{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Code #\n\nThe code reproduces the code we covered together in **[the tutorial](https://www.kaggle.com/ryanholbrook/create-your-first-submission)**.  If you commit the notebook by following the instructions above, then the code is run for you.\n\n## Load Helper Functions ##\n\nSlighlty modified petal_helper.py\n(augmentation method)"},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\n# This is the helper script to accompany the notebooks:\n#\n# Tutorial: https://www.kaggle.com/ryanholbrook/create-your-first-submission\n# Exercise: https://www.kaggle.com/ryanholbrook/exercise-create-your-first-submission\n#\n# These are the tutorial and exercise notebooks for the Learn lesson\n# accompanying the Petals to the Metal competition:\n#\n# https://www.kaggle.com/c/tpu-getting-started\n#\n# Many thanks to Martin Görner, the original author of the code in\n# this script and in the notebooks.\n#\n# https://www.kaggle.com/mgornergoogle/getting-started-with-100-flowers-on-tpu\n\n\n# %% [code]\nimport math, re, os\nimport random\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\nprint(\"Tensorflow version \" + tf.__version__)\nAUTO = tf.data.experimental.AUTOTUNE\n\n# Detect TPU, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver() \n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() \n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)\n\n# %% [markdown]\n# # Competition data access\n# \n# In order to train a model on a TPU, we need to store the dataset in Google Cloud Storage (GCS). \n# \n# The code cell below will copy the flowers dataset to a GCS bucket co-located with the TPU.\n\n# %% [code]\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\n\n# %% [markdown]\n# # Configuration\n\n# %% [code]\nIMAGE_SIZE = [192, 192]                   \nEPOCHS = 20\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-192x192'\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') \nCLASSES = ['pink primrose',    'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea',     'wild geranium',     'tiger lily',           'moon orchid',              'bird of paradise', 'monkshood',        'globe thistle',         # 00 - 09\n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily', # 10 - 19\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',         # 20 - 29\n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',           # 30 - 39\n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',      # 40 - 49\n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',    # 50 - 59\n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',            # 60 - 69\n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',             # 70 - 79\n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',            # 80 - 89\n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',        # 90 - 99\n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']                                                                                                                                               # 100 - 102\n\n# %% [markdown]\n# # Helper functions\n# %% [code]\n# 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_flower(image, title, subplot, red=False, titlesize=16):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n    return (subplot[0], subplot[1], subplot[2]+1)\n    \ndef display_batch_of_images(databatch, predictions=None):\n    \"\"\"This will work with:\n    display_batch_of_images(images)\n    display_batch_of_images(images, predictions)\n    display_batch_of_images((images, labels))\n    display_batch_of_images((images, labels), predictions)\n    \"\"\"\n    # data\n    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n        \n    # auto-squaring: this will drop data that does not fit into square or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n        \n    # size and spacing\n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[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\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.'])\n\n# %% [markdown]\n# These helper functions construct a data pipeline from the TFRecords\n\n# %% [code] {\"_kg_hide-input\":true}\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0  # convert image to floats in [0, 1] range\n    image = tf.reshape(image, [*IMAGE_SIZE, 3]) # explicit size needed for TPU\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"class\": tf.io.FixedLenFeature([], tf.int64),  # shape [] means single element\n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    label = tf.cast(example['class'], tf.int32)\n    return image, label # returns a dataset of (image, label) pairs\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"id\": tf.io.FixedLenFeature([], tf.string),  # shape [] means single element\n        # class is missing, this competitions's challenge is to predict flower classes for the test dataset\n    }\n    example = tf.io.parse_single_example(example, UNLABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    idnum = example['id']\n    return image, idnum # returns a dataset of image(s)\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    # Read from TFRecords. For optimal performance, reading from multiple files at once and\n    # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from multiple files\n    dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset\n\ndef data_augment(image, label):\n    mutation_chance = 0.15\n    init_h, init_w, c = image.shape\n    \n    if random.random() < mutation_chance * 3:\n        image = tf.image.flip_left_right(image)\n        \n    if random.random() < mutation_chance * 3:\n        image = tf.image.flip_up_down(image)\n        \n    if random.random() < mutation_chance * 2:\n        image = tf.image.rot90(image, k=random.randint(1,3)) #1, 2 or 3 times roatate 90deg\n        \n    if random.random() < mutation_chance * 2:\n        image = tf.image.central_crop(image, random.randint(7, 9) / 10)     \n        image = tf.image.resize(image, size=[init_h, init_w])\n        \n    if