{"cells":[{"metadata":{},"cell_type":"markdown","source":"<a id=\"toc\"></a>\n# Table of Contents\n1. [Install libraries and packages](#install_libraries_and_packages)\n1. [Import libraries](#import_libraries)\n1. [Try to detect TPU](#try_to_detect_tpu)\n1. [Access competition data](#access_competition_data)\n1. [Configure hyper-parameters](#configure_hyper_parameters)\n1. [Define visualization utilities](#define_visualization_utilities)\n1. [Read images from TFRecords](#read_images_from_tfrecords)\n1. [Visualize test set](#visualize_test_set)\n1. [Load models](#load_models)\n1. [Make prediction on the test set](#make_prediction_on_the_test_set)"},{"metadata":{},"cell_type":"markdown","source":"<a id=\"install_libraries_and_packages\"></a>\n# Install libraries and packages\n[Back to Table of Contents](#toc)"},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -U efficientnet","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a id=\"import_libraries\"></a>\n# Import libraries\n[Back to Table of Contents](#toc)"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import re, math\n# import math, re, os\nimport tensorflow as tf\nimport numpy as np\nfrom matplotlib import pyplot as plt\nprint(\"Tensorflow version \" + tf.__version__)\nAUTO = tf.data.experimental.AUTOTUNE\nfrom kaggle_datasets import KaggleDatasets\n# from sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\n\nimport efficientnet.tfkeras","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a id=\"try_to_detect_tpu\"></a>\n# Try to detect TPU\n[Back to Table of Contents](#toc)"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Detect hardware, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()  # TPU detection. No parameters necessary if TPU_NAME environment variable is set. On Kaggle this is always the case.\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    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() # default distribution strategy in Tensorflow. Works on CPU and single GPU.\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a id=\"access_competition_data\"></a>\n# Access competition data\nTPUs read data directly from Google Cloud Storage (GCS). This Kaggle utility will copy the dataset to a GCS bucket co-located with the TPU. If you have multiple datasets attached to the notebook, you can pass the name of a specific dataset to the get_gcs_path function. The name of the dataset is the name of the directory it is mounted in. Use !ls /kaggle/input/ to list attached datasets.\n\n[Back to Table of Contents](#toc)"},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path('flower-classification-with-tpus') # you can list the bucket with \"!gsutil ls $GCS_DS_PATH\"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a id=\"configure_hyper_parameters\"></a>\n# Configure hyper-parameters\n[Back to Table of Contents](#toc)"},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE = [512, 512] # at this size, a GPU will run out of memory. Use the TPU\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nCLASSES = ['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\n\n\nGCS_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\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') # predictions on this dataset should be submitted for the competition","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# TEST_FILENAMES = tf.io.gfile.glob('/kaggle/input/flower-classification-with-tpus/tfrecords-jpeg-512x512/test/*.tfrec') # predictions on this dataset should be submitted for the competition","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a id=\"define_visualization_utilities\"></a>\n# Define visualization utilities\ndata -> pixels, nothing of much interest for the machine learning practitioner in this section.\n\n[Back to Table of Contents](#toc)"},{"metadata":{"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\n# def 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[np.argmax(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\n# 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    \n# def 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":"<a id=\"read_images_from_tfrecords\"></a>\n# Read images from TFRecords\n[Back to Table of Contents](#toc)"},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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\ndef 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    one_hot_class = tf.one_hot(label, depth=len(CLASSES))\n    return image, one_hot_class # 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# def force_image_sizes(dataset, image_size):\n#     # explicit size needed for TPU\n#     reshape_images = lambda image, label: (tf.reshape(image, [*image_size, 3]), label)\n#     dataset = dataset.map(reshape_images, num_parallel_calls=AUTO)\n#     return dataset\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_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, one_hot_class):\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, 0.8, 1)\n#     image = tf.image.random_jpeg_quality(image, 80, 100)\n    image = tf.image.random_brightness(image, 0.1)\n    image = tf.image.random_contrast(image, 0.8, 1)\n    return image, one_hot_class\n\n# 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\n# def 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\n\n# NUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\n# NUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\n# STEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n# print('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))\nprint('Dataset: {} unlabeled test