{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Loading Libraries","execution_count":null},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import math, re, os # Importing Regular Expression and Operating systems modules\nimport tensorflow as tf\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\n\nAUTO = tf.data.experimental.AUTOTUNE # Saves time by pre-fetching data to be trained when training \n                                     # is occuring for another set of data\n\nimport numpy as np\nimport keras\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D\nfrom tensorflow.keras.optimizers import SGD\nfrom tensorflow.keras.layers import BatchNormalization\nfrom tensorflow.keras.layers import LeakyReLU\nfrom tensorflow.keras.models import clone_model\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.utils import plot_model\nfrom keras.models import load_model\n\n\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nimport numpy as np\nimport datetime as dt\nimport pandas as pd\nimport math, re, os\nimport tensorflow as tf\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\nAUTO = tf.data.experimental.AUTOTUNE\n\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Data Access\nGCS_DS_PATH = KaggleDatasets().get_gcs_path() # you can list the bucket with \"!gsutil ls $GCS_DS_PATH\"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Checking if TPU is running","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"try:\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    print('TPU not enabled')\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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Start of Main code","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE = [512, 512] # Largest Image size. TPU does not have problem with memory usage\nEPOCHS = 20\nBATCH_SIZE = 128\n\n#Specifying the GCS Path\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}\n\nGCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]] ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Loading the Data[](http://)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAINING_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\n# Label Names\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","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Pre-Processing","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Pre-processing RAW image\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)# convert the compressed string to a 3D uint8 tensor\n    image = tf.cast(image, tf.float32) / 255.0  # casting image to floats in [0, 1] range\n    image = tf.reshape(image, [*IMAGE_SIZE, 3]) # explicit size needed for TPU\n    return image\n\n# Parsing data from TFrecord of Training Data to tensor to feed into model\n# More Details - https://medium.com/coinmonks/beginners-guide-to-feeding-data-in-tensorflow-part2-5e2506d75429\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\n# Parsing data from TFrecord Test Data, does not have labels\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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Loading Dataset","execution_count":null},{"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() # An Options object can be, for instance, used to control which \n                                     # graph optimizations to apply or whether to use performance modeling \n                                     # to dynamically tune the parallelism of operations such as tf.data.Dataset.map \n                                     # or tf.data.Dataset.interleave.\n    \n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed. By default, it is True.\n        \n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from \n                                                                          # multiple files\n    \n    dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original \n                                                 # order. This method applies the properties of the options object \n                                                 # to the dataset\n    \n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n                                                 # The map function applies the function transformation to each element\n                                                 # of the dataset. Returns a dataset of (image, label) pairs if \n                                                 #labeled=True or (image, id) pairs if labeled=False\n    return dataset","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Augmentation","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def data_augment(image, label):\n    # Data augmentation. Because of 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    \n    #image = tf.image.resize_with_crop_or_pad(image, 34, 34) # Add 6 pixels of padding\n    #image = tf.image.random_crop(image, size=[28, 28, 1]) # Random crop back to 28x28\n    image = tf.image.random_brightness(image, max_delta=0.5) # Random brightness\n    image = tf.image.random_flip_left_right(image)\n    image = tf.image.random_flip_up_down(image)\n    image = tf.image.random_saturation(image, 0, 2)\n    return image, label   ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Final Loading of data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n    dataset = dataset.repeat() # the training dataset must repeat for several epochs\n    dataset = dataset.shuffle(2048) # The Dataset.shuffle() transformation maintains a fixed-size buffer of 2048  \n                                    # and chooses the next element uniformly at random from that buffer.\n    dataset = dataset.batch(BATCH_SIZE) # Combines consecutive elements of this dataset into batches.\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() # Caches the elements in this dataset. The first time the dataset is iterated over, \n                              # its elements will be cached either in the specified file or in memory. \n                              # Subsequent iterations will use the cached data.