{"cells":[{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:45:23.274004Z","iopub.status.busy":"2020-11-19T21:45:23.273154Z","iopub.status.idle":"2020-11-19T21:45:30.119096Z","shell.execute_reply":"2020-11-19T21:45:30.119725Z"},"papermill":{"duration":6.890298,"end_time":"2020-11-19T21:45:30.119979","exception":false,"start_time":"2020-11-19T21:45:23.229681","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"import math, re, os\nimport tensorflow as tf\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nfrom tensorflow import keras\nfrom functools import partial\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, LearningRateScheduler\nimport seaborn as sns\n\nfrom tensorflow.keras.applications import ResNet50, InceptionV3, DenseNet201, InceptionResNetV2, Xception, NASNetLarge, ResNet152V2\nprint(\"Tensorflow version \" + tf.__version__)","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:45:30.373218Z","iopub.status.busy":"2020-11-19T21:45:30.372403Z","iopub.status.idle":"2020-11-19T21:45:34.382672Z","shell.execute_reply":"2020-11-19T21:45:34.382035Z"},"papermill":{"duration":4.150374,"end_time":"2020-11-19T21:45:34.382816","exception":false,"start_time":"2020-11-19T21:45:30.232442","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"try:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print('Device:', tpu.master())\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nexcept:\n    strategy = tf.distribute.get_strategy()\nprint('Number of replicas:', strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:45:34.555293Z","iopub.status.busy":"2020-11-19T21:45:34.541822Z","iopub.status.idle":"2020-11-19T21:47:59.71579Z","shell.execute_reply":"2020-11-19T21:47:59.714961Z"},"papermill":{"duration":145.219568,"end_time":"2020-11-19T21:47:59.715925","exception":false,"start_time":"2020-11-19T21:45:34.496357","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"AUTOTUNE = tf.data.experimental.AUTOTUNE\nGCS_PATH = KaggleDatasets().get_gcs_path()\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\nIMAGE_SIZE = [512, 512]\nCLASSES = ['0', '1', '2', '3', '4']\nEPOCHS = 40\nLEARNING_RATE = 3e-5 * strategy.num_replicas_in_sync","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:47:59.952622Z","iopub.status.busy":"2020-11-19T21:47:59.951868Z","iopub.status.idle":"2020-11-19T21:47:59.954997Z","shell.execute_reply":"2020-11-19T21:47:59.955558Z"},"papermill":{"duration":0.04859,"end_time":"2020-11-19T21:47:59.955731","exception":false,"start_time":"2020-11-19T21:47:59.907141","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"def decode_image(image):\n    image = tf.image.decode_jpeg(image, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0\n    image = tf.reshape(image, [*IMAGE_SIZE, 3])\n    return image","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:00.123967Z","iopub.status.busy":"2020-11-19T21:48:00.123143Z","iopub.status.idle":"2020-11-19T21:48:00.126902Z","shell.execute_reply":"2020-11-19T21:48:00.126284Z"},"papermill":{"duration":0.052475,"end_time":"2020-11-19T21:48:00.127039","exception":false,"start_time":"2020-11-19T21:48:00.074564","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"def read_tfrecord(example, labeled):\n    tfrecord_format = {\n        \"image\": tf.io.FixedLenFeature([], tf.string),\n        \"target\": tf.io.FixedLenFeature([], tf.int64)\n    } if labeled else {\n        \"image\": tf.io.FixedLenFeature([], tf.string),\n        \"image_name\": tf.io.FixedLenFeature([], tf.string)\n    }\n    example = tf.io.parse_single_example(example, tfrecord_format)\n    image = decode_image(example['image'])\n    if labeled:\n        label = tf.cast(example['target'], tf.int32)\n        return image, label\n    idnum = example['image_name']\n    return image, idnum","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:00.325942Z","iopub.status.busy":"2020-11-19T21:48:00.324875Z","iopub.status.idle":"2020-11-19T21:48:00.327502Z","shell.execute_reply":"2020-11-19T21:48:00.328493Z"},"papermill":{"duration":0.073623,"end_time":"2020-11-19T21:48:00.328703","exception":false,"start_time":"2020-11-19T21:48:00.25508","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"def load_dataset(filenames, labeled=True, ordered=False):\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTOTUNE) # 