{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":21154,"databundleVersionId":1243559,"sourceType":"competition"}],"dockerImageVersionId":30617,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import tensorflow as tf\n# последовательная модель (стек слоев)\nfrom tensorflow.keras.models import Sequential, Model\n# полносвязный слой и слой выпрямляющий матрицу в вектор\nfrom tensorflow.keras.layers import Dense, Flatten, Input\n# слой выключения нейронов и слой нормализации выходных данных (нормализует данные в пределах текущей выборки)\nfrom tensorflow.keras.layers import Dropout, BatchNormalization, SpatialDropout2D, GaussianDropout\n# слои свертки и подвыборки\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, AveragePooling2D\n# работа с обратной связью от обучающейся нейронной сети\nfrom tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\n# вспомогательные инструменты\nfrom tensorflow.keras import utils\nfrom tensorflow.keras.regularizers import *\nimport numpy as np\nimport os\n\n#  библиотека для работы с наборами данных на Kaggle\nfrom kaggle_datasets import KaggleDatasets\nimport matplotlib.pyplot as plt\n%matplotlib inline \nprint(\"Tensorflow version \" + tf.__version__)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-10T11:18:53.472342Z","iopub.execute_input":"2023-12-10T11:18:53.473051Z","iopub.status.idle":"2023-12-10T11:18:53.482447Z","shell.execute_reply.started":"2023-12-10T11:18:53.473011Z","shell.execute_reply":"2023-12-10T11:18:53.481561Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Обнаружение оборудования, возврат соответствующей стратегии распространения: TPU, GPU, CPU\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()  # Обнаружение TPU. Параметры среды не требуются, если задана переменная среды TPU_NAME. На Kaggle это всегда так.\n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() # стратегия распространения по умолчанию в Tensorflow. Работает на CPU и одном GPU.\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"execution":{"iopub.status.busy":"2023-12-10T11:19:09.513398Z","iopub.execute_input":"2023-12-10T11:19:09.513781Z","iopub.status.idle":"2023-12-10T11:19:17.647844Z","shell.execute_reply.started":"2023-12-10T11:19:09.513749Z","shell.execute_reply":"2023-12-10T11:19:17.646887Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started') #получаем путь к наборам данных\nprint(GCS_DS_PATH)","metadata":{"execution":{"iopub.status.busy":"2023-12-10T11:19:31.390984Z","iopub.execute_input":"2023-12-10T11:19:31.391422Z","iopub.status.idle":"2023-12-10T11:19:31.396939Z","shell.execute_reply.started":"2023-12-10T11:19:31.391382Z","shell.execute_reply":"2023-12-10T11:19:31.395929Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [192, 192] # при таком размере графическому процессору не хватит памяти. Используйте TPU\nEPOCHS = 80\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nNUM_TRAINING_IMAGES = 12753\nNUM_TEST_IMAGES = 7382\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE # находим количество шагов за эпоху","metadata":{"execution":{"iopub.status.busy":"2023-12-10T11:19:38.610163Z","iopub.execute_input":"2023-12-10T11:19:38.610591Z","iopub.status.idle":"2023-12-10T11:19:38.615473Z","shell.execute_reply.started":"2023-12-10T11:19:38.610556Z","shell.execute_reply":"2023-12-10T11:19:38.614704Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def decode_image(image_data):\n    \"\"\"Декодирует изображение в vyjujvthye. vfnhbwe (тензор)\n    Нормализует данные и преобразовывает изображения к указанному размеру\"\"\"\n    image = tf.image.decode_jpeg(image_data, channels=3) # Декодирование изображения в формате JPEG в тензор uint8.\n    image = tf.cast(image, tf.float32) / 255.0  # преобразовать изображение в плавающее в диапазоне [0, 1]\n    image = tf.reshape(image, [*IMAGE_SIZE, 3]) # явный размер, необходимый для TPU\n#     image = tf.keras.applications.inception_resnet_v2.preprocess_input(image)\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string означает байтовую строку\n        \"class\": tf.io.FixedLenFeature([], tf.int64),  # [] означает отдельный элемент\n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT) # парсим отдельный пример в указанном формате\n    image = decode_image(example['image']) # преобразуем изображение к нужному нам формату\n    label = tf.cast(example['class'], tf.int32)\n    return image, label # возвращает набор данных пар (изображение, метка)\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string означает байтовую строку\n        \"id\": tf.io.FixedLenFeature([], tf.string),  # [] означает отдельный элемент\n        # класс отсутствует, задача этого конкурса - предсказать классы цветов для тестового набора данных\n    }\n    example = tf.io.parse_single_example(example, UNLABELED_TFREC_FORMAT)\n    image = decode_image(example['image']) # преобразуем изображение к нужному нам формату\n    idnum = example['id']\n    return image, idnum # returns a dataset of image(s)\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    \"\"\"Читает из TFRecords. Для оптимальной производительности одновременное чтение из нескольких\n    файлов без учета порядка данных. Порядок не имеет значения, поскольку мы все равно будем перетасовывать данные\"\"\"\n\n    ignore_order = tf.data.Options() # Представляет параметры для tf.data.Dataset.