{"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":"markdown","source":"#### What are you trying to do in this notebook?\nIn this competition, we’re building a machine learning model that identifies the type of flowers in a dataset of images (for simplicity, we’re sticking to just over 100 types).\n\nLearn how to use Tensor Processing Units (TPUs) on Kaggle.\n\nTPUs are powerful hardware accelerators specialized in deep learning tasks. They were developed (and first used) by Google to process large image databases, such as extracting all the text from Street View.\n\n#### Why are you trying it?\nWe're trying to classify 104 types of flowers based on their images drawn from five different public datasets. Some classes are very narrow, containing only a particular sub-type of flower (e.g. pink primroses) while other classes contain many sub-types (e.g. wild roses).\nThe dataset contains imperfections - images of flowers in odd places, or as a backdrop to modern machinery - but that's part of the challenge! Build a classifier than can see past all that, to the flowers at the heart of the images.","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-12-03T11:35:19.849834Z","iopub.execute_input":"2021-12-03T11:35:19.850610Z","iopub.status.idle":"2021-12-03T11:35:19.960053Z","shell.execute_reply.started":"2021-12-03T11:35:19.850480Z","shell.execute_reply":"2021-12-03T11:35:19.959210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nimport pandas as pd\nfrom kaggle_datasets import KaggleDatasets\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras import applications\nimport re","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:19.961764Z","iopub.execute_input":"2021-12-03T11:35:19.962013Z","iopub.status.idle":"2021-12-03T11:35:25.453569Z","shell.execute_reply.started":"2021-12-03T11:35:19.961985Z","shell.execute_reply":"2021-12-03T11:35:25.452666Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:25.454707Z","iopub.execute_input":"2021-12-03T11:35:25.454949Z","iopub.status.idle":"2021-12-03T11:35:31.478926Z","shell.execute_reply.started":"2021-12-03T11:35:25.454921Z","shell.execute_reply":"2021-12-03T11:35:31.477822Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [192, 192] # at this size, a GPU will run out of memory. Use the TPU\nEPOCHS = 100\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nNUM_TRAINING_IMAGES = 12753\nNUM_TEST_IMAGES = 7382\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nGCS_DS_PATH = KaggleDatasets().get_gcs_path() # you can list the bucket with \"!gsutil ls $GCS_DS_PATH\"\nprint(GCS_DS_PATH)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:31.480402Z","iopub.execute_input":"2021-12-03T11:35:31.480631Z","iopub.status.idle":"2021-12-03T11:35:31.904088Z","shell.execute_reply.started":"2021-12-03T11:35:31.480603Z","shell.execute_reply":"2021-12-03T11:35:31.902943Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_PATH_2 = GCS_DS_PATH + '/tfrecords-jpeg-192x192'\nAUTO = tf.data.experimental.AUTOTUNE\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH_2 + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH_2 + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH_2 + '/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","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:31.906759Z","iopub.execute_input":"2021-12-03T11:35:31.907024Z","iopub.status.idle":"2021-12-03T11:35:32.149898Z","shell.execute_reply.started":"2021-12-03T11:35:31.906994Z","shell.execute_reply":"2021-12-03T11:35:32.148956Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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 data_augment(image, label):\n    image = tf.image.random_flip_left_right(image)\n    #image = tf.image.random_saturation(image, 0, 2)\n    return image, label  \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) # 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)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset\n\ndef get_training_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-192x192/train/*.tfrec'), 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)\n    return dataset\n\ndef get_validation_dataset(ordered=False):\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-192x192/val/*.tfrec'), 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","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:32.154082Z","iopub.execute_input":"2021-12-03T11:35:32.154371Z","iopub.status.idle":"2021-12-03T11:35:32.173940Z","shell.execute_reply.started":"2021-12-03T11:35:32.154336Z","shell.execute_reply":"2021-12-03T11:35:32.173225Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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)\n\nprint('Dataset: {} training images, {} validation images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES))","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:32.175664Z","iopub.execute_input":"2021-12-03T11:35:32.175996Z","iopub.status.idle":"2021-12-03T11:35:32.194202Z","shell.execute_reply.started":"2021-12-03T11:35:32.175952Z","shell.execute_reply":"2021-12-03T11:35:32.193210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def