{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -q efficientnet","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"0fd5f996-c6bb-40d3-996a-0d55eebc161f","_cell_guid":"2da26627-23be-46c3-8b04-39d7f8fc2a88","trusted":true},"cell_type":"code","source":"import math, re, os\nimport tensorflow as tf\nimport numpy as np\nfrom matplotlib import pyplot as plt\nimport efficientnet.tfkeras as efn\nfrom kaggle_datasets import KaggleDatasets\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\nprint(\"Tensorflow version \" + tf.__version__)\nAUTO = tf.data.experimental.AUTOTUNE","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"90bb39da-a979-458b-afd0-6dc1e4779804","_cell_guid":"2c7d274d-7e8e-4c11-848c-8a69366a02f4","trusted":true},"cell_type":"markdown","source":"# TPU or GPU detection","execution_count":null},{"metadata":{"_uuid":"e3ad3ad1-0051-4f0d-b3f2-f49f61322b93","_cell_guid":"a0468f77-dcd8-4118-b75d-43037332f2a8","trusted":true},"cell_type":"code","source":"# Detect hardware, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()  # TPU detection. No parameters necessary if TPU_NAME environment variable is set. On Kaggle this is always the case.\n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() # default distribution strategy in Tensorflow. Works on CPU and single GPU.\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"de89f7ba-61c7-4882-b03a-fc952558b53c","_cell_guid":"c0a823ea-d861-4e6f-b754-816d597c87f7","trusted":true},"cell_type":"markdown","source":"# Competition data access\nTPUs read data directly from Google Cloud Storage (GCS). This Kaggle utility will copy the dataset to a GCS bucket co-located with the TPU. If you have multiple datasets attached to the notebook, you can pass the name of a specific dataset to the get_gcs_path function. The name of the dataset is the name of the directory it is mounted in. Use `!ls /kaggle/input/` to list attached datasets.","execution_count":null},{"metadata":{"_uuid":"785af0c3-e6f4-44bf-9028-ffcdd3326151","_cell_guid":"90c499a4-57b1-4fd2-9b0a-f24b782017f4","trusted":true},"cell_type":"code","source":"!ls /kaggle/input/","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"49035048-ff14-4e58-92b9-eb19797daf53","_cell_guid":"c7fface2-0f15-4cbc-b3a9-83d117b03150","trusted":true},"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path() # you can list the bucket with \"!gsutil ls $GCS_DS_PATH\"\n!gsutil ls $GCS_DS_PATH","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"e1e6920d-4306-4bc2-af18-c5e9111c8e9c","_cell_guid":"f32d3c5d-f0d6-48a5-aace-931f9894cd19","trusted":true},"cell_type":"markdown","source":"# Configuration","execution_count":null},{"metadata":{"_uuid":"1a9904e6-c158-4a69-be29-83c61450cf45","_cell_guid":"917231f0-3f4d-4bc5-a059-5276315570a1","trusted":true},"cell_type":"code","source":"IMAGE_SIZE = [512, 512] # At this size, a GPU will run out of memory. Use the TPU.\n                        # For GPU training, please select 224 x 224 px image size.\nEPOCHS = 30\nBATCH_SIZE = 32 * strategy.num_replicas_in_sync\n\nGCS_PATH_SELECT = { # available image sizes\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') # predictions on this dataset should be submitted for the competition\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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"dfe2ec31-3d06-4c64-89a3-dc05d8e0ea36","_cell_guid":"40c0dd09-1ac0-4cd5-85e0-e6d3a7eda0ca","trusted":true},"cell_type":"markdown","source":"## Visualization utilities\ndata -> pixels, nothing of much interest for the machine learning practitioner in this section.","execution_count":null},{"metadata":{"_uuid":"4a895cfb-9abc-4a85-a487-a609c2d2248d","_cell_guid":"c351f876-4b39-4d74-9950-f8534daf3bba","trusted":true},"cell_type":"code","source":"# numpy and matplotlib defaults\nnp.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    if numpy_labels.dtype == object: # binary string in this case, 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 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):\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 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()\n\ndef display_confusion_matrix(cmat, score, precision, recall):\n    plt.figure(figsize=(15,15))\n    ax = plt.gca()\n    ax.matshow(cmat, cmap='Reds')\n    ax.set_xticks(range(len(CLASSES)))\n    ax.set_xticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"left\", rotation_mode=\"anchor\")\n    ax.set_yticks(range(len(CLASSES)))\n    ax.set_yticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_yticklabels(), rotation=45, ha=\"right\", rotation_mode=\"anchor\")\n    titlestring = \"\"\n    if score is not None:\n        titlestring += 'f1 = {:.3f} '.format(score)\n    if precision is not None:\n        titlestring += '\\nprecision = {:.3f} '.format(precision)\n    if recall is not None:\n        titlestring += '\\nrecall = {:.3f} '.format(recall)\n    if len(titlestring) > 0:\n        ax.text(101, 1, titlestring, fontdict={'fontsize': 18, 'horizontalalignment':'right', 'verticalalignment':'top', 'color':'#804040'})\n    plt.show()\n    \ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"2f8db308-0f29-4020-a847-0b170bfe8410","_cell_guid":"e5923d41-6fa7-4a59-8f8a-7eb77085aa6b","trusted":true},"cell_type":"markdown","source":"# Datasets","execution_count":null},{"metadata":{"_uuid":"41e4d759-4536-43f5-ae03-e0a52fd1bee1","_cell_guid":"8a5df41c-2292-49f9-9911-fa54315e304b","trusted":true},"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) / 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\n\ndef data_augment(image, label):\n    # data augmentation. Thanks to the dataset.prefetch(AUTO) statement in the next function (below),\n    # this happens essentially for free on TPU. Data pipeline code is executed on the \"CPU\" part\n    # of the TPU while the TPU itself is computing gradients.