{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Petals to the Metal - Flower Classification on TPU\n## Getting Started with TPUs on Kaggle!\n\nhttps://www.kaggle.com/competitions/tpu-getting-started\n\n### The Challenge:\nIt’s difficult to fathom just how vast and diverse our natural world is.\n\nThere are over 5,000 species of mammals, 10,000 species of birds, 30,000 species of fish – and astonishingly, over 400,000 different types of flowers.\n\nIn this competition, you’re challenged to build a machine learning model that identifies the type of flowers in a dataset of images (for simplicity, we’re sticking to just over 100 types).\n\n### Ressources:\n- https://www.kaggle.com/code/ryanholbrook/create-your-first-submission/notebook\n- https://learndatasci.com/tutorials/hands-on-transfer-learning-keras/\n- https://www.tensorflow.org/tutorials/images/transfer_learning\n- https://www.pythonfixing.com/2022/01/fixed-simple-cut-out-augmentation-using.html\n\n### Data:\n- https://www.kaggle.com/competitions/tpu-getting-started/data\n- https://www.kaggle.com/datasets/kirillblinov/tf-flower-photo-tfrec","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"## Imports","metadata":{}},{"cell_type":"code","source":"import math, re, os\nimport numpy as np\nimport tensorflow as tf\nimport tensorflow_addons as tfa\nfrom kaggle_datasets import KaggleDatasets\nfrom matplotlib import pyplot as plt\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:09.682228Z","iopub.execute_input":"2022-06-29T19:02:09.682897Z","iopub.status.idle":"2022-06-29T19:02:17.685510Z","shell.execute_reply.started":"2022-06-29T19:02:09.682799Z","shell.execute_reply":"2022-06-29T19:02:17.684785Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Constants","metadata":{}},{"cell_type":"code","source":"AUTOTUNE = tf.data.experimental.AUTOTUNE\n\nSIZE = 512\n\nGCS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nGCS_PATH_EXT = KaggleDatasets().get_gcs_path('tf-flower-photo-tfrec')\nIMAGE_PATH = GCS_PATH + '/tfrecords-jpeg-{size}x{size}'.format(size=SIZE)\n\nIMAGENET_FILES = tf.io.gfile.glob(GCS_PATH_EXT + '/imagenet_no_test/tfrecords-jpeg-{size}x{size}/*.tfrec'.format(size=SIZE))\nINATURELIST_FILES = tf.io.gfile.glob(GCS_PATH_EXT + '/inaturalist_no_test/tfrecords-jpeg-{size}x{size}/*.tfrec'.format(size=SIZE))\nOPENIMAGE_FILES = tf.io.gfile.glob(GCS_PATH_EXT + '/openimage_no_test/tfrecords-jpeg-{size}x{size}/*.tfrec'.format(size=SIZE))\nOXFORD_FILES = tf.io.gfile.glob(GCS_PATH_EXT + '/oxford_102_no_test/tfrecords-jpeg-{size}x{size}/*.tfrec'.format(size=SIZE))\nTENSORFLOW_FILES = tf.io.gfile.glob(GCS_PATH_EXT + '/tf_flowers_no_test/tfrecords-jpeg-{size}x{size}/*.tfrec'.format(size=SIZE))\n\nTRAINING_FILENAMES = tf.io.gfile.glob(IMAGE_PATH + '/train/*.tfrec') + IMAGENET_FILES + INATURELIST_FILES + OPENIMAGE_FILES + OXFORD_FILES + TENSORFLOW_FILES\n\nVALIDATION_FILENAMES = tf.io.gfile.glob(IMAGE_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(IMAGE_PATH + '/test/*.tfrec') \n\nIMAGE_SIZE = [SIZE, SIZE]\n\nBATCH_SIZE = 128\nEPOCHS = 35","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:17.689418Z","iopub.execute_input":"2022-06-29T19:02:17.691205Z","iopub.status.idle":"2022-06-29T19:02:37.070997Z","shell.execute_reply.started":"2022-06-29T19:02:17.691159Z","shell.execute_reply":"2022-06-29T19:02:37.070035Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"CLASSES = ['pink primrose',    'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea',     'wild geranium',     'tiger lily',           'moon orchid',              'bird of paradise', 'monkshood',        'globe thistle',         # 00 - 09\n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily', # 10 - 19\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',         # 20 - 29\n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',           # 30 - 39\n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',      # 40 - 49\n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',    # 50 - 59\n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',            # 60 - 69\n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',             # 70 - 79\n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',            # 80 - 89\n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',        # 90 - 99\n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']                                                                                                                                               # 100 - 102","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:37.072191Z","iopub.execute_input":"2022-06-29T19:02:37.072402Z","iopub.status.idle":"2022-06-29T19:02:37.083255Z","shell.execute_reply.started":"2022-06-29T19:02:37.072377Z","shell.execute_reply":"2022-06-29T19:02:37.082460Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Connect