{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\n\n# Input data files are available in the \"../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\n# for dirname, _, filenames in os.walk('/kaggle/input/flower-classification-with-tpus/'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# in this version I will try learning rate mentioned in below notebook\n# https://www.kaggle.com/mgornergoogle/five-flowers-with-keras-and-xception-on-tpu\n# Adding validation skip code from below kernel\n# https://www.kaggle.com/wrrosa/tpu-enet-b7-densenet\n# In this kernel I will try more data augmentation techniques","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# fix random seed for reproducibility\nseed = 7\nnp.random.seed(seed)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -q efficientnet\n\nimport efficientnet.tfkeras as efn","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import tensorflow as tf\nprint(\"Tensorflow version \" + tf.__version__)\nAUTO = tf.data.experimental.AUTOTUNE # used in tf.data.Dataset API","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow.keras.backend as K","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.applications import InceptionResNetV2\nfrom tensorflow.keras.applications import ResNet152V2\nfrom tensorflow.keras.applications import DenseNet201","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Detect hardware, return appropriate distribution strategy\ntry:\n    # detect and init the TPU\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    # instantiate a distribution strategy\n    tpu_strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    # default distribution strategy in Tensorflow. Works on CPU and single GPU.\n    tpu_strategy = tf.distribute.get_strategy()\n\nprint(\"No. Of REPLICAS: \", tpu_strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE = [224, 224]\nEPOCHS = 15\nBATCH_SIZE = 16 * tpu_strategy.num_replicas_in_sync\nHEIGHT = 224\nWIDTH = 224\nCHANNELS = 3\n#FOLDS = 5\n\n# As TPUs require access to the GCS path\nfrom kaggle_datasets import KaggleDatasets\nDATASET_PATH = KaggleDatasets().get_gcs_path()\n\nDATASET_PATH_SELECT = { # available image sizes\n    192: DATASET_PATH + '/tfrecords-jpeg-192x192',\n    224: DATASET_PATH + '/tfrecords-jpeg-224x224',\n    331: DATASET_PATH + '/tfrecords-jpeg-331x331',\n    512: DATASET_PATH + '/tfrecords-jpeg-512x512'\n}\n\nSELECTED_DATASET = DATASET_PATH_SELECT[IMAGE_SIZE[0]]\n\nprint(\"SELECTED_DATASET: \", SELECTED_DATASET)\n\nTRAINING_FILENAMES = tf.io.gfile.glob(SELECTED_DATASET + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(SELECTED_DATASET + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(SELECTED_DATASET + '/test/*.tfrec')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# watch out for overfitting!\nSKIP_VALIDATION = True\nif SKIP_VALIDATION:\n    TRAINING_FILENAMES = TRAINING_FILENAMES + VALIDATION_FILENAMES\n    \nVALIDATION_MISMATCHES_IDS = ['861282b96','df1fd14b4','b402b6acd','861282b96','741999f79','4dab7fa08','6423cd23e','617a30d60','87d91aefb','2023d3cac','5f56bcb7f','4571b9509',\n'f4ec48685','f9c50db87','96379ff01','28594d9ce','6a3a28a06','fbd61ef17','55a883e16','83a80db99','9ee42218f','b5fb20185',\n'868bf8b0c','d0caf04b9','ef945a176','9b8f2f5bd','f8da3867d','0bf0b39b3','bab3ef1f5','293c37e25','f739f3e83','5253af526',\n'f27f9a100','077803f97','b4becad84']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"CLASSES = ['pink primrose',    'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea',     'wild geranium',     'tiger lily',           'moon orchid',              'bird of paradise', 'monkshood',        'globe thistle',         # 00 - 09\n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily', # 10 - 19\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',         # 20 - 29\n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',           # 30 - 39\n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',      # 40 - 49\n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',    # 50 - 59\n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',            # 60 - 69\n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',             # 70 - 79\n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',            # 80 - 89\n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',        # 90 - 99\n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"![](http://)**DATA PREPROCESSING UTILITY FUNCTIONS**"},{"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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    }\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    return image, label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"id\": 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['id']\n    return image, idnum","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**More Data Augmentation Techniques**"},{"metadata":{"trusted":true},"cell_type":"code","source":"def