{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":8089,"databundleVersionId":44321,"sourceType":"competition"}],"dockerImageVersionId":30665,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Defining UNET","metadata":{}},{"cell_type":"code","source":"# # Contracting Path\n# c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(s)\n# c1 = tf.keras.layers.Dropout(O.1)(c1)\n# c1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c1)\n# p1 = tf.keras.layers.MaxPooling2D((2, 2))(c1)\n\n# #..................\n# #..................\n\n# #Expansive path\n# u6 = tf.keras.layers.Conv2DTranspose(128, (2, 2), strides=(2, 2),padding='same')(c5)\n# u6 = tf.keras.layers.concatenate([u6, c4)\n# c6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u6)\n# c6 = tf.keras.layers.Dropout(O.2)(c6)\n# c6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c6)\n\n# #Output layer\n# outputs = tf.keras.layers.Conv2D(1, (1, 1), activation='sigmoid')(c9)\n# model = tf.keras.Model(inputs=[inputs], outputs=[outputs])\n# model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n# model.summary()\n","metadata":{},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"import random\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D,Lambda,Conv2DTranspose,concatenate\nfrom tensorflow import keras\nimport tqdm\nimport os\nimport numpy as np\nfrom tqdm import tqdm\n# !pip install scikit-image\nfrom skimage.transform import resize\nfrom skimage.io import imread, imshow\nimport matplotlib.pyplot as plt\nimport zipfile\nfrom tensorflow.keras.preprocessing.image import load_img\nseed=42\nnp.random.seed=seed\n\nIMG_WIDTH = 128\nIMG_HEIGHT = 128\nIMG_CHANNELS = 3\n\n\ndef unzip_files(zip_file_path, target_directory):\n with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:\n zip_ref.extractall(target_directory)\n\nzip_file_path = '/kaggle/input/data-science-bowl-2018/stage1_test.zip'\ntarget_directory = '/kaggle/working/stage1_test'\nunzip_files(zip_file_path, target_directory)\n\nzip_file_path = '/kaggle/input/data-science-bowl-2018/stage1_train.zip'\ntarget_directory = '/kaggle/working/stage1_train'\nunzip_files(zip_file_path, target_directory)\n\nTRAIN_PATH='/kaggle/working/stage1_train/'\nTEST_PATH='/kaggle/working/stage1_test/'\ntrain_ids=next(os.walk(TRAIN_PATH))[1]\n# print(train_ids)\ntest_ids=next(os.walk(TEST_PATH))[1]\n# print(test_ids)\n\n# Load and prepare the image\ndef load_image(filename):\n img = load_img(filename, color_mode='grayscale', target_size=(IMG_HEIGHT,IMG_WIDTH), interpolation='nearest')\n # Convert to array\n img = keras.preprocessing.image.img_to_array(img)\n return img\n # Reshape into a single sample with 1 channel\n\n# Usage example:\n# image_filename = 'path/to/your/image.png'\n# loaded_image = load_image(image_filename)\n\n#train images\nX_train=np.zeros((len(train_ids),IMG_HEIGHT,IMG_WIDTH,IMG_CHANNELS),dtype=np.uint8)\ny_train=np.zeros((len(train_ids),IMG_HEIGHT,IMG_WIDTH,1),dtype=np.bool_)\nfor n,id_ in tqdm(enumerate(train_ids),total=len(train_ids)):\n path=TRAIN_PATH+id_\n #img = keras.preprocessing.image.load_img(path+'/images/'+id_+'.png',grayscale=False,target_size=(IMG_HEIGHT,IMG_WIDTH))\n img=load_image(path+'/images/'+id_+'.png')\n X_train[n]=img\n mask=np.zeros((IMG_HEIGHT,IMG_WIDTH,1),dtype=np.bool_)\n for mask_file in next(os.walk(path+'/masks/'))[2]:\n #mask_=keras.preprocessing.image.load_img(path+'/masks/'+mask_file,grayscale=True,target_size=(IMG_HEIGHT,IMG_WIDTH))\n #mask_=keras.preprocessing.image.img_to_array(mask_)\n mask_=load_image(path+'/masks/'+mask_file)\n # mask_=np.expand_dims(resize(mask_,(IMG_HEIGHT,IMG_WIDTH),mode='constant',preserve_range=True),axis=-1)\n mask=np.maximum(mask,mask_)\n y_train[n]=mask\n\n#test images\nX_test=np.zeros((len(test_ids),IMG_HEIGHT,IMG_WIDTH,IMG_CHANNELS),dtype=np.uint8)\nsizes_test=[]\nfor n,id_ in tqdm(enumerate(test_ids),total=len(test_ids)):\n path=TEST_PATH+id_\n #img = keras.preprocessing.image.load_img(path+'/images/'+id_+'.png',grayscale=False,target_size=(IMG_HEIGHT,IMG_WIDTH))\n img=load_image(path+'/images/'+id_+'.png')\n X_test[n]=img\n sizes_test.append(img)\nprint(\"Done\")\n\nimage_x=random.randint(0,len(train_ids))\nimshow(X_train[image_x])\nplt.show()\nimshow(np.squeeze(y_train[image_x]))","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:52:27.882543Z","iopub.execute_input":"2024-03-17T19:52:27.882926Z","iopub.status.idle":"2024-03-17T19:53:13.688187Z","shell.execute_reply.started":"2024-03-17T19:52:27.882887Z","shell.execute_reply":"2024-03-17T19:53:13.687152Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stderr","text":"2024-03-17 19:52:29.665217: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n2024-03-17 19:52:29.665348: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n2024-03-17 19:52:29.796428: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n100%|██████████| 670/670 [00:26<00:00, 24.95it/s]\n100%|██████████| 65/65 [00:00<00:00, 177.01it/s]\n","output_type":"stream"},{"name":"stdout","text":"Done\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"execution_count":1,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"markdown","source":"## Detailed/Full code","metadata":{}},{"cell_type":"code","source":"#Build the model\n\ninputs = tf.keras.layers.Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS))\ns = tf.keras.layers.Lambda(lambda x: x / 255)(inputs) #Converting integers to floating point by dividing by 255\n\n#Contraction path\nc1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(s) #layers only take input pixel values in floating point\nc1 = tf.keras.layers.Dropout(0.1)(c1)\nc1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c1)\np1 = tf.keras.layers.MaxPooling2D((2, 2))(c1)\n\nc2 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p1)\nc2 = tf.keras.layers.Dropout(0.1)(c2)\nc2 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c2)\np2 = tf.keras.layers.MaxPooling2D((2, 2))(c2)\n \nc3 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p2)\nc3 = tf.keras.layers.Dropout(0.2)(c3)\nc3 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c3)\np3 = tf.keras.layers.MaxPooling2D((2, 2))(c3)\n \nc4 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p3)\nc4 = tf.keras.layers.Dropout(0.2)(c4)\nc4 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c4)\np4 = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(c4)\n \nc5 = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(p4)\nc5 = tf.keras.layers.Dropout(0.3)(c5)\nc5 = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c5)\n\n#Expansive path \nu6 = tf.keras.layers.Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(c5) #Opposite of Conv2D (upsampling/upscaling)\nu6 = tf.keras.layers.concatenate([u6, c4])\nc6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u6)\nc6 = tf.keras.layers.Dropout(0.2)(c6)\nc6 = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c6)\n \nu7 = tf.keras.layers.Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(c6)\nu7 = tf.keras.layers.concatenate([u7, c3])\nc7 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u7)\nc7 = tf.keras.layers.Dropout(0.2)(c7)\nc7 = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c7)\n \nu8 = tf.keras.layers.Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(c7)\nu8 = tf.keras.layers.concatenate([u8, c2])\nc8 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u8)\nc8 = tf.keras.layers.Dropout(0.1)(c8)\nc8 = tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c8)\n \nu9 = tf.keras.layers.Conv2DTranspose(16, (2, 2), strides=(2, 2), padding='same')(c8)\nu9 = tf.keras.layers.concatenate([u9, c1], axis=3)\nc9 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(u9)\nc9 = tf.keras.layers.Dropout(0.1)(c9)\nc9 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(c9)\n \noutputs = tf.keras.layers.Conv2D(1, (1, 1), activation='sigmoid')(c9)\n \nmodel = tf.keras.Model(inputs=[inputs], outputs=[outputs])\nmodel.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:53:23.112568Z","iopub.execute_input":"2024-03-17T19:53:23.113261Z","iopub.status.idle":"2024-03-17T19:53:24.206624Z","shell.execute_reply.started":"2024-03-17T19:53:23.113205Z","shell.execute_reply":"2024-03-17T19:53:24.205738Z"},"trusted":true},"execution_count":2,"outputs":[{"output_type":"display_data","data":{"text/plain":"\u001b[1mModel: \"functional_1\"\u001b[0m\n","text/html":"
Model: \"functional_1\"\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n│ input_layer │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ - │\n│ (\u001b[38;5;33mInputLayer\u001b[0m) │ \u001b[38;5;34m3\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ lambda (\u001b[38;5;33mLambda\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ input_layer[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m3\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m448\u001b[0m │ lambda[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m16\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m16\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m2,320\u001b[0m │ dropout[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m16\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ max_pooling2d │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ \u001b[38;5;34m16\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m4,640\u001b[0m │ max_pooling2d[\u001b[38;5;34m0\u001b[0m]… │\n│ │ \u001b[38;5;34m32\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m32\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m9,248\u001b[0m │ dropout_1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m32\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ max_pooling2d_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ \u001b[38;5;34m32\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m18,496\u001b[0m │ max_pooling2d_1[\u001b[38;5;34m…\u001b[0m │\n│ │ \u001b[38;5;34m64\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_4[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m64\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_5 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m36,928\u001b[0m │ dropout_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m64\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ max_pooling2d_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_5[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ \u001b[38;5;34m64\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m73,856\u001b[0m │ max_pooling2d_2[\u001b[38;5;34m…\u001b[0m │\n│ │ \u001b[38;5;34m128\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_6[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m128\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m147,584\u001b[0m │ dropout_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m128\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ max_pooling2d_3 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ conv2d_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_8 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m295,168\u001b[0m │ max_pooling2d_3[\u001b[38;5;34m…\u001b[0m │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_4 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ conv2d_8[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_9 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m590,080\u001b[0m │ dropout_4[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_transpose │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m131,200\u001b[0m │ conv2d_9[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ (\u001b[38;5;33mConv2DTranspose\u001b[0m) │ \u001b[38;5;34m128\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ concatenate │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_transpose… │\n│ (\u001b[38;5;33mConcatenate\u001b[0m) │ \u001b[38;5;34m256\u001b[0m) │ │ conv2d_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_10 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m295,040\u001b[0m │ concatenate[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m128\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_5 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_10[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m128\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_11 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, │ \u001b[38;5;34m147,584\u001b[0m │ dropout_5[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m128\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_transpose_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m32,832\u001b[0m │ conv2d_11[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ (\u001b[38;5;33mConv2DTranspose\u001b[0m) │ \u001b[38;5;34m64\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ concatenate_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_transpose… │\n│ (\u001b[38;5;33mConcatenate\u001b[0m) │ \u001b[38;5;34m128\u001b[0m) │ │ conv2d_5[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_12 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m73,792\u001b[0m │ concatenate_1[\u001b[38;5;34m0\u001b[0m]… │\n│ │ \u001b[38;5;34m64\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_6 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_12[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m64\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_13 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, │ \u001b[38;5;34m36,928\u001b[0m │ dropout_6[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m64\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_transpose_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m8,224\u001b[0m │ conv2d_13[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ (\u001b[38;5;33mConv2DTranspose\u001b[0m) │ \u001b[38;5;34m32\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ concatenate_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_transpose… │\n│ (\u001b[38;5;33mConcatenate\u001b[0m) │ \u001b[38;5;34m64\u001b[0m) │ │ conv2d_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_14 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m18,464\u001b[0m │ concatenate_2[\u001b[38;5;34m0\u001b[0m]… │\n│ │ \u001b[38;5;34m32\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_7 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_14[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m32\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_15 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, │ \u001b[38;5;34m9,248\u001b[0m │ dropout_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m32\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_transpose_3 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m2,064\u001b[0m │ conv2d_15[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ (\u001b[38;5;33mConv2DTranspose\u001b[0m) │ \u001b[38;5;34m16\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ concatenate_3 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_transpose… │\n│ (\u001b[38;5;33mConcatenate\u001b[0m) │ \u001b[38;5;34m32\u001b[0m) │ │ conv2d_1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_16 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m4,624\u001b[0m │ concatenate_3[\u001b[38;5;34m0\u001b[0m]… │\n│ │ \u001b[38;5;34m16\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_8 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m0\u001b[0m │ conv2d_16[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m16\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_17 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m2,320\u001b[0m │ dropout_8[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m16\u001b[0m) │ │ │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_18 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m, \u001b[38;5;34m128\u001b[0m, │ \u001b[38;5;34m17\u001b[0m │ conv2d_17[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n│ │ \u001b[38;5;34m1\u001b[0m) │ │ │\n└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n","text/html":"
┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n┃ Layer (type)        ┃ Output Shape      ┃    Param # ┃ Connected to      ┃\n┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n│ input_layer         │ (None, 128, 128,  │          0 │ -                 │\n│ (InputLayer)        │ 3)                │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ lambda (Lambda)     │ (None, 128, 128,  │          0 │ input_layer[0][0] │\n│                     │ 3)                │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d (Conv2D)     │ (None, 128, 128,  │        448 │ lambda[0][0]      │\n│                     │ 16)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout (Dropout)   │ (None, 128, 128,  │          0 │ conv2d[0][0]      │\n│                     │ 16)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_1 (Conv2D)   │ (None, 128, 128,  │      2,320 │ dropout[0][0]     │\n│                     │ 16)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ max_pooling2d       │ (None, 64, 64,    │          0 │ conv2d_1[0][0]    │\n│ (MaxPooling2D)      │ 16)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_2 (Conv2D)   │ (None, 64, 64,    │      4,640 │ max_pooling2d[0]… │\n│                     │ 32)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_1 (Dropout) │ (None, 64, 64,    │          0 │ conv2d_2[0][0]    │\n│                     │ 32)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_3 (Conv2D)   │ (None, 64, 64,    │      9,248 │ dropout_1[0][0]   │\n│                     │ 32)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ max_pooling2d_1     │ (None, 32, 32,    │          0 │ conv2d_3[0][0]    │\n│ (MaxPooling2D)      │ 32)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_4 (Conv2D)   │ (None, 32, 32,    │     18,496 │ max_pooling2d_1[… │\n│                     │ 64)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_2 (Dropout) │ (None, 32, 32,    │          0 │ conv2d_4[0][0]    │\n│                     │ 64)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_5 (Conv2D)   │ (None, 32, 32,    │     36,928 │ dropout_2[0][0]   │\n│                     │ 64)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ max_pooling2d_2     │ (None, 16, 16,    │          0 │ conv2d_5[0][0]    │\n│ (MaxPooling2D)      │ 64)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_6 (Conv2D)   │ (None, 16, 16,    │     73,856 │ max_pooling2d_2[… │\n│                     │ 128)              │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_3 (Dropout) │ (None, 16, 16,    │          0 │ conv2d_6[0][0]    │\n│                     │ 128)              │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_7 (Conv2D)   │ (None, 16, 16,    │    147,584 │ dropout_3[0][0]   │\n│                     │ 128)              │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ max_pooling2d_3     │ (None, 8, 8, 128) │          0 │ conv2d_7[0][0]    │\n│ (MaxPooling2D)      │                   │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_8 (Conv2D)   │ (None, 8, 8, 256) │    295,168 │ max_pooling2d_3[… │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_4 (Dropout) │ (None, 8, 8, 256) │          0 │ conv2d_8[0][0]    │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_9 (Conv2D)   │ (None, 8, 8, 256) │    590,080 │ dropout_4[0][0]   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_transpose    │ (None, 16, 16,    │    131,200 │ conv2d_9[0][0]    │\n│ (Conv2DTranspose)   │ 128)              │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ concatenate         │ (None, 16, 16,    │          0 │ conv2d_transpose… │\n│ (Concatenate)       │ 256)              │            │ conv2d_7[0][0]    │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_10 (Conv2D)  │ (None, 16, 16,    │    295,040 │ concatenate[0][0] │\n│                     │ 128)              │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_5 (Dropout) │ (None, 16, 16,    │          0 │ conv2d_10[0][0]   │\n│                     │ 128)              │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_11 (Conv2D)  │ (None, 16, 16,    │    147,584 │ dropout_5[0][0]   │\n│                     │ 128)              │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_transpose_1  │ (None, 32, 32,    │     32,832 │ conv2d_11[0][0]   │\n│ (Conv2DTranspose)   │ 64)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ concatenate_1       │ (None, 32, 32,    │          0 │ conv2d_transpose… │\n│ (Concatenate)       │ 128)              │            │ conv2d_5[0][0]    │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_12 (Conv2D)  │ (None, 32, 32,    │     73,792 │ concatenate_1[0]… │\n│                     │ 64)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_6 (Dropout) │ (None, 32, 32,    │          0 │ conv2d_12[0][0]   │\n│                     │ 64)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_13 (Conv2D)  │ (None, 32, 32,    │     36,928 │ dropout_6[0][0]   │\n│                     │ 64)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_transpose_2  │ (None, 64, 64,    │      8,224 │ conv2d_13[0][0]   │\n│ (Conv2DTranspose)   │ 32)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ concatenate_2       │ (None, 64, 64,    │          0 │ conv2d_transpose… │\n│ (Concatenate)       │ 64)               │            │ conv2d_3[0][0]    │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_14 (Conv2D)  │ (None, 64, 64,    │     18,464 │ concatenate_2[0]… │\n│                     │ 32)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_7 (Dropout) │ (None, 64, 64,    │          0 │ conv2d_14[0][0]   │\n│                     │ 32)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_15 (Conv2D)  │ (None, 64, 64,    │      9,248 │ dropout_7[0][0]   │\n│                     │ 32)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_transpose_3  │ (None, 128, 128,  │      2,064 │ conv2d_15[0][0]   │\n│ (Conv2DTranspose)   │ 16)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ concatenate_3       │ (None, 128, 128,  │          0 │ conv2d_transpose… │\n│ (Concatenate)       │ 32)               │            │ conv2d_1[0][0]    │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_16 (Conv2D)  │ (None, 128, 128,  │      4,624 │ concatenate_3[0]… │\n│                     │ 16)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ dropout_8 (Dropout) │ (None, 128, 128,  │          0 │ conv2d_16[0][0]   │\n│                     │ 16)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_17 (Conv2D)  │ (None, 128, 128,  │      2,320 │ dropout_8[0][0]   │\n│                     │ 16)               │            │                   │\n├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n│ conv2d_18 (Conv2D)  │ (None, 128, 128,  │         17 │ conv2d_17[0][0]   │\n│                     │ 1)                │            │                   │\n└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m1,941,105\u001b[0m (7.40 MB)\n","text/html":"
 Total params: 1,941,105 (7.40 MB)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,941,105\u001b[0m (7.40 MB)\n","text/html":"
