{"cells":[{"metadata":{},"cell_type":"markdown","source":"### About this kernel\n\nV1: This one is just a blend of two kernels:\n\nhttps://www.kaggle.com/xhlulu/flowers-tpu-concise-efficientnet-b7\n\nhttps://www.kaggle.com/ratan123/densenet201-flower-classification-with-tpus\n\nCore kernel: [starter kernel](https://www.kaggle.com/mgornergoogle/getting-started-with-100-flowers-on-tpu). (0.95556)\n\nV2: added confusion matrix from starter kernel, epochs = 20 (0.95388)\n\n**V3: Vote up original kernels and this one if you like my work :)** (0.95083)\n\nV4: Custom LR schedule + adding validation data to training data (https://www.kaggle.com/msheriey/flowers-on-tpu-ensemble-lr-schedule) (0.96049)\n\nV5: Skip validation = False + finding best_alpha (0.95784)\n\nV6: Manually interrupted\n\nV7: Skip validation = True + best_alpha = 0.44 **(0.96523)**\n\nV8: Pushing the max LR up to 0.0001 * strategy.num_replicas_in_sync **(0.96059)**\n\nV9: max LR = 0.00003 * strategy.num_replicas_in_sync (0.95955)\n\nV10: max LR = 0.00006 * strategy.num_replicas_in_sync **(0.96114)**\n\nV11: LR_EXP_DECAY = .5 (from .8) **(0.96256)**\n\nV12: LR_EXP_DECAY = .9 **(0.96056)**\n\nV13: LR_RAMPUP_EPOCHS = 3 and LR_EXP_DECAY = .5 **(0.96044)**\n\nV14: Manually interrupted\n\nV15: LR_RAMPUP_EPOCHS = 5 and LR_EXP_DECAY = .7 **(0.96309)**\n\nV16: LR_EXP_DECAY = .75 **(0.96129)**\n\nV17: Back to LR_EXP_DECAY = .8 + Skip validation = False + exploring mismatches in a validation data (0.95931)\n\nV18: Exploring mismatches in a validation data pt 2 (with image ids) (0.95658)\n\nV19: Skip validation = True + prepare for subsetting data **(0.96242)**\n\nV20: Skip validation = True + filtering out mismatches from validation data (0.95948)\n\nV21: Rewriting function count_data_items() **(0.96049)**\n\nV22: Removing top 9 mismatches from validation data with display **(0.96008)**\n\nV23: Added rotation augmentation from: https://www.kaggle.com/cdeotte/rotation-augmentation-gpu-tpu-0-96 **(0.96137)**\n\nV24: Skip validation = False + EnetB7(weights = 'noisy-student') (0.95940)\n\nV25: Skip validation = True + best_alpha = 0.51 **(0.96412)**\n\nV26: Re-run - good Sunday! **(0.96343)**\n\nV27: Consuming TPU quota (...)"},{"metadata":{"trusted":true,"_kg_hide-input":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,"_kg_hide-input":true},"cell_type":"code","source":"import math, re, os\nimport tensorflow as tf, tensorflow.keras.backend as K\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nimport efficientnet.tfkeras as efn\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\nfrom tensorflow.keras.applications import DenseNet201\nprint(\"Tensorflow version \" + tf.__version__)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Configurations"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"AUTO = tf.data.experimental.AUTOTUNE\n\n# Create strategy from tpu\ntpu = tf.distribute.cluster_resolver.TPUClusterResolver()\ntf.config.experimental_connect_to_cluster(tpu)\ntf.tpu.experimental.initialize_tpu_system(tpu)\nstrategy = tf.distribute.experimental.TPUStrategy(tpu)\n\n# Data access\nGCS_DS_PATH = KaggleDatasets().get_gcs_path()\n\n# Configuration\nIMAGE_SIZE = [512, 512]\nEPOCHS = 20\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Custom LR schedule"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"LR_START = 0.00001\nLR_MAX = 0.00005 * 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    \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,"_kg_hide-input":true},"cell_type":"code","source":"GCS_PATH_SELECT = { # available image sizes\n    192: GCS_DS_PATH + '/tfrecords-jpeg-192x192',\n    224: GCS_DS_PATH + '/tfrecords-jpeg-224x224',\n    331: GCS_DS_PATH + '/tfrecords-jpeg-331x331',\n    512: GCS_DS_PATH + '/tfrecords-jpeg-512x512'\n}\nGCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]]\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') # predictions on this dataset should be submitted for the competition\n\n# watch out for overfitting!