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(partial(read_tfrecord, labeled=labeled), num_parallel_calls=AUTOTUNE)\n    return dataset","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:00.683596Z","iopub.status.busy":"2020-11-19T21:48:00.607588Z","iopub.status.idle":"2020-11-19T21:48:00.687244Z","shell.execute_reply":"2020-11-19T21:48:00.686445Z"},"papermill":{"duration":0.225941,"end_time":"2020-11-19T21:48:00.687385","exception":false,"start_time":"2020-11-19T21:48:00.461444","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"TRAINING_FILENAMES, VALID_FILENAMES = train_test_split(\n    tf.io.gfile.glob(GCS_PATH + '/train_tfrecords/ld_train*.tfrec'),\n    test_size=0.35, random_state=5\n)\n\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test_tfrecords/ld_test*.tfrec')","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:00.849827Z","iopub.status.busy":"2020-11-19T21:48:00.848867Z","iopub.status.idle":"2020-11-19T21:48:00.85179Z","shell.execute_reply":"2020-11-19T21:48:00.85115Z"},"papermill":{"duration":0.047715,"end_time":"2020-11-19T21:48:00.851918","exception":false,"start_time":"2020-11-19T21:48:00.804203","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"def data_augment(image, label):\n    # Thanks to the dataset.prefetch(AUTO) statement in the following function this happens essentially for free on TPU. \n    # Data pipeline code is executed on the \"CPU\" 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_flip_up_down(image)\n    return image, label","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:01.018921Z","iopub.status.busy":"2020-11-19T21:48:01.017912Z","iopub.status.idle":"2020-11-19T21:48:01.02164Z","shell.execute_reply":"2020-11-19T21:48:01.020852Z"},"papermill":{"duration":0.052326,"end_time":"2020-11-19T21:48:01.021791","exception":false,"start_time":"2020-11-19T21:48:00.969465","status":"completed"},"tags":[],"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=AUTOTUNE)  \n    dataset = dataset.repeat()\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTOTUNE)\n    return dataset","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:01.109616Z","iopub.status.busy":"2020-11-19T21:48:01.108559Z","iopub.status.idle":"2020-11-19T21:48:01.111418Z","shell.execute_reply":"2020-11-19T21:48:01.111986Z"},"papermill":{"duration":0.049787,"end_time":"2020-11-19T21:48:01.112145","exception":false,"start_time":"2020-11-19T21:48:01.062358","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"def get_validation_dataset(ordered=False):\n    dataset = load_dataset(VALID_FILENAMES, labeled=True, ordered=ordered) \n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    dataset = dataset.prefetch(AUTOTUNE)\n    return dataset","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:01.204402Z","iopub.status.busy":"2020-11-19T21:48:01.203418Z","iopub.status.idle":"2020-11-19T21:48:01.207545Z","shell.execute_reply":"2020-11-19T21:48:01.20682Z"},"papermill":{"duration":0.050395,"end_time":"2020-11-19T21:48:01.207665","exception":false,"start_time":"2020-11-19T21:48:01.15727","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"def 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(AUTOTUNE)\n    return dataset","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:01.301631Z","iopub.status.busy":"2020-11-19T21:48:01.30084Z","iopub.status.idle":"2020-11-19T21:48:01.304479Z","shell.execute_reply":"2020-11-19T21:48:01.303807Z"},"papermill":{"duration":0.05422,"end_time":"2020-11-19T21:48:01.304611","exception":false,"start_time":"2020-11-19T21:48:01.250391","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"def count_data_items(filenames):\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:01.39253Z","iopub.status.busy":"2020-11-19T21:48:01.391743Z","iopub.status.idle":"2020-11-19T21:48:01.395039Z","shell.execute_reply":"2020-11-19T21:48:01.395972Z"},"papermill":{"duration":0.051209,"end_time":"2020-11-19T21:48:01.396198","exception":false,"start_time":"2020-11-19T21:48:01.344989","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"NUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALID_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\n\nprint('Dataset: {} training images, {} validation images, {} (unlabeled) test images'.format(\n    NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:18.782198Z","iopub.status.busy":"2020-11-19T21:48:18.781353Z","iopub.status.idle":"2020-11-19T21:48:18.808005Z","shell.execute_reply":"2020-11-19T21:48:18.807301Z"},"papermill":{"duration":0.077342,"end_time":"2020-11-19T21:48:18.808133","exception":false,"start_time":"2020-11-19T21:48:18.730791","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# numpy and matplotlib defaults\nnp.set_printoptions(threshold=15, linewidth=80)\n\ndef batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    if numpy_labels.dtype == object: # binary string in this case, these are image ID strings\n        numpy_labels = [None for _ in enumerate(numpy_images)]\n    # If no labels, only image IDs, return None for labels (this is the case for test data)\n    return numpy_images, numpy_labels\n\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_plant(image, title, subplot, red=False, titlesize=16):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n    return (subplot[0], subplot[1], subplot[2]+1)\n\ndef display_batch_of_images(databatch, predictions=None):\n    \"\"\"This will work with:\n    display_batch_of_images(images)\n    display_batch_of_images(images, predictions)\n    display_batch_of_images((images, labels))\n    display_batch_of_images((images, labels), predictions)\n    \"\"\"\n    # data\n    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n        \n    # auto-squaring: this will drop data that does not fit into square or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n        \n    # size and spacing\n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[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_plant(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":{"execution":{"iopub.execute_input":"2020-11-19T21:48:18.904519Z","iopub.status.busy":"2020-11-19T21:48:18.903424Z","iopub.status.idle":"2020-11-19T21:48:18.956871Z","shell.execute_reply":"2020-11-19T21:48:18.956219Z"},"papermill":{"duration":0.104176,"end_time":"2020-11-19T21:48:18.957003","exception":false,"start_time":"2020-11-19T21:48:18.852827","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# load our training dataset for EDA\ntraining_dataset = get_training_dataset()\ntraining_dataset = training_dataset.unbatch().batch(20)\ntrain_batch = iter(training_dataset)","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:20.176923Z","iopub.status.busy":"2020-11-19T21:48:20.175758Z","iopub.status.idle":"2020-11-19T21:48:22.374002Z","shell.execute_reply":"2020-11-19T21:48:22.374605Z"},"papermill":{"duration":3.371477,"end_time":"2020-11-19T21:48:22.374778","exception":false,"start_time":"2020-11-19T21:48:19.003301","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# run this cell again for another randomized set of training images\ndisplay_batch_of_images(next(train_batch))","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:22.732786Z","iopub.status.busy":"2020-11-19T21:48:22.731592Z","iopub.status.idle":"2020-11-19T21:48:22.769732Z","shell.execute_reply":"2020-11-19T21:48:22.768929Z"},"papermill":{"duration":0.136485,"end_time":"2020-11-19T21:48:22.769878","exception":false,"start_time":"2020-11-19T21:48:22.633393","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# load our validation dataset for EDA\nvalidation_dataset = get_validation_dataset()\nvalidation_dataset = validation_dataset.unbatch().batch(20)\nvalid_batch = iter(validation_dataset)","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:22.946423Z","iopub.status.busy":"2020-11-19T21:48:22.945571Z","iopub.status.idle":"2020-11-19T21:48:26.010139Z","shell.execute_reply":"2020-11-19T21:48:26.010819Z"},"papermill":{"duration":3.155802,"end_time":"2020-11-19T21:48:26.010993","exception":false,"start_time":"2020-11-19T21:48:22.855191","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# run this cell again for another randomized set of training images\ndisplay_batch_of_images(next(valid_batch))","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:26.368142Z","iopub.status.busy":"2020-11-19T21:48:26.367301Z","iopub.status.idle":"2020-11-19T21:48:26.410393Z","shell.execute_reply":"2020-11-19T21:48:26.411021Z"},"papermill":{"duration":0.232531,"end_time":"2020-11-19T21:48:26.411209","exception":false,"start_time":"2020-11-19T21:48:26.178678","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# load