\n    if not ordered:\n        ignore_order.experimental_deterministic = False # отключить порядок, увеличить скорость\n\n    dataset = tf.data.TFRecordDataset(filenames) # автоматически чередует чтение из нескольких файлов\n    dataset = dataset.with_options(ignore_order) # использует данные сразу после их поступления, а не в исходном порядке\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord)\n    # возвращает набор данных пар (изображение, метка), если метка = Истина, или пар (изображение, идентификатор), если метка = Ложь\n    return dataset\n\ndef get_training_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-192x192/train/*.tfrec'), labeled=True)\n    dataset = dataset.repeat() # набор обучающих данных должен повторяться в течение нескольких эпох\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    return dataset\n\ndef get_validation_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-192x192/val/*.tfrec'), labeled=True, ordered=False)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache() # кешируем набор\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-192x192/test/*.tfrec'), labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    return dataset\n\ntraining_dataset = get_training_dataset()\nvalidation_dataset = get_validation_dataset()","metadata":{"execution":{"iopub.status.busy":"2023-12-10T11:19:41.671412Z","iopub.execute_input":"2023-12-10T11:19:41.672169Z","iopub.status.idle":"2023-12-10T11:19:41.858825Z","shell.execute_reply.started":"2023-12-10T11:19:41.672131Z","shell.execute_reply":"2023-12-10T11:19:41.857772Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"AUTOTUNE = tf.data.AUTOTUNE\n\ndata_augmentation = tf.keras.Sequential([\n  tf.keras.layers.RandomFlip(\"horizontal\"),\n  tf.keras.layers.RandomRotation(0.2),\n  tf.keras.layers.RandomZoom(0.2),\n])\n\n\ndef prepare(ds,  augment=False):\n  # Batch all datasets.\n  #ds = ds.batch(BATCH_SIZE)\n\n  # Use data augmentation only on the training set.\n  if augment:\n    ds = ds.map(lambda x, y: (data_augmentation(x, training=True), y),\n                num_parallel_calls=AUTOTUNE)\n\n  # Use buffered prefetching on all datasets.\n  return ds.prefetch(buffer_size=AUTOTUNE)\n\ntrain_ds = prepare(training_dataset, augment=True)","metadata":{"execution":{"iopub.status.busy":"2023-12-10T11:19:48.816492Z","iopub.execute_input":"2023-12-10T11:19:48.816897Z","iopub.status.idle":"2023-12-10T11:19:49.293985Z","shell.execute_reply.started":"2023-12-10T11:19:48.816865Z","shell.execute_reply":"2023-12-10T11:19:49.292940Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_custom_model_complex():\n    # Создаем новую последовательную модель\n    model = Sequential()\n\n    # Первый сверточный блок\n    model.add(Conv2D(64, (3, 3), input_shape=(*IMAGE_SIZE, 3), activation='relu'))\n    model.add(BatchNormalization())\n    model.add(Conv2D(64, (3, 3), activation='relu'))\n    model.add(BatchNormalization())\n    model.add(MaxPooling2D(pool_size=(2, 2)))\n    model.add(Dropout(0.25))\n\n    # Второй сверточный блок\n    model.add(Conv2D(128, (3, 3), activation='relu'))\n    model.add(BatchNormalization())\n    model.add(Conv2D(128, (3, 3), activation='relu'))\n    model.add(BatchNormalization())\n    model.add(MaxPooling2D(pool_size=(2, 2)))\n    model.add(Dropout(0.35))\n\n    # Третий сверточный блок\n    model.add(Conv2D(256, (3, 3), activation='relu'))\n    model.add(BatchNormalization())\n    model.add(Conv2D(256, (3, 3), activation='relu'))\n    model.add(BatchNormalization())\n    model.add(Conv2D(256, (3, 3), activation='relu'))\n    model.add(BatchNormalization())\n    model.add(MaxPooling2D(pool_size=(2, 2)))\n    model.add(Dropout(0.45))\n\n    # Полносвязный блок\n    model.add(Flatten())\n    model.add(Dense(512, activation='relu'))\n    model.add(BatchNormalization())\n    model.add(Dropout(0.5))\n\n    model.add(Dense(104, activation='softmax'))\n\n    return model\n\n# Создаем кастомную модель\ncustom_model_complex = get_custom_model_complex()\n\n# Выводим сводку кастомной модели\ncustom_model_complex.summary()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    model =  get_custom_model_complex()\n\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2023-12-10T11:22:41.163824Z","iopub.execute_input":"2023-12-10T11:22:41.164213Z","iopub.status.idle":"2023-12-10T11:22:58.337113Z","shell.execute_reply.started":"2023-12-10T11:22:41.164180Z","shell.execute_reply":"2023-12-10T11:22:58.335823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"callbacks_list = [EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True),\n                  ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3)]\n\nmodel.compile(\n    optimizer='nadam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\n\nhistorical = model.fit(train_ds,\n          steps_per_epoch=STEPS_PER_EPOCH,\n          epochs=EPOCHS,\n          callbacks=callbacks_list,\n          validation_data=validation_dataset)","metadata":{"execution":{"iopub.status.busy":"2023-12-10T11:23:39.091958Z","iopub.execute_input":"2023-12-10T11:23:39.092420Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True) \n\nprint('Вычисляем предсказания...')\ntest_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = model.predict(test_images_ds)\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)\n\nprint('Создание файла submission.csv...')\ntest_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()\ntest_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U') # все в одной партии\nnp.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"![image.png](attachment:c8b9eebb-d8f8-46fb-abd5-7b48984d7f3b.png)","metadata":{},"attachments":{"c8b9eebb-d8f8-46fb-abd5-7b48984d7f3b.png":{"image/png":"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"}}}]}