{"cells":[{"metadata":{},"cell_type":"markdown","source":"**Single EfficientNet B6**\n\nBelow single model scored AUC 0.9475(LB).\n\nThis notebook quotes the awesome notebooks.  \n[Incredible TPUs - finetune EffNetB0-B6 at once](https://www.kaggle.com/agentauers/incredible-tpus-finetune-effnetb0-b6-at-once)  \n[Triple Stratified KFold with TFRecords](https://www.kaggle.com/cdeotte/triple-stratified-kfold-with-tfrecords)\n\nTheir notebooks shows the emsemble of some efficient net,  \nbut I found that one simple model outperform them in terms of Public Score.","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"!pip install -q efficientnet","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","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\nfrom sklearn.model_selection import KFold\nfrom sklearn.metrics import roc_auc_score\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BASEPATH = \"../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\nGCS_PATH    = KaggleDatasets().get_gcs_path('melanoma-512x512')\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":{"trusted":true},"cell_type":"code","source":"print(len(df_train))\nprint(len(df_train[df_train.target==1]))\n# print(files_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"DEVICE = \"TPU\"\n\nbs = 16\n\nCFG = dict(\n    net_count         =   7,\n    batch_size        =  bs,\n    \n    read_size         = 512, \n    crop_size         = 352, \n    net_size          = 352, \n    \n    LR_START          =   0.000005,\n    LR_MAX            =   0.000020,\n    LR_MIN            =   0.000001,\n    LR_RAMPUP_EPOCHS  =   5,\n    LR_SUSTAIN_EPOCHS =   0,\n    LR_EXP_DECAY      =   0.8,\n    epochs            =  12,\n    \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         =  25    \n)","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()\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['target']\n\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    }\n    example = tf.io.parse_single_example(example, tfrec_format)\n    return example['image'], example['image_name'] if return_image_name else 0\n\n \ndef prepare_image(img, cfg=None, augment=True):    \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    return img\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)","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, imgname_or_label: (prepare_image(img, 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":{"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\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   ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ds = get_dataset(files_train, CFG).unbatch().take(12*5)   \n# show_dataset(64, 12, 5, ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ds = 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)\nds = ds.map(lambda img, target: (prepare_image(img, cfg=CFG, augment=True), target), \n            num_parallel_calls=AUTO)\nds = ds.take(12*5)\nds = ds.prefetch(AUTO)\n\n# show_dataset(64, 12, 5, ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_lr_callback(cfg):\n    lr_start   = cfg['LR_START']\n    lr_max     = cfg['LR_MAX'] * strategy.num_replicas_in_sync\n    lr_min     = cfg['LR_MIN']\n    lr_ramp_ep = cfg['LR_RAMPUP_EPOCHS']\n    lr_sus_ep  = cfg['LR_SUSTAIN_EPOCHS']\n    lr_decay   = cfg['LR_EXP_DECAY']\n   \n    def lrfn(epoch):\n        if epoch < lr_ramp_ep:\n            lr = (lr_max - lr_start) / lr_ramp_ep * epoch + lr_start\n            \n        elif epoch < lr_ramp_ep + lr_sus_ep:\n            lr = lr_max\n            \n        else:\n            lr = (lr_max - lr_min) * lr_decay**(epoch - lr_ramp_ep - lr_sus_ep) + lr_min\n            \n        return lr\n\n    lr_callback = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=False)\n    return lr_callback","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_model(cfg):\n    model_input = tf.keras.Input(shape=(cfg['net_size'], cfg['net_size'], 3), name='imgIn')\n\n    dummy = tf.keras.layers.Lambda(lambda x:x)(model_input)\n    \n#     outputs = []    \n#     for i in range(cfg['net_count']):\n#         constructor = getattr(efn, f'EfficientNetB{i}')\n        \n#         x = constructor(include_top=False, weights='imagenet', \n#                         input_shape=(cfg['net_size'], cfg['net_size'], 3), \n#                         pooling='avg')(dummy)\n        \n#         x = tf.keras.layers.Dense(1, activation='sigmoid')(x)\n#         outputs.append(x)\n\n    constructor = getattr(efn, f'EfficientNetB6')\n    x = constructor(include_top=False, weights='imagenet', \n                    