data_augment(image, label):\n    p_spatial = tf.random.uniform([1], minval=0, maxval=1, dtype='float32', seed=seed)\n    p_spatial2 = tf.random.uniform([1], minval=0, maxval=1, dtype='float32', seed=seed)\n    p_pixel = tf.random.uniform([1], minval=0, maxval=1, dtype='float32', seed=seed)\n    p_crop = tf.random.uniform([1], minval=0, maxval=1, dtype='float32', seed=seed)\n    \n    # Spatial-level transforms\n    if p_spatial >= .2: # flips\n        image = tf.image.random_flip_left_right(image, seed=seed)\n        image = tf.image.random_flip_up_down(image, seed=seed)\n        \n    if p_crop >= .7: # crops\n        if p_crop >= .95:\n            image = tf.image.random_crop(image, size=[int(HEIGHT*.6), int(WIDTH*.6), CHANNELS], seed=seed)\n        elif p_crop >= .85:\n            image = tf.image.random_crop(image, size=[int(HEIGHT*.7), int(WIDTH*.7), CHANNELS], seed=seed)\n        elif p_crop >= .8:\n            image = tf.image.random_crop(image, size=[int(HEIGHT*.8), int(WIDTH*.8), CHANNELS], seed=seed)\n        else:\n            image = tf.image.random_crop(image, size=[int(HEIGHT*.9), int(WIDTH*.9), CHANNELS], seed=seed)\n        image = tf.image.resize(image, size=[HEIGHT, WIDTH])\n        \n    if p_spatial2 >= .6: # @cdeotte's functions\n        if p_spatial2 >= .9:\n            image = transform_rotation(image)\n        elif p_spatial2 >= .8:\n            image = transform_zoom(image)\n        elif p_spatial2 >= .7:\n            image = transform_shift(image)\n        else:\n            image = transform_shear(image)\n        \n    # Pixel-level transforms\n    if p_pixel >= .4: # pixel transformations\n        if p_pixel >= .85:\n            image = tf.image.random_saturation(image, lower=0, upper=2, seed=seed)\n        elif p_pixel >= .65:\n            image = tf.image.random_contrast(image, lower=.8, upper=2, seed=seed)\n        elif p_pixel >= .5:\n            image = tf.image.random_brightness(image, max_delta=.2, seed=seed)\n        else:\n            image = tf.image.adjust_gamma(image, gamma=.6)\n\n    return image, label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def transform_rotation(image):\n    # input image - is one image of size [dim,dim,3] not a batch of [b,dim,dim,3]\n    # output - image randomly rotated\n    DIM = HEIGHT\n    XDIM = DIM%2 #fix for size 331\n    \n    rotation = 15. * tf.random.normal([1],dtype='float32')\n    # CONVERT DEGREES TO RADIANS\n    rotation = math.pi * rotation / 180.\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    rotation_matrix = tf.reshape( tf.concat([c1,s1,zero, -s1,c1,zero, zero,zero,one],axis=0),[3,3] )\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(rotation_matrix,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])\n\ndef transform_shear(image):\n    # input image - is one image of size [dim,dim,3] not a batch of [b,dim,dim,3]\n    # output - image randomly sheared\n    DIM = HEIGHT\n    XDIM = DIM%2 #fix for size 331\n    \n    shear = 5. * tf.random.normal([1],dtype='float32')\n    shear = math.pi * shear / 180.\n        \n    # SHEAR MATRIX\n    one = tf.constant([1],dtype='float32')\n    zero = tf.constant([0],dtype='float32')\n    c2 = tf.math.cos(shear)\n    s2 = tf.math.sin(shear)\n    shear_matrix = tf.reshape( tf.concat([one,s2,zero, zero,c2,zero, zero,zero,one],axis=0),[3,3] )    \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(shear_matrix,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])\n\ndef transform_shift(image):\n    # input image - is one image of size [dim,dim,3] not a batch of [b,dim,dim,3]\n    # output - image randomly shifted\n    DIM = HEIGHT\n    XDIM = DIM%2 #fix for size 331\n    \n    height_shift = 16. * tf.random.normal([1],dtype='float32') \n    width_shift = 16. * tf.random.normal([1],dtype='float32') \n    one = tf.constant([1],dtype='float32')\n    zero = tf.constant([0],dtype='float32')\n        \n    # SHIFT MATRIX\n    shift_matrix = tf.reshape( tf.concat([one,zero,height_shift, zero,one,width_shift, zero,zero,one],axis=0),[3,3] )\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(shift_matrix,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])\n\ndef transform_zoom(image):\n    # input image - is one image of size [dim,dim,3] not a batch of [b,dim,dim,3]\n    # output - image randomly zoomed\n    DIM = HEIGHT\n    XDIM = DIM%2 #fix for size 331\n    \n    height_zoom = 1.0 + tf.random.normal([1],dtype='float32')/10.\n    width_zoom = 1.0 + tf.random.normal([1],dtype='float32')/10.