to TPU","metadata":{}},{"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)\n    \nprint(tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:37.085105Z","iopub.execute_input":"2022-06-29T19:02:37.085461Z","iopub.status.idle":"2022-06-29T19:02:43.157514Z","shell.execute_reply.started":"2022-06-29T19:02:37.085432Z","shell.execute_reply":"2022-06-29T19:02:43.156586Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Load and Preprocess Data","metadata":{}},{"cell_type":"code","source":"def decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = (tf.cast(image, tf.float32) / 127.5) - 1\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=AUTOTUNE)\n    dataset = dataset.with_options(ignore_order)\n    \n    if labeled:\n        dataset = dataset.map(read_labeled_tfrecord, num_parallel_calls=AUTOTUNE)\n    else:\n        dataset = dataset.map(read_unlabeled_tfrecord, num_parallel_calls=AUTOTUNE)\n    \n    return dataset","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:43.158753Z","iopub.execute_input":"2022-06-29T19:02:43.159004Z","iopub.status.idle":"2022-06-29T19:02:43.171577Z","shell.execute_reply.started":"2022-06-29T19:02:43.158974Z","shell.execute_reply":"2022-06-29T19:02:43.170972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def random_cut_out(image, label):\n    image = tf.expand_dims(image, axis=0)\n    return tf.squeeze(tfa.image.random_cutout(image, (192, 192), constant_values = 1), axis=0), label\n\ndef data_augment(image, label):\n    p_spatial = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n    p_rotate = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n    \n    image = tf.image.resize(image, [SIZE+30, SIZE+30], method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)\n    image = tf.image.random_crop(image, size=[SIZE, SIZE, 3])\n    \n    if p_rotate > .8:\n        image = tf.image.rot90(image, k=3) \n    elif p_rotate > .6:\n        image = tf.image.rot90(image, k=2) \n    elif p_rotate > .4:\n        image = tf.image.rot90(image, k=1)\n        \n    image = tf.image.random_flip_left_right(image)\n    image = tf.image.random_flip_up_down(image)\n    \n    if p_spatial > .75:\n        image = tf.image.transpose(image)\n        \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=AUTOTUNE)\n    dataset = dataset.map(random_cut_out, 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\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.prefetch(AUTOTUNE)\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(AUTOTUNE)\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))","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:43.172793Z","iopub.execute_input":"2022-06-29T19:02:43.173050Z","iopub.status.idle":"2022-06-29T19:02:43.192644Z","shell.execute_reply.started":"2022-06-29T19:02:43.173012Z","shell.execute_reply":"2022-06-29T19:02:43.192047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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)","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:43.194016Z","iopub.execute_input":"2022-06-29T19:02:43.194620Z","iopub.status.idle":"2022-06-29T19:02:44.931458Z","shell.execute_reply.started":"2022-06-29T19:02:43.194580Z","shell.execute_reply":"2022-06-29T19:02:44.930670Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Explore Data","metadata":{}},{"cell_type":"code","source":"def batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    if numpy_labels.dtype == object: # binary string in this case,\n                                     # these are image ID strings\n        numpy_labels = [None for _ in enumerate(numpy_images)]\n    # If no labels, only image IDs, return None for labels (this is\n    # the case for test data)\n    return numpy_images, numpy_labels\n\ndef title_from_label_and_target(label, correct_label):\n    if correct_label is None:\n        return CLASSES[label], True\n    correct = (label == correct_label)\n    return \"{} [{}{}{}]\".format(CLASSES[label], 'OK' if correct else 'NO', u\"\\u2192\" if not correct else '',\n                                CLASSES[correct_label] if not correct else ''), correct\n\ndef display_one_flower(image, title, subplot, red=False, titlesize=16):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image * 0.5 + 0.5)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n    return (subplot[0], subplot[1], subplot[2]+1)\n    \ndef display_batch_of_images(databatch, predictions=None):\n    \"\"\"This will work with:\n    display_batch_of_images(images)\n    display_batch_of_images(images, predictions)\n    display_batch_of_images((images, labels))\n    display_batch_of_images((images, labels), predictions)\n    \"\"\"\n    # data\n    