{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-12-04T07:20:13.879680Z","iopub.execute_input":"2022-12-04T07:20:13.880700Z","iopub.status.idle":"2022-12-04T07:20:13.932402Z","shell.execute_reply.started":"2022-12-04T07:20:13.880643Z","shell.execute_reply":"2022-12-04T07:20:13.931606Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nimport keras_preprocessing\nfrom keras_preprocessing import image\nfrom tensorflow.keras import layers\n\nimport tensorflow_hub as hub\n\nimport pandas as pd\nimport os\nimport numpy as np\n\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\n# RUN_IN_COLAB comment the next line\nfrom kaggle_datasets import KaggleDatasets\n\nimport random\nimport math","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:13.933885Z","iopub.execute_input":"2022-12-04T07:20:13.934155Z","iopub.status.idle":"2022-12-04T07:20:13.941665Z","shell.execute_reply.started":"2022-12-04T07:20:13.934126Z","shell.execute_reply":"2022-12-04T07:20:13.940778Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# import stuff \nimport numpy as np\nimport pandas as pd \nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nimport seaborn as sns\nfrom PIL import Image\nfrom IPython.display import Image, display\nimport os\n\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.datasets import load_files\nfrom sklearn.model_selection import train_test_split\n\nimport tensorflow_hub as hub\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.preprocessing.image import load_img, img_to_array\nfrom tensorflow.keras.optimizers import Adam, RMSprop, SGD\nfrom tensorflow.keras.applications import ResNet50, VGG16, VGG19, MobileNetV2\nfrom tensorflow.keras.applications.resnet50 import preprocess_input as prepro_res50\nfrom tensorflow.keras.applications.vgg19 import preprocess_input as prepro_vgg19\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, Dense, Flatten, GlobalAveragePooling2D, BatchNormalization, Dropout, MaxPool2D, MaxPooling2D","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:13.942785Z","iopub.execute_input":"2022-12-04T07:20:13.943072Z","iopub.status.idle":"2022-12-04T07:20:13.952213Z","shell.execute_reply.started":"2022-12-04T07:20:13.943030Z","shell.execute_reply":"2022-12-04T07:20:13.951630Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd\n\nfrom PIL import ImageFile\nfrom tqdm import tqdm\nimport h5py\nimport cv2\n\nimport matplotlib.pylab as plt\nfrom matplotlib import cm\n%matplotlib inline\n\nfrom sklearn.model_selection import train_test_split\n\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.preprocessing import image as keras_image\n\nfrom tensorflow.keras.models import Sequential, load_model\nfrom tensorflow.keras.layers import Dense, LSTM, GlobalAveragePooling1D, GlobalAveragePooling2D\nfrom tensorflow.keras.layers import Activation, Flatten, Dropout, BatchNormalization\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, GlobalMaxPooling2D\nfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\nfrom tensorflow.keras.layers import PReLU, LeakyReLU\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.metrics import plot_confusion_matrix\nimport seaborn as sns\n\nimport math, re, os\nimport numpy as np\nimport tensorflow as tf","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:13.953547Z","iopub.execute_input":"2022-12-04T07:20:13.954171Z","iopub.status.idle":"2022-12-04T07:20:13.970825Z","shell.execute_reply.started":"2022-12-04T07:20:13.954140Z","shell.execute_reply":"2022-12-04T07:20:13.969869Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Detect TPU, return appropriate distribution strategy\ntry:\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    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() \n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:13.971999Z","iopub.execute_input":"2022-12-04T07:20:13.972230Z","iopub.status.idle":"2022-12-04T07:20:23.948744Z","shell.execute_reply.started":"2022-12-04T07:20:13.972203Z","shell.execute_reply":"2022-12-04T07:20:23.947997Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nprint(GCS_DS_PATH) # what do gcs paths look like?","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:23.950244Z","iopub.execute_input":"2022-12-04T07:20:23.950849Z","iopub.status.idle":"2022-12-04T07:20:24.368607Z","shell.execute_reply.started":"2022-12-04T07:20:23.950816Z","shell.execute_reply":"2022-12-04T07:20:24.367653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [512, 512]\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-512x512'\nAUTO = tf.data.experimental.AUTOTUNE\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') \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\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    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 