\n    one = tf.constant([1],dtype='float32')\n    zero = tf.constant([0],dtype='float32')\n        \n    # ZOOM MATRIX\n    zoom_matrix = tf.reshape( tf.concat([one/height_zoom,zero,zero, zero,one/width_zoom,zero, zero,zero,one],axis=0),[3,3] )\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(zoom_matrix,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":{},"cell_type":"markdown","source":"**LOAD DATASETS**"},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import re\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_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**EXPLORE DATSETS**"},{"metadata":{"trusted":true},"cell_type":"code","source":"import math","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Training data shape:\")\nfor image, label in get_training_dataset().take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training data label examples:\", label.numpy())\nprint(\"-----------------------------------------------------------\")\nprint(\"Validation data shape:\")\nfor image, label in get_validation_dataset().take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Validation data label examples:\", label.numpy())\nprint(\"-----------------------------------------------------------\")\nprint(\"Test data shape:\")\nfor image, idnum in get_test_dataset().take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test data IDs:\", idnum.numpy().astype('U')) # U=unicode string","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Peek at training data\ntraining_dataset = get_training_dataset()\ntraining_dataset = training_dataset.unbatch().batch(10)\ntrain_batch = iter(training_dataset)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**VISUALIZATION FUNCTION**"},{"metadata":{"trusted":true},"cell_type":"code","source":"from matplotlib import pyplot as plt\nimport math\n# numpy and matplotlib defaults\nnp.set_printoptions(threshold=15, linewidth=80)\n\ndef batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    if numpy_labels.dtype == object: # binary string in this case, these are image ID strings\n        numpy_labels = [None for _ in enumerate(numpy_images)]\n    # If no labels, only image IDs, return None for labels (this is the case for test data)\n    return numpy_images, numpy_labels\n\ndef title_from_label_and_target(label, correct_label):\n    if correct_label is None:\n        return CLASSES[label], True\n    correct = (label == correct_label)\n    return \"{} [{}{}{}]\".format(CLASSES[label], 'OK' if correct else 'NO', u\"\\u2192\" if not correct else '',\n                                CLASSES[correct_label] if not correct else ''), correct\n\ndef display_one_flower(image, title, subplot, red=False, titlesize=16):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n    return (subplot[0], subplot[1], subplot[2]+1)\n\ndef display_batch_of_images(databatch, predictions=None):\n    \"\"\"This will work with:\n    display_batch_of_images(images)\n    display_batch_of_images(images, predictions)\n    display_batch_of_images((images, labels))\n    display_batch_of_images((images, labels), predictions)\n    \"\"\"\n    # data\n    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n        \n    # auto-squaring: this will drop data that does not fit into square or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n        \n    # size and spacing\n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[label]\n        correct = True\n        if predictions is not None:\n            title, correct = title_from_label_and_target(predictions[i], label)\n        dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n        subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n    \n    #layout\n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspace=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# display some images\ndisplay_batch_of_images(next(train_batch))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Peek at test data\ntest_dataset = get_test_dataset()\ntest_dataset = test_dataset.unbatch().batch(10)\ntest_batch = iter(test_dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# display test images\ndisplay_batch_of_images(next(test_batch))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Confusion Matrix Display Function**"},{"metadata":{"trusted":true},"cell_type":"code","source":"def display_confusion_matrix(cmat, score, precision, recall):\n    plt.figure(figsize=(15,15))\n    ax = plt.gca()\n    ax.matshow(cmat, cmap='Reds')\n    ax.set_xticks(range(len(CLASSES)))\n    ax.set_xticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"left\", rotation_mode=\"anchor\")\n    ax.set_yticks(range(len(CLASSES)))\n    ax.set_yticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_yticklabels(), rotation=45, ha=\"right\", rotation_mode=\"anchor\")\n    titlestring = \"\"\n    if score is not None:\n        titlestring += 'f1 = {:.3f} '.format(score)\n    if precision is not None:\n        titlestring += '\\nprecision = {:.3f} '.format(precision)\n    if recall is not None:\n        titlestring += '\\nrecall = {:.3f} '.format(recall)\n    if len(titlestring) > 0:\n        ax.text(101, 1, titlestring, fontdict={'fontsize': 18, 'horizontalalignment':'right', 'verticalalignment':'top', 'color':'#804040'})\n    plt.show()\n\ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#FF5733')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#33FF60')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    