diff --git a/labworks/LW3/IS_lab_4.png b/labworks/LW3/IS_lab_4.png new file mode 100644 index 0000000..9ce5f26 Binary files /dev/null and b/labworks/LW3/IS_lab_4.png differ diff --git a/labworks/LW3/IS_lab_4_90.png b/labworks/LW3/IS_lab_4_90.png new file mode 100644 index 0000000..c520ac8 Binary files /dev/null and b/labworks/LW3/IS_lab_4_90.png differ diff --git a/labworks/LW3/IS_lab_7.png b/labworks/LW3/IS_lab_7.png new file mode 100644 index 0000000..6479bad Binary files /dev/null and b/labworks/LW3/IS_lab_7.png differ diff --git a/labworks/LW3/IS_lab_7_90.png b/labworks/LW3/IS_lab_7_90.png new file mode 100644 index 0000000..74df118 Binary files /dev/null and b/labworks/LW3/IS_lab_7_90.png differ diff --git a/labworks/LW3/Untitled0(1).ipynb b/labworks/LW3/Untitled0(1).ipynb new file mode 100644 index 0000000..6b40aec --- /dev/null +++ b/labworks/LW3/Untitled0(1).ipynb @@ -0,0 +1 @@ +{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4","authorship_tag":"ABX9TyMdzhccQQnmGAjjqRNUC4cu"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"markdown","source":["Импорт модулей"],"metadata":{"id":"Dzf4Ynt3RHl7"}},{"cell_type":"code","execution_count":null,"metadata":{"id":"reN-TdVHPk0R"},"outputs":[],"source":["# импорт модулей\n","from tensorflow import keras\n","from tensorflow.keras import layers\n","from tensorflow.keras.models import Sequential\n","import matplotlib.pyplot as plt\n","import numpy as np\n","from sklearn.metrics import classification_report, confusion_matrix\n","from sklearn.metrics import ConfusionMatrixDisplay"]},{"cell_type":"markdown","source":["Загрузка набора данных"],"metadata":{"id":"g2_CTk0fRX2X"}},{"cell_type":"code","source":["# загрузка датасета\n","from keras.datasets import mnist\n","(X_train, y_train), (X_test, y_test) = mnist.load_data()\n","2\n","# создание своего разбиения датасета\n","from sklearn.model_selection import train_test_split\n","# объединяем в один набор\n","X = np.concatenate((X_train, X_test))\n","y = np.concatenate((y_train, y_test))\n","# разбиваем по вариантам\n","X_train, X_test, y_train, y_test = train_test_split(X, y,\n","test_size = 10000,\n","train_size = 60000,\n","random_state = 39)\n","# вывод размерностей\n","print('Shape of X train:', X_train.shape)\n","print('Shape of y train:', y_train.shape)\n","print('Shape of X test:', X_test.shape)\n","print('Shape of y test:', y_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"iCzWwhTKRa7Y","executionInfo":{"status":"ok","timestamp":1765220905573,"user_tz":-180,"elapsed":129,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"1440dcda-9a84-40a4-bb29-e0733da18c70"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of X train: (60000, 28, 28)\n","Shape of y train: (60000,)\n","Shape of X test: (10000, 28, 28)\n","Shape of y test: (10000,)\n"]}]},{"cell_type":"markdown","source":["Предобработка данных"],"metadata":{"id":"tu2I7_uGR4M9"}},{"cell_type":"code","source":["# Зададим параметры данных и модели\n","num_classes = 10\n","input_shape = (28, 28, 1)\n","# Приведение входных данных к диапазону [0, 1]\n","X_train = X_train / 255\n","X_test = X_test / 255\n","# Расширяем размерность входных данных, чтобы каждое изображение имело\n","# размерность (высота, ширина, количество каналов)\n","3\n","X_train = np.expand_dims(X_train, -1)\n","X_test = np.expand_dims(X_test, -1)\n","print('Shape of transformed X train:', X_train.shape)\n","print('Shape of transformed X test:', X_test.shape)\n","# переведем метки в one-hot\n","y_train = keras.utils.to_categorical(y_train, num_classes)\n","y_test = keras.utils.to_categorical(y_test, num_classes)\n","print('Shape of transformed y train:', y_train.shape)\n","print('Shape of transformed y test:', y_test.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"G3iLFVuhR6WG","executionInfo":{"status":"ok","timestamp":1765220905723,"user_tz":-180,"elapsed":146,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"6a287364-8e5d-4a21-d829-dca62ef62be0"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of transformed X train: (60000, 28, 28, 1)\n","Shape of transformed X test: (10000, 28, 28, 1)\n","Shape of transformed y train: (60000, 10)\n","Shape of transformed y test: (10000, 10)\n"]}]},{"cell_type":"markdown","source":["Реализация сверточной нейронной сети и оценка качества классификации"],"metadata":{"id":"c2-AL2D4SATF"}},{"cell_type":"code","source":["# создаем модель\n","model = Sequential()\n","model.add(layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\", input_shape=input_shape))\n","model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n","model.add(layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"))\n","model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n","model.add(layers.Dropout(0.5))\n","model.add(layers.Flatten())\n","model.add(layers.Dense(num_classes, activation=\"softmax\"))\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":430},"id":"9u7K8x36SA3R","executionInfo":{"status":"ok","timestamp":1765220905821,"user_tz":-180,"elapsed":92,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"9bf0c568-9fb4-4f44-c492-4160aa8aa5e9"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n"," super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_2\"\u001b[0m\n"],"text/html":["
Model: \"sequential_2\"\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┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m320\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_5 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_5 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten_2 (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1600\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m16,010\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d_4 (Conv2D)               │ (None, 26, 26, 32)     │           320 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_4 (MaxPooling2D)  │ (None, 13, 13, 32)     │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_5 (Conv2D)               │ (None, 11, 11, 64)     │        18,496 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_5 (MaxPooling2D)  │ (None, 5, 5, 64)       │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_2 (Dropout)             │ (None, 5, 5, 64)       │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten_2 (Flatten)             │ (None, 1600)           │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_2 (Dense)                 │ (None, 10)             │        16,010 │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","
\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m34,826\u001b[0m (136.04 KB)\n"],"text/html":["
 Total params: 34,826 (136.04 KB)\n","
\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m34,826\u001b[0m (136.04 KB)\n"],"text/html":["
 Trainable params: 34,826 (136.04 KB)\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":["# компилируем и обучаем модель\n","batch_size = 512\n","epochs = 15\n","model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n","model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"9YdsUe1SSrEM","executionInfo":{"status":"ok","timestamp":1765220930442,"user_tz":-180,"elapsed":24618,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"4b648739-f133-4701-dae3-92f26d8af04e"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 40ms/step - accuracy: 0.6094 - loss: 1.2944 - val_accuracy: 0.9478 - val_loss: 0.1765\n","Epoch 2/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 11ms/step - accuracy: 0.9412 - loss: 0.1983 - val_accuracy: 0.9695 - val_loss: 0.1006\n","Epoch 3/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9601 - loss: 0.1309 - val_accuracy: 0.9747 - val_loss: 0.0796\n","Epoch 4/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9690 - loss: 0.1062 - val_accuracy: 0.9773 - val_loss: 0.0661\n","Epoch 5/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9728 - loss: 0.0889 - val_accuracy: 0.9802 - val_loss: 0.0581\n","Epoch 6/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9753 - loss: 0.0769 - val_accuracy: 0.9825 - val_loss: 0.0510\n","Epoch 7/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 12ms/step - accuracy: 0.9781 - loss: 0.0706 - val_accuracy: 0.9845 - val_loss: 0.0472\n","Epoch 8/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9808 - loss: 0.0646 - val_accuracy: 0.9850 - val_loss: 0.0459\n","Epoch 9/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 12ms/step - accuracy: 0.9822 - loss: 0.0584 - val_accuracy: 0.9858 - val_loss: 0.0412\n","Epoch 10/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 12ms/step - accuracy: 0.9818 - loss: 0.0571 - val_accuracy: 0.9860 - val_loss: 0.0400\n","Epoch 11/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 10ms/step - accuracy: 0.9832 - loss: 0.0542 - val_accuracy: 0.9873 - val_loss: 0.0381\n","Epoch 12/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9855 - loss: 0.0481 - val_accuracy: 0.9872 - val_loss: 0.0366\n","Epoch 13/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9852 - loss: 0.0485 - val_accuracy: 0.9882 - val_loss: 0.0353\n","Epoch 14/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9868 - loss: 0.0448 - val_accuracy: 0.9895 - val_loss: 0.0344\n","Epoch 15/15\n","\u001b[1m106/106\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - accuracy: 0.9862 - loss: 0.0455 - val_accuracy: 0.9880 - val_loss: 0.0343\n"]},{"output_type":"execute_result","data":{"text/plain":[""]},"metadata":{},"execution_count":32}]},{"cell_type":"code","source":["# Оценка качества работы модели на тестовых данных\n","scores = model.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"7HGm_ZujS4iY","executionInfo":{"status":"ok","timestamp":1765220931989,"user_tz":-180,"elapsed":1543,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"63c403c1-d856-49d6-aafd-730845986780"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - accuracy: 0.9883 - loss: 0.0410\n","Loss on test data: 0.04110224172472954\n","Accuracy on test data: 0.988099992275238\n"]}]},{"cell_type":"markdown","source":["Применение обученной модели"],"metadata":{"id":"dZ_-0AvWUBHx"}},{"cell_type":"code","source":["# вывод тестового изображения и результата распознавания\n","n = 123\n","result = model.predict(X_test[n:n+1])\n","print('NN output:', result)\n","plt.imshow(X_test[n].reshape(28,28), cmap=plt.get_cmap('gray'))\n","plt.show()\n","print('Real mark: ', np.argmax(y_test[n]))\n","print('NN answer: ', np.argmax(result))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":519},"id":"b628pa6EUEIL","executionInfo":{"status":"ok","timestamp":1765220932465,"user_tz":-180,"elapsed":475,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"17677dca-52ff-4328-e2e4-7f2cb47e1be5"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 330ms/step\n","NN output: [[2.7634337e-06 9.1870556e-10 1.8290423e-06 1.8450550e-08 2.7429451e-07\n"," 8.1886617e-07 9.9999094e-01 5.0058091e-13 3.2977912e-06 7.4129168e-11]]\n"]},{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark: 6\n","NN answer: 6\n"]}]},{"cell_type":"markdown","source":["Вычисление показателей качества классификации"],"metadata":{"id":"hq60m32HUJ-v"}},{"cell_type":"code","source":["# истинные метки классов\n","true_labels = np.argmax(y_test, axis=1)\n","# предсказанные метки классов\n","predicted_labels = np.argmax(model.predict(X_test), axis=1)\n","# отчет о качестве классификации\n","print(classification_report(true_labels, predicted_labels))\n","# вычисление матрицы ошибок\n","conf_matrix = confusion_matrix(true_labels, predicted_labels)\n","# отрисовка матрицы ошибок в виде \"тепловой карты\"\n","display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix)\n","display.plot()\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":771},"id":"6wPLomssUKhn","executionInfo":{"status":"ok","timestamp":1765220933828,"user_tz":-180,"elapsed":1329,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"01f98b67-d648-4a52-984e-388c49982478"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step\n"," precision recall f1-score support\n","\n"," 0 0.99 0.99 0.99 990\n"," 1 0.99 0.99 0.99 1155\n"," 2 0.99 0.99 0.99 1025\n"," 3 0.99 0.99 0.99 1016\n"," 4 0.99 0.99 0.99 959\n"," 5 0.99 0.99 0.99 889\n"," 6 0.99 0.99 0.99 997\n"," 7 0.99 0.98 0.98 1034\n"," 8 0.99 0.98 0.98 991\n"," 9 0.99 0.98 0.98 944\n","\n"," accuracy 0.99 10000\n"," macro avg 0.99 0.99 0.99 10000\n","weighted avg 0.99 0.99 0.99 10000\n","\n"]},{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"markdown","source":["Распознавание собственного изображения"],"metadata":{"id":"9LGDNhoiUUbC"}},{"cell_type":"code","source":["# загрузка собственного изображения\n","from PIL import Image\n","file_data = Image.open('/content/drive/MyDrive/Colab Notebooks/IS_lab_4.png')\n","file_data = file_data.convert('L') # перевод в градации серого\n","test_img = np.array(file_data)\n","# вывод собственного изображения\n","plt.imshow(test_img, cmap=plt.get_cmap('gray'))\n","plt.show()\n","# предобработка\n","test_img = test_img / 255\n","test_img = np.reshape(test_img, (1,28,28,1))\n","# распознавание\n","result = model.predict(test_img)\n","print('I think it\\'s ', np.argmax(result))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":466},"id":"MDmuCf7zUVKk","executionInfo":{"status":"ok","timestamp":1765220933936,"user_tz":-180,"elapsed":79,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"c059e732-7153-48c3-8ff7-45a051924ac7"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step\n","I think it's 4\n"]}]},{"cell_type":"code","source":["from PIL import Image\n","file_data = Image.open('/content/drive/MyDrive/Colab Notebooks/IS_lab_7.png')\n","file_data = file_data.convert('L') # перевод в градации серого\n","test_img = np.array(file_data)\n","\n","plt.imshow(test_img, cmap=plt.get_cmap('gray'))\n","plt.show()\n","\n","test_img = test_img / 255\n","test_img = np.reshape(test_img, (1,28,28,1))\n","\n","result = model.predict(test_img)\n","print('I think it\\'s ', np.argmax(result))"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":466},"id":"_z3VQp_iVfgH","executionInfo":{"status":"ok","timestamp":1765220934114,"user_tz":-180,"elapsed":175,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"5914d3cf-dd33-46c0-bbcc-5822b5222c09"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step\n","I think it's 7\n"]}]},{"cell_type":"markdown","source":["Загрузим модель из первой лабораторной работы и сравним её с полученной в этой ЛР"],"metadata":{"id":"jZBYX7GvWJaR"}},{"cell_type":"code","source":["model_lr1 = keras.models.load_model(\"/content/drive/MyDrive/Colab Notebooks/best_model_100.keras\")\n","model_lr1.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":221},"id":"I5g-tsyFWVY6","executionInfo":{"status":"ok","timestamp":1765220934679,"user_tz":-180,"elapsed":125,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"4bf9fe93-ce4c-49a4-8e79-68b2a66bffd7"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_16\"\u001b[0m\n"],"text/html":["
Model: \"sequential_16\"\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┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_26 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m) │ \u001b[38;5;34m78,500\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_27 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,010\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ dense_26 (Dense)                │ (None, 100)            │        78,500 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_27 (Dense)                │ (None, 10)             │         1,010 │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","
\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m79,512\u001b[0m (310.60 KB)\n"],"text/html":["
 Total params: 79,512 (310.60 KB)\n","
\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m79,510\u001b[0m (310.59 KB)\n"],"text/html":["
 Trainable params: 79,510 (310.59 KB)\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":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m2\u001b[0m (12.00 B)\n"],"text/html":["
 Optimizer params: 2 (12.00 B)\n","