random.random() < mutation_chance:\n        image = tf.image.random_saturation(image, 0, 2)\n        \n    if random.random() < mutation_chance:\n        image = tf.image.random_contrast(image, 0.5, 1.5)   \n        \n    if random.random() < mutation_chance:\n        image = tf.image.random_brightness(image, .3)\n    \n    #if random.random() < mutation_chance:\n    #    f = random.randint(init_w * 0.35)\n    #    image = tf.image.resize_with_crop_or_pad(image, init_h + f, init_w + f)\n    #    image = tf.image.random_crop(image, size=[init_h, init_w, 3])\n        \n    return image, label   \n\ndef get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True, ordered=True)\n    dataset = dataset.repeat() # the training dataset must repeat for several epochs\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\ndef get_validation_dataset(ordered=False):\n    dataset = load_dataset(VALIDATION_FILENAMES, labeled=True, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    dataset = dataset.prefetch(AUTO) # 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\n# %% [markdown]\n\n# %% [code]\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Create Distribution Strategy ##"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Detect TPU, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver() \n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() \n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Loading the Competition Data ##"},{"metadata":{"trusted":true},"cell_type":"code","source":"ds_train = get_training_dataset()\nds_valid = get_validation_dataset()\nds_test = get_test_dataset\n\nprint(\"Training:\", ds_train)\nprint (\"Validation:\", ds_valid)\nprint(\"Test:\", ds_test)\n\n#t1 = get_training_dataset()\n#one_batch = next(iter(t1.unbatch().batch(2)))\n#display_batch_of_images(one_batch)\n\n#t1 = get_training_dataset()\n#one_batch = next(iter(t1.unbatch().batch(2)))\n#display_batch_of_images(one_batch)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Explore the Data ##\n\nTry using some of the helper functions described in the **Getting Started** tutorial to explore the dataset."},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Number of classes: {}\".format(len(CLASSES)))\n\nprint(\"First five classes, sorted alphabetically:\")\nfor name in sorted(CLASSES)[:5]:\n    print(name)\n\nprint (\"Number of training images: {}\".format(NUM_TRAINING_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Examine the shape of the data."},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Training data shapes:\")\nfor image, label in ds_train.take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training data label examples:\", label.numpy())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Test data shapes:\")\nfor image, idnum in ds_test().take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test data IDs:\", idnum.numpy().astype('U')) # U=unicode string","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Peek at training data."},{"metadata":{"trusted":true},"cell_type":"code","source":"one_batch = next(iter(ds_train.unbatch().batch(20)))\ndisplay_batch_of_images(one_batch)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Define Model #"},{"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    \nlr_callback = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose = True)\nes = tf.keras.callbacks.EarlyStopping(monitor='val_loss', mode='min', patience=5, restore_best_weights=True, verbose=1)\ncheckpoint = tf.keras.callbacks.ModelCheckpoint(f'model_{IMAGE_SIZE[0]}.h5', monitor='val_loss', mode='min', save_best_only=True)\n\nwith strategy.scope():\n    pretrained_model = tf.keras.applications.DenseNet201(\n        weights='imagenet',\n        include_top=False ,\n        input_shape=[*IMAGE_SIZE, 3]\n    )\n    pretrained_model.trainable = True\n    \n    model = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n    model.compile(\n        optimizer='adam',\n        loss = 'sparse_categorical_crossentropy',\n        metrics=['sparse_categorical_accuracy'],\n    )\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Train Model ##"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Define the batch size. This will be 16 with TPU off and 128 with TPU on\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\n# Define training epochs for committing/submitting. (TPU on)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    callbacks=[es, checkpoint, lr_callback],\n    steps_per_epoch=STEPS_PER_EPOCH,\n    verbose=1\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Examine training curves."},{"metadata":{"trusted":true},"cell_type":"code","source":"display_training_curves(\n    history.history['loss'],\n    history.history['val_loss'],\n    'loss',\n    211,\n)\ndisplay_training_curves(\n    history.history['sparse_categorical_accuracy'],\n    history.history['val_sparse_categorical_accuracy'],\n    'accuracy',\n    212,\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Validation ##\n\nCreate a confusion matrix."},{"metadata":{"trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Look at examples from the dataset, with true and predicted classes."},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Test Predictions ##\n\nCreate predictions to submit to the competition."},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Generating submission.csv file...')\n\n# Get image ids from test set and convert to integers\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')\n\n# Write the submission file\nnp.savetxt(\n    'submission.csv',\n    np.rec.fromarrays([test_ids, predictions]),\n    fmt=['%s', '%d'],\n    delimiter=',',\n    header='id,label',\n    comments='',\n)\n\n# Look at the first few predictions\n!head submission.csv","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"---\n**[Deep Learning Home Page](https://www.kaggle.com/learn/deep-learning)**\n\n\n\n\n\n*Have questions or comments? Visit the [Learn Discussion forum](https://www.kaggle.com/learn-forum) to chat with other Learners.*"}],"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}