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","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:24.370030Z","iopub.execute_input":"2022-12-04T07:20:24.370450Z","iopub.status.idle":"2022-12-04T07:20:24.603901Z","shell.execute_reply.started":"2022-12-04T07:20:24.370414Z","shell.execute_reply":"2022-12-04T07:20:24.602994Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def data_augment(image, label):\n    # Thanks to the dataset.prefetch(AUTO)\n    # statement in the next function (below), this happens essentially\n    # for free on TPU. Data pipeline code is executed on the \"CPU\"\n    # part 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\ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec\n    # 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)\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))\n","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:24.605083Z","iopub.execute_input":"2022-12-04T07:20:24.605371Z","iopub.status.idle":"2022-12-04T07:20:24.617622Z","shell.execute_reply.started":"2022-12-04T07:20:24.605325Z","shell.execute_reply":"2022-12-04T07:20:24.616757Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define the batch size. This will be 16 with TPU off and 128 (=16*8) with TPU on\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nds_train = get_training_dataset()\nds_valid = get_validation_dataset()\nds_test = get_test_dataset()\n\nprint(\"Training:\", ds_train)\nprint (\"Validation:\", ds_valid)\nprint(\"Test:\", ds_test)","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:24.619089Z","iopub.execute_input":"2022-12-04T07:20:24.619318Z","iopub.status.idle":"2022-12-04T07:20:24.791723Z","shell.execute_reply.started":"2022-12-04T07:20:24.619292Z","shell.execute_reply":"2022-12-04T07:20:24.790863Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from matplotlib import pyplot as plt\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,\n                                     # 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\n    # 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\n    # 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()\n\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.'])","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:24.793047Z","iopub.execute_input":"2022-12-04T07:20:24.793302Z","iopub.status.idle":"2022-12-04T07:20:24.812938Z","shell.execute_reply.started":"2022-12-04T07:20:24.793274Z","shell.execute_reply":"2022-12-04T07:20:24.812007Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.set_printoptions(threshold=15, linewidth=80)\n\nprint(\"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())","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:24.816050Z","iopub.execute_input":"2022-12-04T07:20:24.816584Z","iopub.status.idle":"2022-12-04T07:20:29.893789Z","shell.execute_reply.started":"2022-12-04T07:20:24.816544Z","shell.execute_reply":"2022-12-04T07:20:29.893009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Test data shapes:\")\nfor image, idnum in ds_test.take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test data IDs:\", idnum.numpy().astype('U')) # U=unicode string","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:29.894807Z","iopub.execute_input":"2022-12-04T07:20:29.895064Z","iopub.status.idle":"2022-12-04T07:20:32.640899Z","shell.execute_reply.started":"2022-12-04T07:20:29.895037Z","shell.execute_reply":"2022-12-04T07:20:32.639892Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(20))","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:32.642402Z","iopub.execute_input":"2022-12-04T07:20:32.642806Z","iopub.status.idle":"2022-12-04T07:20:32.661237Z","shell.execute_reply.started":"2022-12-04T07:20:32.642765Z","shell.execute_reply":"2022-12-04T07:20:32.660018Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:32.662646Z","iopub.execute_input":"2022-12-04T07:20:32.663402Z","iopub.status.idle":"2022-12-04T07:20:37.641574Z","shell.execute_reply.started":"2022-12-04T07:20:32.663367Z","shell.execute_reply":"2022-12-04T07:20:37.639471Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import math","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:20:37.643338Z","iopub.execute_input":"2022-12-04T07:20:37.643889Z","iopub.status.idle":"2022-12-04T07:20:37.648748Z","shell.execute_reply.started":"2022-12-04T07:20:37.643849Z","shell.execute_reply":"2022-12-04T07:20:37.647326Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"steps_per_epoch = math.ceil(NUM_TRAINING_IMAGES / BATCH_SIZE)\n\ndef define_model(show_summary=False):\n    model = tf.keras.models.Sequential([\n\n        tf.keras.Input(shape=[*IMAGE_SIZE, 3]),\n    \n        # This is the first convolution\n        layers.Conv2D(64, (3,3), activation='relu'),\n        layers.MaxPooling2D(2, 2),\n\n        # The second convolution\n        layers.Conv2D(64, (3,3), activation='relu'),\n        