 Trainable params: 1,941,105 (7.40 MB)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n","text/html":"
 Non-trainable params: 0 (0.00 B)\n
\n"},"metadata":{}}]},{"cell_type":"code","source":"'''\nfit(\n\t\tx=None,\n\t\ty=None,\n\t\tbatch_size=None,\n\t\tepochs=1,\n\t\tverbose=1,\n\t\tcallbacks=None, #Checkpoints, EarlyStopping, TensorBoard, ReduceLROnPlateau\n\t\tvalidation_split=0.0,\n\t\tvalidation_data=None,\n\t\tshuffle=True,\n\t\tclass_weight=None,\n\t\tsample_weight=None,\n\t\tinitial_epoch=0,\n\t\tsteps_per_epoch=None,\n\t\tvalidation_steps=None,\n\t\tvalidation_batch_size=None,\n\t\tvalidation_freq=1,\n\t\tmax_queue_size=10,\n\t\tworkers=1,\n\t\tuse_multiprocessing=False,\n\t\t**kwargs\n)\n'''\n#Load model\n# model=tf.keras.models.load_model('model_for_nuclei.h5')\n\n#model checkpoint\ncheckpointer=tf.keras.callbacks.ModelCheckpoint('model_for_nuclei.keras',verbose=1,save_best_only=True)\ncallbacks=[tf.keras.callbacks.EarlyStopping(patience=2,monitor='val_loss'),\n\t\t\t\t\t tf.keras.callbacks.TensorBoard(log_dir='logs')]\n\nresult=model.fit(X_train,y_train,validation_split=0.1,batch_size=16,epochs=25,callbacks=callbacks)\nmodel.save('/kaggle/working/model_for_nuclei.h5')","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:53:30.804912Z","iopub.execute_input":"2024-03-17T19:53:30.805588Z","iopub.status.idle":"2024-03-17T19:55:05.757396Z","shell.execute_reply.started":"2024-03-17T19:53:30.805554Z","shell.execute_reply":"2024-03-17T19:55:05.756389Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":"Epoch 1/25\n\u001b[1m 1/38\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m20:15\u001b[0m 33s/step - accuracy: 0.8311 - loss: 0.6648","output_type":"stream"},{"name":"stderr","text":"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nI0000 00:00:1710705244.516820 113 device_compiler.h:186] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process.\n","output_type":"stream"},{"name":"stdout","text":"\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m63s\u001b[0m 824ms/step - accuracy: 0.8549 - loss: 0.5634 - val_accuracy: 0.8689 - val_loss: 0.3456\nEpoch 2/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 35ms/step - accuracy: 0.8555 - loss: 0.2769 - val_accuracy: 0.9071 - val_loss: 0.2174\nEpoch 3/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9203 - loss: 0.1812 - val_accuracy: 0.9355 - val_loss: 0.1549\nEpoch 4/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 35ms/step - accuracy: 0.9461 - loss: 0.1421 - val_accuracy: 0.9462 - val_loss: 0.1313\nEpoch 5/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 35ms/step - accuracy: 0.9521 - loss: 0.1258 - val_accuracy: 0.9517 - val_loss: 0.1171\nEpoch 6/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 35ms/step - accuracy: 0.9594 - loss: 0.1052 - val_accuracy: 0.9425 - val_loss: 0.1411\nEpoch 7/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 35ms/step - accuracy: 0.9589 - loss: 0.1083 - val_accuracy: 0.9521 - val_loss: 0.1142\nEpoch 8/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9603 - loss: 0.1007 - val_accuracy: 0.9565 - val_loss: 0.1030\nEpoch 9/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9611 - loss: 0.0988 - val_accuracy: 0.9582 - val_loss: 0.0979\nEpoch 10/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9639 - loss: 0.0912 - val_accuracy: 0.9598 - val_loss: 0.0971\nEpoch 11/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9674 - loss: 0.0833 - val_accuracy: 0.9596 - val_loss: 0.0934\nEpoch 12/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9664 - loss: 0.0844 - val_accuracy: 0.9618 - val_loss: 0.0933\nEpoch 13/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9659 - loss: 0.0847 - val_accuracy: 0.9614 - val_loss: 0.0899\nEpoch 14/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9649 - loss: 0.0886 - val_accuracy: 0.9593 - val_loss: 0.0946\nEpoch 15/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9676 - loss: 0.0823 - val_accuracy: 0.9632 - val_loss: 0.0848\nEpoch 16/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9651 - loss: 0.0876 - val_accuracy: 0.9622 - val_loss: 0.0876\nEpoch 17/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9667 - loss: 0.0845 - val_accuracy: 0.9647 - val_loss: 0.0829\nEpoch 18/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9700 - loss: 0.0752 - val_accuracy: 0.9600 - val_loss: 0.0935\nEpoch 19/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9668 - loss: 0.0825 - val_accuracy: 0.9640 - val_loss: 0.0827\nEpoch 20/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 37ms/step - accuracy: 0.9708 - loss: 0.0738 - val_accuracy: 0.9657 - val_loss: 0.0802\nEpoch 21/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 36ms/step - accuracy: 0.9704 - loss: 0.0752 - val_accuracy: 0.9674 - val_loss: 0.0772\nEpoch 22/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 37ms/step - accuracy: 0.9732 - loss: 0.0672 - val_accuracy: 0.9666 - val_loss: 0.0785\nEpoch 23/25\n\u001b[1m38/38\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 37ms/step - accuracy: 0.9695 - loss: 0.0762 - val_accuracy: 0.9669 - val_loss: 0.0773\n","output_type":"stream"}]},{"cell_type":"code","source":"# Predict on train, val and test\nmodel = tf.keras.models.load_model('model_for_nuclei.h5')\npreds_train = model.predict(X_train[:int(X_train.shape[0]*0.9)], verbose=1)\npreds_val = model.predict(X_train[int(X_train.shape[0]*0.9):], verbose=1)\npreds_test = model.predict(X_test, verbose=1)\n\n# Threshold predictions\npreds_train_t = (preds_train > 0.5).astype(np.uint8)\npreds_val_t = (preds_val > 0.5).astype(np.uint8)\npreds_test_t = (preds_test > 0.5).astype(np.uint8)\n\n#Perform a sanity check on some random training samples\nix=random.randint(0,len(preds_train_t))\nimshow(X_train[ix])\nplt.show()\nimshow(np.squeeze(y_train[ix]))\nplt.show()\nimshow(np.squeeze(preds_train_t[ix]))\nplt.show()\n\n#Perform a sanity check on some random validation samples\nix=random.randint(0,len(preds_val_t))\nimshow(X_train[int(X_train.shape[0]*0.9):][ix])\nplt.show()\nimshow(np.squeeze(y_train[int(y_train.shape[0]*0.9):][ix]))\nplt.show()\nimshow(np.squeeze(preds_val_t[ix]))\nplt.show()\n\n#Perform a sanity check on some random test samples\nix=random.randint(0,len(preds_test_t))\nimshow(X_test[ix])\nplt.show()\nimshow(np.squeeze(preds_test_t[ix]))\nplt.show()\n\n# Create list of upsampled test masks\npreds_test_upsampled = []\nfor i in range(len(preds_test)):\n preds_test_upsampled.append(resize(np.squeeze(preds_test[i]), \n (sizes_test[i][0], sizes_test[i][1]), \n mode='constant', preserve_range=True,\n anti_aliasing=np.any(np.array(preds_test_t) < np.array(preds_train_t))))","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:05:45.909614Z","iopub.execute_input":"2024-03-17T20:05:45.909967Z","iopub.status.idle":"2024-03-17T20:05:51.752827Z","shell.execute_reply.started":"2024-03-17T20:05:45.909942Z","shell.execute_reply":"2024-03-17T20:05:51.751688Z"},"trusted":true},"execution_count":13,"outputs":[{"name":"stdout","text":"\u001b[1m19/19\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 59ms/step\n\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 230ms/step\n\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 239ms/step\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"
","image/png":"iVBORw0KGgoAAAANSUhEUgAAAd4AAAHVCAYAAABfWZoAAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABjZklEQVR4nO2df5BddXn/n7vZ7A8SdteEZjdbEtlaZsIvFQnEBaZV2Skog1BSLUysERmpmighrUDU0FKFRTujNA5CdSzgFESZEVSscTBBKBqSEIgV0RDHDERxN7VpdvNrN5vd8/0j37197if3efa5z/mcc+9d3q+Znbk/zvmcz/mcz7mfPe/nVyFJkoQAAAAAkAsN1e4AAAAA8FoCCy8AAACQI1h4AQAAgBzBwgsAAADkCBZeAAAAIEew8AIAAAA5goUXAAAAyBEsvAAAAECOYOEFAAAAcgQLLwAAAJAjVV1477rrLjrllFOopaWFlixZQlu2bKlmdwAAAIDMKVQrV/M3v/lNev/730/33HMPLVmyhO688056+OGHaceOHTRv3jx134mJCXr11VfpxBNPpEKhkFOPAQAAgPIkSUL79++n7u5uamiY4pk2qRLnnXdesmLFiuL78fHxpLu7O+nv759y3927dydEhD/84Q9/+MNfTf3t3r17yjWskarAkSNHaNu2bbRmzZriZw0NDdTX10ebNm06bvvR0VEaHR0tvk/+/0N6Q0ND5k+8YfsJEwj4d0kgHGjfVXpcbf/YffCMJ98n3H/GjBnF1zNnzhS34/8h8n1C+HfSOYWfNzb+3zTnxx0fHxfb5tuNjY2VbHfw4MHi6yNHjoh95f2Q5o22j2c7bQ5kidYH6zlZsJ5f+MQhzZVwrjU1NRVft7a2lj2O9jTD51p4TD7f+JzS5iE/1tGjR0u247+JfB5K864S0v5+5YnUv7zV0CRJaHx8nE488cQpt63KwvuHP/yBxsfHqbOzs+Tzzs5O+tWvfnXc9v39/XTrrbce93mhUMh9cK03elbHCb/jk077sUm7oFr7oP3Y8NdhX/mPjfQ6bJ/3QVus+Y8c/2Hkr8P2pB9JomOmjnL7aIuCNJbaP3ba59b5Jh039j8C2jGlcUj7D2kl7VnGgah0MePXmS/C2lzT+sDbkxbXcDvp/iEqXYiz/B2M0bb0OyXdS5VQC/9cSttJ1IVX85o1a2hoaKj4t3v37mp3CQAAAHBRlSfek046iWbMmEGDg4Mlnw8ODlJXV9dx2zc3N1Nzc3Ne3QMAAAAyoypPvE1NTXTOOefQhg0bip9NTEzQhg0bqLe3txpdAgAAAHKhKk+8RESrV6+m5cuX0+LFi+m8886jO++8kw4ePEjXXHNNxW1Z7WQevDY4T/tWpwhPHzwOOFZnLc0OKPUptFdJ9l/NpifZgrkTl9bv0HbLv+P2s5GREbGvnuvuubZWJz+vHdaznXXeWL+T2o7RnmcfyQEqnF/8veTIFx6X2zb5a60Pmq+BdJyQajlNWfxSasGJK7aTrETVFt6//uu/pv/+7/+mW265hQYGBujNb34zrV+//jiHKwAAAGA6UbUEGmkYHh6m9vZ2mjFjRlnP5mo88cZoP8tLEfuJV9ouhodhlk+82n/Y1Xjitc4v6xNvnnieeD1tx/B+5ljHTpo3tfLEG6pG5Y4TUmthQrXWnzTheEmS0NGjR2loaIja2trUbav2xBuTLGPVspYeauGfhLxkSyua5C4dS/shk0I3tB88KaxE6581djRG7LW0XZ6LcNq5a10cs8Qzv8IFkP+TxhfhcD5Y2g7bty7Q0nG0fy5jEyPuvNqkCZmr5FzqIpwIAAAAmC5g4QUAAAByZFpIzRoee5q1vdiktZl5vT/Tppa0jrHVg9HaB0l6C1PrWbM8eVLtecbOY2PMk7yk69jpLdNmEQuRxiG0rUrfeY4TomV2sszXGNmgrPeqJ9Odpw9Z/o5778dKxxlPvAAAAECOYOEFAAAAcgQLLwAAAJAj097GW2tY7TQx7CVZ2kis/bFm5ophD5OwhmHEtt9brmeMcCJre1ZixnVb27b2J4a9UdqnkmNJbWRpH/eMq8cuHH6n+WbEPMesswRqx7KgXduZM2dSkiQlYYgaeOIFAAAAcgQLLwAAAJAj015q9mQiqVY2lbSJ4WOHDnja04p6e+Q/LRTI2te04TtZZkaLkQoyS/k29nE9bXuus+c4lXwnHbcWs3FJWMP7+D2sZWezbieR5+9u2t+Y8Do3NDQgcxUAAABQq2DhBQAAAHJk2kvNVvKqOhR62FqzKkltx9inGt6DXolVkns83t0xZHErsT2FPeMqfe7JJBTuF2O8PMU6qpXdy9OH2B7raYmRnS3tuceYQ2mzUFmvBX/Nq1BNvrdGTxDhiRcAAADIFSy8AAAAQI5Me6m5Wt7KHvkjtudrlvVSY5PW4zmGV7PVy5NjrX0aswCARmzP3tjEkC05tVDn1SqRS6aM2DVzY1zP2ElLYv4eesxzVqxjl7YPeOIFAAAAcgQLLwAAAJAjWHgBAACAHJn2Nt5qZaGSiFGgIK0tK3YCea0/VrupNXxkxowZxdfNzc2m43DbGn999OjRku2kMActTCBG4vos27bMjxiFO2KPg3Q9recXezttm7T3o/eesfTBW7DCGmIY89yt4T/h/RjTR8EbtjdjxoyK+oEnXgAAACBHsPACAAAAOfKakpprIcuNJ8OShqcWbiV98mxn2ccqK4UZYmbPnl18zWVnvk8oIfPvxsfHy74mKpWwxsbGyn5ebr9JPOMYI4OXRtpMXx6s/Q5DMvj15Ndda49fa/46yzltvWbW+9FaUCCGGSEtMcL2pPasMq91vGLPcX7cclnvkLkKAAAAqFGw8AIAAAA5Mi2kZk2iiC2b1YKXdOw6tFn2x5rwnUuL/HVra2vJdk1NTWXb4zJliDQftH1mzpxZfB1KSCMjI8XXXJLW8HiJanjMEll6AFs9lPmYn3DCCeJ2vG2+T9g36TqNjo6WbMevU4xMTDGJ4SkcO4NXWrNXiGVcrfNLk3S1335LVMZUfdLahlczAAAAUKNg4QUAAAByBAsvAAAAkCPTwsabl/0ya9Jmi7FmIArx2D7SotlfuB03tMNKdkD+OgxB4jah8DupD1rYkZTVStvOcsxwH2sFG0+mI2s/PcXEw2vG7bA821hor5fCtDiaXZ5f27DtAwcOFF9z+6/VDihtU+69hRhZo7Iky8xV1mpOln3C7zxhWtb5r1VDg40XAAAAqGGw8AIAAAA5Mi2kZg1Pth5PZiGvHOxpWzpOJd+lJW1GKk2u00IHuBwpjZGWRF0bVylsJWyPS6e8PzzMKGwjRogHRxqjamVn047LJWAp21j4XpKUtWurhR21tLQUX1vNCNaxlMbfG4poPa5FOo3xu2Ttm7fIQbn+aP2zhuDFGG/pekJqBgAAAOoILLwAAABAjkx7qdkqN3D5w+olavUa1vpj8erzykBpJc3YGWs0pATkoeQoeRlqx5HaDospSN7P2rhyqTKU0I4cOVJ2O07sQgghFjnRWg/WanYJPcclL/XQ65S/5+OleapytIxGvE88Y1Y4B/g1k9oLP7d42ofk5aEcY37FkKRjytpec4olEkCbX9p3lYInXgAAACBHsPACAAAAOYKFFwAAAMiRaW/jtZI27MiaJSXEY4PLsuJS2ow6VpuSNl5ae5KdRbPvecI9tExMvD3+Xbgdtyta7YXS/LLasD3ECBHhr3m41VRtcPj4hbZXCY+t1Jr9il8bfpywb/w930e7thxveEzaLHNpK/Ro7XmI/TtXybEktPA3DsKJAAAAgBoGCy8AAACQI5CaKyR2QXMLXinR47bvkdk51kw5mjSsbcdlPWsYB+8DL4geSoZcItXOVUqWHobRWLJsxQ4ZsqK1x8+Pn1N4HOkaegoPhN9pWagsWMP2NNlZCn3SijkcPny4+JqHJmmE46XdG9J+nsxoaeXpsA0+RlaZneM111nP3RImp93rGkmSVDRP8cQLAAAA5AgWXgAAACBH6lpqljzJ0nrXxShQYO2PpQ2vjC1lgAolVqtHsYRHBtX24VIeT26vbWeVrjlWz+pwf35cq7wWu0iChOeahRI5f69l8OLny2vcat631iIJ/LprbUuyv1Wu1eRzqe1w3vDveL3hUMbmMnRaj+QQq3TqkVitfbWOuYTXa9v6G2O578J9JHNDeG0hNQMAAAA1DBZeAAAAIEfqWmqeJEZ9xtgJuaU2YgfBa1i9Uy2ewuH7tDK0JvFxb9BQ0uEJ9z1FEix9CwmlWN5XSXYmkmXVvGTnEEle5mNKZE8awLfjEquW/EI7d8kLnHubW73cY9TC1eRlqW3JM56o9Pz4HNdkXo+Hc4zfOSnpjNVbPEYCodj3jKUNr/mwoaEBCTQAAACAWgULLwAAAJAjWHgBAACAHJkWNt6QtJlurDaNLDPExDgOt9PwjE2x7YppbTthG1qieSnMR7PBSbYirW2pEEL4ntsYrRmbYmTk8djYeb+5LVILq9KyPEn2bat9VSuAIYX1aHiyXVkLZViLH2hFOLhdXSqsUO59pX2NbQ+1fD4VlnvVapu2jkMM0hZvkcATLwAAAJAj0Rfe/v5+Ovfcc+nEE0+kefPm0RVXXEE7duwo2WZkZIRWrFhBc+fOpdmzZ9PSpUtpcHAwdlcAAACAmiO61Pzkk0/SihUr6Nxzz6WjR4/SJz/5SfqLv/gLevHFF2nWrFlERHTDDTfQ97//fXr44Yepvb2dVq5cSVdeeSX95Cc/qehYk4/+sRPIW/dJ6/ZvxepmH4a9SFlXtHAiTQKT0CQYKSxBa4PvMzIyUrIdPw9rUQMpTCXsD2/PWnTBKl3HTvjukdl52BCfG9aawNp80NqT5kDYb0le1mRn3h7PDKUVP9DuBSmUSrvXpesU3o+8PX6facUUPL8X2j1nLdZhvW8lYmezS9ufcL+060JaSTv6wrt+/fqS9/fddx/NmzePtm3bRn/2Z39GQ0ND9LWvfY0efPBBesc73kFERPfeey+ddtpp9Mwzz9Bb3/rW2F0CAAAAaobMbbxDQ0NERDRnzhwiItq2bRuNjY1RX19fcZtFixbRwoULadOmTWXbGB0dpeHh4ZI/AAAAoB7J1Kt5YmKCVq1aRRdccAGdeeaZREQ0MDBATU1N1NHRUbJtZ2cnDQwMlG2nv7+fbr31VvE4MbKppJV0NKwZn6yehFJS9jADkSTRhXIdl1i57BXKvJwsvQc5Ye1TKauVNYuVJltKGYi0Pmi1WbXvJvF6AFsLP0gFDyQP26mOKx1LSyAvyaqaRC7dW5o0rMnvHglf6o9Vmtfg488jDjRiRFh42o6xXdq2rR7+sTPv8WutFQwpFMoX7JHI9Il3xYoV9MILL9BDDz2Uqp01a9bQ0NBQ8W/37t2ReggAAADkS2ZPvCtXrqTHHnuMnnrqKTr55JOLn3d1ddGRI0do3759JU+9g4OD1NXVVbat5ubmkic7AAAAoF6J/sSbJAmtXLmSHnnkEdq4cSP19PSUfH/OOefQzJkzacOGDcXPduzYQa+88gr19vbG7g4AAABQU0R/4l2xYgU9+OCD9J3vfIdOPPHEot22vb2dWltbqb29na699lpavXo1zZkzh9ra2uhjH/sY9fb2ZuLRnNb24a3aobUhIdmotAo93O6gVcfh34U2PSk7URgOwW1R1qxM3mof0v68D9wOq1Vf8lRI4mMU2mr5d1q4jcV2552fUlhVOFeka2vNDGW1i2lVmqRztNr0OFp1ImsIkWav5ecRzv+p+hZinYexq5LFCK+UrnvaqmQxyLJtzS6sfT42Nmb2+SHKYOG9++67iYjobW97W8nn9957L33gAx8gIqIvfvGL1NDQQEuXLqXR0VG6+OKL6ctf/nLsrgAAAAA1R/SF1/IfVUtLC91111101113xT48AAAAUNNMyyIJMfGEHhDZM8RI+0iFwIlkCdmb+UVymQ8l6bRZrThaiJQGPy7PVMTHKAyrkqTUUJq0mhGkcw+lZb6dVbKSrmc4PtzZUAtz4PDrx/fRwmO0+cXHT8oOFm6nwdvg15D3IRxjq8nDGm4mmW7469HRUbEP2jWTMlR5s0vFDumz9MFqRkh7zDyxFmDQTBQokgAAAADUMFh4AQAAgByZFlKzVb5N69GntefJSKVtJ2UZ0vpqlcU1zz0umYTH5VJZlh7d1iw1Ur3hUNqUzs8qzYdezVJGqlCat8rLFqzmBq1tqQCAJq9xyTc8Pz4/+JhoMq92nSz1dMM5Kcn5mhSo9VXyjvd4gWvRA5VKk1Mh3RcxCgpwYkjLniIJadv27mP9XUqSpKJj44kXAAAAyBEsvAAAAECOYOEFAAAAcmRa2HiteGytsat2aMeS7KthW5J9yJoJyGpfCu2KlmohMcbBajuXbHBhVSXJXh7aAaXwGC1bErdZWguka/ZV3gcpQ1m4nWa3ttiZtfmghQlZw2Ok9rXQIAmtbSksLtzPk9lJs/lL/QnP21pxqdK+ZYEn25gVT6WotMfRjmWtZsbv+/C3ETZeAAAAoIbBwgsAAADkSF1LzZbiw7GT9Hva1pBCiLRsP5qkZjmOJtdp4RCWsBWrjGeV4axZlXjboRQohR1pUpQ1c5VH/tNkfy5h8ddaAQwtfESSYq0hMZrcJ0muWl+5fK5JttL1jFEs3fI5kf06Wws68POQCm2ExAiBrHT/kCxl3looeGDdRwuFq/Q88MQLAAAA5AgWXgAAACBH6lpqlkgrP3G0fWIkMJekZo83rybfavKm5Lka9kHyCJbkTA3vuFrbs2xn7YMVj7wZmgrCAg8W+JhrJgrrGEsSvpaRSss6JdXqDb3PJRnak5lOyzin9ZVvJ0nh1vHS7oW03vAaMbyfPdJ8Wm/lGFm2PJK51azEtws9+puamuDVDAAAANQqWHgBAACAHMHCCwAAAOTItLDxWouqh7ZNiy1Ys794bIKafUh6rWVY0kIeLPYq7bjWIu1WYocOWAvXZ4nHHs3HMbTpWouq8za0sCPJFq/ZbqVQl7AP0tzT7jPJ3hu+l+a/1Ybn9bnwVPaxjgO3aWv3Iyf2vLbaV7P0s0hb+cg6Bzw+PdZzDa/fyMgIbLwAAABArYKFFwAAAMiRaSE1a3BZNgy1sBS9DiWFMLF7WqQMQpoMJMlhWviCtp1VgtRCVSQ8klWMIhUeskxW7wlxs2aX0j6X2rBKnVrbUnap8JhSX8PteIhGS0uLqU/WrFHWOS5J89ZwPO23I8wEJ/XB+p2FGCE6MYoaWMK+vFK19NvmMTd4M26hSAIAAABQw2DhBQAAAHKkrqXmySIJ4WO/5OWp1ZflcMkglFd5e1wa82ZistTG1TxVY2RYsh5X8tjUsgxl2T+OJll56vtmiafWcojHO9WaVUmS68K2pQxQocRqlRMPHz5cfC1lxfJImGGfrPejJJ+HkrE0rqFZir9PO8fDNqwmJw8xauamjUCw3rdpIyfSmJsgNQMAAAA1ChZeAAAAIEemhdQcJprnkrIma1hqmmrympZsPexnpWh9sCbGkCQYrV6qNRGC5hkq7SP1TSNG8L61D1kWSZDkUo88p+1n9YCXCl5oWL2VrVJ/uB2XYg8cOFB8PWvWLLEPVu9bKWmJVtCB/45IHskhfLuwCEReJiJrIQNr21ZvZWsfPHiTZli2i5GkpNLzxRMvAAAAkCNYeAEAAIAcwcILAAAA5Ehd23gbGhqoUCgcFyakJfqXkOxxoQ2Vv9e2s9rNLDYXzc6sZQyS7LpacnopC4+GNZRHuy4xslpJVJJ9ptI+aPtL48+vnxY+pIXRSMfRrpk1g5RWoMPStrWYQnjP8O+4vffgwYPF12FGK8mfQ+ufFtZjsVuHY8Lf85Ao7fwsn1dC2jluDVXKMhOWNyTTcsxy7XvakEDmKgAAAKCGwcILAAAA5EhdS81SOJFVopDkDynLDZEsDWqhFpoEYQn30KQ7HhqhhRaFYyT1VZMtpXOyJv3Ps5CBpQ9eadkjw1nqLmv7aJKodk5aeJiENVxN2kebNxwtAxRndHRU3IdLzfxe0ELmOFrBA+lzLSOVZqqx/i7llUEtxjE9WeGsYY6e3xhPKJVGVtcCT7wAAABAjmDhBQAAAHKkrqXmmTNnli2SYM1mY5FJrF6doZQleRtr9T/5d1xSs56flvDdKm1pMrskw6XNFhObGN7KsSUmi1mDSK4BqyHVkCWyebFqc1KTkPl7rQ+SFKt5/VrvYd42L1qiSc3WohKSbGyV/WPLnlZiRwhYZV7rsbxeyZNY53iIx8xk6Y8HPPECAAAAOYKFFwAAAMgRLLwAAABAjtS1jXcyc1WI1c5iqcrjLahttZ9ItiOr7VY7P27/4uFEWoiUZsuynJPVBqTZ1tJWeopRycTaniecgqNlG9OqE0mZlEJfAy1cQ2qb+xfwtrXsbNI+4XvPmFvHVQuX8vgnWOdklhmprHh8KWJfC80fwOpvIrWnfe7xz/Fkn0v7u8TBEy8AAACQI1h4AQAAgBypa6m5UCiIcnM5NFlPSpweSneSZOKVKCS5jmfhsYYThViLKWiSJietXKd9bi2mkBaPtOg1I3CsJgrpOOHYS0U9rIUytAxLUkhNmDWKh+/EyAjGkbJ78fuCSM7IpsmMPBOWNTublTyzs6U1u3ja1sxU1pBFS/GQ8Dtpvmv9C+8ZPn+l+1H7beSkDS3CEy8AAACQI1h4AQAAgBypa6l5EmshA03+4JIVlyQ0qYZLHqEkIXlMa/Dj8tehnGaVZbmcohVdkNrWpJq00qJHnra2kXUdTmt7khmBvw7nqvU6SRKYVnhAmu9aG1xOtrbthZ8vL37Q3NxcfG2VGbV7Rrtv+flqdXultmPMm7QyZmxPZq1tayEDSVLmpgOtrrqnryF8/o6MjBRfewpbpAVPvAAAAECOYOEFAAAAcgQLLwAAAJAjdW3jbWhoKBtOZM14IsHtQ6Hmz+0Bmou7lFlIKywu7aPZj7UwIckGF9rqpNAlLVORx97hySQTYjmut4KK9Thps95w+1JLS0vJPtbQLimkLLy2HD4/NPulZI/WQsBiwOc1Hxdu+9PCfzjhOEghLOEY83tBGi/tHvZgteVb729r29p2aa+tdlx+PaXXRPaMelJftd/N8FhTtRUbPPECAAAAOYKFFwAAAMiRupaaJ6UELTG8Jh1IYR0x3PGl/mhI4SdhaIRV8rUmTuftSYXFwzbShlB4QyY8xdLTXjNve1JfuVTJZWciObzCW0xBmiuS9E0ky9Ba257rGe7T2tpa9jtN2rUmyJfmijaukikpHC8pC5LWV2vWu7ThLHkl/Q/bs2bU479tWqiYFp7JfyutWf34vaXNB34vaFR6bfDECwAAAORI5gvvHXfcQYVCgVatWlX8bGRkhFasWEFz586l2bNn09KlS2lwcDDrrgAAAABVJ1OpeevWrfSv//qv9MY3vrHk8xtuuIG+//3v08MPP0zt7e20cuVKuvLKK+knP/mJ6zjW2q5aliBrvVTJo1iTtjQscqRW21KrgSlJKNZ6qdYE8rHlK2uBAmkf63GzzJ6loV0zLu/zORB6YUqynCad8r5KGZrC7TyFQDTvW/5daEKR5D9rhqwYNaylvkpZtcJ9NNk57fyPITVb5WBre1Zp12L2snpta1nJtKxw/J7hc946H7Sa05WS2RPvgQMHaNmyZfTVr36VXve61xU/Hxoaoq997Wv0hS98gd7xjnfQOeecQ/feey/99Kc/pWeeeSar7gAAAAA1QWYL74oVK+jSSy+lvr6+ks+3bdtGY2NjJZ8vWrSIFi5cSJs2bSrb1ujoKA0PD5f8AQAAAPVIJlLzQw89RM899xxt3br1uO8GBgaoqamJOjo6Sj7v7OykgYGBsu319/fTrbfeetznhUKhrEwgJdcO5TkpSYU10YPmhedJhCB5NYdelFzq0pLdS4k7wv5IXraa1Jw2kbtVsvImZZfatl7bGOfqkbglE0OYEEKqV6sdK7Ykajlm2D8pSUb4nWR2sZ6rNdLBKjPyaxG2rSXcsaDN8bSe45p867l/rIk2rOekRWhI11ozvUlzKNxP2k6Tp/k9yGs6E1WeVCX6E+/u3bvp+uuvpwceeOC4G8vLmjVraGhoqPi3e/fuKO0CAAAAeRN94d22bRvt2bOH3vKWt1BjYyM1NjbSk08+SevWraPGxkbq7OykI0eO0L59+0r2GxwcpK6urrJtNjc3U1tbW8kfAAAAUI9El5ovuugi+vnPf17y2TXXXEOLFi2im266iRYsWEAzZ86kDRs20NKlS4mIaMeOHfTKK69Qb29v7O4AAAAANUX0hffEE0+kM888s+SzWbNm0dy5c4ufX3vttbR69WqaM2cOtbW10cc+9jHq7e2lt771rRUdSyqSINlFrAUKtNADyT4RIxOTdJww3IOfB7dBaKEk0v7he6uNSrIdanZ0S9+042hYbXXWjFRWW6IVjy1M+9w692L2VUMbL/4d90/QCovwc+I2VGsWK20eekKktHnD+8fvVWuIYWwbu9a29Tsrnr5y+6hknw3b1sIhebY3q71dKxIiofnTjI6OUpIk5kxXVUkZ+cUvfpEaGhpo6dKlNDo6ShdffDF9+ctfrkZXAAAAgFwpJHnVQYrI8PAwtbe300knnVR86pWwBnhLTxDWJ17tKZL/F6QlK5AIz0/6LzHrJ17pO88Tbwxie99yPJ7CIRavUavXtkbsJ14P1ty8/OmkublZ3E5Snazeo5pCoJXak/axJpY5fPiw2FePF3Et/DzHyMMt/aby/NwnnHBCyT78CVMq0UhUOqe068SxlnmUymyGn08+8Y6MjNDQ0NCUfkh1XSRhkhiypXWB9iTI136oLT+01h+RGMTOxOTBE07EiRFCYW3PeqN7qFaIlGfxt2Yb0+Rgy7HCayGFGmnyrTZe2j+yEtK5xwi90chrgY6dFY7DZWctPFMbV2kOaO1JZqVwQZXaCM+vpaWluPBaQJEEAAAAIEew8AIAAAA5Mi2lZskDTtLrw32snq8xJD6PROTxFPbIjB68HprWzFXcLihtF0qEkk1Ps3V7soMdPHiw5Lu0sn3a/b1IbXjt0VKWLe3ekgilP6m9cA6EtaUn0bIgSdtZa/1qxLD3WjzgY8+HGEUXpAxqYTYoa61eCU8N63CNkM6pXH8qMTXhiRcAAADIESy8AAAAQI5g4QUAAABypK5tvFLmKincwxoe4IlltW4XI1OOhNc+GzMUwVMMW4PH6BGV2l4lO421GHxou5VsSlrYC7dRhXGp3K5onQ/Scaz7eeaK9Zpp31nDiTSk+1ObN5L9XrvPrHH/UhyvNR+AFevvl7Zf7FCxGDHk0nGl/cOxk4rVaxnPtPGXKrTx1/z3hajU5qtdF+vaUty+oq0BAAAAkAosvAAAAECO1LXUXCgUqFAoqCEBVqnZWvzAmgHHKhdJbVvxSD15pqHzSFtcSgrlYCkzjVaoXDqOtUiCtb1Zs2aJ7Umfh+EL0tzzmhvShifFCIWTCh5YM1zxMdL6YA35sf4OSNuF16zSIuhE8UN+JLzXzJplKy1SaBFR6ThrZgQptWTYHr+PJdlZk7Gl/njAEy8AAACQI1h4AQAAgBypa6l5fHyckiQxZ80JkWQqqzynyUVcysgy6bm1LqvWdpbJ1iVpXrsuknQUvpfkZes4aBmurGMiJWgnKq28InlCa166fLtQ3uTvrZ60aWVCa31ZTxYrIp+ntsezWmtPGktNxrZeC6kPMTzbPZmwYheDkY5j3Sf83CrtapEKHMkkoP2GWn+zKgVPvAAAAECOYOEFAAAAcgQLLwAAAJAjdW3jTZKEkiQxZyoKbQjcLqi5tUtooUWe8J0sq9HE6I/FjmS1r2oVpawVbNLaq8J9uH3IaqOXbM5EtiLaWrgH70+YUefQoUNl29bmoUTsLEVWtPnF7XuaHV1CuxbaPJauJ38dVjqSbIRe23vM3w6rj4qVGL8d0jwKx4tfd/46tOPyY/Fro4Uixs66Vil44gUAAAByBAsvAAAAkCN1LTVLmasktPAFSXqwSltaWAjHWkzcUwA7Np7C51aJSZN5raFBkiSnhQRYww08MrY2B6TsTZpZg49DOA95QQYuO8dOkB9DjuTJ7rXwDEvmMKuUrsmR1tA6fizpHML3Wd6b3ixUtUDasCM+/pqEbDX9SGaEMGxPMnuVC32qpEAGnngBAACAHMHCCwAAAORIXUvNkleztUYnx5qQW5IbQonC6mXokfU8WWqsGa6sx7Vu46nFqsm8UuYpLSOVJ1OOJndzqYvvE3oeW/qgzV3L52FfuSSnkWW9Ve2e0frHt7OaG6R5HUr4kgQZbifJy9xbtlqZpqy/HZ7x8v4mpD0n7XNrAQyJMKpAakMzf1iPNbkWWcETLwAAAJAjWHgBAACAHMHCCwAAAORIXdt4J8OJQm1dCgsJ9fvQLisdgyPZNCqxBVS6nRYeEyN8JOY+1vArzXYrZRTTjmXtq5YBh7/X7D6esCNPlSZOuJ2UFcvaBytp7XbhfnzsQpu4ZCe23lvWjHNaNSHJ/ptlBS+N2CFg1jDASvfP87hh5rCmpiZT//h191R/40j3nxU88QIAAAA5goUXAAAAyJG6lponXbit8oIm2XqSjGthCRIe+TYGHsnK04ZXjpTCPbRiClL4ibVgu5alxhrGwdEyV1mlKWv2MmkcPNmNrEXjvcn8peIHWhYq6d7U7mFt3oyOjpbdTgsDtPTHS14ZrrzHSVscIK1Zg8g+/vw7ntFNK54jfR7+jkvjF4bFjY6OIpwIAAAAqFWw8AIAAAA5UtdS88TEBCVJcpyMJ3mKWmUEbRup9qO3kEHa+p1WKdAjnWrHtfQn/E7bTsoaZa0nqnksWusuS+aC0PtZ8krW5GSPt7iGZ65YC1bw89AkfE02tvRVk/qtRUY40r1JVHptvXVypc/rqViBJ9uVtT3tc89vrXU7fj25SUHLXqYVS5GONdX8gtQMAAAA1ChYeAEAAIAcqWupeWRkhAqFQoknW4iWQINjDdjn3myavGn1LEybsELDIyullZ+8HrJSsQGrfMuvmTUxQyg3cWlKk6T5flqhDKlOqDbXpDnq8dAM4WOpjbGl30TH7r9JpOICYZ8kWZCoNBGCdN3Da8HHnL+2mpWs9602d2MnpUjbVy2xjKdtK9Yx8hRssZrUtGIKFo916z7lTIuQmgEAAIAaBQsvAAAAkCNYeAEAAIAcqWsb79GjR6lQKByny0sFybWwCcmmF9rtrBls8spMox3Tk8Df0wdP0QbNjq4Vr7DYzrXMVVr4lnW80hYT1/axhpdJxwptwdweze8La4EJzbYmhR1Z75nQDsttvtb+SWFC1kxaVhuoZ4xi226tx7W2bcWTGc2aPU5ryxqK6Dl3yT9Hs/FqwMYLAAAA1DBYeAEAAIAcqWupeZJQHuBZRbRwIotMZc1yExIzU5FVWokRjhQ77MizHZeBtAwzUtsemUtrQytQoIXbWIs4cKTvwrbDkJ1JeEgOUen48fPzZAezzsMwFEiS5rUMRB7zhdY3a0EHz30bIxOZ1AfrcavVV09BBk/mPWl/jdCUIc2pGObDSscVT7wAAABAjmDhBQAAAHKkrqXmiYkJKhQKbk87iRiSQl71LGPU3rS2l9b72Sorcak5lFS17GOTaJ6JmresJHWGx7TWDpbqfPLXlvMJj0NUak7h8rLWV2tWLOs8ksYyNA9IXuqaNG/JIFUJ1vvE6klrweqtHNtEpM3xmOfn3c+b0avStmP8fnEsRTzMbaXaGwAAAAAVgYUXAAAAyBEsvAAAAECO1LWNt5x9txLSVsmIgcWuFbs/WVYnij0+YQUb3ieeiUkqYh/2SbPdcrQC99ZKQxbbpBaqxG2jvBIQUakdlfcvPCfeJ76dVhheatta8ccT/hN+lzasR7MfS/to/fGg+TGktTlr3/E5EFZuk7L6hb4UUvY+7T7TQus4WYZXxg5PSjsnJfDECwAAAOQIFl4AAAAgR+paap4kRtJsbTvLPl6yDNGxSunWcbBISdbjaNdC6zeXXLk8FiM0QsrsFMp1kkQdhtFIsrZUvD2Ey+yhxMclQ02OlPrK29OyYoWZsKS2+Wspq1ZIlmF7MWRey/6VbOeRl7XP+Xt+nfh8Decun6N8DoRzV5ofhw8fLtmOz18txCZt+FSMME7pPtHC+2L/3hePk0mrAAAAAChLJgvv7373O3rf+95Hc+fOpdbWVjrrrLPo2WefLX6fJAndcsstNH/+fGptbaW+vj7auXNnFl0BAAAAaoroUvP//u//0gUXXEBvf/vb6Qc/+AH90R/9Ee3cuZNe97rXFbf5/Oc/T+vWraP777+fenp6aO3atXTxxRfTiy++SC0tLeZjTUoRXjnAImXETtztwSMTa3gTgVtkuRjZerxJ0C3tWaVArSazJOtp48PlV01q5seVPLiJSqVBTZqX6t9q8jSX2bUiI1K/Pdcl7KuVtIn5rVjNJDEyv1nr+/I5wH83petXrk/l9iGSr3XYHpeeeTa12FmjYkd5SJm+vFR6ftEX3s997nO0YMECuvfee4uf9fT0FF8nSUJ33nknffrTn6bLL7+ciIi+/vWvU2dnJz366KN01VVXxe4SAAAAUDNEl5q/+93v0uLFi+k973kPzZs3j84++2z66le/Wvx+165dNDAwQH19fcXP2tvbacmSJbRp06aybY6OjtLw8HDJHwAAAFCPRF94f/Ob39Ddd99Np556Kv3whz+kj3zkI/Txj3+c7r//fiIiGhgYICKizs7Okv06OzuL34X09/dTe3t78W/BggWxuw0AAADkQnSpeWJighYvXky33347ERGdffbZ9MILL9A999xDy5cvd7W5Zs0aWr16dfH98PBwlMU3rwpCadu2hh5Y7SqabVPDYxP3EDNDTCVYC7ZLtqwwJEOyr2pZo6SMWVqYQ9pqO1Ybr4aWwcuyjxVvZZuYYUNZhxRarxO3+/O5Z61OxPe3ZlALt+M+Dny78LiS3d/qcyHtM1UbWeH9DZ0k+hPv/Pnz6fTTTy/57LTTTqNXXnmFiIi6urqIiGhwcLBkm8HBweJ3Ic3NzdTW1lbyBwAAANQj0RfeCy64gHbs2FHy2UsvvUSvf/3rieiYo1VXVxdt2LCh+P3w8DBt3ryZent7Y3cHAAAAqCmiS8033HADnX/++XT77bfTe9/7XtqyZQt95Stfoa985StEdOyRfNWqVfTZz36WTj311GI4UXd3N11xxRWuY8bONBU7fMdz3BjJvtO64McOCYhdeNvaH6uEbNmfqFSG47JzWNCBY5UtW1tbyx4nDPeQQp+0MdEkSAktrEraLhyvtEXDtetkTcyfNpQty+Lt2rG0cCIpe5nUVog2dpIJJTR58O14mB2/L8L+pS0WoX0Xu8iLtY2mpiZKkkT9DeBEX3jPPfdceuSRR2jNmjX0T//0T9TT00N33nknLVu2rLjNjTfeSAcPHqTrrruO9u3bRxdeeCGtX7++ohheAAAAoB4pJLHruOXA8PAwtbe304wZM6b8jyRP55y0eJ54rXljPdTCE28M9SF2iTkp4D5G/t1Zs2aVPY72xMv/yw634/DvrH3lT6vaE69WwtCaUEPqQ55PvJb9NazOjp4n8PDazp49u/jamrubt8GfZK0OS6F6wefeoUOHiq/DJ14tN/hUn4d9iDGuEl4H1ebmZkqShPbv309DQ0NT+iHVdZGEQiFdPV4L3sVHmgyxJSvPhMwS7Z8Ej3yuIUnIHlkqRPtOkk6t58QludATmv8