images'.format(NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a id=\"visualize_test_set\"></a>\n# Visualize test set\n[Back to Table of Contents](#toc)"},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Test data shapes:\")\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":"# peer at test data\ntest_dataset = get_test_dataset()\ntest_dataset = test_dataset.unbatch().batch(20)\ntest_batch = iter(test_dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# run this cell again for next set of images\ndisplay_batch_of_images(next(test_batch))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a id=\"load_models\"></a>\n# Load models\n[Back to Table of Contents](#toc)"},{"metadata":{},"cell_type":"markdown","source":"EfficientNetB7"},{"metadata":{"trusted":true},"cell_type":"code","source":"EFFICIENTNETB7_CKPT = '/kaggle/input/flowers-with-tpu-efficientnetb7-focalloss/model.h5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = efficientnet.tfkeras.EfficientNetB7(weights=None, include_top=False)\n\n    effb7 = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    effb7.load_weights(EFFICIENTNETB7_CKPT)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"DenseNet201"},{"metadata":{"trusted":true},"cell_type":"code","source":"DENSENET201_CKPT = '/kaggle/input/flowers-with-tpu-densenet201-focalloss/model.h5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.DenseNet201(weights=None, input_shape=[*IMAGE_SIZE, 3], include_top=False)\n\n    den201 = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    den201.load_weights(DENSENET201_CKPT)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"ResNet152"},{"metadata":{"trusted":true},"cell_type":"code","source":"RESNET152_CKPT = '/kaggle/input/flowers-with-tpu-resnet152-focalloss/model.h5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.ResNet152V2(weights=None, input_shape=[*IMAGE_SIZE, 3], include_top=False)\n\n    res152 = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    res152.load_weights(RESNET152_CKPT)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"InceptionResNet"},{"metadata":{"trusted":true},"cell_type":"code","source":"INCEPTIONRESNET_CKPT = '/kaggle/input/flowers-with-tpu-inceptionresnet-focalloss/model.h5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.InceptionResNetV2(weights=None, input_shape=[*IMAGE_SIZE, 3], include_top=False)\n\n    inres = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    inres.load_weights(INCEPTIONRESNET_CKPT)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Xception"},{"metadata":{"trusted":true},"cell_type":"code","source":"XCEPTION_CKPT = '/kaggle/input/flowers-with-tpu-xception-focalloss/model.h5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.Xception(weights=None, input_shape=[*IMAGE_SIZE, 3], include_top=False)\n\n    xcep = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    xcep.load_weights(XCEPTION_CKPT)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Inception"},{"metadata":{"trusted":true},"cell_type":"code","source":"INCEPTION_CKPT = '/kaggle/input/flowers-with-tpu-inception-focalloss/model.h5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.InceptionV3(weights=None, input_shape=[*IMAGE_SIZE, 3], include_top=False)\n\n    incep = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    incep.load_weights(INCEPTION_CKPT)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"MobileNet"},{"metadata":{"trusted":true},"cell_type":"code","source":"MOBILENET_CKPT = '/kaggle/input/flowers-with-tpu-mobilenet-focalloss/model.h5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.MobileNetV2(weights=None, input_shape=[*IMAGE_SIZE, 3], include_top=False)\n\n    mobi = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    mobi.load_weights(MOBILENET_CKPT)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"VGG19"},{"metadata":{"trusted":true},"cell_type":"code","source":"VGG19_CKPT = '/kaggle/input/flowers-with-tpu-vgg19-focalloss/model.h5'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.VGG19(weights=None, input_shape=[*IMAGE_SIZE, 3], include_top=False)\n\n    vgg19 = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    vgg19.load_weights(VGG19_CKPT)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<a id=\"make_prediction_on_the_test_set\"></a>\n# Make prediction on the test set\n[Back to Table of Contents](#toc)"},{"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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"effb7_probabilities = effb7.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"den201_probabilities = den201.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"res152_probabilities = res152.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"inres_probabilities = inres.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"xcep_probabilities = xcep.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"incep_probabilities = incep.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mobi_probabilities = mobi.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vgg19_probabilities = vgg19.predict(test_images_ds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"probabilities = np.mean(\n    [\n        effb7_probabilities,\n        den201_probabilities,\n        res152_probabilities,\n        inres_probabilities,\n        xcep_probabilities,\n        incep_probabilities,\n        mobi_probabilities,\n        vgg19_probabilities\n    ],\n    axis=0\n)\n\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('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='')\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":1}