layers.MaxPooling2D(2,2),\n\n        # The third convolution\n        layers.Conv2D(128, (3,3), activation='relu'),\n        layers.MaxPooling2D(2,2),\n\n        # The fourth convolution\n        layers.Conv2D(128, (3,3), activation='relu'),\n        layers.MaxPooling2D(2,2),\n\n        # Flatten the results to feed into a DNN\n        layers.GlobalAveragePooling2D(),\n        layers.Dropout(0.5),\n        # 512 neuron hidden layer\n        layers.Dense(512, activation='relu'),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    if show_summary:\n        model.summary()\n        \n    model.compile(\n        optimizer='adam',\n        loss = 'sparse_categorical_crossentropy',\n        metrics=['sparse_categorical_accuracy'])\n    \n    return model","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:26:23.257755Z","iopub.execute_input":"2022-12-04T07:26:23.258768Z","iopub.status.idle":"2022-12-04T07:26:23.269489Z","shell.execute_reply.started":"2022-12-04T07:26:23.258723Z","shell.execute_reply":"2022-12-04T07:26:23.268135Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    model = define_model(show_summary=True)","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:26:25.368803Z","iopub.execute_input":"2022-12-04T07:26:25.369145Z","iopub.status.idle":"2022-12-04T07:26:25.643866Z","shell.execute_reply.started":"2022-12-04T07:26:25.369111Z","shell.execute_reply":"2022-12-04T07:26:25.642705Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define training epochs\nEPOCHS = 50\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    steps_per_epoch=STEPS_PER_EPOCH\n)","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:26:26.282418Z","iopub.execute_input":"2022-12-04T07:26:26.282753Z","iopub.status.idle":"2022-12-04T07:45:34.142240Z","shell.execute_reply.started":"2022-12-04T07:26:26.282721Z","shell.execute_reply":"2022-12-04T07:45:34.141352Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.evaluate(ds_valid)","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:46:10.078498Z","iopub.execute_input":"2022-12-04T07:46:10.079437Z","iopub.status.idle":"2022-12-04T07:46:12.330614Z","shell.execute_reply.started":"2022-12-04T07:46:10.079378Z","shell.execute_reply":"2022-12-04T07:46:12.329989Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():    \n    pretrained_model = efn.EfficientNetB7(\n        weights='imagenet', \n        include_top=False ,\n        input_shape=[*IMAGE_SIZE, 3]\n    )\n    pretrained_model.trainable = True # transfer learning\n    model = tf.keras.Sequential([\n        pretrained_model, \n        tf.keras.layers.Dropout(.02),\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.BatchNormalization(),\n        tf.keras.layers.Dense(len(CLASSES), kernel_regularizer=regularizers.L2(REG_FACTOR), \n            activation='softmax')\n    ])","metadata":{"execution":{"iopub.status.busy":"2022-12-04T08:04:05.655030Z","iopub.execute_input":"2022-12-04T08:04:05.655346Z","iopub.status.idle":"2022-12-04T08:04:35.908409Z","shell.execute_reply.started":"2022-12-04T08:04:05.655311Z","shell.execute_reply":"2022-12-04T08:04:35.906236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# upgrade pip if needed\n#!pip install --upgrade pip  # get the latest version\n# install tensorflow-addons\n!pip install -q -U tensorflow-addons\n# install EfficientNet\n!pip install -q efficientnet","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:57:53.577105Z","iopub.execute_input":"2022-12-04T07:57:53.577555Z","iopub.status.idle":"2022-12-04T07:58:21.440192Z","shell.execute_reply.started":"2022-12-04T07:57:53.577515Z","shell.execute_reply":"2022-12-04T07:58:21.439304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import efficientnet.tfkeras as efn","metadata":{"execution":{"iopub.status.busy":"2022-12-04T07:58:21.442336Z","iopub.execute_input":"2022-12-04T07:58:21.442611Z","iopub.status.idle":"2022-12-04T07:58:21.753731Z","shell.execute_reply.started":"2022-12-04T07:58:21.442578Z","shell.execute_reply":"2022-12-04T07:58:21.753017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(\n    optimizer='adam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)","metadata":{"execution":{"iopub.status.busy":"2022-12-04T08:04:35.913616Z","iopub.status.idle":"2022-12-04T08:04:35.914370Z","shell.execute_reply.started":"2022-12-04T08:04:35.914157Z","shell.execute_reply":"2022-12-04T08:04:35.914178Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define training epochs\nEPOCHS = 50\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    steps_per_epoch=STEPS_PER_EPOCH,\n)","metadata":{"execution":{"iopub.status.busy":"2022-12-04T08:04:00.374218Z","iopub.status.idle":"2022-12-04T08:04:00.374563Z","shell.execute_reply.started":"2022-12-04T08:04:00.374380Z","shell.execute_reply":"2022-12-04T08:04:00.374408Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}