def __getitem__(self, item):\n        # select the ids of the current batch\n        current_ids = self.data_ids[item*self.batch_size:(item+1)*self.batch_size]\n        X, y = self.__generate_batch(current_ids)\n        return X, y\n    \n    # collect the preprocessed images and targets of one batch\n    def __generate_batch(self, current_ids):\n        X = np.empty((self.batch_size, *self.input_shape, 3))\n        y = np.empty((self.batch_size, self.num_classes))\n        for idx, ident in enumerate(current_ids):\n            # Store sample\n            #image = self.preprocessor.preprocess(ident) \n            image = preprocess(ident,self.prep)\n            X[idx] = image\n            # Store class\n            y[idx] = self.__get_target(ident)\n        return X, y\n    \n    # extract the targets of one image id:\n    def __get_target(self, ident):\n        targets = self.dataframe.loc[ident].values\n        return targets\n    \ndef turn_pred_to_dataframe(data_df, pred):\n    df = pd.DataFrame(pred, columns=data_df.columns, index=data_df.index)\n    df = df.stack().reset_index()\n    df.loc[:, \"ID\"] = df.id.str.cat(df.subtype, sep=\"_\")\n    df = df.drop([\"id\", \"subtype\"], axis=1)\n    df = df.rename({0: \"Label\"}, axis=1)\n    return df\n\ndef weighted_loss(y_true, y_pred):\n    \n    class_weights = tf.constant([2., 1., 1., 1., 1., 1.])\n    \n    eps = tf.keras.backend.epsilon()\n    \n    y_pred = tf.clip_by_value(y_pred, eps, 1.0-eps)\n\n    loss = -(        y_true  * tf.math.log(      y_pred)\n            + (1.0 - y_true) * tf.math.log(1.0 - y_pred))\n    \n    loss_samples = _normalized_weighted_average(loss, class_weights)\n    \n    return tf.reduce_mean(loss_samples)\n\nimport keras.losses\n\ntest_dataloader = DataLoader(testdf,32,shuffle=False,input_shape=(224,224),prep=\"SIGMOID\")\n\ntest_pred = model.predict(test_dataloader,verbose=1)\n\npred = test_pred[0:testdf.shape[0]]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:26:01.419525Z","iopub.status.idle":"2024-12-08T05:26:01.419899Z","shell.execute_reply":"2024-12-08T05:26:01.419704Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_generator = DataGenerator(partition['test'], labels, **params)\n\nprint(\"Test Accuracy: \", model.evaluate(test_generator))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:26:01.420852Z","iopub.status.idle":"2024-12-08T05:26:01.421213Z","shell.execute_reply":"2024-12-08T05:26:01.421026Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"#EfficientNetB0","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras import layers, models, optimizers, applications\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# Load the EfficientNetB0 model pre-trained on ImageNet\nbase_model = applications.EfficientNetB0(weights='imagenet', include_top=False, input_shape=(224, 224, 3))\n\n# Freeze the base model\nbase_model.trainable = False\n\n# Add custom layers for classification\nx = base_model.output\nx = layers.GlobalAveragePooling2D()(x)\nx = layers.Dense(128, activation='relu')(x)\nx = layers.Dropout(0.3)(x)\noutput = layers.Dense(1, activation='sigmoid')(x)  # For binary classification, use sigmoid; for multi-class, use softmax\n\n# Create the model\nmodel = Model(inputs=base_model.input, outputs=output)\n\n# Compile the model\nmodel.compile(optimizer=optimizers.Adam(learning_rate=0.001),\n              loss='binary_crossentropy',  # Change to 'categorical_crossentropy' for multi-class\n              metrics=['accuracy'])\n# Data augmentation and preprocessing\ntrain_datagen = ImageDataGenerator(\n    rescale=1./255,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    fill_mode='nearest'\n)\n\nval_datagen = ImageDataGenerator(rescale=1./255)\n\n# Paths to training and validation datasets\ntrain_dir = 'path/to/train_data'\nval_dir = 'path/to/val_data'\n\n# Data generators\ntrain_generator = train_datagen.flow_from_directory(\n    train_dir,\n    target_size=(224, 224),\n    batch_size=32,\n    class_mode='binary'  # Change to 'categorical' for multi-class\n)\n\nval_generator = val_datagen.flow_from_directory(\n    val_dir,\n    target_size=(224, 224),\n    batch_size=32,\n    class_mode='binary'  # Change to 'categorical' for multi-class\n)\n\n# Callbacks\nearly_stopping = EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)\nmodel_checkpoint = ModelCheckpoint('best_model.h5', monitor='val_loss', save_best_only=True)\n\n# Train the model\nhistory = model.fit(\n    train_generator,\n    validation_data=val_generator,\n    epochs=20,\n    callbacks=[early_stopping, model_checkpoint],\n    verbose=1\n)\n\n# Evaluate the model\nloss, accuracy = model.evaluate(val_generator)\nprint(f\"Validation Loss: {loss}\")\nprint(f\"Validation Accuracy: {accuracy}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-08T05:26:01.422056Z","iopub.status.idle":"2024-12-08T05:26:01.422412Z","shell.execute_reply":"2024-12-08T05:26:01.422229Z"}},"outputs":[],"execution_count":null}]}