\n"]},"metadata":{}}]},{"cell_type":"code","source":["X_train_flat = X.reshape(70000, 28*28)\n","X_train_flat = X_train_flat / 255.0\n","X_train_flat, X_test_flat, y_train_flat, y_test_flat = train_test_split(\n"," X_train_flat, y, test_size=10000, train_size=60000, random_state=39\n",")\n","y_train_flat = keras.utils.to_categorical(y_train_flat, num_classes)\n","y_test_flat = keras.utils.to_categorical(y_test_flat, num_classes)\n","print('Shape of transformed X train:', X_train_flat.shape)\n","print('Shape of transformed X test:', X_test_flat.shape)\n","print('Shape of transformed y train:', y_train_flat.shape)\n","print('Shape of transformed y test:', y_test_flat.shape)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"RdKmjz59W8SB","executionInfo":{"status":"ok","timestamp":1765220934974,"user_tz":-180,"elapsed":287,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"2c8d1a9f-2512-4101-fe56-acf38140f186"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of transformed X train: (60000, 784)\n","Shape of transformed X test: (10000, 784)\n","Shape of transformed y train: (60000, 10)\n","Shape of transformed y test: (10000, 10)\n"]}]},{"cell_type":"code","source":["scores = model_lr1.evaluate(X_test_flat, y_test_flat)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"0KJygQVEW_hj","executionInfo":{"status":"ok","timestamp":1765220937230,"user_tz":-180,"elapsed":2254,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"992765f0-16df-44d0-ead4-d8f1c9ad6fb4"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 5ms/step - accuracy: 0.9153 - loss: 0.3012\n","Loss on test data: 0.2998492121696472\n","Accuracy on test data: 0.9138000011444092\n"]}]},{"cell_type":"markdown","source":["Работа с набором CIFAR-10"],"metadata":{"id":"uMjahLELXt6z"}},{"cell_type":"code","source":["# загрузка датасета\n","from keras.datasets import cifar10\n","(X_train, y_train), (X_test, y_test) = cifar10.load_data()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"q5DbBUbCXyR9","executionInfo":{"status":"ok","timestamp":1765221287271,"user_tz":-180,"elapsed":6661,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"169ee2f4-76c1-481d-86cf-26e79a78ffe7"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n","\u001b[1m170498071/170498071\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 0us/step\n"]}]},{"cell_type":"code","source":["# создание своего разбиения датасета\n","# объединяем в один набор\n","X = np.concatenate((X_train, X_test))\n","y = np.concatenate((y_train, y_test))\n","\n","# разбиваем по вариантам\n","X_train, X_test, y_train, y_test = train_test_split(\n"," X, y, test_size=10000, train_size=50000, random_state=39\n",")\n","# вывод размерностей\n","print('Shape of X train:', X_train.shape)\n","print('Shape of y train:', y_train.shape)\n","print('Shape of X test:', X_test.shape)\n","print('Shape of y test:', y_test.shape)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"197DXGkEZSat","executionInfo":{"status":"ok","timestamp":1765221413124,"user_tz":-180,"elapsed":168,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"75c95f69-107f-426f-df21-902fe9e78512"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of X train: (50000, 32, 32, 3)\n","Shape of y train: (50000, 1)\n","Shape of X test: (10000, 32, 32, 3)\n","Shape of y test: (10000, 1)\n"]}]},{"cell_type":"code","source":["class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',\n","'dog', 'frog', 'horse', 'ship', 'truck']\n","plt.figure(figsize=(10,10))\n","for i in range(25):\n"," plt.subplot(5,5,i+1)\n"," plt.xticks([])\n"," plt.yticks([])\n"," plt.grid(False)\n"," plt.imshow(X_train[i])\n"," plt.xlabel(class_names[y_train[i][0]])\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":826},"id":"Ag_MNxOzYR9j","executionInfo":{"status":"ok","timestamp":1765221426490,"user_tz":-180,"elapsed":502,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"5092c1cd-e906-425a-de04-016b2de3c140"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["# Зададим параметры данных и модели\n","num_classes = 10\n","input_shape = (32, 32, 3)\n","\n","# Приведение входных данных к диапазону [0, 1]\n","X_train = X_train / 255.0\n","X_test = X_test / 255.0\n","\n","print('Shape of transformed X train:', X_train.shape)\n","print('Shape of transformed X test:', X_test.shape)\n","\n","# Переводим метки в one-hot encoding\n","y_train = keras.utils.to_categorical(y_train, num_classes)\n","y_test = keras.utils.to_categorical(y_test, num_classes)\n","print('Shape of transformed y train:', y_train.shape)\n","print('Shape of transformed y test:', y_test.shape)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ls7IIEeXaiCb","executionInfo":{"status":"ok","timestamp":1765221740419,"user_tz":-180,"elapsed":1237,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"e0ceb86c-1842-4250-ce04-01f00fec6450"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Shape of transformed X train: (50000, 32, 32, 3)\n","Shape of transformed X test: (10000, 32, 32, 3)\n","Shape of transformed y train: (50000, 10)\n","Shape of transformed y test: (10000, 10)\n"]}]},{"cell_type":"code","source":["model = Sequential()\n","\n","model.add(layers.Conv2D(32, (3,3), padding=\"same\", activation=\"relu\",\n"," input_shape=input_shape))\n","model.add(layers.BatchNormalization())\n","model.add(layers.Conv2D(32, (3,3), padding=\"same\", activation=\"relu\"))\n","model.add(layers.BatchNormalization())\n","model.add(layers.BatchNormalization())\n","model.add(layers.Dropout(0.25))\n","\n","\n","model.add(layers.Conv2D(64, (3,3), padding=\"same\", activation=\"relu\"))\n","model.add(layers.Conv2D(64, (3,3), padding=\"same\", activation=\"relu\"))\n","model.add(layers.MaxPooling2D((2,2)))\n","model.add(layers.Dropout(0.25))\n","\n","model.add(layers.Conv2D(128, (3,3), padding=\"same\", activation=\"relu\"))\n","model.add(layers.MaxPooling2D((2,2)))\n","model.add(layers.Dropout(0.25))\n","\n","model.add(layers.Flatten())\n","model.add(layers.Dense(128, activation=\"relu\"))\n","model.add(layers.Dropout(0.5))\n","model.add(layers.Dense(num_classes, activation=\"softmax\"))\n","model.summary()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":821},"id":"-qgb6EuIam8s","executionInfo":{"status":"ok","timestamp":1765229977847,"user_tz":-180,"elapsed":314,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"7ce7acff-3d67-4d23-8dc1-d5d49f8332a3"},"execution_count":128,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n"," super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"]},{"output_type":"display_data","data":{"text/plain":["\u001b[1mModel: \"sequential_15\"\u001b[0m\n"],"text/html":["
Model: \"sequential_15\"\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┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d_52 (\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;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_29 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m128\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_53 (\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;34m32\u001b[0m) │ \u001b[38;5;34m9,248\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_30 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m128\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_31 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m128\u001b[0m │\n","│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_37 (\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;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_54 (\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;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_55 (\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;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_34 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_38 (\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;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_56 (\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;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_35 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\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 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_39 (\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;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten_15 (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8192\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_27 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m1,048,704\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_40 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_28 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,290\u001b[0m │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n"],"text/html":["
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n","┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n","┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n","│ conv2d_52 (Conv2D)              │ (None, 32, 32, 32)     │           896 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_29          │ (None, 32, 32, 32)     │           128 │\n","│ (BatchNormalization)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_53 (Conv2D)              │ (None, 32, 32, 32)     │         9,248 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_30          │ (None, 32, 32, 32)     │           128 │\n","│ (BatchNormalization)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ batch_normalization_31          │ (None, 32, 32, 32)     │           128 │\n","│ (BatchNormalization)            │                        │               │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_37 (Dropout)            │ (None, 32, 32, 32)     │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_54 (Conv2D)              │ (None, 32, 32, 64)     │        18,496 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_55 (Conv2D)              │ (None, 32, 32, 64)     │        36,928 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_34 (MaxPooling2D) │ (None, 16, 16, 64)     │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_38 (Dropout)            │ (None, 16, 16, 64)     │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ conv2d_56 (Conv2D)              │ (None, 16, 16, 128)    │        73,856 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ max_pooling2d_35 (MaxPooling2D) │ (None, 8, 8, 128)      │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_39 (Dropout)            │ (None, 8, 8, 128)      │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ flatten_15 (Flatten)            │ (None, 8192)           │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_27 (Dense)                │ (None, 128)            │     1,048,704 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dropout_40 (Dropout)            │ (None, 128)            │             0 │\n","├─────────────────────────────────┼────────────────────────┼───────────────┤\n","│ dense_28 (Dense)                │ (None, 10)             │         1,290 │\n","└─────────────────────────────────┴────────────────────────┴───────────────┘\n","
\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Total params: \u001b[0m\u001b[38;5;34m1,189,802\u001b[0m (4.54 MB)\n"],"text/html":["
 Total params: 1,189,802 (4.54 MB)\n","
\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,189,610\u001b[0m (4.54 MB)\n"],"text/html":["
 Trainable params: 1,189,610 (4.54 MB)\n","
\n"]},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m192\u001b[0m (768.00 B)\n"],"text/html":["
 Non-trainable params: 192 (768.00 B)\n","
\n"]},"metadata":{}}]},{"cell_type":"code","source":["# компилируем и обучаем модель\n","model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n","model.fit(X_train, y_train, batch_size=64, validation_split=0.1, epochs=50)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"v6einaknayfG","executionInfo":{"status":"ok","timestamp":1765230506617,"user_tz":-180,"elapsed":525401,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"b5266b42-dc60-43ca-f817-0aea002c110c"},"execution_count":129,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m26s\u001b[0m 25ms/step - accuracy: 0.2890 - loss: 1.9436 - val_accuracy: 0.5242 - val_loss: 1.3238\n","Epoch 2/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.5058 - loss: 1.3752 - val_accuracy: 0.5944 - val_loss: 1.1384\n","Epoch 3/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.5717 - loss: 1.1952 - val_accuracy: 0.6540 - val_loss: 1.0330\n","Epoch 4/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.6078 - loss: 1.1018 - val_accuracy: 0.6750 - val_loss: 0.9730\n","Epoch 5/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.6435 - loss: 1.0084 - val_accuracy: 0.6826 - val_loss: 0.9025\n","Epoch 6/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 15ms/step - accuracy: 0.6635 - loss: 0.9596 - val_accuracy: 0.6910 - val_loss: 0.9187\n","Epoch 7/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m19s\u001b[0m 14ms/step - accuracy: 0.6766 - loss: 0.9151 - val_accuracy: 0.6944 - val_loss: 0.8935\n","Epoch 8/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.6900 - loss: 0.8780 - val_accuracy: 0.7118 - val_loss: 0.8351\n","Epoch 9/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7026 - loss: 0.8393 - val_accuracy: 0.7242 - val_loss: 0.8037\n","Epoch 10/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7103 - loss: 0.8130 - val_accuracy: 0.7256 - val_loss: 0.8080\n","Epoch 11/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 15ms/step - accuracy: 0.7247 - loss: 0.7776 - val_accuracy: 0.7216 - val_loss: 0.8186\n","Epoch 12/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7316 - loss: 0.7570 - val_accuracy: 0.7464 - val_loss: 0.7636\n","Epoch 13/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7411 - loss: 0.7408 - val_accuracy: 0.7188 - val_loss: 0.7994\n","Epoch 14/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7461 - loss: 0.7251 - val_accuracy: 0.7462 - val_loss: 0.7230\n","Epoch 15/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7513 - loss: 0.6972 - val_accuracy: 0.7402 - val_loss: 0.7612\n","Epoch 16/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 15ms/step - accuracy: 0.7535 - loss: 0.6857 - val_accuracy: 0.7336 - val_loss: 0.7845\n","Epoch 17/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7570 - loss: 0.6822 - val_accuracy: 0.7594 - val_loss: 0.7080\n","Epoch 18/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7681 - loss: 0.6493 - val_accuracy: 0.7562 - val_loss: 0.7110\n","Epoch 19/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7655 - loss: 0.6519 - val_accuracy: 0.7472 - val_loss: 0.7445\n","Epoch 20/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7692 - loss: 0.6357 - val_accuracy: 0.7504 - val_loss: 0.7394\n","Epoch 21/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7796 - loss: 0.6127 - val_accuracy: 0.7504 - val_loss: 0.7497\n","Epoch 22/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7817 - loss: 0.6067 - val_accuracy: 0.7588 - val_loss: 0.7231\n","Epoch 23/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7868 - loss: 0.5887 - val_accuracy: 0.7700 - val_loss: 0.6992\n","Epoch 24/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7915 - loss: 0.5789 - val_accuracy: 0.7782 - val_loss: 0.6825\n","Epoch 25/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.7990 - loss: 0.5668 - val_accuracy: 0.7674 - val_loss: 0.6921\n","Epoch 26/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 15ms/step - accuracy: 0.8018 - loss: 0.5562 - val_accuracy: 0.7748 - val_loss: 0.6816\n","Epoch 27/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8088 - loss: 0.5431 - val_accuracy: 0.7844 - val_loss: 0.6551\n","Epoch 28/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8062 - loss: 0.5438 - val_accuracy: 0.7852 - val_loss: 0.6404\n","Epoch 29/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8089 - loss: 0.5272 - val_accuracy: 0.7744 - val_loss: 0.6705\n","Epoch 30/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8136 - loss: 0.5237 - val_accuracy: 0.7806 - val_loss: 0.6414\n","Epoch 31/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8122 - loss: 0.5183 - val_accuracy: 0.7850 - val_loss: 0.6457\n","Epoch 32/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8202 - loss: 0.5026 - val_accuracy: 0.7744 - val_loss: 0.6928\n","Epoch 33/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8216 - loss: 0.5051 - val_accuracy: 0.7848 - val_loss: 0.6481\n","Epoch 34/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8181 - loss: 0.4995 - val_accuracy: 0.7850 - val_loss: 0.6710\n","Epoch 35/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8242 - loss: 0.4876 - val_accuracy: 0.7900 - val_loss: 0.6416\n","Epoch 36/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8259 - loss: 0.4865 - val_accuracy: 0.7820 - val_loss: 0.6664\n","Epoch 37/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8318 - loss: 0.4723 - val_accuracy: 0.7928 - val_loss: 0.6512\n","Epoch 38/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8304 - loss: 0.4738 - val_accuracy: 0.7980 - val_loss: 0.6287\n","Epoch 39/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8389 - loss: 0.4546 - val_accuracy: 0.7838 - val_loss: 0.6557\n","Epoch 40/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8379 - loss: 0.4542 - val_accuracy: 0.7850 - val_loss: 0.6656\n","Epoch 41/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8414 - loss: 0.4457 - val_accuracy: 0.7942 - val_loss: 0.6333\n","Epoch 42/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8418 - loss: 0.4431 - val_accuracy: 0.7948 - val_loss: 0.6201\n","Epoch 43/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8425 - loss: 0.4342 - val_accuracy: 0.7912 - val_loss: 0.6254\n","Epoch 44/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8442 - loss: 0.4375 - val_accuracy: 0.7920 - val_loss: 0.6304\n","Epoch 45/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8476 - loss: 0.4289 - val_accuracy: 0.8010 - val_loss: 0.6174\n","Epoch 46/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8486 - loss: 0.4237 - val_accuracy: 0.8012 - val_loss: 0.6151\n","Epoch 47/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8526 - loss: 0.4200 - val_accuracy: 0.7984 - val_loss: 0.6139\n","Epoch 48/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8552 - loss: 0.4111 - val_accuracy: 0.8024 - val_loss: 0.6180\n","Epoch 49/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8540 - loss: 0.4089 - val_accuracy: 0.7944 - val_loss: 0.6362\n","Epoch 50/50\n","\u001b[1m704/704\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 14ms/step - accuracy: 0.8590 - loss: 0.3945 - val_accuracy: 0.8000 - val_loss: 0.6588\n"]},{"output_type":"execute_result","data":{"text/plain":[""]},"metadata":{},"execution_count":129}]},{"cell_type":"code","source":["# Оценка качества работы модели на тестовых данных\n","scores = model.evaluate(X_test, y_test)\n","print('Loss on test data:', scores[0])\n","print('Accuracy on test data:', scores[1])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"XL62otWabTfq","executionInfo":{"status":"ok","timestamp":1765230511180,"user_tz":-180,"elapsed":2811,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"e3b1a2a6-26be-4d9e-e5fc-3a9d835fb807"},"execution_count":130,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 5ms/step - accuracy: 0.7982 - loss: 0.6423\n","Loss on test data: 0.6325967311859131\n","Accuracy on test data: 0.8019000291824341\n"]}]},{"cell_type":"code","source":["# вывод двух тестовых изображений и результатов распознавания\n","for n in [7, 16]:\n"," result = model.predict(X_test[n:n+1])\n"," plt.imshow(X_test[n].reshape(32,32,3), cmap=plt.get_cmap('gray'))\n"," plt.show()\n"," print('Real mark: ', np.argmax(y_test[n]))\n"," print('NN answer: ', np.argmax(result))\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":988},"id":"zrybayjjofQL","executionInfo":{"status":"ok","timestamp":1765230515580,"user_tz":-180,"elapsed":1022,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"2e56a490-8844-4b3e-e3f9-6b0a1cac7b16"},"execution_count":131,"outputs":[{"output_type":"stream","name":"stderr","text":["WARNING:tensorflow:6 out of the last 25 calls to .one_step_on_data_distributed at 0x7c45cc4d1b20> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n"]},{"output_type":"stream","name":"stdout","text":["\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 694ms/step\n"]},{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"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\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark: 4\n","NN answer: 0\n","\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 