\n\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\ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec files, i.e. flowers00-230.tfrec = 230 data items\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n#print('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))\n    ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Setting Properties of Graph Plots","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# numpy and matplotlib defaults\nnp.set_printoptions(threshold=15, linewidth=80)  # These options determine the way floating point numbers, arrays and \n                                                 # other NumPy objects are displayed. Threshold specifies no. of array elements\n                                                 # which trigger summarisation. Linewidth specifies no. of chars per line for\n                                                 # inserting linebreaks\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)]  # If no labels, only image IDs, return None for labels \n                                                                # (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","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Function to display an image","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 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        \n    # auto-squaring: this will drop data that does not fit into square or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n    \n    # size and spacing\n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[label]\n        correct = True\n        if predictions is not None:\n            title, correct = title_from_label_and_target(predictions[i], label)\n        dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n        subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n    \n    #layout\n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspace=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Confusion Matrix","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def display_confusion_matrix(cmat, score, precision, recall):\n    plt.figure(figsize=(15,15))\n    ax = plt.gca()\n    ax.matshow(cmat, cmap='Reds')\n    ax.set_xticks(range(len(CLASSES)))\n    ax.set_xticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"left\", rotation_mode=\"anchor\")\n    ax.set_yticks(range(len(CLASSES)))\n    ax.set_yticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_yticklabels(), rotation=45, ha=\"right\", rotation_mode=\"anchor\")\n    titlestring = \"\"\n    if score is not None:\n        titlestring += 'f1 = {:.3f} '.format(score)\n    if precision is not None:\n        titlestring += '\\nprecision = {:.3f} '.format(precision)\n    if recall is not None:\n        titlestring += '\\nrecall = {:.3f} '.format(recall)\n    if len(titlestring) > 0:\n        ax.text(101, 1, titlestring, fontdict={'fontsize': 18, 'horizontalalignment':'right', 'verticalalignment':'top', 'color':'#804040'})\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training and Validation Curves","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"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":"# Checking whether all the data is properly loaded","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Training data shapes:\")\nfor image, label in get_training_dataset().take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training data label examples:\", label.numpy())\nprint(\"Validation data shapes:\")\nfor image, label in get_validation_dataset().take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Validation data label examples:\", label.numpy())\nprint(\"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\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Sample Training data\ntraining_dataset = get_training_dataset()\ntraining_dataset = training_dataset.unbatch().batch(20)\ntrain_batch = iter(training_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(train_batch))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Sample 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":"# Learning Rate Scheduler","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 = 0.00001\nLR_RAMPUP_EPOCHS = 5\nLR_SUSTAIN_EPOCHS = 0\nLR_EXP_DECAY = .8\n\ndef lrfn(epoch):\n    if epoch < LR_RAMPUP_EPOCHS:\n        lr = (LR_MAX - LR_START) / LR_RAMPUP_EPOCHS * epoch + LR_START\n    elif epoch < LR_RAMPUP_EPOCHS + LR_SUSTAIN_EPOCHS:\n        lr = LR_MAX\n    else:\n        lr = (LR_MAX - LR_MIN) * LR_EXP_DECAY**(epoch - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS) + LR_MIN\n    return lr\n    \n\nlr_callback = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose = True)\n\nrng = [i for i in range(25 if EPOCHS<25 else 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":{},"cell_type":"markdown","source":"# Model Design","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Adding Resnet Model\ndef res_net_block(input_data, filters,fsize,pool = False):\n    res = input_data\n\n\n    if pool:\n        input_data = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(input_data)\n        input_data = layers.Conv2D(filters, kernel_size=(1, 1), strides=(1,1), padding='same')(input_data)\n        res = layers.BatchNormalization()(input_data)   \n\n\n    x1 =  layers.BatchNormalization()(input_data)\n    x1 = layers.Conv2D(filters, fsize, activation='relu', padding='same')(x1)\n    x1 = tf.nn.leaky_relu(x1, alpha=0.01, name='Leaky_ReLU')\n    x1 = layers.Dropout(0.1)(x1)\n\n    if pool:\n        x1 =  layers.BatchNormalization()(x1)\n        x1 = tf.nn.leaky_relu(x1, alpha=0.01, name='Leaky_ReLU') \n        x1 = layers.Conv2D(filters=filters, kernel_size=fsize, strides=[1, 1], padding=\"same\")(x1)\n    \n    x = layers.Add()([ x1 , res ])\n    x = tf.nn.leaky_relu(x, alpha=0.01, name='Leaky_ReLU') \n    