\nSKIP_VALIDATION = True\nif SKIP_VALIDATION:\n    TRAINING_FILENAMES = TRAINING_FILENAMES + VALIDATION_FILENAMES\n## V20  \n# VALIDATION_MISMATCHES_IDS = ['861282b96','df1fd14b4','b402b6acd','741999f79','4dab7fa08','6423cd23e','617a30d60','87d91aefb','2023d3cac','5f56bcb7f','4571b9509','f4ec48685','f9c50db87','96379ff01','28594d9ce','6a3a28a06','fbd61ef17','55a883e16','83a80db99','9ee42218f','b5fb20185','868bf8b0c','d0caf04b9','ef945a176','9b8f2f5bd','f8da3867d','0bf0b39b3','bab3ef1f5','293c37e25','f739f3e83','5253af526','f27f9a100','077803f97','b4becad84']\n## V22\n# VALIDATION_MISMATCHES_IDS = ['861282b96','617a30d60','4571b9509','f4ec48685','28594d9ce','6a3a28a06','55a883e16','9b8f2f5bd','293c37e25']\n## V23\nVALIDATION_MISMATCHES_IDS = []","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Unhide to see `CLASSES`:"},{"metadata":{"trusted":true,"_kg_hide-input":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']                                                                                                                                               # 100 - 102","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Helper Functions\n## Visualization"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"# 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, figsize  = 13.0):\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 =  figsize\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()\n\ndef 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='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Augmentation"},{"metadata":{"_kg_hide-input":true,"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    # 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    # SHEAR MATRIX\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    # 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    # 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    return K.dot(K.dot(rotation_matrix, shear_matrix), K.dot(zoom_matrix, shift_matrix))\n\ndef transform(image,label):\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 = IMAGE_SIZE[0]\n    XDIM = DIM%2 #fix for size 331\n    \n    rot = 15. * tf.random.normal([1],dtype='float32')\n    shr = 5. * tf.random.normal([1],dtype='float32') \n    h_zoom = 1.0 + tf.random.normal([1],dtype='float32')/10.\n    w_zoom = 1.0 + tf.random.normal([1],dtype='float32')/10.\n    h_shift = 16. * tf.random.normal([1],dtype='float32') \n    w_shift = 16. * 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]),label\n\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Datasets Functions"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true,"_kg_hide-input":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\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"class\": tf.io.FixedLenFeature([], tf.int64),  # shape [] means single element\n        \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 # returns a dataset of (image, label) pairs\n\ndef 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 # returns a dataset of image(s)\n\ndef read_labeled_id_tfrecord(example):\n    LABELED_ID_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        \"id\": tf.io.FixedLenFeature([], tf.string),  # shape [] means single element\n    }\n    example = tf.io.parse_single_example(example, LABELED_ID_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    label = tf.cast(example['class'], tf.int32)\n    idnum =  example['id']\n    return image, label, idnum # returns a dataset of (image, label, idnum) triples\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    # Read from TFRecords. For optimal performance, reading from multiple files at once and\n    # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from multiple files\n    dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n    dataset = dataset.map(read_labeled_id_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n    \n    return dataset\n\ndef load_dataset_with_id(filenames, 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_id_tfrecord, num_parallel_calls=AUTO)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset\n\ndef data_augment(image, label):\n    # data augmentation. Thanks to the dataset.prefetch(AUTO) statement in the next function (below),\n    # this happens essentially for free on TPU. Data pipeline code is executed on the \"CPU\" part\n    # of the TPU while the TPU itself is computing gradients.\n    image = tf.image.random_flip_left_right(image)\n    #image = tf.image.random_saturation(image, 0, 2)\n    return image, label   \n\ndef get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\n    dataset = dataset.filter(lambda image, label, idnum: tf.reduce_sum(tf.cast(idnum == VALIDATION_MISMATCHES_IDS, tf.int32))==0)\n    dataset = dataset.map(lambda image, label, idnum: [image, label])\n    dataset = dataset.map(transform, num_parallel_calls=AUTO)\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.filter(lambda image, label, idnum: tf.reduce_sum(tf.cast(idnum == VALIDATION_MISMATCHES_IDS, tf.int32))==0)\n    dataset = dataset.map(lambda image, label, idnum: [image, label])\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_validation_dataset_with_id(ordered=False):\n    dataset = load_dataset_with_id(VALIDATION_FILENAMES, 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\n\n# counting