47ms/step\n"]},{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"iVBORw0KGgoAAAANSUhEUgAAAaAAAAGdCAYAAABU0qcqAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAL4NJREFUeJzt3Wts3OWZ9/HfnMfHcRzHJ+KEJEAoh6TaFFKLlqUkS5KVEJRoBW2lDV0EgnVQIdttm1ULhd2VWSq1tFUaXixLtlIDLasGBNrCQmiMuk3YTZYopQc/JE9KQuNDTvbYY8/5/7xg4z6GBO4rsXPb5vuRRortK5fv/2HmmvHM/CYUBEEgAADOs7DvBQAAPpoYQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAAL6K+F/Be5XJZR44cUU1NjUKhkO/lAACMgiDQ0NCQWltbFQ6f+XHOlBtAR44cUVtbm+9lAADO0eHDhzV37twz/nzSBtCmTZv0rW99S729vVq6dKm+//3v6+qrr/7Q/1dTUyNJ+tL965VIJJx+lyVNKBIxbrKhdyLptt5Tkob64UzG1DtkCFiqq0uZesdiMVN9RUWVe3E4YuqdLxada8vFgql3xLCWcNj2aD0ate3DD7oX+V6FvPs+kaRSuexcW1FRYepdLpeca4tF91pJcl+1FI3arveBYZ9IUrHkvs9z2VFT70Q87lxbKtn2YS6Xc64tG3pns1k9+MBDY7fnZzIpA+jHP/6xNmzYoMcff1zLly/XY489plWrVqm7u1uNjY0f+H9P/dktkUhMygAyn4iG3slk0tTbMoAsJ7hkG0AVFbZ1x2LuVwhJqqg03GgZB1CkYBlAtmM/mQPIug8tAygfsQ1aywCqrKw09bYMoILhzoQklQ3nuPVOU9k6gAx3boynyqQOIMt5VTLeBkn60KdRJuVFCN/+9rd155136otf/KIuu+wyPf7446qsrNS//Mu/TMavAwBMQxM+gPL5vPbs2aOVK1f+8ZeEw1q5cqV27tz5vvpcLqd0Oj3uAgCY+SZ8AB07dkylUklNTU3jvt/U1KTe3t731Xd2diqVSo1deAECAHw0eH8f0MaNGzU4ODh2OXz4sO8lAQDOgwl/EUJDQ4MikYj6+vrGfb+vr0/Nzc3vq7e82AAAMHNM+COgeDyuZcuWafv27WPfK5fL2r59u9rb2yf61wEApqlJeRn2hg0btG7dOn3iE5/Q1Vdfrccee0yZTEZf/OIXJ+PXAQCmoUkZQLfeequOHj2qBx54QL29vfr4xz+uF1988X0vTAAAfHRNWhLC+vXrtX79+rP+/1VVVc5v7DS9aczwxlJJChuSE8Ix2+60vPEulxk29c6PutdXJWxv/ozVzjLVl0rub9IrFvKm3qNZ93dyF/LutZJUZXnXv/HNhcWibTstuYhZw7vbJSkScT/+kZzt+jOZeY6WN2eHI7Z1WxWL7vvc8uZ2SSqX3G/fisY381reiBqJTPwbYr2/Cg4A8NHEAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHgxaVE855MlSsQagxGJuu+iyupaU+9M+qRzbUi2dQ8NuveucIw8OiVRUWWqHx0dda4Nx9zjPiRJhqiXSNgWC5PLu6/bGoFize6Jx2OTtpZi0X0tpZIt5idk2c6wLRLKkFBjioM6G8WiW/SMJEVCtu0sB+4bao0+KhTc94vltrOQdzsHeQQEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8GLKZsElkxWqqHDLKCuXDaFQRlU17vlusYpKU++Q3NddmbRlpMVj7nlTR48eNfWOxPtM9XX1s51rK425dGFDVl+pZMtIs9XbMtKs56wl7zASmbz7lTFjVl806r7uUtmWd6iQ+7G35uNZM9VmzTLcTkTcc/0kyXAzocxIxtbboFQy5N05HnceAQEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvJiyUTzFYkGFglucgyWmJJFI2BYSuMeDJJMVptbFQsG9OGaL77jo8mbn2uC3b5p6D56wRfc0N7c419bUVJl6W+JbymVbjEw47H5eDYeGTb0D2WJnEnHD2kO23oVC3rk2HLbdZ41G3c/bqCFaR5IpiicWdY+RkWQ8OlJNdcq5Nm68Lhfy7scnl8+aekej7tc3SxSP63nCIyAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAF1M2Cy4ajSnmmJlkyadKpepM66iurXGuDcK2jKdQKORcOzIyauqdrJ3tXHvBvIWm3sd6/2CqHxnJONc2GnLjJClfcM+nChmy3SQpEna/ejTMsWXYRaxribif47nciKl3NueeHxaN2G4ywoacRuv94Xyh7FwbMeavpVLu2W6SVDDkOmaGbccnKBsy2IzHJ2bI6otE3Y9PJOp23HkEBADwYsIH0De/+U2FQqFxl0svvXSifw0AYJqblD/BXX755XrllVf++EuiU/YvfQAATyZlMkSjUTU3u38eDQDgo2dSngN666231NraqoULF+oLX/iCDh06dMbaXC6ndDo97gIAmPkmfAAtX75cW7Zs0YsvvqjNmzfr4MGD+vSnP62hoaHT1nd2diqVSo1d2traJnpJAIApaMIH0Jo1a/QXf/EXWrJkiVatWqV///d/18DAgH7yk5+ctn7jxo0aHBwcuxw+fHiilwQAmIIm/dUBdXV1uuSSS7R///7T/jyRSCiRSEz2MgAAU8ykvw9oeHhYBw4cUEuL7Q2GAICZbcIH0Je//GV1dXXp97//vX75y1/qs5/9rCKRiD73uc9N9K8CAExjE/4nuHfeeUef+9zndPz4cc2ZM0ef+tSntGvXLs2ZM8fUp23ehaqsrHSqLRmiKgp598gMSYrGks61YeP7nQo593idZMx2XyGXde8dS1SYejc02F5if7y/z7n2grb5pt7RqlnOtflC0dQ7bIgeicbdzxNJKhXdz1lJmj27wbm2rtYWC3Skp8e5Nj14+hcTnUnRsJ3Fku34lMuGekPslSTlCzlTfS7rHmeUy9pug04ODDjXzmm03c7GK9yv+xFD5FnR8dBM+AB6+umnJ7olAGAGIgsOAOAFAwgA4AUDCADgBQMIAOAFAwgA4AUDCADgBQMIAOAFAwgA4AUDCADgBQMIAODFpH8cw9nq6e1VhWNOkeXjHEZH3TPSJOnoiePOtQsWLTL1Hjx5wrm2Imn7yIp40j2brBSNm3rPnmPLgvvD26f/KI7TCRszu2bV1zvX9h87ZupdDgLn2uFhW0Za0pgd19jknvGVMmbB/f7tt51rR4zXn3zeku9WNvWurHTfh9FozNQ7n7NlwSUS7mupqKg29nbPa6usdsvPPCWXd9/OuOF2NhJzGy08AgIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeDFlo3jC0XcvLhJJ95iNikpbpE3WEMlx5J3Dpt7pE+7RMKOGGAxJajREg8Titt4NTa2m+v6eQ8616cGTpt6JGvc4o8xQ2tY77n5ehWwpMoq7p6tIkqIqOdeeNJxXkjQ46B43FQlHTL0rDNfNZNK2U0KGu8/xmC1uyhLvJUmxmPt2jgyPmHoHcfeb6aDkfp5YFYrusUqutTwCAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHgxZbPgZs2epcrKSqfaoBw49y0as5JihjywnnfeMfU+3n/EuTaZsGVZNTY1OdcmkjWm3uG4bS2WjK+eP9j2YTFkyBqrrjX1DgzZV+HA/RyUpNywLZfu4P/5rXNtOWRqrWjIfe3xuC0LrmzIyAuV3fe3JEVdwyIlFXNZU++gWDDVD+XzzrXGw2PKaqxO2a7Lw1n3rMu+/j7n2tERt7w7HgEBALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvJiyWXCRaEKRqFsGUqHgnttUWeWWL3fKcNo9s6tUcM+DkiQZsq96jxw1tc5+LONcW1PXaOpdLtgyu0ol9/pRY2ZXc9Q9C25WXZ2pdynnnpM1Mjhg6j1w0nY808d6nWvDMVteWyjsXh9KuOf6SVIk4n58ikVbTmMoZultO2f7Tp4w1Z88cdK5Nmo4ZyWpJlXnXHtx9eWm3uGQezLd0JD7bUp2dNTt9zt3BABgApkH0GuvvaYbb7xRra2tCoVCevbZZ8f9PAgCPfDAA2ppaVFFRYVWrlypt956a6LWCwCYIcwDKJPJaOnSpdq0adNpf/7oo4/qe9/7nh5//HG9/vrrqqqq0qpVq5TN2v60AgCY2czPAa1Zs0Zr1qw57c+CINBjjz2mr3/967rpppskST/84Q/V1NSkZ599Vrfddtu5rRYAMGNM6HNABw8eVG9vr1auXDn2vVQqpeXLl2vnzp2n/T+5XE7pdHrcBQAw803oAOrtffeVOk3v+TTOpqamsZ+9V2dnp1Kp1Nilra1tIpcEAJiivL8KbuPGjRocHBy7HD582PeSAADnwYQOoObmZklSX9/4zw7v6+sb+9l7JRIJ1dbWjrsAAGa+CR1ACxYsUHNzs7Zv3z72vXQ6rddff13t7e0T+asAANOc+VVww8PD2r9//9jXBw8e1N69e1VfX6958+bpvvvu0z/8wz/o4osv1oIFC/SNb3xDra2tuvnmmydy3QCAac48gHbv3q3PfOYzY19v2LBBkrRu3Tpt2bJFX/nKV5TJZHTXXXdpYGBAn/rUp/Tiiy8qmUyafk82V1I44hbNYYn7yBcC0zpCYffeYZVNvWsq3GNN4mH3yAxJ+r9vdTvXVlXPMvVW2baduaxbLIckLbpksal3qr7BuTYSsZ3usYT7uXJyZNjU+2jPEVO9Su5xUzWpGlPrWNxw3Uy4xxNJUtzQ++jRflPvrOG8ihlieyTpxAlbFM/Q0JBzbSmwXZdTDe5RWR//xCdMveMh9+vE7Ab369rIyIhTnXkAXXfddQqCM18xQ6GQHn74YT388MPW1gCAjxDvr4IDAHw0MYAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABemKN4zpeqylpVVlU51eayWee+sagtE6rO8PEQ77wVMfU+OeyeH9Uwu97Uu+/EgHPtzl/+wtQ7aouyUkXc/TSrqa0z9Y7E3LPG8jlbjlm46F5v7Z1JD5rq86PuWXPlYt7UOxw23AwYc8xqalLOtf29fzD17uvvca6tq6sz9c4ablMkfWA82XslqowfOVMuOpdachclqXneAufaUNT9PMkMu52vPAICAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHgxZaN4aqoqVVVV6VSbM0REJJMJ0zpCco/BaG6bZ+o9MpJ2rp27cKGp9wWX1DjXHn77sKn3oQPdpvq6Cy90rs1mbJE25fJJ59pwyP1YSlIy5h7bVFNTZ+oditnOw5zhXBketcbIGLOVDJLV1c61kYQtJisSc7/eD2Xco4wkKRSy7ZN8vuDeOzpi6h3Jup8rhw8etPWOx51rj/T3OteOjLhtI4+AAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF5M2Sy4fG5UsajbfCwbIr7CxtircNh9Rs+dN9/U+/f/1z1Trae/39R7/sIm59pZs+pMvfvjttMmKJecaxOxiKm3iobsuJD7OiQpiLgf+6rKKlPvulmzTPXlsvt2lou2zLuEIYMtFnPPDpOkiOFUqal1zy+UpHDkAufa48ePm3pHDfmSkpSsDNx7GzIGJSlkuA2KJ2wZg5mRjHPtwIB77uLo6KhTHY+AAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeMIAAAF4wgAAAXjCAAABeTNkonnR6SMWiW3RKdVWtc9983hDdIilkiG8ZSg+Yep88ecK59vcHD5p6F0vuhzY/MmLqPZoZNNXns4bjk3WPBpGkSNhwCofd41IkKWqI4smN2s6r4SHbPiwVC861aUNkiiQF5bJzbcwYIzOacY/XiSeTpt7ZrPs+z+VsxycSsUVCVVRWOtcW3Xe3JCnneDsoSemMWwTOKeXBYefaiir3YxmE3PYfj4AAAF4wgAAAXpgH0GuvvaYbb7xRra2tCoVCevbZZ8f9/Pbbb1coFBp3Wb169UStFwAwQ5gHUCaT0dKlS7Vp06Yz1qxevVo9PT1jl6eeeuqcFgkAmHnML0JYs2aN1qxZ84E1iURCzc3NZ70oAMDMNynPAe3YsUONjY1avHix7rnnng/8MKhcLqd0Oj3uAgCY+SZ8AK1evVo//OEPtX37dv3TP/2Turq6tGbNGpVKp38pYWdnp1Kp1Nilra1topcEAJiCJvx9QLfddtvYv6+88kotWbJEixYt0o4dO7RixYr31W/cuFEbNmwY+zqdTjOEAOAjYNJfhr1w4UI1NDRo//79p/15IpFQbW3tuAsAYOab9AH0zjvv6Pjx42ppaZnsXwUAmEbMf4IbHh4e92jm4MGD2rt3r+rr61VfX6+HHnpIa9euVXNzsw4cOKCvfOUruuiii7Rq1aoJXTgAYHozD6Ddu3frM5/5zNjXp56/WbdunTZv3qx9+/bpX//1XzUwMKDW1lbdcMMN+vu//3slEgnT7ymW8s55ZuVy0b2vNYhJ7hlcuawth2k0l3WuLZbc1yFJ5YL7Wg6/ffo/j55JULTlalVWuWd89ff3mHrHonHn2njCvVaSyqUq51pr/lpf7zvGtbif46MZ93wvSRoddc8CjEZtWXC5nPt5WFFZbeqdL7jvk2zW/bomSUFgyw20KIVsN7ulkPt5my+458ZJUjxR4V4bda8NOWY0mgfQdddd94EH56WXXrK2BAB8BJEFBwDwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwYsI/D2iiJBJhJRJu87FUds8my43YcswUuGewBYF7NpUkNTY1OteejNjuK/T+4ZBzbXZkyNS7rr7OVB+JuZ9m1giunCEjLzdkO/ZHDbl0w0O2LLih9ICp3qIi6Z69J0mWXR6YqqV80XCdMOa1JRLu25k07pPhYVueXjbrfm7V1s829a5vmOVcO2tWytQ7HHKvLVuunI61PAICAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHgxZaN4srkhhSJuMR7RcNy5b6nsHt0iSUE571xbzNl6V9fUONf29Rwx9c4PDrqvo7rC1DuWtNUfH0wb1lJr6m1IElFhdNTUe+DEMefawZP9pt7hsC3SJhyOOdda9ve7vd3vh5bLZVPvkiH6KhE3Xn8q3WN+Zs2qN/Uul0qm+sG0+/Utkrbd7M6a1eBcW8zb4ozeOeweIVUyxDCNOl7XeAQEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8GLKZsEFQV5BEHGqLQXuGUUVVe65cZJUMOS7DQ/assZiMfd8L0telyTls+6ZUC0XzDX1br5wgam+tjblXBuN2o5PqeieTRbO2XKy4lH3rLHhoaOm3hUVVab6aCTpXBtO2nrPaWx0X0fU/ZyVpAMHDjjXxiK2c7yy2n07qwy5i5JUUWXbh6GI+01p2LidJ465n1tv/fbXpt6pOXOcayvr3HMaS0W3beQREADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADACwYQAMALBhAAwAsGEADAiykbxZPJjqoccovYKYfc++YcIyJOiYbdY35ilbbes5Lu8SBtF8wz9R6pa3CuXXTxJabeobjttIlXuse3lAPDwZQUL7lH9yTckp3+WJ90793YZjs+s2bNNtUPnhx0rq0suEcISdLCixY619Y3Npt6t17o3tv9mvauZIX78SkWSqbe5ZJtNXUXuMdTnTh+zNS75+3fO9f+4e39pt7pQfe1tC5w38asYxQYj4AAAF6YBlBnZ6euuuoq1dTUqLGxUTfffLO6u7vH1WSzWXV0dGj27Nmqrq7W2rVr1dfXN6GLBgBMf6YB1NXVpY6ODu3atUsvv/yyCoWCbrjhBmUymbGa+++/X88//7yeeeYZdXV16ciRI7rlllsmfOEAgOnN9Mf8F198cdzXW7ZsUWNjo/bs2aNrr71Wg4ODeuKJJ7R161Zdf/31kqQnn3xSH/vYx7Rr1y598pOfnLiVAwCmtXN6Dmhw8N0nRuvr6yVJe/bsUaFQ0MqVK8dqLr30Us2bN087d+48bY9cLqd0Oj3uAgCY+c56AJXLZd1333265pprdMUVV0iSent7FY/HVVdXN662qalJvb29p+3T2dmpVCo1dmlrazvbJQEAppGzHkAdHR1688039fTTT5/TAjZu3KjBwcGxy+HDh8+pHwBgejir9wGtX79eL7zwgl577TXNnfvHj3Nubm5WPp/XwMDAuEdBfX19am4+/fsHEomEEonE2SwDADCNmR4BBUGg9evXa9u2bXr11Ve14D1vTFq2bJlisZi2b98+9r3u7m4dOnRI7e3tE7NiAMCMYHoE1NHRoa1bt+q5555TTU3N2PM6qVRKFRUVSqVSuuOOO7RhwwbV19ertrZW9957r9rb23kFHABgHNMA2rx5syTpuuuuG/f9J598Urfffrsk6Tvf+Y7C4bDWrl2rXC6nVatW6Qc/+MGELBYAMHOYBlAQfHg+UjKZ1KZNm7Rp06azXpQkZUeGpcAt06ok9/yw/EjZtI5kwn0XZUbd8o/Geofcs6yam+eYekfjSefaIGR7LUquYNvO0eFh59pI2H2fSFJ1rNq5tucMr8Q8k+GRvHPt3AUXm3pXVFWZ6mMV7vW/e3OvqffJ9Ann2prZ9abeNfUp51rbNVMKDOlxYePTzNGY7T80JNyvb/WNtuvywPF+59p0f4+pd6ngfvs2lHbPjcvl3K47ZMEBALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALxgAAEAvGAAAQC8YAABALw4q49jOB9ikZDiEbeInSAUc+4bFEumdRRz7vX5nC2iRqGCc2ll0n0bJSkSc++dN+6TQG4RSadkMiPOtfGoe6SJJGWODzrXnjjqHmkiSS1zW5xrk7XukUCSVCzbgmcqat2jeAqOEVanHB846lxbn2sy9VbY/byNxm0xTPG4e1xOoWDbJwrZjk+x5B7blKy0xfzMv3Duhxf9rwMjx029o4alhKLutykqutXyCAgA4AUDCADgBQMIAOAFAwgA4AUDCADgBQMIAOAFAwgA4AUDCADgBQMIAOAFAwgA4AUDCADgxZTNgiuXSiqX3PKbIjH3DKlyYFtHYPgPCWNeW5Vh3VFba5XKo861IcfMvbHeBffcK0kqOeZCSVKxbLtPdPKYe/ZVNGHbzoqUe1DWaHHI1DsI207ESMS9Pllly9PLG3LMwhFTa4UN+9zaO2TYJ+W8LQuuWDLknkkqy/26bM2jTFRY8vRs57jChv0SNqzbsZZHQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAAL6ZsFE+pWFLRMbKiFLjHZiRjtkybaNR9FxWy7vE3khTIPdoin8+aeoei7rkmhcAWU5LL5Uz10Yh7TIkKxogauUeP1NXXmnrnSyPutWXbPgxFyqb6aMw9XicRd48Qepf7/dCw8S5r2JAMUyjYzvGiIeIpX7BF64SNuUDD6WHn2kx60NQ73XfEubZYtm1ncdT9vA2PuN++5XJu8U48AgIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4MWWz4PLlQOGyWy7Y6GjauW9NpXumliQFo+65ZyeGjpp6J+SeN1URrzD1TlbVONfmS7Zst2JgyzGrqHBfS9mYBTc7Ve9c2zb3AlPvrNz3y8mRk7be+YypvjTqXl8Rs50rxZL7Pg+Mx2d4xP26mR4ZMvWOJt1zHUMhW7ZbyHjffGDAfTtLRdv17djJfufagjGnMRRx34fhEffcuHzOLeeSR0AAAC9MA6izs1NXXXWVampq1NjYqJtvvlnd3d3jaq677jqFQqFxl7vvvntCFw0AmP5MA6irq0sdHR3atWuXXn75ZRUKBd1www3KZMb/eeDOO+9UT0/P2OXRRx+d0EUDAKY/03NAL7744rivt2zZosbGRu3Zs0fXXnvt2PcrKyvV3Nw8MSsEAMxI5/Qc0ODgux+sVF8//ongH/3oR2poaNAVV1yhjRs3amTkzB/slcvllE6nx10AADPfWb8Krlwu67777tM111yjK664Yuz7n//85zV//ny1trZq3759+upXv6ru7m799Kc/PW2fzs5OPfTQQ2e7DADANHXWA6ijo0NvvvmmfvGLX4z7/l133TX27yuvvFItLS1asWKFDhw4oEWLFr2vz8aNG7Vhw4axr9PptNra2s52WQCAaeKsBtD69ev1wgsv6LXXXtPcuXM/sHb58uWSpP379592ACUSCSUS1s+wBwBMd6YBFASB7r33Xm3btk07duzQggULPvT/7N27V5LU0tJyVgsEAMxMpgHU0dGhrVu36rnnnlNNTY16e3slSalUShUVFTpw4IC2bt2qP//zP9fs2bO1b98+3X///br22mu1ZMmSSdkAAMD0ZBpAmzdvlvTum03/f08++aRuv/12xeNxvfLKK3rssceUyWTU1tamtWvX6utf//qELRgAMDOY/wT3Qdra2tTV1XVOCzolMzKqYtktc2w0755/lM+f+SXhpxMK3HsPG7OsQvEq59pk1L1Wkgo598yuUMz2VGAybnv1fiLi/hxfTgVT76pK99yzSMiWAxgJ3PPDysVhU+9Q2baWaCjkXFtbZcvqGxp2X3vakHkmSSO5UffeWds+TNS4H/tY1D3zTJKCsvv+lqR43L1/ssZ27I8fNpyHhmw3Saqume1cWzu71bk2l3W73SQLDgDgBQMIAOAFAwgA4AUDCADgBQMIAOAFAwgA4AUDCADgBQMIAOAFAwgA4AUDCADgxVl/HtBkK5dKKpdKTrX5nHt8SySwRVUkYu5xH/W1to+VqK2odq+tTpl6B2H3Q5st2SJQYhHb/ZZKQzxIvNI9dkSSwlH3tQyMnDT1LpbzzrW54UFT71DUdtULDPuwKPd1S1I06b4PS4HbdfKUWCzuXJuqmGPqHU26R9rEjPe1g6ItzihR4b6WiNxjsiSpOln/4UX/Kxxzj9aRpGii0rk2lZrlXJuNZ53qeAQEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8IIBBADwggEEAPCCAQQA8GLKZsElkjElk275V0VDblOqota0jnjUPZsslgzZekfce4dDtvsK8aR7Ll0sZFt3ueievfduf/ftjCRsp2ReRefacsiW71UquWeqxeO24xMO2zLv8nn37UxUuOcXSlJVzP1cqTZmEhZL7rlnsaoqU++y5f5zwX3/SVI5YjtXQobrcnbYlr1YXemewZaI2rIu0yMjzrVDafe8w2w251THIyAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBcMIACAFwwgAIAXDCAAgBdTNoonGYsrGY+7FVe6x2BUJ6pN6wgbokQiUfdaSUoZokdqa20RQvmSIbqlytY7KJdM9dHAPeolFDZG8QTuawkCW7zKiePuvZOVSVPvGuM+Dwfu+yUWcbze/K+IIb4lnrRtZ8lw/QnHbTEyRUO8TiHrHqskSaP5rKk+MER2pYzHfnQw41wbi9geU5TD7sdnaHTIubaQd9vfPAICAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeMEAAgB4wQACAHjBAAIAeDFls+BKpYJKRbf5mDRkSJWLBdM6ciPu9UHB1jsZds+POpmzZVllS+719UG9qbcxUk2lwD1Xq372HFPviCFr7MSxAVNvSy5d0piRFg3Zcs8q4+65gYHczytJKpbdD2g4bFt3LOa+lrzxummJXrT2HhkettUbrm8R6/3+qHt9SbYrZ7LKPadxcOiYc225SBYcAGAKMw2gzZs3a8mSJaqtrVVtba3a29v1s5/9bOzn2WxWHR0dmj17tqqrq7V27Vr19fVN+KIBANOfaQDNnTtXjzzyiPbs2aPdu3fr+uuv10033aRf//rXkqT7779fzz//vJ555hl1dXXpyJEjuuWWWyZl4QCA6c30HNCNN9447ut//Md/1ObNm7Vr1y7NnTtXTzzxhLZu3arrr79ekvTkk0/qYx/7mHbt2qVPfvKTE7dqAMC0d9bPAZVKJT399NPKZDJqb2/Xnj17VCgUtHLlyrGaSy+9VPPmzdPOnTvP2CeXyymdTo+7AABmPvMA+tWvfqXq6molEgndfffd2rZtmy677DL19vYqHo+rrq5uXH1TU5N6e3vP2K+zs1OpVGrs0tbWZt4IAMD0Yx5Aixcv1t69e/X666/rnnvu0bp16/Sb3/zmrBewceNGDQ4Ojl0OHz581r0AANOH+X1A8XhcF110kSRp2bJl+u///m9997vf1a233qp8Pq+BgYFxj4L6+vrU3Nx8xn6JREKJhPtr0QEAM8M5vw+oXC4rl8tp2bJlisVi2r59+9jPuru7dejQIbW3t5/rrwEAzDCmR0AbN27UmjVrNG/ePA0NDWnr1q3asWOHXnrpJaVSKd1xxx3asGGD6uvrVVtbq3vvvVft7e28Ag4A8D6mAdTf36+//Mu/VE9Pj1KplJYsWaKXXnpJf/ZnfyZJ+s53vqNwOKy1a9cql8tp1apV+sEPfnBWCyvmc3JM4lEx4h6DETI+5osk4861gSHSRJJGh0edawcHjpt6z2lxj7Spq6419e7vt62lss49RiZZZYu0GTk+6Fwbi9j+1HtBi/sLYoKw7dgHo0VTfU28xrl2cDRj6q2Qe+mosXc84R7dUzDG5YTLhiyesq13+qR77IwkncwMOdcWLeuWlDBEjZUKtsiuqNzXEjKs27XWNICeeOKJD/x5MpnUpk2btGnTJktbAMBHEFlwAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAAL8xp2JMtCN6NcMhlDZESEUOWSNi2yWFDvE5QtsWrqFxyLs3mbBEbo6NZ59pMZsTUe2TEvbckKe5+PycxbF2Le5xRdiRn6m3ZL5MdxRMuuO/DzKhtH5YMcSzWu6yF4tSI4skbrg+S7fojSdms+7lVMkbxWCK+JjOKJ2e4DTpVe+r2/ExCwYdVnGfvvPMOH0oHADPA4cOHNXfu3DP+fMoNoHK5rCNHjqimpkah0B8f2aTTabW1tenw4cOqrbWFZ04nbOfM8VHYRontnGkmYjuDINDQ0JBaW1sVDp/5YfOU+xNcOBz+wIlZW1s7ow/+KWznzPFR2EaJ7ZxpznU7U6nUh9bwIgQAgBcMIACAF9NmACUSCT344INKJGwfKjbdsJ0zx0dhGyW2c6Y5n9s55V6EAAD4aJg2j4AAADMLAwgA4AUDCADgBQMIAODFtBlAmzZt0oUXXqhkMqnly5frv/7rv3wvaUJ985vfVCgUGne59NJLfS/rnLz22mu68cYb1draqlAopGeffXbcz4Mg0AMPPKCWlhZVVFRo5cqVeuutt/ws9hx82Hbefvvt7zu2q1ev9rPYs9TZ2amrrrpKNTU1amxs1M0336zu7u5xNdlsVh0dHZo9e7aqq6u1du1a9fX1eVrx2XHZzuuuu+59x/Puu+/2tOKzs3nzZi1ZsmTszabt7e362c9+Nvbz83Usp8UA+vGPf6wNGzbowQcf1P/8z/9o6dKlWrVqlfr7+30vbUJdfvnl6unpGbv84he/8L2kc5LJZLR06VJt2rTptD9/9NFH9b3vfU+PP/64Xn/9dVVVVWnVqlXKZo1hp5592HZK0urVq8cd26eeeuo8rvDcdXV1qaOjQ7t27dLLL7+sQqGgG264QZlMZqzm/vvv1/PPP69nnnlGXV1dOnLkiG655RaPq7Zz2U5JuvPOO8cdz0cffdTTis/O3Llz9cgjj2jPnj3avXu3rr/+et1000369a9/Lek8HstgGrj66quDjo6Osa9LpVLQ2toadHZ2elzVxHrwwQeDpUuX+l7GpJEUbNu2bezrcrkcNDc3B9/61rfGvjcwMBAkEongqaee8rDCifHe7QyCIFi3bl1w0003eVnPZOnv7w8kBV1dXUEQvHvsYrFY8Mwzz4zV/Pa3vw0kBTt37vS1zHP23u0MgiD40z/90+BLX/qSv0VNklmzZgX//M//fF6P5ZR/BJTP57Vnzx6tXLly7HvhcFgrV67Uzp07Pa5s4r311ltqbW3VwoUL9YUvfEGHDh3yvaRJc/DgQfX29o47rqlUSsuXL59xx1WSduzYocbGRi1evFj33HOPjh8/7ntJ52RwcFCSVF9fL0nas2ePCoXCuON56aWXat68edP6eL53O0/50Y9+pIaGBl1xxRXauHGjRkZsH4ExlZRKJT399NPKZDJqb28/r8dyyoWRvtexY8dUKpXU1NQ07vtNTU363e9+52lVE2/58uXasmWLFi9erJ6eHj300EP69Kc/rTfffFM1NTW+lzfhent7Jem0x/XUz2aK1atX65ZbbtGCBQt04MAB/d3f/Z3WrFmjnTt3KhKJ+F6eWblc1n333adrrrlGV1xxhaR3j2c8HlddXd242ul8PE+3nZL0+c9/XvPnz1dra6v27dunr371q+ru7tZPf/pTj6u1+9WvfqX29nZls1lVV1dr27Ztuuyyy7R3797zdiyn/AD6qFizZs3Yv5csWaLly5dr/vz5+slPfqI77rjD48pwrm677baxf1955ZVasmSJFi1apB07dmjFihUeV3Z2Ojo69Oabb0775yg/zJm286677hr795VXXqmWlhatWLFCBw4c0KJFi873Ms/a4sWLtXfvXg0ODurf/u3ftG7dOnV1dZ3XNUz5P8E1NDQoEom87xUYfX19am5u9rSqyVdXV6dLLrlE+/fv972USXHq2H3UjqskLVy4UA0NDdPy2K5fv14vvPCCfv7zn4/72JTm5mbl83kNDAyMq5+ux/NM23k6y5cvl6Rpdzzj8bguuugiLVu2TJ2dnVq6dKm++93vntdjOeUHUDwe17Jly7R9+/ax75XLZW3fvl3t7e0eVza5hoeHdeDAAbW0tPheyqRYsGCBmpubxx3XdDqt119/fUYfV+ndT/09fvz4tDq2QRBo/fr12rZtm1599VUtWLBg3M+XLVumWCw27nh2d3fr0KFD0+p4fth2ns7evXslaVodz9Mpl8vK5XLn91hO6EsaJsnTTz8dJBKJYMuWLcFvfvOb4K677grq6uqC3t5e30ubMH/zN38T7NixIzh48GDwn//5n8HKlSuDhoaGoL+/3/fSztrQ0FDwxhtvBG+88UYgKfj2t78dvPHGG8Hbb78dBEEQPPLII0FdXV3w3HPPBfv27QtuuummYMGCBcHo6Kjnldt80HYODQ0FX/7yl4OdO3cGBw8eDF555ZXgT/7kT4KLL744yGazvpfu7J577glSqVSwY8eOoKenZ+wyMjIyVnP33XcH8+bNC1599dVg9+7dQXt7e9De3u5x1XYftp379+8PHn744WD37t3BwYMHg+eeey5YuHBhcO2113peuc3Xvva1oKurKzh48GCwb9++4Gtf+1oQCoWC//iP/wiC4Pwdy2kxgIIgCL7//e8H8+bNC+LxeHD11VcHu3bt8r2kCXXrrbcGLS0tQTweDy644ILg1ltvDfbv3+97Wefk5z//eSDpfZd169YFQfDuS7G/8Y1vBE1NTUEikQhWrFgRdHd3+130Wfig7RwZGQluuOGGYM6cOUEsFgvmz58f3HnnndPuztPptk9S8OSTT47VjI6OBn/9138dzJo1K6isrAw++9nPBj09Pf4WfRY+bDsPHToUXHvttUF9fX2QSCSCiy66KPjbv/3bYHBw0O/Cjf7qr/4qmD9/fhCPx4M5c+YEK1asGBs+QXD+jiUfxwAA8GLKPwcEAJiZGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAALxhAAAAvGEAAAC8YQAAAL/4f1bYU6+TR0jAAAAAASUVORK5CYII=\n"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Real mark: 4\n","NN answer: 4\n"]}]},{"cell_type":"code","source":["# истинные метки классов\n","true_labels = np.argmax(y_test, axis=1)\n","# предсказанные метки классов\n","predicted_labels = np.argmax(model.predict(X_test), axis=1)\n","# отчет о качестве классификации\n","print(classification_report(true_labels, predicted_labels, target_names=class_names))\n","# вычисление матрицы ошибок\n","conf_matrix = confusion_matrix(true_labels, predicted_labels)\n","# отрисовка матрицы ошибок в виде \"тепловой карты\"\n","display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix, display_labels=class_names)\n","display.plot()\n","plt.show()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":771},"id":"w0L7TzS0x3A2","executionInfo":{"status":"ok","timestamp":1765230538258,"user_tz":-180,"elapsed":5577,"user":{"displayName":"Егор Кирсанов","userId":"10290320580506007453"}},"outputId":"f6abf527-0c57-45f6-d537-8b38d1d4b1bb"},"execution_count":133,"outputs":[{"output_type":"stream","name":"stdout","text":["\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 8ms/step\n"," precision recall f1-score support\n","\n"," airplane 0.78 0.85 0.81 983\n"," automobile 0.90 0.93 0.91 1026\n"," bird 0.73 0.69 0.71 1007\n"," cat 0.63 0.64 0.64 1011\n"," deer 0.81 0.75 0.78 985\n"," dog 0.70 0.71 0.71 974\n"," frog 0.86 0.79 0.82 1007\n"," horse 0.81 0.84 0.83 982\n"," ship 0.88 0.93 0.90 1026\n"," truck 0.92 0.88 0.90 999\n","\n"," accuracy 0.80 10000\n"," macro avg 0.80 0.80 0.80 10000\n","weighted avg 0.80 0.80 0.80 10000\n","\n"]},{"output_type":"display_data","data":{"text/plain":["
