{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"DEVICE = \"TPU\"\nBASEPATH = \"../input/siim-isic-melanoma-classification\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -q efficientnet","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport random, re, math, time\nrandom.seed(a=128)\n\nfrom os.path import join \n\nimport tensorflow as tf\nimport tensorflow.keras.backend as K\n#import tensorflow_addons as tfa\nimport efficientnet.tfkeras as efn\n\nfrom tqdm.keras import TqdmCallback\n\nfrom PIL import Image\nimport PIL\n\nimport matplotlib.pyplot as plt\n\nfrom sklearn.model_selection import KFold\n\nfrom sklearn.utils.class_weight import compute_class_weight\n\nimport plotly\nimport plotly.graph_objects as go\nimport plotly.express as px\nfrom plotly.subplots import make_subplots\n\nfrom pandas_summary import DataFrameSummary\n\nfrom kaggle_datasets import KaggleDatasets\n\nfrom tqdm import tqdm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if DEVICE == \"TPU\":\n    print(\"connecting to TPU...\")\n    try:\n        tpu = tf.distribute.cluster_resolver.TPUClusterResolver()  # TPU detection. No parameters necessary if TPU_NAME environment variable is set. On Kaggle this is always the case.\n        print('Running on TPU ', tpu.master())\n    except ValueError:\n        print(\"Could not connect to TPU\")\n        tpu = None\n\n    if tpu:\n        try:\n            print(\"initializing  TPU ...\")\n            tf.config.experimental_connect_to_cluster(tpu)\n            tf.tpu.experimental.initialize_tpu_system(tpu)\n            strategy = tf.distribute.experimental.TPUStrategy(tpu)\n            print(\"TPU initialized\")\n        except _:\n            print(\"failed to initialize TPU\")\n    else:\n        DEVICE = \"GPU\"\n\nif DEVICE != \"TPU\":\n    print(\"Using default strategy for CPU and single GPU\")\n    strategy = tf.distribute.get_strategy()\n\nif DEVICE == \"GPU\":\n    print(\"Num GPUs Available: \", len(tf.config.experimental.list_physical_devices('GPU')))\n    \nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)\nAUTO = tf.data.experimental.AUTOTUNE\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Configuration\nEPOCHS = 6\nBATCH_SIZE = 8 * strategy.num_replicas_in_sync\nIMAGE_SIZE = [384, 384]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_csv(os.path.join(BASEPATH, 'train.csv'))\ndf_test = pd.read_csv(os.path.join(BASEPATH, 'test.csv'))\nsub = pd.read_csv(os.path.join(BASEPATH, 'sample_submission.csv'))\n\nGCS_PATH = KaggleDatasets().get_gcs_path('melanoma-384x384')\nTRAINING_FILENAMES = np.array(tf.io.gfile.glob(GCS_PATH + '/train*.tfrec'))\nTEST_FILENAMES = np.array(tf.io.gfile.glob(GCS_PATH + '/test*.tfrec'))\n\nCLASSES = [0,1]   ","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    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.random_flip_left_right(image)\n    image = tf.image.random_flip_up_down(image)\n    image = tf.image.random_hue(image, 0.01)\n    image = tf.image.random_saturation(image, 0.7, 1.3)\n    image = tf.image.random_contrast(image, 0.8, 1.2)\n    image = tf.image.random_brightness(image, 0.1)\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\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":"def lrfn(epoch):\n    LR_START          = 0.000005\n    LR_MAX            = 0.000020 * strategy.num_replicas_in_sync\n    LR_MIN            = 0.000001\n    LR_RAMPUP_EPOCHS = 5\n    LR_SUSTAIN_EPOCHS = 0\n    LR_EXP_DECAY = .8\n    \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\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.layers import GlobalAveragePooling2D, Dense, BatchNormalization, Activation, Dropout\nfrom tensorflow.keras.regularizers import l2\n#reg_l2 = 0.001","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Efficeint Net B7\n\n\nwith strategy.scope():\n    model7 = tf.keras.Sequential([\n        efn.EfficientNetB7(\n            input_shape=(*IMAGE_SIZE, 3),\n            weights='imagenet',\n            include_top=False\n        ),\n        GlobalAveragePooling2D(),\n        Dense(1, activation='sigmoid')\n    ])\n    \nmodel7.compile(\n    optimizer='adam',\n    loss = 'binary_crossentropy',\n    metrics=['accuracy']\n)\n\n\n\n\nwith strategy.scope():\n    modelRN = tf.keras.Sequential([\n         tf.keras.applications.ResNet152V2(\n            input_shape=(331, 331, 3),\n            weights='imagenet',\n            include_top=False\n        ),\n        GlobalAveragePooling2D(),\n        Dense(1, activation='sigmoid')\n    ])\n    \nmodelRN.compile(\n         optimizer='adam',\n         loss = 'binary_crossentropy',\n         metrics=['accuracy']\n)\n\n\n\n\nwith strategy.scope():\n    modelIV3 = tf.keras.Sequential([\n         tf.keras.applications.InceptionV3(\n            input_shape=(*IMAGE_SIZE, 3),\n            weights='imagenet',\n            include_top=False\n        ),\n        GlobalAveragePooling2D(),\n        Dense(1, activation='sigmoid')\n    ])\n    \nmodelIV3.compile(\n         optimizer='adam',\n         loss = 'binary_crossentropy',\n         metrics=['accuracy']\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr_schedule = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=1)\nhistory7 = model7.fit(get_training_dataset(), steps_per_epoch=STEPS_PER_EPOCH, epochs=EPOCHS, callbacks=[lr_schedule])\nhistoryRN = modelRN.fit(get_training_dataset(), steps_per_epoch=STEPS_PER_EPOCH, epochs=EPOCHS, callbacks=[lr_schedule])\nhistoryIV3 = modelIV3.fit(get_training_dataset(), steps_per_epoch=STEPS_PER_EPOCH, epochs=EPOCHS, callbacks=[lr_schedule])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True)\n\nprint('Computing predictions...')\ntest_images_ds = test_ds.map(lambda image, idnum: image)\n\nprobabilitiesRN = modelRN.predict(test_images_ds)\nprobabilities7 = model7.predict(test_images_ds)\nprobabilitiesV3 = modelIV3.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Generating submission.csv files...')\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') # all in one batch","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_dfRN = pd.DataFrame({'image_name': test_ids, 'target': np.concatenate(probabilitiesRN)})\npred_df7 = pd.DataFrame({'image_name': test_ids, 'target': np.concatenate(probabilities7)})\npred_dfV3 = pd.DataFrame({'image_name': test_ids, 'target': np.concatenate(probabilitiesV3)})\n\npred_df7.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subRN = sub.copy()\nsub7 = sub.copy()\nsubV3 = sub.copy()\nsubRN.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ndel subRN['target']\nsubRN = subRN.merge(pred_dfRN, on='image_name')\nsubRN.to_csv('submissionRN.csv', index=False)\n\n\ndel subV3['target']\nsubV3 = subV3.merge(pred_dfV3, on='image_name')\nsubV3.to_csv('submissionV3.csv', index=False)\n\n\ndel sub7['target']\nsub7 = sub7.merge(pred_df7, on='image_name')\nsub7.to_csv('submission7.csv', index=False)\n\nsubRN.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#average\n\nensemble1 = (subRN['target'] + sub7['target']+ subV3['target'])/3\nensemble_img1 = subRN['image_name']\nensemble_sub1 = pd.concat([ensemble_img1, ensemble1], axis = 1)\nensemble_sub1.to_csv('submissionV3.csv', index=False)\nensemble_sub1.head()","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}