{"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\n# import numpy as np # linear algebra\n# import 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\n# import os\n# for 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_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":"2023-10-11T06:58:59.991572Z","iopub.execute_input":"2023-10-11T06:58:59.992051Z","iopub.status.idle":"2023-10-11T06:58:59.996386Z","shell.execute_reply.started":"2023-10-11T06:58:59.992021Z","shell.execute_reply":"2023-10-11T06:58:59.995680Z"},"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    gpus = tf.config.experimental.list_physical_devices('GPU')\n    # print(gpus)\n    for gpu in gpus:\n        tf.config.experimental.set_memory_growth(gpu, True)\n        print(gpu)\n    if gpus:\n        strategy = tf.distribute.MirroredStrategy()\n    else:\n        strategy = tf.distribute.get_strategy() # default distribution strategy in Tensorflow. Works on CPU a\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"execution":{"iopub.status.busy":"2023-10-11T06:59:04.560962Z","iopub.execute_input":"2023-10-11T06:59:04.561663Z","iopub.status.idle":"2023-10-11T06:59:27.507540Z","shell.execute_reply.started":"2023-10-11T06:59:04.561628Z","shell.execute_reply":"2023-10-11T06:59:27.506460Z"},"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":{"execution":{"iopub.status.busy":"2023-10-11T06:59:41.635195Z","iopub.execute_input":"2023-10-11T06:59:41.636473Z","iopub.status.idle":"2023-10-11T06:59:41.642906Z","shell.execute_reply.started":"2023-10-11T06:59:41.636407Z","shell.execute_reply":"2023-10-11T06:59:41.641897Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_DS_PATH_EXT = KaggleDatasets().get_gcs_path('tf-flower-photo-tfrec')\nprint(GCS_DS_PATH_EXT)","metadata":{"execution":{"iopub.status.busy":"2023-10-11T08:59:52.726676Z","iopub.execute_input":"2023-10-11T08:59:52.727098Z","iopub.status.idle":"2023-10-11T08:59:52.732420Z","shell.execute_reply.started":"2023-10-11T08:59:52.727064Z","shell.execute_reply":"2023-10-11T08:59:52.731454Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [224, 224] # 192, 224, 331, 512\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-224x224'\n\nAUTO = tf.data.experimental.AUTOTUNE\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\n\nGCS_PATH_EXT = '/tfrecords-jpeg-224x224'\n\nIMAGENET_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/imagenet' + GCS_PATH_EXT + '/*.tfrec')\nINATURELIST_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/inaturalist' + GCS_PATH_EXT + '/*.tfrec')\nOPENIMAGE_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/openimage' + GCS_PATH_EXT + '/*.tfrec')\nOXFORD_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/oxford_102' + GCS_PATH_EXT + '/*.tfrec')\nTENSORFLOW_FILES = tf.io.gfile.glob(GCS_DS_PATH_EXT + '/tf_flowers' + GCS_PATH_EXT + '/*.tfrec')\n\nADDITIONAL_TRAINING_FILENAMES = IMAGENET_FILES + INATURELIST_FILES + OPENIMAGE_FILES + OXFORD_FILES + TENSORFLOW_FILES  \n\nTRAINING_FILENAMES = TRAINING_FILENAMES + ADDITIONAL_TRAINING_FILENAMES\n\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":{"execution":{"iopub.status.busy":"2023-10-11T08:59:57.803407Z","iopub.execute_input":"2023-10-11T08:59:57.804394Z","iopub.status.idle":"2023-10-11T08:59:57.969699Z","shell.execute_reply.started":"2023-10-11T08:59:57.804341Z","shell.execute_reply":"2023-10-11T08:59:57.968506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def random_blackout(img, sl=0.1, sh=0.2, rl=0.4, p=0.3):\n    if(tf.random.uniform([], 0, 1) > p):\n        return img\n    \n    else:\n        h = tf.shape(img)[0]\n        w = tf.shape(img)[1]\n        c = tf.shape(img)[2]\n        origin_area = tf.cast(h*w, tf.float32)\n\n        e_size_l = tf.cast(tf.round(tf.sqrt(origin_area * sl * rl)), tf.int32)\n        e_size_h = tf.cast(tf.round(tf.sqrt(origin_area * sh / rl)), tf.int32)\n\n        e_height_h = tf.minimum(e_size_h, h)\n        e_width_h = tf.minimum(e_size_h, w)\n\n        erase_height = tf.random.uniform(shape=[], minval=e_size_l, maxval=e_height_h, dtype=tf.int32)\n        erase_width = tf.random.uniform(shape=[], minval=e_size_l, maxval=e_width_h, dtype=tf.int32)\n\n        erase_area = tf.zeros(shape=[erase_height, erase_width, c])\n        erase_area = tf.cast(erase_area, tf.uint8)\n\n        pad_h = h - erase_height\n        pad_top = tf.random.uniform(shape=[], minval=0, maxval=pad_h, dtype=tf.int32)\n        pad_bottom = pad_h - pad_top\n\n        pad_w = w - erase_width\n        pad_left = tf.random.uniform(shape=[], minval=0, maxval=pad_w, dtype=tf.int32)\n        pad_right = pad_w - pad_left\n\n        erase_mask = tf.pad([erase_area], [[0,0],[pad_top, pad_bottom], [pad_left, pad_right], [0,0]], constant_values=1)\n        erase_mask = tf.squeeze(erase_mask, axis=0)\n        erased_img = tf.multiply(tf.cast(img,tf.float32), tf.cast(erase_mask, tf.float32))\n        \n        return tf.cast(erased_img, img.dtype)\n\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    # Random changes to image\n    image = tf.image.random_flip_left_right(image)\n    image = tf.image.random_flip_up_down(image)\n    image = tf.image.random_brightness(image, max_delta=0.2)\n    image = tf.image.random_contrast(image, lower=0.8, upper=1.2)\n    image = tf.image.random_saturation(image, lower=0.8, upper=1.2)\n#     image = tf.image.random_crop(image, size=[*IMAGE_SIZE, 3])\n#     image = tf.image.resize(image, size=IMAGE_SIZE)\n#     image = random_blackout(image,sl=0.07,sh=0.08)\n    \n#     image = tf.image.stateless_random_flip_left_right(image)\n#     image = tf.image.stateless_random_flip_up_down(image)\n#     image = tf.image.stateless_random_brightness(image, max_delta=0.2)\n#     image = tf.image.stateless_random_contrast(image, lower=0.8, upper=1.2)\n#     image = tf.image.stateless_random_saturation(image, lower=0.8, upper=1.2)\n#     image = tf.image.stateless_random_crop(image, size=[*IMAGE_SIZE, 3])\n    \n    image = random_blackout(image,sl=0.07,sh=0.08,p=0.4)    \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:\\n{} training images\\n{} validation images\\n{} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","metadata":{"execution":{"iopub.status.busy":"2023-10-11T09:00:09.952671Z","iopub.execute_input":"2023-10-11T09:00:09.953954Z","iopub.status.idle":"2023-10-11T09:00:09.973330Z","shell.execute_reply.started":"2023-10-11T09:00:09.953904Z","shell.execute_reply":"2023-10-11T09:00:09.972304Z"},"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\n# ds_train = get_training_dataset()\nds_train = get_training_dataset()#.concatenate(get_training_dataset(True))\nds_valid = get_validation_dataset()\nds_test = get_test_dataset()\n\n# nRows,nCols,nDims = train_images.shape[1:]\n# train_data = train_images.reshape(train_images.shape[0], nRows, nCols, nDims)\n# test_data = test_images.reshape(test_images.shape[0], nRows, nCols, nDims)\n# input_shape = (nRows, nCols, nDims)\n\n# train_data = train_data.astype('float32')\n# test_data = test_data.astype('float32')\n\nprint(\"Training:\", ds_train)\nprint (\"Validation:\", ds_valid)\nprint(\"Test:\", ds_test)","metadata":{"execution":{"iopub.status.busy":"2023-10-11T09:00:18.985629Z","iopub.execute_input":"2023-10-11T09:00:18.986052Z","iopub.status.idle":"2023-10-11T09:00:19.431843Z","shell.execute_reply.started":"2023-10-11T09:00:18.986021Z","shell.execute_reply":"2023-10-11T09:00:19.430842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","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":{}},{"cell_type":"markdown","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":{}},{"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: # 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)\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, only_error = False):\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\n#         For Displaying only wrong labled predection\n        if(only_error and not correct):\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        if(not only_error):\n            dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n            subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n    \n    #layout\n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspace=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n    plt.show()\n\n\ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","metadata":{"execution":{"iopub.status.busy":"2023-10-11T07:06:13.934556Z","iopub.execute_input":"2023-10-11T07:06:13.935245Z","iopub.status.idle":"2023-10-11T07:06:14.268524Z","shell.execute_reply.started":"2023-10-11T07:06:13.935211Z","shell.execute_reply":"2023-10-11T07:06:14.267608Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"ds_iter = iter(ds_train.unbatch().batch(50))","metadata":{}},{"cell_type":"markdown","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{}},{"cell_type":"code","source":"reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(\n    monitor = 'val_sparse_categorical_accuracy',\n    factor = 0.23, patience = 2, min_delta = 0.001,\n    mode='auto',verbose=1)\n\nearly_stopping = tf.keras.callbacks.EarlyStopping(\n    monitor = 'val_sparse_categorical_accuracy',\n    patience=4,\n    min_delta=0.0005,\n    restore_best_weights=True,\n    verbose=1)\n\nos.makedirs('checkpoints', exist_ok=True)\n\ncheckpoint_cb = tf.keras.callbacks.ModelCheckpoint('my_best.h5',\n            save_weights_only=True,\n            monitor='val_sparse_categorical_accuracy',\n            mode='max',\n            save_best_only=True,\n            verbose=1)\n\nbest_epoch_cb = tf.keras.callbacks.LambdaCallback(on_train_end=lambda logs: \n                 print(f\"Best val_sparse_categorical_accuracy: {checkpoint_cb.best:.4f}\"))\n\nprint(\"Callbacks created...\")","metadata":{"execution":{"iopub.status.busy":"2023-10-11T07:08:44.857471Z","iopub.execute_input":"2023-10-11T07:08:44.858324Z","iopub.status.idle":"2023-10-11T07:08:57.954811Z","shell.execute_reply.started":"2023-10-11T07:08:44.858287Z","shell.execute_reply":"2023-10-11T07:08:57.953790Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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 = 0.0005 * strategy.num_replicas_in_sync,\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    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(50)]\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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.DenseNet201(\n        weights='imagenet',\n        include_top=False ,\n        pooling='avg',\n        input_shape=[*IMAGE_SIZE, 3]\n    )\n    pretrained_model.trainable = True\n    #     pretrained_model_VGG19 = tf.keras.applications.VGG19(\n#         weights='imagenet',\n#         include_top=False ,\n# #         pooling='avg',\n#         input_shape=[*IMAGE_SIZE, 3]\n#     )\n#     pretrained_model_VGG19.trainable = True\n\n    # adding regularization\n#     regularizer = tf.keras.regularizers.l2(0.0001)\n\n#     for layer in pretrained_model.layers:\n#         for attr in ['kernel_regularizer']:\n#             if hasattr(layer, attr):\n#                 setattr(layer, attr, regularizer)\n    \n    model = tf.keras.Sequential([\n        # To a base pretrained on  DenseNet201 to extract features from images...