{"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":"2022-11-27T06:48:53.088327Z","iopub.execute_input":"2022-11-27T06:48:53.089352Z","iopub.status.idle":"2022-11-27T06:48:53.313950Z","shell.execute_reply.started":"2022-11-27T06:48:53.089242Z","shell.execute_reply":"2022-11-27T06:48:53.313157Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import math, re, os\nimport tensorflow as tf\nfrom matplotlib import pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\n\nprint(\"Tensorflow version \", tf.__version__)\nAUTO = tf.data.experimental.AUTOTUNE","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:48:53.315552Z","iopub.execute_input":"2022-11-27T06:48:53.315767Z","iopub.status.idle":"2022-11-27T06:48:59.846178Z","shell.execute_reply.started":"2022-11-27T06:48:53.315742Z","shell.execute_reply":"2022-11-27T06:48:59.845299Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"try:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver.connect()\n    strategy = tf.distribute.TPUStrategy(tpu)\nexcept ValueError:\n    strategy = tf.distribute.get_strategy()\n    \nprint(\"Number of accelerators: \", strategy.num_replicas_in_sync)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:48:59.847848Z","iopub.execute_input":"2022-11-27T06:48:59.848163Z","iopub.status.idle":"2022-11-27T06:49:06.045761Z","shell.execute_reply.started":"2022-11-27T06:48:59.848123Z","shell.execute_reply":"2022-11-27T06:49:06.045057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path() # TPU Version\n# GCS_DS_PATH = \"/kaggle/input/flower-classification-with-tpus\" # CPU Version","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:06.048341Z","iopub.execute_input":"2022-11-27T06:49:06.048636Z","iopub.status.idle":"2022-11-27T06:49:06.419797Z","shell.execute_reply.started":"2022-11-27T06:49:06.048605Z","shell.execute_reply":"2022-11-27T06:49:06.418940Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [512, 512]\nEPOCHS = 12\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nGCS_PATH_SELECT = {\n    192: GCS_DS_PATH + '/tfrecords-jpeg-192x192',\n    224: GCS_DS_PATH + '/tfrecords-jpeg-224x224',\n    331: GCS_DS_PATH + '/tfrecords-jpeg-331x331',\n    512: GCS_DS_PATH + '/tfrecords-jpeg-512x512',\n}\nGCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]]\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","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:06.421438Z","iopub.execute_input":"2022-11-27T06:49:06.421686Z","iopub.status.idle":"2022-11-27T06:49:06.664741Z","shell.execute_reply.started":"2022-11-27T06:49:06.421658Z","shell.execute_reply":"2022-11-27T06:49:06.663810Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Visualization utilities","metadata":{}},{"cell_type":"code","source":"np.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    \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], \n                                '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    \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',\n                 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    \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], 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_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    \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    \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,\n                                               'horizontalalignment': 'right',\n                                               'verticalalignment': 'top',\n                                               '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":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-11-27T06:49:06.666442Z","iopub.execute_input":"2022-11-27T06:49:06.666671Z","iopub.status.idle":"2022-11-27T06:49:06.692734Z","shell.execute_reply.started":"2022-11-27T06:49:06.666645Z","shell.execute_reply":"2022-11-27T06:49:06.691440Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Datasets","metadata":{}},{"cell_type":"code","source":"def decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\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\n\ndef data_augment(image, label):\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()\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=True):\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)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nVALIDATION_STEPS = -(-NUM_VALIDATION_IMAGES // BATCH_SIZE)\nTEST_STEPS = -(-NUM_TEST_IMAGES//BATCH_SIZE) \n# 19//2 = 9\n# -(-19//2) = 