wat7FUp3d8JjSQqxl65Eya4X78B9TnpkrxjzM8p/L2Mn3Pf3xHDecK5Z9wv7weWP1KJb2ISqdXyeccILY14MHDxZfezObTfV5SJa/eeUW3kpMKiiSAAAAAOQIFl4AAAAgR+paao6J1U4gSTAxbJFSH7w1IvOS4Ty2GauEb01Ib90nttytwWU4KdlBWPzAarPk21mLJHj24YQ2Xt6GZsNLK79q0ql0fnnaC2MncLD2weOlbjlmeFyr9zMnrAPMbcEe05vlmETZ+pHw9sr5XFRyDfDECwAAAOQIFl4AAAAgR7DwAgAAADlS1zbeSV09huZfrTAHqQ3NrhLbzd6aSSYv+1deSc9D9//YcZZSaJAWypM2DE1rT4rJDftjTZDPYzU92am88ekcyW6tHStGjLyFPO9bbmPXwo749dTC1ayxtpKdOdyOhxodOHCgbH+mOlalfY0dhjZVmBbCiQAAAIAaBQsvAAAAkCN1LTVb5ILYkmjsBN9pqYVUdlmGU3j2sUrpMULApBR8Wp+4PBfKvFKYTyhjSYURtPA36XU4XlLBgzDjUNoMRNp2WYaFWNvwmGC0zz3nwV9rBQr4a0lODt/zfcL5xbfTTAo8HE6TjXnfeeY23l7Ytue3Vto/JK3podxvTCXyNZ54AQAAgBzBwgsAAADkSF1LzRIxPUO9MlfaLEixpesYkrTkQWrNGKT1J6YHqdekkNaTWcssZOmPto9W41arlyrB+xpKxlJS/HA7TxY3af/wvVV2jp2dzerNa/lOOz/P75JViuWE88FaoUry0NXkbqscL81XLcpA+zztb20ME8X4+DikZgAAAKBWwcILAAAA5AgWXgAAACBHpqWNl+OxWVrb05Dsnp5sKppNw2p7sobRWI/rsb/EsJNZ+uC1mXnGhYdTeKpIaTZL7Vz5cbVry/skVRDSwoR4gXuPjTHsAyesYCOFzlhtvLx/vN/hd1Y7uHQc6z0co9qVJ4xG87ng46CFAvE2uE1W8zXQwuR4P3h7UmhR+F4b17S/Rdr9Y7VhHz16FDZeAAAAoFbBwgsAAADkyLSUmtPKCJzYWae0EAMpJMOaicl63BjFIqz9scrBXvnbgkdyt56TtRh5mEHIgjVrEZeGw+NIUjGXFkNZVspcpfVP+5xLi1xeLldMvByeUKVwvPj58tceE1PsEEPrPLRmCtNkdUs2tXA7TZqXTBkhUtgdnw88Q1bYPyue3yLtmNYMVxMTE5CaAQAAgFoFCy8AAACQI3UtNRcKhVRSsCWTjFcClaQVq/yhyX2eDDgxMlel7YO0v0aMDFdpZWyrx652baWiBlqRBGvdXi0bkVTkgMt6oUTouRd4H7i3bPiddbykc9fGhPc17IPUdnhveWRoj8dzWs9qIrl/WvED6bcoLPAheRSHSPNQGzu+HZ974TWzSutSfzzez9q5TuUtDqkZAAAAqFGw8AIAAAA5goUXAAAAyJG6tvF63POl/T1VNrjmH4ZGaBmNLP3hbvZaFp7wOw+xM2alOWZ4XE8lEq+dzWOr4+Mf2sksFXa8lVYkG1yYgYj3T/IbiJFhiZ+7dRw0+P2jjZdkL9TCY3j/QjuiVABeszdar621ipfUniezk2YX5scJ540U5mjta7lwm0mkDFfhvJFClbS2PXPNM//ThpniiRcAAADIESy8AAAAQI7UtdRsCSfyFDe3ykBcCgld4aWwibSJ+InsMiPHek6efWJIlR5i98EjTY2MjBRft7S0lGwnSYuafCiZJcLtuPQmhQlVclwJbYw9YULS/uXeT8IlSM30I8nOYf+sIUk8gb81/Cp2pjtO2LYkf1uLv1iLKUjXear2JaR9wusv9c9b3CQtMa8znngBAACAHMHCCwAAAORIXUvNaT1cpbY0aZjLIVwC82Y3ko5rrW3J5bDDhw+XbMc9WjVPx7TJ22MQO7OW1HZseZrLXuH4e+rLSjKhVgvX48UqtRX2weN97vUW50gZt0Kzi6U/YR9425oHtuRJG8r5Vm9xa2Y0abysWbasvzdaX3kb/DihHCzNj1AGt8zD8FpodYA50hh5i6BYjpM2ox6eeAEAAIAcwcILAAAA5AgWXgAAACBH6trGO4k3TEiyT1gz5WjZqaQQCE/WFS0LDyfcTgqBCMOOpNCUPEmbZSa27daapUsL3ZDshTHCEqz9s2QW8mbPsmTmqmQ7y7h47XZW25/FFh+GjUl2fuvvjRUtnEgK/9FCu6xzgL/Wfh+0TH4W/4Lw/uG/r6FdXWojbSUyre2ptkN1IgAAAKBGwcILAAAA5Mi0kJo1aSt2kXYuf2gZXTSXfo7k0q9JmNbwHy53azKQVHQhLMBgkXS8cpp07mll1EqQQjK0PmRZLN3Tnke+9SKFO4VhIdY+SEUOtGT+1oxUnkIlHH7PaKE3J5xwQvH1oUOHxLZjm0Z4BjVNaraawKxZzqT7RCtqLxU/0NrWQos845dlRkMLeOIFAAAAcgQLLwAAAJAjdS01TxZJ8Eo1Fs9JzTtSa8vqlSnJwZonoVUmkeQ1LdG55k09Ojpatg+eROkhMTNSeZHG3+r1a90uRj1eq8wesw9WT2Gt8IPVk1aSILXMSVyG1rJnWWvm8j7w41rnO88qRyTfP14PW2nM+TiEsr90zbwFUfh48fPVokE4vL2wr9r1tPbPso9GVuYBPPECAAAAOYKFFwAAAMiRupaaK8WajFzaptz7SUJpTPIslCQXDU3G1mQvT/EDTWqWPK1jSDBpZWOPx6FnPlTSB8uc8kp8luNo38UeY+4Br83x2MU6pKgAa+IIDak9Te6WvHe142rSvMfsYi1qYJ03VjOC1m9L8QnNW9mTOEUbu7RSf1rTFp54AQAAgBzBwgsAAADkCBZeAAAAIEemhY3XY+OybmcNeQi30+wsUntS8W/NTqNlqZHa09D6ysMFeNJyqy1FI3ZWJQvejGeejFmWsB7tO2/Ij6dtT1YyPt/DjGd83ljPSfI10LKuWTOMWeekFMKi3WfSvRkiZWqrpH/Sbwcf/zBERxrX8PfBGopo6RuRnPkrzEQm9dU6X2P8Fnn3R5EEAAAAoEbBwgsAAADkyLSXmjW4/CHJQqGLu5QVJpRgLJlawvYl2dibVN8qd0vH0s6JJ0H3yHhaHzgxEshLx8ky3CDcL23IlUd+9LadVkrnGZqISueHVsM6TKxfbn9NlrWOsTZfJSnVI0+HNWRjmxss4Umh7C+FRWm/S9bwN82cZclEpmXo0z5P+9uRNluc1gcJPPECAAAAORJ94R0fH6e1a9dST08Ptba20hve8Ab6zGc+c9x/TbfccgvNnz+fWltbqa+vj3bu3Bm7KwAAAEDNEV1q/tznPkd333033X///XTGGWfQs88+S9dccw21t7fTxz/+cSIi+vznP0/r1q2j+++/n3p6emjt2rV08cUX04svvkgtLS3mY7W0tJQtkiBlcwrlVknasmbK0WRZSR7z1r20EMpKHKvnt9YH6XxjZF/ySKRpCytYv8vy/LwytqU/3uOmldnDY/J5yeVELYG/ZAbS5Ehp/3A/6R4O30v3gvU6WyMJNKxFJSS08bJKyNb5r52vVK9ZuxbWoiVWU5fF9JNXFEb0hfenP/0pXX755XTppZcSEdEpp5xC3/jGN2jLli1EdOzE7rzzTvr0pz9Nl19+ORERff3rX6fOzk569NFH6aqrrordJQAAAKBmiC41n3/++bRhwwZ66aWXiIjoZz/7GT399NP0zne+k4iIdu3aRQMDA9TX11fcp729nZYsWUKbNm0q2+bo6CgNDw+X/AEAAAD1SPQn3ptvvpmGh4dp0aJFNGPGDBofH6fbbruNli1bRkREAwMDRETU2dlZsl9nZ2fxu5D+/n669dZbY3cVAAAAyJ3oC++3vvUteuCBB+jBBx+kM844g7Zv306rVq2i7u5uWr58uavNNWvW0OrVq4vvh4eHacGCBTRz5swpM6loNiVLtiot3MBqu5X6o22nbaNVQLG0Ya0CYg0x0PrKiVF424LX1T8v+07MsATvcTlZZx6T7KvhPJQyLmkhSNJYeuyN2nbWTGYjIyPF12FWprT3jLafNA5hH6Ti8lpGMM3uLdnBw35Lv1nW8CT+2lrVSiOtP01aoi+8n/jEJ+jmm28u2mrPOussevnll6m/v5+WL19OXV1dREQ0ODhI8+fPL+43ODhIb37zm8u22dzcTM3NzbG7CgAAAOROdBvvoUOHyiZemPwPo6enh7q6umjDhg3F74eHh2nz5s3U29sbuzsAAABATRH9ifeyyy6j2267jRYuXEhnnHEGPf/88/SFL3yBPvjBDxLRMQli1apV9NnPfpZOPfXUYjhRd3c3XXHFFRUdq6GhgRoaGsxysCcZuSYha9KWJM9o0rBUGEFzs7e60lulN2sbXBa0Jr6PEfIjSW9ayIkVa8Ym6TuruSF2xqy02bi8mdEsbWvta0XVuSSqScN8O48sHmbZsphuNFONJolK+2j9i525LTzfSXghixDNpOaRbKUxCs9Vurbe3xHrnJfa8NybEtEX3i996Uu0du1a+uhHP0p79uyh7u5u+tu//Vu65ZZbitvceOONdPDgQbruuuto3759dOGFF9L69esriuEFAAAA6pFCEvtfqhwYHh6m9vZ2Oumkk6Z84uXfectvSftoTgfSf0RWZyhruT/NWcWK9YlXKv2mlfbKMtcyRytx5vnv1PPEq7XhIUtntNgOZ562Q6QnK/557CderQ8S1Xri9cxDTX3gfjPWJ95wfLTvpL5Kv8/hmHBHtcOHDxdfe53W0v4OTNVWkiQ0NjZGQ0ND1NbWprZb10USJqVmbWGyeh7H9vi0egXyNvhiyyeXNbuO5u0nydMhmvezJP9pxJbNLP/4WK+z9cb0SsOe9jw/upZjZk2MfxKkH2HN89iTiUnDMq+tXrXeeSi14VlItLa1THdSEZQQ6R/e8JpZzl3zco9hzvKYFq1toUgCAAAAUMNg4QUAAAByBAsvAAAAkCN1beNtbGws61wl6e2a041k8NeqnPDXmsbPbRWegvRhv63OCVY7rGQnDm1AFkeWPH31PHbOLPunzUOPHdDadpZ4ist7+ya1z+ddeP9oNkJpuyznh8fGGGO8PL4BUkYxIjmLWJjISPKn0Rwupd827kwV9iFL50JrVrKY4IkXAAAAyBEsvAAAAECO1LXUPD4+TkmSmOWncDvJFV6Tg6XwpFCqsSb45seyusXzY1mzNGmhQFJ73oToEtp4WROnZ5nVJ60c6SlUPlUbadqyEkNeixEXbAkVs8Zox4ihtfStEjxzN20mM2vb1tCu8L7lYUf8dYiUb0DLB+AJD4ttRoiZrYqDJ14AAAAgR7DwAgAAADlS11LzJJrcas1cZc2AY00ZKXkKh0nKudTMvQetNYG1zFVcutHGKLYnoOU41mtRCxmbPNKkhkcKjHF+aduLIaVbyVKKTXvc2NK8N4Oa1ZPZgyQvh32QvJI952T9rdXa1n6TpbY51rTC5T6v5H7AEy8AAACQI1h4AQAAgBzBwgsAAADkSF3beJMkmVJr55q/VuWEo2WkkjI7hbYBawUhS3k9r4t8lu7z1uLmWdpAOTHCLqx2ZmkfK54xttrMYlTEsRK7kpJlXDzZwWLjCYnSvosxX63909qT8GR28m7nIWZ4X4xrawFPvAAAAECOYOEFAAAAcmRaSM1WuS6Ucrn0zMN6tExTVplQa0OiWoUH0kqfsUMZ0kq73nCPtHJYLWTN8UplljZiS50xzCRZZRby4jHPxE7M7zFReIk9p6R9PCF9VrNX2nBKD3jiBQAAAHIECy8AAACQI3UtNUtY6uyG7zXPYwthZijurWxtuxpZeMJj8X2sWVxio41D7KT4HqzjxZHmgCYFau15zsnqhWwdY2tdaEsftO20PqTN3uSRYq3yaIxoBM94pS3GoOHxRI9xXI9Hsfb75TGToEgCAAAAUKdg4QUAAABypK6l5kKhQIVC4Th5gHsoazJv2sTdXF4Oix9IXs2xpR+OJhl6JCuvR7cFr4esdE6efseW17Tjau1J8Lnr8ZYNSXv9vIkxtGT1EjHmv9SeJudb7lXv3E/r2WvdL/bYWffzmHvSRhxoxJCN03pWS+CJFwAAAMgRLLwAAABAjmDhBQAAAHKkrm28k7aj0E5jDd/h2/GsVtLnRHbbbezwCs/+HvtJ1uEHle7v6YM3tCitLdhzna02bGt7MfaJERIjHdfyeSVtp+2DZn9Omy0sS38OIl8mubxCAkNihuJYf+c8WbGs90+5eVPJ2OKJFwAAAMgRLLwAAABAjtS11Jwkx4okSHVsiUql4TC7FH/PpQNr+EOtyTaa5K4RowhA2razbM+TiSlLrHJyjOsSM7OQFq6WpenAQ+zwmBjheGlD2cJ9pHCzGCYmjykjSxOFZ27EmE9ZZfXDEy8AAACQI1h4AQAAgBypa6n56NGjZSUNSV62eh57kpFrfdD2ienJbJVOs5TItbZ5f7RambGlqBjJ8yvtT/g+y2xCMTOKVdIHj2eotL/2nVboxNN2bMndk5kuxtzN8riW/mhtW/tgbTsG0ljGuGeQuQoAAACoYbDwAgAAADmChRcAAADIkbq28Y6MjJStTmS1gXqQQnRCjd9TJFxqL0ZmodghLBzNbuSxz8WoIMRJa4us5FjScT0ZqaxoVYws5+61MWaZGS1G+I60nYalfzFCb7S+Wa9TzOxqsasExQ4vi+HvkDZUTDpOpfsS4YkXAAAAyBUsvAAAAECO1LXUPPloHzvJeLljpMEqg0rhP1YZu5LjWvAUCbcWrNDkNWsGqdhykTXMwSMbz5gxo/i6sfH/brvwXKW2QxMH79PY2Ji4HT+uJ5F+nmYJyz4h1uxNVonVI8Vm+dsRu+BBWhODN9TSEh7mHa8sQ/U8vwkW8MQLAAAA5AgWXgAAACBHpoXUnPZzjdhSm9a+JEfyz8N9pDrCIR5JOjyuJBtr2cGssjj/TvPStezvxSqfc6TrRyRLyvxzbby0TF+ezE58rnB52koMr1oNj+knyyxIaU01sWvheuTNGJm+Yme4shZvsbad9jpVY67giRcAAADIESy8AAAAQI5g4QUAAABypK5tvBbyqkxjtTuEdkD+vqmpqezn3nAPyb1fy+gi2XHD99Lr0dHRkn24/VdDOg9PlqcY1V6040r22ubm5or76g1n8bTH+83n15EjR0r2sdrg8qrEE9t+b7XZVyNMJTyu1h/LdnlW3kmbYSxGpi/rdmmrE5VrG5mrAAAAgBoFCy8AAACQI3UtNVcqBWVZaFmTAvnrmTNnlmzH33MJzCp/WPeRMhiF+2kyYyiTl9unpaWl5LuRkZHia6vsLEmi4Xf8uFpIkyc0RZMm+XsuL4ftaWFD5Y6pEV4XSe7Wwo6keRiOMZeeeQhSiCdUJW2y+xhZ6mLvE1ty9+CZ454CDLGLKXjCNa3mp9hhRzHBEy8AAACQI1h4AQAAgBypa6m5UChQoXB8Pd60pPUaJpIzEIVSsyQVezwEQ0mUy69cgtQS83PZMZQtJUlay7AktReeH9+Oy7eaB6qU7Sr0rE4rWYXbcWmXf2f1ltWkdE9RCWkcwvfSOYX95nNUkvPDNjx91cgya1TawgPWOq/WNvIaE+1Y3rY9HtjSfWKVu/P8va/EYxpezQAAAECNUvHC+9RTT9Fll11G3d3dVCgU6NFHHy35PkkSuuWWW2j+/PnU2tpKfX19tHPnzpJt9u7dS8uWLaO2tjbq6Oiga6+9lg4cOJDqRAAAAIB6oGKp+eDBg/SmN72JPvjBD9KVV1553Pef//znad26dXT//fdTT08PrV27li6++GJ68cUXix6vy5Yto9///vf0+OOP09jYGF1zzTV03XXX0YMPPlhRXyYf7b3JyCX5w+ppp8knXK7TCh5wrHVoueQnyYLhsbTjalKltJ00RpqMrUms0hhZawLz44SJLKzFATwJNPh48XMI27DWWrYmr7AmD5HGnM8ha03gUMLn4xo76UxaT1qtP1pRCcuxvL83WXrVpk2aYfV+jt2HGAltpH2sxPDArnTMC0kKwbxQKNAjjzxCV1xxBREdO+nu7m76u7/7O/r7v/97IiIaGhqizs5Ouu++++iqq66iX/7yl3T66afT1q1bafHixUREtH79enrXu95Fv/3tb6m7u3vK4w4PD1N7ezs1NjYW7byctAuvdR9OuJDwLFT8Bzn8cebEXni1/nH4OWnhIxbCPkihKbEXXv46tEWmXXjD+cVDpqSwnnA/6dqG4yD1z/rDGF4/yX6vLbzSWGoLr1ZRKm04V1rfhxBrNSfLccI2rP2T9rfuo7XhCdGJcVxtf0+WrdgLb9p/SKbaP0kSGhsbo6GhIWpra1O3jWrj3bVrFw0MDFBfX1/xs/b2dlqyZAlt2rSJiIg2bdpEHR0dxUWXiKivr48aGhpo8+bNZdsdHR2l4eHhkj8AAACgHom68A4MDBARUWdnZ8nnnZ2dxe8GBgZo3rx5Jd83NjbSnDlzituE9Pf3U3t7e/FvwYIFMbsNAAAA5EZdhBOtWbOGVq9eXXw/PDxcsvjGTqKuIcmHWnYjj21Ak8OkLFSajM0lQy2ExdpX6z58O2571TJSaUjnzvsQjoOUQUqTZbW+SXZTT5iJJu1rUrVV4pPmodXOGYa/cfic8sh41nOyEkPmtWznlTM9oTxppdgYdnRPeGUl36XdRzIZWv0lYvSh0vOL+sTb1dVFRESDg4Mlnw8ODha/6+rqoj179pR8f/ToUdq7d29xm5Dm5mZqa2sr+QMAAADqkagLb09PD3V1ddGGDRuKnw0PD9PmzZupt7eXiIh6e3tp3759tG3btuI2GzdupImJCVqyZEnM7gAAAAA1R8VS84EDB+jXv/518f2uXbto+/btNGfOHFq4cCGtWrWKPvvZz9Kpp55aDCfq7u4uej6fdtppdMkll9CHPvQhuueee2hsbIxWrlxJV111lcmjOSYx5Y9QkrNmCbJIRFriey6japmFOFrCfat3quT5GvZh1qxZZY8TA2vCdw73Ng+3k6Qpa4iUJvN60K5FWtnfs0+4HZ/zocezhSxDPzSs5249rsfr2kpa+TbGPZfluccIfZK+yzIMKi0VL7zPPvssvf3tby++n7S9Ll++nO677z668cYb6eDBg3TdddfRvn376MILL6T169eXhGA88MADtHLlSrrooouooaGBli5dSuvWrYtwOgAAAEBtkyqOt1qEcbx5Ij3hhEkbJAccLdZTwvrE63WkkOJAtSde6ekpfOK15l1Oi/afN+8fjysOn9KkJ97wmvFzkvI2E8V94tXakq5FuT6V287qFKbFaGtPvGmTa8S+x2O3bX3qqwYxYnqtxH7az+s4MeZDoXCsZsCRI0dMcbx14dU8FZ7sM5VsJx1LS/SgeTxL7UmeplrbUlvhdtriKHnmags+/44v1lzKDdEkd6sHoiexgjSWoWe1NSuZhDeRi9SGdn7WvkqLt5YgxFo3WZr/eXqTeqIRtHOPmbQhy2xLYfuepEFWrAtdlsk+YizcMf8B1P5ZtYAiCQAAAECOYOEFAAAAcgQLLwAAAJAj08LG69X/PTYEyXZrDTnRslDx1zxZfmiL5G1r9jjJgUbLXKUVq5fChriDkTWDl+YEZHUqktoOCw1I11m7ZtawKmthCqkPWgiYZlOSnOBiOJ54nMKs9i8t21Vam16MzEnSuVsLK1gzXMUmSyfT2M5j1ixb1v2tRTikNvJyCuPgiRcAAADIESy8AAAAQI7UtdQ8KRFUK85Py1ok1b/V6uJyiTSGFCLJoOHn0nZhAn+pni4PIdJkSk1q5mghP5K07pEZPTL2VMfiSIUppJC0EE22lOR4rfCANWOT1D9tHkq1fkM818kjGVqPE46XZDaxnh8n7DePe44R/pM2jEnDOq4xQ4NiSMgx5GWpvanC0CqR4fHECwAAAOQIFl4AAAAgR+paai4UCqlkFY9MJcl/mszgSXbPE9BrGaSktsLttMxV/Dsud4fH4TIc758my0qSaJiGkW+nya+S9OmRGa3ZoLSMYByt+IRnrmjnJKUK1dJWSvK+1Qs5pBrZkrz3Ox8HbhqxpnC1ZqLTJGl+LJ5iM9zOKrFmmarSem95sgSmzT7nOY62nZUYXvOT4IkXAAAAyBEsvAAAAECOYOEFAAAAcqSubbxpSVuJRMsu5cnY5HHh5/YhrTIND2UIMztZbX/cRhXaxiQk25hm19IyQ0nHlUJ3wu9iZBay2uA8NmhPNRRr2JEURuPxadCw2upiVxHTxsvinxBinePS/aNlRmttbS2+DsP2RkZGyrZnDbfx2H6zDBOqpB/VxlrprpwvC8KJAAAAgBoFCy8AAACQI3UtNWeZuaXS42vF5Tmh/GQtQm/pQyghc3mZv7aG/ITnIIXySGFQ4T58jMLzk8bBWthdC+Pg23FZzyt3p80apYX4WAvcpy0ooM1dT8EKqWiD1lerrOcpxK5JzWnDQjRzkfa59f7m91B4T0t4QiM5Ma6FtT3P73baTFNTfTeJdp9p9wwyVwEAAAA1DBZeAAAAIEfqWmpuaGigQqGQq8ecta5qWm8/LZOTJFNpHq3adlaZyuKBrclwVm9lqxTI5U1rDVmtD9K1CL1OQzl9qv2JZJkxRm1XqXhF+N6TJUiTRKXziH0/xs4yxIlRhMCayUy6f8L9+fzifQjnYVp5WSPtNfRmj5O2i134QSJG9iwLeOIFAAAAcgQLLwAAAJAjWHgBAACAHKlrG29MzT1tyENoz5EyKWl2RSmbkDUjkrXKiUbaQuVWm6Bmt7aGE2n2L46UucoTshUei9vjrHYo7bjSuVuzcWnVhKSKRlr/ND8GPg4xwj041nAW65hbqwtJ7Um2cq09LUMcb0/LesfnVzjHeYigdN2tc1zDU+Unxm9P2nDR2CFNnu0k8MQLAAAA5AgWXgAAACBH6lpqzooYmV+4DMQlPk1WssjOIVzOCqUtSY70SqKWjE2aDGfN3MO/0zJccbRiEZIkrUn4mizFj6VJzZKcJV1zIntifr6fZsrg7zUZWuqfNl4eqVkbV21cyu2voYXWpQ2Z0yRMzUwiHdeaxc3626GZU/g146+toXUaMbOphXhCMvMKQfKAJ14AAAAgR7DwAgAAADlS11JzoVCgQqFgTlruwZsUPGay+9CbkUuGXNK2esta0SRW6ZysXtuaF7LV61SS9TTJnX/nvba8Pf5ak5qttXklj2Jr/7Sxk9rW5i4fr/CaWes4W6VAy/XwZl3j10nz7ra0Z/XI16R06Zghmje1ZbxC84JUgCGsAWzNeifhGVdv3V9PRjbr/pVkIESRBAAAAKBGwcILAAAA5EhdS82TaNIDxxNQrWGt/chlm1DS4VKS5NGqSXzW5PRWOVJrj0tTTU1NZfunSema97P1mkleuponNO+3Vcq1juXo6Ki4nZT8QEvmIG2n9VWT+qX9+NhppgzNE9rqBR4Tr0c+nwP8PrPWe9ba5ngSdWjnpPVHaoPvE/6mSLWzw2vG57VmTvEkoYlRwCLt/p75