number of unique ids in dataset\ndef count_data_items(filenames):\n    dataset = load_dataset(filenames,labeled = False)\n    dataset = dataset.map(lambda image, idnum: idnum)\n    dataset = dataset.filter(lambda idnum: tf.reduce_sum(tf.cast(idnum == VALIDATION_MISMATCHES_IDS, tf.int32))==0)\n    uids = next(iter(dataset.batch(21000))).numpy().astype('U') \n    return len(np.unique(uids))\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = (1 - SKIP_VALIDATION) * 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":"## Display mismatches\nThis images from validation data seem to be really strange labeled.... :)"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"if len(VALIDATION_MISMATCHES_IDS)>0:\n    dataset = load_dataset(TRAINING_FILENAMES,labeled = True)\n    dataset = dataset.filter(lambda image, label, idnum: tf.reduce_sum(tf.cast(idnum == VALIDATION_MISMATCHES_IDS, tf.int32))>0)\n    dataset = dataset.map(lambda image, label, idnum: [image, label])\n    imgs = next(iter(dataset.batch(len(VALIDATION_MISMATCHES_IDS))))\n    display_batch_of_images(imgs)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training Model"},{"metadata":{},"cell_type":"markdown","source":"## Load Model into TPU"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Need this line so Google will recite some incantations\n# for Turing to magically load the model onto the TPU\nwith strategy.scope():\n    enet = efn.EfficientNetB7(\n        input_shape=(512, 512, 3),\n        weights='noisy-student',\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), activation='softmax')\n    ])\n        \nmodel.compile(\n    optimizer=tf.keras.optimizers.Adam(lr=0.0001),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Training"},{"metadata":{"trusted":true},"cell_type":"code","source":"#scheduler = tf.keras.callbacks.ReduceLROnPlateau(patience=3, verbose=1)\n\nhistory = 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)","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":{},"cell_type":"markdown","source":"## Training 2:"},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    rnet = DenseNet201(\n        input_shape=(512, 512, 3),\n        weights='imagenet',\n        include_top=False\n    )\n\n    model2 = tf.keras.Sequential([\n        rnet,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n        \nmodel2.compile(\n    optimizer=tf.keras.optimizers.Adam(lr=0.0001),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\nmodel2.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":{},"cell_type":"markdown","source":"# Finding best alpha\nOur final model is just mix of two presented above. In the first commit it was arithmetic mean (alpha = 0.5). Note that using validation data as training will fit your model with accuracy equal 1.0.\nThus formula presented below of linear combination of models will work only with validation data:\n\nprob = alpha  prob(model) + (1 - alpha)  prob(model2)"},{"metadata":{"trusted":true},"cell_type":"code","source":"if 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 = 0.51","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(best_alpha)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Mismatches on a validation data"},{"metadata":{"trusted":true},"cell_type":"code","source":"if not SKIP_VALIDATION:\n    \n    cmdataset_with_id = get_validation_dataset_with_id(ordered=True)\n    ids_ds = cmdataset_with_id.map(lambda image, label, idnum: idnum).unbatch()\n    ids = next(iter(ids_ds.batch(NUM_VALIDATION_IMAGES))).numpy().astype('U') # get everything as one batch\n\n    val_batch = iter(cmdataset.unbatch().batch(1))\n    noip = sum(cm_predictions!=cm_correct_labels)\n    print('Number of incorrect predictions: ' + str(noip) + ' ('+str(round(noip/NUM_VALIDATION_IMAGES*100,1))+'%)')\n    for fi in range(NUM_VALIDATION_IMAGES):\n        x = next(val_batch)\n        if cm_predictions[fi] != cm_correct_labels[fi]:\n            print(\"Image id: '\" + ids[fi] + \"'\")\n            display_batch_of_images(x,np.array([cm_predictions[fi]]),figsize = 2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Confusion matrix"},{"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    #cmat = (cmat.T / cmat.sum(axis=1)).T # normalized\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":"# 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\nprint('Computing predictions...')\ntest_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = best_alpha*model.predict(test_images_ds) + (1-best_alpha)*model2.predict(test_images_ds)\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)\n\nprint('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}