"],"image/png":"iVBORw0KGgoAAAANSUhEUgAAAkAAAAGwCAYAAABB4NqyAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAA1WJJREFUeJzs3Xd8E+UfwPFPVpOmey8KpVD2FGQjDhRlOXCgIEO2DNlDhmyULYqgKFMU1J/iRoaAgKwyhUJZhe69Z+bvj0BqLKPYpGnt83698oLcXe6+TS5333yf556TGI1GI4IgCIIgCFWI1N4BCIIgCIIglDeRAAmCIAiCUOWIBEgQBEEQhCpHJECCIAiCIFQ5IgESBEEQBKHKEQmQIAiCIAhVjkiABEEQBEGocuT2DkCwPoPBQHx8PC4uLkgkEnuHIwiCIDwAo9FITk4OgYGBSKW2q1MUFhai0Wissi4HBwdUKpVV1lVeRAL0HxQfH09wcLC9wxAEQRDKICYmhmrVqtlk3YWFhdSs4Uxist4q6/P39ycqKqpSJUEiAfoPcnFxAeDDPxrj6CyzczTFtrQMtXcIJUidHO0dQgmGvAJ7h1A5GA32jqCkijiwfgWsAst8vO0dQgmGjCx7h2CmM2o5qNthPpbbgkajITFZz82TIbi6lK3KlJ1joEaLG2g0GpEACfZ1u9nL0VmG2qXiJEByicLeIZQglTjYO4QSDBKdvUOoJCpgAoRIgEpDJq2I37uKd3wqjy4Mzi4SnF3Kth0DFW8fKw2RAAmCIAhCFaU3GtCXMW/XV8RqbCmIBEgQBEEQqigDRgxlrFyW9fX2Ii6DFwRBEAShyhEVIEEQBEGoogwYytybruxrsA+RAAmCIAhCFaU3GtGX8erFsr7eXkQTmCAIgiAIVY6oAAmCIAhCFVWVO0GLBEgQBEEQqigDRvRVNAESTWCCIAiCIFQ5ogIkCIIgCFWUaAITqgyDHk5/4M7VH5wpSJGh9tUT9kIuzd7MNI+Yf2qVO9d/diIvUY5UYcS7oYYW4zPwbVpkXs/u4b6kXVRSmCbFwc1AYNtCHp6UjpOfdW6s16h1Di8NTyKscQFe/lpmDwrlyG/uf1vCSL+JCTz9airObnoiTjiz6u1g4qNscx+abq8m0O3VBPyCTO/BzStqvvgomPA/PPENKmTT7+F3fN2Ct+pxaGf53fdIKjXSd3wCT7yQjoevlrREBbu/9uKL9/3BTsPVV8SY+o5P4PUJSRbTYq4qGdypvl3iAXhlVBLtu2YRXLsITaGUiHA1ny0IIPaa/e6tVBHeJy+fQga+dYWW7dNQqvQkxKhZMbsBVyLcbi1hpO+Iazz9fBxOLjoizrqzemE94qOdbBZTo1Y5vDgsgbDG+Xj5aZkzpDZHdnmY509Yep0nX0qzeE34fldm9K9rs5j+rap8FViVS4Bu3LhBzZo1OX36NM2aNSvTugYMGEBmZiY7duywSmzl4dwnblz8wpVH3kvBI0xL6nkHDk7zwcHFQMN+2QC41dTSdlYaLsE69EUSzm9wY+dAf17aE4Ojp2m8h4DWhTQdnoWjj578JBnH3/Pk9zG+9NieYJU4VWoD1yPU/Lbdm3c+vV5i/stvJvHswBSWjqtBYowD/ScmsPDzqwx5vAHaIuu37KYmOrBhaQhxNx2RSKDzc0nMWn2RUc83I/a6mtfat7JY/plXEuk1KI7wPzzuskbbePnNJLr3S2Hp2BBuXlYR1jSfCctukpcj4/v1vuUaS0WOCeDGJRVTe9cyP9fr7Hs/oyZt8/hxozeXz6iRyY0MmJrAwi+vM6RTXYoK7HdPP3u+T84uWpZuPMG5E57MGtWcrAwHAqvnk5NdfN+uFwfcoOerMSyf1ZDEOEdef/Ma81afZnivtmg1tnnfVGo9URfV7PrKh1mfXL3jMif2u7F8Yk3zc21R5bxf1n9ZlUuAgoODSUhIwNu74t2NuDwkn1ZRo3M+1R8z3XHcpZqO6z8VkHJOaV6mVo88i9e0fjuNy9+4kHHJAcd2hQA0Gphtnu8SpKPJ0Cz2vOmLQQtSK9xTMHyfG+H73O4y18hzg5L5cpU/R3a5A7B4bAjbT5+jXZdMDvzgWfYA/uHYPi+L55tWhtDt1UTqNcsh+qoTGamWN3ds1zmNg796U5hfvieuBi1zObLLneO/m967pFgljz2bQd1mefd5ZdWKCUCvh4yUinMDzOl9Qi2eLxtbna/OXyCsSQHnjznbKSr7vk8vDrxBSqKKFbMbmqclxTv+bQkjz70WzbZ1NTm635RML5vZkC/2/EHbx1L44zd/m8QVvt+d8P3u91xGWySpUPvX3Rgo+22FK+cwiFWwE7RMJsPf3x+5/M65n9FoRKf7796N27d5IfFHVGRFmf7+tIsOJJ5UUe2R/Dsur9dA5HYXHFz0eNbT3HGZokwp135wwq95kVWSn/vxr67By0/HqYMu5mn5OTIunXGifgvbn1SlUiOduqagUuu5dNq1xPzaDXOp1SCP377xs3ks/xQR7kyz9jkE1TQlqqH182n4cC4n7ppMVs2YAIJqavji5Hk2/hnBlA9u4hN45/3bXpxcTc3JOZn2q/6Afd+nNp1SuBLhyrTFZ/li734++PIoXZ6PNc/3DyrA00fDmWPFP1DycxVEnnelfpPMcovzTpq0yWHbydN8+vtfjJp/Axf3inle0d+6Cqysj8roP5kA7dy5kw4dOuDu7o6Xlxfdu3fn2rVrgKkJTCKRcObMGQD279+PRCLh119/pUWLFiiVSg4dOsTs2bNp1qwZH3/8McHBwajVal5++WWysrL+1Xb/vu1vv/2Wxx57DLVaTdOmTTly5IjFeg4dOkTHjh1xdHQkODiYMWPGkJdnnRN702FZhHbN45unq7G+QQg7ngukUf8save0XH/0Pkc2NavBxsYhnN/gxtMbElF5Wub5x5d4sKlpDT5vVYPcBDmd11j2FbAVTx8tAJmpltlWZorcPM8WQurk8e2pP/nhr8OMmnOVeSPrE31NXWK5Li8mEn3VkYt3SI5sbftqPw784MGnByL4OeoUq3+7xHef+rLvO+tXxSpzTJdOO7F0XHWm963FB9Oq4V+9iGXfXcHRyTp92MpKIjEyfE4c54+ruRnpeP8X2Ii93yf/oAK6vRRLfLSaGW8+xM9fV2P45Eie6BEPgIe3KRnLSLeswGamKfHwsl9CG37AjaXjazL1tbp89m41GrfJYf6my0ilFS9R0But86iM/pMJUF5eHuPHjyc8PJy9e/cilUp5/vnnMRjuXqibOnUq7777LhcvXqRJkyYAXL16la+++ooff/yRnTt3cvr0ad58880yb3f69OlMnDiRM2fOUKdOHV599VVz1enatWs8/fTT9OrVi3PnzrF9+3YOHTrEqFGj7rrdoqIisrOzLR53c/0XJ6796Myjy1J47rs4Hnkvlb/Wu3HlW8sSe0DrQp7/Po4e2xOo9kgBv4/1pSDNcndpMiiL53bE8fSGBKRSODDZh0raF65UYqMcGflcc8a+3IyfvwxgwnuXqV7LsnLmoNTzaPcUu1R/AB7pkcHjz6fz7qgQRj5Tn6XjavDi8CQ6v5h2/xdXoZjC97ly8Cd3oi46cvKAKzNeD8XZVc8jPTLtFtPfjVoYR416hSwaUcOucdj7fZJIjVy95MKmD8O4HunKzm+rsfO7ILq+GHv/F9vRgR+9OLrHgxuRao7s8uCdgWHUbZZHk7Y59g5N+Jv/ZB+gXr16WTxfv349Pj4+RERE4Ox857b0uXPn8uSTT1pMKywsZPPmzQQFBQHwwQcf0K1bN5YtW4a/f8m25Xttt1GjRubpEydOpFu3bgDMmTOHhg0bcvXqVerVq8eiRYvo06cPY8eOBSAsLIxVq1bRqVMn1qxZg0pV8oqQRYsWMWfOnPu8KyYnFnvSZGgmtbqbKj6edbXkxss5+7EbYS/kmpdTqI0oauhwraHDt1kRXz9Zjctfu9B0eHEFTOVpQOVpwK2mDvdayWx7pDrJZ5T4NS8qsV1rSr/Vru7urSU9ubgK5O6j49oF2/1a1mmlJESb1n/1gjN1GufwbL94PnintnmZDk+noVQZ2LvDPgnQkBlxbF/tb+4HdeOSI75BGnqPSmTPN173eXXViemf8rLlxF5XEhhi2323NEYuiKX1k9lMeL4WqQkO939BOSrv9ykjVUnMdcuruWKinGj/RPKt+ab3x8NTQ0ZqcT9Gd68irke6UFEkxqjITJMTWKOQM4fLvzJ8L6IP0H/MlStXePXVVwkNDcXV1ZWQkBAAoqOj7/qali1blphWvXp1c/ID0LZtWwwGA5GRkWXa7u0KE0BAQAAAycmmL/TZs2fZuHEjzs7O5keXLl0wGAxERUXdcbvTpk0jKyvL/IiJibnr36krlCD5x6culRoxGu99hYLRAHrN3Zcx3voGGO6xjLUkRjuQliSneYfiX1NqZz31muVx8aTtLn39J4kUFA6WX/0uvRI59rsnWRn26fyodDSYP4vbDPqSn3l5qogx/ZNKrSewhsYioS5/RkYuiKXd01lMfqkWSTHK+7+knJX3+xRxxp2gGpZV1qDq+SQnmH4IJsY5kp7iQNPWxdVERycddRtlc/Gce7nEWBre/hpcPXR23r/uzIAEfRkfBjsNZ1FW/8kKUI8ePahRowbr1q0jMDAQg8FAo0aN0Gju3ibs5FT2E2dpt6tQFH8JJLcG37ndTJabm8uwYcMYM2ZMifVXr179jttVKpUolaU7WFZ/LJ8za9xxCtDhEaYlLcKB8xvcCHvRlExo8yWcXeNO9SfycfTRU5QhJWKrK/lJMmo+Y6oaJZ9VknrOAb8WRTi4GciJlnPyfQ9cqmvxbV5YqjjuR6XWW/zK9A8uIrRBPjmZclLiHdjxmS+vjkkkLkpJYoyS/hPjSUtS8KfFWEHWM2D8DcL/8CA5QYnaydTM1aRVFjMGFV+dElC9gEYPZzNraMN7rMm2ju52o/eYRJLjHLh5WUWtRgW8MDSZXdvtV2mpiDENmRnH0d1uJMcq8PLX8fqEBPQG2L+jfIct+LtRC+N47PkMZg+sSUGuFI9b/dnycmRoCu2TLdr7ffru8+os23iCl9+I4uBuP+o2zOKZXrGsmtfg1hISdnxRnd6Do4iPVpN06zL4tBQlR/b52Cyuux+fZORkyuk7Np5Dv3qQkaIgoEYRg6bFEH9Dyck/7NvxX7D0n0uA0tLSiIyMZN26dXTs2BEwdSr+N6Kjo4mPjycwMBCAo0ePIpVKqVu35GBW1truQw89REREBLVr177/wv9Cm5lpnHrfgz/neFOYJkXtq6du7xyaj8wAQCKDzOsKrnznS2GGDJWHHu/GRXT7IgGPMNMBWa4ycGO3E6c+8ECXL8HRV0+1jgU0W5mJzEoV+zpN81ny9RXz8+Gz4wDY9ZUny8aH8NVHfqjUBt56LxpnVz0XTjgzvW9tm4wBBODupWXie5fx9NWQlyMnKlLNjEENOf1n8YngqV5JpCYqOXXI3SYxlMZHM4PpPymeUQtjcPc2DTr4y+febF1pm8uBK2tM3gFapq2+gYuHnqx0OReOOzG2Rx2y0u13SOwxwFTFWPrtNYvpS8cGs/sr+3QYt/f7dCXCjfkTmjJg9FVeG3qdxDhHPl5Sl/2/BpiX+WZjCCpHPaNnXMTZRceFM+7MGtncZmMAAdRpksfi7cUtAcNmmaruu7/24oPpIdSsl0/nXqk4uepJT1Jw8qAbm5cFodVUoLLnLQaj6VHWdVRG/7kEyMPDAy8vLz755BMCAgKIjo5m6tSp/2pdKpWK/v37s3TpUrKzsxkzZgwvv/zyHfv/WGu7U6ZMoU2bNowaNYrBgwfj5OREREQEu3fv5sMPP/xXf8ffOTgbaTM9nTbT0+84X6400nl18j3X4VlXS9fNiWWO5V7OHXGhS7WH7rGEhM1LA9m8NNCmcdy2cnrYfZfZtCKETStCbB/MPRTkyVg7O5i1s4PtGsffVcSYFr0ZYu8QSugS2NTeIZRQEd6n4wd9OH7wXtUcCZ+vqc3na2zzo/FOzh115ekaD991/vR+FW/E57u53YxV1nVURhUvHS0jqVTKtm3bOHnyJI0aNWLcuHEsWbLkX62rdu3avPDCC3Tt2pWnnnqKJk2a8NFHH9l0u02aNOHAgQNcvnyZjh070rx5c2bNmmWuQgmCIAiCUHYSo/G/fOHyvzd79mx27NhhHi+oMsnOzsbNzY3PTjVD7WLfQdT+7rN65fcLrbSkTiXH8bE3Q96dB6UU/uGfPasrgop4OJVUvF/nMl/b9c/5twzpmfYOwUxn1LJP+zVZWVm4utrmqrHb54k/LwTg7FK2WkhujoF2DRNsGq8t/OeawARBEARBKB2DUYLhPlcBl2YdldF/rglMEARBEAThfkQCdBezZ8+ulM1fgiAIglBaZR0DyBqdqO1FNIEJgiAIQhWlR4q+jLWQinEHvQcnEiBBEARBqKKMVugDdL87CVRUoglMEARBEIQqR1SABEEQBKGKqsoDIYoESBAEQRCqKL1Rit5Yxj5AFXD4q9IQTWCCIAiCIFQ5ogIkCIIgCFWUAQmGMtZCDFTOEpBIgARBEAShihJ9gIT/pM9bhyGXKOwdhtkvMUftHUIJXau1sHcIlUNFvMeVUDoV8LMzZGbZO4QSJLKK0yNEYpSA1t5R/PeJBEgQBEEQqijrdIKueEl2aYgESBAEQRCqKFMfoDLeDLWSNoFVnJqfIAiCIAhCOREVIEEQBEGoogxWuBeYuApMEARBEIRKRfQBEgRBEAShyjEgrbLjAIk+QIIgCIIgVDmiAiQIgiAIVZTeKEFvLONAiGV8vb2IBEgQBEEQqii9FTpB60UTmCAIgiAIQuUgKkCCIAiCUEUZjFIMZbwKzCCuAhMEQRAEoTKpyk1gIgESaNQqhxeHJRDWOB8vPy1zhtTmyC4P83yVWs8bU2Np+1QGrh46EmOUfL/Bj1+2+lothvxcKVsWB/LnTjey0hTUapjPsLmx1GmWD8DysTXY87WXxWtaPJrFvK3XAEiKceDLlf6cPexCRooCTz8tj7+QzitjElE42O7L6eWvYdDbCTz8eDZKlYH4G0qWja/OlXNqm23zXvqOT+D1CUkW02KuKhncqb5d4vm7HgNSeXFEMp4+Oq5HOPLRjCAiz9jnfWrUOpeX3kwx7fP+Oma/EcKRnW52ieW2V0Yl0b5rFsG1i9AUSokIV/PZggBir6nsGpe9P7dGrbJ5cWgiYY3yTMenoWEc2V18fHL31jJoSgwPdczCyVXP+eMufDS7BvE3bPO+vTwijvZdMqgWWmD6nE65sP69YOKiHM3LjJ4fRfP2WXj6aSjMkxFxypn171Un9rrjPdYslDfRB8iKNm7ciLu7+z2XmT17Ns2aNTM/HzBgAM8995xN47oflVpP1EU1q2fWuOP8oTNjaNkpiyVjQxn6RGN2fObHyLk3adM5w2oxvD+xBqcPujBx1U0+2nOR5p1yeLt3GKkJxXezb/FYFp+fPmd+TF59wzwv5qoKg0HC6PeiWfN7BENnx/LLFm82vRtotRj/ydlNx/IdV9DrJMzoG8qQx+rxydxAcrNkNttmady4pKJ3s4bmx/jnwuwaD0CnnhkMfSeercv9GdmlDtcjVCz44jpuXva55bVKbeD6BRUfvl3NLtu/kyZt8/hxozdju4cxrXcoMrmRhV9eR+mot1tMFeFzUzkaTMenWXc6Phl55+PL+FcvYs7QMEZ1b0hynAOLPr9ks/etcascftzix7heDXm7Xz3kCiMLNltu7+p5J5ZPDmXok02ZPqAeEgks2HwJqbTiVUoMFF8J9m8fBnv/Ef9Spa4Abdy4kbFjx5KZmWnvUEpt4sSJjB492t5hWAjf7074fve7zm/QIpc9//Pm3FFXAH790peufVKo2yyPo3s87vq60ioqkHD4F3dmrb9G4za5APSdkMDx3W78vNmb/lMSAFA4GPH01d1xHS0fy6blY9nm5wE1NMReS+KXzT4MnhVX5hjv5OU3k0mNd2DZ+OrmaUkxSpts60Ho9ZCRorj/guXohaGp7PzCk13bPQFYNaUarZ7Ipsur6Xz1oV+5xxO+z5Xwfa7lvt17md4n1OL5srHV+er8BcKaFHD+mLNdYqoIn1v4AXfCD7jfcV5QzULqP5THsKcacfOKqSr1wYwQvjx+msd6prFzu/Wq1LfNHFjP4vnySaFsCz9FWKM8zp+4dYzcVrzd5Dglm5YHs+aXv/CrVkRCtH0rev9knYEQK2ctpXJGXYk5Ozvj5eV1/wUrkIiTzrTpnIGXnwYw0qRtNkE1Czn5h3WaDPR6CQa9BAel5a8jB5WBiBPFB/6/jjjzapPGDOnYgA+nBpOdfu9KS162DGf3OydM1tDmqSwun1Mz/eMotp89z+rfInnmtTSbba+0gmpq+OLkeTb+GcGUD27iE6ixazxyhYGwJvmcOuhinmY0Sjh90IUGLfLtGFnF5uRqqijkZNqnolgZPrfbzduaouJTmdEoQauR0rBlbrnEoHa59Tll3bmeoHTU89SLKSREK0lJcCiXmITSsWsCtHPnTjp06IC7uzteXl50796da9dMfTr279+PRCKxqO6cOXMGiUTCjRs32L9/PwMHDiQrKwuJRIJEImH27NkAZGRk0K9fPzw8PFCr1TzzzDNcuXLFvJ7bTVU//fQTdevWRa1W8+KLL5Kfn8+mTZsICQnBw8ODMWPGoNcXlzXvt97bduzYQVhYGCqVii5duhATE2Oe988msH8yGAwsWrSImjVr4ujoSNOmTfnmm2/+5TtsHWveqc7NK45sPX6Wn66eZP6my6yeWYPzx13u/+JSUDsbqN8ily/f9yctUYFeD7//z5NLJ51ITzJVMlo8ls2E92+ycPsVBk6P46+jzsx6vTb6u1S546OU/LjBl659U60S450EVNfQ/fVU4qOUvP1aKD9t9mLE3Fg6v5Rus23ez6XTTiwdV53pfWvxwbRq+FcvYtl3V3B0sl8ziqunHpkcMlMsTxAZqXI8fGyXoFZmEomR4XPiOH9czc1I+/QbqQyfW8w1FUlxDgycHIuzqw65wsBLw+LxCdTg6Wv7xF8iMTJs5k0uhDtz87Jlv6hufZP49q8T7LgQTstOmUzvVw+dtuLVHG7fC6ysj8rIrlHn5eUxfvx4wsPD2bt3L1KplOeffx6D4f4tiu3atWPlypW4urqSkJBAQkICEydOBEz9asLDw/nhhx84cuQIRqORrl27otUWt1vn5+ezatUqtm3bxs6dO9m/fz/PP/88v/zyC7/88gtbtmzh448/tkg+SrveBQsWsHnzZg4fPkxmZia9e/cu9XuyaNEiNm/ezNq1a7lw4QLjxo2jb9++HDhw4K6vKSoqIjs72+JhTT0HJFG/eR7vvBHG6O4NWLcgmJHzbtK8fZbVtjFx1Q2MRni9RWOerdmcH9b70Om5DKS39tBOz2bQ5qksatYvpN3TWczedI3LZ5z468+SSVhqgoKZfWvRoXsGT/exXUVGIoWr5x3Z8G4g1y6o+XWrN79+4UW3122XdN1P+D5XDv7kTtRFR04ecGXG66E4u+p5pEem3WISHtyohXHUqFfIohF37pcnmOh1UuYNDyOoZiHfnD3F9xHhNG2bw/F9bhgMth+deOTcG4TUyefdMbVLzNv3vRejejRm0iv1iYtSMe2DKygcKl5vGQMSqzwqI7v2AerVq5fF8/Xr1+Pj40NERMR9X+vg4ICbmxsSiQR/f3/z9CtXrvDDDz9w+PBh2rVrB8DWrVsJDg5mx44dvPTSSwBotVrWrFlDrVq1AHjxxRfZsmULSUlJODs706BBAx577DH27dvHK6+88kDr/fDDD2ndujUAmzZton79+hw/fpxWrVrd828qKipi4cKF7Nmzh7Zt2wIQGhrKoUOH+Pjjj+nUqdMdX7do0SLmzJlz3/fs33BQGhgwKY55w2pz/Hd3AKIuqanVIJ9eQxM5fdg6zWABIRoW/+8KhflS8nOkePrpWDS8Jv7Vi+68fA0Nrp5a4m8oadYxxzw9LVHB1JfCqN8ijzGLo60S292kJ8u5edmyPT/mqooOXa2XGJZVXrac2OtKAkPu/D6Wh+x0GXoduP+jauDhrSMjpVJ3Q7SJkQtiaf1kNhOer0WqHZtMKsvndvW8EyO7NULtokOhMJKVrmDldxe48peTTbc7YvYNWj2WyaTe9UlNLNn3Lz9HTn6OnPgbKi6dcebr0ydp1yWdAz962zSuB2Wdu8GLCtADu3LlCq+++iqhoaG4uroSEhICQHT0vz9xXbx4Eblcbk5AALy8vKhbty4XL140T1Or1ebkB8DPz4+QkBCcnZ0tpiUnJz/QeuVyOQ8//LD5eb169XB3d7dY5m6uXr1Kfn4+Tz75JM7OzubH5s2bzU2DdzJt2jSysrLMj783uZWVXGFE4WDkn0U5g16CxAZ7j0ptwNNPR06mjFMHXGjTJfOOy6XGK8jJkOPpV1x9S01QMOXFMMKa5DNuxU1z9chWIk44EVzLMrEICi0iOa7idEBWqfUE1tCQnmy/mHRaKVfOqWneoThRlUiMNOuQS8RJ+1wGXzEZGbkglnZPZzH5pVp271Bf2T63/Bw5WekKAkMKCWucZ3GpvHUZGTH7Bu2eSmdq3/okxd6/U7NEAkiw6ZAclYVer2fmzJnmbh61atVi3rx5GP82mKLRaGTWrFkEBATg6OhI586dS3Q3SU9Pp0+fPri6uuLu7s6gQYPIzX2wfl92TeN79OhBjRo1WLduHYGBgRgMBho1aoRGozEnIn9/U/7e1FRWCoXlCUEikdxxWmma46zl9of3888/ExQUZDFPqbz7wVCpVN5z/v2o1HqLCoF/cBGhDfLJyZSREq/k3BEXBr8di6ZQSlKckiatc3iiVyqfzKt+j7U+mJP7XTAaJVSrVUj8DSXr5wVRrVYRT76SRkGelC+WB9C+awYevjoSbihZvyCIgJAiWnQyNfelJiiY+mIYvtU0DJoZR1Za8a59tyvHyurbdb6s+P4yvUcn8ceP7tRtlk/XPmmsnGy/S6uHzIzj6G43kmMVePnreH1CAnoD7N9hq5NB6Xz7iTcTV8Zw+ayayNNqnh+SgkptYNc2T7vEo1LrCaxZ3EfEP1hDaMMC0z4fZ5+qy6iFcTz2fAazB9akIFeKh4/peJeXI0NTaJ/fqhXhczMl8YXm5/7BRYTWzyMnS05KvJKOXdPJSpOTHO9ASL0CRsy6yZFdHpw6aJtxnUbOvcGjPdOYO7SO6XPyNu1HeTlyNEVS/IMLeaR7GqcOupOVLsfbX8PLw+PRFEo5cY+rbe3FOgMhlv717733HmvWrGHTpk00bNiQ8PBwBg4ciJubG2PGjAFg8eLFrFq1ik2bNlGzZk1mzpxJly5diIiIQKUyJZx9+vQhISGB3bt3o9VqGThwIEOHDuWLL74odSx2S4DS0tKIjIxk3bp1dOzYEYBDhw6Z5/v4+ACQkJCAh4fp4H3mzBmLdTg4OFh0UgaoX78+Op2OY8eOmZuqbm+rQYMG/zre0q5Xp9MRHh5ubu6KjIwkMzOT+vXvPxBdgwYNUCqVREdH37W5yxbqNMlj8fZI8/Nhs0wVpN1fe7FsYiiLRtdi4ORYJr9/HRd3HcmxSjYtqcbPn/tYLYa8bBkb3w0iNUGBi7ue9l0z6D8lHrkC9DojURcd2fO1J3nZMjz9tDzUKYfXJ8WjuHXl2Ok/XIi/oSL+hop+LRtbrPuXuFNWi/PvLp9VM3dwTQZOTaDP2EQSYxxY+04Q+76zz0kdwDtAy7TVN3Dx0JOVLufCcSfG9qhDVrp9mywO/OCBm5eefpMS8fDRcf2CI9P71CQz1T6VqTpNC1jyv+Kq6vA58QDs2u7BsnHWS+wfRI8Bpv5qS7+1rPYuHRvM7q/ss09VhM+tTuM8Fm+7ZH4+bKaphWD3N94smxSKp6+GodOjcffWkp6iYO+33nzxge3G/+re19QqsHibZVV/2aRQ9vzPB02RlEYP5/DcwEScXfVkpio4f8KF8S82ICut4lSHbzMYJRjKeDf3B3n9n3/+ybPPPku3bt0ACAkJ4csvv+T48eOAqeixcuVKZsyYwbPPPgvA5s2b8fPzY8eOHfTu3ZuLFy+yc+dOTpw4QcuWLQH44IMP6Nq1K0uXLiUwsHSfv92Oih4eHnh5efHJJ58QEBBAdHQ0U6dONc+vXbs2wcHBzJ49mwULFnD58mWWLVtmsY6QkBByc3PZu3cvTZs2Ra1WExYWxrPPPsuQIUP4+OOPcXFxYerUqQQFBZnfzH+jtOtVKBSMHj2aVatWIZfLGTVqFG3atLlv/x8AFxcXJk6cyLhx4zAYDHTo0IGsrCwOHz6Mq6sr/fv3/9fx38u5o648XePhu87PSFGwfFJNm2z7tkd6ZvJIz8w7zlM6Gpn/xdV7vv7JV9J58pXyv/rq2B43ju2x7wjCf7fozRB7h3BXP2zw5ocNFaP/w7kjznQJbGrvMCxUtHhus/fndu6YK0/XvPvx8/uN/ny/0f+u863tmdDW95yfnuzArDfq3XOZ/6p/XoBzp9aJdu3a8cknn3D58mXq1KnD2bNnOXToEMuXLwcgKiqKxMREOnfubH6Nm5sbrVu35siRI/Tu3ZsjR47g7u5uTn4AOnfujFQq5dixYzz//POlitdufYCkUinbtm3j5MmTNGrUiHHjxrFkyRLzfIVCwZdffsmlS5do0qQJ7733HvPnz7dYR7t27Rg+fDivvPIKPj4+LF68GIANGzbQokULunfvTtu2bTEajfzyyy8lmrgeVGnWq1armTJlCq+99hrt27fH2dmZ7du3l3ob8+bNY+bMmSxatIj69evz9NNP8/PPP1Ozpm0TEEEQBKHqMdxqAivL4/ZAiMHBwbi5uZkfixYtKrG9qVOn0rt3b+rVq4dCoaB58+aMHTuWPn36AJCYmAiY+uD+nZ+fn3leYmIivr6Wg1zK5XI8PT3Ny5SGxGispLdxFe4qOzsbNzc3HlO8hFxScUquP984au8QSuharYW9Q6gcxGFCsCJJGfos2opEUnEu5dYZNfxe+BVZWVm4utpmxPLb54mFxx9D5Vy2xqDCXB1vt9pHTEyMRbx3qgBt27aNSZMmsWTJEho2bMiZM2cYO3Ysy5cvp3///vz555+0b9+e+Ph4AgICzK97+eWXkUgkbN++nYULF7Jp0yYiIyMt1u3r68ucOXMYMWJEqeKuONcyCoIgCIJQabm6ut43YZs0aZK5CgTQuHFjbt68yaJFi+jfv795WJukpCSLBCgpKck8iLC/v7/5Cu3bdDod6enpFsPi3E/lvHhfEARBEIQy0yOxyqO08vPzkf5jjBKZTGa+4rpmzZr4+/uzd+9e8/zs7GyOHTtmHh+vbdu2ZGZmcvLkSfMyv//+OwaDwWKomvsRFSBBEARBqKIMRimGMg5k+CCv79GjBwsWLKB69eo0bNiQ06dPs3z5ct544w3A1BQ5duxY5s+fT1hYmPky+MDAQJ577jkAc//YIUOGsHbtWrRaLaNGjaJ3796lvgIMRAIkCIIgCEI5+eCDD5g5cyZvvvkmycnJBAYGMmzYMGbNmmVeZvLkyeTl5TF06FAyMzPp0KEDO3fuNI8BBKY7MYwaNYonnngCqVRKr169WLVq1QPFIjpB/weJTtClJzpBl5I4TAhWJDpB31t5doKedawzKueynScKc7XMbb3HpvHagqgACYIgCEIVVd5NYBWJSIAEQRAEoYoSN0MVBEEQBEGoQkQFSBAEQRCqKCMSDA9wGfvd1lEZiQRIEARBEKoo0QQmCIIgCIJQhYgK0H+YzM8bmbTiXG7aNeghe4dQguMB3/svVM40L2jtHULloNfbO4JKwajV2TuEEgwFhfYOoQSj0WDvEMwMxvI7BhiMEgzGsjVhlfX19iISIEEQBEGoom7f0b2s66iMKmfUgiAIgiAIZSAqQIIgCIJQRYkmMEEQBEEQqhwDUgxlbAwq6+vtpXJGLQiCIAiCUAaiAiQIgiAIVZTeKEFfxiassr7eXkQCJAiCIAhVlOgDJAiCIAhClWO0wt3gjWIkaEEQBEEQhMpBVIAEQRAEoYrSI0FfxpuZlvX19iISIEEQBEGoogzGsvfhMRitFEw5E01ggiAIgiBUOaICVMVJpUZeG3KZx56Ow8OziPRUFXt+rsa29bUBCTKZgX7DI2nZLgX/oHzycuWcOeHNxtX1SE9VlVucjVrn8tKbKYQ1zsfLX8fsN0I4stPNpts0pujRfpyL/lgRFBqRBMlxmOqKtJ7CND/91vwTGsg1IG3qgOItF6TVir9WxiIj2o9y0P9eCFqQPuyAwzgXJJ6yMsfXZ0QUfd68YTEtJkrNsJ6tAXj6xXge7ZpE7fo5qJ31vNSuA3k5ijJv99/G5Oyqpe/IKB5qm45PQBFZGQqO/O7Nlg9Dyc8tv0PRS4OjGTj+Bjs2B/HJu7VwdtPSd9RNHmqXURzXXi+2rAopt7gqQkzdXkuk26uJ+FUrAuDmFUe++DCY8D88AFA4GBgy7QaduqWicDBw8pA7q98JJTPNwSbx3NaodQ4vDU8irHEBXv5aZg8K5chv7n9bwki/iQk8/Woqzm56Ik44s+rtYOKjyu/4tOnoBfyDS97A9IeN3qyeXq3c4vg3DFboBF3W19uLSICs5NFHH6VZs2asXLnyjvNDQkIYO3YsY8eOfaD1zp49mx07dnDmzJkyx3gnL75+ja4v3GTF3KbcvO5CWP0sxs44S16unB+/qolSpadW3Wy+XF+bqCuuOLtqGTYugllLwxk7oINNYroTldrA9QsqfvvSk3fW37D59ow5BopGpSNt5oBysQe4SzHG6sDFVCo2Go0UTc9CIgflAndwkqD7Kh/N+AyUm7yROJqW036Yg+FoEQ5z3JE4SdCszEEzMwvlak+rxHnjihPThzQ1P9fri0vZSpWek4c9OXnYk4Fjr1tle2WJycu3CC8fDZ8uq030NSf8AgsZNTMSLx8NCyc0KpfYwhrl8MzLCVy/5GSe5uWjMcW1JJToa2pTXO9cNcU1rkGViSk10YENS2sQd0OFRAKdn09m1ppLjHq2KdFX1QybHsXDj2awcExd8nJkvPnOdWasjmRi78Y2iec2ldrA9Qg1v2335p1PS+7HL7+ZxLMDU1g6rgaJMQ70n5jAws+vMuTxBmiLyufEPKZrXaSy4nagkHqFvLvtGgd/su2PNGswIMFQxj48ZX29vYgEqJycOHECJyen+y9Yzuo3yeDYH36cOOwHQHKCmk5PxVO3QSY/Avl5CmaMaW3xmjVLG7Jy42F8/ApISXIslzjD97kSvs+1XLYFoPsiD4mPDIdpfzuABRRXbYyxeowRWhw2eiGtafoaKca7UPh8Ifq9Bci7qzHmGtD/UoDDTDdkD5l+JTtMdaWoXxqGCxqkDcv+y1mvl5CRprzjvO8/DwagccuMMm/nQdwtpptXnVkwvjjRSYx1ZNMHoUxaFIFUZsCgt+3JSqXWM3nxJVa9U4few6L/FpcTC8YWJxWJMY5sej+ESe9dQiozYtDb7uBekWI69rtlUr5pRQ26vZZEvWY5pCY68NSLySyeEMbZo6bvxPKptVn32xnqNcvh0hkXq8dzW/g+N8L33S2RMPLcoGS+XOXPkV3uACweG8L20+do1yWTAz9Y54fG/WSlW55KXxmVRHyUA+eOOJfL9oV/p3LWrSohHx8f1Gr1XedrtSXLp+Xh4jkPmrZMIzA4F4CaYdk0aJpO+BHfu77GyVmHwQC55dhsUd70h4uQ1FNQNCuTgmeTKRyUhu7H/OIFNLd+7f0th5FIJUgUEgx/mT5Lw2Ud6EDaonghaQ05Ej8phgvW+byDquezZe9hPvv1CJPejcDHv9Aq6y2vmJycdeTnym2e/AC8OeMKxw94cuaIx32XLY7Ltr9sK2JMYGoa79QtFZVaz6UzLoQ1ykPhYOT0YXfzMrHX1STFOVCvWY7N47kb/+oavPx0nDpYnIDl58i4dMaJ+i3y7BKTXGHg8Rcy+G27F1SCysjtkaDL+qiMRAJkRTqdjlGjRuHm5oa3tzczZ87EaDSdKENCQiyaxyQSCWvWrKFnz544OTmxYMECAN599138/PxwcXFh0KBBFBba9oT29eZa/LE7kI+/OsD3h39h1eaDfL+tJvt/C7rj8goHPQNHXeTArkAK8mzbn8SejAl69N/nI60mQ7nEA/mzjmhX5aDbWQCA5FYio/skF2OOAaPWiPaLPIwpBoxpBtM60vSgAInLP75mHlKM6YYyxxj5lyvLZ9Zn5oimrJ5XB7+gApZsOoWjWlfmdZdHTK7uGl4ddoNfvwm0eVyPPJNM7Qa5bFxR877LurpreXVENL9+7V/lYgqpk8e3Z47yw4UjjJp7jXlv1iP6qhoPHw1ajYS8HMsfPZmpDnj6aGwa0714+mhvxWF5LMpMkZvnlbd2T2fh7Kpn11flU30qq9t9gMr6qIz+uz/h7WDTpk0MGjSI48ePEx4eztChQ6levTpDhgy54/KzZ8/m3XffZeXKlcjlcr766itmz57N6tWr6dChA1u2bGHVqlWEhobec7tFRUUUFRWZn2dnZ5c65o6dE3j06TiWzGrOzevOhNbJZui4CNJTVOz9xbLznkxmYNqCUwCsXlw+fTbsxgDSugoUQ02/LKV1FBiidOi+L0D+tCMSuQSHee5oFmdT2D0FZKZKj7S1A5TTJaHhh7zM/79x2ZnIv1zZ+NsROnZJZtd3tk8qyhKTo5OOOavPEX3dia1rQmwak7d/IcOmXWP64MZoNfc+UDs66Ziz9jzR19RsXV2jSsUEEBvlyMieTXFy0dPh6TQmLL7C5D7/8e+6lXXpnc6Jfa6kJ/13fyD+V4gEyIqCg4NZsWIFEomEunXr8tdff7FixYq7JkCvvfYaAwcOND/v3bs3gwYNYtCgQQDMnz+fPXv23LcKtGjRIubMmfOvYn5j9EVzFQjg5jVXfP0LeKn/VYsESCYzMHXhKXwCCnj7zTb/6eoPgMRLiiTE8kotaQ05+j+KE01pXQWqz7ww5hpABxJ3KYXD05DWVdxahwy0pg7VFlWgDAMST+v/YsrLURB3U01g9QKrr/vfulNMjmod89aeJT9fzry3GqHX2fbXY1jDXDy8tXzwzSnzNJkcGrXMosdrcTzbrCMGg8QU1yfnyc+TMW90Q5vGVRFjAtBppSREm/r1Xb3gTJ3GuTzbP4E/fvZG4WDEyUVnUQVy99aQnmLbq8DuJT1FcSsOLenJxcckdx8d1y6UT//Ev/MN0tC8Yw7zBt+/qldRGLDCvcAqQVPfnVTOulUF1aZNGySS4h2hbdu2XLlyBb1ef8flW7ZsafH84sWLtG5t2eG4bdu2993utGnTyMrKMj9iYmJKHbNSpcdosNx5DQYJ0r/tGbeTn8DgPKaPak1Otv0OeOVF2sgBY7Tl52aI1SP1K3n5usRZisRdiiFWhzFSh6yDqQOwtI4c5GA4VdxEYIjWYUwyIG1o/QRS5agjILiA9JQ7d4q2h3/G5OikY/4nZ9Fppcwd3RitpuzDAdzPmSPujOjZglEvFD8u/+XM/p98GfVCC1Oi4aRj/qd/odNKmDuy4X2rMv/FmO5EIjWicDBw5bwTWo2EZu2yzPOCahbgF6SxaQfo+0mMdiAtSU7zDsX9kNTOeuo1y+PiyfK/6OSpV9LITJVzbG/5XbBRVsZbV4GV5WGspAmQqADZkbWuClMqlSiV/+6kd/ygH68MvEpKkoqb112oVSeb51+NYvePpuqPTGbg7XdPUatuFnMmPIxMasTD01SRysl2QGfjX6S3qdR6AmsWJxL+wRpCGxaQkykjJc76CZn8JTVFI9PRbslD9pgSw0Ut+h/zUUwsPrDp9xWCuxSJnxTjdR3aD3KQdlAie9j0WUicpci6OqJdnQMuUiROErTv5yBtqLDKFWCDJlzl2AEvkuNVePlo6DsyCoNewv5fTR3YPbyK8PDWmKsvIWF5FOTJSE5QkZttmwrevWJydNKx4OOzKB31LJnaALWTDrWTqW9QVoYDBoNtDqIF+XJuXrU81BUWyMjOVHDzqpMprk//QqkysGRKPdTOetTOpuQ3K11hk7gqYkwDJtwk/A93kuOVqJ30PNojlSats5nxRgPyc+Xs+saXIdOiyMmUk58rY8SsKCJOudg8AVKp9QSGFFde/YOLCG2QT06mnJR4B3Z85surYxKJi1KSGKOk/8R40pIU/GkxVpDtSSRGnnolnT1fe5ZLR3VrEXeDF6zi2LFjFs+PHj1KWFgYMlnpfuXWr1+fY8eO0a9fP4t12NLaZQ3pOyySNyddwM3DNBDir99V58vPwgDw8i2kzSNJAHz4+UGL104d0Ya/TnmVWKct1GlawJL/XTM/Hz4nHoBd2z1YNq661bcnra/AYb472k9y0W3OReIvQzHKBfmTxWV1Y5oB3eocjBkGJF5SZF0ckfezTGoVo1zQSkEzKxO0RqQPK3EYZ50ThrdfEVPei8DVXUtWhgMXTrkxrk8LsjNMyVXXl+MtBiVcsuk0AMtn1GPP9wFWieFBYmrcMoN6TU3909b/arlfD+jShuT48m+yAKjdIJd6TU0VhPW/nbCYN6BzK5Ljy29APXvG5O6lZeLiq3j6asjLkRF1yYkZbzQwX/n18YKaGAwSZnwYaTEQoq3VaZrPkq+vmJ8Pnx0HwK6vPFk2PoSvPvJDpTbw1nvROLvquXDCmel9a5fbGEC3Ne+Yg181Lb9trxydnwWQGG9fpiSUyaOPPsrJkycZMmQIw4YN49SpUwwZMoRly5YxbNiwEgMhSiQSvvvuO5577jnzOrZv386AAQP46KOPaN++PVu3bmXFihWEhoY+0ECI2dnZuLm50bnaCOTSitMcoouJtXcIJTge8LN3CCVoXrDP1SuVzl2algVLRq39rgq8G0OB/YdrKMFY9iszrUVn1LLfuIOsrCxcXW3TnHb7PPH87oEonMpWkdbmafjuyQ02jdcWRAXIivr160dBQQGtWrVCJpPx1ltvMXTo0FK//pVXXuHatWtMnjyZwsJCevXqxYgRI/jtt99sGLUgCIJQVVXlJjBRAfoPEhWg0hMVoEpMVIBKRVSASqmKVoCe3fWGVSpA3z+1XlSABEEQBEGoHMS9wARBEARBqHKqchOYGAdIEARBEIQqR1SABEEQBKGKqsoVIJEACYIgCEIVVZUTINEEJgiCIAhClSMqQIIgCIJQRVXlCpBIgARBEAShijJS9svYK+tggiIBEgRBEIQqqipXgEQfIEEQBEEQqhxRARIEQRCEKqoqV4BEAvQfZsjIxCAp2z1erEpS8b4kmuc09g6hhNxt7vYOoQSnF5LtHUIJxgah9g6hBOmVaHuHUIJEJrN3CCVVoPtuVXVVOQESTWCCIAiCIFQ5ogIkCIIgCFVUVa4AiQRIEARBEKooo1GCsYwJTFlfby+iCUwQBEEQhCpHVIAEQRAEoYoyICnzQIhlfb29iARIEARBEKqoqtwHSDSBCYIgCIJQ5YgKkCAIgiBUUVW5E7RIgARBEAShiqrKTWAiARIEQRCEKqoqV4BEHyBBEARBEKocUQESBEEQhCrKaIUmsMpaARIJkEC31xLp9moiftWKALh5xZEvPgwm/A8PAJ55JZFHe6RSu2Eeamc9Lz7Uiryc8t91vPw1DHo7gYcfz0apMhB/Q8my8dW5ck5d7rG8NPgmA8dFsWNLEJ+8G4ZvYAEbdx+747ILxzXg0C5f62w4VYfis3RkJwqgyIgxUI5mgg/GOkoAFEtTkO/OtXiJvoUjmoX+5ufyLzKRHs9Hel0DcgmF39awTmzce19ydtPy+pgYHuqQiU+ghqx0OUf2eLJ5RXXyc623PzVqkMSLz0cQVjsdL88C5izsxJFjweb5E8b8yZNPXLd4TfipAGbMecL8fPb0fYTWzMDdrZDcXAdOnw3gs83NSU+3zb720uBoBo6/wY7NQXzybi0ARs2+TPM2mXj6aijMlxFxxpUNy2oSG2WbGLr2jqfbqwn4Bd367K6q+XJ1dcIPegLg4a1h0KQomrXLQO2kJzbKke0fV+fwLm+bxFMaL49MYtDbCXz3qTdr36lmtzgq0rHpQRkBo7Hs66iMRAIkkJrowIalNYi7oUIigc7PJzNrzSVGPduU6KtqlI4Gwv9wJ/wPd96YZJ+7XTu76Vi+4wrn/nRhRt9QMtPkBNUsIjer/O90HdYom2deSuB6pJN5Wmqiij6d2los9/RLCfQaGEP4IU/rbDhHj3J8AoYmKorm+4O7FEmcFpwtW7L1LR3RTPjbSUnxj19nOiP6R5ww1Fci/80yWSqre+1LEokRTz8Nn74XQvRVNb6BRYyaew0vXw0LRtezWgwqlY6oGx7s2luLWdP+uOMyJ04GsnxV8eel1Vq+h2f/8mfb141Iz3DEy6uAIQNPMmPKH4yf8rTV4rwtrFEOz7ycwPVLThbTr15wYf+PviQnqHBx09Jn5E3mf/oXbzzZCoPB+r+4U5OUbFhWk/ibjkgkRp54LpmZqyMY/UJzoq86MeG9SJxcdMx9syHZGXIe7Z7C1BUXeevF5ly/6Gz1eO6nTtN8uvVN43qEqty3/XcV6