10\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":"2022-11-27T06:49:06.695109Z","iopub.execute_input":"2022-11-27T06:49:06.695353Z","iopub.status.idle":"2022-11-27T06:49:06.714020Z","shell.execute_reply.started":"2022-11-27T06:49:06.695327Z","shell.execute_reply":"2022-11-27T06:49:06.713191Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Dataset visualizations","metadata":{}},{"cell_type":"code","source":"print(\"Training data shapes:\")\nfor image, label in get_training_dataset().take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training data label examples:\", label.numpy())\nprint(\"=\"*30)\nprint(\"Validation data shapes:\")\nfor image, label in get_validation_dataset().take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Validation data label examples:\", label.numpy())\nprint(\"=\"*30)\nprint(\"Test data shapes:\")\nfor image, idnum in get_test_dataset().take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test data IDs:\", idnum.numpy().astype(\"U\"))","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:06.715194Z","iopub.execute_input":"2022-11-27T06:49:06.715436Z","iopub.status.idle":"2022-11-27T06:49:13.825675Z","shell.execute_reply.started":"2022-11-27T06:49:06.715410Z","shell.execute_reply":"2022-11-27T06:49:13.824614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"training_dataset = get_training_dataset()\ntraining_dataset = training_dataset.unbatch().batch(20)\ntrain_batch = iter(training_dataset)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:13.826781Z","iopub.execute_input":"2022-11-27T06:49:13.827037Z","iopub.status.idle":"2022-11-27T06:49:13.878208Z","shell.execute_reply.started":"2022-11-27T06:49:13.827009Z","shell.execute_reply":"2022-11-27T06:49:13.877252Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_batch_of_images(next(train_batch))","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:13.881667Z","iopub.execute_input":"2022-11-27T06:49:13.882200Z","iopub.status.idle":"2022-11-27T06:49:16.661462Z","shell.execute_reply.started":"2022-11-27T06:49:13.882153Z","shell.execute_reply":"2022-11-27T06:49:16.660393Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_dataset = get_test_dataset()\ntest_dataset = test_dataset.unbatch().batch(20)\ntest_batch = iter(test_dataset)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:16.663400Z","iopub.execute_input":"2022-11-27T06:49:16.663899Z","iopub.status.idle":"2022-11-27T06:49:16.707129Z","shell.execute_reply.started":"2022-11-27T06:49:16.663863Z","shell.execute_reply":"2022-11-27T06:49:16.706316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_batch_of_images(next(test_batch))","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:16.708292Z","iopub.execute_input":"2022-11-27T06:49:16.708589Z","iopub.status.idle":"2022-11-27T06:49:19.246250Z","shell.execute_reply.started":"2022-11-27T06:49:16.708544Z","shell.execute_reply":"2022-11-27T06:49:19.245333Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model","metadata":{}},{"cell_type":"code","source":"with strategy.scope():\n#     img_adjust_layer = tf.keras.layers.Lambda(\n#         lambda data: tf.keras.applications.xception.preproces_input(\n#             tf.cast(data, tf.float32)), input_shape=[*IMAGE_SIZE, 3])\n#     pretrained_model = tf.keras.applications.Xception(weights='imagenet', include_top=False)\n    img_adjust_layer = tf.keras.layers.Lambda(\n        lambda data: tf.keras.applications.vgg16.preprocess_input(\n            tf.cast(data, tf.float32)), input_shape=[*IMAGE_SIZE, 3]\n    )\n    \n    pretrained_model = tf.keras.applications.VGG16(weights=\"imagenet\", include_top=False)\n    pretrained_model.trainable = False\n    \n    model = tf.keras.Sequential([\n        img_adjust_layer,\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n    \nmodel.compile(\n    optimizer='adam',\n    loss='sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n    # NEW on TPU in Tensorflow 24: sending multiple batches to the TPU at once saves communications\n    # overheads and allows the XLA compile to unroll the loop on TPU and optimize hardware utilization.