{"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":"# 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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-10-30T13:06:21.766885Z","iopub.execute_input":"2022-10-30T13:06:21.767378Z","iopub.status.idle":"2022-10-30T13:06:21.894092Z","shell.execute_reply.started":"2022-10-30T13:06:21.767266Z","shell.execute_reply":"2022-10-30T13:06:21.893054Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings(action='ignore')","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:21.895434Z","iopub.execute_input":"2022-10-30T13:06:21.895651Z","iopub.status.idle":"2022-10-30T13:06:21.898730Z","shell.execute_reply.started":"2022-10-30T13:06:21.895626Z","shell.execute_reply":"2022-10-30T13:06:21.898206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import math, re, os\nimport numpy as np\nimport tensorflow as tf\n\nprint(\"Tensorflow version \" + tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:21.899598Z","iopub.execute_input":"2022-10-30T13:06:21.899763Z","iopub.status.idle":"2022-10-30T13:06:27.781369Z","shell.execute_reply.started":"2022-10-30T13:06:21.899742Z","shell.execute_reply":"2022-10-30T13:06:27.780052Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"try:\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":{"execution":{"iopub.status.busy":"2022-10-30T13:06:27.784012Z","iopub.execute_input":"2022-10-30T13:06:27.784297Z","iopub.status.idle":"2022-10-30T13:06:33.539620Z","shell.execute_reply.started":"2022-10-30T13:06:27.784272Z","shell.execute_reply":"2022-10-30T13:06:33.538690Z"},"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)","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:33.540687Z","iopub.execute_input":"2022-10-30T13:06:33.540878Z","iopub.status.idle":"2022-10-30T13:06:33.919963Z","shell.execute_reply.started":"2022-10-30T13:06:33.540855Z","shell.execute_reply":"2022-10-30T13:06:33.919071Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [512, 512]\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-512x512'\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',        \n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily',\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',        \n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',          \n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',     \n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',   \n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',           \n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',            \n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',           \n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',       \n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']\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\n    image = tf.reshape(image, [*IMAGE_SIZE, 3])\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string),\n        \"class\": tf.io.FixedLenFeature([], tf.int64),\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\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string),\n        \"id\": tf.io.FixedLenFeature([], tf.string),\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\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False\n        \n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO)\n    dataset = dataset.with_options(ignore_order)\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord,\n                         num_parallel_calls=AUTO)\n    return dataset","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:33.920995Z","iopub.execute_input":"2022-10-30T13:06:33.921197Z","iopub.status.idle":"2022-10-30T13:06:34.060569Z","shell.execute_reply.started":"2022-10-30T13:06:33.921171Z","shell.execute_reply":"2022-10-30T13:06:34.059697Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def data_augment(image, label):\n    image = tf.image.random_flip_left_right(image)\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()\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(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    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)\n\nprint(\"Dataset: {} training images, {} validation images, {} unlabeled test images\"\n     .format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:34.061676Z","iopub.execute_input":"2022-10-30T13:06:34.062010Z","iopub.status.idle":"2022-10-30T13:06:34.074026Z","shell.execute_reply.started":"2022-10-30T13:06:34.061983Z","shell.execute_reply":"2022-10-30T13:06:34.073327Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"BATCH_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":{"execution":{"iopub.status.busy":"2022-10-30T13:06:34.075186Z","iopub.execute_input":"2022-10-30T13:06:34.075976Z","iopub.status.idle":"2022-10-30T13:06:34.363361Z","shell.execute_reply.started":"2022-10-30T13:06:34.075939Z","shell.execute_reply":"2022-10-30T13:06:34.362337Z"},"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":{"execution":{"iopub.status.busy":"2022-10-30T13:06:34.364882Z","iopub.execute_input":"2022-10-30T13:06:34.365177Z","iopub.status.idle":"2022-10-30T13:06:38.581357Z","shell.execute_reply.started":"2022-10-30T13:06:34.365133Z","shell.execute_reply":"2022-10-30T13:06:38.580263Z"},"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\"))","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:38.583899Z","iopub.execute_input":"2022-10-30T13:06:38.584144Z","iopub.status.idle":"2022-10-30T13:06:41.081439Z","shell.execute_reply.started":"2022-10-30T13:06:38.584114Z","shell.execute_reply":"2022-10-30T13:06:41.080356Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from matplotlib import pyplot as plt\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:\n        numpy_labels = [None for _ in enumerate(numpy_images)]\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),\n                 color='red' if red else 'black', fontdict={'verticalalignment': 'center'},\n                 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    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n           \n    rows = int(math.sqrt(len(images)))\n    cols = len(images) // rows\n    \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    for i, (image, label) in enumerate(zip(images[:rows*cols], \n                                          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\n        subplot = display_one_flower(image, title, subplot, not correct,\n                                    titlesize=dynamic_titlesize)\n        \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_training_curves(training, validation, title, subplot):\n    if subplot % 10 == 1:\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_xlabel(\"epoch\")\n    ax.legend(['train', 'valid.'])","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:41.083303Z","iopub.execute_input":"2022-10-30T13:06:41.083502Z","iopub.status.idle":"2022-10-30T13:06:41.098416Z","shell.execute_reply.started":"2022-10-30T13:06:41.083478Z","shell.execute_reply":"2022-10-30T13:06:41.097931Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(20))","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:41.099407Z","iopub.execute_input":"2022-10-30T13:06:41.099603Z","iopub.status.idle":"2022-10-30T13:06:41.132524Z","shell.execute_reply.started":"2022-10-30T13:06:41.099564Z","shell.execute_reply":"2022-10-30T13:06:41.131447Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:41.133808Z","iopub.execute_input":"2022-10-30T13:06:41.134156Z","iopub.status.idle":"2022-10-30T13:06:44.356850Z","shell.execute_reply.started":"2022-10-30T13:06:41.134127Z","shell.execute_reply":"2022-10-30T13:06:44.355846Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCHS = 12\n\nwith strategy.scope():\n    pretrained_model = tf.keras.applications.VGG16(\n        weights='imagenet',\n        include_top=False,\n        input_shape=[*IMAGE_SIZE, 3]\n    )\n    pretrained_model.trainable=False\n    \n    model = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:44.357974Z","iopub.execute_input":"2022-10-30T13:06:44.358224Z","iopub.status.idle":"2022-10-30T13:06:46.757459Z","shell.execute_reply.started":"2022-10-30T13:06:44.358191Z","shell.execute_reply":"2022-10-30T13:06:46.756885Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(\n    optimizer='adam',\n    loss='sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n)\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:46.758487Z","iopub.execute_input":"2022-10-30T13:06:46.758840Z","iopub.status.idle":"2022-10-30T13:06:46.798701Z","shell.execute_reply.started":"2022-10-30T13:06:46.758808Z","shell.execute_reply":"2022-10-30T13:06:46.797881Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def exponential_lr(epoch,\n                  start_lr=0.00001, min_lr=0.00001, max_lr=0.00005,\n                  rampup_epochs=5, sustain_epochs=0,\n                  exp_decay=0.8):\n    def lr(epoch, start_lr, min_lr, max_lr, rampup_epochs, sustain_epochs, exp_decay):\n        if epoch < rampup_epochs:\n            lr = ((max_lr - start_lr) /\n                 rampup_epochs * epoch + start_lr)\n        elif epoch < rampup_epochs + sustain_epochs:\n            lr = max_lr\n        else :\n            lr = ((max_lr - min_lr) *\n                 