\n#         pretrained_model_VGG19,\n        pretrained_model,\n#         tf.keras.layers.GlobalAveragePooling2D(),\n#         tf.keras.layers.Conv2D(64, 3, strides=1, padding='same',\n#                                activation='relu'), \n#         tf.keras.layers.MaxPooling2D(2), \n#         tf.keras.layers.Dropout(rate=0.25),\n#         tf.keras.layers.BatchNormalization(),\n#         tf.keras.layers.Conv2D(32, 3, padding='same', activation='relu'),\n#         tf.keras.layers.MaxPooling2D(2),\n#         tf.keras.layers.Dropout(rate=0.25),\n#         tf.keras.layers.BatchNormalization(),\n#         tf.keras.layers.Conv2D(16, 3, padding='same', activation='relu'),\n#         tf.keras.layers.MaxPooling2D(2),\n#         tf.keras.layers.Dropout(rate=0.25),\n#         tf.keras.layers.BatchNormalization(),\n#         tf.keras.layers.Flatten(),\n##### MY BEST so far############################\n#         tf.keras.layers.BatchNormalization(),\n#         tf.keras.layers.Flatten(),\n#         tf.keras.layers.Dense(256, activation='relu'),\n#         tf.keras.layers.Dropout(rate=0.5),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n################################################\n#         tf.keras.layers.Conv2D(128, 32, strides=1, padding='same', activation='relu',\n#                                kernel_regularizer=tf.keras.regularizers.L2(0.01)), \n\n    \n#         tf.keras.layers.Conv2D(16, 3, strides=1, padding='same',\n#                                activation='relu', input_shape=[*IMAGE_SIZE, 3],\n#                                kernel_regularizer=tf.keras.regularizers.L2(0.01)), \n#         tf.keras.layers.MaxPooling2D(2), \n#         tf.keras.layers.Dropout(rate=0.25),\n#         tf.keras.layers.BatchNormalization(),\n        \n        \n#         tf.keras.layers.Conv2D(64, 3, padding='same', activation='relu', kernel_regularizer=tf.keras.regularizers.L2(0.01)),\n#         tf.keras.layers.MaxPooling2D(2),\n#         tf.keras.layers.Dropout(rate=0.25),\n#         tf.keras.layers.BatchNormalization(),\n\n#         tf.keras.layers.Conv2D(256, 3, padding='same', activation='relu', kernel_regularizer=tf.keras.regularizers.L2(0.01)),\n#         tf.keras.layers.MaxPooling2D(2),\n#         tf.keras.layers.Dropout(rate=0.25),\n#         tf.keras.layers.BatchNormalization(),\n        \n#         tf.keras.layers.Conv2D(64, 3, padding='same', activation='relu'),\n#         tf.keras.layers.MaxPooling2D(),\n#         tf.keras.layers.Dropout(rate=0.5),\n#         tf.keras.layers.BatchNormalization(),\n\n#         tf.keras.layers.Conv2D(256, 3, padding='same', activation='relu'),\n#         tf.keras.layers.MaxPooling2D(),\n#         tf.keras.layers.Dropout(rate=0.25),\n#         tf.keras.layers.BatchNormalization(),\n        \n#         tf.keras.layers.Flatten(),\n#         tf.keras.layers.Dense(256, activation = 'relu'),\n#         tf.keras.layers.Dropout(rate=0.3),\n#         tf.keras.layers.Dense(len(CLASSES), activation='softmax\n                              \n#         tf.keras.layers.GlobalAveragePooling2D(),\n#         tf.keras.layers.Dense(256, activation='relu'),\n#         tf.keras.layers.Dropout(0.1),\n#         tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n    \n    model.compile(\n#         optimizer='rmsprop',\n        optimizer='adam',\n        loss = 'sparse_categorical_crossentropy',\n        metrics=['sparse_categorical_accuracy'],\n    )\n    \n#     model.build([*IMAGE_SIZE, 3])\n    \nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2023-10-11T09:00:30.350170Z","iopub.execute_input":"2023-10-11T09:00:30.350603Z","iopub.status.idle":"2023-10-11T09:01:06.929654Z","shell.execute_reply.started":"2023-10-11T09:00:30.350571Z","shell.execute_reply":"2023-10-11T09:01:06.928413Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define training epochs\nEPOCHS = 