{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"DEVICE = \"TPU\"\n\nCFG = dict(\n    epochs = 25,\n    lr = 0.1,  # learning rate  \n    inp_size = 512, # input image size\n    net_count         =   7,\n    batch_size        =  32,\n    \n    read_size         =512, \n    crop_size         = 512, \n    net_size          = 512,\n    rot               = 180.0,\n    shr               =   2.0,\n    hzoom             =   8.0,\n    wzoom             =   8.0,\n    hshift            =   8.0,\n    wshift            =   8.0,\n\n    optimizer         = 'adam',\n    label_smooth_fac  =   0.05,\n    \n    tta_steps         =  4  \n)","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 os, random, re, math, time\nrandom.seed(a=42)\n\nimport numpy as np\nimport pandas as pd\n\nimport tensorflow as tf\nimport tensorflow.keras.backend as K\nimport efficientnet.tfkeras as efn\n\nimport PIL\n\nfrom kaggle_datasets import KaggleDatasets\n\nfrom tqdm import tqdm\nfrom tensorflow.keras.callbacks import ModelCheckpoint\n\nimport xgboost as xgb\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.utils import class_weight\n\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"SEED=42\n\ndef seed_everything(SEED):\n    np.random.seed(SEED)\n    tf.random.set_seed(SEED)\n\nseed_everything(SEED)\n\nBASEPATH = \"../input/siim-isic-melanoma-classification\"\ndf_train = pd.read_csv(os.path.join(BASEPATH, 'train.csv'))\ndf_test  = pd.read_csv(os.path.join(BASEPATH, 'test.csv'))\ndf_sub   = pd.read_csv(os.path.join(BASEPATH, 'sample_submission.csv'))\n\n\nGCS_PATH    = KaggleDatasets().get_gcs_path('512x512-melanoma-tfrecords-70k-images')\n#GCS_PATH_2019    = KaggleDatasets().get_gcs_path('isic2019-128x128')\n\n#files_train_2019 = np.array(tf.io.gfile.glob(GCS_PATH_2019 + '/train*.tfrec'))\n#files_train_2020 = np.array(tf.io.gfile.glob(GCS_PATH + '/train*.tfrec'))\n\nfiles_train = np.sort(np.array(tf.io.gfile.glob(GCS_PATH + '/train*.tfrec')))\nfiles_test  = np.sort(np.array(tf.io.gfile.glob(GCS_PATH + '/test*.tfrec')))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"##### split to files_train ,files_valid (80% ,20%)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"files_train ,files_valid = train_test_split(files_train,test_size = 0.20,random_state = SEED)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# train on images","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"if DEVICE == \"TPU\":\n    print(\"connecting to TPU...\")\n    try:\n        tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\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    \n\nAUTO     = tf.data.experimental.AUTOTUNE\nREPLICAS = strategy.num_replicas_in_sync\nprint(f'REPLICAS: {REPLICAS}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_mat(rotation, shear, height_zoom, width_zoom, height_shift, width_shift):\n    # returns 3x3 transformmatrix which transforms indicies\n        \n    # CONVERT DEGREES TO RADIANS\n    rotation = math.pi * rotation / 180.\n    shear    = math.pi * shear    / 180.\n\n    def get_3x3_mat(lst):\n        return tf.reshape(tf.concat([lst],axis=0), [3,3])\n    \n    # ROTATION MATRIX\n    c1   = tf.math.cos(rotation)\n    s1   = tf.math.sin(rotation)\n    one  = tf.constant([1],dtype='float32')\n    zero = tf.constant([0],dtype='float32')\n    \n    rotation_matrix = get_3x3_mat([c1,   s1,   zero, \n                                   -s1,  c1,   zero, \n                                   zero, zero, one])    \n    # SHEAR MATRIX\n    c2 = tf.math.cos(shear)\n    s2 = tf.math.sin(shear)    \n    \n    shear_matrix = get_3x3_mat([one,  s2,   zero, \n                                zero, c2,   zero, \n                                zero, zero, one])        \n    # ZOOM MATRIX\n    zoom_matrix = get_3x3_mat([one/height_zoom, zero,           zero, \n                               zero,            one/width_zoom, zero, \n                               zero,            zero,           one])    \n    # SHIFT MATRIX\n    shift_matrix = get_3x3_mat([one,  zero, height_shift, \n                                zero, one,  