ax.set_xlabel('epoch')\n    ax.legend(['training', 'validation'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Loss and Accuracy Functions**"},{"metadata":{"trusted":true},"cell_type":"code","source":"def loss_fn(y_true,y_pred):\n    ## sparse_categorical_crossentropy with logits\n    return tf.keras.losses.sparse_categorical_crossentropy(y_true,y_pred,from_logits = True)\n\ndef acc_fn(y_true,y_pred):\n    ## see if we need softmax or not \n    return tf.keras.metrics.sparse_categorical_accuracy(y_true,y_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"models = []\nhistories = []","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with tpu_strategy.scope():\n    enet = efn.EfficientNetB7(\n        input_shape=[*IMAGE_SIZE, 3],\n        weights='imagenet',\n        include_top=False\n    )\n\n    model = tf.keras.Sequential([\n        enet,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES))\n    ])\n        \nmodel.compile(\n    optimizer=tf.keras.optimizers.Adam(lr=3e-5 * tpu_strategy.num_replicas_in_sync),\n    loss = loss_fn,\n    metrics=[acc_fn]\n)\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Learning rate schedule for TPU, GPU and CPU.\n# Using an LR ramp up because fine-tuning a pre-trained model.\n# Starting with a high LR would break the pre-trained weights.\n\nLR_START = 0.00001\nLR_MAX = 0.00005 * tpu_strategy.num_replicas_in_sync\nLR_MIN = 0.00001\nLR_RAMPUP_EPOCHS = 5\nLR_SUSTAIN_EPOCHS = 0\nLR_EXP_DECAY = .8\n\ndef 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# Reduce learning rate when a metric has stopped improving\nlr_callback = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=True)\n\nrng = [i for i in range(EPOCHS)]\ny = [lrfn(x) for x in rng]\nplt.plot(rng, y)\nprint(\"Learning rate schedule: {:.3g} to {:.3g} to {:.3g}\".format(y[0], max(y), y[-1]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(\n    get_training_dataset(), \n    steps_per_epoch=STEPS_PER_EPOCH,\n    epochs=EPOCHS,\n    callbacks=[lr_callback],\n    validation_data=None if SKIP_VALIDATION else get_validation_dataset(),\n    verbose = 1\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if not SKIP_VALIDATION:\n    display_training_curves(history.history['loss'], history.history['val_loss'], 'loss', 211)\n    display_training_curves(history.history['sparse_categorical_accuracy'], history.history['val_sparse_categorical_accuracy'], 'accuracy', 212)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# with tpu_strategy.scope():\n#     res = ResNet152V2(\n#         input_shape=[*IMAGE_SIZE, 3],\n#         weights='imagenet',\n#         include_top=False\n#     )\n\n#     model2 = tf.keras.Sequential([\n#         res,\n#         tf.keras.layers.GlobalAveragePooling2D(),\n#         tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n#     ])\n        \n# model2.compile(\n#     optimizer=tf.keras.optimizers.Adam(lr=0.0001),\n#     loss = 'sparse_categorical_crossentropy',\n#     metrics=['sparse_categorical_accuracy']\n# )\n# model2.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# history2 = model2.fit(\n#     get_training_dataset(), \n#     steps_per_epoch=STEPS_PER_EPOCH,\n#     epochs=EPOCHS, \n#     callbacks=[lr_callback],\n#     validation_data=None if SKIP_VALIDATION else get_validation_dataset()\n# )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# if not SKIP_VALIDATION:\n#     display_training_curves(history2.history['loss'], history2.history['val_loss'], 'loss', 211)\n#     display_training_curves(history2.history['sparse_categorical_accuracy'], history2.history['val_sparse_categorical_accuracy'], 'accuracy', 212)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# with tpu_strategy.scope():\n#     Inct=InceptionResNetV2(\n#         input_shape=[*IMAGE_SIZE, 3],\n#         weights='imagenet',\n#         include_top=False\n      \n#     )\n#     model3 = tf.keras.Sequential([\n#         Inct,\n#         tf.keras.layers.GlobalMaxPooling2D(),\n#         tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n#     ])\n        \n# model3.compile(\n#     optimizer=tf.keras.optimizers.Adam(lr=0.0001),\n#     loss = 'sparse_categorical_crossentropy',\n#     metrics=['sparse_categorical_accuracy']\n# )\n# model3.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# history3 = model3.fit(\n#     get_training_dataset(), \n#     steps_per_epoch=STEPS_PER_EPOCH,\n#     epochs=EPOCHS, \n#     callbacks=[lr_callback],\n#     validation_data=None if SKIP_VALIDATION else get_validation_dataset()\n# )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# if not SKIP_VALIDATION:\n#     display_training_curves(history3.history['loss'], history3.history['val_loss'], 'loss', 211)\n#     display_training_curves(history3.history['sparse_categorical_accuracy'], history3.history['val_sparse_categorical_accuracy'], 'accuracy', 212)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Removing other 2 models and using only 2 since did not see much affect of using 4 models**"},{"metadata":{"trusted":true},"cell_type":"code","source":"with tpu_strategy.scope():\n    den=DenseNet201(\n        input_shape=[*IMAGE_SIZE, 3],\n        weights='imagenet',\n        include_top=False\n      \n    )\n    model2 = tf.keras.Sequential([\n        den,\n        tf.keras.layers.GlobalMaxPooling2D(),\n        tf.keras.layers.Dense(len(CLASSES))\n    ])\n        \nmodel2.compile(\n    optimizer=tf.keras.optimizers.Adam(lr=3e-5 * tpu_strategy.num_replicas_in_sync),\n    loss = loss_fn,\n    metrics = [acc_fn]\n)\nmodel2.