sample_images(images, row_count, column_count):\n    fig, axs = plt.subplots(row_count, column_count, figsize=(10,10))\n    for i in range(row_count):\n        for j in range(column_count):\n            axs[i,j].imshow(images[i * column_count + j])\n            axs[i,j].axis('off')\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:32.195833Z","iopub.execute_input":"2021-12-03T11:35:32.197024Z","iopub.status.idle":"2021-12-03T11:35:32.204878Z","shell.execute_reply.started":"2021-12-03T11:35:32.196982Z","shell.execute_reply":"2021-12-03T11:35:32.203976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def find_mean_img(full_mat, title, size = (192, 192, 3)):\n    # calculate the average\n    mean_img = np.mean(full_mat, axis = 0)\n    # reshape it back to a matrix\n    mean_img = mean_img.reshape(size)\n    plt.imshow(mean_img, vmin=0, vmax=255)\n    plt.title(f'Average {title}')\n    plt.axis('off')\n    plt.show()\n    return mean_img","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:32.205952Z","iopub.execute_input":"2021-12-03T11:35:32.206699Z","iopub.status.idle":"2021-12-03T11:35:32.216580Z","shell.execute_reply.started":"2021-12-03T11:35:32.206667Z","shell.execute_reply":"2021-12-03T11:35:32.215597Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"training_dataset = get_training_dataset()\nvalidation_dataset = get_validation_dataset()","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:32.218167Z","iopub.execute_input":"2021-12-03T11:35:32.218401Z","iopub.status.idle":"2021-12-03T11:35:32.618520Z","shell.execute_reply.started":"2021-12-03T11:35:32.218372Z","shell.execute_reply":"2021-12-03T11:35:32.617576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for item in training_dataset:\n    images = item[0].numpy()\n    labels = item[1].numpy()\n    break\nimages.shape, labels.shape","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:32.619817Z","iopub.execute_input":"2021-12-03T11:35:32.620102Z","iopub.status.idle":"2021-12-03T11:35:36.329944Z","shell.execute_reply.started":"2021-12-03T11:35:32.620049Z","shell.execute_reply":"2021-12-03T11:35:36.328882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.unique(labels, return_counts = True)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:36.331670Z","iopub.execute_input":"2021-12-03T11:35:36.331909Z","iopub.status.idle":"2021-12-03T11:35:36.339958Z","shell.execute_reply.started":"2021-12-03T11:35:36.331882Z","shell.execute_reply":"2021-12-03T11:35:36.339123Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_images(images, 4, 4)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:36.341161Z","iopub.execute_input":"2021-12-03T11:35:36.341375Z","iopub.status.idle":"2021-12-03T11:35:37.627612Z","shell.execute_reply.started":"2021-12-03T11:35:36.341349Z","shell.execute_reply":"2021-12-03T11:35:37.626996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(labels) \n\nfull_mat_F1 = images [labels == 4, :,:,:]\nfull_mat_F2 = images [labels == 67,:,:,:]\nfull_mat_F3 = images [labels == 73,:,:,:]","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:37.630498Z","iopub.execute_input":"2021-12-03T11:35:37.631084Z","iopub.status.idle":"2021-12-03T11:35:37.640784Z","shell.execute_reply.started":"2021-12-03T11:35:37.631038Z","shell.execute_reply":"2021-12-03T11:35:37.640046Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"F1_mean = find_mean_img(full_mat_F1, 'F1')\nF2_mean = find_mean_img(full_mat_F2, 'F2')\nF3_mean = find_mean_img(full_mat_F3, 'F3')","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:37.642446Z","iopub.execute_input":"2021-12-03T11:35:37.642870Z","iopub.status.idle":"2021-12-03T11:35:38.172193Z","shell.execute_reply.started":"2021-12-03T11:35:37.642838Z","shell.execute_reply":"2021-12-03T11:35:38.171336Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"checkpoint_path = \"model.h5\"\ncheckpoint = tf.keras.callbacks.ModelCheckpoint(checkpoint_path, save_best_only=True)\n","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:38.173380Z","iopub.execute_input":"2021-12-03T11:35:38.173600Z","iopub.status.idle":"2021-12-03T11:35:38.178461Z","shell.execute_reply.started":"2021-12-03T11:35:38.173572Z","shell.execute_reply":"2021-12-03T11:35:38.177566Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"LR_START = 0.00005\nLR_MAX =   0.00005 * strategy.num_replicas_in_sync\nLR_MIN =   0.0000025\nLR_RAMPUP_EPOCHS = 3\nLR_SUSTAIN_EPOCHS = 6\nLR_EXP_DECAY = .8\ndef scheduler_callback(epoch):\n    if epoch < LR_RAMPUP_EPOCHS:\n        lr =  np.random.random_sample() * 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\nscheduler = tf.keras.callbacks.LearningRateScheduler(scheduler_callback, verbose=True)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:38.179691Z","iopub.execute_input":"2021-12-03T11:35:38.180033Z","iopub.status.idle":"2021-12-03T11:35:38.189013Z","shell.execute_reply.started":"2021-12-03T11:35:38.180004Z","shell.execute_reply":"2021-12-03T11:35:38.188295Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"early_stop = tf.keras.callbacks.EarlyStopping(patience=10)\n","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:38.190409Z","iopub.execute_input":"2021-12-03T11:35:38.190876Z","iopub.status.idle":"2021-12-03T11:35:38.199375Z","shell.execute_reply.started":"2021-12-03T11:35:38.190845Z","shell.execute_reply":"2021-12-03T11:35:38.198631Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"callbacks = [early_stop, checkpoint, scheduler]","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:38.200397Z","iopub.execute_input":"2021-12-03T11:35:38.200649Z","iopub.status.idle":"2021-12-03T11:35:38.208909Z","shell.execute_reply.started":"2021-12-03T11:35:38.200624Z","shell.execute_reply":"2021-12-03T11:35:38.208162Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"optimizer = tf.keras.optimizers.Adam(learning_rate=0.001, \n                                                 beta_1=0.9, \n                                                 beta_2=0.999, \n                                                 epsilon=1e-07, \n                                                 amsgrad=False)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:38.210338Z","iopub.execute_input":"2021-12-03T11:35:38.210820Z","iopub.status.idle":"2021-12-03T11:35:38.219816Z","shell.execute_reply.started":"2021-12-03T11:35:38.210781Z","shell.execute_reply":"2021-12-03T11:35:38.219280Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_types = [\n    \"dense_net\", \n    \"xception\", \n    \"inception\", \n    \"inceptionResNet\",\n]\n\nmodel_type = model_types[1]\n\ndef get_pretraind_model(model_type, input_shape):\n    if model_type == \"dense_net\":\n        return applications.densenet.DenseNet121(\n                include_top=False,\n                input_shape=input_shape               \n            )\n    if model_type == \"xception\":\n        return applications.Xception(\n            include_top=False,\n            input_shape=input_shape                        \n        )\n    if model_type == \"inception\":\n        return applications.InceptionV3(\n            include_top=False,\n            input_shape=input_shape                          \n        )\n    if model_type == \"inceptionResNet\":\n        return applications.InceptionResNetV2(\n            include_top=False,\n                input_shape=input_shape                         \n        )","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:38.221686Z","iopub.execute_input":"2021-12-03T11:35:38.222177Z","iopub.status.idle":"2021-12-03T11:35:38.231319Z","shell.execute_reply.started":"2021-12-03T11:35:38.222146Z","shell.execute_reply":"2021-12-03T11:35:38.230737Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def train(\n    model_type, epochs, optimizer, callbacks, \n    strategy, layers):\n    tf.keras.backend.clear_session()\n    with strategy.scope():  \n        input_shape = [*IMAGE_SIZE, 3]   \n        pretrained_model = get_pretraind_model(model_type, input_shape)\n        print(pretrained_model.summary())\n        pretrained_model.trainable = True \n        all_layers = [pretrained_model] + layers + [tf.keras.layers.Dense(104, activation='softmax')]\n        model = tf.keras.Sequential(all_layers)\n        model.compile(\n            optimizer=optimizer,\n            loss = 'sparse_categorical_crossentropy',\n            metrics=['sparse_categorical_accuracy']\n        )\n        history = model.fit(training_dataset, \n                            steps_per_epoch=STEPS_PER_EPOCH, \n                            epochs=epochs, \n                            validation_data=validation_dataset, \n                            callbacks=callbacks\n                           )\n        pd.DataFrame(history.history).plot()\n        plt.show()\n        return model","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:38.232313Z","iopub.execute_input":"2021-12-03T11:35:38.232958Z","iopub.status.idle":"2021-12-03T11:35:38.245939Z","shell.execute_reply.started":"2021-12-03T11:35:38.232924Z","shell.execute_reply":"2021-12-03T11:35:38.245381Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = train(\n    model_type, EPOCHS, optimizer, callbacks, strategy, \n    layers=[\n        tf.keras.layers.Dropout(0.5), \n        tf.keras.layers.GlobalAveragePooling2D(), \n        tf.keras.layers.Dropout(0.5)\n    ]\n)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:35:38.247210Z","iopub.execute_input":"2021-12-03T11:35:38.247776Z","iopub.status.idle":"2021-12-03T11:46:21.043253Z","shell.execute_reply.started":"2021-12-03T11:35:38.247735Z","shell.execute_reply":"2021-12-03T11:46:21.042305Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\n\ndef display_confusion_matrix(cmat, score, precision, recall):\n    plt.figure(figsize=(15,15))\n    ax = plt.gca()\n    ax.matshow(cmat, cmap='Reds')\n    ax.set_xticks(range(len(CLASSES)))\n    ax.set_xticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"left\", rotation_mode=\"anchor\")\n    ax.set_yticks(range(len(CLASSES)))\n    ax.set_yticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_yticklabels(), rotation=45, ha=\"right\", rotation_mode=\"anchor\")\n    