\n    steps_per_execution=16\n)\n\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:19.247450Z","iopub.execute_input":"2022-11-27T06:49:19.247704Z","iopub.status.idle":"2022-11-27T06:49:21.782889Z","shell.execute_reply.started":"2022-11-27T06:49:19.247675Z","shell.execute_reply":"2022-11-27T06:49:21.782033Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training","metadata":{}},{"cell_type":"code","source":"history = model.fit(get_training_dataset(),\n                   steps_per_epoch=STEPS_PER_EPOCH,\n                   epochs=EPOCHS,\n                   validation_data=get_validation_dataset(),\n                   validation_steps=VALIDATION_STEPS)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:49:21.784160Z","iopub.execute_input":"2022-11-27T06:49:21.784522Z","iopub.status.idle":"2022-11-27T06:53:13.574726Z","shell.execute_reply.started":"2022-11-27T06:49:21.784465Z","shell.execute_reply":"2022-11-27T06:53:13.573954Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_training_curves(history.history[\"loss\"], history.history[\"val_loss\"], 'loss', 211)\ndisplay_training_curves(history.history['sparse_categorical_accuracy'],\n                       history.history['val_sparse_categorical_accuracy'], 'accuracy', 212)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:53:13.575932Z","iopub.execute_input":"2022-11-27T06:53:13.576623Z","iopub.status.idle":"2022-11-27T06:53:14.130308Z","shell.execute_reply.started":"2022-11-27T06:53:13.576592Z","shell.execute_reply":"2022-11-27T06:53:14.129378Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Confusion matrix","metadata":{}},{"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, steps=VALIDATION_STEPS)\ncm_predictions = np.argmax(cm_probabilities, axis=-1)\nprint(\"Correct labels: \", cm_correct_labels.shape, cm_correct_labels)\nprint(\"Predicted labels: \", cm_predictions.shape, cm_predictions)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:53:14.131771Z","iopub.execute_input":"2022-11-27T06:53:14.132459Z","iopub.status.idle":"2022-11-27T06:53:33.711839Z","shell.execute_reply.started":"2022-11-27T06:53:14.132416Z","shell.execute_reply":"2022-11-27T06:53:33.710880Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cmat = confusion_matrix(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)))\nscore = f1_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\nprecision = precision_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\nrecall = recall_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\ncmat = (cmat.T/cmat.sum(axis=1)).T\ndisplay_confusion_matrix(cmat, score, precision, recall)\nprint(\"f1 score: {:.3f}, precision: {:.3f}, recall: {:.3f}\".format(score, precision, recall))","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:53:33.713606Z","iopub.execute_input":"2022-11-27T06:53:33.713940Z","iopub.status.idle":"2022-11-27T06:53:38.849774Z","shell.execute_reply.started":"2022-11-27T06:53:33.713900Z","shell.execute_reply":"2022-11-27T06:53:38.848906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Predictions","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.predict(test_images_ds, steps=TEST_STEPS)\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T07:00:30.911092Z","iopub.execute_input":"2022-11-27T07:00:30.911592Z","iopub.status.idle":"2022-11-27T07:00:40.032889Z","shell.execute_reply.started":"2022-11-27T07:00:30.911544Z","shell.execute_reply":"2022-11-27T07:00:40.031949Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Generating submission.csv file...\")\ntest_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()\ntest_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U')\nnp.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]),\n           fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')\n!head submission.csv","metadata":{"execution":{"iopub.status.busy":"2022-11-27T07:00:43.564096Z","iopub.execute_input":"2022-11-27T07:00:43.564446Z","iopub.status.idle":"2022-11-27T07:00:45.747025Z","shell.execute_reply.started":"2022-11-27T07:00:43.564412Z","shell.execute_reply":"2022-11-27T07:00:45.746123Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Visual validation","metadata":{}},{"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:53:57.545653Z","iopub.execute_input":"2022-11-27T06:53:57.545899Z","iopub.status.idle":"2022-11-27T06:53:57.589531Z","shell.execute_reply.started":"2022-11-27T06:53:57.545871Z","shell.execute_reply":"2022-11-27T06:53:57.588527Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"images, labels = next(batch)\nprobabilities = model.predict(tf.cast(images, tf.float32))\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions)","metadata":{"execution":{"iopub.status.busy":"2022-11-27T06:53:57.590744Z","iopub.execute_input":"2022-11-27T06:53:57.591001Z","iopub.status.idle":"2022-11-27T06:54:12.063042Z","shell.execute_reply.started":"2022-11-27T06:53:57.590973Z","shell.execute_reply":"2022-11-27T06:54:12.062286Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}