width_shift, \n                                zero, zero, one])\n    \n    return K.dot(K.dot(rotation_matrix, shear_matrix), \n                 K.dot(zoom_matrix,     shift_matrix))\n\n\ndef transform(image, cfg):    \n    # input image - is one image of size [dim,dim,3] not a batch of [b,dim,dim,3]\n    # output - image randomly rotated, sheared, zoomed, and shifted\n    DIM = cfg[\"read_size\"]\n    XDIM = DIM%2 #fix for size 331\n    \n    rot = cfg['rot'] * tf.random.normal([1], dtype='float32')\n    shr = cfg['shr'] * tf.random.normal([1], dtype='float32') \n    h_zoom = 1.0 + tf.random.normal([1], dtype='float32') / cfg['hzoom']\n    w_zoom = 1.0 + tf.random.normal([1], dtype='float32') / cfg['wzoom']\n    h_shift = cfg['hshift'] * tf.random.normal([1], dtype='float32') \n    w_shift = cfg['wshift'] * tf.random.normal([1], dtype='float32') \n\n    # GET TRANSFORMATION MATRIX\n    m = get_mat(rot,shr,h_zoom,w_zoom,h_shift,w_shift) \n\n    # LIST DESTINATION PIXEL INDICES\n    x   = tf.repeat(tf.range(DIM//2, -DIM//2,-1), DIM)\n    y   = tf.tile(tf.range(-DIM//2, DIM//2), [DIM])\n    z   = tf.ones([DIM*DIM], dtype='int32')\n    idx = tf.stack( [x,y,z] )\n    \n    # ROTATE DESTINATION PIXELS ONTO ORIGIN PIXELS\n    idx2 = K.dot(m, tf.cast(idx, dtype='float32'))\n    idx2 = K.cast(idx2, dtype='int32')\n    idx2 = K.clip(idx2, -DIM//2+XDIM+1, DIM//2)\n    \n    # FIND ORIGIN PIXEL VALUES           \n    idx3 = tf.stack([DIM//2-idx2[0,], DIM//2-1+idx2[1,]])\n    d    = tf.gather_nd(image, tf.transpose(idx3))\n        \n    return tf.reshape(d,[DIM, DIM,3])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def read_labeled_tfrecord(example):\n    tfrec_format = {\n        'image'                        : tf.io.FixedLenFeature([], tf.string),\n        'image_name'                   : tf.io.FixedLenFeature([], tf.string),\n        'patient_id'                   : tf.io.FixedLenFeature([], tf.int64),\n        'sex'                          : tf.io.FixedLenFeature([], tf.int64),\n        'age_approx'                   : tf.io.FixedLenFeature([], tf.int64),\n        'anatom_site_general_challenge': tf.io.FixedLenFeature([], tf.int64),\n        #'diagnosis'                    : tf.io.FixedLenFeature([], tf.int64),\n        'target'                       : tf.io.FixedLenFeature([], tf.int64)\n    }           \n    example = tf.io.parse_single_example(example, tfrec_format)\n    return (example['image'], (example['sex'], example['age_approx'], example['anatom_site_general_challenge']), example['target'])\n\ndef read_unlabeled_tfrecord(example, return_image_name):\n    tfrec_format = {\n        'image'                        : tf.io.FixedLenFeature([], tf.string),\n        'image_name'                   : tf.io.FixedLenFeature([], tf.string),\n        'patient_id'                   : tf.io.FixedLenFeature([], tf.int64),\n        'sex'                          : tf.io.FixedLenFeature([], tf.int64),\n        'age_approx'                   : tf.io.FixedLenFeature([], tf.int64),\n        'anatom_site_general_challenge': tf.io.FixedLenFeature([], tf.int64)\n    }\n    example = tf.io.parse_single_example(example, tfrec_format)\n    return (example['image'], (example['sex'], example['age_approx'], example['anatom_site_general_challenge']), (example['image_name'] if return_image_name else 0))\n\ndef prepare_data(data, cfg=None, augment=True):\n    img = data[0]\n    img = tf.image.decode_jpeg(img, channels=3)\n    img = tf.image.resize(img, [cfg['read_size'], cfg['read_size']])\n    img = tf.cast(img, tf.float32) / 255.0\n    \n    if augment:\n        img = transform(img, cfg)\n        img = tf.image.random_crop(img, [cfg['crop_size'], cfg['crop_size'], 3])\n        img = tf.image.random_flip_left_right(img)\n        img = tf.image.random_hue(img, 0.01)\n        img = tf.image.random_saturation(img, 0.7, 1.3)\n        img = tf.image.random_contrast(img, 0.8, 1.2)\n        img = tf.image.random_brightness(img, 0.1)\n\n    else:\n        img = tf.image.central_crop(img, cfg['crop_size'] / cfg['read_size'])\n                                   \n    img = tf.image.resize(img, [cfg['net_size'], cfg['net_size']])\n    img = tf.reshape(img, [cfg['net_size'], cfg['net_size'], 3])\n    \n    sex_oh = tf.one_hot(data[1][0], 2)\n    age_aprox = tf.dtypes.cast(tf.reshape(data[1][1], [1]), tf.float32)\n    anatom_site_general_challenge = tf.one_hot(data[1][2], 7)\n    dense = tf.concat([sex_oh, age_aprox, anatom_site_general_challenge], axis=0)\n    return (img, dense)\n\ndef count_data_items(filenames):\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) \n         for filename in filenames]\n    return np.sum(n)\n\nNUM_TEST_IMAGES = count_data_items(files_valid)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(NUM_TEST_IMAGES)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_dataset(files, cfg, augment = False, shuffle = False, repeat = False, \n                labeled=True, return_image_names=True):\n    \n    ds = tf.data.TFRecordDataset(files, num_parallel_reads=AUTO)\n    ds = ds.cache()\n    \n    if repeat:\n        ds = ds.repeat()\n    \n    if shuffle: \n        ds = ds.shuffle(1024*8)\n        opt = tf.data.Options()\n        opt.experimental_deterministic = False\n        ds = ds.with_options(opt)\n        \n    if labeled: \n        ds = ds.map(read_labeled_tfrecord, num_parallel_calls=AUTO)\n    else:\n        ds = ds.map(lambda example: read_unlabeled_tfrecord(example, return_image_names), \n                    num_parallel_calls=AUTO)      \n\n    ds = ds.map(lambda img, dense, imgname_or_label: (prepare_data((img, dense), augment=augment, cfg=cfg), \n                                               imgname_or_label), \n                num_parallel_calls=AUTO)\n    \n    ds = ds.batch(cfg['batch_size'] * REPLICAS)\n    ds = ds.prefetch(AUTO)\n    return ds","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## image from train data\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def show_dataset(thumb_size, cols, rows, ds):\n    mosaic = PIL.Image.new(mode='RGB', size=(thumb_size*cols + (cols-1), \n                                             thumb_size*rows + (rows-1)))\n   \n    for idx, data in enumerate(iter(ds)):\n        img, target_or_imgid = data[0][0], data[1]\n        #img, target_or_imgid = data\n        ix  = idx % cols\n        iy  = idx // cols\n        img = np.clip(img.numpy() * 255, 0, 255).astype(np.uint8)\n        img = PIL.Image.fromarray(img)\n        img = img.resize((thumb_size, thumb_size), resample=PIL.Image.BILINEAR)\n        mosaic.paste(img, (ix*thumb_size + ix, \n                           iy*thumb_size + iy))\n\n    display(mosaic)\n    \nds = get_dataset(files_train, CFG).unbatch().take(12*5)   \nshow_dataset(64, 12, 5, ds)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## images from the valid data.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"ds = get_dataset(files_valid, CFG).unbatch().take(12*5)   \nshow_dataset(64, 12, 5, ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(df_train.diagnosis.unique())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Test of image augmentation","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"image before the augmentaion \")\nds = get_dataset(files_train, CFG).unbatch().take(1)   \nshow_dataset(200, 1, 1, ds)\nprint(\"image after the augmentaion \")\nds = tf.data.TFRecordDataset(files_train, num_parallel_reads=AUTO)\nds = ds.take(1).cache().repeat()\nds = ds.map(read_labeled_tfrecord, num_parallel_calls=AUTO)\n# ds = ds.map(lambda img, target: (prepare_image(img, cfg=CFG, augment=True), target), \n#             num_parallel_calls=AUTO)\nds = ds.map(lambda img, dense, target: (prepare_data((img, dense), cfg=CFG, augment=True), target), \n            num_parallel_calls=AUTO)\nds = ds.take(12*5)\nds = ds.prefetch(AUTO)\n\nshow_dataset(64, 12, 5, ds)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Images from the test data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"ds = get_dataset(files_test, CFG, augment=True, repeat=True, \n                         labeled=False, return_image_names=False).unbatch().take(12*5)   \nshow_dataset(64, 12, 5, ds)","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}