dgkPBiRAFVgs2fPZseOHZw5c8am2zn2u+UJetOKGnR7LYl6zXKIvqpmx8ZAABq3yrJpHPfy8pvJpMY7sGx8dfO0pBhlucehUuuY/N5FVr1Th97DbpqnGwwSMlIt42n3RCoHd/pQmG+dr5n8qyyM3jK0E33M04z+ipILKiTgefdt6vqZKnuyXTlWievv7rUv7frGjwWjihOdhGgVm5ZXZ/KyK0hlRgx665zUw08FEX4q6J7LaLVSMjId7zr/ux/qm/+fnOLMV/9ryKxpB5DJDOj11us6qVLrmbz40q39yfLHxc6vA4pjiFexeVUIH+04hW9QIYkxd4/93zq+z8vi+eaVIXTrnUC9pjlEX3WifrNsVs+pzeW/XADYtrY6zw2II6xhbrknQCq1nikf3mTl5GBeHZNYrtv+p4pybPq3DEiQVNGRoEUnaMGCVGqkU7dUVGo9l8642DscszZPZXH5nJrpH0ex/ex5Vv8WyTOvpZV7HG/OuMLxP7w4c/TeVZ3aDXKoVT+XXd8G3HO5ByE7mo+xjhKH+UmoXr6J8s04ZL9kl1hOeq7QNH9QLIpVqZCtt1oMD6I0+5KTi578XJnVkp/SatIoiW2bvubTj75n1PBjuLgU3XVZZ+ciHut0g4uXfKya/MCt/emAJ2eOeNxzOaWjniefTyIhRkVqou1PrlKpkUe6JqNS67l467O7eMaVR7qm4uymRSIxzXdwMHDuuJvN4/mnUQtjOb7XldMH7X+MqijHpn/r9lVgZX1URqICZGMGg4GlS5fyySefEBMTg5+fH8OGDWP69OlMmTKF7777jtjYWPz9/enTpw+zZs1CoVCwceNG5syZA4BEYtq5NmzYwIABA0pso6ioiKKi4gN4dnbJk+L9hNTJY/lXf+GgNFCQL2Pem/WIvlpx2q8Dqmvo/noq367zYdsqP+o0y2fE3Fi0Wgl7vrZSE9N9PPJMErXr5/LWKw/dd9mneiUQfU3NxTPWOzlIEnTIfspB94Ir2t7uSC8XoViTDgoJ+idNJwJDS0f07dUY/RVIErQoNmSgnJ5I0cpAkJXPQaq0+5Krh5ZXR8bw6za/conrtvDTgRw+GkxikjMB/rkMeP0M82f9zrgpXTAYihOcN/qdome3SFQqPRcveTNr/mNWjeORZ5Kp3SCXt16++/7UrXc8b0y8jqPaQMx1R6YPboxOa7vfrSF18lj25Zniz25UA2KumZrmFo2tz9QVF/nq2FF0WglFhVLmjW5AQrT1q1H30qlnBrUbFTC6W51y3e7dVIRjk/DviATIxqZNm8a6detYsWIFHTp0ICEhgUuXLgHg4uLCxo0bCQwM5K+//mLIkCG4uLgwefJkXnnlFc6fP8/OnTvZs2cPAG5udz6ZLlq0yJws/VuxUY6M7NkUJxc9HZ5OY8LiK0zu06jCJEESKVw558iGd03NcdcuqAmpW0i311PL5SDj7V/IsKlXmT6kKVrNvdv2HZR6Hu2axJdrQ6wbhNGIIUyJ7g3T36uvrUR6Q4v85xxzAqR/tLgpwljTAU1NB1QDYpGeK8TQvHxOVKXZl9TOOuasu0j0VTWffxB8j7VZ34GDIeb/37jpQdQNdzZ+8j1NGiVx5lxxxe6b7xrw257a+Prk0bf3OSaNPcyseY+BFcr93v6FDJt2jemDG6PV3D2h2feTL6ePeODpXcQLA2OZtvwiE/s0u+dryiI2ypFRzz+Ek4uODl1SmfBuJJNfb0LMNSdef+sGzi56pg1oRHaGgrad05i24iKT+zblxmWn+6/cCnwCNYyYG8e0V2uhLaoYDRj2PjaVlcEoQSIGQhSsLScnh/fff58PP/yQ/v37A1CrVi06dOgAwIwZM8zLhoSEMHHiRLZt28bkyZNxdHTE2dkZuVyOv7//Hdd/27Rp0xg/frz5eXZ2NsHBD3ZS0Wml5l9yVy84U6dxLs/2T+CDmbUeaD22kp4s5+Zly86OMVdVdOhaPv2Swhrk4OGt5YOvw83TZHJo1DKLHq/G8WzzTuaOqR2eSkHpaGDvD9atbBg9ZRhrWPb5MQQrkB3Ku/trAhQY3aRI4rVQTgnQ/fYlRyc98z67SEGuqTqk19n3RJaY5EJmlpLAgByLBCg7R0V2joq4eFdiYl35fP131K+bysVIn3usrXTCGuaa9qdvTpmnmfen1+J4tllHDAYJ+bly8nPlxN905NI5V7468iftOqdy4BcrXVX4D5afnQthjXJ5tl8833xajZ59Exje/SGir5qSnahIZxq2yKb7a/F8ODvMJvH8U+3G+Xj46Fi9M9I8TSaHxm3y6Dkgle41m9qkg/i92PvYVFZGoxWuAqukl4GJBMiGLl68SFFREU888cQd52/fvp1Vq1Zx7do1cnNz0el0uLq6PvB2lEolSqV1+wVIpEYUDgarrrMsIk44EVzLsp9GUGgRyXF36ARsA2eOejDi2ZYW08YtiCT2upqvPwu2OOg+9UICx/Z5kZ3hYNUYDA1USGK0FtOkcVoMvvf4GqfoINuA0dN+V6T8fV9SO+uYvz4CrUbKnOH1bFbJeBDeXnm4uhSRnnH3BPFWKzQKhXX6U5054s6Ini0spo1bEElslJqvPw2++0lcQrl+L6W3PjuVo2mbxn/EZTCYKiDl5cwhF4Y+Xtdi2oTl0cRcU/HVat9yT37A/scm4d8TCZANOTre/YB65MgR+vTpw5w5c+jSpQtubm5s27aNZcuWlWOEJgMm3CT8D3eS45WonfQ82iOVJq2zmfFGA8A0/oeHj5bAGoUAhNTNpyBPRnK8A7lZ5fMl/3adLyu+v0zv0Un88aM7dZvl07VPGisnl8/YHwX5cm5etbzSpTBfSnaW5fSA6vk0apnFOyMaWz0G3QtuKMfFI/8yE/0jTkgji5D9koN27K1L3gsMyD/PRN9BDR4yJAk6FJ+mYwyUY2hR3PwkSdZBjt70r8GI5Jrp4G0MVIBj2c5m99qX1M46FmyIQKkysGRiHdTOetTOpoQiK11htZOXSqUlMKD4Cjd/v1xCa6aTk6MkJ9eBvr3PcejP6mRkOhLgn8Og/qeJT3Dh5ClTE0bdOqnUqZ3GhYs+5OY6EOCfS78+Z4lPcObipbJXf+D2/mR5+C0skJGdqeDmVSf8qxXwyDMpnDrsQVaGAm+/Il4aHIOmSMqJP2zTrDJgfBThf3iSnHDrs+ueTONWWcwc3IiY647E3VAxes4VPl0cSnamnLad02jeLpPZwxvaJJ47KciTcTPS8rhamC8lJ6Pk9PJi72NTWVXlW2GIBMiGwsLCcHR0ZO/evQwePNhi3p9//kmNGjWYPn26edrNmzctlnFwcECvt/0VPO5eWiYuvoqnr4a8HBlRl5yY8UYDTh92B6Drq4n0HRNrXn7pl+cBWDalNnu+tU0p/p8un1Uzd3BNBk5NoM/YRBJjHFj7ThD7vqtYbexPPZ9IapKSU4etH5exrhLNLD8UG9KRb83E6C9HO9wT/eO3EjApSKM0yHfnQJ4Bo5ccw0OOaPt7gEPxAUq+OcNisETVm/EAFC32x9C0bCeRe+1LjVtlUa+Zabvr956yeF3/Rx8iOc4647nUqZ3G4gV7zM+HDToJwO69oXywthU1QzLp/Nh1nJy0pKc7cvJMAJu3NkWrM1XJiopktG8bzeuvnkWl0pGe4Uj4qUAWftXRvIytaYqkNGyRxbOvx+HspiMzVcH5k25MeK0ZWenWrSze5uapZcJ7kXj6aMjLkRMV6cTMwY04/afpCrV3hjVi4IQo3llzAUe1nvhoR5ZPrUO4jRKyyqKyHJvupionQBKjsbK23lUOc+bM4f3332flypW0b9+elJQULly4gI+PD7169WLLli08/PDD/Pzzz8yZMwe9Xk9mZiYAX3zxBUOHDuXQoUNUq1YNFxeXUjV1ZWdn4+bmxuNOryKX2OZg+W8Y8vPtHUIJMnd3e4dQQu42d3uHUILTC8n2DqEEY4NQe4dQgvSKfQYKvSdDxTvE63OsPwbVf4nOqGW/cQdZWVn/qltEadw+T9T9Yioyddm6UOjzi4h87d1SxxsXF8eUKVP49ddfyc/Pp3bt2mzYsIGWLU3dDIxGI++88w7r1q0jMzOT9u3bs2bNGsLCivuapaenM3r0aH788UekUim9evXi/fffx9m59GNS2b8B/j9u5syZTJgwgVmzZlG/fn1eeeUVkpOT6dmzJ+PGjWPUqFE0a9aMP//8k5kzZ1q8tlevXjz99NM89thj+Pj48OWXX9rprxAEQRCEssvIyKB9+/YoFAp+/fVXIiIiWLZsGR4exWNhLV68mFWrVrF27VqOHTuGk5MTXbp0obCw0LxMnz59uHDhArt37+ann37ijz/+YOjQoQ8Ui6gA/QeJClDpiQpQ6YgKUOmIClDpiArQvZVnBajOVutUgC73KV0FaOrUqRw+fJiDBw/ecb7RaCQwMJAJEyYwceJEALKysvDz82Pjxo307t2bixcv0qBBA06cOGGuGu3cuZOuXbsSGxtLYGBgqeIWFSBBEARBqKJMl8GXdSRo07qys7MtHn8foPe2H374gZYtW/LSSy/h6+tL8+bNWbdunXl+VFQUiYmJdO7c2TzNzc2N1q1bc+TIEcB0EZG7u7s5+QHo3LkzUqmUY8fufFPqOxEJkCAIgiAIZRYcHIybm5v5sWjRohLLXL9+3dyf57fffmPEiBGMGTOGTZs2AZCYaLq3m5+f5Thqfn5+5nmJiYn4+lpegCOXy/H09DQvUxriKjBBEARBqKKseRVYTEyMRRPYnS7aMRgMtGzZkoULFwLQvHlzzp8/z9q1a80DBpcXUQESBEEQhCrKaKUHgKurq8XjTglQQEAADRo0sJhWv359oqNN/edu3/kgKSnJYpmkpCTzPH9/f5KTLfsl6nQ60tPT73vnhL8TCZAgCIIgCOWiffv2REZGWky7fPkyNWrUAKBmzZr4+/uzd+9e8/zs7GyOHTtG27ZtAWjbti2ZmZmcPHnSvMzvv/+OwWCgdevWpY5FNIEJgiAIQhVV3gMhjhs3jnbt2rFw4UJefvlljh8/zieffMInn3wCgEQiYezYscyfP5+wsDBq1qzJzJkzCQwM5LnnngNMFaOnn36aIUOGsHbtWrRaLaNGjaJ3796lvgIMRAIkCIIgCFXX39uwyrKOUnr44Yf57rvvmDZtGnPnzqVmzZqsXLmSPn36mJeZPHkyeXl5DB06lMzMTDp06MDOnTtRqYpHi9+6dSujRo3iiSeeMA+EuGrVqgcKWyRAgiAIglBVWaECxAO+vnv37nTv3v2u8yUSCXPnzmXu3Ll3XcbT05Mvvvjigbb7T6IPkCAIgiAIVY6oAAmCIAhCFWUaCLHs66iMRAIkCIIgCFVUVb4bvEiA/sv0epDo7R1Fscr6M6GcOffLs3cIJYTu19k7hBKudrhs7xBKMMpk9g6hBIlL6e+OXW5yK94+jkEcK6sakQAJgiAIQlVllDxwJ+Y7rqMSEgmQIAiCIFRRVbkPkLgKTBAEQRCEKkdUgARBEAShqirngRArEpEACYIgCEIVJa4Cu48ffvih1Cvs2bPnvw5GEARBEAShPJQqAbp9A7L7kUgk6PUV6FJCQRAEQRDurZI2YZVVqRIgg8Fg6zgEQRAEQShnVbkJrExXgRUWFlorDkEQBEEQypvRSo9K6IETIL1ez7x58wgKCsLZ2Znr168DMHPmTD777DOrBygIgiAIgmBtD5wALViwgI0bN7J48WIcHBzM0xs1asSnn35q1eAEQRAEQbAliZUelc8DJ0CbN2/mk08+oU+fPsj+dt+bpk2bcunSJasGJwiCIAiCDVXhJrAHHgcoLi6O2rVrl5huMBjQarVWCUooXy+PiKN9lwyqhRagKZQSccqF9e8FExflaF5m9PwomrfPwtNPQ2GejIhTzqx/rzqx1x3vsWbradQ6l5feTCGscT5e/jpmvxHCkZ1u5bLtO3lp8E0Gjotix5YgPnk3zDy9XtMs+r8VRd3G2RgMEq5fcmbG0CZoimxzk0wvn0IGvnWFlu3TUKr0JMSoWTG7AVcibr83RvqOuMbTz8fh5KIj4qw7qxfWIz7aySrbj+pZhC6h5HS3F6X4TlGQtFBLwXEDulSQOoKqiRTv0TIcQop/e+UfN5C2VkfRNSNSFbh2l+E1QoZEbr1flY1aZfPi0ETCGuXh5adlztAwjuz2MM9399YyaEoMD3XMwslVz/njLnw0uwbxN1RWi+HvXh4eR/un0kzfuaJb37nFNSy+cwHVCxk89QYNW+agcDAS/oc7a+aEkJnmcI81l42996fSkEqN9B2fwBMvpOPhqyUtUcHur7344n1/7FmJ6DEglRdHJOPpo+N6hCMfzQgi8ozabvEI9/fAFaAGDRpw8ODBEtO/+eYbmjdvbpWgKqtHH32UsWPH2juMB9a4VQ4/bvFjXK+GvN2vHnKFkQWbL6F0LB7S4Op5J5ZPDmXok02ZPqAeEgks2HwJqbR8Un+V2sD1Cyo+fLtauWzvXsIaZfPMSwlcj7Q86NdrmsW8j89x6k8PxvZuwVuvtODHL4IwGGxzUHZ20bJ04wn0OimzRjVneK92rFteh5xshXmZFwfcoOerMXy4sD7j+rWisEDGvNWnUThYZ7iK4E0O1Py1+BH0oWnbzp1NCZ+qnhS/WQpqfOVA4AcKMELcKC1GvWm/KbpsIH6sFnVbKdU/d8B/oYLcPwykfmjd4TRUjgaiLqpZPavGHeYaeefjy/hXL2LO0DBGdW9IcpwDiz63/A5YU+NWWfz4uT/jXmrM2/0bIJcbWbAxwrw9paOeBRsjMBolTO3bgAkvN0SuMDD7k0tIJLb5zlWE/ak0Xn4zie79Ulg9I5ghjzbgs0VBvDQiiWffSCm3GP6pU88Mhr4Tz9bl/ozsUofrESoWfHEdN69KUBQQFaDSmzVrFv379ycuLg6DwcC3335LZGQkmzdv5qeffrJFjIKNzRxYz+L58kmhbAs/RVijPM6fcAXg122+5vnJcUo2LQ9mzS9/4VetiIRo2/xK/rvwfa6E73O1+XbuR6XWMfm9i6x6pw69h920mDd0ylV+2FqNrz8tPsnG3bDdL8AXB94gJVHFitkNzdOS4v9ekTPy3GvRbFtXk6P7TZ/fspkN+WLPH7R9LIU/fvMvcwxyD8vkLmOTHkU1cHzINN3theLKlyJQgtcIiH7NgDYBHKpBzm4DDrUleA0xHYocgiV4j5aR+LYOryEypE7WSR7DD7gTfsD9jvOCahZS/6E8hj3ViJtXTJ/XBzNC+PL4aR7rmcbO7b53fF1ZzHyjgcXz5VNqs+14uPk717BFDr5BRYzq2YT8XNN7s2xSbb4+dYKmbbM48+ed/5ayqAj7U2k0aJnLkV3uHP/dVJVKilXy2LMZ1G2WVy7bv5MXhqay8wtPdm33BGDVlGq0eiKbLq+m89WHfnaLq1Sq8N3gH7gC9Oyzz/Ljjz+yZ88enJycmDVrFhcvXuTHH3/kySeftEWMwi0ajaZctqN2Mf2ay8m6c36sdNTz1IspJEQrSUmwXTm+InpzxhWO/+HFmaOeFtPdPDXUa5pDZpqCpZ+fYuuBw7y38TQNHsq0WSxtOqVwJcKVaYvP8sXe/Xzw5VG6PB9rnu8fVICnj4Yzx7zM0/JzFUSed6V+E+vHZdQayf5Vj2tPGRJJyQOiocBI9o8G5IGguHVOMGpAorRcTqqUYCyCwkvl87NS4WDajqao+HBoNErQaqQ0bJlbLjGoXXQA5GTKb8VkACNoNcUxaTVSjAZo2DLHJjFUtP3pbiLCnWnWPoegmqZhWELr59Pw4VxO7LNPk7hcYSCsST6nDrqYpxmNEk4fdKFBi3y7xCSUzr8aB6hjx47s3r2b5ORk8vPzOXToEE899ZS1Y6vQ8vLy6NevH87OzgQEBLBs2TKL+UVFRUycOJGgoCCcnJxo3bo1+/fvt1jm0KFDdOzYEUdHR4KDgxkzZgx5ecW/YkJCQpg3bx79+vXD1dWVoUOH3jGWoqIisrOzLR7/lkRiZNjMm1wId+bmZcvqRbe+SXz71wl2XAinZadMpverh05bpqGkKpVHnkmidv1cNq6oWWKef7UCAPqMvMFv3wQwc1gTrl50YdFnZwmsbpuDoH9QAd1eiiU+Ws2MNx/i56+rMXxyJE/0iAfAw9uUMGekWyapmWlKPLysn0zn7jdgyDX14bHY3td6rj5SxLVHNOT9aSBotQMShSlBUreVUnjOSM5veox6I7pkI2mfmZIBfWr5JEAx11QkxTkwcHIszq465AoDLw2LxydQg6ev7X90SCRGhk2/wYVwF3MF6tIZFwoLZLwx6SZKlR6lo57BU28ik4Onj21iqmj7091sX+3HgR88+PRABD9HnWL1b5f47lNf9n3nef8X24Crpx6ZHDJTLH8wZqTK8fDR2SWmB2E0WudRGf3rs1d4eDhbtmxhy5YtnDx50poxVQqTJk3iwIEDfP/99+zatYv9+/dz6tQp8/xRo0Zx5MgRtm3bxrlz53jppZd4+umnuXLlCgDXrl3j6aefplevXpw7d47t27dz6NAhRo0aZbGdpUuX0rRpU06fPs3MmTPvGMuiRYtwc3MzP4KDg//13zVy7g1C6uTz7piSHd33fe/FqB6NmfRKfeKiVEz74Irpl2oV4O1fyLCpV1k8pT5aTckOzdJb36Rfvwpk944Arl9yYd17tYmNUvPUC4k2iUkiNXL1kgubPgzjeqQrO7+txs7vguj6Yuz9X2wD2T/ocWorRe5jWf1xeUZK9c8VVPtYgUN1CYnTtBiKTEdMpzZSvMfISF6k42p7DTd6aXBqd+vNLKequl4nZd7wMIJqFvLN2VN8HxFO07Y5HN/nZrP+W383cnYUIXUKeHdscWf6rHQFC0fXofUTGXx77jj/O30cJ1cdV847YbRRTBVtf7qbR3pk8Pjz6bw7KoSRz9Rn6bgavDg8ic4vptk7tMpJ9AEqvdjYWF599VUOHz6Mu7s7AJmZmbRr145t27ZRrZr9O6naWm5uLp999hmff/45TzzxBACbNm0y/+3R0dFs2LCB6OhoAgMDAZg4cSI7d+5kw4YNLFy4kEWLFtGnTx9zp+mwsDBWrVpFp06dWLNmDSqVqV/N448/zoQJE+4Zz7Rp0xg/frz5eXZ29r9KgkbMvkGrxzKZ1Ls+qYnKEvPzc+Tk58iJv6Hi0hlnvj59knZd0jnwo/cDb6uyCWuQg4e3lg++DjdPk8mhUcsserwax5DurQGIvmZZNYu5rsYnwDYjpmekKom5btkROybKifZPJN+ab/ql7uGpISO1+PN09yrieqQL1qRNMJJ/3EjA4pLJocxZgsxZAtVB1VjCtcc15O034NLFtKxHHznur8nQp4LUBXQJRtJW61EElV+/gqvnnRjZrRFqFx0KhZGsdAUrv7vAlb9se3XTiHeu0+rxDCa92rDEd+7UIXfeePwhXD206HUS8nLkbD0STkJMye+mNVSk/elehsyIY/tqfw78YKr43LjkiG+Qht6jEtnzjdd9Xm192eky9Dpw/0e1x8NbR0bKA59ihXL0wJ/O4MGD0Wq1XLx4kbp16wIQGRnJwIEDGTx4MDt37rR6kBXNtWvX0Gg0tG7d2jzN09PT/H789ddf6PV66tSpY/G6oqIivLxMX9CzZ89y7tw5tm7dap5vNBoxGAxERUVRv359AFq2bHnfeJRKJUplWQ6KRkbMvkm7p9KZ8loDkmLv36lZcmvsq9v9J/7rzhz1YMSzlp/FuAWRxF5X8/VnwSTGqEhNcqBazQKLZYJCCgg/aJvSfMQZd4JqWDavBVXPJznB9PklxjmSnuJA09ZpXL9sOkE5Oumo2yibn7/+91XCO8n+UY/MA5za37uobLz1a9H4jxYTiUSC3Mf0/5zf9Mj9QFmv/DtW5ueYDomBIYWENc5j83Jb/aAzMuKdKNo9mc6UPg3v+Z3LzjBdhdW0TRbuXlqO7v3v70/3onQ0YPxH4dmglyCxU2u8Tivlyjk1zTvkmIfmkEiMNOuQyw8byz8he2BVuBP0AydABw4c4M8//zSf7AHq1q3LBx98QMeOHa0aXGWVm5uLTCbj5MmTFoNFAjg7O5uXGTZsGGPGjCnx+urVq5v/7+Rk+/E1Rs69waM905g7tA4FuVJzW39ejhxNkRT/4EIe6Z7GqYPuZKXL8fbX8PLweDSFUk7sd7d5fAAqtZ7AmsVnTf9gDaENC8jJlJESZ/uO2AX5cm5edbaYVpgvJTurePr/NgTTd+QNrkc6cf2SM52fTaJazXwWjGt4p1WW2XefV2fZxhO8/EYUB3f7UbdhFs/0imXVvNtXGEnY8UV1eg+OIj5aTVKcI6+/eY20FCVH9vlYLQ6jwUj2j3pcu1mO3aONNZKzW4+6jRSZhwRdkpGMTXokKlD/LVHK2KJD3VYKEsjdZyB9k56ARXIkMusdVFVqPYE1iitx/sFFhNbPIydLTkq8ko5d08lKk5Mc70BIvQJGzLrJkV0enDpom461I+dE8WiPVOYOr0tBnuxv3zmZecyoJ3slE3PNkax0BfWa5zB8xg2+2xBgMVaQNVWU/el+ju52o/eYRJLjHLh5WUWtRgW8MDSZXdvtl2x8+4k3E1fGcPmsmsjTap4fkoJKbWDXNvv0S3oQEqPpUdZ1VEYPnAAFBwffccBDvV5vbu75r6tVqxYKhYJjx46Zk5WMjAwuX75Mp06daN68OXq9nuTk5LsmhQ899BARERF3HFSyvHXvaypxL9520WL6skmh7PmfD5oiKY0ezuG5gYk4u+rJTFVw/oQL419sQFaa4k6rtLo6TQtY8r9r5ufD55g6Zu7a7sGycdXv9rJy9f2WYByUBoZOvoaLm5brkc5MH9KExBjbnLCuRLgxf0JTBoy+ymtDr5MY58jHS+qy/9cA8zLfbAxB5ahn9IyLOLvouHDGnVkjm9+xH9O/lX/ciC4RXHta/gSXKKHgjJHMbVr02SD3BMfmUoI/VSD3LE5u8v40kL5ej1ELyjAJgUvlOLW37sCRdRrnsXhb8Uj1w2ZGA7D7G2+WTQrF01fD0OnRuHtrSU9RsPdbb774wHbHs+59kgBY/EWExfRlk2ux51vTJebVQgsYMDEaFzcdSXFKtq0J4rv1ASXWZS0VZX+6n49mBtN/UjyjFsbg7m0aCPGXz73ZurJ8LsO/kwM/eODmpaffpEQ8fHRcv+DI9D41yUwtn+NjmVijD08lTYAkRuOD9d/+/vvvWbhwIatXrzY3z4SHhzN69GimTJnCc889Z4s4K5wRI0bw66+/sn79enx9fZk+fTq///47gwYNYuXKlfTt25fDhw+zbNkymjdvTkpKCnv37qVJkyZ069aNc+fO0aZNG9544w0GDx6Mk5MTERER7N69mw8//BAwXQU2duzYBx5cMTs7Gzc3Nx5XvYxcUnEuUzcU2qYvTFnIPDzuv1B5c6h4B83Qn7LsHUIJVzvYO4KSJLLySwRKS+LifP+Fypk+pQJ2WDaU32CO96MzatnP92RlZeHqapvxz26fJ4JXzkXqWLax3AwFhcSMnWXTeG2hVBUgDw8Pi3E98vLyaN26NXK56eU6nQ65XM4bb7xRZRKgJUuWkJubS48ePXBxcWHChAlkZRWfJDZs2MD8+fOZMGECcXFxeHt706ZNG7p37w5AkyZNOHDgANOnT6djx44YjUZq1arFK6+8Yq8/SRAEQahqqnAfoFJVgDZt2lTqFfbv379MAQllJypApScqQKUjKkClIypApSMqQPdWrhWg5fOsUwEaP/O/WQESSY0gCIIgCP8lZRqkoLCwsMTtGSpT9icIgiAIVVoV7gT9wCMn5OXlMWrUKHx9fXFycsLDw8PiIQiCIAhCJVGFR4J+4ARo8uTJ/P7776xZswalUsmnn37KnDlzCAwMZPPmzbaIURAEQRAEwaoeuAnsxx9/ZPPmzTz66KMMHDiQjh07Urt2bWrUqMHWrVvp06ePLeIUBEEQBMHaqvBVYA9cAUpPTyc0NBQw9fdJT08HoEOHDvzxxx/WjU4QBEEQBJu5PRJ0WR+V0QMnQKGhoURFRQFQr149vvrqK8BUGbp9c1RBEARBEISK7IEToIEDB3L27FkApk6dyurVq1GpVIwbN45JkyZZPUBBEARBEGykCneCfuA+QOPGjTP/v3Pnzly6dImTJ09Su3ZtmjRpYtXgBEEQBEEQbKFM4wAB1KhRgxo1algjFkEQBEEQypEEK9wN3iqRlL9SJUCrVq0q9QrHjBnzr4MRBEEQBEEoD6VKgFasWFGqlUkkEpEAVSCGIg2Gyto9v7wYDfaOoARDNR97h1DC1Q4V715g6t0Vb9T5/Mcz7B1CCZKiInuHUFIFuu+WmbQC3cfNaIDyOjRV4cvgS5UA3b7qSxAEQRCE/xBxKwxBEARBEISqo8ydoAVBEARBqKSqcAVIJECCIAiCUEVZYyTnytrVVDSBCYIgCIJQ5YgKkCAIgiBUVVW4CexfVYAOHjxI3759adu2LXFxcQBs2bKFQ4cOWTU4QRAEQRBsqArfCuOBE6D//e9/dOnSBUdHR06fPk3RrTEmsrKyWLhwodUDFARBEARBsLYHToDmz5/P2rVrWbduHQqFwjy9ffv2nDp1yqrBCYIgCIJgO7c7QZf1URk9cB+gyMhIHnnkkRLT3dzcyMzMtEZMgiAIgiCUhyo8EvQDV4D8/f25evVqiemHDh0iNDTUKkEJgiAIglAORB+g0hsyZAhvvfUWx44dQyKREB8fz9atW5k4cSIjRoywRYyCIAiCIAhW9cBNYFOnTsVgMPDEE0+Qn5/PI488glKpZOLEiYwePdoWMQrlrO/4BF6fkGQxLeaqksGd6tspIujeL5Vu/dLwC9YAcDNSxdYVfoTvs88NMV8aHM3A8TfYsTmIT96thbOblr6jbvJQuwx8AorIylBwZK8XW1aFkJ9rvdEmGjVM5sUXIgirlYGXVwFzFnTkyNHgOy47+s3jdHvmKmvXPcSOH+qVmK+Q61m57DdqhWby5phnuB7lUeb4XhkRT/suGVSrVYCmUErEKWfWvxdM7HVHAJzddLw+LpYWHbPxCSwiK03Bkd0ebFoeRH6O9d4nQ4oezdo89Mc0UGhEEiRDOc0FWT1Tv0VjugHN2lz0J7QYcw3ImipweMsZaXBxDEVLctCf1GBMNYCjBFkjBQ7DnZDWsE6cjVrl8OLwJMIa5+Plp2XO4Foc2eUOgExupP+kOB5+LIuA6hrycmScPuTC+neDSE9ysMr27+ef+7glI3M/Pk/LjhnMG92AI3u9yyUmgEatc3npzRTT++avY/YbIRzZ6VZu2/8nqdRI3/EJPPFCOh6+WtISFez+2osv3vcHKn7TUFUeCPGBv8kSiYTp06czadIkrl69Sm5uLg0aNMDZ2dkW8f0nPProozRr1oyVK1faO5RSu3FJxdTexQc9vc6+X+SUBAXrFwYQF6VEIoEnX0pn9oYbjHyqDjcvq8o1lrBGOTzzcgLXLzmZp3n5aPDy0fDpklCir6nxCyxk1DtX8fLRsHBcA6ttW6XSERXlwa7dtZg1/eBdl2vXJoZ6dVNJTXO86zKDBp4mLd2RWqGZVouvcescftziy+VzTkjlMHBiDAs2RzL0ycYUFcjw8tPg5atl3cJgoq844hukYfSCKDz9NCx4M8wqMRhzDBSOzETWXIFqsRsSdymGWD0SF1PB22g0Ujg9C2QSlAtdkThJ0G4voHB8Fo6bPZE4mvZ1aV058ieVSPxkGLMNaDfkUzghC8ftnkhkZf8+qNQGoiIc2bXdi1nrrlvMUzoaqN0ony9WBRAVocbZTcfw2THM/uwaY7rb/ofInfbxv3uuXxxGO530VGoD1y+o+O1LT95Zf8M+QfzNy28m0b1fCkvHhnDzsoqwpvlMWHaTvBwZ36/3tXd491eFxwH61z9lHBwcaNDAegd2oWLR6yEjRXH/BcvJsd2Wv/A2vhdA935p1GuRV64JkEqtZ/LiS6x6pw69h0Wbp9+86sSCscXfh8QYRza9H8Kk9y4hlRkx6K2TQIafDCT8ZOA9l/HyzGfEsHBmvPMYc2cduOMyLVvE81DzROYv6kirlj9bJTaAGQPqWjxfNimU7SdPE9Y4j/PHXbl5Wc38vyU6CdEqNi0NZtLya1Z7n7Rb85H4SlFOK64OSgNl5v8bY/UYLuhw3OSBtKbpEOgwwZn859LQ7S1E0d2UNCp6/i15DJAhGeJEwcAMjIkGJEHF6/u3wve7Eb7/zpWL/BwZb/epYzHto5nVWfXTJXwCNaTE264KdLd9/LbQerm8MCCWt15+iK1/HLVZHHcTvs/VbpXfO2nQMpcju9w5/rvps0yKVfLYsxnUbZZn58iE+3ngBOixxx5DIrn7Qer3338vU0BCxRBUU8MXJ8+jKZJy8aQT6xcF2PSg+yCkUiMde2SiVBu4GH7nX6i28uaMKxw/4MmZIx53PDn8nZOzjvxcudWSn9KQSIxMGn+Eb76tz81o9zsu4+5ewFujjjF3wSMUFZX9RH4vahc9ADmZdz/UOLnoyM+VWe190h3WIGvlQOGsLPRntEh9ZMifU6HocSuh0dxa0KF4exKpBIlCguGcFrqXrJoZC4xofylEEiBF4mufOwg5ueoxGCAv27af2b32caVKz+Qll/hofm0yUivG8cDeIsKdeaZPKkE1C4mLUhFaP5+GD+fy8dxq9g6tdKxxGXslrQA98De5WbNmNG3a1Pxo0KABGo2GU6dO0bhxY1vEWKnk5eXRr18/nJ2dCQgIYNmyZRbzMzIy6NevHx4eHqjVap555hmuXLliscy6desIDg5GrVbz/PPPs3z5ctzd3e+6zaKiIrKzsy0eZXHptBNLx1Vnet9afDCtGv7Vi1j23RUcnfRlWm9ZhdQrYMeVv/jpxjnGvBvL3EEhRF8pv+rPI88kU7tBLhtX1Lzvsq7uWl4dEc2vX/uXQ2TFXu4Vgd4g4fsf695lCSMTxh7ll1/DuHLVy6axSCRGhs+8yYUTzty8rL7jMq4eWl4dHc+v23ystl1jgh7d9wVIq8lQLXVD/qwKzfu5aH8tNMVVQ4bET4rmkzyMOQaMWiOarfkYUwwY0wwW69J+V0BelxTyu6SiP6ZBtdwdiaL8m4MVSgNvTItj//ee5OfaLgG63z4+ZOo1Lp525ejv5dfnp6LbvtqPAz948OmBCH6OOsXq3y7x3ae+7PvO096hlU4VvgrsgStAK1asuOP02bNnk5ubW+aAKrtJkyZx4MABvv/+e3x9fXn77bc5deoUzZo1A2DAgAFcuXKFH374AVdXV6ZMmULXrl2JiIhAoVBw+PBhhg8fznvvvUfPnj3Zs2cPM2fOvOc2Fy1axJw5c6z2N/y9vBx10ZFLp9VsORbBIz0y+W2bbU+a9xJ7TcmbT9ZB7aKnY/csJr4fzaQXapdLEuTtX8iwadeYPrgxWs29fzc4OumYs/Y80dfUbF1dw+ax3Va7VjrP9oxk1NinuVvny2d7XEbtqGP7N7Zvvh459yYhdQuY8NKdt6V21jN3/WWirzjy+cog623YYOq/4zDU1C9RVkeBIUqP7ocCFM+okMglKOe7onkvh/xuaSADWQsFstYO/PNILn9SiaylAmOaAe22AoreyUa12h2JsvySIJncyPSPriPByIfTq9tsO/fbx1s/lkbT1pmM7tXCZjFURo/0yODx59N5d1QINy87UqthPsNnx5KWpGDPN/Y7Xgr3Z7XLLvr27UurVq1YunSptVZZ6eTm5vLZZ5/x+eef88QTTwCwadMmqlUzlUJvJz6HDx+mXbt2AGzdupXg4GB27NjBSy+9xAcffMAzzzzDxIkTAahTpw5//vknP/300123O23aNMaPH29+np2dTXDwna8M+jfysuXEXlcSGFJktXX+GzqtlPgbSgCu/qWmbrN8nhucwqop1vtb7yasYS4e3lo++KZ4tHOZHBq1zKLHa3E826wjBoMER7WOeZ+cJz9PxrzRDdHryq+5pFHDZNzdCtmy/vviGGVGhrxxmud7RtJ/8LM0bZJEvbqp/PjtdovXfrBiJ7/vD2HZyrZWieXNOTdo/XgmE1+pT2piyaYSRyc98zdGUpArY+6wMKu+TxIvKdIQy0ObtIYM/YHi/VdWV4Hjek+MuQbQgcRdSsGwDKR1LV8ncZYicZZCMEgbKsjvlor+YBHyzuVTeZTJjbz90XV8gzRM6V3HptWf++3jP28PJCC4kK+PHrZ43dsrI7hw0o2pA5raLLaKbMiMOLav9ufAD6aKz41Lps79vUclVo4ESHSCLrsjR46gUpXv1TgVzbVr19BoNLRu3do8zdPTk7p1Tc0RFy9eRC6XW8z38vKibt26XLx4ETCNtP38889brLdVq1b3TICUSiVKpdKaf4oFlVpPYA0Ne/9XcTpFA0gkoHAon2/emSPujOhp+ct33IJIYqPUfP1psCn5cdIxf91faDVS5o5seN9KkbXt3VeT02csm9wWzN3H3n012b3HNEjpmk9asGlLE/N8L68CFs7dx8LF7YmMtEazhpE359yk3VMZTH61PkmxJfdLtbOeBZsuodVImT0kzOrvk7SxAkOMzmKaIUaPxK/kdiTO0lvzdRgidSgG3aNP2a0ThVFrzWjv7nbyE1SzkCmv1LlnPypruN8+np2p4NftARbz1/xwknXv1eLYvkrS3GMDSkcDRsuWUwx6CRL7dBV7YOIy+AfwwgsvWDw3Go0kJCQQHh5+36YaoXIYMjOOo7vdSI5V4OWv4/UJCegNsH9H2ceJ+bcGTkvgxO8upMQ54Ois57HnM2nSLpfpr5XP6OMF+XJuXrX8uhQWyMjOVHDzqhOOTjoWfPoXSpWBJVPqoXbWo3Y29ZnKSldgMFinyUSl0hIYUNzU7O+XR2jNDHJyHUhJcSInxzLh0OukZGSoiI0zNWumpFie4AsLTX9TQoILqWl37qfzIEbOvcljz6YxZ2gYBblSPLxNPY7zcuRoiqSm5GfzJVSOBhaPq2WT90nxkiOFb2ai2ZKH/DEVhotadD8WoJzoYl5Gt68IibsEiZ8MwzUdmg9ykXVwQN7KVK0yxOvR/V6E7GEFEncpxmQD2q35oJQgb2Odzr8qtd6iquofXERog3xyMuWkJyuYsfYatRvlM2tgbaQy8PAxZV45mTJ0WuufXe+3jwN37PickqAkKe7uwy1Ym0qtJ7CmxvzcP1hDaMMCcjJlpMSVf8fso7vd6D0mkeQ4B25eVlGrUQEvDE1m1/ZKUP2p4h44AXJzs7xsUyqVUrduXebOnctTTz1ltcAqo1q1aqFQKDh27BjVq5va6jMyMrh8+TKdOnWifv366HQ6jh07Zm4CS0tLIzIy0jykQN26dTlx4oTFev/53Na8A7RMW30DFw89WelyLhx3YmyPOmSl2/YX6L24e+uYtCoaT18d+Tkyoi6qmP5aKKf+cLn/i8tB7Qa51GuaA8D63yw/rwGdW5Ecb53qaJ3a6SxetNf8fNhgU3PF7r01rdZ8VRY9Xk8GYMm2SxbTl02sye7/+VC7YR71m5suD95w4JzFMv07NCUpruyVTFl9BcoFrmg+zkO7KR+JvwyH0c7Inyr+DIxpejQfFmDMMCDxkiLvokLR/28JoAMYzmrRfp0POUYkHlKkTRU4fuSOxMM6yUedJvks/uqy+fmwd2IB2P21F5+vCKDtU1kArPntosXrJr9ch3NHK8Z+bw91mhaw5H/XzM+Hz4kHYNd2D5aNs10fqbv5aGYw/SfFM2phDO7epoEQf/ncm60ry/cCCOHBSYzG0g9npdfrOXz4MI0bN8bDw37VgIpsxIgR/Prrr6xfvx5fX1+mT5/O77//zqBBg1i5ciXPPfccV65c4eOPP8bFxYWpU6dy9epVi07QjzzyCEuWLKFHjx78/vvvTJ8+Hb1eT0ZGRqliyM7Oxs3NjUclzyGXVKBmK3uNnHYPMnf7jSB7N4ZaFfDy2fMl7/9nb+rdFWcsmNvyHy/dd7Q8SZ3Ld6iI0tBnZtk7hJKkth1e4EHojFr2G74lKysLV1fb7Oe3zxO1pi1EVsbuK/rCQq4tetum8drCA/2UkclkPPXUU+Ku7/ewZMkSOnbsSI8ePejcuTMdOnSgRYvidvUNGzbQokULunfvTtu2bTEajfzyyy8oFKZEpX379qxdu5bly5fTtGlTdu7cybhx46p8/ypBEATB+m73ASrrozJ64DaNRo0acf36dWrWvP9YKFWRs7MzW7ZsYcuWLeZpkyZNMv/fw8ODzZs333MdQ4YMYciQIRbPa9eubf1gBUEQBKGKeuDG7Pnz5zNx4kR++uknEhISrDoAn2CydOlSzp49y9WrV/nggw/YtGkT/fv3t3dYgiAIwn9RFRwEER4gAZo7dy55eXl07dqVs2fP0rNnT6pVq4aHhwceHh64u7uLfkFWcvz4cZ588kkaN27M2rVrWbVqFYMHD7Z3WIIgCMJ/jZ1Hgn733XeRSCSMHTvWPK2wsJCRI0fi5eWFs7MzvXr1IikpyeJ10dHRdOvWDbVaja+vL5MmTUKn0/EgSt0ENmfOHIYPH86+ffseaAPCg/vqq6/sHYIgCIIg2NSJEyf4+OOPadKkicX0cePG8fPPP/P111/j5ubGqFGjeOGFFzh82DQIp16vp1u3bvj7+/Pnn3+SkJBAv379UCgULFy4sNTbL3UCdPtisU6dOpV65YIgCIIgVFzWHAjxn91g7jVIb25uLn369GHdunXMnz/fPD0rK4vPPvuML774gscffxwwXTxUv359jh49Sps2bdi1axcRERHs2bMHPz8/mjVrxrx585gyZQqzZ8/GwaF040E9UB+ge90FXhAEQRCESsaKTWDBwcG4ubmZH4sWLbrrZkeOHEm3bt3o3LmzxfSTJ0+i1WotpterV4/q1atz5MgRwHTnicaNG+Pn52depkuXLmRnZ3PhwoVS/+kPdBVYnTp17psEpaenP8gqBUEQBEH4D4iJibEYB+hu1Z9t27Zx6tSpOw7ym5iYiIODA+7u7hbT/fz8SExMNC/z9+Tn9vzb80rrgRKgOXPmlBgJWhAEQRCEysmaTWCurq73HQgxJiaGt956i927d9t9fLsHSoB69+6Nr6+vrWIRBEEQBKE8lfPd4E+ePElycjIPPfSQeZper+ePP/7gww8/5LfffkOj0ZCZmWlRBUpKSsLf33R7EX9/f44fP26x3ttXid1epjRK3QdI9P8RBEEQBKEsnnjiCf766y/OnDljfrRs2ZI+ffqY/69QKNi7t/ieh5GRkURHR9O2rel+h23btuWvv/4iOTnZvMzu3btxdXU131ezNB74KjBBEARBEP4jyrkC5OLiQqNGjSymOTk54eXlZZ4+aNAgxo8fj6enJ66urowePZq2bdvSpk0bAJ566ikaNGjA66+/zuLFi0lMTGTGjBmMHDnyrv2O7qTUCZDBYCj1SgVBEARBqPis2QfIWlasWIFUKqVXr14UFRXRpUsXPvroI/N8mUzGTz/9xIgRI2jbti1OTk7079+fuXPnPtB2HvheYELlIZHJkEgqzh2OjXq9vUMoSVZx3p/bZEmZ9g6hBEMFbALPf6Li3VG8x7mk+y9Uzn5o6G3vEEqqQHdeNzNUoOOTsRxjKecK0J3s37/f4rlKpWL16tWsXr36rq+pUaMGv/zyS5m2+8D3AhMEQRAEQajsRAVIEARBEKqqClABsheRAAmCIAhCFVUR+wCVF9EEJgiCIAhClSMqQIIgCIJQVYkmMEEQBEEQqhrRBCYIgiAIglCFiAqQIAiCIFRVoglMEARBEIQqpwonQKIJTBAEQRCEKkdUgARBEAShipLcepR1HZWRSIAEQRAEoaqqwk1gIgESaNQqhxeHJxHWOB8vPy1zBtfiyC73Oy47euFNuvVNZe2cauz4zK/cYtx09AL+wdoS03/Y6M3q6dVsvv0+I6Lo8+YNi2kxUWqG9WyNs6uWviOjeKhtOj4BRWRlKDjyuzdbPgwlP9d2X7H1O/bhF1hQYvpPX1dnzZJGANRrnEG/EZep2zATg17C9SsuzBzTCk2RbW5G+fKIONp3yaBaaAGaQikRp1xY/14wcVGOFsvVa55D/wmx1GuWi0EP1y46MaN/PTRFtmmVb9QqhxeHJRTv40Nqc2SXh3m+Sq3njamxtH0qA1cPHYkxSr7f4McvW32tsn2jHiJXOxL7o5LCVCkqXwPBzxVRZ3gBt+8zazRC5IeO3PxahTZHgmdzLU1m5eEcYjCvR5Mp4a8FTiTtV4AUAp/U0GhaHnInq4R5Ty+PTGLQ2wl896k3a9+x/Xfubhyd9PSfFE+7p7Nw99Zy7byaNe9U4/LZcngT7qJR61xeejPFtH/565j9RghHdrrZLZ4HUZUvgxcJkJUYjUaGDRvGN998Q0ZGBqdPn6ZZs2b2DqtUVGoDURGO7Nruxax11++6XLsuGdRrnkdqoqIcozMZ07UuUlnxtyykXiHvbrvGwZ/K7yBz44oT04c0NT/X601nLi/fIrx8NHy6rDbR15zwCyxk1MxIvHw0LJzQyGbxjB3QzuJm9jVCc1iw+jiH9gYApuRn7vsn+HpjLdYubYBeJ6FmnRwMhrus0Aoat8rhxy1+XD7nhExmZMCkWBZsvsSwp5pQVGAKtl7zHOZvjGT7mkDWzKmBXichtH4+RhseRFVqPVEX1ez6yodZn1wtMX/ozBiatctmydhQkmKVPNQxi1Hzb5KepODoHo87rPHBXPnUkRvbVDRflItLbT2Z5+Wcnu6MwtlI6OuFAFz9TMX1z1U0X5iLupqByFVqjg515bEfM5EpTes5NdmZwhQpbT/NwaCDM9OdOTvbmRZLcssc473UaZpPt75pXI9Q2XQ7pTFuyU1C6hay+K0apCcpePyFdN798gpDHm9AWqKDXWJSqQ1cv6Dity89eWf9DbvEIDw4kQBZyc6dO9m4cSP79+8nNDQUb29ve4dUauH73Qjff+9EwstPw4i5Mcx4PYy5G0qeQGwtK91yV31lVBLxUQ6cO+JcbjHo9RIy0pQlpt+86syC8cWJTmKsI5s+CGXSogikMgMGvW2qGtmZlrG82O8a8TFq/jrlCcCQsRf5YXsIX2+uZV4mLtq279fMgfUsni+fFMq28FOENcrj/AlXAIbNuMn3G/34em1gcVz/qBBZW/h+d8L3u991foMWuez5nzfnjppi/PVLX7r2SaFuszyrJEAZZ+T4P67Br5OpiqkO0hD3i4aMv0z7tdEI1zc7UmdYAQFPmJZp/m4uv3X0IHGvA0FdNeRck5F8yIFHvsrEvZEegMbT8zg63IWGkySofG2TQarUeqZ8eJOVk4N5dUyiTbZRWg4qAx26ZjL7jVqcP+YCwOfLA2nTOYvur6eyaUngfdZgG+H7XAnf52qXbZdZFW4CE1eBWcm1a9cICAigXbt2+Pv7I5dbnrA1Go2dIis7icTIpJU3+OZjP25etu2JqjTkCgOPv5DBb9u9KM/ud0HV89my9zCf/XqESe9G4ONfeNdlnZx15OfKbZb8/JNcbuCxZ+LY/WM1QIKbRxH1GmeSleHA0k//5PNf9/Du2qM0aJpeLvHcpnYxnahzskzfBzcvLfWa55GVpmDZ1xf44vhJFn8ZQcOWOeUa1z9FnHSmTecMvPw0gJEmbbMJqlnIyT+sU2H0aKYj5aiC3Bum/SHrkoy0Uwr8OpqOC/mxUopSpfi0LW7mVbgY8WiiI/2M6b3LOCNH4WowJz8A3m21SKSQcc52VdlRC2M5vteV0wddbLaN0pLJjMjkoCmy/N4XFUpp2Mq2VbD/NGMZH5WUSICsYMCAAYwePZro6GgkEgkhISE8+uijjBo1irFjx+Lt7U2XLl0AOHDgAK1atUKpVBIQEMDUqVPR6XTmdeXk5NCnTx+cnJwICAhgxYoVPProo4wdO/au2y8qKiI7O9viYU0vv5mIXg/fr7dOf4iyavd0Fs6uenZ95Vlu24z8y5XlM+szc0RTVs+rg19QAUs2ncJRrSuxrKu7hleH3eDXb8rv12ibR5Nwdtax5ydT3wz/oHwAXhtyhZ07gpn11sNci3Rl4erjBAbnlUtMEomRYTNvciHcmZuX1QAEBJuSxj5vxbFzuy8zB9Tj6gUnFm25SGDI3RNKW1vzTnVuXnFk6/Gz/HT1JPM3XWb1zBqcP26dk37YkAKCumr4vZs7Pzbx5EAvN2q9XkC1HqYEqCjVdChWelu2Tyq9DOZ5halSHDwtzzZSOSjcjBSm2uaHQKeeGdRuVMD6RQE2Wf+DKsiTERHuxGtjE/H00yCVGnn8hTTqt8jD07dkH0FBuBeRAFnB+++/z9y5c6lWrRoJCQmcOHECgE2bNuHg4MDhw4dZu3YtcXFxdO3alYcffpizZ8+yZs0aPvvsM+bPn29e1/jx4zl8+DA//PADu3fv5uDBg5w6deqe21+0aBFubm7mR3BwsNX+ttqN83h2YDLLJoRQUS527NI7nRP7XElPKr++SOGHvDi0y5cbl5059acX77zZBCcXHR27JFss5+ikY87qc0Rfd2LrmpByi++pnjGEH/EhPdXUR0N666P69dvq7PkpmOuX3Vi3ogGxN514skdMucQ0cu4NQurk8+6Y2uZpkltHnF++9GX3Nz5ci3Dik/k1iI1S8dRLyXdZk+31HJBE/eZ5vPNGGKO7N2DdgmBGzrtJ8/ZZVll//E4HYn9yoMWSXDp9k0XzRblc3eBI9I6STaoVhU+ghhFz43hvdA20Nuqc/m8sfisEiQS+PHmen66f5rk3Utj/vQdGG/Zt+y+73Qm6rI/KSPQBsgI3NzdcXFyQyWT4+/ubp4eFhbF48WLz8+nTpxMcHMyHH36IRCKhXr16xMfHM2XKFGbNmkVeXh6bNm3iiy++4IknngBgw4YNBAbeu5Iwbdo0xo8fb36enZ1ttSSoUatc3L11bDnyl3maTA5DZsTy/BvJ9G/f2CrbKS3fIA3NO+Ywb3DNct3uP+XlKIi7qSawevFVWI5qHfPWniU/X868txqh15XPScPHv4BmD6eycEoL87T0W32VYqIs+/zE3HC+Z9OdtYyYfYNWj2UyqXd9UhOLT/LpyaakNfqKZVNq9FVHfAPt00zsoDQwYFIc84bV5vjv7gBEXVJTq0E+vYYmcvpw2ZvBLixVEzbYVAUCcK2jpyBextV1jlR/rshc+SlKlaLyKW7iKkqT4lrPVGVUeRvQpFv+CDHoQJslQeVt/TNQ7cb5ePjoWL0z0jxNJofGbfLoOSCV7jWbYjCU/4+ihJtKJr1YB6WjHicXA+nJCt7+6DoJ0RU3mazQqnAfIJEA2VCLFi0snl+8eJG2bdsikRQfNNq3b09ubi6xsbFkZGSg1Wpp1aqVeb6bmxt169a953aUSiVKpW2+/Hv/58Xpg5ad+xZ8foW933qy+6vy7+j91CtpZKbKObbXvh0OVY46AoIL+P1HU8Lr6KRj/sdn0WqkzB3dGK3GNpeZ38mTPWLIylBy/LCPeVpSvCOpyUqCalg2dwVVzyP8T59/rsKKjIyYfZN2T6Uz5bUGJMVaXjWUFKskNVFBtVDLy/er1SzkxAF3G8Z1d3KFEYWDscTVcQa9xFyxKit9gaREvV0iNZqrFupqBpTeBlKOKnCrb0qAtLkSMs7JCeltSlg9munQZkvJvCDDvaFpmdRjCowG8Ghi/eafM4dcGPq45bFnwvJoYq6p+Gq1r12Sn78rKpBRVCDD2U1Hi045fLowyK7xCJWPSIBsyMnJfuNSPAiVWk9gSJH5uX9wEaEN8snJlJMS70BOpuVuotdKyEhREHu9fC+JlUiMPPVKOnu+9sSgL9+D76AJVzl2wIvkeBVePhr6jozCoJew/1dfHJ10LPj4LEpHPUumNkDtpEPtZPrVnpXhYNMThURi5Mnusez9OegfHa4lfPt5KH2GXiHqigvXL7vyRLc4qtXIZeHU5jaLZ+TcGzzaM425Q+tQkCvFw9tU8cjLkd8a40fC/9YF0HdsHFGX1FyLcKLzCylUq1XAgpFhNovr7vu4jJR4JeeOuDD47Vg0hVKS4pQ0aZ3DE71S+WRedats3/8xDVc+dkQdYMCltp6si3KubXKk+gummCQSCO1XwJWPHXGuoUddzcClVWpUvgb8nzC9hy619Ph20HB2ljNN3snDoIO/5jsR1FVjkyvACvJk3Iy0rNQV5kvJySg5vTy16JSNRGIk5pqKoJAiBs+II+aakl3bvewWk0qtJ7BmcQXTP1hDaMMC0/4VZ59L80tLjAMklIv69evzv//9D6PRaK4CHT58GBcXF6pVq4aHhwcKhYITJ05QvbrpwJuVlcXly5d55JFHbBZXnSb5LP7qsvn5sHdiAdj9tdetvj8VQ/OOOfhV0/Lb9vLr/Hybt18RU96LwNVdS1aGAxdOuTGuTwuyMxxo3DKDek1NHc/X/3rU4nUDurQhOd52J4tmrVLxDShk148lB6b7fltNHBwMDBl3ERdXLVFXXJgxuhWJcbZLzLv3NfXjWbztosX0ZZNC2fM/U+Vpx4YAFEojQ6dH4+Ku4/pFNdP71Sch2nYJdZ0meSzeXtyUM2yWqR/U7q+9WDYxlEWjazFwciyT37+Oi7uO5Fglm5ZU4+fPrVMtazw9j0ur1Jyb60RRumkgxBovF1J3RHElrPagQvQFEs6+42waCPEhLW0+yTaPAQTw0OJc/lrgxJ9vuCKRGgl4UkPjt8unU3tF4eSiZ+DUOLwDtORkyjj8qwcb3gtEr7NfRapO0wKW/O+a+fnwOfEA7NruwbJx1kmibaYKN4FJjEZbDj9WdaxcuZKVK1dy48YNAB599FGaNWvGypUrzcvExcVRp04dBg4cyKhRo4iMjGTw4MGMHDmS2bNnAzBkyBD27t3LZ599hq+vL++88w67du1i0KBBrFixolSxZGdn4+bmxmPyXsgl5T9o4d0Y9fr7L1TOZJ5lH+PF2iSO9h9q4J8MqWn2DqEEo77i9XrtcTbB3iGU8EPDCjgmmbXaFq3JUHGOTzqjlv18T1ZWFq6utmnuv32eaDxoITKHsv340GsK+euzt20ary1UwL3wvysoKIhffvmF48eP07RpU4YPH86gQYOYMWOGeZnly5fTtm1bunfvTufOnWnfvj3169dHpbL/CKyCIAjCf4u4Ckwos7Fjx1qM1bN///47LtepUyeOHz9+1/W4uLiwdetW8/O8vDzmzJnD0KFDrRWqIAiCIJhU4SYwkQBVMKdPn+bSpUu0atWKrKws5s6dC8Czzz5r58gEQRCE/xyRAAkVydKlS4mMjMTBwYEWLVpw8ODBSnVvMUEQBEGo6EQCVME0b96ckydP2jsMQRAEoQoQl8ELgiAIglD1VOEmMHEVmCAIgiAIVY6oAAmCIAhCFSUxGpGUcTjAsr7eXkQCJAiCIAhVlWgCEwRBEARBqDpEBUgQBEEQqihxFZggCP9v777Dmrr+P4C/k5CEhIS9lSlbcS+KVVsH7lVHrVZQ3KvuUauCo7YqzmqHtmJ/atXWalutVUvFOlHcCqIgUxBQ2Zvk/P7Il2gAEYUk2Hxez8PzcNe5n9yVT845915CCNE91ARGCCGEEKI7qAboP4zJGVhDqptsgHcKyPMLtB1CFZyiYm2HUBWfr+0IquAaNLyYfvcy03YIVYyNSdB2CFXscnfQdghVcTjajuAFHI3VqlATGCGEEEJ0jw43gVECRAghhOgoXa4Boj5AhBBCCNE5VANECCGE6CpqAiOEEEKILnpbm7DqiprACCGEEKJzqAaIEEII0VWM1f0RJQ3wESe1QQkQIYQQoqPoLjBCCCGEEB1CNUCEEEKIrqK7wAghhBCiazhyxV9dy3gbURMYIYQQQnQO1QARNOuQh2GT0+HqXQQz6zIEBTrj4glj5XTf3lnoO/oJXJsXwtBEhik9PfAwSqzRGPuNeYK+Y57Cyq4UAJAYo4+9G60QedpQYzE0a5+LoRMfw7VZAcysyhA80RUXT5kopxublyFwYTJav5sDA0MZ7lyWYnuQA1IT9NUSz/DJj+Db8ykaOxehtISLqGtS/LDWAY/iRQAAy0bF2H3merXLrp7hhnPH6//FnX1HpqHvyDRYNSoBACQ+EGPfdjtE/mtaaU6GFTui0K5zFlZM9cTFMPW9RHTUlHiMmpqgMi45XoxJAzoAAPgCGSbMj0PnXungCxiunTfFttVuyH4qUFtM1RkxPR2+fXJg51KC0mIuoiLF+H61DVLi1HP8yGXAja1GiPtdgqInXIgtZXAZXIAWU3PA4QDyMuDqJmOk/CtCfrIe+BI5bN8pRtu52RBbyZTlPLkrwNX1xnhyWwgOj8GhZyHaL8oC30A97SKa3k61MXpOGj6em64yLjlWiPFdPLUU0WugJjBSna5du6Jly5bYtGmTtkNRK32xHA+jxDhxwBzLdz6sdvrdKxL8e9QEs9claSFCIDONjx8+t8GjeCE4HKDHsGcI2pWAaT3dkHhfMxc+fZEc8dFinDxojmXfxlaayrD82/soL+cieKIrCvN5GBL4GGv23MPEHt4oKeLVezze7XPwxx5r3L8tAY/HEDA3CatDozCpV0uUFPHwJE2Ijzq2UVmm94fp+GB8KiLPGNd7PADw5LEAu9Y74lGiCBwO0H1QOpZti8b0wS2RFGugnG+Qf6pGL5oJDwywZEIL5bBM9vzN3xMXxKJd56dYM7cZCvL1MOXT+/hs423MG9OmuqLUprlPAf4INcf9G2Lw9BgCFqXh858eYkIXd7UcP7d3GOLeT1K8++VTGLuU4ukdIc4uNoNAKofXmDyUF3PwLEqAllNyYOpRipJcLiJWm+LvKRYY8OtjAEBhOg8nxlrCqXchOi59htJ8Li5/boKzi83w/pYn9R4zoPntVFsJ9/Sx6MMmymFZeUN6u/zL6fJdYJQAEUSeNkLkaaOXTg87pPh1btW4RFMhVRFxSjW+0C9t0G/MU3i0KdBYAhR5xviliUMjp2J4ti7ApJ7NkPhAUTu29TNH/HT5Ot4b8BR/HbCs93iWjvNSGd6w0AX7L0fCtVkB7lwxhFzOQdYT1VqMd3o+w9njZiguVM8XRcRp1Zqc3Zsc0XfkY3i0zFMmQM4e+fhg3CPM/KAl9p2/rJY4KpPJOMh6KqwyXiwpR88haVi70As3Lytq8zYu9cB3v1+Ge/McxNx6+XlR35aMclYZDpllj4N37sK1eRHuREjqfX0Z14Ww71YEu65FAABp40I8PCZG5i3FMSOQMvjtylBZpuPSZzg6zAb5qTxIbGVIDheBqwf4LH8Gzv86VPgEP8NvA2yRm5gNQ4fyeo9b09uptmQyICuTr7X1vzEdfg4Q9QHSoNLSUm2H8J/A5TJ0GZgFoViO6EiDVy+gAXyB4gJQWvL8lGKMg7JSLpq2zddIDGKp4ssmL7v63zUuTfPRxKsQJw5aaSQeLpehS59M6ItluHdd0VQp1JdhYUgMtq1oUiU5U6dG9oX4v7Dz+P74Rcz/IgoW1sUAAFevPPD5DDcuPW/KTIk3QEaqEJ4tcjUWX3UMDBXNTHnZ6klWLVuVIO2SPnLiFcfLs3t8pF/VR+POxS9dpiyfC3AYBIaKXq+yUg64fKZMfgBAT19xLqRfrZpwqoO6t1NtNXIqxb6rdxB6IQoLtybCwpau9w0dJUCvIJfLsWDBApiamsLa2hpBQUHKaUlJSRg4cCAkEgkMDQ0xfPhwpKc/bwcOCgpCy5YtsXPnTjg5OUFfX1FT8csvv8Db2xsikQhmZmbo3r07CgoKlMvt3LkTnp6e0NfXh4eHB7Zv315jjCUlJcjNzVX5+y9y9CjCkQe3cTThFmZ+kYIVgY5IeqC9dv8XJcfpI/2RAGMXpEBiWA49vhzDJqXCwrYUppbqvxByOAyTliTgbqRUWQNVmd/wDCTFihB9XarWWBzdCvDrtQv4/fZ5TA+OxcppnkiKU8Q0cXE8oq4b4pIa+/xUFnPbEBuWemLplBbYttINVo2KsG73NYjE5TAxL0VZKQcFeaq/3LOeCmBirr0vMA6HYXLwI9y5LEZijEgt62g+MRdOfQrwa29bhDa1x2+DbNDUPxdNBhRUO395CRC53hjOfQshkCiSHJuOxSh6wsPtnYaQlQIlOVxEhhgDAIoy1Z+QaGI71ca96wZYP9seS0Y3wdbFjWFtX4KQww8gMpC9emEtq2gCq+vf24iawF5h9+7dmDNnDiIiInDx4kUEBATA19cX3bp1UyY/Z86cQXl5OaZNm4YRI0YgPDxcuXxsbCwOHTqEX3/9FTweD2lpaRg5ciTWrl2LwYMHIy8vD2fPngX7XxXi3r17sWzZMnz11Vdo1aoVrl+/jgkTJsDAwAD+/v7VxrhmzRoEBwdrYnNoVUqcEFN7uEEsleHdfjmYtzkJ84e4NIgkSFbOxcrJrpj9ZTx+uXkNsnLg+nkjXD5tBI4GugJMC4qHo1sR5n3YtNrpAqEMXfs/wU/bGqs9lpR4EaYNagUDqQyd/J5g7pf3sWB0c9g4FKFFx2xMH9xK7TG8KPLc82Qr4b4EMbcNEXriIt71y0BpiXZrDV5m+ueP4OBRjLmDXNS2jvjjYsT9YYAuIU9g7FKGZ9ECXF5jApGlDK6DVZMgeRkQ/okFGAN8gp8qx5u4luHdL57gyhemuLrBGBwu4PVxLkTmMkADx70mtlNtvHgzRny0CPeui/F/EVHo3D8bJ/ZrLtl/I9QJmrxM8+bNsXz5cgCAq6srvvrqK4SFhQEAbt++jfj4eNjZ2QEAfvzxRzRt2hRXrlxBu3btACiavX788UdYWFgAAK5du4by8nIMGTIEDg4OAABvb2/l+pYvX46QkBAMGTIEAODk5ISoqCh8++23L02AFi9ejDlz5iiHc3NzlTH9l5SXcZGaoKhWj70thnvLQgwan4ktCxvGZ429Y4BpfZtBLC0Hn8+Q84yPTYfv4sFt9TbTTVn+EO3fz8L8kU3x5HH1zQ6dej+DUF+OsMMWao0FUOyntCTFr/HYuxK4eedh4JhUlJZwYWNfjF+uXFSZf8nWaNyNNMTCMc3VHhsAFOTx8ShRDFv7Ily/aAq+gMFAWqZSC2RiVqrRJroXTVudgg49cjF3cBM8SVNfDFfWmqD5xBw49y0EAJi6lyE/VQ+3vzVSSYDkZcDpWRbIT9VDr93pytqfCk36F6JJ/0IUPeFCT8QADnA31BBSu/rv//MiTW2nN1GQq4eUh0LYOmqv3yR5NUqAXqF5c9WLso2NDTIyMhAdHQ07OzuVRMPLywvGxsaIjo5WJkAODg7K5AcAWrRogW7dusHb2xt+fn7o2bMnhg4dChMTExQUFCAuLg6BgYGYMGGCcpny8nIYGb28M6ZQKIRQqJn29oaEw3ne96YhKcxTnFa2jsVw9S7AjxvUVevCMGV5PN7p8QwLRzVFesrLa8L8hmUg4h8T5DzTfCdNDhfgC+TYs9Uef/2s2v/om6PX8d0aZ0ScrnybvProi8phY1eEf/6wxoMoKcrKOGjZIQvn/1Z0VG/kWAhL2xJE39TcIxYUGKatfoR3euVg/lAXpCer95yWFXOq1E5yeUylP2tF8pObqIfeP6ZD3+TlT7wTmSum3f/FADwhg61vkTrChqa305vQF8tg61CKsEMNv1M03QVGXorPVz2AORwO5PLaP/bSwED11z+Px8OpU6dw4cIFnDx5Elu3bsWSJUsQEREBsVjRT2LHjh3o0KFDleXURV8sU/mlYm1XAmevQuRl6yEzVQCpcTksbEthZl0GALBrougkmZXJ19hdD2MXp+HKP1JkPhJAJJHhvcHZaP5OPpZ85PzqheuJ4qL2vIOotV0JnD0LkJejh8xUId7t8ww5T/WQkSqAo0cRpixLxMWTJrh2Vj13Ek0LjkfX/k+wYrI7igp4yj4rBXk8laYdG4ciNGuXi2XjPdQSx4sC5iQg8l8TZKQJITaQoWu/TDRvn4PPApsi64mg2lqVzFRhjclbXQXOjUXEGTNkpOrDzKIUo6fFQy7jIPy4JQrz9XDyVxtMmB+LvBw+Cgv0MHnxfUTdMNToHWCAojnnvcFZCBrrhKJ8LkwsFOdbQR4PpcX1313T7r0i3PzGCAa2Mhi7lOJZtAB3dhnC9QNFp315GfDPTAs8jRKgx7cZkMuAwkxFHEIjOXj/25VRe6SwbFUCvliO1Av6uLLWBG3nZkNoqJ5vRU1vp9qYsPQRLp0yQkYKH2bW5fh4bhpkciD8iMmrF9Y2Hb4LjBKgN+Tp6Ynk5GQkJycra4GioqKQnZ0NLy+vGpflcDjw9fWFr68vli1bBgcHBxw+fBhz5syBra0tHj58iFGjRmniYwAA3FoUYt3PD5TDk4MeAQBOHjRFyBxHdOyRg3kbE5XTP/06AQDwfxussWeDrUZiNDYvx/wtSTC1LEdhHg/x0fpY8pEzrv2r3g69L3LzLsDa/feUw5OWKp6JdOoXc4TMd4apZSkmLkmCsXkZnmXyEfarOfZtVd/26TdK0eF+7b4olfEhC5rg71+f33bfc2gmnjwW4NpZY7XFUsHYrAzzvrwPU8tSFOTpIT5GjM8Cm+L6Be19EZhblWDhl1EwNC5DTpYAd68ZYfaoNsjNUnyDf7fWBYxxsGTjHfD5cly9YIrtq9w0Hmf/AEXfmvW/xqmMXz/LDqcO1n8NWcfPnuHaZmNcDDZF8VPFgxDdR+Sj5bRsAEBBOg/J/yh+lP02UPU47vXjY9h0UPxoenJLgBtbjVBWwIWRcxneCX4Gl0HVd6SuD5reTrVhblOGxdsSIDWRIeeZHu5eNsCs/m7IeUZfsQ0Zh7G3NHXTgOoehDho0CAYGxtj165daN26NaRSKTZt2oTy8nJMnToVEolE2Qk6KCgIR44cwY0bN5TLR0REICwsDD179oSlpSUiIiIwevRoHDlyBL1798bOnTsxc+ZMfPHFF+jVqxdKSkoQGRmJrKwslX4+NcnNzYWRkRG6codAj9OAqmDlDe+OCE4DbDrkqLG27401wJg4ggZ0bP+P7OkzbYdQxdiYxFfPpGG73B20HUJVmrhboZbKWRnC2RHk5OTA0FA9TbEV3xM+vVdAj1+3GtjysmJcPL5MrfGqA6Wnb4jD4eC3337DjBkz0LlzZ3C5XPTq1Qtbt26tcTlDQ0P8+++/2LRpE3Jzc+Hg4ICQkBD07t0bADB+/HiIxWKsW7cO8+fPh4GBAby9vTFr1iwNfCpCCCE6RYfvAqMaoP8gqgGqPaoBqqUGGBPVANUO1QDVkq7WAPWqpxqgv6gGiBBCCCFvCboLjBBCCCG6R84Uf3Ut4y1ECRAhhBCiq3S4DxC9C4wQQgghOocSIEIIIURHcVAPL0N9jfWtWbMG7dq1g1QqhaWlJQYNGoSYmBiVeYqLizFt2jSYmZlBIpHggw8+UHnROKB4GXnfvn0hFothaWmJ+fPno7z89V6/QgkQIYQQoqsqngRd179aOnPmDKZNm4ZLly7h1KlTKCsrQ8+ePVFQ8PzhmbNnz8Yff/yBn3/+GWfOnEFqaqry/ZgAIJPJ0LdvX5SWluLChQvYvXs3QkNDsWzZstf66NQHiBBCCCF1lpubqzJc3Xsq//rrL5Xh0NBQWFpa4urVq+jcuTNycnLw/fffY9++fXj//fcBALt27YKnpycuXbqEjh074uTJk4iKisLff/8NKysrtGzZEitXrsTChQsRFBQEgaB2L8elGiBCCCFER9W5+euF2+jt7OxgZGSk/FuzZs0r15+TkwMAMDVVvMbk6tWrKCsrQ/fu3ZXzeHh4wN7eHhcvXgQAXLx4Ed7e3rCyev5yZT8/P+Tm5uLu3bu1/uxUA0QIIYToqnq8Cyw5OVnlQYiVa38qk8vlmDVrFnx9fdGsWTMAwOPHjyEQCGBsbKwyr5WVFR4/fqyc58Xkp2J6xbTaogSIEEIIIXVmaGj4Wk+CnjZtGu7cuYNz586pMaqXoyYwQgghREdxGKuXv9c1ffp0HD16FKdPn0bjxo2V462trVFaWors7GyV+dPT02Ftba2cp/JdYRXDFfPUBtUA/Ydx9QXgcmrXGUwTWGmptkOogpWUaDuEKhi34b13qyG+x43UTkN879aJ1BvaDqEKv8ZttB3CC7iae7ig/H9/dS2jlhhjmDFjBg4fPozw8HA4OTmpTG/Tpg34fD7CwsLwwQcfAABiYmKQlJQEHx8fAICPjw9Wr16NjIwMWFpaAgBOnToFQ0NDeHl51ToWSoAIIYQQohHTpk3Dvn378Ntvv0EqlSr77BgZGUEkEsHIyAiBgYGYM2cOTE1NYWhoiBkzZsDHxwcdO3YEAPTs2RNeXl74+OOPsXbtWjx+/BifffYZpk2b9sp+Ry+iBIgQQgjRUW/ahFW5jNr6+uuvAQBdu3ZVGb9r1y4EBAQAADZu3Agul4sPPvgAJSUl8PPzw/bt25Xz8ng8HD16FFOmTIGPjw8MDAzg7++PFStWvFbclAARQgghukrD7wJjtUiW9PX1sW3bNmzbtu2l8zg4OODPP/+s/YqrQQkQIYQQoqte80nOLy3jLUR3gRFCCCFE51ANECGEEKKjXnySc13KeBtRAkQIIYToKmoCI4QQQgjRHVQDRAghhOgojlzxV9cy3kaUABFCCCG6iprACCGEEEJ0B9UAEUIIIbpKww9CbEgoAdJxwyc/gm/Pp2jsXITSEi6irknxw1oHPIoXKecxMS9F4KJEtPLNgdhAhpR4EfZvb4TzJ8zUFlez9nkYOjkdrt6FMLMqQ/D4Jrh40hgAwNNj8J//CO3ey4GNfSkK8ni4fk6KH75ohGfpmnv564jp6fDtkwM7lxKUFnMRFSnG96ttkBKnr7EYmnXIw7DJ6XD1LoKZdRmCAp1x8YTxC3MwjJmXhl4jn0BiJEPUFQm2fGqH1HjNxdhvzBP0HfMUVnaKl+Emxuhj70YrRJ421FgMlTXrkI9hUzMVx5d1OYLGOeLiX0ZaiwdoGMdTZdrYd4X5XOxea4MLx42Q/VQPTZoWYcrKFLi3LAIArJ9lj1MHTVWWadM1F5/vewgAuHlBggVDXaote8ufMcpy6guXyzB6Thq6DXkGE8syPH3Mx6mfzbBvszUATr2uSx00/SqMhoSawNQoICAAgwYNqnEeR0dHbNq0SSPxVMe7fQ7+2GON2cO88am/F/T0GFaHRkEoev7273nrY9HYqQjBk9wxpW8LnD9hisVb7qOJV4Ha4tIXyxEfJcK2z+yqTBOK5HBpVoh9W2wwvY8nVk50RmPnYgR9H6e2eKrT3KcAf4SaY1Y/Vyz+0Bk8PYbPf3qosu3UTV8sx8MoMb6qZjsBwPCp6Rg4NhNbF9vjk/7uKC7k4vM9seALNddrMTONjx8+t8H0Xm6Y0dsNN89LELQrAQ5uxRqLoTJ9sRwP7+rjq08bay2GyhrC8VSZNvbdxrl2uPavBAu2JuKbsHto0yUPi0a44EkaXzlP2/dy8dONO8q/xdsTldO82haoTPvpxh30+ugprO1L4NaifpMfQHGO9RuTiW2f2WFCVy98v6YRhk1Jx8BxmfW+LlK/qAZIy65cuQIDAwOtrX/pOC+V4Q0LXbD/ciRcmxXgzhXFrzzPVnn4arkz7t+SAgD2b2+MwWPT4NIsH3FR6ok9MtwIkeHV/yIvzOPh01FuKuO2L7XHlqP3YGFbisxUzdQCLRnlrDIcMsseB+/chWvzItyJkGgkhsjTRog8/bKaC4ZBgRn4aYu1svZs7SxHHLh+C+/4ZePM76YvWa5+RZxSjS/0Sxv0G/MUHm0KkHhfO7UbkacNtVoDVZ2GcDxVpul9V1LEwbk/jRG0Kx7eHRU/sD6e9xiXThni6I9mCFioeHM4X8BgallebRmVp5WXARdPGGLguCfgqKFCxqttPi6eNMblfxTbKj1FiPcGZsG9pfp+INYr6gRNtMXCwgJisVjbYSiJpYoLR17289w4+roUnfs8gcSoDBwOQ5e+TyAQynErouF8gRgYyiCXAwW5PK3GAAB52dqL4UXW9qUwsyrHtbNS5bjCPB7u3TCAZxvtXJy5XIYuA7MgFMsRHam9xP9t0NCOJ03sO5mMA7mMA0GlGkqhvhx3Lz9PAm9dlGC4d1MEdvLAlkWNkfvs5dvo4kkj5GXpoeeIZ2qJOSpSgpa+eWjkpKgVc/YsRNN2+bjy0h8mDQwDIK/j39uZ/1ACVB9++eUXeHt7QyQSwczMDN27d0dBwfMvmPXr18PGxgZmZmaYNm0aysrKlNMqN4FxOBx8/fXX6N27N0QiEZydnfHLL7/UuP6SkhLk5uaq/L0JDodh0pIE3I2UIvHB86Ts8xlu0OMz/Hw1Er9HRWDGqodYOdUdaYmiGkrTHL5QjnGLHyH8N1MU5mvny4LDYZgc/Ah3LouRGNMwtoupheI4y37CVxmfnamnnKYpjh5FOPLgNo4m3MLML1KwItARSQ+017eloWtIx5Mm951YIodnmwLs22SNp4/1IJMBYYdMEH3VAM/SFT/K2nbNxfzNifjyYBwCl6Th9kUJlox2huwlLYUnfjJDm655sLBVzzF/YJsVzvxugp1nonAs/hq2nbiHwzstcfqwZmpY66qiD1Bd/95GlADVUVpaGkaOHIlx48YhOjoa4eHhGDJkCNj/DojTp08jLi4Op0+fxu7duxEaGorQ0NAay1y6dCk++OAD3Lx5E6NGjcKHH36I6Ojol86/Zs0aGBkZKf/s7KrvD/Iq04Li4ehWhC9muaqMHzM7GQZSGRZ/7IWZg73x6w82WLzlPhzdtF/Fy9NjWLL9IThg+GqJvdbimP75Izh4FGPNFAetxdCQpcQJMbWHG2b2dcXRH80xb3MS7F211weooWtIx5Om992CrYlgDPiodTP0c2yBI9+bo+ugLHD+923VdVA2fPxy4eRZjHd652DFjw9x/4YBbl2o2kyYmcrH1XAp/EY+VVu8nftn4f3Bz/DFdEdM6+2J9bMdMHRyOroPVd86Sf2gBKiO0tLSUF5ejiFDhsDR0RHe3t6YOnUqJBLFyWhiYoKvvvoKHh4e6NevH/r27YuwsLAayxw2bBjGjx8PNzc3rFy5Em3btsXWrVtfOv/ixYuRk5Oj/EtOTn7tzzFl+UO0fz8LC0d74cljoXK8jX0xBox5jI2Lm+DGRSPE3zPAvq12eHBbgn6j0197PfWJp8fw6faHsGxUisWj3LRW+zNtdQo69MjFgqFN8CRNc3ehvcqzTEXNj7G56i9fY4ty5TRNKS/jIjVBiNjbYuxaY4P4KBEGjadOotVpaMeTpvedrWMp1v8ai99ib2FP5F1s/fMByss4sHEoqXZ+G4dSGJmWIzVBWGXayQOmkJqUw6dnjtrinfDZIxzYZo0zv5si4Z4IYYfM8OsOS3w4/bHa1lmvGJ73A3rjP21/iDdDCVAdtWjRAt26dYO3tzeGDRuGHTt2ICsrSzm9adOm4PGefzHb2NggIyOjxjJ9fHyqDNdUAyQUCmFoaKjyV3sMU5Y/xDs9nmHRaC+kp6hWbQv1FfXKrNJNQ3K5ok+AtlQkP42cirH4I1eVPkuawzBtdQre6ZWDBcOaID256gVYmx4nCfA0XQ+tOuUpx4klMni0LED0Ve32v+FwFJ1VyYsa9vFUQVP7Tl8sh5lVOfKyebh6xhA+ftU37Wem8pGbxYOppWqiz5giAeo+NAt6asz3hSJ51eujjKOssWrw6pz81EMnai2hu8DqiMfj4dSpU7hw4QJOnjyJrVu3YsmSJYiIiAAA8PmqZx6Hw4Fc3nBenDItOB5d+z/BisnuKCrgwcRc8byPgjweSkt4SH4owqMEfcxY+RA7v3BAXjYfPj2eoZVvDoImeKgtLn2xDLaOz3/xWduVwNmrEHnZeniWwcdn38TBpVkhlo11AZcHmPyvT0teNg/lZZq58kz//BHeG5yFoLFOKMrnKmMoyOOhtFgzMdS0nTJTBTjyvSVGznyMR/FCPE4Wwn9eKp6m83FB5VlB6jV2cRqu/CNF5iMBRBIZ3hucjebv5GPJR86vXlhN9MUy2DqVKoet7Urh3LQIedk8ZD7STq1LQzieKtPGvosMl4IxwK5JCR7FC7BzZSPYuRSj54inKCrgYk+INTr1zYaJZTnSEgTYucoWtk4laNM1T6WcG+ckeJwkRK+P1NsUdemUET6c+RgZjwRIvK+PJs2KMGRiBk4eUN9z0kj9oASoHnA4HPj6+sLX1xfLli2Dg4MDDh8+/MblXbp0CWPGjFEZbtWqVX2EWkW/UYpmrLX7olTGhyxogr9/tYSsnItlgR4YOz8JQd/FQCSWITVRHyELXHDljIlaYgIAt+aFWHvwvnJ40vIUAMCpn82wZ6ONskr76xOqNWMLhrvh1iUpNKF/gOLCuv5X1ecPrZ9lV+VBberi1qIQ635+oByeHPQIAHDyoClC5jji4HYr6Ivl+OTLJEgMZbh7RYIlo11QVqK5L1Rj83LM35IEU8tyFObxEB+tjyUfOePav5rZT9Vxa1GEdYee77fJwakAgJMHTBAyWzt9yRrC8VSZNvZdQS4Pu9bY4EkaH1JjGXz7ZGPsojTo8QFZOUN8tD5O/eyEglwezKzK0bpLLvwXPIZAqFoL8ddPZvBqmw971+qbzurL9qV28J+fiumfJ8PYXPEgxD/3mGPvJmu1rrfeyFH35zU2nN/0r4XD2Ftad9VAREREICwsDD179oSlpSUiIiIwevRoHDlyBAcOHEB2djaOHDminH/WrFm4ceMGwsPDASjuAps1axZmzZoFQJFMmZub48svv0SnTp2wd+9erFq1Crdv34aXl1fVAKqRm5sLIyMjvC/+EHoc7fchqMBKS189k4ax8uqfJaJV3IZx27MKufYexkf+e06k3tB2CFX4NW6j7RCUylkZwuW/Iicn5zW7NNRexfdEt2YLoMerW3NruawEYXfWqjVedaAaoDoyNDTEv//+i02bNiE3NxcODg4ICQlB7969ceDAgTcqMzg4GPv378fUqVNhY2ODn376qdbJDyGEEEJejRKgOvL09MRff/1V7bTqbnev/NqLhISEKvPY2tri5MmT9RAdIYQQUgMdfhI0JUCEEEKIrtLhBOhtuVGPEEIIIaTeUA1QA0N90gkhhGiMDtcAUQJECCGE6Codvg2eEiBCCCFER9XHy0zpZaiEEEIIIW8JqgEihBBCdBX1ASKEEEKIzpEzgFPHBEb+diZA1ARGCCGEEJ1DNUCEEEKIrqImMEIIIYTonnpIgEAJEGlgWJkMjNNw3nbONTPVdghVyNIztB1CVewtfagGaZi4PG1HUEUvpw7aDqGKlXHntB2CUkGeHOHe2o7iv48SIEIIIURXURMYIYQQQnSOnKHOTVh0FxghhBBCyNuBaoAIIYQQXcXkde93+Jb2W6QEiBBCCNFV1AeIEEIIITqH+gARQgghhOgOqgEihBBCdBU1gRFCCCFE5zDUQwJUL5FoHDWBEUIIIUTnUA0QIYQQoquoCYwQQgghOkcuB1DH5/jI6TlA5C3VrH0ehk5Kg6t3IcysyhA8wQUXT5oop+uLZRi3KAU+PbNgaFKOx8lC/LbLCn/utVRbTGYWxRj7yQO09X0Kob4MaclibAzywoMoIwDAqElx6Oz3GBbWxSgr4yI22hA/fuWCmDtGaoupshHT0+HbJwd2LiUoLeYiKlKM71fbICVOX2MxVDZ6Tho+npuuMi45VojxXTy1FFHD3E7NOuRj2NRMxTFvXY6gcY64+Jfmjp2GGlOzDnkYNjkdrt5FMLMuQ1CgMy6eMFZO9+2dhb6jn8C1eSEMTWSY0tMDD6PEaotnxJRU+PploXGTIsWxc02CH760Q8pDkXKe3iMz8N6Ap2jStAAGUjk+aN4aBXn199UmlwH/bGqEm0fMkJ/Jh9SqFK0+eIKuM9LA4SjmWerUrtpl/RYlo9OkxwCAkE7Nkf1IqDK9x4JkdJ7yuN5iJa+HEqAGJiEhAU5OTrh+/TpatmypkXXqi2WIjxbj5EELLPsutsr0iUuT0fKdXKyb5Yz0FCFav5uD6asS8Sydj0t/m1RTYt1IpGVYH3oFt66YYtn0VsjJEsDWvhB5uXzlPI8Sxfj6Sw88ThFBIJRj8OhErNp+DYEDfZGbJaj3mKrT3KcAf4Sa4/4NMXh6DAGL0vD5Tw8xoYs7Soq09wbuhHv6WPRhE+WwrJyjtViAhrmd9MVyPLyrjxM/mWL5DwlaiaGyhhCTvliOh1FinDhgjuU7H1Y7/e4VCf49aoLZ65LUHo93hzz88X+WuH/LAFw9YOy8ZKz+MQYTe3grjx2hvhyRZ4wQecYI4xam1HsMZ7+xwZW9FhiyPh6WbkV4dMsAhxc4QV8qg8/YDADAgsvXVZZ5EG6MIwsd4dU7S2X8+7NT0HZkpnJYaNAAak6oCYy8SteuXdGyZUts2rRJ26HUu8hwY0SGG790ulebfPx9yBy3LhkCAI7/ZIk+ozLh3rJALQnQ0LEJyHysj41BTZXj0lNFKvOE/2WjMvxdiDv8BqfCyTUPNy+b1XtM1VkyylllOGSWPQ7euQvX5kW4EyHRSAzVkcmArEz+q2fUkIa4nSJPGyLytKFW1v0yDSGmyNNGiDz98lqnsEOKc8uqcYlG4vkswF1lOGS+Mw5cvQ5X7wLcuazYVkd2WQMAmnfIVUsMSdck8OiRDff3cwAAJo1LcfsPU6TclABQJEBSi3KVZaJPGcPJJw+m9qrbSSiRV5lX63Q4AaK7wOoJYwzl5Q3swK4nUVcl6Ng9C2ZWpQAYmvvkopFTMa7+q57q+Y5dMvEgyhCL197EvrBwbP3pEvwGv/yXnZ6eHL2HpCA/Tw/x96Vqiak2DAxlAIC8bO3V/gBAI6dS7Lt6B6EXorBwayIsbEu1Gk9lDWU7kbePWFpx7Gjut7t963w8PG+IJw8VzVdpUSIkXpHCrWt2tfPnZ+rh/mkjtB6eWWXa2a9t8HmrVtjW1wvnvrWG7L/5lfHWoASoFgICAnDmzBls3rwZHA4HHA4HoaGh4HA4OH78ONq0aQOhUIhz584hICAAgwYNUll+1qxZ6Nq1q3JYLpdj7dq1cHFxgVAohL29PVavXl3tumUyGcaNGwcPDw8kJVVf5VxSUoLc3FyVv/r09XJ7JD4QYe/lmzgaexWrdt/HtqUOuHNZPcmGdaMi9B2WgtQkMT6b2hrHfm6MyQti0K1/qsp87d/NxKHz/+BIRBgGjU7CksmtkZutmeavyjgchsnBj3DnshiJMaJXL6Am964bYP1seywZ3QRbFzeGtX0JQg4/gMhAprWYXtRQthN5+3A4DJOXJuLuFQkS76uv31Fl705Jg3f/Z9jS3RvLXdvg635N4TMuHS0GPat2/uuHzCE0kMOrl2rzV8eAdAzfGodx++6h3UeZOLPdBie/sNPER6iZnNXP31uImsBqYfPmzbh//z6aNWuGFStWAADu3r0LAFi0aBHWr18PZ2dnmJjUrjlo8eLF2LFjBzZu3IhOnTohLS0N9+7dqzJfSUkJRo4ciYSEBJw9exYWFhbVlrdmzRoEBwe/4ad7tQEB6fBsVYDl41yR8UiAZh3yMG2log/Q9fP1XwvE4TI8iDLE7q9cAQAPYwzh4JKPPkNTEPaHrXK+m1dMMf3DjjA0LkWvIY+weO0tzP64A3I01AfoRdM/fwQHj2LMHeSi8XW/6MUmlPhoEe5dF+P/IqLQuX82TuzXTNNgTRrKdiJvn2krEuHoXoS5w7w0ut47x0xx8zczDN38EJauRXgcJcafK+1haFWKVh88rTL/tZ/N0XzgU/CFqkmB7/jnNydYexaBx2f4fYkDesxPgZ5QewkEY3KwOr7Nva7LawslQLVgZGQEgUAAsVgMa2tFe3NFwrJixQr06NGj1mXl5eVh8+bN+Oqrr+Dv7w8AaNKkCTp16qQyX35+Pvr27YuSkhKcPn0aRkYvTzQWL16MOXPmKIdzc3NhZ1c/vywEQjkC5j/CykkuuPyPMQAg/p4YTbwK8cHEx2pJgLKeCJH80EBlXHK8AXy7ZaiMKynmIS1ZjLRkMWJuG2PHb+fgN/gRDv7gVO8x1WTa6hR06JGLuYOb4EmadmqgXqYgVw8pD4WwddRMn42aNOTtRBq2qcEJ6PB+NuaN8MSTx5o9dk6ssUPnyWlo3l9R42PtUYTsRwL8u92mSgKUcFmCJw9FGL417pXlNm6ZD3k5F1kpQlg0KVZL7LXC6qEG5y3tA0QJUB21bdv2teaPjo5GSUkJunXrVuN8I0eOROPGjfHPP/9AJKq5qUAoFEIoFNY4z5vS4zPwBazKYx7kMg44ampAjbphjEYOhSrjGtkXIiOt5tumuRyAz9fkLxGGaasf4Z1eOZg/1AXpyerZB3WhL5bB1qEUYYe02Sm64W8n0lAxTA1OxDs9s7BgpCfSUzR/7JQVccHhqn7Bc3gAk1e9u/LaQQvYehfAxqvoleU+jhKDw2WQmJfVW6zk9VACVEcGBqo1FVwuF6xSNlxW9vwAf1UyU6FPnz7Ys2cPLl68iPfff7/ugdZAXyxTqSGwtiuBs1ch8rJ5yEwV4tZFKcZ/moLSYi7SHwnRvEMeun3wBN+ttFdLPIf32CMk9AqGj4vH2VNWcG+ag94fpGDLSkXVt1Bfhg/HP8SlMxbIeiKEoXEZ+g1PhpllCc6eslJLTNWZ/vkjvDc4C0FjnVCUz4WJhWI/F+TxUFqsne51E5Y+wqVTRshI4cPMuhwfz02DTA6EH6n/u/VqqyFuJ32xDLZOzzuHW9uVwrlpkeKYf6Sd2qmGENPLrwV6yEwVQGpcDgvbUphZK/ah3f9qLrIy+Wq583DaikS8N/Apgie6Ko4dc8X2KcjTQ2mJ4tgxMS+FiUUZbB0VsTh6FKEon4uMVCHyc+r+FefRLRtnttnCyLYUlm5FSLsrxoXvrdB62BOV+YrzuLjzpwl6LUmuUkbSNQOk3JDAqWMuhBI5kq8Z4Pgqe7QY9BQiIy33z2MMdX6ZF9UA/bcJBALIZK8+UC0sLHDnzh2VcTdu3ACfr7g4uLq6QiQSISwsDOPHj39pOVOmTEGzZs0wYMAAHDt2DF26dKnbB6iBW/MCrD0QoxyetExxAp/62Qwh85yxZkYTjF2QggWbH0JqXI6MFCF2r2uMY3uq75NUVw+ijLBqbgsEzIjFRxMf4vEjEb5d547w44pb3+VyoLFjIZb0vwUj41Lk5vBx/64R5o9ri6SHmrutun+Aovp7/a+q1d3rZ9nh1EFTjcXxInObMizelgCpiQw5z/Rw97IBZvV3Q84z7Z3qDXE7ubUowrpDz+OZHKzoYH/ygAlCZqsnsX8bYnJrUYh1Pz94HkPQI0UMB00RMscRHXvkYN7GROX0T79OAAD83wZr7Nlgi/rW/2NFs/e6/ap9JEPmOeHUIcX1p++oDIye9fwGiZCD0VXmqYu+QYkI29AIfyx1QMFTxYMQ243MRNeZqjdl3P7DDGBQNpW9SE/AcPsPU5zeZIvyUi5M7ErgMy4dvoEN4CGIcjnAqWPN+VvaB4jDKldXkGpNnDgRN27cwMGDByGRSHDr1i1069YNWVlZMDY2Vs534sQJ9O7dG6GhofDx8cGePXuwadMmtGrVCuHh4QCA4OBgbN68GZs2bYKvry8yMzNx9+5dBAYGVnkQ4qZNm7B06VIcP368Sj+hl8nNzYWRkRHe4w+DHqfhPA+Ga2qs7RCqkKVnvHomTeNo98GF1aLLxNuL2/AeN8DhN7zf3ivundN2CEoFeXJ0905GTk4ODA3V82yoiu+JbtJR0OPUrYaxnJUiLG+vWuNVB7oNvpbmzZsHHo8HLy8vWFhYvPSWdD8/PyxduhQLFixAu3btkJeXhzFjxqjMs3TpUsydOxfLli2Dp6cnRowYgYyM6r+IZ82aheDgYPTp0wcXLlyo989FCCFEh1U8CLGuf28hqgH6D6IaoNqjGqBaosvE24tqgGpFV2uA3hd/WC81QP8U7qcaIEIIIYSQhq7hpeGEEEII0Qy6C4wQQgghOkfOAI5uJkDUBEYIIYQQnUM1QIQQQoiuYgxAXZ8D9HbWAFECRAghhOgoJmdgdWwCe1tvJqcEiBBCCNFVTI661wC9nU+Cpj5AhBBCCNGobdu2wdHREfr6+ujQoQMuX76s8RgoASKEEEJ0FJOzevl7HQcOHMCcOXOwfPlyXLt2DS1atICfn99L34igLpQAEUIIIbqKyevn7zVs2LABEyZMwNixY+Hl5YVvvvkGYrEYP/zwg5o+ZPWoD9B/UEWHtHJWpuVIVHHlpdoOoQpZA9tGCvQqDFKPGmD/DE4DPJ4K8hrOdirIV8Siic7F5Sir83MQy6G4jubm5qqMFwqFEAqFKuNKS0tx9epVLF68WDmOy+Wie/fuuHjxYt0CeU2UAP0H5eXlAQDOlh/RbiCVNcDXbjVIDe+7gbzNGs73+nMl2g6gqtPe2o6gqry8PBgZGamlbIFAAGtra5x7/Ge9lCeRSGBnZ6cybvny5QgKClIZ9+TJE8hkMlhZWamMt7Kywr179+olltqiBOg/yNbWFsnJyZBKpeDU4cWaubm5sLOzQ3JycoN5wR3FVDsUU+1QTLVDMdVOfcXEGENeXh5sbW3rMTpV+vr6iI+PR2lp/dTMM8aqfN9Urv1paCgB+g/icrlo3LhxvZVnaGjYYC4wFSim2qGYaodiqh2KqXbqIyZ11fy8SF9fH/r6+mpfz4vMzc3B4/GQnp6uMj49PR3W1tYajYU6QRNCCCFEIwQCAdq0aYOwsDDlOLlcjrCwMPj4+Gg0FqoBIoQQQojGzJkzB/7+/mjbti3at2+PTZs2oaCgAGPHjtVoHJQAkZcSCoVYvnx5g2rHpZhqh2KqHYqpdiim2mmIMTVEI0aMQGZmJpYtW4bHjx+jZcuW+Ouvv6p0jFY3DntbX+JBCCGEEPKGqA8QIYQQQnQOJUCEEEII0TmUABFCCCFE51AC9B+UkJAADoeDGzdu1LmsgIAADBo0qM7lNBShoaEwNjaucZ6goCBIJBLMmjULQPXbwNHREZs2bXrt9QcFBaFly5avvdzboGvXrspt1hBpKz7GGCZOnAhTU9N6Oy9fR0PfL69Sm2vQm56P2lKf12jy5igB+g+ys7NDWloamjVrpu1QapVwNDTz5s1DixYtapznypUrmDhxooYiql//5SSsIfrrr78QGhqKo0ePNpjz8r+mvs7Htz1ZJK+HboP/D+LxeDU+UZMxBplMBj092v3VkUgk4PP5Nc5jYWFR4/SysrJXlkFeT2lpKQQCgbbDeG1xcXGwsbHBO++8U+30t+1zNcR4X3U+1he6dv63UA3QW+qvv/5Cp06dYGxsDDMzM/Tr1w9xcXEAqlavhoeHg8Ph4Pjx42jTpg2EQiHOnTunrAn49ttvYWdnB7FYjOHDhyMnJ0e5nkePHuHs2bPK9XTo0AFt2rSBsbExDA0NweFwcP36deX8f/75JzgcDr755hu0bNkSY8eORU5ODjgcDjgcjvLFeMePH4elpSU4HA64XC4cHBxw8+ZNZTkVNUdHjx6Fu7s7xGIxhg4disLCQuzevRuOjo4wMTHBzJkzIZPJlMtlZWVhzJgxMDExgVgsRu/evfHgwYMq2+/IkSNwdXWFvr4+/Pz8kJycrJwWFBSEyMhIlJeXY/r06di3bx+OHz+OpUuXgjEGuVwOExMTmJqaQiQSoUWLFuBwOPj6668xYMAAGBgYYPXq1QCAL774AlZWVpBKpQgMDERxcXHddz4UT05du3YtXFxcIBQKYW9vr1znwoUL4ebmBrFYDGdnZyxduhRlZWXK7RocHIybN28q90loaOhrr7+goABjxoyBRCKBjY0NQkJCVKaXlJRg3rx5aNSoEQwMDNChQweEh4erzHPu3Dm8++67EIlEsLOzw8yZM1FQUKCc7ujoiJUrV2LMmDEwNDR8rV/4r4qvNsfJjh07lOfF4MGDsWHDhteuzQwICMCMGTOQlJQEDocDR0dHdO3aFdOnT8esWbNgbm4OPz8/AMCZM2fQvn17CIVC2NjYYNGiRSgvL1eWlZeXh1GjRsHAwAA2NjbYuHFjrWss5HI5FixYAFNTU1hbW6u8oDIpKQkDBw6ERCKBoaEhhg8frvKagorrxM6dO+Hk5KR8dcIvv/wCb29viEQimJmZoXv37ir7b+fOnfD09IS+vj48PDywffv2GmN8VXnr16+HjY0NzMzMMG3aNOUxDVRtAqs4H3v37g2RSARnZ2f88ssvNa4/ICAAZ86cwebNm1XOjequndU1y82aNQtdu3ZV2eYvO0crk8lkGDduHDw8PJCUlFRjnKQeMfJW+uWXX9ihQ4fYgwcP2PXr11n//v2Zt7c3k8lkLD4+ngFg169fZ4wxdvr0aQaANW/enJ08eZLFxsayp0+fsuXLlzMDAwP2/vvvs+vXr7MzZ84wFxcX9tFHHynX07VrV9auXTvletq2bcvs7e1ZTEwM27FjBwPAvLy8mEwmY4wxduzYMQaAOTs7s8OHD7NPP/2U6enpscaNG7Pk5GSWl5fHYmNjGY/HY1ZWVmzv3r0sNDSUSaVSJpVKWWlpKWOMsV27djE+n8969OjBrl27xs6cOcPMzMxYz5492fDhw9ndu3fZH3/8wQQCAdu/f78y3gEDBjBPT0/277//shs3bjA/Pz/m4uJSpdy2bduyCxcusMjISNa+fXv2zjvvKMuo2C4SiYR98sknbNCgQax169ZMLBaz7777jq1atYrp6emxSZMmsbi4OLZr1y4GgJmYmLAffviBxcXFscTERHbgwAEmFArZzp072b1799iSJUuYVCplLVq0qPP+X7BgATMxMWGhoaEsNjaWnT17lu3YsYMxxtjKlSvZ+fPnWXx8PPv999+ZlZUV+/LLLxljjBUWFrK5c+eypk2bsrS0NJaWlsYKCwtfe/1Tpkxh9vb27O+//2a3bt1i/fr1Y1KplH3yySeMMcbGjx/P3nnnHfbvv/+y2NhYtm7dOiYUCtn9+/cZY4zFxsYyAwMDtnHjRnb//n12/vx51qpVKxYQEKBch4ODAzM0NGTr169nsbGxLDY2tt7ie9Vxcu7cOcblctm6detYTEwM27ZtGzM1NWVGRkavtZ2ys7PZihUrWOPGjVlaWhrLyMhgXbp0YRKJhM2fP5/du3eP3bt3j6WkpDCxWMymTp3KoqOj2eHDh5m5uTlbvny5sqzx48czBwcH9vfff7Pbt2+zwYMHq3yml+nSpQszNDRkQUFB7P79+2z37t2Mw+GwkydPMplMxlq2bMk6derEIiMj2aVLl1ibNm1Yly5dlMtXnA+9evVi165dYzdv3mSpqalMT0+PbdiwgcXHx7Nbt26xbdu2sby8PMYYY3v27GE2Njbs0KFD7OHDh+zQoUPM1NSUhYaGVhtjTeX5+/szQ0NDNnnyZBYdHc3++OMP5blYwcHBgW3cuFE5DICZmZmxHTt2sJiYGPbZZ58xHo/HoqKiatxXPj4+bMKECcpz4++//6722unv788GDhyosvwnn3yist1qOkdfvEYXFxezwYMHs1atWrGMjIwa9yWpX5QA/UdkZmYyAOz27dsvTYCOHDmisszy5csZj8djKSkpynHHjx9nXC6XpaWlMcZYlRP9xfVUlFsxzNjzBOiLL75gjCkSDqlUygCw6OhoxhhjQ4cOZQDY+fPnleUePXqUAWB79uxRLgdA5Utv0qRJTCwWKy+yjDHm5+fHJk2axBhj7P79+1XKffLkCROJROzgwYMq5V66dEk5T3R0NAPAIiIilNvFwMCAeXp6MrlcrtwGCxcuZB4eHkwsFjNra+sqF1x3d3eV7evj48OmTp2qMq5Dhw51ToByc3OZUChUXkxfZd26daxNmzbK4eXLl9cphry8PCYQCJTblDHGnj59ykQiEfvkk09YYmIi4/F47NGjRyrLdevWjS1evJgxxlhgYCCbOHGiyvSzZ88yLpfLioqKGGOKL7VBgwbVe3y1OU5GjBjB+vbtq1LuqFGjXjsBYoyxjRs3MgcHB+Vwly5dWKtWrVTm+fTTT5m7uzuTy+XKcdu2bWMSiYTJZDKWm5vL+Hw++/nnn5XTs7OzmVgsrlUC1KlTJ5Vx7dq1YwsXLmQnT55kPB6PJSUlKafdvXuXAWCXL19mjCmOFz6fr/LlfPXqVQaAJSQkVLvOJk2asH379qmMW7lyJfPx8al2/prK8/f3Zw4ODqy8vFw5btiwYWzEiBHK4eoSoMmTJ6uU06FDBzZlypRq11+hS5cuKtvzZdfOVyVArzpHK67RZ8+eZd26dWOdOnVi2dnZNcZG6h81gb2lHjx4gJEjR8LZ2RmGhoZwdHQEgBqrT9u2bVtlnL29PRo1aqQc9vHxgVwuR0xMDAAgNzcXkZGRyvU4ODgAALp3744+ffool6u8Xg8PD+X/HA4HAJCRkQEAyqa5Hj16QCKRQCKRYPjw4QCAS5cuKZcTi8Vo0qSJctjKygqOjo6QSCQq4yrKjY6Ohp6eHjp06KCcbmZmBnd3d0RHRyvH6enpoV27diqxGhsbq8wDAB07dlTGXrFtYmNjUVhYiPT0dCxcuFAZPwCVKvmKeF6MpaKMuoqOjkZJSQm6detW7fQDBw7A19cX1tbWkEgk+Oyzz+q1Wj0uLg6lpaUqn83U1BTu7u4AgNu3b0Mmk8HNzU25fSQSCc6cOaNspr158yZCQ0NVpvv5+UEulyM+Pl5ZbnXHbF3jq81xEhMTg/bt26uUW3m4Ltq0aaMyHB0dDR8fH5XjzdfXF/n5+UhJScHDhw9RVlamEoORkZHyM71K8+bNVYZtbGyQkZGB6Oho2NnZwc7OTjnNy8uryvng4OCg0s+mRYsW6NatG7y9vTFs2DDs2LEDWVlZABTNj3FxcQgMDFTZv6tWrVLu/8pqKg8AmjZtCh6PVyX+mlQ+13x8fKqc47X1usfhq87RCiNHjkRBQQFOnjypkbe/E1XUk+st1b9/fzg4OGDHjh2wtbWFXC5Hs2bNUFpa+tJlDAwMXns9YWFhEAqF2L17N2xtbdGnTx8kJCRg6tSpcHJywpgxYwBAud6KJKC6DsByuRwAUFRUBC6Xi2vXrqlc1AYMGABTU1PlcOUyOBxOteMqytUE9r83x1haWiIwMFD58j5XV1csXrxYIzGIRKKXTrt48SJGjRqF4OBg+Pn5wcjICPv376/SB0ad8vPzwePxcPXqVZX9C0CZLObn52PSpEmYOXNmleXt7e2V/7/JMfs20PTnqut5UzleHo+HU6dO4cKFCzh58iS2bt2KJUuWICIiAmKxGICiD1XlHwCVj4falFcf8ddV5c/P5XKV14IKL/4AqukcfVGfPn2wZ88eXLx4Ee+//37dAyWvhWqA3kJPnz5FTEwMPvvsM3Tr1g2enp4qv5ZeR1JSElJTU5XDly5dApfLhbu7O54+fYrc3Fy4u7ujW7dusLS0REJCAgDFL8rqfhVFRUWpDAsEgioXqlatWkEul+Pp06dwcXGBi4sLTExMkJCQAG9v7zf6HADg6emJ8vJy5UUTeL6tvLy8lOPKy8sRGRmpHI6JiUF2djY8PT1VynuxHECxbSo6NMpkMlhYWCjjBwBzc/Mq8VRXRl25urpCJBIhLCysyrQLFy7AwcEBS5YsQdu2beHq6orExESVeQQCgUrH8dfVpEkT8Pl8lc+WlZWF+/fvA1DsX5lMhoyMDOX2qfiruDuxdevWiIqKqjLdxcWlzncYvSq+2hwn7u7uuHLlikq5lYfrk6enJy5evKjypXr+/HlIpVI0btwYzs7O4PP5KjHk5OQoP1Nd1pucnKxyE0BUVBSys7NVzpnqcDgc+Pr6Ijg4GNevX4dAIMDhw4dhZWUFW1tbPHz4sMq+dXJyeu3y3lTlc+3SpUtVzvHKantuWFhYIC0tTWXci8/0qekcfdGUKVPwxRdfYMCAAThz5swr10vqF9UAvYVMTExgZmaG7777DjY2NkhKSsKiRYveqCx9fX34+/tj/fr1yM3NxcyZMzF8+HBYW1tDLpdDKBQiISEBsbGxSEhIAI/Hg0wmQ1paGsRiMQQCAUpLS5Gamopjx45h586dKuU7OjoiPz8fgOKCXVhYiNWrV+PPP/9Ev379EBISAjMzMwQHB0MgEGDgwIFvvF1cXV0xcOBATJgwAd9++y2kUikWLVqERo0aqZTL5/MxY8YMbNmyBXp6epg+fTo6duxYpYkjKSkJc+bMQU5ODlJSUvD3338jJCQEycnJWLNmDS5fvoy4uDjlXXP//POPyp0hn3zyCQICAtC2bVv4+vpi7969uHv3Lpydnd/4MwKKfbZw4UIsWLAAAoEAvr6+yMzMxN27d+Hq6oqkpCTs378f7dq1w7Fjx6p8iTg6OiI+Ph43btxA48aNIZVKX+vt1RKJBIGBgZg/fz7MzMxgaWmJJUuWgMtV/J5yc3PDqFGjMGbMGISEhKBVq1bIzMxEWFgYmjdvjr59+2LhwoXo2LEjpk+fjvHjx8PAwABRUVE4deoUvvrqqzptn1fFV5vjZMaMGejcuTM2bNiA/v37459//sHx48dVmqjq09SpU7Fp0ybMmDED06dPR0xMDJYvX445c+aAy+VCKpXC398f8+fPh6mpKSwtLbF8+XJwudw6xdS9e3d4e3tj1KhR2LRpE8rLyzF16lR06dKlxmafiIgIhIWFoWfPnrC0tERERAQyMzOVCUZwcDBmzpwJIyMj9OrVCyUlJYiMjERWVhbmzJnzWuXdunXrjT7bzz//jLZt26JTp07Yu3cvLl++jO+//77GZRwdHREREYGEhARIJJKX1jK9//77WLduHX788Uf4+Phgz549uHPnDlq1agWg5nM0MDBQpawZM2ZAJpOhX79+OH78ODp16vRGn5e8AS33QSJv6NSpU8zT05MJhULWvHlzFh4ezgCww4cPv7QTdFZWlkoZFZ1ht2/fzmxtbZm+vj4bOnQoe/bsmXKeHj16MIlEolzP+vXrGQCmp6fHmjdvzrZu3coAMIFAwN599122bds2BoAdO3ZMWcbYsWOVnaUr7mr5+++/mY2NjXK8RCJhs2fPVi6za9euKh1Oq+u8W7kz4rNnz9jHH3/MjIyMmEgkYn5+fso7j14s99ChQ8zZ2ZkJhULWvXt3lpiYqLIeAwMDNnXqVDZ58mTG5/MZn89nn376KZPL5UwulzMTExNmYWHB+Hw+s7CwYADYqlWrquyn1atXM3NzcyaRSJi/vz9bsGBBvdwFJpPJ2KpVq5iDgwPj8/nM3t6eff7554wxxubPn8/MzMyYRCJhI0aMYBs3blTZlsXFxeyDDz5gxsbGDADbtWvXa68/Ly+PjR49monFYmZlZcXWrl2r0oG0tLSULVu2jDk6OjI+n89sbGzY4MGD2a1bt5RlXL58WXl8GRgYsObNm7PVq1crp1fu2Fqf8b3qOGGMse+++441atSIiUQiNmjQILZq1SpmbW392rFU1wm6uo7L4eHhrF27dkwgEDBra2u2cOFCVlZWppyem5vLPvroI2Un/A0bNrD27duzRYsW1bj+6tY3cOBA5u/vzxhjLDExkQ0YMIAZGBgwqVTKhg0bxh4/fqyct7rzLioqivn5+TELCwsmFAqZm5sb27p1q8o8e/fuZS1btmQCgYCZmJiwzp07s19//bXaGGsqrzZ3XFXXCXrbtm2sR48eTCgUMkdHR3bgwIEatxNjjMXExLCOHTsykUikPDequ3YyxtiyZcuYlZUVMzIyYrNnz2bTp09Xiammc7TyNZoxxkJCQphUKlXpnE/Ui8NYpYZMojOCgoJw5MgRehw7IbUwYcIE3Lt3D2fPntV2KAAUnY0bNWqEkJCQKrUKuo7D4eDw4cP/qdf4kPpHTWCEEFKN9evXo0ePHjAwMMDx48exe/fuVz7MT52uX7+Oe/fuoX379sjJycGKFSsAoE7NxoToMkqACCGkGpcvX8batWuRl5cHZ2dnbNmyBePHj9dqTOvXr0dMTAwEAgHatGmDs2fPVul8TwipHWoCI4QQQojOodvgCSGEEKJzKAEihBBCiM6hBIgQQgghOocSIEIIIYToHEqACCGEEKJzKAEihKhFQECAyoPounbtilmzZmk8jvDwcHA4HGRnZ790Hg6HgyNHjtS6zKCgILRs2bJOcSUkJIDD4dCDSAnREkqACNEhAQEB4HA44HA4EAgEcHFxwYoVK1BeXq72df/6669YuXJlreatTdJCCCF1QQ9CJETH9OrVC7t27UJJSQn+/PNPTJs2DXw+H4sXL64yb2lpaZ3fzl7B1NS0XsohhJD6QDVAhOgYoVAIa2trODg4YMqUKejevTt+//13AM+brVavXg1bW1u4u7sDAJKTkzF8+HAYGxvD1NQUAwcOREJCgrJMmUyGOXPmwNjYGGZmZliwYAEqP2O1chNYSUkJFi5cCDs7OwiFQri4uOD7779HQkIC3nvvPQCAiYkJOBwOAgICAAByuRxr1qyBk5MTRCIRWrRogV9++UVlPX/++Sfc3NwgEonw3nvvqcRZWwsXLoSbmxvEYjGcnZ2xdOlSlJWVVZnv22+/hZ2dHcRiMYYPH46cnByV6Tt37oSnpyf09fXh4eGh1VdpEEJUUQJEiI4TiUQoLS1VDoeFhSEmJganTp3C0aNHUVZWBj8/P0ilUpw9exbnz5+HRCJBr169lMuFhIQgNDQUP/zwA86dO4dnz57h8OHDNa53zJgx+Omnn7BlyxZER0fj22+/hUQigZ2dHQ4dOgQAiImJQVpaGjZv3gwAWLNmDX788Ud88803uHv3LmbPno3Ro0fjzJkzABSJ2pAhQ9C/f3/cuHED48ePx6JFi157m0ilUoSGhiIqKgqbN2/Gjh07sHHjRpV5YmNjcfDgQfzxxx/466+/cP36dUydOlU5fe/evVi2bBlWr16N6OhofP7551i6dCl279792vEQQtRAq++iJ4RolL+/Pxs4cCBjjDG5XM5OnTrFhEIhmzdvnnK6lZUVKykpUS7zf//3f8zd3Z3J5XLluJKSEiYSidiJEycYY4zZ2NiwtWvXKqeXlZWxxo0bK9fFGGNdunRhn3zyCWOMsZiYGAaAnTp1qto4T58+zQCwrKws5bji4mImFovZhQsXVOYNDAxkI0eOZIwxtnjxYubl5aUyfeHChVXKqgwAO3z48Eunr1u3jrVp00Y5vHz5csbj8VhKSopy3PHjxxmXy2VpaWmMMcaaNGnC9u3bp1LOypUrmY+PD2OMsfj4eAaAXb9+/aXrJYSoD/UBIkTHHD16FBKJBGVlZZDL5fjoo48QFBSknO7t7a3S7+fmzZuIjY2FVCpVKae4uBhxcXHIyclBWloaOnTooJymp6eHtm3bVmkGq3Djxg3weDx06dKl1nHHxsaisLAQPXr0UBlfWlqKVq1aAQCio6NV4gAAHx+fWq+jwoEDB7BlyxbExcUhPz8f5eXlMDQ0VJnH3t4ejRo1UlmPXC5HTEwMpFIp4uLiEBgYiAkTJijnKS8vh5GR0WvHQwipf5QAEaJj3nvvPXz99dcQCASwtbWFnp7qZcDAwEBlOD8/H23atMHevXurlGVhYfFGMYhEotdeJj8/HwBw7NgxlcQDUPRrqi8XL17EqFGjEBwcDD8/PxgZGWH//v0ICQl57Vh37NhRJSHj8Xj1Fish5M1RAkSIjjEwMICLi0ut52/dujUOHDgAS0vLKrUgFWxsbBAREYHOnTsDUNR0XL16Fa1bt652fm9vb8jlcpw5cwbdu3evMr2iBkomkynHeXl5QSgUIikp6aU1R56ensoO3RUuXbr06g/5ggsXLsDBwQFLlixRjktMTKwyX1JSElJTU2Fra6tcD5fLhbu7O6ysrGBra4uHDx9i1KhRr7V+QohmUCdoQkiNRo0aBXNzcwwcOBBnz55FfHw8wsPDMXPmTKSkpAAAPvnkE3zxxRc4cuQI7t27h6lTp9b4DB9HR0f4+/tj3LhxOHLkiLLMgwcPAgAcHBzA4XBw9OhRZGZmIj8/H1KpFPPmzcPs2bOxe/duxMXF4dq1a9i6dauyY/HkyZPx4MEDzJ8/HzExMdi3bx9CQ0Nf6/O6uroiKSkJ+/fvR1xcHLZs2VJth259fX34+/vj5s2bOHv2LGbOnInhw4fD2toaABAcHIw1a9Zgy5YtuH//Pm7fvo1du3Zhw4YNrxUPIUQ9KAEihNRILBbj33//hb29PYYMGQJPT08EBgaiuLhYWSM0d+5cfPzxx/D394ePjw+kUikGDx5cY7lff/01hg4diqlTp8LDwwMTJkxAQUEBAKBRo0YIDg7GokWLYGVlhenTpwMAVq5ciaVLl2LNmjXw9PREr169cOzYMTg5OQFQ9Ms5dOgQjhw5ghYtWuCbb77B559//lqfd8CAAZg9ezamT5+Oli1b4sKFC1i6dGmV+VxcXDBkyBD06dMHPXv2RPPmzVVucx8/fjx27tyJXbt2wdvbG126dEFoaKgyVkKIdnHYy3opEkIIIYT8R1ENECGEEEJ0DiVAhBBCCNE5lAARQgghROdQAkQIIYQQnUMJECGEEEJ0DiVAhBBCCNE5lAARQgghROdQAkQIIYQQnUMJECGEEEJ0DiVAhBBCCNE5lAARQgghROf8Px0b5kVipLAmAAAAAElFTkSuQmCC\n"},"metadata":{}}]}]} \ No newline at end of file diff --git a/labworks/LW3/best_model_100.keras b/labworks/LW3/best_model_100.keras new file mode 100644 index 0000000..6eb2bba Binary files /dev/null and b/labworks/LW3/best_model_100.keras differ diff --git a/labworks/LW3/images_for_report/1.png b/labworks/LW3/images_for_report/1.png new file mode 100644 index 0000000..8fe8caf Binary files /dev/null and b/labworks/LW3/images_for_report/1.png differ diff --git a/labworks/LW3/images_for_report/2.png b/labworks/LW3/images_for_report/2.png new file mode 100644 index 0000000..91a67ac Binary files /dev/null and b/labworks/LW3/images_for_report/2.png differ diff --git a/labworks/LW3/images_for_report/3.png b/labworks/LW3/images_for_report/3.png new file mode 100644 index 0000000..9a34302 Binary files /dev/null and b/labworks/LW3/images_for_report/3.png differ diff --git a/labworks/LW3/images_for_report/4.png b/labworks/LW3/images_for_report/4.png new file mode 100644 index 0000000..e3283b2 Binary files /dev/null and b/labworks/LW3/images_for_report/4.png differ diff --git a/labworks/LW3/images_for_report/5.png b/labworks/LW3/images_for_report/5.png new file mode 100644 index 0000000..3d02cab Binary files /dev/null and b/labworks/LW3/images_for_report/5.png differ diff --git a/labworks/LW3/images_for_report/6.png b/labworks/LW3/images_for_report/6.png new file mode 100644 index 0000000..dbe2e1c Binary files /dev/null and b/labworks/LW3/images_for_report/6.png differ diff --git a/labworks/LW3/images_for_report/7.png b/labworks/LW3/images_for_report/7.png new file mode 100644 index 0000000..9deb537 Binary files /dev/null and b/labworks/LW3/images_for_report/7.png differ diff --git a/labworks/LW3/images_for_report/8.png b/labworks/LW3/images_for_report/8.png new file mode 100644 index 0000000..40de024 Binary files /dev/null and b/labworks/LW3/images_for_report/8.png differ diff --git a/labworks/LW3/images_for_report/9.png b/labworks/LW3/images_for_report/9.png new file mode 100644 index 0000000..44ac30f Binary files /dev/null and b/labworks/LW3/images_for_report/9.png differ diff --git a/labworks/LW3/report.md b/labworks/LW3/report.md new file mode 100644 index 0000000..95fcfac --- /dev/null +++ b/labworks/LW3/report.md @@ -0,0 +1,611 @@ +# Отчёт по лабораторной работе №3 + +**Кобзев Александр, Кирсанов Егор — А-01-22** + +## 1.1. В среде Google Colab создали новый блокнот (notebook). Импортировали необходимые для работы библиотеки и модули. + +```python +from google.colab import drive +drive.mount('/content/drive') +import os +os.chdir('/content/drive/MyDrive/Colab Notebooks/is_lab3') + +from tensorflow import keras +from tensorflow.keras import layers +from tensorflow.keras.models import Sequential +import matplotlib.pyplot as plt +import numpy as np +from sklearn.metrics import classification_report, confusion_matrix +from sklearn.metrics import ConfusionMatrixDisplay +``` + +--- + +## 1.2. Загрузили набор данных MNIST, содержащий размеченные изображения рукописных цифр. + +```python +from keras.datasets import mnist +(X_train, y_train), (X_test, y_test) = mnist.load_data() +``` + +--- + +## 1.3. Разбили набор данных на обучающие и тестовые данные в соотношении 60 000:10 000 элементов. При разбиении параметр random_state выбрали равным (4k – 1)=39, где k=10 –номер бригады. Вывели размерности полученных обучающих и тестовых массивов данных. + +```python +from sklearn.model_selection import train_test_split +X = np.concatenate((X_train, X_test)) +y = np.concatenate((y_train, y_test)) +X_train, X_test, y_train, y_test = train_test_split(X, y, +test_size = 10000, +train_size = 60000, +random_state = 39) +# вывод размерностей +print('Shape of X train:', X_train.shape) +print('Shape of y train:', y_train.shape) +print('Shape of X test:', X_test.shape) +print('Shape of y test:', y_test.shape) +``` + +``` +Shape of X train: (60000, 28, 28) +Shape of y