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history4 = model2.fit(\n    get_training_dataset(), \n    steps_per_epoch=STEPS_PER_EPOCH,\n    epochs=EPOCHS, \n    callbacks=[lr_callback],\n    validation_data=None if SKIP_VALIDATION else get_validation_dataset()\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if not SKIP_VALIDATION:\n    display_training_curves(history4.history['loss'], history4.history['val_loss'], 'loss', 211)\n    display_training_curves(history4.history['sparse_categorical_accuracy'], history4.history['val_sparse_categorical_accuracy'], 'accuracy', 212)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Finding best alpha and Beta\nif not SKIP_VALIDATION:\n    cmdataset = get_validation_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and labels, order matters.\n    images_ds = cmdataset.map(lambda image, label: image)\n    labels_ds = cmdataset.map(lambda image, label: label).unbatch()\n    cm_correct_labels = next(iter(labels_ds.batch(NUM_VALIDATION_IMAGES))).numpy() # get everything as one batch\n    m = model.predict(images_ds)\n    m2 = model2.predict(images_ds)\n    scores = []\n    for alpha in np.linspace(0,1,100):\n        cm_probabilities = alpha*m+(1-alpha)*m2\n        cm_predictions = np.argmax(cm_probabilities, axis=-1)\n        scores.append(f1_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro'))\n        \n    print(\"Correct   labels: \", cm_correct_labels.shape, cm_correct_labels)\n    print(\"Predicted labels: \", cm_predictions.shape, cm_predictions)\n    plt.plot(scores)\n    best_alpha = np.argmax(scores)/100\n    cm_probabilities = best_alpha*m+(1-best_alpha)*m2\n    cm_predictions = np.argmax(cm_probabilities, axis=-1)\nelse:\n    best_alpha = 0.44","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(best_alpha)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**CONFUSION MATRIX FUNCTION**"},{"metadata":{"trusted":true},"cell_type":"code","source":"if not SKIP_VALIDATION:\n    cmat = confusion_matrix(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)))\n    score = f1_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\n    precision = precision_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\n    recall = recall_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\n    display_confusion_matrix(cmat, score, precision, recall)\n    print('f1 score: {:.3f}, precision: {:.3f}, recall: {:.3f}'.format(score, precision, recall))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**MAKE PREDICTIONS**"},{"metadata":{"trusted":true},"cell_type":"code","source":"# test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\n\n# print('Computing predictions...')\n# test_images_ds = test_ds.map(lambda image, idnum: image)\n# probabilities = (model.predict(test_images_ds) + model2.predict(test_images_ds)+model3.predict(test_images_ds)+model4.predict(test_images_ds))/4\n# predictions = np.argmax(probabilities, axis=-1)\n# print(predictions)\n\n# # Generating submission.csv file\n# test_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()\n# test_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U') # all in one batch\n# np.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TTA_NUM = 10\nprobabilities = []\nfor i in range(TTA_NUM):\n    print('TTA Number: ',i)\n    test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\n    test_images_ds = test_ds.map(lambda image, idnum: image)\n    probabilities.append(model.predict(test_images_ds,verbose =1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prob1 = np.mean(probabilities,axis =0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TTA_NUM = 10\nprobabilities = []\nfor i in range(TTA_NUM):\n    print('TTA Number: ',i)\n    test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\n    test_images_ds = test_ds.map(lambda image, idnum: image)\n    probabilities.append(model2.predict(test_images_ds,verbose =1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prob2 = np.mean(probabilities,axis =0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prob = best_alpha*prob1 + (1-best_alpha)*prob2\npredictions = np.argmax(prob, axis=-1)\nprint(predictions)\n\n# 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\nnp.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')","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}