{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"pip install keras","metadata":{"execution":{"iopub.status.busy":"2022-08-27T10:53:31.058385Z","iopub.execute_input":"2022-08-27T10:53:31.058692Z","iopub.status.idle":"2022-08-27T10:53:38.822634Z","shell.execute_reply.started":"2022-08-27T10:53:31.058662Z","shell.execute_reply":"2022-08-27T10:53:38.821892Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import math, re, os\nimport numpy as np\nimport tensorflow as tf\nimport tensorflow.keras\nimport tensorflow.keras.layers as L\nimport pandas as pd\nfrom tensorflow import keras \nprint(\"Tensorflow version \" + tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2022-08-27T11:01:26.775149Z","iopub.execute_input":"2022-08-27T11:01:26.777170Z","iopub.status.idle":"2022-08-27T11:01:26.782713Z","shell.execute_reply.started":"2022-08-27T11:01:26.777104Z","shell.execute_reply":"2022-08-27T11:01:26.781856Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Detect TPU, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver() \n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() \n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"papermill":{"duration":5.235128,"end_time":"2021-07-20T07:36:31.066938","exception":false,"start_time":"2021-07-20T07:36:25.831810","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:01:31.375472Z","iopub.execute_input":"2022-08-27T11:01:31.376032Z","iopub.status.idle":"2022-08-27T11:01:37.078090Z","shell.execute_reply.started":"2022-08-27T11:01:31.375987Z","shell.execute_reply":"2022-08-27T11:01:37.077538Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nprint(GCS_DS_PATH) # what do gcs paths look like?","metadata":{"papermill":{"duration":0.431918,"end_time":"2021-07-20T07:36:31.515638","exception":false,"start_time":"2021-07-20T07:36:31.083720","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:01:40.615332Z","iopub.execute_input":"2022-08-27T11:01:40.615584Z","iopub.status.idle":"2022-08-27T11:01:41.011811Z","shell.execute_reply.started":"2022-08-27T11:01:40.615558Z","shell.execute_reply":"2022-08-27T11:01:41.010983Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nIMAGE_SIZE = [224, 224]\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-224x224'\nAUTO = tf.data.experimental.AUTOTUNE\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') \n\nCLASSES = ['pink primrose',    'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea',     'wild geranium',     'tiger lily',           'moon orchid',              'bird of paradise', 'monkshood',        'globe thistle',         # 00 - 09\n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily', # 10 - 19\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',         # 20 - 29\n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',           # 30 - 39\n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',      # 40 - 49\n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',    # 50 - 59\n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',            # 60 - 69\n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',             # 70 - 79\n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',            # 80 - 89\n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',        # 90 - 99\n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']                                                                                                                                               # 100 - 102\n\n\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0  # convert image to floats in [0, 1] range\n    image = tf.reshape(image, [*IMAGE_SIZE, 3]) # explicit size needed for TPU\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"class\": tf.io.FixedLenFeature([], tf.int64),  # shape [] means single element\n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    label = tf.cast(example['class'], tf.int32)\n    return image, label # returns a dataset of (image, label) pairs\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"id\": tf.io.FixedLenFeature([], tf.string),  # shape [] means single element\n        # class is missing, this competitions's challenge is to predict flower classes for the test dataset\n    }\n    example = tf.io.parse_single_example(example, UNLABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    idnum = example['id']\n    return image, idnum # returns a dataset of image(s)\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    # Read from TFRecords. For optimal performance, reading from multiple files at once and\n    # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from multiple files\n    dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.241512,"end_time":"2021-07-20T07:36:31.774572","exception":false,"start_time":"2021-07-20T07:36:31.533060","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:01:43.844740Z","iopub.execute_input":"2022-08-27T11:01:43.845000Z","iopub.status.idle":"2022-08-27T11:01:44.110454Z","shell.execute_reply.started":"2022-08-27T11:01:43.844974Z","shell.execute_reply":"2022-08-27T11:01:44.109466Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef data_augment(image, label):\n    # Thanks to the dataset.prefetch(AUTO)\n    # statement in the next function (below), this happens essentially\n    # for free on TPU. Data pipeline code is executed on the \"CPU\"\n    # part of the TPU while the TPU itself is computing gradients.