{"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":30615,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip install -q efficientnet","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-09T12:21:16.576001Z","iopub.execute_input":"2023-12-09T12:21:16.577290Z","iopub.status.idle":"2023-12-09T12:21:23.732337Z","shell.execute_reply.started":"2023-12-09T12:21:16.577210Z","shell.execute_reply":"2023-12-09T12:21:23.731383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.applications import DenseNet201 \nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras import layers\nfrom tensorflow.keras.layers import Dense, Flatten\nfrom tensorflow.keras.layers import Dropout, BatchNormalization, GaussianDropout\nfrom tensorflow.keras.layers import GlobalAveragePooling2D\nfrom tensorflow.keras.callbacks import ModelCheckpoint\n#  библиотека для работы с наборами данных на Kaggle\nfrom kaggle_datasets import KaggleDatasets\nimport re\nimport numpy as np\nimport random\nimport matplotlib.pyplot as plt\n%matplotlib inline \nprint(\"Tensorflow version \" + tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:21:23.734128Z","iopub.execute_input":"2023-12-09T12:21:23.734387Z","iopub.status.idle":"2023-12-09T12:21:40.049336Z","shell.execute_reply.started":"2023-12-09T12:21:23.734358Z","shell.execute_reply":"2023-12-09T12:21:40.048648Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"MODEL_CLASS = DenseNet201","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:21:40.050210Z","iopub.execute_input":"2023-12-09T12:21:40.050805Z","iopub.status.idle":"2023-12-09T12:21:40.054331Z","shell.execute_reply.started":"2023-12-09T12:21:40.050775Z","shell.execute_reply":"2023-12-09T12:21:40.053650Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"AUTO = tf.data.experimental.AUTOTUNE\n# 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.\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:21:40.056007Z","iopub.execute_input":"2023-12-09T12:21:40.056231Z","iopub.status.idle":"2023-12-09T12:21:49.175693Z","shell.execute_reply.started":"2023-12-09T12:21:40.056207Z","shell.execute_reply":"2023-12-09T12:21:49.174832Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_DS_PATH = '/kaggle/input/tpu-getting-started'\nGCS_DS_PATH_EXT = 'tf-flower-photo-tfrec'\nIMAGE_SIZE = [512, 512] # при таком размере графическому процессору не хватит памяти. Используйте TPU\nEPOCHS = 35\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nGCS_PATH_SELECT = { # available image sizes\n    192: GCS_DS_PATH + '/tfrecords-jpeg-192x192',\n    224: GCS_DS_PATH + '/tfrecords-jpeg-224x224',\n    331: GCS_DS_PATH + '/tfrecords-jpeg-331x331',\n    512: GCS_DS_PATH + '/tfrecords-jpeg-512x512'\n}\nGCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]]\n\n# External data\nGCS_PATH_SELECT_EXT = {\n    192: '/tfrecords-jpeg-192x192',\n    224: '/tfrecords-jpeg-224x224',\n    331: '/tfrecords-jpeg-331x331',\n    512: '/tfrecords-jpeg-512x512'\n}\nGCS_PATH_EXT = GCS_PATH_SELECT_EXT[IMAGE_SIZE[0]]\n\nIMAGENET_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/imagenet' + GCS_PATH_EXT + '/*.tfrec')\nINATURELIST_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/inaturalist' + GCS_PATH_EXT + '/*.tfrec')\nOPENIMAGE_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/openimage' + GCS_PATH_EXT + '/*.tfrec')\nOXFORD_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/oxford_102' + GCS_PATH_EXT + '/*.tfrec')\nTENSORFLOW_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/tf_flowers' + GCS_PATH_EXT + '/*.tfrec')\n\nADDITIONAL_TRAINING_FILENAMES = IMAGENET_FILES + INATURELIST_FILES + OPENIMAGE_FILES + OXFORD_FILES + TENSORFLOW_FILES  \n\nCLASSES = ['pink primrose',    'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea',     'wild geranium',     'tiger lily',           'moon orchid',              'bird of paradise', 'monkshood',        'globe thistle',         # 00 - 09\n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily', # 10 - 19\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',         # 20 - 29\n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',           # 30 - 39\n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',      # 40 - 49\n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',    # 50 - 59\n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',            # 60 - 69\n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',             # 70 - 79\n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',            # 80 - 89\n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',        # 90 - 99\n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']                          # 100 - 102\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') # predictions on this dataset should be submitted for the competition \n\nTRAINING_FILENAMES = TRAINING_FILENAMES + ADDITIONAL_TRAINING_FILENAMES","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:21:49.176861Z","iopub.execute_input":"2023-12-09T12:21:49.177105Z","iopub.status.idle":"2023-12-09T12:21:49.215770Z","shell.execute_reply.started":"2023-12-09T12:21:49.177079Z","shell.execute_reply":"2023-12-09T12:21:49.214943Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def random_blockout(img, sl=0.1, sh=0.2, rl=0.4):\n    p=random.random()\n    if p>=0.25:\n        w, h, c = IMAGE_SIZE[0], IMAGE_SIZE[1], 3\n        origin_area = tf.cast(h*w, tf.float32)\n\n        e_size_l = tf.cast(tf.round(tf.sqrt(origin_area * sl * rl)), tf.int32)\n        e_size_h = tf.cast(tf.round(tf.sqrt(origin_area * sh / rl)), tf.int32)\n\n        e_height_h = tf.minimum(e_size_h, h)\n        e_width_h = tf.minimum(e_size_h, w)\n\n        erase_height = tf.random.uniform(shape=[], minval=e_size_l, maxval=e_height_h, dtype=tf.int32)\n        erase_width = tf.random.uniform(shape=[], minval=e_size_l, maxval=e_width_h, dtype=tf.int32)\n\n        erase_area = tf.zeros(shape=[erase_height, erase_width, c])\n        erase_area = tf.cast(erase_area, tf.uint8)\n\n        pad_h = h - erase_height\n        pad_top = tf.random.uniform(shape=[], minval=0, maxval=pad_h, dtype=tf.int32)\n        pad_bottom = pad_h - pad_top\n\n        pad_w = w - erase_width\n        pad_left = tf.random.uniform(shape=[], minval=0, maxval=pad_w, dtype=tf.int32)\n        pad_right = pad_w - pad_left\n\n        erase_mask = tf.pad([erase_area], [[0,0],[pad_top, pad_bottom], [pad_left, pad_right], [0,0]], constant_values=1)\n        erase_mask = tf.squeeze(erase_mask, axis=0)\n        erased_img = tf.multiply(tf.cast(img,tf.float32), tf.cast(erase_mask, tf.float32))\n\n        return tf.cast(erased_img, img.dtype)\n    else:\n        return tf.cast(img, img.dtype)","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:21:49.216926Z","iopub.execute_input":"2023-12-09T12:21:49.217214Z","iopub.status.idle":"2023-12-09T12:21:49.228336Z","shell.execute_reply.started":"2023-12-09T12:21:49.217172Z","shell.execute_reply":"2023-12-09T12:21:49.227545Z"},"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, num_parallel_reads=AUTO) # 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, num_parallel_calls=AUTO)\n    # возвращает набор данных пар (изображение, метка), если метка = Истина, или пар (изображение, идентификатор), если метка = Ложь\n    return dataset\n\ndef data_augment(image, label):\n    # data augmentation. Thanks to the dataset.prefetch(AUTO) statement in the next function (below),\n    # this happens essentially for free on TPU. Data pipeline code is executed on the \"CPU\" part\n    # of the TPU while the TPU itself is computing gradients.\n    flag = random.randint(1,3)\n    coef_1 = random.randint(70, 90) * 0.01\n    coef_2 = random.randint(70, 90) * 0.01\n    if flag == 1:\n        image = tf.image.random_flip_left_right(image, seed=2020)\n    elif flag == 2:\n        image = tf.image.random_flip_up_down(image, seed=2020)\n    #else:\n        #image = tf.image.random_crop(image, [int(IMAGE_SIZE[0]*coef_1), int(IMAGE_SIZE[0]*coef_2), 3],seed=2020)\n    image = random_blockout(image)\n    return image, label   \n\ndef get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\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    dataset = dataset.prefetch(AUTO) #готовим следующий набор, пока предыдущий обучается\n    return dataset\n\ndef get_validation_dataset():\n    dataset = load_dataset(VALIDATION_FILENAMES, labeled=True, ordered=False)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache() # кешируем набор\n    dataset = dataset.prefetch(AUTO) #готовим следующий набор, пока предыдущий обучается\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(TEST_FILENAMES, labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) #готовим следующий набор, пока предыдущий обучается\n    return dataset\n                               \ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec files, i.e. flowers00-230.tfrec = 230 data items\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\n# training_dataset = get_training_dataset()\n# validation_dataset = get_validation_dataset()\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:21:49.229532Z","iopub.execute_input":"2023-12-09T12:21:49.229977Z","iopub.status.idle":"2023-12-09T12:21:49.259060Z","shell.execute_reply.started":"2023-12-09T12:21:49.229946Z","shell.execute_reply":"2023-12-09T12:21:49.258341Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"LR_START = 0.00001\nLR_MAX = 0.00005 * strategy.num_replicas_in_sync#0.0001\nLR_MIN = 0.00001\nLR_RAMPUP_EPOCHS = 5\nLR_SUSTAIN_EPOCHS = 0\nLR_EXP_DECAY = .75\n\ndef lrfn(epoch):\n    if epoch < LR_RAMPUP_EPOCHS:\n        lr = (LR_MAX - LR_START) / LR_RAMPUP_EPOCHS * epoch + LR_START\n    elif epoch < LR_RAMPUP_EPOCHS + LR_SUSTAIN_EPOCHS:\n        lr = LR_MAX\n    else:\n        lr = (LR_MAX - LR_MIN) * LR_EXP_DECAY**(epoch - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS) + LR_MIN\n    return lr\n    \nlr_callback = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=True)\n\n# построим график изменения шага обучение в зависимости от эпох\nrng = [i for i in range(EPOCHS)]\ny = [lrfn(x) for x in rng]\nplt.plot(rng, y)\nprint(\"Learning rate schedule: {:.3g} to {:.3g} to {:.3g}\".format(y[0], max(y), y[-1]))","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:21:49.260044Z","iopub.execute_input":"2023-12-09T12:21:49.260288Z","iopub.status.idle":"2023-12-09T12:21:49.455232Z","shell.execute_reply.started":"2023-12-09T12:21:49.260262Z","shell.execute_reply":"2023-12-09T12:21:49.454380Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_model(use_model):\n    # noisy-student\n    base_model = use_model(weights='imagenet', \n                      include_top=False, pooling='avg',\n                      input_shape=(*IMAGE_SIZE, 3))\n#     base_model.trainable = False\n    x = base_model.output\n    predictions = Dense(104, activation='softmax')(x)\n    return Model(inputs=base_model.input, outputs=predictions)\n\n\nwith strategy.scope():    \n    model = get_model(MODEL_CLASS) # тут подставить свою модель\n        \nmodel.compile(\n    optimizer='nadam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:22:00.368080Z","iopub.execute_input":"2023-12-09T12:22:00.368425Z","iopub.status.idle":"2023-12-09T12:22:59.072534Z","shell.execute_reply.started":"2023-12-09T12:22:00.368394Z","shell.execute_reply":"2023-12-09T12:22:59.071325Z"},"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":{"iopub.status.busy":"2023-12-09T13:36:52.932146Z","iopub.execute_input":"2023-12-09T13:36:52.932886Z","iopub.status.idle":"2023-12-09T13:38:16.008370Z","shell.execute_reply.started":"2023-12-09T13:36:52.932843Z","shell.execute_reply":"2023-12-09T13:38:16.007415Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model.fit(get_training_dataset(), \n          steps_per_epoch=STEPS_PER_EPOCH, \n          epochs=EPOCHS, \n          callbacks=[lr_callback, ModelCheckpoint(filepath='my_denceNet_201.h5', monitor='val_loss',\n                                  save_best_only=True)],\n          validation_data=get_validation_dataset(),\n          workers = 3)","metadata":{"execution":{"iopub.status.busy":"2023-12-09T12:23:21.433230Z","iopub.execute_input":"2023-12-09T12:23:21.433700Z","iopub.status.idle":"2023-12-09T13:29:38.898289Z","shell.execute_reply.started":"2023-12-09T12:23:21.433660Z","shell.execute_reply":"2023-12-09T13:29:38.897071Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = tf.keras.models.load_model('my_denceNet_201.h5')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('Generating submission.csv file...')\n\n# Get image ids from test set and convert to unicode\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')\n\n# Write the submission file\nnp.savetxt(\n    'submission.csv',\n    np.rec.fromarrays([test_ids, predictions]),\n    fmt=['%s', '%d'],\n    delimiter=',',\n    header='id,label',\n    comments='',\n)","metadata":{"execution":{"iopub.status.busy":"2023-12-09T13:36:48.681929Z","iopub.execute_input":"2023-12-09T13:36:48.682777Z","iopub.status.idle":"2023-12-09T13:36:48.715418Z","shell.execute_reply.started":"2023-12-09T13:36:48.682735Z","shell.execute_reply":"2023-12-09T13:36:48.714154Z"},"trusted":true},"execution_count":null,"outputs":[]}]}