ao3KsIAnXgAAACBHsPACAAAAOYKFFwAAAMiRurbxTmrz3sTpaW1Uae3CRKX2NWtmIU8ftKxAVvuqFJbD9w+LxHMbtmYrktBsSpItkodYEfkyLGl9kPoT2nslW5uWWYiPl8d+bw0B0+Zd7IIHHtIWLQmR/CzC+Sr5WWg22dgFHTiaT4I0V/i9rl1bKftZ+F6aQ+X6lAarD47HJjvVsSzEDNfEEy8AAACQI1h4AQAAgByZFlJz2m3C7dLWDK2kDxY5JUadSk9WGC2Uh0uVXJ4L5RgppEJr2zquUsJ3TwhMJViT3YcZtCaRCj2EbWhhQlJ/rOFXHrOGhhb24rm2EjGkTat0yvvNw+e0+9k6rpp0bTU3WCRuT7hU2IfYoWKVZIOy7OOZE2nrCKMeLwAAAFBHYOEFAAAAcqSupeZJPMnDw+0sdTjLHSstMRPDa6TNtBIei7enFR6Q6uR6vXSl42qkzZrjHX9N0pT6I81DqySnFanwFEmwEiOrjySRWueKx4s1lIYlj2fNPGAtfuApDsC/C731LXKwtc6utp21qIfU7xhY54OGxaSmnZ8mzVcKnngBAACAHMHCCwAAAOQIFl4AAAAgR+raxlsoFKa0JXhCeTy2Na/+H7MqkvVcYyDZgEK7q1Ss3tqe1UblKZSddfiVx+4Zu3KLJfTJOg5eW2uWIRqea6shzWUerqZlZ7NW4NJ8CKTzsN4/WqUujmY3lbLMWatfefBms5Ow+mZYK3/F/H3FEy8AAACQI1h4AQAAgBypa6nZgjVsIqbMpZFleJJHHq1kO4/E7UluHjshunW7vOaAlRjtxZbZLW1nGf4TO3TQ09cwrEeSg8MQJL6dFApEVCpr8+949iwiWVLWzknKZBaaiHgfYoQicjxFJTy/1bHNazHbwxMvAAAAkCNYeAEAAIAcqWupeVJ+sHoPhl6BHg/ZWsMjDefVnyzasJyTNh80r1NJJgy3k4oNeLy2rVmjYkjuHlk8a/NFpX3Q+u2pOR3i8QKXtguzYlnnoeQlrUnc1kxTvE9SkZFK2rNiMR3ELlqi4fFWjmlKwhMvAAAAkCMVL7xPPfUUXXbZZdTd3U2FQoEeffTR4ndjY2N000030VlnnUWzZs2i7u5uev/730+vvvpqSRt79+6lZcuWUVtbG3V0dNC1115LBw4cSH0yAAAAQK1T8cJ78OBBetOb3kR33XXXcd8dOnSInnvuOVq7di0999xz9O1vf5t27NhB7373u0u2W7ZsGf3iF7+gxx9/nB577DF66qmn6LrrrvOfBQAAAFAnFJIUwnWhUKBHHnmErrjiCnGbrVu30nnnnUcvv/wyLVy4kH75y1/S6aefTlu3bqXFixcTEdH69evpXe96F/32t7+l7u7uKY87PDxM7e3t1NjYSIVCwa29e4ohp3Vxj9F27Gw9VjzZvSz7E9kzKVmyhWk2M551KNxfCvcIkex41mL1WqiGJ5RKwzI/YttDrcQIV0sbGmQ999jhLNZsSXweanNSai+cX/w9n4eaPdp6b1qR7uEYWbGsPi9Z2HiTJKGxsTEaGhqitrY2ddvMbbxDQ0NUKBSoo6ODiIg2bdpEHR0dxUWXiKivr48aGhpo8+bNZdsYHR2l4eHhkj8AAACgHsl04R0ZGaGbbrqJrr766uJ/AAMDAzRv3ryS7RobG2nOnDk0MDBQtp3+/n5qb28v/i1YsCDLbgMAAACZkVk40djYGL33ve+lJEno7rvvTtXWmjVraPXq1cX3w8PDJYuvV+ZNWxghtrwmbWfdJ3aRhLRSTyXbeeQ76XWY4aex8f+muTXkhH/H9yeSpetQruNI7YVhHDyDkCcblEbs8J+088MjpXvun0qI+ZtgLZqhZa6SihVM1SepD1lm+vKE3mjjkPa31np/V9JGLDJZeCcX3Zdffpk2btxYond3dXXRnj17SrY/evQo7d27l7q6usq219zcTM3NzVl0FQAAAMiV6FLz5KK7c+dO+tGPfkRz584t+b63t5f27dtH27ZtK362ceNGmpiYoCVLlsTuDgAAAFBTVPzEe+DAAfr1r39dfL9r1y7avn07zZkzh+bPn09/9Vd/Rc899xw99thjND4+XrTbzpkzh5qamui0006jSy65hD70oQ/RPffcQ2NjY7Ry5Uq66qqrTB7NHClzVbltKtmO4/UoTitrxPCctGafsWTrCb+zSoaa16LUtvY5f88lWy75hvVS+XG5TBz2W8pCFfZbkqu1zGjSGGmJ9CUP1LCvGpZ5pM2HLOXgqfZLQ4xCDVYkSdoq82r3Gf/OmnnPuk2McYgpQ3vNT5ZjWrezytPhtai0kETF4UQ//vGP6e1vf/txny9fvpz+8R//kXp6esru98QTT9Db3vY2IjqWQGPlypX0ve99jxoaGmjp0qW0bt06mj17tqkPk+FEM2bMoEKhkOvCa23bE+Yg7e+1fVjPyWOjsk6bWlt4+T7WhTfsgzUUgX8nhSCF+0sVZ7wLr4e0dq0sF15v29I+sUPwYtgRrT/2nral77x+Mlnaf2OHE1mOk2bhrSScqOIn3re97W2pHT3mzJlDDz74YKWHBgAAAOqeui6SID3txpRstf+APE+b1uNqbaV9IrFKOh6P1qy9Tvl/mvzJVksuYH1S4N7Q2tO5JP9Zn+j5ay2Jh3WuWWuxppWNY3uCZvm0GaONvDxfvYpW2sQWWapl1vas/bESe05JbaetUYwiCQAAAECOYOEFAAAAcgQLLwAAAJAjdW3jlZBsY1kn4fbsk9YenadHtyXJeOzsWaENlNthpYxUWtiFZguWzk/LLKTZVy3ez5q9nZ+fVkyBeziH3s6WaxvDe13a39uGtT9W3wzL3I3dByvec8qSGOGMMffJkhhzvFCorFgPnngBAACAHMHCCwAAAOTItJSaJenTmm3EKuVa8YTlxHTTj7FPiBTKECOUxDP+mtytycaWPmghP1KSjPA7a/gVl4q5LB5uJyUC0RJySH2zEiO7kbUPMRPQaH3wJJPJUkrPY79aInb2Pw+xzHWQmgEAAIAaBQsvAAAAkCPTUmq2etxmKdVYc6zGzOwUI2uUJwdznjKc5r0sHTNtztawPckzOsynLGW4ss5JSXYOt9O8nyViZ2jyyHUx5kpaGdv6XQzzkzUnumWfrLezYm0vbQRJjP54zHpZeXfjiRcAAADIESy8AAAAQI5g4QUAAABypK5tvJPavNVW5KnKY83qE6OKiCcbFMdrT42Rvceyj3U7LZRHCqPRQm+k42j1ePl2Y2NjYnv8uJp9lbetZbuSzl2zPWnjZalcFNuOFSMTU2ybZVqfCU/4m7WqWIyKP9bzk/wirJW1vL+HsauUSW3klXUtbb/xxAsAAADkSF0+8U7+F1LpfzSxk01Yv/M8sXr295JnDthKsSaE0J5OrE9ckjJhfRqw1vC11s/VzklqQ3vKyivZStYKTbXb9vYh9rjEPMcYx/R+lxVpf3craYNva9mnLhfe/fv3E1H6YsSg9hkdHS15f+DAgSr1BAAApmb//v3U3t6ublNIauFfwwqZmJigV199lZIkoYULF9Lu3bupra2t2t2qGsPDw7RgwQKMA8aBiDAOk2AcjoFxOEbW45AkCe3fv5+6u7vV3A1EdfrE29DQQCeffDINDw8TEVFbW9trekJNgnE4BsbhGBiHY2AcjoFxOEaW4zDVk+4kcK4CAAAAcgQLLwAAAJAjdb3wNjc30z/8wz9Qc3NztbtSVTAOx8A4HAPjcAyMwzEwDseopXGoS+cqAAAAoF6p6ydeAAAAoN7AwgsAAADkCBZeAAAAIEew8AIAAAA5goUXAAAAyJG6XXjvuusuOuWUU6ilpYWWLFlCW7ZsqXaXMqW/v5/OPfdcOvHEE2nevHl0xRVX0I4dO0q2GRkZoRUrVtDcuXNp9uzZtHTpUhocHKxSj/PhjjvuoEKhQKtWrSp+9loZh9/97nf0vve9j+bOnUutra101lln0bPPPlv8PkkSuuWWW2j+/PnU2tpKfX19tHPnzir2OD7j4+O0du1a6unpodbWVnrDG95An/nMZ45LfD/dxuGpp56iyy67jLq7u6lQKNCjjz5a8r3lnPfu3UvLli2jtrY26ujooGuvvbbucqFr4zA2NkY33XQTnXXWWTRr1izq7u6m97///fTqq6+WtFGVcUjqkIceeihpampK/u3f/i35xS9+kXzoQx9KOjo6ksHBwWp3LTMuvvji5N57701eeOGFZPv27cm73vWuZOHChcmBAweK23z4wx9OFixYkGzYsCF59tlnk7e+9a3J+eefX8VeZ8uWLVuSU045JXnjG9+YXH/99cXPXwvjsHfv3uT1r3998oEPfCDZvHlz8pvf/Cb54Q9/mPz6178ubnPHHXck7e3tyaOPPpr87Gc/S9797ncnPT09yeHDh6vY87jcdtttydy5c5PHHnss2bVrV/Lwww8ns2fPTv7lX/6luM10HIf/+I//SD71qU8l3/72txMiSh555JGS7y3nfMkllyRvetObkmeeeSb5z//8z+RP//RPk6uvvjrnM0mHNg779u1L+vr6km9+85vJr371q2TTpk3Jeeedl5xzzjklbVRjHOpy4T3vvPOSFStWFN+Pj48n3d3dSX9/fxV7lS979uxJiCh58sknkyQ5NslmzpyZPPzww8VtfvnLXyZElGzatKla3cyM/fv3J6eeemry+OOPJ3/+539eXHhfK+Nw0003JRdeeKH4/cTERNLV1ZX88z//c/Gzffv2Jc3Nzck3vvGNPLqYC5deemnywQ9+sOSzK6+8Mlm2bFmSJK+NcQgXHMs5v/jiiwkRJVu3bi1u84Mf/CApFArJ7373u9z6HpNy/4CEbNmyJSGi5OWXX06SpHrjUHdS85EjR2jbtm3U19dX/KyhoYH6+vpo06ZNVexZvgwNDRER0Zw5c4iIaNu2bTQ2NlYyLosWLaKFCxdOy3FZsWIFXXrppSXnS/TaGYfvfve7tHjxYnrPe95D8+bNo7PPPpu++tWvFr/ftWsXDQwMlIxDe3s7LVmyZFqNw/nnn08bNmygl156iYiIfvazn9HTTz9N73znO4notTMOHMs5b9q0iTo6Omjx4sXFbfr6+qihoYE2b96ce5/zYmhoiAqFAnV0dBBR9cah7qoT/eEPf6Dx8XHq7Ows+byzs5N+9atfValX+TIxMUGrVq2iCy64gM4880wiIhoYGKCmpqbihJqks7OTBgYGqtDL7HjooYfoueeeo61btx733WtlHH7zm9/Q3XffTatXr6ZPfvKTtHXrVvr4xz9OTU1NtHz58uK5lrtPptM43HzzzTQ8PEyLFi2iGTNm0Pj4ON122220bNkyIqLXzDhwLOc8MDBA8+bNK/m+sbGR5syZM23HZWRkhG666Sa6+uqri9WJqjUOdbfwgmNPey+88AI9/fTT1e5K7uzevZuuv/56evzxx6mlpaXa3akaExMTtHjxYrr99tuJiOjss8+mF154ge655x5avnx5lXuXH9/61rfogQceoAcffJDOOOMM2r59O61atYq6u7tfU+MAdMbGxui9730vJUlCd999d7W7U39ezSeddBLNmDHjOC/VwcFB6urqqlKv8mPlypX02GOP0RNPPEEnn3xy8fOuri46cuQI7du3r2T76TYu27Ztoz179tBb3vIWamxspMbGRnryySdp3bp11NjYSJ2dna+JcZg/fz6dfvrpJZ+ddtpp9MorrxARFc91ut8nn/jEJ+jmm2+mq666is466yz6m7/5G7rhhhuov7+fiF4748CxnHNXVxft2bOn5PujR4/S3r17p924TC66L7/8Mj3++OMltXirNQ51t/A2NTXROeecQxs2bCh+NjExQRs2bKDe3t4q9ixbkiShlStX0iOPPEIbN26knp6eku/POeccmjlzZsm47Nixg1555ZVpNS4XXXQR/fznP6ft27cX/xYvXkzLli0rvn4tjMMFF1xwXDjZSy+9RK9//euJiKinp4e6urpKxmF4eJg2b948rcbh0KFD1NBQ+jM2Y8YMmpiYIKLXzjhwLOfc29tL+/bto23bthW32bhxI01MTNCSJUty73NWTC66O3fupB/96Ec0d+7cku+rNg6ZuW1lyEMPPZQ0Nzcn9913X/Liiy8m1113XdLR0ZEMDAxUu2uZ8ZGPfCRpb29PfvzjHye///3vi3+HDh0qbvPhD384WbhwYbJx48bk2WefTXp7e5Pe3t4q9jofuFdzkrw2xmHLli1JY2NjcttttyU7d+5MHnjggeSEE05I/v3f/724zR133JF0dHQk3/nOd5L/+q//Si6//PK6D6MJWb58efLHf/zHxXCib3/728lJJ52U3HjjjcVtpuM47N+/P3n++eeT559/PiGi5Atf+ELy/PPPF711Led8ySWXJGeffXayefPm5Omnn05OPfXUugsn0sbhyJEjybvf/e7k5JNPTrZv317yuzk6OlpsoxrjUJcLb5IkyZe+9KVk4cKFSVNTU3LeeeclzzzzTLW7lClEVPbv3nvvLW5z+PDh5KMf/Wjyute9LjnhhBOSv/zLv0x+//vfV6/TOREuvK+Vcfje976XnHnmmUlzc3OyaNGi5Ctf+UrJ9xMTE8natWuTzs7OpLm5ObnooouSHTt2VKm32TA8PJxcf/31ycKFC5OWlpbkT/7kT5JPfepTJT+s03EcnnjiibK/B8uXL0+SxHbO//M//5NcffXVyezZs5O2trbkmmuuSfbv31+Fs/GjjcOuXbvE380nnnii2EY1xgH1eAEAAIAcqTsbLwAAAFDPYOEFAAAAcgQLLwAAAJAjWHgBAACAHMHCCwAAAOQIFl4AAAAgR7DwAgAAADmChRcAAADIESy8AAAAQI5g4QUAAAByBAsvAAAAkCP/D9KYNQydbes5AAAAAElFTkSuQmCC"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"iVBORw0KGgoAAAANSUhEUgAAAhYAAAHWCAYAAAArR8D6AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA5m0lEQVR4nO3df3RU9Z3/8dcESEKFJAQ2CcEg2VYXrAgIkgbst1qzjT+KYmkLNC0ppbBa0oI5WyFVgsUfUdvSVIhkdYvWs1Kou0pVbDw0gNQ1Bgimq1YBFxQOOkGWDQOxJGHm8/2DZcpAApPkczM/7vNxzj3H3LnzuZ/7yUx4+35/Pvd6jDFGAAAAFiREugMAACB+EFgAAABrCCwAAIA1BBYAAMAaAgsAAGANgQUAALCGwAIAAFhDYAEAAKwhsAAAANYQWAAAAGsILAAAiENbt27VlClTlJ2dLY/Ho/Xr11/wPVu2bNFVV12lpKQkfe5zn9NTTz3V5fMSWAAAEIdaWlo0ZswYVVVVhXX8vn37dPPNN+u6665TY2OjFi5cqO9///t65ZVXunReTyQfQlZVVaWf/exn8nq9GjNmjFasWKGJEydGqjsAAMQlj8ej559/XlOnTu30mEWLFmnDhg16++23g/tmzJih5uZm1dTUhH2uiGUs1q1bp9LSUi1dulQ7d+7UmDFjVFhYqEOHDkWqSwAAuFZdXZ0KCgpC9hUWFqqurq5L7fS12amuWL58uebOnavZs2dLkqqrq7VhwwatXr1aixcvPu97A4GAPvroIw0cOFAej6c3ugsAQIeMMTp27Jiys7OVkPC3/18/ceKE2trarJ/r7H/3kpKSlJSU1OO2vV6vMjMzQ/ZlZmbK5/Ppr3/9q/r37x9WOxEJLNra2tTQ0KCysrLgvoSEBBUUFHQYGbW2tqq1tTX488GDB3X55Zf3Sl8BAAjHgQMHdPHFF0s6FVTkXjJA3kN+q+cYMGCAjh8/HrJv6dKluvfee62epyciElgcPnxYfr+/w8jovffeO+f4iooK/fSnPz1n/zW6SX3Vz7F+Iro8v/stq+3ddtloq+3h/Gz//jpj4/fqZF+j+XMX79ft1PX5jgd0yVUfaODAgcF9bW1t8h7ya1/DJUoZaGfWge9YQLnjP9SBAweUkpIS3G8jWyFJWVlZampqCtnX1NSklJSUsLMVUgRLIV1RVlam0tLS4M8+n085OTnqq37q6yGwcAtbX87T+Ow475WPGs/4qXemdHXn9xraT8nJvtZ+/E7wvwuzxzp2nu6w/R07UzRct5PXJ6nD0nzKwATr501JSQkJLGzJz8/Xyy+/HLJv48aNys/P71I7EQkshgwZoj59+nQYGWVlZZ1zvK36EQAAvclvAvJbWnvpN4EuHX/8+HG9//77wZ/37dunxsZGpaena/jw4SorK9PBgwf19NNPS5Juv/12rVy5UnfddZe+973vadOmTfrd736nDRs2dOm8EVkVkpiYqPHjx6u2tja4LxAIqLa2tsuREQAA0SogY3Xrih07dmjcuHEaN26cJKm0tFTjxo1TeXm5JOnjjz/W/v37g8fn5uZqw4YN2rhxo8aMGaNf/OIX+td//VcVFhZ26bwRK4WUlpaquLhYEyZM0MSJE1VZWamWlpbgKhEAANB91157rc53q6qO7qp57bXX6s033+zReSMWWEyfPl2ffPKJysvL5fV6NXbsWNXU1JwzoRMAEPuiYT5Jd/pw7vybrgkooK4VMM7fViyI6OTNkpISlZSURLILAADAophYFQIAQCzyGyO/pSdn2GrHaQQWcI1oSMXGu56mjd3ATZ/DeLjW811DOJ/37ky6PF9bsYCnmwIAAGvIWAAA4JCAjPwuy1gQWABwJco25zoz7d+d8YmH0kdXnL7ek6Zd0t6I9iWaEFgAAOAQN86xILAAAMAhrAoBolh30rRuS826Fb/nyGHscTYCCwAAHBL4v81WW7GA5aYAAMAaMhYAADjEb3G5qa12nEZggZh0dl33zDkX1Hx7F8s24xPfIzv85tRmq61YQCkEAABYQ8YCAACHuHHyJoFFF4WT9iWF2PsYc/eJld95rPQTsIXAAgAAhwTkkV8ea23FAgILAAAcEjCnNlttxQICCwecXS4hFQr0HN8jIDYQWAAA4BC/xVKIrXacRmABAIBD3BhYcB8LAABgDRmLC+CugkB86s7TcrvTNtwtYDwKGEurQiy14zQyFgAAwBoyFgAAOMSNcywILHoBD8gCuieWvi+x1Ff0Hr8S5LdUHPBbacV5lEIAAIA1ZCwAAHCIsTh508TI5E0CCwBRJRIlhbPPycMGge4jsAAAwCFM3gQAANb4TYL8xtLkTR5CFrucvCkWK0QQb7pzo6lo/+xHe/+AaEZgAQCAQwLyKGBpAWZAsZGyYLkpAACwhowFAAAOYfImAPQAcxOAUHYnb1IKAQAALkPGAgAAh5yavGnpsemUQmJXd5bPAQAAAgsAABwTsPh001hZbkpgAQCAQ9w4eZPAAp3qThmIVQEA4G4EFgAAOCSgBNfdeZPAAgAAh/iNR35j6QZZltpxGvexAAAA1pCxiKCz5zBEw/yEni6v5emtAPA3fourQvwxUgohYwEAAKwhYwEAgEMCJkEBS8tNAyw3RSzgzqIA4BxKIQAAAD1AxgIAAIcEZG+ZaMBKK84jsLiAs1c2UDoAAKBzBBYAADjE7p03Y2P2AoEFAAAOsfsQMgKLuHRmaYSyCAAAoayHPxUVFbr66qs1cOBAZWRkaOrUqdq1a1fIMSdOnND8+fM1ePBgDRgwQNOmTVNTU5PtrgAAEFEBeaxuscB6YPHqq69q/vz5euONN7Rx40a1t7frK1/5ilpaWoLH3HnnnXrxxRf17LPP6tVXX9VHH32kr33ta7a7AgAAepn1UkhNTU3Iz0899ZQyMjLU0NCg//f//p+OHj2qX//611qzZo2+/OUvS5KefPJJjRo1Sm+88Ya+8IUv2O4SAAAR4cY5Fo738ujRo5Kk9PR0SVJDQ4Pa29tVUFAQPGbkyJEaPny46urqnO4OAAC95vSdN21tscDRyZuBQEALFy7U5MmTdcUVV0iSvF6vEhMTlZaWFnJsZmamvF5vh+20traqtbU1+LPP53OszwAAoPscDX/mz5+vt99+W2vXru1ROxUVFUpNTQ1uOTk5lnoIAIBzAsZjdYsFjmUsSkpK9NJLL2nr1q26+OKLg/uzsrLU1tam5ubmkKxFU1OTsrKyOmyrrKxMpaWlwZ99Pl/Egot4WGIaD9cAAIhO1jMWxhiVlJTo+eef16ZNm5Sbmxvy+vjx49WvXz/V1tYG9+3atUv79+9Xfn5+h20mJSUpJSUlZAMAINoFLM6vcO2dN+fPn681a9bo97//vQYOHBicN5Gamqr+/fsrNTVVc+bMUWlpqdLT05WSkqIf/vCHys/PZ0UIACCuBEyCApZWc9hqx2nWA4tVq1ZJkq699tqQ/U8++aS++93vSpJ++ctfKiEhQdOmTVNra6sKCwv12GOP2e6KFbbLBmc/1AwAgHhiPbAwxlzwmOTkZFVVVamqqsr26QEAiBp+eeS3dMdMW+04jWeFAADgEDeWQmKjlwAAICaQsegAyzG7jzkkAPA3ftkrYfittOI8MhYAAMAaMhYAADjEjXMsCCwAAHEr3NK2U2Vcnm4KAADiSlVVlUaMGKHk5GTl5eVp27Zt5z2+srJS//AP/6D+/fsrJydHd955p06cOBH2+chYAADgECOPApYmb5putLNu3TqVlpaqurpaeXl5qqysVGFhoXbt2qWMjIxzjl+zZo0WL16s1atXa9KkSdq9e7e++93vyuPxaPny5WGdk8Cil52ZlmMFBQDY1d1VffH6t3n58uWaO3euZs+eLUmqrq7Whg0btHr1ai1evPic419//XVNnjxZ3/rWtyRJI0aM0MyZM1VfXx/2OSmFAADgkNNzLGxtXdHW1qaGhgYVFBQE9yUkJKigoEB1dXUdvmfSpElqaGgIlkv27t2rl19+WTfddFPY5yVjAQCAQwLGo4CxUwo53Y7P5wvZn5SUpKSkpHOOP3z4sPx+vzIzM0P2Z2Zm6r333uvwHN/61rd0+PBhXXPNNTLG6OTJk7r99tv1k5/8JOx+krEAACCG5OTkKDU1NbhVVFRYa3vLli168MEH9dhjj2nnzp167rnntGHDBt13331ht0HGIoLOrgX2Vl3vzPPYuMtoPNUjAfS+zv4Ohfu3xfbdkm3Ot/ArQX5L/w9/up0DBw4oJSUluL+jbIUkDRkyRH369FFTU1PI/qamJmVlZXX4niVLlug73/mOvv/970uSRo8erZaWFs2bN0933323EhIufC1kLAAAiCEpKSkhW2eBRWJiosaPH6/a2trgvkAgoNraWuXn53f4nk8//fSc4KFPnz6Swnt6uUTGAgAAxzgxx6IrSktLVVxcrAkTJmjixImqrKxUS0tLcJXIrFmzNGzYsGA5ZcqUKVq+fLnGjRunvLw8vf/++1qyZImmTJkSDDAuhMAiisTrcicAOFO4pYtIlYs760N3zh9QggKWigPdaWf69On65JNPVF5eLq/Xq7Fjx6qmpiY4oXP//v0hGYp77rlHHo9H99xzjw4ePKi/+7u/05QpU/TAAw+EfU4CCwAA4lhJSYlKSko6fG3Lli0hP/ft21dLly7V0qVLu30+AgsAABziNx75LZVCbLXjNAILlzs7tdfT2dkA0BEbKzdsr/7o6fn5u9gxAgsAABwS6cmbkUBgAQCAQ4xJUMDS485NjDw2Pe4Di3BTZ6S0TmEcACA8p/998R0LaNBlke1LNIn7wAIAgEjxyyO/pcem22rHaQQWAAA4JGDszY0IhHfjy4iLjYINAACICXGZsejOkqRIL2MCAMSfgMXJm7bacVps9BIAAMSEuMxYAAAQDQLyKGBp0qWtdpxGYAEAUcZ2aZZl5JHjxlt6UwoBAADWkLEAAMAhbpy8GReBhZMrOsJ9SBcA9ISTf1vObJuyCJwWF4EFAADRKCCLDyFj8iYAAO5mLK4KMTESWMRGwQYAAMQEMhZddGZ9kvkWAHoiEn9Dzj4ncy6cFTAWSyEsNwUAAG5DxgIAAIew3BRdYrssQkoSAOILpRAAAIAeIGMBAIBDeAgZzhHuDGrKGAAAEFgAAOAYN86xILAAAMAhBBZAGLjBDgCgMwQWAAA4hIwFAACwxo2BBfexAAAA1sRFxuLsGj8PB7Mj3HHs7DjmXgA4za0PcDSyd/8JY6UV55GxAAAA1sRFxgIAgGjkxjkWBBZddGYKLx5T/W5KUQKIjFgtX3f2N/+kaZe0t8PX3BhYUAoBAADWkLEAAMAhbsxYEFi4XKykIIF45NaVEmfrrXGIx/J1NHK8FPLQQw/J4/Fo4cKFwX0nTpzQ/PnzNXjwYA0YMEDTpk1TU1OT010BAKBXnc5Y2NpigaOBxfbt2/Uv//IvuvLKK0P233nnnXrxxRf17LPP6tVXX9VHH32kr33ta052BQCAXmeMx+oWCxwLLI4fP66ioiI98cQTGjRoUHD/0aNH9etf/1rLly/Xl7/8ZY0fP15PPvmkXn/9db3xxhtOdQcAAPQCx+ZYzJ8/XzfffLMKCgp0//33B/c3NDSovb1dBQUFwX0jR47U8OHDVVdXpy984QtOdQm9jKegAuE73/fD5ryDaP8ehtu/WJmTEpDH2p03bbXjNEcCi7Vr12rnzp3avn37Oa95vV4lJiYqLS0tZH9mZqa8Xm+H7bW2tqq1tTX4s8/ns9pfAABgh/VSyIEDB7RgwQI988wzSk5OttJmRUWFUlNTg1tOTo6VdgEAcJIbJ29az1g0NDTo0KFDuuqqq4L7/H6/tm7dqpUrV+qVV15RW1ubmpubQ7IWTU1NysrK6rDNsrIylZaWBn/2+XznDS5YwnV+jAngLtFe/uiOWLkmm5MuY2XypvXA4vrrr9dbb70Vsm/27NkaOXKkFi1apJycHPXr10+1tbWaNm2aJGnXrl3av3+/8vPzO2wzKSlJSUlJtrsKAAAssx5YDBw4UFdccUXIvosuukiDBw8O7p8zZ45KS0uVnp6ulJQU/fCHP1R+fj4TNwEAcYU7b/aSX/7yl0pISNC0adPU2tqqwsJCPfbYY5HoChwUK6lKIB7x/UOk9EpgsWXLlpCfk5OTVVVVpaqqqt44PQAAEcEcCwAAYI2xWAohsIgSrBA5xc3XDsQavq+IZXEfWAAAEClGkjH22ooFBBYAADgkII88Lrult+OPTQcAAO5BxiJOUaMF3O3MvwEsPY0cN64KIWMBAACsIWMBAIBDAsYjD3fejF82lp6SUgTgBMqX8ckYi6tCYmRZCKUQAABgjasyFgAA9CY3Tt50bWBBScMZjCsQfVghgt7k2sACAACnkbEAAADWuHFVCJM3AQCANWQs4gjL1QAgurDcFAAAoAfIWAAA4JBTGQtbkzetNOM4Agv0GMvXAKBjblwVQikEAABYQ8YCAACHmP/bbLUVCwgs0GWRKn30dNULJRsAcB6BBQAADnHjHAsCCwAAnOLCWgiBBcLSW2UEJ2/ydXbblEYAuEFVVZV+9rOfyev1asyYMVqxYoUmTpzY6fHNzc26++679dxzz+nIkSO65JJLVFlZqZtuuims8xFYAADgFIulEHWjnXXr1qm0tFTV1dXKy8tTZWWlCgsLtWvXLmVkZJxzfFtbm/7xH/9RGRkZ+vd//3cNGzZMH374odLS0sI+J4EFAABxavny5Zo7d65mz54tSaqurtaGDRu0evVqLV68+JzjV69erSNHjuj1119Xv379JEkjRozo0jm5jwUAAA45/awQW1tXtLW1qaGhQQUFBcF9CQkJKigoUF1dXYfveeGFF5Sfn6/58+crMzNTV1xxhR588EH5/f6wz0vGIo6cOWfAxlwF5iC4T2efGz4LQPc4sSrE5/OF7E9KSlJSUtI5xx8+fFh+v1+ZmZkh+zMzM/Xee+91eI69e/dq06ZNKioq0ssvv6z3339fP/jBD9Te3q6lS5eG1U8yFgAAxJCcnBylpqYGt4qKCmttBwIBZWRk6PHHH9f48eM1ffp03X333aqurg67DTIWAAA4xXi6Nemy07YkHThwQCkpKcHdHWUrJGnIkCHq06ePmpqaQvY3NTUpKyurw/cMHTpU/fr1U58+fYL7Ro0aJa/Xq7a2NiUmJl6wmwQWcSqWUtdOLjEN97yxNF491Z3xZqmu82yXMhEdujM34nxtSVJKSkpIYNGZxMREjR8/XrW1tZo6daqkUxmJ2tpalZSUdPieyZMna82aNQoEAkpIOFXU2L17t4YOHRpWUCFRCgEAIG6VlpbqiSee0G9+8xu9++67uuOOO9TS0hJcJTJr1iyVlZUFj7/jjjt05MgRLViwQLt379aGDRv04IMPav78+WGfk4wFAABOifCdN6dPn65PPvlE5eXl8nq9Gjt2rGpqaoITOvfv3x/MTEin5m+88soruvPOO3XllVdq2LBhWrBggRYtWhT2OQksAHSZW8tIQCwqKSnptPSxZcuWc/bl5+frjTfe6Pb5CCwAAHAIDyEDAAB2xcjDw2xh8iYAALCGjAUiguV0vYvxBiLDjaUQMhYAAMAaMhYAADglwstNI4HAAgCizNlLeHtaymJJcCR5/m+z1Vb0oxQCAACsIWMBAIBTKIUAiBesBIkf3XlAGeUPRAqBBQAATiFjAQAArDGeU5uttmIAgQUAxJDeKnF0p5QW7+WXzsbEdyygQZf1bl+iGYEFAAAOMebUZqutWMByUwAAYA0ZCwAAnMLkTQCxiuWl6KmefobOfn+8z7kIiwsnb1IKAQAA1pCxAADAIR5zarPVViwgsADgGiyhRFf1uMTowjkWjpRCDh48qG9/+9saPHiw+vfvr9GjR2vHjh3B140xKi8v19ChQ9W/f38VFBRoz549TnQFAAD0IuuBxf/+7/9q8uTJ6tevn/7whz/oL3/5i37xi19o0KBBwWMeeeQRPfroo6qurlZ9fb0uuugiFRYW6sSJE7a7AwBA5JyevGlriwHWSyEPP/ywcnJy9OSTTwb35ebmBv/bGKPKykrdc889uvXWWyVJTz/9tDIzM7V+/XrNmDHDdpcAuJSNlTJntkFZpGsYO3eynrF44YUXNGHCBH3jG99QRkaGxo0bpyeeeCL4+r59++T1elVQUBDcl5qaqry8PNXV1XXYZmtrq3w+X8gGAEDUM5a3GGA9sNi7d69WrVqlSy+9VK+88oruuOMO/ehHP9JvfvMbSZLX65UkZWZmhrwvMzMz+NrZKioqlJqaGtxycnJsdxsAAPsILHouEAjoqquu0oMPPqhx48Zp3rx5mjt3rqqrq7vdZllZmY4ePRrcDhw4YLHHAADAFutzLIYOHarLL788ZN+oUaP0H//xH5KkrKwsSVJTU5OGDh0aPKapqUljx47tsM2kpCQlJSXZ7iqAboq2enlv3XWUOQPoMpab9tzkyZO1a9eukH27d+/WJZdcIunURM6srCzV1tYGX/f5fKqvr1d+fr7t7gAAgF5kPWNx5513atKkSXrwwQf1zW9+U9u2bdPjjz+uxx9/XJLk8Xi0cOFC3X///br00kuVm5urJUuWKDs7W1OnTrXdHQAAIseFzwqxHlhcffXVev7551VWVqZly5YpNzdXlZWVKioqCh5z1113qaWlRfPmzVNzc7OuueYa1dTUKDk52XZ3gE6RygbgNG7pbclXv/pVffWrX+30dY/Ho2XLlmnZsmVOnB4AAEQIzwoBAMApLpy8SWABxLDeWg0RjWWj3rr2cM8fjWMERIIjDyEDAADuRMYCAACHeGRx8qadZhxHYIGIODNt7OZ0PgDEGwILAACc4sL7WDDHAgAAWEPGAgAAp7DcFIgvzKvoPsYOPcVnSK4MLCiFAAAAa8hYAADgEJ4VAkRAJJaexgvbYxfNqWs+G4hJlEIAAAC6j4wFAABOcWHGgsACcSGaU/iAW/A9hERgAQCAY5i8CQAA7OGW3gAAAN1HxgJRhRpt9509dp0tz4zVMQ73+tC7YvXzFK4eL+l24eRNMhYAAMAaMhYAADiEyZsA4ka8p6gjjfFFWCiFAAAAdB8ZCwAAnGKxFBIrGQsCCwAxqbceXuemkoebrrU7Ohufk6Zd0t5e7Us0I7AAAMApLpxjQWABAIBTXBhYMHkTAABYQ8YCQMzrrPZ9vrkXzCdAb3DjfSzIWAAAAGsILAAAgDWUQgDELcodiDgmbwIAAHQfGQsAABzixsmbBBYAADgpRgICWyiFAAAAa8hYAADgFBdO3iSwANDrbDw0jBUfQHQisAAAwCFM3gQAAPa4sBTC5E0AAGANGQsAvcLGvIrO2mO+BaKVG0shZCwAAIhjVVVVGjFihJKTk5WXl6dt27aF9b61a9fK4/Fo6tSpXTofgQUAAE4xlrcuWrdunUpLS7V06VLt3LlTY8aMUWFhoQ4dOnTe933wwQf653/+Z33xi1/s8jljuhTy/O63lDLw3NiItCgQHWyXP4Bocvrz7TsW0KDLOjkowpM3ly9frrlz52r27NmSpOrqam3YsEGrV6/W4sWLO3yP3+9XUVGRfvrTn+pPf/qTmpubu3ROMhYAAMShtrY2NTQ0qKCgILgvISFBBQUFqqur6/R9y5YtU0ZGhubMmdOt88Z0xgIAgGjmxORNn88Xsj8pKUlJSUnnHH/48GH5/X5lZmaG7M/MzNR7773X4Tlee+01/frXv1ZjY2O3+xmXgUU46VfKJUD8YIUIekO0lPZycnJCfl66dKnuvffeHrd77Ngxfec739ETTzyhIUOGdLuduAwsAACICg7MsThw4IBSUlKCuzvKVkjSkCFD1KdPHzU1NYXsb2pqUlZW1jnH//d//7c++OADTZkyJbgvEAhIkvr27atdu3bps5/97AW7yRwLAACc4sCqkJSUlJCts8AiMTFR48ePV21tbXBfIBBQbW2t8vPzzzl+5MiReuutt9TY2BjcbrnlFl133XVqbGw8J1PSGTIWAADEqdLSUhUXF2vChAmaOHGiKisr1dLSElwlMmvWLA0bNkwVFRVKTk7WFVdcEfL+tLQ0STpn//m4NrA4u1ZGXRaIXXx/Ea0ifefN6dOn65NPPlF5ebm8Xq/Gjh2rmpqa4ITO/fv3KyHBbvHCtYEFAABuUFJSopKSkg5f27Jly3nf+9RTT3X5fAQWAAA4xYVPNyWwAADAIZEuhUSC9VUhfr9fS5YsUW5urvr376/Pfvazuu+++2TM30bEGKPy8nINHTpU/fv3V0FBgfbs2WO7KwAAoJdZDywefvhhrVq1SitXrtS7776rhx9+WI888ohWrFgRPOaRRx7Ro48+qurqatXX1+uiiy5SYWGhTpw4Ybs7AABEToQfQhYJ1kshr7/+um699VbdfPPNkqQRI0bot7/9bfAxrcYYVVZW6p577tGtt94qSXr66aeVmZmp9evXa8aMGba7FBbu3AfYd+Z3KVruWgj0KhfOsbCesZg0aZJqa2u1e/duSdKf//xnvfbaa7rxxhslSfv27ZPX6w15KEpqaqry8vI6fShKa2urfD5fyAYAAKKP9YzF4sWL5fP5NHLkSPXp00d+v18PPPCAioqKJEler1eSOnwoyunXzlZRUaGf/vSntrsKAICjPP+32WorFlgPLH73u9/pmWee0Zo1a/T5z39ejY2NWrhwobKzs1VcXNytNsvKylRaWhr82efzhX1rUQDRobMSY7SXSMLtX6yUUG2Md6xcKyLDemDx4x//WIsXLw7OlRg9erQ+/PBDVVRUqLi4OPjgk6amJg0dOjT4vqamJo0dO7bDNjt7JCwAAFGNORY99+mnn55ze9A+ffoEn5CWm5urrKyskIei+Hw+1dfXd/hQFAAAYtXp+1jY2mKB9YzFlClT9MADD2j48OH6/Oc/rzfffFPLly/X9773PUmSx+PRwoULdf/99+vSSy9Vbm6ulixZouzsbE2dOtV2dwAAQC+yHlisWLFCS5Ys0Q9+8AMdOnRI2dnZ+qd/+ieVl5cHj7nrrrvU0tKiefPmqbm5Wddcc41qamqUnJxsuzsAotzZ9fpomHPRnT5E85J122MazdcadVxYCrEeWAwcOFCVlZWqrKzs9BiPx6Nly5Zp2bJltk8PAAAiiGeFAADgpBjJNNhCYNEB0nxA5ETiOxcN5Rfbeuua+Ht5fjyEDAAAoAfIWAAA4BQmb+JsZ6cTI53qi7e7ACK+8PlEPIvGFUzRiMACAACHuHGOBYEFAABOcWEphMmbAADAGjIWMaCndwGUqGnDOdSZzxWpJZj8LqKPG0shZCwAAIA1ZCwAAHCKC+dYEFi4BHfHQzSJhs8jZQP73FaCPX19J027pL0dH+TCwIJSCAAAsIaMBQAADnHj5M2YDixuu2y0+nr6xWVKMx6vCeiI29LncBlKIQAAAN0X0xkLAACimccYeYydVIOtdpwWF4EFD4YBACA6xEVgAQBAVHLhHAsCCwAAHOLGVSFM3gQAANaQsQAAB7Gc1uVcWAohYwEAAKwhYwEAgEPcOMciLgOLM1ONLD1FZ3r62SClDYTiO9EBSiEAAADdF5cZCwAAogGlEEQUZRtn2R7fM9tzcwq4p6XHSI1dPJZM4/GaEHsILAAAcIoL51gQWAAA4KBYKWHYwuRNAABgTdxnLGK1/gs7qDNHJ75XzmO+RZQw5tRmq60YQMYCAABYE/cZCwAAIoXlpohb8Z56JtUbHeL9c2ZDJJYpd+c8PDzNEheuCqEUAgAArCFjAQCAQzyBU5uttmKBqwILUnlA+HqrvBQN38uz++DktUfD9YYjVvqJ6OOqwAIAgF7lwjkWBBYAADiEVSFAjIiGVSCkiu1g9QEQXwgsAABwigvvvElgAQCAQ9xYCuE+FgAAwBoyFnEqHuvU0TCvIt5FwxhH4s6UZ+MBXrDGhatCyFgAAABryFgAAOAQN86xILAAuiAeS0w4v56WRfjMuJwLV4VQCgEAANaQsQAAwCGUQhBRpFzPFQ0z8uNxXNE9fBaACyOwAADAKS5cbkpgAQCAQ9xYCmHyJgAAsKbLgcXWrVs1ZcoUZWdny+PxaP369SGvG2NUXl6uoUOHqn///iooKNCePXtCjjly5IiKioqUkpKitLQ0zZkzR8ePH+/RhbhVYfbY4AY7zhxTxrX3MfaIKwFjd4sBXQ4sWlpaNGbMGFVVVXX4+iOPPKJHH31U1dXVqq+v10UXXaTCwkKdOHEieExRUZHeeecdbdy4US+99JK2bt2qefPmdf8qAABAVOjyHIsbb7xRN954Y4evGWNUWVmpe+65R7feeqsk6emnn1ZmZqbWr1+vGTNm6N1331VNTY22b9+uCRMmSJJWrFihm266ST//+c+VnZ3dg8sBACCKMHmzZ/bt2yev16uCgoLgvtTUVOXl5amurk4zZsxQXV2d0tLSgkGFJBUUFCghIUH19fW67bbbbHYpZpEG7l2MNwAneGRx8qadZhxnNbDwer2SpMzMzJD9mZmZwde8Xq8yMjJCO9G3r9LT04PHnK21tVWtra3Bn30+n81uAwAAS2JiVUhFRYVSU1ODW05OTqS7BADAhZ1+VoitLQZYzVhkZWVJkpqamjR06NDg/qamJo0dOzZ4zKFDh0Led/LkSR05ciT4/rOVlZWptLQ0+LPP5yO4cIme3o003LYROfwegPhiNWORm5urrKws1dbWBvf5fD7V19crPz9fkpSfn6/m5mY1NDQEj9m0aZMCgYDy8vI6bDcpKUkpKSkhGwAA0e70DbJsbd1RVVWlESNGKDk5WXl5edq2bVunxz7xxBP64he/qEGDBmnQoEEqKCg47/Ed6XJgcfz4cTU2NqqxsVHSqQmbjY2N2r9/vzwejxYuXKj7779fL7zwgt566y3NmjVL2dnZmjp1qiRp1KhRuuGGGzR37lxt27ZN//mf/6mSkhLNmDGDFSEAgPhiLG9dtG7dOpWWlmrp0qXauXOnxowZo8LCwnMqB6dt2bJFM2fO1ObNm1VXV6ecnBx95Stf0cGDB8M+p8eYrhVttmzZouuuu+6c/cXFxXrqqadkjNHSpUv1+OOPq7m5Wddcc40ee+wxXXbZZcFjjxw5opKSEr344otKSEjQtGnT9Oijj2rAgAFh9cHn8yk1NVX/u/vvlTIwgVSqC4VbFuGz0X1OPgCO3wviyUnTri36vY4ePRrMqJ/+d+qa6+5V377Jds5z8oRe23xvyHkuJC8vT1dffbVWrlwpSQoEAsrJydEPf/hDLV68+ILv9/v9GjRokFauXKlZs2aFdc4uz7G49tprdb5YxOPxaNmyZVq2bFmnx6Snp2vNmjVdPTUAADHFY4w8liZdnm7n7JWRSUlJSkpKOuf4trY2NTQ0qKysLLgvISFBBQUFqqurC+ucn376qdrb25Wenh52P2NiVQgAADEpYHmTlJOTE7JSsqKiosNTHz58WH6//7y3gLiQRYsWKTs7O+T+VBfC000BAIghBw4cCCmFdJStsOGhhx7S2rVrtWXLFiUnh1/OiYvA4uxaMPXb+Mfv2HndWerL7wUI5UQpJNzVkUOGDFGfPn3U1NQUsr+pqanT2zuc9vOf/1wPPfSQ/vjHP+rKK6/sUj8phQAAEIcSExM1fvz4kFtABAIB1dbWBm8B0ZFHHnlE9913n2pqakIevxGuuMhYAAAQlSL8ELLS0lIVFxdrwoQJmjhxoiorK9XS0qLZs2dLkmbNmqVhw4YF52k8/PDDKi8v15o1azRixIjgXIwBAwaEvXKTwALABVHiALrJ5q24u9HO9OnT9cknn6i8vFxer1djx45VTU1NcELn/v37lZDwt+LFqlWr1NbWpq9//esh7SxdulT33ntvWOcksAAAII6VlJSopKSkw9e2bNkS8vMHH3zQ4/MRWAAA4JCe3Iq7o7ZiAZM3AQCANWQsAABwSoTnWEQCgQUAAA7xBE5tttqKBZRCAACANXGZsTjzLoEskwMARIwLSyFkLAAAgDVxmbEAACAqRPjOm5FAYAEAgEOceAhZtKMUAgAArCFjAQCAU1w4eTMuAwtWggChq6M6w3cFgG1xGVgAABAVjCRbN7aKjYQFgQUAAE5h8iYAAEAPkLEA4kQ4cyou9B7mXACWGVmcvGmnGacRWAAA4BQXrgqhFAIAAKwhYwHEsO6UP3CucMeRUlHv6s7nO+p+RwFJHottxQAyFgAAwBoyFgAAOMSNy03jIrCIutQX4CDKH93X07E78/383bHH5mc66lY6MXkTAACg++IiYwEAQFRyYcYipgOL2y4brb6efpHuBhA34iHV31uloqhLuceQ3iznxcNnOtbEdGABAEBUI2MBAACs4T4WAAAA3UfGAohykVpeyt0o0VMsjXbnfSzIWAAAAGvIWAAA4BQmbwKIBrGUQo6G5XyxNF5wmYCRPJYCgkBsBBaUQgAAgDVkLAAAcAqlEAAAuoeSFCQCCwAAHGQxYyEyFgAAuJsLSyFM3gQAANaQsQBc5swlobZr4jzxEzhLwMhaCSNGlpsSWAAA4BQTOLXZaisGUAoBAADWkLEAXCAeSxIsbUQ4Iv7ZZ/ImAABA95GxAADAKUzehNv1NL0c8bQjAFeLur9BlEIAAAC6j4wFAABOMbKYsbDTjNMILFzOyRskRV1KEr0unj8P8XY9Npw9Jr21coffRXTpcilk69atmjJlirKzs+XxeLR+/frga+3t7Vq0aJFGjx6tiy66SNnZ2Zo1a5Y++uijkDaOHDmioqIipaSkKC0tTXPmzNHx48d7fDEAAESV03MsbG0xoMuBRUtLi8aMGaOqqqpzXvv000+1c+dOLVmyRDt37tRzzz2nXbt26ZZbbgk5rqioSO+88442btyol156SVu3btW8efO6fxUAAESjQMDuFgO6XAq58cYbdeONN3b4WmpqqjZu3Biyb+XKlZo4caL279+v4cOH691331VNTY22b9+uCRMmSJJWrFihm266ST//+c+VnZ3djcsAAADRwPE5FkePHpXH41FaWpokqa6uTmlpacGgQpIKCgqUkJCg+vp63XbbbU53yfW4Y2H0s/GgsHivOzv5MDXY0dln8Hy/r7j73LpwuamjgcWJEye0aNEizZw5UykpKZIkr9erjIyM0E707av09HR5vd4O22ltbVVra2vwZ5/P51ynAQBAtzl2H4v29nZ985vflDFGq1at6lFbFRUVSk1NDW45OTmWegkAgINcOHnTkYzF6aDiww8/1KZNm4LZCknKysrSoUOHQo4/efKkjhw5oqysrA7bKysrU2lpafBnn89HcNFFpIpjl5Op4UgtD4xVcZemjxBXjSO39O6500HFnj17tHnzZg0ePDjk9fz8fDU3N6uhoUHjx4+XJG3atEmBQEB5eXkdtpmUlKSkpCTbXQUAAJZ1ObA4fvy43n///eDP+/btU2Njo9LT0zV06FB9/etf186dO/XSSy/J7/cH502kp6crMTFRo0aN0g033KC5c+equrpa7e3tKikp0YwZM1gRAgCIK8YEZIydZaK22nFalwOLHTt26Lrrrgv+fLpEUVxcrHvvvVcvvPCCJGns2LEh79u8ebOuvfZaSdIzzzyjkpISXX/99UpISNC0adP06KOPdvMS0BFS2nATJ1eIuCptD1jQ5cDi2muvlTnPBJLzvXZaenq61qxZ09VTAwAQW4yxNzfCzZM3AQCA/i8YcFdgwWPTAQCANTGdsXh+91tKGZhADRSwJB7uZsldSxFVAgHJY2nSZbxO3gQAAGGiFAIAANB9cZGxODvdSRozchj7+BGrZREbfT2zDT7T6AkTCMhYKoXEyn0syFgAAABr4iJjAQBAVHLhHAsCizgSS+lquENvlRH47CNqBYzkcVdgQSkEAABYQ8YCAACnGCPJ1n0sYiNjQWAB4IKiYWUE5Q4gNhBYAADgEBMwMpbmWITzkM9oQGABAIBTTED2SiHcxwIAAERYVVWVRowYoeTkZOXl5Wnbtm3nPf7ZZ5/VyJEjlZycrNGjR+vll1/u0vkILOJIYfbY4OaG8wJAtDMBY3XrqnXr1qm0tFRLly7Vzp07NWbMGBUWFurQoUMdHv/6669r5syZmjNnjt58801NnTpVU6dO1dtvvx