{"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_minor":4,"nbformat":4,"cells":[{"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\nimport os\nfor 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 20GB 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"!pip install --upgrade tensorflow-io","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:26:29.868306Z","iopub.execute_input":"2023-07-05T04:26:29.868729Z","iopub.status.idle":"2023-07-05T04:26:47.246880Z","shell.execute_reply.started":"2023-07-05T04:26:29.868688Z","shell.execute_reply":"2023-07-05T04:26:47.245503Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nimport matplotlib.pyplot as plt","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:38:40.669118Z","iopub.execute_input":"2023-07-05T04:38:40.670099Z","iopub.status.idle":"2023-07-05T04:38:40.676265Z","shell.execute_reply.started":"2023-07-05T04:38:40.670051Z","shell.execute_reply":"2023-07-05T04:38:40.674209Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import cv2, pandas as pd, matplotlib.pyplot as plt\ntrain = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\nprint('Examples WITH Melanoma')\nimgs = train.loc[train.target==1].sample(10).image_name.values\nplt.figure(figsize=(20,8))\nfor i,k in enumerate(imgs):\n    img = cv2.imread('../input/jpeg-melanoma-128x128/train/%s.jpg'%k)\n    img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)\n    plt.subplot(2,5,i+1); plt.axis('off')\n    plt.imshow(img)\nplt.show()\nprint('Examples WITHOUT Melanoma')\nimgs = train.loc[train.target==0].sample(10).image_name.values\nplt.figure(figsize=(20,8))\nfor i,k in enumerate(imgs):\n    img = cv2.imread('../input/jpeg-melanoma-128x128/train/%s.jpg'%k)\n    img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)\n    plt.subplot(2,5,i+1); plt.axis('off')\n    plt.imshow(img)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:38:44.719564Z","iopub.execute_input":"2023-07-05T04:38:44.719929Z","iopub.status.idle":"2023-07-05T04:38:47.248661Z","shell.execute_reply.started":"2023-07-05T04:38:44.719898Z","shell.execute_reply":"2023-07-05T04:38:47.244327Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install efficientnet","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:38:51.163193Z","iopub.execute_input":"2023-07-05T04:38:51.163566Z","iopub.status.idle":"2023-07-05T04:39:04.289389Z","shell.execute_reply.started":"2023-07-05T04:38:51.163537Z","shell.execute_reply":"2023-07-05T04:39:04.288099Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nfrom kaggle_datasets import KaggleDatasets\nimport tensorflow as tf\nimport tensorflow.keras.backend as K\nimport efficientnet.tfkeras as efn\nfrom sklearn.model_selection import KFold\nfrom sklearn.metrics import roc_auc_score\n#import matplotlib.pyplot as plt","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:09.051195Z","iopub.execute_input":"2023-07-05T04:39:09.052114Z","iopub.status.idle":"2023-07-05T04:39:09.676973Z","shell.execute_reply.started":"2023-07-05T04:39:09.052078Z","shell.execute_reply":"2023-07-05T04:39:09.675862Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"DEVICE = \"TPU\" #or \"GPU\"\n\n# USE DIFFERENT SEED FOR DIFFERENT STRATIFIED KFOLD\nSEED = 42\n\n# NUMBER OF FOLDS. USE 3, 5, OR 15 \nFOLDS = 3\n\n# WHICH IMAGE SIZES TO LOAD EACH FOLD\n# CHOOSE 128, 192, 256, 384, 512, 768 \nIMG_SIZES = [128,128,128]\n\n# INCLUDE OLD COMP DATA? YES=1 NO=0\nINC2019 = [0,0,0]\nINC2018 = [1,1,1]\n\n# BATCH SIZE AND EPOCHS\nBATCH_SIZES = [32]*FOLDS\nEPOCHS = [12]*FOLDS\n\n# WHICH EFFICIENTNET B? TO USE\nEFF_NETS = [6,6,6]\n\n# WEIGHTS FOR FOLD MODELS WHEN PREDICTING TEST\nWGTS = [1/FOLDS]*FOLDS\n\n# TEST TIME AUGMENTATION STEPS\nTTA = 11","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:12.781318Z","iopub.execute_input":"2023-07-05T04:39:12.781674Z","iopub.status.idle":"2023-07-05T04:39:12.789866Z","shell.execute_reply.started":"2023-07-05T04:39:12.781648Z","shell.execute_reply":"2023-07-05T04:39:12.788337Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_PATH = [None]*FOLDS; GCS_PATH2 = [None]*FOLDS\nfor i,k in enumerate(IMG_SIZES):\n    GCS_PATH[i] = KaggleDatasets().get_gcs_path('melanoma-%ix%i'%(k,k))\n    GCS_PATH2[i] = KaggleDatasets().get_gcs_path('isic2019-%ix%i'%(k,k))\nfiles_train = np.sort(np.array(tf.io.gfile.glob(GCS_PATH[0] + '/train*.tfrec')))\nfiles_test  = np.sort(np.array(tf.io.gfile.glob(GCS_PATH[0] + '/test*.tfrec')))","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:18.069939Z","iopub.execute_input":"2023-07-05T04:39:18.070321Z","iopub.status.idle":"2023-07-05T04:39:20.460279Z","shell.execute_reply.started":"2023-07-05T04:39:18.070292Z","shell.execute_reply":"2023-07-05T04:39:20.459219Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROT_ = 180.0\nSHR_ = 2.0\nHZOOM_ = 8.0\nWZOOM_ = 8.0\nHSHIFT_ = 8.0\nWSHIFT_ = 8.0","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:21.829095Z","iopub.execute_input":"2023-07-05T04:39:21.830032Z","iopub.status.idle":"2023-07-05T04:39:21.834515Z","shell.execute_reply.started":"2023-07-05T04:39:21.830000Z","shell.execute_reply":"2023-07-05T04:39:21.833582Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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, DIM=256):    \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    XDIM = DIM%2 #fix for size 331\n    \n    rot = ROT_ * tf.random.normal([1], dtype='float32')\n    shr = SHR_ * tf.random.normal([1], dtype='float32') \n    h_zoom = 1.0 + tf.random.normal([1], dtype='float32') / HZOOM_\n    w_zoom = 1.0 + tf.random.normal([1], dtype='float32') / WZOOM_\n    h_shift = HSHIFT_ * tf.random.normal([1], dtype='float32') \n    w_shift = 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])","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:24.512397Z","iopub.execute_input":"2023-07-05T04:39:24.512772Z","iopub.status.idle":"2023-07-05T04:39:24.530598Z","shell.execute_reply.started":"2023-07-05T04:39:24.512741Z","shell.execute_reply":"2023-07-05T04:39:24.529324Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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, augment=True, dim=256):    \n    img = tf.image.decode_jpeg(img, channels=3)\n    img = tf.cast(img, tf.float32) / 255.0\n    \n    if augment:\n        img = transform(img,DIM=dim)\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    img = tf.reshape(img, [dim,dim, 3])\n            \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)","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:28.793050Z","iopub.execute_input":"2023-07-05T04:39:28.793583Z","iopub.status.idle":"2023-07-05T04:39:28.806360Z","shell.execute_reply.started":"2023-07-05T04:39:28.793552Z","shell.execute_reply":"2023-07-05T04:39:28.805226Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_dataset(files, augment = False, shuffle = False, repeat = False, \n                labeled=True, return_image_names=True, batch_size=16, dim=256):\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, dim=dim), \n                                               imgname_or_label), \n                num_parallel_calls=AUTO)\n    \n    ds = ds.batch(batch_size * REPLICAS)\n    ds = ds.prefetch(AUTO)\n    return ds","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:32.472449Z","iopub.execute_input":"2023-07-05T04:39:32.472806Z","iopub.status.idle":"2023-07-05T04:39:32.482274Z","shell.execute_reply.started":"2023-07-05T04:39:32.472778Z","shell.execute_reply":"2023-07-05T04:39:32.481280Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EFNS = [efn.EfficientNetB0, efn.EfficientNetB1, efn.EfficientNetB2, efn.EfficientNetB3, \n        efn.EfficientNetB4, efn.EfficientNetB5, efn.EfficientNetB6]\n\ndef build_model(dim=128, ef=0):\n    inp = tf.keras.layers.Input(shape=(dim,dim,3))\n    base = EFNS[ef](input_shape=(dim,dim,3),weights='imagenet',include_top=False)\n    x = base(inp)\n    