exp_decay ** (epoch - rampup_epochs - sustain_epochs) +\n                  min_lr)\n        return lr\n    return lr(epoch, start_lr, min_lr, max_lr, rampup_epochs, sustain_epochs, exp_decay)\n\nlr_callback = tf.keras.callbacks.LearningRateScheduler(exponential_lr, verbose=True)\n\nrng = [i for i in range(EPOCHS)]\ny = [exponential_lr(x) for x in rng]\nplt.plot(rng, y)\n\nprint(\"Learning rate schedule: {:.3g} to {:.3g} to {:.3g}\".format(y[0],\n                                                                 max(y), y[-1]))","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:46.799844Z","iopub.execute_input":"2022-10-30T13:06:46.800042Z","iopub.status.idle":"2022-10-30T13:06:46.960434Z","shell.execute_reply.started":"2022-10-30T13:06:46.800018Z","shell.execute_reply":"2022-10-30T13:06:46.959670Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCHS = 420\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    steps_per_epoch=STEPS_PER_EPOCH,\n    callbacks=[lr_callback],\n)","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:06:46.961554Z","iopub.execute_input":"2022-10-30T13:06:46.961836Z","iopub.status.idle":"2022-10-30T13:07:30.453521Z","shell.execute_reply.started":"2022-10-30T13:06:46.961795Z","shell.execute_reply":"2022-10-30T13:07:30.451817Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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)","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:07:30.455314Z","iopub.execute_input":"2022-10-30T13:07:30.455556Z","iopub.status.idle":"2022-10-30T13:07:30.817411Z","shell.execute_reply.started":"2022-10-30T13:07:30.455527Z","shell.execute_reply":"2022-10-30T13:07:30.816891Z"},"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, precions, 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',\n                                              'verticalalignment':'top', 'color':'#804040'})\n    plt.show()\n    \ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1:\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_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:07:30.818273Z","iopub.execute_input":"2022-10-30T13:07:30.818616Z","iopub.status.idle":"2022-10-30T13:07:31.546431Z","shell.execute_reply.started":"2022-10-30T13:07:30.818573Z","shell.execute_reply":"2022-10-30T13:07:31.545119Z"},"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","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:08:10.661454Z","iopub.execute_input":"2022-10-30T13:08:10.662201Z","iopub.status.idle":"2022-10-30T13:08:23.086608Z","shell.execute_reply.started":"2022-10-30T13:08:10.662161Z","shell.execute_reply":"2022-10-30T13:08:23.084935Z"},"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)\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)\n\ndisplay_confusion_matrix(cmat, score, precision, recall)","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:08:23.088170Z","iopub.execute_input":"2022-10-30T13:08:23.088395Z","iopub.status.idle":"2022-10-30T13:08:26.648727Z","shell.execute_reply.started":"2022-10-30T13:08:23.088366Z","shell.execute_reply":"2022-10-30T13:08:26.647452Z"},"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":"2022-10-30T13:08:26.650080Z","iopub.execute_input":"2022-10-30T13:08:26.650355Z","iopub.status.idle":"2022-10-30T13:08:26.689565Z","shell.execute_reply.started":"2022-10-30T13:08:26.650322Z","shell.execute_reply":"2022-10-30T13:08:26.688531Z"},"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)","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:08:26.692901Z","iopub.execute_input":"2022-10-30T13:08:26.693171Z","iopub.status.idle":"2022-10-30T13:08:40.089348Z","shell.execute_reply.started":"2022-10-30T13:08:26.693140Z","shell.execute_reply":"2022-10-30T13:08:40.088710Z"},"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":{"execution":{"iopub.status.busy":"2022-10-30T13:08:40.090535Z","iopub.execute_input":"2022-10-30T13:08:40.090880Z","iopub.status.idle":"2022-10-30T13:08:54.311262Z","shell.execute_reply.started":"2022-10-30T13:08:40.090847Z","shell.execute_reply":"2022-10-30T13:08:54.310355Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Generating submission.csv file...\")\n\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\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!head submission.csv","metadata":{"execution":{"iopub.status.busy":"2022-10-30T13:08:54.312882Z","iopub.execute_input":"2022-10-30T13:08:54.313327Z","iopub.status.idle":"2022-10-30T13:08:56.535567Z","shell.execute_reply.started":"2022-10-30T13:08:54.313283Z","shell.execute_reply":"2022-10-30T13:08:56.533981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}