32OQksAACIU8uXL9fcuXM1e/ZsXX755aqurtZnPvMZrV69usPjf/WrX+mGG27Qj3/8Y40aNUr33XefrrrqKq1cuTLsc8bkHIvTE1h8xzuuN5007b3ZnajkO9Z7tTjGG72hNz/TZ+LzjQs5qVOfkY4mV540rdbmRpw+j8/nC9mflJSkpKSkc45va2tTQ0ODysrKgvsSEhJUUFCgurq6Ds9RV1en0tLSkH2FhYVav3592P2MycDi2LFjkqRLrvqgkyP29lpfotWgy3rzbIw3nNe7n+kz8flGeI4dO6bU1FRJUmJiorKysvSat2vzEy5kwIABysnJCdm3dOlS3Xvvvecce/jwYfn9fmVmZobsz8zM1Hvvvddh+16vt8PjvV5v2H2MycAiOztbBw4ckDFGw4cP14EDB5SSkhLpbkWEz+dTTk6Oq8dAYhxOYxxOYRwYg9N6YxyMMTp27Jiys7OD+5KTk7Vv3z61tbVZP5fH4wnZ11G2IpJiMrBISEjQxRdfHEwHpaSkuPqLIzEGpzEOpzAOpzAOjMFpTo/D6UzFmZKTk5WcnOzYOS9kyJAh6tOnj5qamkL2NzU1KSsrq8P3ZGVlden4jjB5EwCAOJSYmKjx48ertrY2uC8QCKi2tlb5+fkdvic/Pz/keEnauHFjp8d3JCYzFgAA4MJKS0tVXFysCRMmaOLEiaqsrFRLS4tmz54tSZo1a5aGDRumiooKSdKCBQv0pS99Sb/4xS908803a+3atdqxY4cef/zxsM8Z04FFUlKSli5dGnX1pd7EGJzCOJzCOJzCODAGp7l9HKZPn65PPvlE5eXl8nq9Gjt2rGpqaoITNPfv36+EhL8VLyZNmqQ1a9bonnvu0U9+8hNdeumlWr9+va644oqwz+kxsXLzcQAAEPWYYwEAAKwhsAAAANYQWAAAAGsILAAAgDUxG1h09TGwsa6iokJXX321Bg4cqIyMDE2dOlW7du0KOebEiROaP3++Bg8erAEDBmjatGnn3Ogknjz00EPyeDxauHBhcJ9bxuDgwYP69re/rcGDB6t///4aPXq0duzYEXzdGKPy8nINHTpU/fv3V0FBgfbs2RPBHtvn9/u1ZMkS5ebmqn///vrsZz+r++67L+R5DfE4Dlu3btWUKVOUnZ0tj8dzzjMcwrnmI0eOqKioSCkpKUpLS9OcOXN0/PjxXryKnjvfOLS3t2vRokUaPXq0LrroImVnZ2vWrFn66KOPQtqIh3GISiYGrV271iQmJprVq1ebd955x8ydO9ekpaWZpqamSHfNMYWFhebJJ580b7/9tmlsbDQ33XSTGT58uDl+/HjwmNtvv93k5OSY2tpas2PHDvOFL3zBTJo0KYK9ds62bdvMiBEjzJVXXmkWLFgQ3O+GMThy5Ii55JJLzHe/+11TX19v9u7da1555RXz/vvvB4956KGHTGpqqlm/fr3585//bG655RaTm5tr/vrXv0aw53Y98MADZvDgweall14y+/btM88++6wZMGCA+dWvfhU8Jh7H4eWXXzZ33323ee6554wk8/zzz4e8Hs4133DDDWbMmDHmjTfeMH/605/M5z73OTNz5sxevpKeOd84NDc3m4KCArNu3Trz3nvvmbq6OjNx4kQzfvz4kDbiYRyiUUwGFhMnTjTz588P/uz3+012drapqKiIYK9616FDh4wk8+qrrxpjTn2R+vXrZ5599tngMe+++66RZOrq6iLVTUccO3bMXHrppWbjxo3mS1/6UjCwcMsYLFq0yFxzzTWdvh4IBExWVpb52c9+FtzX3NxskpKSzG9/+9ve6GKvuPnmm833vve9kH1f+9rXTFFRkTHGHeNw9j+o4VzzX/7yFyPJbN++PXjMH/7wB+PxeMzBgwd7re82dRRgnW3btm1Gkvnwww+NMfE5DtEi5kohpx8DW1BQENx3ocfAxqOjR49KktLT0yVJDQ0Nam9vDxmXkSNHavjw4XE3LvPnz9fNN98ccq2Se8bghRde0IQJE/SNb3xDGRkZGjdunJ544ong6/v27ZPX6w0Zh9TUVOXl5cXVOEyaNEm1tbXavXu3JOnPf/6zXnvtNd14442S3DMOZwrnmuvq6pSWlqYJEyYEjykoKFBCQoLq6+t7vc+95ejRo/J4PEpLS5Pk3nHoDTF3583uPAY23gQCAS1cuFCTJ08O3g3N6/UqMTEx+KU5rauPu412a9eu1c6dO7V9+/ZzXnPLGOzdu1erVq1SaWmpfvKTn2j79u360Y9+pMTERBUXFwevtaePPo52ixcvls/n08iRI9WnTx/5/X498MADKioqkiTXjMOZwrlmr9erjIyMkNf79u2r9PT0uB2XEydOaNGiRZo5c2bwQWRuHIfeEnOBBU79H/vbb7+t1157LdJd6VUHDhzQggULtHHjxog+MTDSAoGAJkyYoAcffFCSNG7cOL399tuqrq5WcXFxhHvXe373u9/pmWee0Zo1a/T5z39ejY2NWrhwobKzs101Dji/9vZ2ffOb35QxRqtWrYp0d1wh5koh3XkMbDwpKSnRSy+9pM2bN+viiy8O7s/KylJbW5uam5tDjo+ncWloaNChQ4d01VVXqW/fvurbt69effVVPfroo+rbt68yMzPjfgwkaejQobr88stD9o0aNUr79++XpOC1xvt35Mc//rEWL16sGTNmaPTo0frOd76jO++8M/gwJbeMw5nCueasrCwdOnQo5PWTJ0/qyJEjcTcup4OKDz/8UBs3bgx5bLqbxqG3xVxg0Z3HwMYDY4xKSkr0/PPPa9OmTcrNzQ15ffz48erXr1/IuOzatUv79++Pm3G5/vrr9dZbb6mxsTG4TZgwQUVFRcH/jvcxkKTJkyefs9R49+7duuSSSyRJubm5ysrKChkHn8+n+vr6uBqHTz/9NOThSZLUp08fBQIBSe4ZhzOFc835+flqbm5WQ0ND8JhNmzYpEAgoLy+v1/vslNNBxZ49e/THP/5RgwcPDnndLeMQEZGePdoda9euNUlJSeapp54yf/nLX8y8efNMWlqa8Xq9ke6aY+644w6TmppqtmzZYj7++OPg9umnnwaPuf32283w4cPNpk2bzI4dO0x+fr7Jz8+PYK+dd+aqEGPcMQbbtm0zffv2NQ888IDZs2ePeeaZZ8xnPvMZ82//9m/BYx566CGTlpZmfv/735v/+q//MrfeemvML7M8W3FxsRk2bFhwuelzzz1nhgwZYu66667gMfE4DseOHTNvvvmmefPNN40ks3z5cvPmm28GVzuEc8033HCDGTdunKmvrzevvfaaufTSS2NumeX5xqGtrc3ccsst5uKLLzaNjY0hfzNbW1uDbcTDOESjmAwsjDFmxYoVZvjw4SYxMdFMnDjRvPHGG5HukqMkdbg9+eSTwWP++te/mh/84Adm0KBB5jOf+Yy57bbbzMcffxy5TveCswMLt4zBiy++aK644gqTlJRkRo4caR5//PGQ1wOBgFmyZInJzMw0SUlJ5vrrrze7du2KUG+d4fP5zIIFC8zw4cNNcnKy+fu//3tz9913h/zDEY/jsHnz5g7/FhQXFxtjwrvm//mf/zEzZ840AwYMMCkpKWb27Nnm2LFjEbia7jvfOOzbt6/Tv5mbN28OthEP4xCNeGw6AACwJubmWAAAgOhFYAEAAKwhsAAAANYQWAAAAGsILAAAgDUEFgAAwBoCCwAAYA2BBQAAsIbAAgAAWENgAQAArCGwAAAA1hBYAAAAa/4/mN5T3JKrmXcAAAAASUVORK5CYII="},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}},{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[13], line 43\u001b[0m\n\u001b[1;32m 38\u001b[0m preds_test_upsampled \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m 39\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;28mlen\u001b[39m(preds_test)):\n\u001b[1;32m 40\u001b[0m preds_test_upsampled\u001b[38;5;241m.\u001b[39mappend(resize(np\u001b[38;5;241m.\u001b[39msqueeze(preds_test[i]), \n\u001b[1;32m 41\u001b[0m (sizes_test[i][\u001b[38;5;241m0\u001b[39m], sizes_test[i][\u001b[38;5;241m1\u001b[39m]), \n\u001b[1;32m 42\u001b[0m mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mconstant\u001b[39m\u001b[38;5;124m'\u001b[39m, preserve_range\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[0;32m---> 43\u001b[0m anti_aliasing\u001b[38;5;241m=\u001b[39mnp\u001b[38;5;241m.\u001b[39many(\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpreds_test_t\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m<\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpreds_train_t\u001b[49m\u001b[43m)\u001b[49m)))\n","\u001b[0;31mValueError\u001b[0m: operands could not be broadcast together with shapes (65,128,128,1) (603,128,128,1) "],"ename":"ValueError","evalue":"operands could not be broadcast together with shapes (65,128,128,1) (603,128,128,1) ","output_type":"error"}]},{"cell_type":"code","source":"from scipy.spatial import QhullError\nfrom scipy import spatial\nspatial.QhullError = QhullError\nfrom skimage.morphology import label\n\n\ndef rle_encoding(x):\n dots = np.where(x.T.flatten() == 1)[0]\n run_lengths = []\n prev = -2\n for b in dots:\n if (b>prev+1): run_lengths.extend((b + 1, 0))\n run_lengths[-1] += 1\n prev = b\n return run_lengths\n\ndef prob_to_rles(x, cutoff=0.5):\n lab_img = label(x > cutoff)\n for i in range(1, lab_img.max() + 1):\n yield rle_encoding(lab_img == i)\nnew_test_ids = []","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:57:19.227895Z","iopub.execute_input":"2024-03-17T19:57:19.228478Z","iopub.status.idle":"2024-03-17T19:57:19.235647Z","shell.execute_reply.started":"2024-03-17T19:57:19.228446Z","shell.execute_reply":"2024-03-17T19:57:19.23468Z"},"trusted":true},"execution_count":8,"outputs":[]},{"cell_type":"code","source":"new_test_ids = []\nrles = []\nfor n, id_ in enumerate(test_ids):\n rle = list(prob_to_rles(preds_test_upsampled[n]))\n rles.extend(rle)\n new_test_ids.extend([id_] * len(rle))","metadata":{"execution":{"iopub.status.busy":"2024-03-17T19:57:22.156509Z","iopub.execute_input":"2024-03-17T19:57:22.157413Z","iopub.status.idle":"2024-03-17T19:57:22.197988Z","shell.execute_reply.started":"2024-03-17T19:57:22.157378Z","shell.execute_reply":"2024-03-17T19:57:22.196824Z"},"trusted":true},"execution_count":9,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[9], line 4\u001b[0m\n\u001b[1;32m 2\u001b[0m rles \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m 3\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m n, id_ \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(test_ids):\n\u001b[0;32m----> 4\u001b[0m rle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(prob_to_rles(\u001b[43mpreds_test_upsampled\u001b[49m\u001b[43m[\u001b[49m\u001b[43mn\u001b[49m\u001b[43m]\u001b[49m))\n\u001b[1;32m 5\u001b[0m rles\u001b[38;5;241m.\u001b[39mextend(rle)\n\u001b[1;32m 6\u001b[0m new_test_ids\u001b[38;5;241m.\u001b[39mextend([id_] \u001b[38;5;241m*\u001b[39m \u001b[38;5;28mlen\u001b[39m(rle))\n","\u001b[0;31mIndexError\u001b[0m: list index out of range"],"ename":"IndexError","evalue":"list index out of range","output_type":"error"}]},{"cell_type":"code","source":"import pandas as pd\n# Create submission DataFrame\nsub = pd.DataFrame()\nsub['ImageId'] = new_test_ids\nsub['EncodedPixels'] = pd.Series(rles).apply(lambda x: ' '.join(str(y) for y in x))\nsub.to_csv('submission.csv', index=False)","metadata":{},"execution_count":13,"outputs":[]},{"cell_type":"code","source":"import tensorboard\n\n\n!tensorboard --logdir=logs/ --host localhost --port 8088","metadata":{},"execution_count":20,"outputs":[{"name":"stdout","output_type":"stream","text":"2024-03-16 22:56:40.751431: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n\n2024-03-16 22:56:40.752315: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n\n2024-03-16 22:56:40.875262: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n\n2024-03-16 22:56:41.157331: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n\nTo enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n\n2024-03-16 22:56:42.865572: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n\n\n\nNOTE: Using experimental fast data loading logic. To disable, pass\n\n \"--load_fast=false\" and report issues on GitHub. More details:\n\n https://github.com/tensorflow/tensorboard/issues/4784\n\n\n\nTensorBoard 2.15.1 at http://localhost:8088/ (Press CTRL+C to quit)\n\n^C\n"}]},{"cell_type":"code","source":"!ps -ef | grep 'tensorboard' | awk '{print $2}' | xargs kill -9","metadata":{},"execution_count":45,"outputs":[{"name":"stdout","output_type":"stream","text":"kill: sending signal to 9965 failed: No such process\n"}]},{"cell_type":"code","source":"# def mdl():\n\t\n# \tIMG_WIDTH = 128\n# \tIMG_HEIGHT = 128\n# \tIMG_CHANNELS = 3\n# \tinputs = tf.keras.layers.Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS))\n# \tmodel=Sequential()\n# \ts=Lambda(lambda x: x/255.0)(inputs)\n# \tmodel.add(Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same',input_shape=s.shape[1:]))\n# \tmodel.add(Dropout(0.1))\n# \tmodel.add(Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(MaxPooling2D((2, 2)))\n\n# \tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(Dropout(0.1))\n# \tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(MaxPooling2D((2, 2)))\n\n# \tmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(Dropout(0.2))\n# \tmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(MaxPooling2D((2, 2)))\n\n# \tmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(Dropout(0.2))\n# \tmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\n# \tmodel.add(Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(Dropout(0.3))\n# \tmodel.add(Conv2D(256, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n\n# \tmodel.add(Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same'))\n# \tconcat = concatenate([model.layers[-1].output, model.layers[12].output])\n# \t# model.add(concatenate([model.layers[-1], model.layers[7]]))\n# \tmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same')(concat))\n# \tmodel.add(Dropout(0.2))\n# \tmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n\t\n# \tmodel.add(Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same'))\n# \tmodel.add(concatenate([model.layers[-1], model.layers[5]]))\n# \tmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(Dropout(0.2))\n# \tmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n\n# \tmodel.add(Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same'))\n# \tmodel.add(concatenate([model.layers[-1], model.layers[3]]))\n# \tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(Dropout(0.1))\n# \tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n\n# \tmodel.add(Conv2DTranspose(16, (2, 2), strides=(2, 2), padding='same'))\n# \tmodel.add(concatenate([model.layers[-1], model.layers[1]], axis=3))\n# \tmodel.add(Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n# \tmodel.add(Dropout(0.1))\n# \tmodel.add(Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'))\n\n# \tmodel.add(Conv2D(1, (1, 1), activation='sigmoid'))\n# \tmodel.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n\t\n# \treturn model\n\t\n\n# mdl().summary()","metadata":{},"execution_count":11,"outputs":[]}]}