x = tf.keras.layers.GlobalAveragePooling2D()(x)\n    x = tf.keras.layers.Dense(1,activation='sigmoid')(x)\n    model = tf.keras.Model(inputs=inp,outputs=x)\n    opt = tf.keras.optimizers.Adam(learning_rate=0.001)\n    loss = tf.keras.losses.BinaryCrossentropy(label_smoothing=0.05) \n    model.compile(optimizer=opt,loss=loss,metrics=['AUC'])\n    return model","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:34.724027Z","iopub.execute_input":"2023-07-05T04:39:34.724775Z","iopub.status.idle":"2023-07-05T04:39:34.734479Z","shell.execute_reply.started":"2023-07-05T04:39:34.724740Z","shell.execute_reply":"2023-07-05T04:39:34.733410Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_lr_callback(batch_size=8):\n    lr_start   = 0.000005\n    lr_max     = 0.00000125 * REPLICAS * batch_size\n    lr_min     = 0.000001\n    lr_ramp_ep = 5\n    lr_sus_ep  = 0\n    lr_decay   = 0.8\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","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:37.163019Z","iopub.execute_input":"2023-07-05T04:39:37.163901Z","iopub.status.idle":"2023-07-05T04:39:37.171632Z","shell.execute_reply.started":"2023-07-05T04:39:37.163858Z","shell.execute_reply":"2023-07-05T04:39:37.170179Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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}')","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:39.950496Z","iopub.execute_input":"2023-07-05T04:39:39.950869Z","iopub.status.idle":"2023-07-05T04:39:40.233361Z","shell.execute_reply.started":"2023-07-05T04:39:39.950825Z","shell.execute_reply":"2023-07-05T04:39:40.232309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# USE VERBOSE=0 for silent, VERBOSE=1 for interactive, VERBOSE=2 for commit\nimport re,math\nVERBOSE = 0\nDISPLAY_PLOT = True\nskf = KFold(n_splits=FOLDS,shuffle=True,random_state=SEED)\noof_pred = []; oof_tar = []; oof_val = []; oof_names = []; oof_folds = [] \npreds = np.zeros((count_data_items(files_test),1))\n\nfor fold,(idxT,idxV) in enumerate(skf.split(np.arange(15))):\n    \n    # DISPLAY FOLD INFO\n    #if DEVICE=='TPU':\n        #tf.tpu.experimental.initialize_tpu_system(tpu)\n    print('#'*25); print('#### FOLD',fold+1)\n    print('#### Image Size %i with EfficientNet B%i and batch_size %i'%\n          (IMG_SIZES[fold],EFF_NETS[fold],BATCH_SIZES[fold]*REPLICAS))\n    \n    # CREATE TRAIN AND VALIDATION SUBSETS\n    files_train = tf.io.gfile.glob([GCS_PATH[fold] + '/train%.2i*.tfrec'%x for x in idxT])\n    if INC2019[fold]:\n        files_train += tf.io.gfile.glob([GCS_PATH2[fold] + '/train%.2i*.tfrec'%x for x in idxT*2+1])\n        print('#### Using 2019 external data')\n    if INC2018[fold]:\n        files_train += tf.io.gfile.glob([GCS_PATH2[fold] + '/train%.2i*.tfrec'%x for x in idxT*2])\n        print('#### Using 2018+2017 external data')\n    np.random.shuffle(files_train); print('#'*25)\n    files_valid = tf.io.gfile.glob([GCS_PATH[fold] + '/train%.2i*.tfrec'%x for x in idxV])\n    files_test = np.sort(np.array(tf.io.gfile.glob(GCS_PATH[fold] + '/test*.tfrec')))\n    \n    # BUILD MODEL\n    K.clear_session()\n    with strategy.scope():\n        model = build_model(dim=IMG_SIZES[fold],ef=EFF_NETS[fold])\n        \n    # SAVE BEST MODEL EACH FOLD\n    sv = tf.keras.callbacks.ModelCheckpoint(\n        'fold-%i.h5'%fold, monitor='val_loss', verbose=0, save_best_only=True,\n        save_weights_only=True, mode='min', save_freq='epoch')\n   \n    # TRAIN\n    print('Training...')\n    history = model.fit(\n        get_dataset(files_train, augment=True, shuffle=True, repeat=True,\n                dim=IMG_SIZES[fold], batch_size = BATCH_SIZES[fold]), \n        epochs=EPOCHS[fold], callbacks = [sv,get_lr_callback(BATCH_SIZES[fold])], \n        steps_per_epoch=count_data_items(files_train)/BATCH_SIZES[fold]//REPLICAS,\n        validation_data=get_dataset(files_valid,augment=False,shuffle=False,\n                repeat=False,dim=IMG_SIZES[fold]), #class_weight = {0:1,1:2},\n        verbose=VERBOSE\n    )\n    \n    print('Loading best model...')