{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\n# import os\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# !pip install -q efficientnet\nimport os\nimport re\nimport tensorflow_hub as hub\nimport numpy as np\nimport pandas as pd\nimport math\n\nfrom matplotlib import pyplot as plt\n\nfrom sklearn import metrics\nfrom sklearn.model_selection import train_test_split\n\nimport tensorflow as tf\nimport tensorflow.keras.layers as L\n\n# import efficientnet.tfkeras as efn\n\nfrom kaggle_datasets import KaggleDatasets","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"AUTO = tf.data.experimental.AUTOTUNE\n\n# Data access\nGCS_PATH = KaggleDatasets().get_gcs_path('siim-isic-melanoma-classification')\n\n# Configuration\nEPOCHS = 1\nBATCH_SIZE = 8 *8\nIMAGE_SIZE = [1024, 1024]\nimSize = 128","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def append_path(pre):\n    return np.vectorize(lambda file: os.path.join(GCS_DS_PATH, pre, file))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/sample_submission.csv')\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/tfrecords/train*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/tfrecords/test*.tfrec')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAINING_FILENAMES = TRAINING_FILENAMES[:7]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/train.csv')\ntrain.head(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.target.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0  # convert image to floats in [0, 1] range\n    image = tf.reshape(image, [*IMAGE_SIZE, 3])# explicit size needed for TPU\n    image = tf.image.resize(image, [imSize,imSize])\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        #\"class\": tf.io.FixedLenFeature([], tf.int64),  # shape [] means single element\n        \"target\": tf.io.FixedLenFeature([], tf.int64),  # shape [] means single element\n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    #label = tf.cast(example['class'], tf.int32)\n    label = tf.cast(example['target'], tf.int32)\n    return image, label # returns a dataset of (image, label) pairs\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"image_name\": tf.io.FixedLenFeature([], tf.string),  # shape [] means single element\n        # class is missing, this competitions's challenge is to predict flower classes for the test dataset\n    }\n    example = tf.io.parse_single_example(example, UNLABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    idnum = example['image_name']\n    return image, idnum # returns a dataset of image(s)\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    # Read from TFRecords. For optimal performance, reading from multiple files at once and\n    # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from multiple files\n    dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\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    image = tf.image.central_crop(image, central_fraction=0.5)\n    image = tf.image.resize(image, [imSize,imSize])\n    image = tf.image.random_flip_left_right(image)\n    #image = tf.image.random_saturation(image, 0, 2)\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() # the training dataset must repeat for several epochs\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\ndef get_validation_dataset(ordered=False):\n    dataset = load_dataset(VALIDATION_FILENAMES, labeled=True, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\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) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\n\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\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nprint('Dataset: {} training images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow.keras.backend as K\ndef focal_loss(gamma=2., alpha=.25):\n    def focal_loss_fixed(y_true, y_pred):\n        pt_1 = tf.where(tf.equal(y_true, 1), y_pred, tf.ones_like(y_pred))\n        pt_0 = tf.where(tf.equal(y_true, 0), y_pred, tf.zeros_like(y_pred))\n\n        return -K.mean(alpha * K.pow(1. - pt_1, gamma) * K.log(K.epsilon()+pt_1))-K.mean((1-alpha) * K.pow( pt_0, gamma) * K.log(1. - pt_0 + K.epsilon()))\n    return focal_loss_fixed","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class MyBiTModel(tf.keras.Model):\n  \"\"\"BiT with a new head.\"\"\"\n\n  def __init__(self, num_classes, module):\n    super().__init__()\n\n    self.num_classes = num_classes\n    self.head = tf.keras.layers.Dense(num_classes, kernel_initializer='zeros')\n    self.bit_model = module\n  \n  def call(self, images):\n    # No need to cut head off since we are using feature extractor model\n    bit_embedding = self.bit_model(images)\n    return self.head(bit_embedding)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nmodule = hub.KerasLayer(\"https://tfhub.dev/google/bit/m-r101x1/1\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nmodel = MyBiTModel(num_classes=1, module=module)\n\nmodel.compile(optimizer=tf.keras.optimizers.Adam(lr = 1e-5),\n              loss=focal_loss(),\n              metrics=['accuracy'])\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True)\n# valid_dataset = get_validation_dataset(ordered=False)\ntrain_dataset = get_training_dataset() ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"STEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nmodel.fit(\n    train_dataset, \n    steps_per_epoch=STEPS_PER_EPOCH,\n    epochs=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = model.predict(test_images_ds,verbose = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nprint('Generating submission.csv file...')\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')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df = pd.DataFrame({'image_name': test_ids, 'target': np.concatenate(probabilities)})\npred_df.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del sub['target']\nsub = sub.merge(pred_df, on='image_name')\nsub.to_csv('submission.csv', index=False)\nsub.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}