train: (60000,) +Shape of X test: (10000, 28, 28) +Shape of y test: (10000,) +``` + +--- + +## 1.4. Провели предобработку данных: привели обучающие и тестовые данные к формату, пригодному для обучения сверточной нейронной сети. Входные данные принимают значения от 0 до 1, метки цифр закодированы по принципу «one-hot encoding». Вывели размерности предобработанных обучающих и тестовых массивов данных. + +```python +# Зададим параметры данных и модели +num_classes = 10 +input_shape = (28, 28, 1) +# Приведение входных данных к диапазону [0, 1] +X_train = X_train / 255 +X_test = X_test / 255 +# Расширяем размерность входных данных, чтобы каждое изображение имело размерность (высота, ширина, количество каналов) + +X_train = np.expand_dims(X_train, -1) +X_test = np.expand_dims(X_test, -1) +print('Shape of transformed X train:', X_train.shape) +print('Shape of transformed X test:', X_test.shape) +# переведем метки в one-hot +y_train = keras.utils.to_categorical(y_train, num_classes) +y_test = keras.utils.to_categorical(y_test, num_classes) +print('Shape of transformed y train:', y_train.shape) +print('Shape of transformed y test:', y_test.shape) +``` + +``` +Shape of transformed X train: (60000, 28, 28, 1) +Shape of transformed X test: (10000, 28, 28, 1) +Shape of transformed y train: (60000, 10) +Shape of transformed y test: (10000, 10) +``` + +--- + +## 1.5. Реализовали модель сверточной нейронной сети и обучили ее на обучающих данных с выделением части обучающих данных в качестве валидационных. Вывели информацию об архитектуре нейронной сети. + +```python +# создаем модель +model = Sequential() +model.add(layers.Conv2D(32, kernel_size=(3, 3), activation="relu", input_shape=input_shape)) +model.add(layers.MaxPooling2D(pool_size=(2, 2))) +model.add(layers.Conv2D(64, kernel_size=(3, 3), activation="relu")) +model.add(layers.MaxPooling2D(pool_size=(2, 2))) +model.add(layers.Dropout(0.5)) +model.add(layers.Flatten()) +model.add(layers.Dense(num_classes, activation="softmax")) + +model.summary() +``` + +``` +Model: "sequential_2" +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓ +┃ Layer (type) ┃ Output Shape ┃ Param # ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩ +│ conv2d_4 (Conv2D) │ (None, 26, 26, 32) │ 320 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ max_pooling2d_4 (MaxPooling2D) │ (None, 13, 13, 32) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ conv2d_5 (Conv2D) │ (None, 11, 11, 64) │ 18,496 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ max_pooling2d_5 (MaxPooling2D) │ (None, 5, 5, 64) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dropout_2 (Dropout) │ (None, 5, 5, 64) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ flatten_2 (Flatten) │ (None, 1600) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dense_2 (Dense) │ (None, 10) │ 16,010 │ +└─────────────────────────────────┴────────────────────────┴───────────────┘ + Total params: 34,826 (136.04 KB) + Trainable params: 34,826 (136.04 KB) + Non-trainable params: 0 (0.00 B) +``` + +```python +# компилируем и обучаем модель +batch_size = 512 +epochs = 15 +model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"]) +model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1) +``` + +--- + +## 1.6. Оценили качество обучения на тестовых данных. Вывели значение функции ошибки и значение метрики качества классификации на тестовых данных. + +```python +# Оценка качества работы модели на тестовых данных +scores = model.evaluate(X_test, y_test) +print('Loss on test data:', scores[0]) +print('Accuracy on test data:', scores[1]) +``` + +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9883 - loss: 0.0410 +Loss on test data: 0.04110224172472954 +Accuracy on test data: 0.988099992275238 +``` + +--- + +## 1.7. Подали на вход обученной модели два тестовых изображения. Вывели изображения, истинные метки и результаты распознавания. + +```python +for n in [123,321]: + result = model.predict(X_test[n:n+1]) + print('NN output:', result) + + plt.imshow(X_test[n].reshape(28,28), cmap=plt.get_cmap('gray')) + plt.show() + print('Real mark: ', np.argmax(y_test[n])) + print('NN answer: ', np.argmax(result)) +``` + +![image](images_for_report/1.png) + +``` +Real mark: 6 +NN answer: 6 +``` + +![image](images_for_report/2.png) + +``` +Real mark: 4 +NN answer: 4 +``` + +--- + +## 1.8. Вывели отчет о качестве классификации тестовой выборки и матрицу ошибок для тестовой выборки. + +```python +# истинные метки классов +true_labels = np.argmax(y_test, axis=1) +# предсказанные метки классов +predicted_labels = np.argmax(model.predict(X_test), axis=1) +# отчет о качестве классификации +print(classification_report(true_labels, predicted_labels)) +# вычисление матрицы ошибок +conf_matrix = confusion_matrix(true_labels, predicted_labels) +# отрисовка матрицы ошибок в виде "тепловой карты" +display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix) +display.plot() +plt.show() +``` + +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step + precision recall f1-score support + + 0 0.99 0.99 0.99 990 + 1 0.99 0.99 0.99 1155 + 2 0.99 0.99 0.99 1025 + 3 0.99 0.99 0.99 1016 + 4 0.99 0.99 0.99 959 + 5 0.99 0.99 0.99 889 + 6 0.99 0.99 0.99 997 + 7 0.99 0.98 0.98 1034 + 8 0.99 0.98 0.98 991 + 9 0.99 0.98 0.98 944 + + accuracy 0.99 10000 + macro avg 0.99 0.99 0.99 10000 +weighted avg 0.99 0.99 0.99 10000 +``` + +![image](images_for_report/3.png) + +--- + +## 1.9. Загрузили, предобработали и подали на вход обученной нейронной сети собственное изображение, созданное при выполнении лабораторной работы №1. Вывели изображение и результат распознавания. + +```python +# загрузка собственного изображения +from PIL import Image +file_data = Image.open('/content/drive/MyDrive/Colab Notebooks/IS_lab_4.png') +file_data = file_data.convert('L') # перевод в градации серого +test_img = np.array(file_data) +# вывод собственного изображения +plt.imshow(test_img, cmap=plt.get_cmap('gray')) +plt.show() +# предобработка +test_img = test_img / 255 +test_img = np.reshape(test_img, (1,28,28,1)) +# распознавание +result = model.predict(test_img) +print('I think it\'s ', np.argmax(result)) +``` + +![image](images_for_report/4.png) + +``` +I think it's 4 +``` + +```python +from PIL import Image +file_data = Image.open('/content/drive/MyDrive/Colab Notebooks/IS_lab_7.png') +file_data = file_data.convert('L') # перевод в градации серого +test_img = np.array(file_data) +# вывод собственного изображения +plt.imshow(test_img, cmap=plt.get_cmap('gray')) +plt.show() +# предобработка +test_img = test_img / 255 +test_img = np.reshape(test_img, (1,28,28,1)) +# распознавание +result = model.predict(test_img) +print('I think it\'s ', np.argmax(result)) +``` + +![image](images_for_report/5.png) + +``` +I think it's 7 +``` + +--- + +## 1.10. Загрузили с диска модель, сохраненную при выполнении лабораторной работы №1. Вывели информацию об архитектуре модели. Повторили для этой модели п. 6. + +```python +model_lr1 = keras.models.load_model("/content/drive/MyDrive/Colab Notebooks/best_model_100.keras") +model_lr1.summary() +``` + +``` +Model: "sequential_16" +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓ +┃ Layer (type) ┃ Output Shape ┃ Param # ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩ +│ dense_26 (Dense) │ (None, 100) │ 78,500 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dense_27 (Dense) │ (None, 10) │ 1,010 │ +└─────────────────────────────────┴────────────────────────┴───────────────┘ + Total params: 79,512 (310.60 KB) + Trainable params: 79,510 (310.59 KB) + Non-trainable params: 0 (0.00 B) + Optimizer params: 2 (12.00 B) +``` + +```python +X_train_flat = X.reshape(70000, 28*28) +X_train_flat = X_train_flat / 255.0 +X_train_flat, X_test_flat, y_train_flat, y_test_flat = train_test_split( + X_train_flat, y, test_size=10000, train_size=60000, random_state=39 +) +y_train_flat = keras.utils.to_categorical(y_train_flat, num_classes) +y_test_flat = keras.utils.to_categorical(y_test_flat, num_classes) +print('Shape of transformed X train:', X_train_flat.shape) +print('Shape of transformed X test:', X_test_flat.shape) +print('Shape of transformed y train:', y_train_flat.shape) +print('Shape of transformed y test:', y_test_flat.shape) +``` + +``` +Shape of transformed X train: (60000, 784) +Shape of transformed X test: (10000, 784) +Shape of transformed y train: (60000, 10) +Shape of transformed y test: (10000, 10) +``` + +```python +scores = model_lr1.evaluate(X_test_flat, y_test_flat) +print('Loss on test data:', scores[0]) +print('Accuracy on test data:', scores[1]) +``` + +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9153 - loss: 0.3012 +Loss on test data: 0.2998492121696472 +Accuracy on test data: 0.9138000011444092 +``` + +--- + +## 1.11. Сравнить обученную модель сверточной сети и наилучшую модель полносвязной сети из лабораторной работы №1 по следующим показателям: +- количество настраиваемых параметров в сети +- количество эпох обучения +- качество классификации тестовой выборки. + +| Модель | Количество настраиваемых параметров | Количество эпох обучения | Качество классификации тестовой выборки | +|----------|-------------------------------------|---------------------------|-----------------------------------------| +| Сверточная | 34 826 | 15 | accuracy: 0.9880; loss: 0.041 | +| Полносвязная | 79,512 | 150 | accuracy: 0.914; loss: 0.299 | + +### Сверточная нейронная сеть показала себя более эффективной: она обучается быстрее, требует меньше параметров и при этом обеспечивает более высокое качество распознавания изображений по сравнению с полносвязной моделью. + +--- + +## 2. Изменили изменив набор данных MNIST на CIFAR-10 +### При этом: +- в п. 3 разбиение данных на обучающие и тестовые произвести в соотношении 50 000:10 000 +- после разбиения данных (между п. 3 и 4) вывести 25 изображений из обучающей выборки с подписями классов +- в п. 7 одно из тестовых изображений должно распознаваться корректно, а другое – ошибочно. + +--- + +## 2.1. Загрузили набор данных CIFAR-10, содержащий цветные изображения размеченные на 10 классов: самолет, автомобиль, птица, кошка, олень, собака, лягушка, лошадь, корабль, грузовик. + +```python +from keras.datasets import cifar10 +(X_train, y_train), (X_test, y_test) = cifar10.load_data() +``` + +--- + +## 2.2. Разбили набор данных на обучающие и тестовые данные в соотношении 60 000:10 000 элементов. Параметр random_state выбрали равным (4k – 1)=39, где k=10 – номер бригады. Вывели размерности полученных обучающих и тестовых массивов данных. + +```python +# создание своего разбиения датасета +# объединяем в один набор +X = np.concatenate((X_train, X_test)) +y = np.concatenate((y_train, y_test)) + +# разбиваем по вариантам +X_train, X_test, y_train, y_test = train_test_split( + X, y, test_size=10000, train_size=50000, random_state=39 +) +# вывод размерностей +print('Shape of X train:', X_train.shape) +print('Shape of y train:', y_train.shape) +print('Shape of X test:', X_test.shape) +print('Shape of y test:', y_test.shape) +``` + +``` +Shape of X train: (50000, 32, 32, 3) +Shape of y train: (50000, 1) +Shape of X test: (10000, 32, 32, 3) +Shape of y test: (10000, 1) +``` + +### Вывели 25 изображений из обучающей выборки с подписями классов: + +```python +class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', +'dog', 'frog', 'horse', 'ship', 'truck'] +plt.figure(figsize=(10,10)) +for i in range(25): + plt.subplot(5,5,i+1) + plt.xticks([]) + plt.yticks([]) + plt.grid(False) + plt.imshow(X_train[i]) + plt.xlabel(class_names[y_train[i][0]]) +plt.show() +``` + +![image](images_for_report/6.png) + +--- + +## 2.3. Провели предобработку данных: привели обучающие и тестовые данные к формату, пригодному для обучения сверточной нейронной сети. Входные данные принимают значения от 0 до 1, метки цифр закодированы по принципу «one-hot encoding». Вывели размерности предобработанных обучающих и тестовых массивов данных. + +```python +# Зададим параметры данных и модели +num_classes = 10 +input_shape = (32, 32, 3) + +# Приведение входных данных к диапазону [0, 1] +X_train = X_train / 255.0 +X_test = X_test / 255.0 + +print('Shape of transformed X train:', X_train.shape) +print('Shape of transformed X test:', X_test.shape) + +# Переводим метки в one-hot encoding +y_train = keras.utils.to_categorical(y_train, num_classes) +y_test = keras.utils.to_categorical(y_test, num_classes) +print('Shape of transformed y train:', y_train.shape) +print('Shape of transformed y test:', y_test.shape) +``` + +``` +Shape of transformed X train: (50000, 32, 32, 3) +Shape of transformed X test: (10000, 32, 32, 3) +Shape of transformed y train: (50000, 10) +Shape of transformed y test: (10000, 10) +``` + +--- + +## 2.4. Реализовали модель сверточной нейронной сети и обучили ее на обучающих данных с выделением части обучающих данных в качестве валидационных. Вывели информацию об архитектуре нейронной сети. + +```python +model = Sequential() + +model.add(layers.Conv2D(32, (3,3), padding="same", activation="relu", + input_shape=input_shape)) +model.add(layers.BatchNormalization()) +model.add(layers.Conv2D(32, (3,3), padding="same", activation="relu")) +model.add(layers.BatchNormalization()) +model.add(layers.BatchNormalization()) +model.add(layers.Dropout(0.25)) + + +model.add(layers.Conv2D(64, (3,3), padding="same", activation="relu")) +model.add(layers.Conv2D(64, (3,3), padding="same", activation="relu")) +model.add(layers.MaxPooling2D((2,2))) +model.add(layers.Dropout(0.25)) + +model.add(layers.Conv2D(128, (3,3), padding="same", activation="relu")) +model.add(layers.MaxPooling2D((2,2))) +model.add(layers.Dropout(0.25)) + +model.add(layers.Flatten()) +model.add(layers.Dense(128, activation="relu")) +model.add(layers.Dropout(0.5)) +model.add(layers.Dense(num_classes, activation="softmax")) +model.summary() +``` + +``` +Model: "sequential_15" +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓ +┃ Layer (type) ┃ Output Shape ┃ Param # ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩ +│ conv2d_52 (Conv2D) │ (None, 32, 32, 32) │ 896 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ batch_normalization_29 │ (None, 32, 32, 32) │ 128 │ +│ (BatchNormalization) │ │ │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ conv2d_53 (Conv2D) │ (None, 32, 32, 32) │ 9,248 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ batch_normalization_30 │ (None, 32, 32, 32) │ 128 │ +│ (BatchNormalization) │ │ │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ batch_normalization_31 │ (None, 32, 32, 32) │ 128 │ +│ (BatchNormalization) │ │ │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dropout_37 (Dropout) │ (None, 32, 32, 32) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ conv2d_54 (Conv2D) │ (None, 32, 32, 64) │ 18,496 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ conv2d_55 (Conv2D) │ (None, 32, 32, 64) │ 36,928 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ max_pooling2d_34 (MaxPooling2D) │ (None, 16, 16, 64) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dropout_38 (Dropout) │ (None, 16, 16, 64) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ conv2d_56 (Conv2D) │ (None, 16, 16, 128) │ 73,856 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ max_pooling2d_35 (MaxPooling2D) │ (None, 8, 8, 128) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dropout_39 (Dropout) │ (None, 8, 8, 128) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ flatten_15 (Flatten) │ (None, 8192) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dense_27 (Dense) │ (None, 128) │ 1,048,704 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dropout_40 (Dropout) │ (None, 128) │ 0 │ +├─────────────────────────────────┼────────────────────────┼───────────────┤ +│ dense_28 (Dense) │ (None, 10) │ 1,290 │ +└─────────────────────────────────┴────────────────────────┴───────────────┘ + Total params: 1,189,802 (4.54 MB) + Trainable params: 1,189,610 (4.54 MB) + Non-trainable params: 192 (768.00 B) +``` + +```python +# компилируем и обучаем модель +model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"]) +model.fit(X_train, y_train, batch_size=64, validation_split=0.1, epochs=50) +``` + +--- + +## 2.5. Оценили качество обучения на тестовых данных. Вывели значение функции ошибки и значение метрики качества классификации на тестовых данных. + +```python +# Оценка качества работы модели на тестовых данных +scores = model.evaluate(X_test, y_test) +print('Loss on test data:', scores[0]) +print('Accuracy on test data:', scores[1]) +``` + +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.7982 - loss: 0.6423 +Loss on test data: 0.6325967311859131 +Accuracy on test data: 0.8019000291824341 +``` + +--- + +## 2.6. Подали на вход обученной модели два тестовых изображения. Вывели изображения, истинные метки и результаты распознавания. + +```python +# вывод двух тестовых изображений и результатов распознавания +for n in [7, 16]: + result = model.predict(X_test[n:n+1]) + plt.imshow(X_test[n].reshape(32,32,3), cmap=plt.get_cmap('gray')) + plt.show() + print('Real mark: ', np.argmax(y_test[n])) + print('NN answer: ', np.argmax(result)) +``` + +![image](images_for_report/7.png) + +``` +Real mark: 4 +NN answer: 0 +``` + +![image](images_for_report/8.png) + +``` +Real mark: 4 +NN answer: 4 +``` + +--- + +## 2.7. Вывели отчет о качестве классификации тестовой выборки и матрицу ошибок для тестовой выборки. + +```python +# истинные метки классов +true_labels = np.argmax(y_test, axis=1) +# предсказанные метки классов +predicted_labels = np.argmax(model.predict(X_test), axis=1) +# отчет о качестве классификации +print(classification_report(true_labels, predicted_labels, target_names=class_names)) +# вычисление матрицы ошибок +conf_matrix = confusion_matrix(true_labels, predicted_labels) +# отрисовка матрицы ошибок в виде "тепловой карты" +display = ConfusionMatrixDisplay(confusion_matrix=conf_matrix, display_labels=class_names) +display.plot() +plt.show() +``` + +``` +313/313 ━━━━━━━━━━━━━━━━━━━━ 4s 8ms/step + precision recall f1-score support + + airplane 0.78 0.85 0.81 983 + automobile 0.90 0.93 0.91 1026 + bird 0.73 0.69 0.71 1007 + cat 0.63 0.64 0.64 1011 + deer 0.81 0.75 0.78 985 + dog 0.70 0.71 0.71 974 + frog 0.86 0.79 0.82 1007 + horse 0.81 0.84 0.83 982 + ship 0.88 0.93 0.90 1026 + truck 0.92 0.88 0.90 999 + + accuracy 0.80 10000 + macro avg 0.80 0.80 0.80 10000 +weighted avg 0.80 0.80 0.80 10000 + +``` + +![image](images_for_report/9.png) + + +### Модель успешно обучилась распознавать изображения из CIFAR-10, однако справляется с задачей хуже, чем на MNIST. Это связано с тем, что цветные изображения сложнее и содержат больше разнообразия, поэтому нейросети требуется более глубокая архитектура и больше ресурсов для достижения высокой точности. \ No newline at end of file