input_shape=(cfg['net_size'], cfg['net_size'], 3), \n                    pooling='avg')(dummy)\n    x = tf.keras.layers.Dense(1, activation='sigmoid')(x)\n    outputs = [x]\n        \n    model = tf.keras.Model(model_input, outputs, name='aNetwork')\n    model.summary()\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def compile_new_model(cfg):    \n    with strategy.scope():\n        model = get_model(cfg)\n     \n#         losses = [tf.keras.losses.BinaryCrossentropy(label_smoothing = cfg['label_smooth_fac'])\n#                   for i in range(cfg['net_count'])]\n        losses = [tf.keras.losses.BinaryCrossentropy(label_smoothing = cfg['label_smooth_fac'])]\n        \n        model.compile(\n            optimizer = cfg['optimizer'],\n            loss      = losses,\n            metrics   = [tf.keras.metrics.AUC(name='auc')])\n        \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"nsplits = 5\nrand = 1023\nfolds = KFold(n_splits=nsplits, shuffle = True, random_state = rand)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_tr = pd.DataFrame()\ncnt = 0\nfor tr_idx,va_idx in folds.split(files_train):\n    CFG['batch_size'] = bs\n    files_train_tr = files_train[tr_idx]\n    files_train_va = files_train[va_idx]\n    ds_train     = get_dataset(files_train_tr, CFG, augment=True, shuffle=True, repeat=True)\n    # ds_train     = ds_train.map(lambda img, label: (img, tuple([label] * CFG['net_count'])))\n    ds_train     = ds_train.map(lambda img, label: (img, tuple([label])))\n    steps_train  = count_data_items(files_train_tr) / (CFG['batch_size'] * REPLICAS)\n\n    model        = compile_new_model(CFG)\n    history      = model.fit(ds_train, \n                         verbose          = 1,\n                         steps_per_epoch  = steps_train, \n                         epochs           = CFG['epochs'],\n                         callbacks        = [get_lr_callback(CFG)])\n    \n    # make train prediction\n    CFG['batch_size'] = 256\n\n    cnt_train   = count_data_items(files_train_va)\n    steps      = cnt_train / (CFG['batch_size'] * REPLICAS) * CFG['tta_steps']\n    ds_trainAug = get_dataset(files_train_va, CFG, augment=True, repeat=True, \n                             labeled=False, return_image_names=False)\n\n    probs = model.predict(ds_trainAug, verbose=1, steps=steps)\n    probs = probs[:cnt_train * CFG['tta_steps'],:]\n    probs = np.stack(np.split(probs, CFG['tta_steps'], axis=0), axis=0)\n    \n    ds = get_dataset(files_train_va, CFG, augment=False, repeat=False, \n                 labeled=False, return_image_names=True)\n    image_names = np.array([img_name.numpy().decode(\"utf-8\") \n                        for img, img_name in iter(ds.unbatch())])\n    pred = pd.DataFrame(dict(\n    image_name = image_names,\n    target     = np.mean(probs[:,:,0], axis=0)))\n    \n    pred_tr = pd.concat([pred_tr, pred], axis=0)\n    \n    # make submission data\n    cnt_test   = count_data_items(files_test)\n    steps      = cnt_test / (CFG['batch_size'] * REPLICAS) * CFG['tta_steps']\n    ds_testAug = get_dataset(files_test, CFG, augment=True, repeat=True, \n                             labeled=False, return_image_names=False)\n\n    probs = model.predict(ds_testAug, verbose=1, steps=steps)\n    \n    probs = probs[:cnt_test * CFG['tta_steps'],:]\n    probs = np.stack(np.split(probs, CFG['tta_steps'], axis=0), axis=0)\n    \n    if cnt == 0:\n        probs_sub = probs/nsplits\n        cnt = 1\n    else:\n        probs_sub += probs/nsplits","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_tr = pred_tr.sort_values('image_name') \npred_tr.to_csv('pred_tr.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_tr.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_tr = pred_tr.merge(df_train, on = [\"image_name\"], how = \"left\")\nprint(roc_auc_score(pred_tr[\"target_y\"], pred_tr[\"target_x\"]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ds = get_dataset(files_test, CFG, augment=False, repeat=False, \n                 labeled=False, return_image_names=True)\n\nimage_names = np.array([img_name.numpy().decode(\"utf-8\") \n                        for img, img_name in iter(ds.unbatch())])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame(dict(\n    image_name = image_names,\n    target     = np.mean(probs_sub[:,:,0], axis=0)))\n#     target = np.mean(probs, axis = 1)))\n\nsubmission = submission.sort_values('image_name') \nsubmission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.head(10)","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}