\n    model.load_weights('fold-%i.h5'%fold)\n    \n    # PREDICT OOF USING TTA\n    print('Predicting OOF with TTA...')\n    ds_valid = get_dataset(files_valid,labeled=False,return_image_names=False,augment=True,\n            repeat=True,shuffle=False,dim=IMG_SIZES[fold],batch_size=BATCH_SIZES[fold]*4)\n    ct_valid = count_data_items(files_valid); STEPS = TTA * ct_valid/BATCH_SIZES[fold]/4/REPLICAS\n    pred = model.predict(ds_valid,steps=STEPS,verbose=VERBOSE)[:TTA*ct_valid,] \n    oof_pred.append( np.mean(pred.reshape((ct_valid,TTA),order='F'),axis=1) )                 \n    #oof_pred.append(model.predict(get_dataset(files_valid,dim=IMG_SIZES[fold]),verbose=1))\n    \n    # GET OOF TARGETS AND NAMES\n    ds_valid = get_dataset(files_valid, augment=False, repeat=False, dim=IMG_SIZES[fold],\n            labeled=True, return_image_names=True)\n    oof_tar.append( np.array([target.numpy() for img, target in iter(ds_valid.unbatch())]) )\n    oof_folds.append( np.ones_like(oof_tar[-1],dtype='int8')*fold )\n    ds = get_dataset(files_valid, augment=False, repeat=False, dim=IMG_SIZES[fold],\n                labeled=False, return_image_names=True)\n    oof_names.append( np.array([img_name.numpy().decode(\"utf-8\") for img, img_name in iter(ds.unbatch())]))\n    \n    # PREDICT TEST USING TTA\n    print('Predicting Test with TTA...')\n    ds_test = get_dataset(files_test,labeled=False,return_image_names=False,augment=True,\n            repeat=True,shuffle=False,dim=IMG_SIZES[fold],batch_size=BATCH_SIZES[fold]*4)\n    ct_test = count_data_items(files_test); STEPS = TTA * ct_test/BATCH_SIZES[fold]/4/REPLICAS\n    pred = model.predict(ds_test,steps=STEPS,verbose=VERBOSE)[:TTA*ct_test,] \n    preds[:,0] += np.mean(pred.reshape((ct_test,TTA),order='F'),axis=1) * WGTS[fold]\n    \n    # REPORT RESULTS\n    auc = roc_auc_score(oof_tar[-1],oof_pred[-1])\n    oof_val.append(np.max( history.history['val_auc'] ))\n    print('#### FOLD %i OOF AUC without TTA = %.3f, with TTA = %.3f'%(fold+1,oof_val[-1],auc))\n    \n    # PLOT TRAINING\n    if DISPLAY_PLOT:\n        plt.figure(figsize=(15,5))\n        plt.plot(np.arange(EPOCHS[fold]),history.history['auc'],'-o',label='Train AUC',color='#ff7f0e')\n        plt.plot(np.arange(EPOCHS[fold]),history.history['val_auc'],'-o',label='Val AUC',color='#1f77b4')\n        x = np.argmax( history.history['val_auc'] ); y = np.max( history.history['val_auc'] )\n        xdist = plt.xlim()[1] - plt.xlim()[0]; ydist = plt.ylim()[1] - plt.ylim()[0]\n        plt.scatter(x,y,s=200,color='#1f77b4'); plt.text(x-0.03*xdist,y-0.13*ydist,'max auc\\n%.2f'%y,size=14)\n        plt.ylabel('AUC',size=14); plt.xlabel('Epoch',size=14)\n        plt.legend(loc=2)\n        plt2 = plt.gca().twinx()\n        plt2.plot(np.arange(EPOCHS[fold]),history.history['loss'],'-o',label='Train Loss',color='#2ca02c')\n        plt2.plot(np.arange(EPOCHS[fold]),history.history['val_loss'],'-o',label='Val Loss',color='#d62728')\n        x = np.argmin( history.history['val_loss'] ); y = np.min( history.history['val_loss'] )\n        ydist = plt.ylim()[1] - plt.ylim()[0]\n        plt.scatter(x,y,s=200,color='#d62728'); plt.text(x-0.03*xdist,y+0.05*ydist,'min loss',size=14)\n        plt.ylabel('Loss',size=14)\n        plt.title('FOLD %i - Image Size %i, EfficientNet B%i, inc2019=%i, inc2018=%i'%\n                (fold+1,IMG_SIZES[fold],EFF_NETS[fold],INC2019[fold],INC2018[fold]),size=18)\n        plt.legend(loc=3)\n        plt.show()  ","metadata":{"execution":{"iopub.status.busy":"2023-07-05T04:39:55.842227Z","iopub.execute_input":"2023-07-05T04:39:55.842632Z","iopub.status.idle":"2023-07-05T09:24:25.648516Z","shell.execute_reply.started":"2023-07-05T04:39:55.842602Z","shell.execute_reply":"2023-07-05T09:24:25.647646Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}