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n        \n    # auto-squaring: this will drop data that does not fit into square\n    # or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n        \n    # size and spacing\n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[label]\n        correct = True\n        if predictions is not None:\n            title, correct = title_from_label_and_target(predictions[i], label)\n        dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n        subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n    \n    #layout\n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspace=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:44.932667Z","iopub.execute_input":"2022-06-29T19:02:44.932889Z","iopub.status.idle":"2022-06-29T19:02:44.951805Z","shell.execute_reply.started":"2022-06-29T19:02:44.932865Z","shell.execute_reply":"2022-06-29T19:02:44.950693Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(20))","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:44.953115Z","iopub.execute_input":"2022-06-29T19:02:44.953341Z","iopub.status.idle":"2022-06-29T19:02:44.979634Z","shell.execute_reply.started":"2022-06-29T19:02:44.953315Z","shell.execute_reply":"2022-06-29T19:02:44.978466Z"},"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":"2022-06-29T19:02:44.982320Z","iopub.execute_input":"2022-06-29T19:02:44.982550Z","iopub.status.idle":"2022-06-29T19:02:56.979839Z","shell.execute_reply.started":"2022-06-29T19:02:44.982523Z","shell.execute_reply":"2022-06-29T19:02:56.976738Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Define Model","metadata":{}},{"cell_type":"code","source":"with strategy.scope():\n    pretrained_model_xception = tf.keras.applications.Xception(input_shape=[*IMAGE_SIZE, 3],\n                                               include_top=False,\n                                               weights='imagenet')\n    \n    model_xception = tf.keras.Sequential([\n        # To a base pretrained on ImageNet to extract features from images...\n        pretrained_model_xception,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dropout(0.2),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:02:56.981826Z","iopub.execute_input":"2022-06-29T19:02:56.982645Z","iopub.status.idle":"2022-06-29T19:03:07.165799Z","shell.execute_reply.started":"2022-06-29T19:02:56.982601Z","shell.execute_reply":"2022-06-29T19:03:07.164940Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(pretrained_model_xception.layers)","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:03:07.167244Z","iopub.execute_input":"2022-06-29T19:03:07.167482Z","iopub.status.idle":"2022-06-29T19:03:07.173551Z","shell.execute_reply.started":"2022-06-29T19:03:07.167454Z","shell.execute_reply":"2022-06-29T19:03:07.172691Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_xception.summary()","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:03:07.175078Z","iopub.execute_input":"2022-06-29T19:03:07.175605Z","iopub.status.idle":"2022-06-29T19:03:07.202555Z","shell.execute_reply.started":"2022-06-29T19:03:07.175560Z","shell.execute_reply":"2022-06-29T19:03:07.201614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    \n    model_xception.compile(loss='sparse_categorical_crossentropy',\n                  optimizer='nadam',\n                  metrics=['sparse_categorical_accuracy'])","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:03:07.204126Z","iopub.execute_input":"2022-06-29T19:03:07.204465Z","iopub.status.idle":"2022-06-29T19:03:07.249625Z","shell.execute_reply.started":"2022-06-29T19:03:07.204431Z","shell.execute_reply":"2022-06-29T19:03:07.248804Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training","metadata":{}},{"cell_type":"code","source":"# Learning Rate Schedule for Fine Tuning #\ndef 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\n    def lr(epoch, start_lr, min_lr, max_lr, rampup_epochs, sustain_epochs, exp_decay):\n        # linear increase from start to rampup_epochs\n        if epoch < rampup_epochs:\n            lr = ((max_lr - start_lr) /\n                  rampup_epochs * epoch + start_lr)\n        # constant max_lr during sustain_epochs\n        elif epoch < rampup_epochs + sustain_epochs:\n            lr = max_lr\n        # exponential decay towards min_lr\n        else:\n            lr = ((max_lr - min_lr) *\n                  exp_decay**(epoch - rampup_epochs - sustain_epochs) +\n                  min_lr)\n        return lr\n    \n    return lr(epoch,\n              start_lr,\n              min_lr,\n              max_lr,\n              rampup_epochs,\n              sustain_epochs,\n              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)\nprint(\"Learning rate schedule: {:.3g} to {:.3g} to {:.3g}\".format(y[0], max(y), y[-1]))","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:03:07.250963Z","iopub.execute_input":"2022-06-29T19:03:07.251187Z","iopub.status.idle":"2022-06-29T19:03:07.493939Z","shell.execute_reply.started":"2022-06-29T19:03:07.251162Z","shell.execute_reply":"2022-06-29T19:03:07.493137Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"STEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model_xception.