our test dataset for EDA\ntesting_dataset = get_test_dataset()\ntesting_dataset = testing_dataset.unbatch().batch(20)\ntest_batch = iter(testing_dataset)","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:26.744678Z","iopub.status.busy":"2020-11-19T21:48:26.743913Z","iopub.status.idle":"2020-11-19T21:48:27.89988Z","shell.execute_reply":"2020-11-19T21:48:27.900494Z"},"papermill":{"duration":1.333241,"end_time":"2020-11-19T21:48:27.900651","exception":false,"start_time":"2020-11-19T21:48:26.56741","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# we only have one test image\ndisplay_batch_of_images(next(test_batch))","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T21:48:28.8307Z","iopub.status.busy":"2020-11-19T21:48:28.829632Z","iopub.status.idle":"2020-11-19T21:48:28.833152Z","shell.execute_reply":"2020-11-19T21:48:28.832481Z"},"papermill":{"duration":0.248904,"end_time":"2020-11-19T21:48:28.83328","exception":false,"start_time":"2020-11-19T21:48:28.584376","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"LR_START = 1e-8\nLR_MIN = 1e-8\nLR_MAX = LEARNING_RATE\nLR_RAMPUP_EPOCHS = 3\nLR_SUSTAIN_EPOCHS = 0\nN_CYCLES = .5\n\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        progress = (epoch - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS) / (EPOCHS - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS)\n        lr = LR_MAX * (0.5 * (1.0 + tf.math.cos(math.pi * N_CYCLES * 2.0 * progress)))\n        if LR_MIN is not None:\n            lr = tf.math.maximum(LR_MIN, lr)\n            \n    return lr\n\nrng = [i for i in range(EPOCHS)]\ny = [lrfn(x) for x in rng]\n\nsns.set(style='whitegrid')\nfig, ax = plt.subplots(figsize=(20, 6))\nplt.plot(rng, y)\n\nprint(f'{EPOCHS} total epochs and {NUM_TRAINING_IMAGES//BATCH_SIZE} steps per epoch')\nprint(f'Learning rate schedule: {y[0]:.3g} to {max(y):.3g} to {y[-1]:.3g}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"STEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALID_STEPS = NUM_VALIDATION_IMAGES // BATCH_SIZE","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def train_model(model_cls, filename):\n    with strategy.scope():           \n        base_model = model_cls(weights='imagenet', \n                          include_top=False, \n                          input_shape=[*IMAGE_SIZE, 3])\n        base_model.trainable = True\n\n        model = tf.keras.Sequential([\n            tf.keras.layers.BatchNormalization(renorm=True),\n            base_model,\n            tf.keras.layers.GlobalAveragePooling2D(),\n            tf.keras.layers.Dense(8, activation='softmax'),\n            tf.keras.layers.Dropout(0.3),\n            tf.keras.layers.Dense(len(CLASSES), activation='softmax')  \n        ])\n\n        model.compile(\n            optimizer=tf.keras.optimizers.Adam(lr=LEARNING_RATE),\n            loss='sparse_categorical_crossentropy',  \n            metrics=['sparse_categorical_accuracy']\n        )\n    \n    train_dataset = get_training_dataset()\n    valid_dataset = get_validation_dataset()\n    \n    model_checkpoint_callback = keras.callbacks.ModelCheckpoint(\n        filepath=filename,\n        monitor='sparse_categorical_accuracy',\n        save_best_only=True\n    )\n    \n\n    history = model.fit(\n        train_dataset, \n        steps_per_epoch=STEPS_PER_EPOCH, \n        epochs=EPOCHS,\n        callbacks=[model_checkpoint_callback, LearningRateScheduler(lrfn, verbose=0)],\n        validation_data=valid_dataset,\n        validation_steps=VALID_STEPS\n    )\n    \n    history_frame = pd.DataFrame(history.history)\n    history_frame.loc[:, ['loss', 'val_loss']].plot()\n    history_frame.loc[:, ['sparse_categorical_accuracy', 'val_sparse_categorical_accuracy']].plot();\n    return model\n    ","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":0.22538,"end_time":"2020-11-19T21:48:29.285377","exception":false,"start_time":"2020-11-19T21:48:29.059997","status":"completed"},"tags":[]},"cell_type":"markdown","source":"## DenseNet201"},{"metadata":{"trusted":true},"cell_type":"code","source":"densenet201_trained = train_model(DenseNet201, 'densenet201.h5')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## InceptionV3"},{"metadata":{"trusted":true},"cell_type":"code","source":"inception_trained = train_model(InceptionV3, 'inceptionv3.h5')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## EfficientNetB3"},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -U --pre efficientnet","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import efficientnet.keras as efn\nefficient_net_b3_trained = train_model(efn.EfficientNetB3, 'efficient_netb3.h5')","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T22:05:05.184942Z","iopub.status.busy":"2020-11-19T22:05:05.183725Z","iopub.status.idle":"2020-11-19T22:05:05.18757Z","shell.execute_reply":"2020-11-19T22:05:05.186823Z"},"papermill":{"duration":1.270192,"end_time":"2020-11-19T22:05:05.187694","exception":false,"start_time":"2020-11-19T22:05:03.917502","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# this code will convert our test image data to a float32 \ndef to_float32(image, label):\n    return tf.cast(image, tf.float32), label","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T22:05:07.746039Z","iopub.status.busy":"2020-11-19T22:05:07.744935Z","iopub.status.idle":"2020-11-19T22:05:22.234912Z","shell.execute_reply":"2020-11-19T22:05:22.235492Z"},"papermill":{"duration":15.776858,"end_time":"2020-11-19T22:05:22.235661","exception":false,"start_time":"2020-11-19T22:05:06.458803","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"def get_ds_for_predict():\n    test_ds = get_test_dataset(ordered=True) \n    test_ds = test_ds.map(to_float32)\n\n    print('Computing predictions...')\n    test_images_ds = testing_dataset\n    test_images_ds = test_ds.map(lambda image, idnum: image)\n    return test_images_ds\n\ndef vote_in_ensemble(v1, v2, v3):\n    if v1 == v2:\n        return v1\n    if v2 == v3:\n        return v2\n    if v1 == v3:\n        return v3\n    return v1\n\n\nprobabilities_dense = densenet201_trained.predict(get_ds_for_predict())\nprobabilities_inception = inception_trained.predict(get_ds_for_predict())\nprobabilities_efficient_net_b3 = efficient_net_b3_trained.predict(get_ds_for_predict())\npredictions_dense = np.argmax(probabilities_dense, axis=-1)\npredictions_inception = np.argmax(probabilities_inception, axis=-1)\npredictions_efficient = np.argmax(probabilities_efficient_net_b3, axis=-1)\nresult = []\nprint(predictions_dense)\nprint(predictions_inception)\nprint(predictions_efficient)\n\nfor idx, val in enumerate(predictions_dense):\n    result.append(\n        vote_in_ensemble(\n            predictions_dense[idx],\n            predictions_inception[idx],\n            predictions_efficient[idx]\n        )\n    )\nprint(result)","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":1.271799,"end_time":"2020-11-19T22:05:24.759257","exception":false,"start_time":"2020-11-19T22:05:23.487458","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# Creating a submission file\nNow that we've trained a model and made predictions we're ready to submit to the competition! You can run the following code below to get your submission file."},{"metadata":{"execution":{"iopub.execute_input":"2020-11-19T22:05:27.316025Z","iopub.status.busy":"2020-11-19T22:05:27.315202Z","iopub.status.idle":"2020-11-19T22:05:28.241598Z","shell.execute_reply":"2020-11-19T22:05:28.24078Z"},"papermill":{"duration":2.185537,"end_time":"2020-11-19T22:05:28.241723","exception":false,"start_time":"2020-11-19T22:05:26.056186","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"print('Generating submission.csv file...')\ntest_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()\ntest_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U') # all in one batch\nnp.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')\n!head submission.csv","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":1.255302,"end_time":"2020-11-19T22:05:30.746339","exception":false,"start_time":"2020-11-19T22:05:29.491037","status":"completed"},"tags":[]},"cell_type":"markdown","source":"Be aware that because this is a code competition with a hidden test set, internet and TPUs cannot be enabled on your submission notebook. Therefore TPUs will only be available for training models. For a walk-through on how to train on TPUs and run inference/submit on GPUs, see our [TPU Docs](https://www.kaggle.com/docs/tpu#tpu6)."}],"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}