50\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nwith strategy.scope():\n    history = 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#         callbacks=[lr_callback, early_stopping],\n        callbacks=[reduce_lr, early_stopping]\n    #     workers = 4,\n    #     use_multiprocessing=True\n    )","metadata":{"execution":{"iopub.status.busy":"2023-10-11T09:01:18.086944Z","iopub.execute_input":"2023-10-11T09:01:18.087680Z","iopub.status.idle":"2023-10-11T09:48:25.875057Z","shell.execute_reply.started":"2023-10-11T09:01:18.087640Z","shell.execute_reply":"2023-10-11T09:48:25.873883Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","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":"2023-10-09T05:05:20.037209Z","iopub.execute_input":"2023-10-09T05:05:20.038345Z","iopub.status.idle":"2023-10-09T05:05:20.814973Z","shell.execute_reply.started":"2023-10-09T05:05:20.038307Z","shell.execute_reply":"2023-10-09T05:05:20.813850Z"}}},{"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=(25,25))\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_spr_matrix(score, precision, recall):\n    print('f1 = {:.3f} '.format(score))\n    print('\\nprecision = {:.3f} '.format(precision))\n    print('\\nrecall = {:.3f} '.format(recall))","metadata":{"execution":{"iopub.status.busy":"2023-10-11T09:48:53.528967Z","iopub.execute_input":"2023-10-11T09:48:53.529671Z","iopub.status.idle":"2023-10-11T09:48:54.227491Z","shell.execute_reply.started":"2023-10-11T09:48:53.529633Z","shell.execute_reply":"2023-10-11T09:48:54.226296Z"},"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":{"execution":{"iopub.status.busy":"2023-10-11T09:49:10.581085Z","iopub.execute_input":"2023-10-11T09:49:10.582258Z","iopub.status.idle":"2023-10-11T09:49:38.630589Z","shell.execute_reply.started":"2023-10-11T09:49:10.582220Z","shell.execute_reply":"2023-10-11T09:49:38.629294Z"},"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)\n\ndisplay_confusion_matrix(cmat, score, precision, recall)\n# display_spr_matrix(score, precision, recall)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-10-11T09:49:45.647873Z","iopub.execute_input":"2023-10-11T09:49:45.648324Z","iopub.status.idle":"2023-10-11T09:49:47.944166Z","shell.execute_reply.started":"2023-10-11T09:49:45.648287Z","shell.execute_reply":"2023-10-11T09:49:47.942999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(60)\nbatch = iter(dataset)","metadata":{}},{"cell_type":"markdown","source":"images, labels = next(batch)\nprobabilities = model.predict(images)\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions,only_error=True)\n# display_batch_of_images_wrong_prediction((images, labels), predictions)","metadata":{}},{"cell_type":"markdown","source":"wrong_pred =[]\nfor x in range(len(cm_correct_labels)):\n    if(cm_correct_labels[x] != cm_predictions[x]):\n        wrong_pred.append([CLASSES[cm_correct_labels[x]],CLASSES[cm_predictions[x]]])\nwrong_pred","metadata":{"execution":{"iopub.status.busy":"2023-10-06T07:09:17.640551Z","iopub.execute_input":"2023-10-06T07:09:17.640970Z","iopub.status.idle":"2023-10-06T07:09:17.657764Z","shell.execute_reply.started":"2023-10-06T07:09:17.640938Z","shell.execute_reply":"2023-10-06T07:09:17.656805Z"}}},{"cell_type":"markdown","source":"wrong_pred = [['hibiscus', 'mallow'],\n ['black-eyed susan', 'sunflower'],\n ['rose', 'azalea'],\n ['thorn apple', 'pincushion flower'],\n ['clematis', 'lotus'],\n ['wallflower', 'magnolia'],\n ['wallflower', 'clematis'],\n ['mallow', 'geranium'],\n ['wallflower', 'wild geranium'],\n ['pink primrose', 'wild rose'],\n ['daffodil', 'common dandelion'],\n ['gazania', 'barberton daisy'],\n ['camellia', 'rose'],\n ['cosmos', 'daisy'],\n ['marigold', 'common dandelion'],\n ['desert-rose', 'azalea'],\n ['buttercup', 'common tulip'],\n ['mallow', 'windflower'],\n ['carnation', 'rose'],\n ['rose', 'camellia'],\n ['camellia', 'cyclamen '],\n ['anthurium', 'giant white arum lily'],\n ['mallow', 'wild geranium'],\n ['tiger lily', 'azalea'],\n ['marigold', 'sunflower'],\n ['wild geranium', 'japanese anemone'],\n ['camellia', 'wild rose'],\n ['cyclamen ', 'gaura'],\n ['common tulip', 'rose'],\n ['poinsettia', 'geranium'],\n ['snapdragon', 'common tulip'],\n ['toad lily', 'blackberry lily'],\n ['black-eyed susan', 'sunflower'],\n ['gazania', 'tiger lily'],\n ['bird of paradise', 'wild rose'],\n ['balloon flower', 'monkshood'],\n ['daisy', 'barberton daisy'],\n ['sweet pea', 'spear thistle'],\n ['sword lily', 'peruvian lily'],\n ['rose', 'daisy'],\n ['rose', 'common tulip'],\n ['balloon flower', 'monkshood'],\n ['pincushion flower', 'camellia'],\n ['daisy', 'common dandelion'],\n ['gazania', 'black-eyed susan'],\n ['petunia', 'morning glory'],\n ['yellow iris', 'iris'],\n ['petunia', 'mexican petunia'],\n ['common dandelion', 'rose'],\n ['sweet pea', 'sword lily'],\n ['sunflower', 'marigold'],\n ['columbine', 'windflower'],\n ['common tulip', 'tiger lily'],\n ['bougainvillea', 'rose'],\n ['thorn apple', 'windflower'],\n ['primula', 'daffodil'],\n ['sunflower', 'primula'],\n ['sunflower', 'black-eyed susan'],\n ['carnation', 'azalea'],\n ['common tulip', 'wild rose'],\n ['bee balm', 'spear thistle'],\n ['peruvian lily', 'snapdragon'],\n ['snapdragon', 'trumpet creeper'],\n ['artichoke', 'globe thistle'],\n ['primula', 'daffodil'],\n ['common tulip', 'common dandelion'],\n ['common dandelion', 'daisy'],\n ['common tulip', 'rose'],\n ['sweet william', 'carnation'],\n ['camellia', 'mallow'],\n ['morning glory', 'bougainvillea'],\n ['rose', 'lotus'],\n ['clematis', 'magnolia'],\n ['common dandelion', 'tree poppy'],\n ['anthurium', 'cyclamen '],\n ['windflower', 'japanese anemone'],\n ['hibiscus', 'petunia'],\n ['rose', 'common tulip'],\n ['anthurium', 'common tulip'],\n ['pincushion flower', 'grape hyacinth'],\n ['columbine', 'common tulip'],\n ['wild geranium', 'pink primrose'],\n ['magnolia', 'snapdragon'],\n ['azalea', 'carnation'],\n ['pincushion flower', 'king protea'],\n ['sunflower', 'lotus'],\n ['buttercup', 'wild geranium'],\n ['gazania', 'marigold'],\n ['poinsettia', 'bee balm'],\n ['buttercup', 'common dandelion'],\n ['windflower', 'common tulip'],\n ['common tulip', 'common dandelion'],\n ['windflower', 'wild geranium'],\n ['gazania', 'sunflower'],\n ['tiger lily', 'peruvian lily'],\n ['balloon flower', 'monkshood'],\n ['rose', 'carnation'],\n ['yellow iris', 'iris'],\n ['frangipani', 'windflower'],\n ['tree poppy', 'daisy'],\n ['iris', 'windflower'],\n ['artichoke', 'spear thistle'],\n ['common tulip', 'daisy'],\n ['toad lily', 'canna lily'],\n ['gazania', 'blanket flower'],\n ['camellia', 'mallow'],\n ['magnolia', 'thorn apple'],\n ['wild geranium', 'wild rose'],\n ['balloon flower', 'wild pansy'],\n ['petunia', 'morning glory'],\n ['clematis', 'hippeastrum '],\n ['rose', 'foxglove'],\n ['camellia', 'rose'],\n ['daisy', 'common tulip'],\n ['sunflower', 'black-eyed susan'],\n ['rose', 'sunflower'],\n ['camellia', 'carnation'],\n ['pincushion flower', 'sweet william'],\n ['snapdragon', 'bee balm'],\n ['pincushion flower', 'common dandelion'],\n ['toad lily', 'wild geranium'],\n ['wild pansy', 'morning glory'],\n ['camellia', 'rose'],\n ['thorn apple', 'wallflower'],\n ['bee balm', 'gaura'],\n ['bougainvillea', 'rose'],\n ['sword lily', 'iris'],\n ['artichoke', 'wild geranium'],\n ['buttercup', 'daffodil'],\n ['clematis', 'king protea'],\n ['black-eyed susan', 'sunflower'],\n ['pink primrose', 'wild rose'],\n ['columbine', 'bee balm'],\n ['windflower', 'common tulip'],\n ['king protea', 'sunflower'],\n ['iris', 'cyclamen '],\n ['rose', 'common tulip'],\n ['common tulip', 'poinsettia'],\n ['common dandelion', 'daisy'],\n ['mallow', 'globe-flower'],\n ['common tulip', 'magnolia'],\n ['carnation', 'bougainvillea'],\n ['sunflower', 'gazania'],\n ['buttercup', 'common dandelion'],\n ['artichoke', 'globe thistle'],\n ['black-eyed susan', 'sunflower'],\n ['lotus', 'rose'],\n [\"colt's foot\", 'common dandelion'],\n ['azalea', 'clematis'],\n ['sword lily', 'hippeastrum '],\n ['morning glory', 'spear thistle'],\n ['common dandelion', 'rose'],\n ['gaura', 'wild geranium'],\n ['cyclamen ', 'common tulip'],\n ['tree poppy', 'mallow'],\n ['clematis', 'rose'],\n ['rose', 'pincushion flower'],\n ['clematis', 'columbine'],\n ['windflower', 'japanese anemone'],\n ['poinsettia', 'bougainvillea'],\n ['morning glory', 'daisy'],\n ['rose', 'sunflower'],\n ['sweet william', 'primula'],\n ['bougainvillea', 'anthurium'],\n ['petunia', 'azalea'],\n ['common tulip', 'rose'],\n ['hibiscus', 'rose'],\n ['columbine', 'primula'],\n ['poinsettia', 'snapdragon'],\n ['rose', 'pincushion flower'],\n ['petunia', 'balloon flower'],\n ['wild geranium', 'windflower'],\n ['grape hyacinth', 'monkshood'],\n ['iris', 'yellow iris'],\n ['thorn apple', 'magnolia'],\n ['lotus', 'buttercup'],\n ['wallflower', 'buttercup'],\n ['anthurium', 'hibiscus'],\n ['sunflower', 'common dandelion'],\n ['pink primrose', 'wild rose'],\n ['thorn apple', 'morning glory'],\n ['mallow', 'wild geranium'],\n ['marigold', 'common dandelion'],\n ['sunflower', 'gazania'],\n ['buttercup', 'marigold'],\n ['windflower', 'wild rose'],\n ['gazania', 'daisy'],\n ['poinsettia', 'rose']]","metadata":{}},{"cell_type":"markdown","source":"import pandas as pd \ntemp = pd.DataFrame(wrong_pred,columns = ['True_lable', 'Prediction'])\n# print(temp.loc[temp['Prediction'] in \n# for x in temp.True_lable.unique():\n#     print(temp.loc[temp['True_lable'] == x ])\npd.set_option('display.max_rows',None)\nnew = temp.groupby(['True_lable','Prediction']).size()\ndisplay(new)\nprint('------------------------------')\nnew1 = temp.groupby(['Prediction','True_lable']).size()\ndisplay(new1)\npd.reset_option('display.max_rows')","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)\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)\nprint('predictions done...')","metadata":{"execution":{"iopub.status.busy":"2023-10-11T09:50:05.801201Z","iopub.execute_input":"2023-10-11T09:50:05.802215Z","iopub.status.idle":"2023-10-11T09:50:30.620505Z","shell.execute_reply.started":"2023-10-11T09:50:05.802176Z","shell.execute_reply":"2023-10-11T09:50:30.619068Z"},"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\n\nprint('Generating submission.csv file done...')","metadata":{"execution":{"iopub.status.busy":"2023-10-11T09:50:33.865139Z","iopub.execute_input":"2023-10-11T09:50:33.865507Z","iopub.status.idle":"2023-10-11T09:50:34.848852Z","shell.execute_reply.started":"2023-10-11T09:50:33.865476Z","shell.execute_reply":"2023-10-11T09:50:34.847690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# import pandas as pd\n# history_df = pd.DataFrame(history.history)\n# history_df.loc[:, ['loss', 'val_loss']].plot(title=\"Cross-entropy\")\n# history_df.loc[:, ['sparse_categorical_accuracy', 'val_sparse_categorical_accuracy']].plot(title=\"Accuracy\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\n\n# print('Computing predictions...')\n# test_images_ds = test_ds.map(lambda image, idnum: image)\n# probabilities = model.predict(test_images_ds)\n# predictions = np.argmax(probabilities, axis=-1)\n# print(predictions)\n\n# print('Generating submission.csv file...')\n# test_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()\n# test_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U') # all in one batch\n# np.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}