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    steps_per_epoch=STEPS_PER_EPOCH,\n    callbacks=[lr_callback, tf.keras.callbacks.ModelCheckpoint(filepath='Xception.h5', monitor='val_loss',\n                                            save_best_only=True)],\n    workers=3\n)","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:03:07.494913Z","iopub.execute_input":"2022-06-29T19:03:07.495148Z","iopub.status.idle":"2022-06-29T19:53:54.765559Z","shell.execute_reply.started":"2022-06-29T19:03:07.495122Z","shell.execute_reply":"2022-06-29T19:53:54.764117Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:53:54.766947Z","iopub.status.idle":"2022-06-29T19:53:54.767317Z","shell.execute_reply.started":"2022-06-29T19:53:54.767149Z","shell.execute_reply":"2022-06-29T19:53:54.767165Z"},"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":"2022-06-29T19:53:54.768543Z","iopub.status.idle":"2022-06-29T19:53:54.769114Z","shell.execute_reply.started":"2022-06-29T19:53:54.768942Z","shell.execute_reply":"2022-06-29T19:53:54.768968Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_xception = tf.keras.models.load_model('Xception.h5')","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:53:54.769771Z","iopub.status.idle":"2022-06-29T19:53:54.770292Z","shell.execute_reply.started":"2022-06-29T19:53:54.770111Z","shell.execute_reply":"2022-06-29T19:53:54.770127Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Evaluation","metadata":{}},{"cell_type":"code","source":"def 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()","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:53:54.771272Z","iopub.status.idle":"2022-06-29T19:53:54.771796Z","shell.execute_reply.started":"2022-06-29T19:53:54.771610Z","shell.execute_reply":"2022-06-29T19:53:54.771628Z"},"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_xception.predict(images_ds)\ncm_predictions = np.argmax(cm_probabilities, axis=-1)\n\nlabels = range(len(CLASSES))\ncmat = confusion_matrix(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n)\ncmat = (cmat.T / cmat.sum(axis=1)).T # normalize","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:53:54.772717Z","iopub.status.idle":"2022-06-29T19:53:54.773391Z","shell.execute_reply.started":"2022-06-29T19:53:54.773082Z","shell.execute_reply":"2022-06-29T19:53:54.773114Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"score = f1_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nprecision = precision_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nrecall = recall_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\ndisplay_confusion_matrix(cmat, score, precision, recall)","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:53:54.774780Z","iopub.status.idle":"2022-06-29T19:53:54.775290Z","shell.execute_reply.started":"2022-06-29T19:53:54.775034Z","shell.execute_reply":"2022-06-29T19:53:54.775060Z"},"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":"2022-06-29T19:53:54.776322Z","iopub.status.idle":"2022-06-29T19:53:54.776648Z","shell.execute_reply.started":"2022-06-29T19:53:54.776479Z","shell.execute_reply":"2022-06-29T19:53:54.776500Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"images, labels = next(batch)\nprobabilities = model_xception.predict(images)\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions)","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:53:54.777850Z","iopub.status.idle":"2022-06-29T19:53:54.778199Z","shell.execute_reply.started":"2022-06-29T19:53:54.778033Z","shell.execute_reply":"2022-06-29T19:53:54.778053Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Prediction and Submission","metadata":{}},{"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_xception.predict(test_images_ds)\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)","metadata":{"execution":{"iopub.status.busy":"2022-06-29T19:53:54.779765Z","iopub.status.idle":"2022-06-29T19:53:54.780131Z","shell.execute_reply.started":"2022-06-29T19:53:54.779918Z","shell.execute_reply":"2022-06-29T19:53:54.779939Z"},"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":{"execution":{"iopub.status.busy":"2022-06-29T19:53:54.781337Z","iopub.status.idle":"2022-06-29T19:53:54.781904Z","shell.execute_reply.started":"2022-06-29T19:53:54.781717Z","shell.execute_reply":"2022-06-29T19:53:54.781744Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}