\n    image = tf.image.random_flip_left_right(image)\n    #image = tf.image.random_saturation(image, 0, 2)\n    return image, label   \n\ndef get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n    dataset = dataset.repeat() # the training dataset must repeat for several epochs\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\ndef get_validation_dataset(ordered=False):\n    dataset = load_dataset(VALIDATION_FILENAMES, labeled=True, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(TEST_FILENAMES, labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec\n    # files, i.e. flowers00-230.tfrec = 230 data items\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))\n","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.033567,"end_time":"2021-07-20T07:36:31.825037","exception":false,"start_time":"2021-07-20T07:36:31.791470","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:01:50.769059Z","iopub.execute_input":"2022-08-27T11:01:50.769731Z","iopub.status.idle":"2022-08-27T11:01:50.781496Z","shell.execute_reply.started":"2022-08-27T11:01:50.769691Z","shell.execute_reply":"2022-08-27T11:01:50.780861Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define the batch size. This will be 16 with TPU off and 128 (=16*8) with TPU on\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nds_train = get_training_dataset()\nds_valid = get_validation_dataset()\nds_test = get_test_dataset()\n\nprint(\"Training:\", ds_train)\nprint (\"Validation:\", ds_valid)\nprint(\"Test:\", ds_test)","metadata":{"papermill":{"duration":0.347115,"end_time":"2021-07-20T07:36:32.189363","exception":false,"start_time":"2021-07-20T07:36:31.842248","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:01:55.378735Z","iopub.execute_input":"2022-08-27T11:01:55.379260Z","iopub.status.idle":"2022-08-27T11:01:55.669192Z","shell.execute_reply.started":"2022-08-27T11:01:55.379229Z","shell.execute_reply":"2022-08-27T11:01:55.668340Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.set_printoptions(threshold=15, linewidth=80)\n\nprint(\"Training data shapes:\")\nfor image, label in ds_train.take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training data label examples:\", label.numpy())","metadata":{"papermill":{"duration":2.943619,"end_time":"2021-07-20T07:36:35.150992","exception":false,"start_time":"2021-07-20T07:36:32.207373","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:01:59.306165Z","iopub.execute_input":"2022-08-27T11:01:59.306511Z","iopub.status.idle":"2022-08-27T11:02:01.523410Z","shell.execute_reply.started":"2022-08-27T11:01:59.306467Z","shell.execute_reply":"2022-08-27T11:02:01.522525Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Test data shapes:\")\nfor image, idnum in ds_test.take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test data IDs:\", idnum.numpy().astype('U')) # U=unicode string","metadata":{"papermill":{"duration":1.740298,"end_time":"2021-07-20T07:36:36.910171","exception":false,"start_time":"2021-07-20T07:36:35.169873","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:02:03.668059Z","iopub.execute_input":"2022-08-27T11:02:03.669096Z","iopub.status.idle":"2022-08-27T11:02:05.155650Z","shell.execute_reply.started":"2022-08-27T11:02:03.669044Z","shell.execute_reply":"2022-08-27T11:02:05.154270Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCHS = 12\n\nwith strategy.scope():    \n    densenet = tf.keras.applications.DenseNet201(\n        input_shape = (224, 224, 3),\n        weights = 'imagenet',  # Use the preset parameters of ImageNet\n        include_top = False  # Drop the fully connected network on the top\n    )\n    \n    densenet.trainable =True\n    model = tf.keras.Sequential([\n        densenet,\n        #tf.keras.layers.Dropout(0.2),\n        #tf.keras.layers.BatchNormalization(),\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation = 'softmax')\n    ])\n\n    model.compile(\n        optimizer=tf.keras.optimizers.Adam(), loss = 'sparse_categorical_crossentropy', \n        metrics = ['sparse_categorical_accuracy']\n    )","metadata":{"papermill":{"duration":36.152566,"end_time":"2021-07-20T07:37:13.082679","exception":false,"start_time":"2021-07-20T07:36:36.930113","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:02:06.607745Z","iopub.execute_input":"2022-08-27T11:02:06.608039Z","iopub.status.idle":"2022-08-27T11:02:44.485676Z","shell.execute_reply.started":"2022-08-27T11:02:06.608010Z","shell.execute_reply":"2022-08-27T11:02:44.484841Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(\n    optimizer=keras.optimizers.Adam(learning_rate=0.00001),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n)","metadata":{"papermill":{"duration":0.088643,"end_time":"2021-07-20T07:37:13.194201","exception":false,"start_time":"2021-07-20T07:37:13.105558","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:04:45.343369Z","iopub.execute_input":"2022-08-27T11:04:45.343705Z","iopub.status.idle":"2022-08-27T11:04:45.404281Z","shell.execute_reply.started":"2022-08-27T11:04:45.343672Z","shell.execute_reply":"2022-08-27T11:04:45.403560Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"NUM_TRAINING_IMAGES = 12753\nNUM_TEST_IMAGES = 7382\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=30,steps_per_epoch=STEPS_PER_EPOCH\n)","metadata":{"papermill":{"duration":666.36078,"end_time":"2021-07-20T07:48:19.577728","exception":false,"start_time":"2021-07-20T07:37:13.216948","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:04:49.315783Z","iopub.execute_input":"2022-08-27T11:04:49.316071Z","iopub.status.idle":"2022-08-27T11:15:47.666002Z","shell.execute_reply.started":"2022-08-27T11:04:49.316043Z","shell.execute_reply":"2022-08-27T11:15:47.665043Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pd.DataFrame(history.history).plot(figsize=(8,5))","metadata":{"papermill":{"duration":1.197068,"end_time":"2021-07-20T07:48:21.703035","exception":false,"start_time":"2021-07-20T07:48:20.505967","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:15:47.667521Z","iopub.execute_input":"2022-08-27T11:15:47.667742Z","iopub.status.idle":"2022-08-27T11:15:48.001531Z","shell.execute_reply.started":"2022-08-27T11:15:47.667719Z","shell.execute_reply":"2022-08-27T11:15:48.000812Z"},"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)","metadata":{"papermill":{"duration":1.566441,"end_time":"2021-07-20T07:48:24.191290","exception":false,"start_time":"2021-07-20T07:48:22.624849","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:15:48.002741Z","iopub.execute_input":"2022-08-27T11:15:48.003266Z","iopub.status.idle":"2022-08-27T11:15:49.712710Z","shell.execute_reply.started":"2022-08-27T11:15:48.003226Z","shell.execute_reply":"2022-08-27T11:15:49.711823Z"},"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":{"papermill":{"duration":20.224866,"end_time":"2021-07-20T07:48:45.390700","exception":false,"start_time":"2021-07-20T07:48:25.165834","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:15:49.714523Z","iopub.execute_input":"2022-08-27T11:15:49.714728Z","iopub.status.idle":"2022-08-27T11:16:08.264908Z","shell.execute_reply.started":"2022-08-27T11:15:49.714705Z","shell.execute_reply":"2022-08-27T11:16:08.264014Z"},"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":{"papermill":{"duration":5.839563,"end_time":"2021-07-20T07:48:52.157241","exception":false,"start_time":"2021-07-20T07:48:46.317678","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:16:08.266131Z","iopub.execute_input":"2022-08-27T11:16:08.266369Z","iopub.status.idle":"2022-08-27T11:16:13.128772Z","shell.execute_reply.started":"2022-08-27T11:16:08.266342Z","shell.execute_reply":"2022-08-27T11:16:13.128282Z"},"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)","metadata":{"papermill":{"duration":15.768806,"end_time":"2021-07-20T07:49:08.862652","exception":false,"start_time":"2021-07-20T07:48:53.093846","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:16:13.129749Z","iopub.execute_input":"2022-08-27T11:16:13.130201Z","iopub.status.idle":"2022-08-27T11:16:27.789269Z","shell.execute_reply.started":"2022-08-27T11:16:13.130171Z","shell.execute_reply":"2022-08-27T11:16:27.788338Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('Generating submission.csv file...')\n\n# Get image ids from test set and convert to unicode\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","metadata":{"papermill":{"duration":2.577094,"end_time":"2021-07-20T07:49:12.374642","exception":false,"start_time":"2021-07-20T07:49:09.797548","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-08-27T11:16:27.790645Z","iopub.execute_input":"2022-08-27T11:16:27.790909Z","iopub.status.idle":"2022-08-27T11:16:29.697011Z","shell.execute_reply.started":"2022-08-27T11:16:27.790881Z","shell.execute_reply":"2022-08-27T11:16:29.695719Z"},"trusted":true},"execution_count":null,"outputs":[]}]}