titlestring = \"\"\n    if score is not None:\n        titlestring += 'f1 = {:.3f} '.format(score)\n    if precision is not None:\n        titlestring += '\\nprecision = {:.3f} '.format(precision)\n    if recall is not None:\n        titlestring += '\\nrecall = {:.3f} '.format(recall)\n    if len(titlestring) > 0:\n        ax.text(101, 1, titlestring, fontdict={'fontsize': 18, 'horizontalalignment':'right', 'verticalalignment':'top', 'color':'#804040'})\n    plt.show()\n    \ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:46:21.045008Z","iopub.execute_input":"2021-12-03T11:46:21.046061Z","iopub.status.idle":"2021-12-03T11:46:21.699424Z","shell.execute_reply.started":"2021-12-03T11:46:21.046017Z","shell.execute_reply":"2021-12-03T11:46:21.698490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cmdataset = 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_probabilities = model.predict(images_ds)\ncm_predictions = np.argmax(cm_probabilities, axis=-1)\n\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 # normalize","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:46:21.700953Z","iopub.execute_input":"2021-12-03T11:46:21.701328Z","iopub.status.idle":"2021-12-03T11:46:34.062474Z","shell.execute_reply.started":"2021-12-03T11:46:21.701284Z","shell.execute_reply":"2021-12-03T11:46:34.059899Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"score = f1_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nprecision = precision_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nrecall = recall_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\ndisplay_confusion_matrix(cmat, score, precision, recall)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:46:34.064406Z","iopub.execute_input":"2021-12-03T11:46:34.064725Z","iopub.status.idle":"2021-12-03T11:46:39.121644Z","shell.execute_reply.started":"2021-12-03T11:46:34.064683Z","shell.execute_reply":"2021-12-03T11:46:39.120994Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:46:39.122897Z","iopub.execute_input":"2021-12-03T11:46:39.123511Z","iopub.status.idle":"2021-12-03T11:46:39.228271Z","shell.execute_reply.started":"2021-12-03T11:46:39.123464Z","shell.execute_reply":"2021-12-03T11:46:39.227264Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from matplotlib import pyplot as plt\nimport math\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":"2021-12-03T11:46:39.229872Z","iopub.execute_input":"2021-12-03T11:46:39.230187Z","iopub.status.idle":"2021-12-03T11:46:39.253403Z","shell.execute_reply.started":"2021-12-03T11:46:39.230151Z","shell.execute_reply":"2021-12-03T11:46:39.252342Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"images, labels = next(batch)\nprobabilities = model.predict(images)\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions)\n","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:46:39.254639Z","iopub.execute_input":"2021-12-03T11:46:39.254958Z","iopub.status.idle":"2021-12-03T11:46:45.777456Z","shell.execute_reply.started":"2021-12-03T11:46:39.254927Z","shell.execute_reply":"2021-12-03T11:46:45.776447Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True)\n\nprint('Computing predictions...')\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","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:46:45.778751Z","iopub.execute_input":"2021-12-03T11:46:45.779003Z","iopub.status.idle":"2021-12-03T11:47:07.074215Z","shell.execute_reply.started":"2021-12-03T11:46:45.778972Z","shell.execute_reply":"2021-12-03T11:47:07.073546Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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.\nmodel.load_weights(checkpoint_path)\nprint('Computing predictions...')\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\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='')","metadata":{"execution":{"iopub.status.busy":"2021-12-03T11:47:07.075531Z","iopub.execute_input":"2021-12-03T11:47:07.075946Z","iopub.status.idle":"2021-12-03T11:47:22.501206Z","shell.execute_reply.started":"2021-12-03T11:47:07.075915Z","shell.execute_reply":"2021-12-03T11:47:22.500148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Did it work?\nKaggle provides all users TPU Quota at no cost, which we can use to explore this competition. In this competition, Kaggle provids a starter notebook to try our hand at this problem using the power of Tensor Processing Units (TPUs). Yes, it works because of the TPUs, TPUs are powerful hardware accelerators specialized in deep learning tasks.\n\n#### What did you not understand about this process?\nWell, everything provides in the competition data page. I've no problem while working on it. If you guys don't understand the thing that I'll do in this notebook then please comment on this notebook.\n\n#### What else do you think you can try as part of this approach?\nWell, everything is in its place. If I feel like i need to add something to it then i'll definitely do this.\n\n### PLEASE UPVOTE if you like this notebook. It will keep me motivated to update my notebook. :)","metadata":{}}]}