{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"collapsed":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport tensorflow as tf\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport PIL\nfrom PIL import Image\nimport os\nimport seaborn as sns\nfrom kaggle_datasets import KaggleDatasets\nimport re\n\n\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"MAIN_PATH = '/kaggle/input/siim-isic-melanoma-classification/'\nTRAIN_JPEG_DIR = MAIN_PATH+'jpeg/train/'\nTEST_JPEG_DIR = MAIN_PATH+'jpeg/test/'\n\ntrain_df = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/train.csv')\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_id = 'ISIC_0188432'\n\ndef show_sample():\n    img_path = TRAIN_JPEG_DIR+f'{sample_id}.jpg'\n    im = Image.open(img_path)\n    plt.imshow(im)\n    \nshow_sample()\ntrain_df[train_df.image_name == sample_id]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.nunique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['target'].plot(kind='hist')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df[['sex','target']].groupby(['sex']).sum()/train_df[['sex','target']].groupby(['sex']).count()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df[['age_approx','target']].groupby(['age_approx']).sum()/train_df[['age_approx','target']].groupby(['age_approx']).count()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install efficientnet\nimport efficientnet.tfkeras as efn\n# IMAGE_SIZE = [1024,1024]\n# model = tf.keras.Sequential([\n#     efn.EfficientNetB2(\n#         input_shape=(*IMAGE_SIZE, 3),\n#         weights='imagenet',\n#         include_top=False\n#     ),\n#     tf.keras.layers.GlobalAveragePooling2D(),\n#     tf.keras.layers.Dense(1, activation='sigmoid')\n#     ])\n\n# model.compile(\n#     optimizer='adam',\n#     loss='binary_crossentropy',\n#     metrics=['binary_accuracy']\n# )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# model.layers[0].trainable = False\n# model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['image_name'] = train_df['image_name'].apply(lambda x: x+'.jpg')\ntrain_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"try:\n    # TPU detection. No parameters necessary if TPU_NAME environment variable is\n    # set: this is always the case on Kaggle.\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\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    # Default distribution strategy in Tensorflow. Works on CPU and single GPU.\n    strategy = tf.distribute.get_strategy()\n\nAUTO = tf.data.experimental.AUTOTUNE\nEPOCHS = 12\nBATCH_SIZE = 8 * strategy.num_replicas_in_sync\nIMAGE_SIZE = [1024, 1024]\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)\nprint(AUTO,BATCH_SIZE)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_PATH = KaggleDatasets().get_gcs_path('siim-isic-melanoma-classification')\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/tfrecords/train*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/tfrecords/test*.tfrec')\n\nCLASSES = [0,1]   \n\ndef 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\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_saturation(image, 0, 2)\n    return image, label  \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\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 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 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\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 build_lrfn(lr_start=0.00001, lr_max=0.0001, \n               lr_min=0.000001, lr_rampup_epochs=20, \n               lr_sustain_epochs=0, lr_exp_decay=.8):\n    lr_max = lr_max * strategy.num_replicas_in_sync\n\n    def 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    \n    return lrfn","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"L = tf.keras.layers\nwith strategy.scope():\n    model = tf.keras.Sequential([\n        efn.EfficientNetB5(\n            input_shape=(*IMAGE_SIZE, 3),\n            #weights='imagenet',\n            weights='imagenet',\n            include_top=False\n        ),\n        L.GlobalAveragePooling2D(),\n        L.Dense(1024, activation = 'relu'), \n        L.Dropout(0.3), \n        L.Dense(512, activation= 'relu'), \n        L.Dropout(0.2), \n        L.Dense(256, activation='relu'), \n        L.Dropout(0.2), \n        L.Dense(128, activation='relu'), \n        L.Dropout(0.1), \n        L.Dense(1, activation='sigmoid')\n    ])\n    model.compile(\n    optimizer='adam',\n    #loss = 'binary_crossentropy',\n    loss = tf.keras.losses.BinaryCrossentropy(label_smoothing = 0.1),\n    metrics=['binary_crossentropy']\n    )\n    model.summary()\n    \n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lrfn = build_lrfn()\nlr_schedule = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=1)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(\n    get_training_dataset(), \n    epochs=EPOCHS, \n    callbacks=[lr_schedule],\n    steps_per_epoch=STEPS_PER_EPOCH\n    #validation_data=valid_dataset\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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\ntest_ds = get_test_dataset(ordered=True)\n\nprint('Computing predictions...')\n# test_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = model.predict(test_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.save('aaa',probabilities)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ids_ds","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_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()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/sample_submission.csv')\ndel sub['target']\nsub = sub.merge(pred_df, on='image_name')\nsub.to_csv('submission_label_smoothing.csv', index=False)\nsub.to_csv('submission.csv', index=False)\nsub.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}