return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Using a hybridnet\ndef hybridnet():\n    inputs = keras.Input(shape=(512,512,3))\n    \n    x = layers.Conv2D(64, (5, 5), strides = (2, 2), name = 'conv1')(inputs)\n    x = tf.keras.layers.BatchNormalization()(x)\n    x = tf.nn.leaky_relu(x, alpha=0.01, name='Leaky_ReLU') \n    x = layers.MaxPooling2D(3)(x)\n    x = layers.Dropout(0.1)(x)\n\n    num_res_net_blocks = 10\n    x = res_net_block(x, 64,3,True)\n    for i in range(num_res_net_blocks):\n        x = res_net_block(x, 64,3)\n        \n    num_res_net_blocks = 20\n    x = res_net_block(x, 128,3,True)\n    for i in range(num_res_net_blocks):\n        x = res_net_block(x, 128,3)\n        \n    num_res_net_blocks = 30\n    x = res_net_block(x, 256,3,True)\n    for i in range(num_res_net_blocks):\n        x = res_net_block(x, 256,5)\n        \n    #xx1 = layers.GlobalAveragePooling2D()(xx1)\n    x = layers.GlobalAveragePooling2D()(x)\n    x = layers.Dense(256, activation='relu',name='my_dense')(x)\n    \n    #xx2 = layers.Add()([ xx1 , xx2 ])\n    x = layers.Dense(512, activation='relu')(x)\n   \n    \n    x = tf.keras.layers.Dense(out_ptron, activation='softmax')(x)\n    \n    model = keras.Model(inputs, outputs=x)\n    return model","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Selecting the Adam optimiser","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"history_list = []\nEPOCHS = 10","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true},"cell_type":"code","source":"from keras.models import Model\nfrom tensorflow import keras\n#!pip install -q efficientnet\n#import efficientnet.tfkeras as efn\nwith strategy.scope():\n    \n    out_ptron = len(CLASSES)\n    model = hybridnet()\n\n\n        \nmodel.compile(\n    optimizer = tf.keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, amsgrad=False),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Fitting our model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(get_training_dataset(), steps_per_epoch=STEPS_PER_EPOCH, epochs=EPOCHS, callbacks=[lr_callback],validation_data=get_validation_dataset())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Saving model in default directory\nmodel.save('FlowerTPU_model1.h5')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Displaying model loss and accuracy","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"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":{"trusted":true},"cell_type":"code","source":"display_training_curves(history.history['loss'], history.history['val_loss'], 'loss', 211)\ndisplay_training_curves(history.history['sparse_categorical_accuracy'], history.history['val_sparse_categorical_accuracy'], 'accuracy', 212)\nprint(\"Score is low since we are not using any pretrained weights\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Comparing with a pretrained Densenet201","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Loading the model into the TPU\nfrom tensorflow.keras.applications import ResNet50V2,ResNet101V2,ResNet152V2,DenseNet201\nwith 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(\noptimizer = tf.keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, amsgrad=False),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\nmodel2.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Configuration\nIMAGE_SIZE = [512, 512]\nEPOCHS = 10\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr_schedule = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=1)\n\nhistory = model2.fit(get_training_dataset(), steps_per_epoch=STEPS_PER_EPOCH, epochs=EPOCHS, callbacks=[lr_callback],validation_data=get_validation_dataset())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Saving model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Saving model in default directory\nmodel2.save('FlowerTPU_model2.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Displaying Training curves\ndisplay_training_curves(history.history['loss'], history.history['loss'], 'loss', 211)\ndisplay_training_curves(history.history['sparse_categorical_accuracy'], history.history['sparse_categorical_accuracy'], 'accuracy', 212)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Using Effinet Pre-trained","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom keras.models import Model\nfrom tensorflow import keras\n!pip install -q efficientnet\nimport efficientnet.tfkeras as efn\nwith strategy.scope():\n    \n    efficient_net = efn.EfficientNetB7(\n        input_shape=(512, 512, 3),\n        weights='imagenet',\n        include_top=False\n    )\n    \n\n    model3 = tf.keras.Sequential([\n        efficient_net,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n        \nmodel3.compile(\n    optimizer=tf.keras.optimizers.Adam(),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\nmodel3.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Configuration\nIMAGE_SIZE = [512, 512]\nEPOCHS = 50\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr_schedule = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=1)\n\nhistory = model3.fit(get_training_dataset(), steps_per_epoch=STEPS_PER_EPOCH, epochs=EPOCHS, callbacks=[lr_callback],validation_data=get_validation_dataset())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Saving model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Saving model in default directory\nmodel3.save('FlowerTPU_model3.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"display_training_curves(history.history['loss'], history.history['loss'], 'loss', 211)\ndisplay_training_curves(history.history['sparse_categorical_accuracy'], history.history['sparse_categorical_accuracy'], 'accuracy', 212)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Final prediction and submission","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# Predictions for model3\ntest_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 = model3.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}