{"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\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Create Distribution Strategy ##","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import tensorflow as tf\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print(\"Running on tpu\", tpu.master())\n    \nexcept ValueError:\n    tpu = None\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy()\n    \nprint(\"Replicas\", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Loading the Competition Data ##","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-512x512'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"AUTO = tf.data.experimental.AUTOTUNE\nIMAGE_SIZE = [512,512]\nEPOCHS = 12\nBATCH_SIZE = 16*strategy.num_replicas_in_sync\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')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Count images in each file","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"import math, re, os\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"NUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\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":"# Define helper functions ","execution_count":null},{"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\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    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    \n","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    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads = AUTO) # automatically interleaves reads from multiple files\n    dataset = dataset.with_options(ignore_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    \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.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)\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)\n    return dataset\n    ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Datasets","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"ds_train = get_training_dataset()\nds_val = get_validation_dataset()\nds_test = get_test_dataset()\n\nprint(\"Training\", ds_train)\nprint(\"Validation\", ds_val)\nprint(\"Test\", ds_test)\n\n","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":{"trusted":true},"cell_type":"code","source":"print(\"Number of classes: {}\".format(len(CLASSES)))\nprint(\"First five classes, sorted alphabetically:\")\nfor name in sorted(CLASSES)[:5]:\n    print(name)\nprint(\"number of training images: {}\".format(NUM_TRAINING_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Examine the shape of data**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Training data shapes\")\nfor image,label in ds_train.take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"training data label examples:\", label.numpy())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Test data shapes\")\n\nfor image,idnum in ds_test.take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"test data IDs\", idnum.numpy().astype('U'))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Dataset visualization","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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 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 : #if binary string, these are image ids, and return none as label for test data\n        numpy_labels = [None for _ in enumerate(numpy_images)]\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                               \n    \ndef display_batch_of_images(databatch, predictions = None):\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    #auto-squaring, drop data that does not fit itno square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n    \n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot = (rows,cols,1)\n    \n    if rows<cols:\n        plt.figure(figsize = (FIGSIZE, FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize = (FIGSIZE/cols*rows, FIGSIZE))\n        \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            \n        dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3\n        subplot = display_one_flower(image,title,subplot,not correct, titlesize = dynamic_titlesize)\n    \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    \n    \n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\none_batch = next(iter(ds_train.unbatch().batch(20)))\ndisplay_batch_of_images(one_batch)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Define Learning rate Schedule **","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"LR_START = 0.00001\nLR_MAX = 0.00005 * strategy.num_replicas_in_sync\nLR_MIN = LR_START\nLR_RAMPUP_EPOCHS = 5 #5\nLR_SUSTAIN_EPOCHS = 0 # 0\nLR_EXP_DECAY = 0.80\n\ndef lrfn(epoch):\n    if epoch < LR_RAMPUP_EPOCHS:  \n        lr = LR_START + (epoch * (LR_MAX - LR_START) / LR_RAMPUP_EPOCHS)   #   np.random.random_sample() * LR_START\n    elif epoch < (LR_RAMPUP_EPOCHS + LR_SUSTAIN_EPOCHS):  ####5-7lun\n        lr = LR_MAX\n    else:    \n        lr = LR_MIN + (LR_MAX - LR_MIN) * LR_EXP_DECAY ** (epoch - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS)\n#    print('For epoch', epoch, 'setting lr to', lr)\n    return lr\n\nlr_callback = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose = True)\n\nrng = [i for i in range(30)]\ny = [lrfn(x) for x in rng]\nplt.plot(rng, y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"early_stop = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=20, restore_best_weights = True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Define Model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -q efficientnet","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import efficientnet.tfkeras as efficientnet\nwith strategy.scope():\n    pretrained_model = efficientnet.EfficientNetB7(\n        weights = 'noisy-student',\n        include_top = False,\n        input_shape = [*IMAGE_SIZE, 3]        \n    )\n    pretrained_model.trainable = True\n    \n    model = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES),activation = 'softmax')\n    ])\n    \n    model.compile(\n        optimizer = 'adam',\n        loss = 'sparse_categorical_crossentropy',\n        metrics = ['sparse_categorical_accuracy'],\n    )\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**TRAIN MODEL**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH_SIZE = 16*strategy.num_replicas_in_sync\nEPOCHS = 11\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES//BATCH_SIZE\n\nhistory = model.fit(\n    ds_train, \n    validation_data = ds_val,\n    epochs = EPOCHS,\n    steps_per_epoch = STEPS_PER_EPOCH,\n    callbacks = [lr_callback, early_stop]\n)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**EXAMINE TRAINING CURVE**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def display_training_curves(training, validation, title,subplot):\n    if subplot%10 == 1:\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_xlabel('epoch')\n    ax.legend(['train ', 'valid'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"display_training_curves(\n    history.history['loss'],\n    history.history['val_loss'],\n    'loss',\n    211,\n)\n\ndisplay_training_curves(\n    history.history['sparse_categorical_accuracy'],\n    history.history['val_sparse_categorical_accuracy'],\n    'accuracy',\n    212,\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Validation: **\nCreate Confusion Matrix\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\ncmdataset = get_validation_dataset(ordered = True)\nimages_ds = cmdataset.map(lambda image,label:image)\nlabels_ds = cmdataset.map(lambda image,label:label ).unbatch()\n\ncm_correct_labels = next(iter(labels_ds.batch(NUM_VALIDATION_IMAGES))).numpy()\ncm_probabilites = model.predict(images_ds)\ncm_predictions = np.argmax(cm_probabilites, axis = -1)\nlabels = range(len(CLASSES))\ncmat = confusion_matrix(\n    cm_correct_labels,\n    cm_predictions,\n    labels = labels,\n)\ncmat = (cmat.T/cmat.sum(axis=1)).T","execution_count":null,"outputs":[]},{"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 = \"left\", 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    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"score  = f1_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels = labels,\n    average= 'macro',\n)\n\nprecision = precision_score(\n\tcm_correct_labels,\n    cm_predictions,\n    labels = labels,\n    average = 'macro',\n)\n\nrecall = recall_score(\n\tcm_correct_labels,\n    cm_predictions,\n    labels = labels,\n    average = 'macro',\n)\ndisplay_confusion_matrix(cmat,score,precision,recall)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Look at examples from the dataset, with true and predicted classes.**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images,labels = next(batch)\nprobabilites = model.predict(images)\npredictions = np.argmax(probabilites, axis = -1)\ndisplay_batch_of_images((images,labels), predictions)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Test Predictions :\nCreate predictions to submit to the competition.**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ds = get_test_dataset(ordered = True)\nprint(\"Computing predictions for test set\")\ntest_images_ds = test_ds.map(lambda image,idnum: image)\nprobabilities = model.predict(test_images_ds)\npredictions = np.argmax(probabilities, axis = -1)\nprint(predictions)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Generating submision 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')\n\nnp.savetxt(\n    \"submission.csv\",\n    np.rec.fromarrays([test_ids, predictions]),\n    fmt = ['%s', '%d'],\n    delimiter = ',',\n    header = 'id,label',\n    comments = '',\n    \n)\n!head submission.csv","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}