\n    image = tf.image.random_flip_left_right(image)\n    image = tf.image.random_flip_up_down(image)\n#     image = tf.image.random_saturation(image,1,1.5)\n#     image = tf.image.adjust_brightness(image, 0.2)\n#     image = tf.image.rot90(image)\n    image = tf.image.central_crop(image, central_fraction=0.9)\n    image = tf.image.resize(image, [*IMAGE_SIZE])\n    return image, label\n\ndef get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES+VALIDATION_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(2040) #12753 #16465\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) # prefetch next batch while training (autotune prefetch buffer size)\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) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec 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+VALIDATION_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\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"c6e49afc-2bfb-4808-be49-57b0aaf4a576","_cell_guid":"b7c5165c-1b0f-4a95-871e-a3601210212a","trusted":true},"cell_type":"markdown","source":"# Dataset visualizations","execution_count":null},{"metadata":{"_uuid":"db372026-3daf-4bb8-ac81-b7b85aa0e921","_cell_guid":"25e64880-02b9-41ba-abb9-8f6ecc4836c7","trusted":true},"cell_type":"code","source":"# data dump\nprint(\"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(\"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(\"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')) # U=unicode string","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"39e4c07e-9732-4703-aa5f-46679c299eff","_cell_guid":"e7859570-6284-4132-acec-6de369c8a2ca","trusted":true},"cell_type":"code","source":"# Peek at training data\ntraining_dataset = get_training_dataset()\ntraining_dataset = training_dataset.unbatch().batch(20)\ntrain_batch = iter(training_dataset)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"657a4cce-988f-4c37-846c-28a01fb4a466","_cell_guid":"71063526-ac2b-4117-a3e0-03eeb64c31fe","trusted":true},"cell_type":"code","source":"# run this cell again for next set of images\ndisplay_batch_of_images(next(train_batch))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"843cb876-f180-4c23-af4f-21164ae24c68","_cell_guid":"920b0acf-fa46-4dea-87d8-a91e318fbf38","trusted":true},"cell_type":"code","source":"# peer at test data\ntest_dataset = get_test_dataset()\ntest_dataset = test_dataset.unbatch().batch(20)\ntest_batch = iter(test_dataset)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"0828486c-f056-4383-be8c-d7eaf0c53be3","_cell_guid":"bf1ee930-aa35-4255-b3c1-a9042e439afe","trusted":true},"cell_type":"code","source":"# run this cell again for next set of images\ndisplay_batch_of_images(next(test_batch))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3a7ce044-cbf9-43ed-b29a-9269e0faee59","_cell_guid":"24036955-acbd-46b4-ac2f-38100f43e006","trusted":true},"cell_type":"markdown","source":"# Model","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def lrfn(epoch):\n    LR_START = 0.00001\n    LR_MAX = 0.00005 * strategy.num_replicas_in_sync\n    LR_MIN = 0.00001\n    LR_RAMPUP_EPOCHS = 5\n    LR_SUSTAIN_EPOCHS = 8\n    LR_EXP_DECAY = .8\n    \n    if epoch < LR_RAMPUP_EPOCHS:\n        lr = (LR_MAX - LR_START) / LR_RAMPUP_EPOCHS * epoch + LR_START\n    elif epoch < LR_RAMPUP_EPOCHS + LR_SUSTAIN_EPOCHS:\n        lr = LR_MAX\n    else:\n        lr = (LR_MAX - LR_MIN) * LR_EXP_DECAY**(epoch - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS) + LR_MIN\n    return lr","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"f2f02d7b-0c62-4c10-b4b4-f32faa431fcb","_cell_guid":"293dbca2-e9e6-474b-ba56-9c9b02bc26c5","trusted":true},"cell_type":"code","source":"with strategy.scope():\n#     pretrained_model = tf.keras.applications.DenseNet201(weights='imagenet', include_top=False ,input_shape=[*IMAGE_SIZE, 3])\n#     pretrained_model = tf.keras.applications.Xception(weights='imagenet', include_top=False ,input_shape=[*IMAGE_SIZE, 3])\n#     pretrained_model = tf.keras.applications.VGG16(weights='imagenet', include_top=False ,input_shape=[*IMAGE_SIZE, 3])\n    pretrained_model = efn.EfficientNetB7(weights='noisy-student', include_top=False ,input_shape=[*IMAGE_SIZE, 3])\n    pretrained_model.trainable = True # False = transfer learning, True = fine-tuning\n\n#     set_trainable = False\n#     for layer in pretrained_model.layers:\n#         if layer.name in ['conv4_block1_0_bn', 'conv5_block1_0_bn']:\n#             set_trainable = True\n#         if set_trainable:\n#             layer.trainable = True\n#         else:\n#             layer.trainable = False\n    \n    model = tf.keras.Sequential([\n        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n#         tf.keras.layers.Dropout(0.7),\n#         tf.keras.layers.Dense(2*len(CLASSES),activation='relu',kernel_regularizer=tf.keras.regularizers.l2(0.01)),\n#         tf.keras.layers.Dropout(0.7),\n        tf.keras.layers.Dense(len(CLASSES),activation='softmax', activity_regularizer=tf.keras.regularizers.l2(0.01))\n    ])\n\n# lr_schedule = tf.keras.callbacks.LearningRateScheduler(\n#     lambda epoch: 1e-4 * 10**(epoch / 20))\n\nopt = tf.keras.optimizers.Adam(lr=0.0001, beta_1=0.9, beta_2=0.999, amsgrad=False)\n\nmodel.compile(\n    optimizer=opt,\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\n\nmodel.summary()\n\n# pretrained_model.summary()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d1f956c7-7f94-45e1-b10d-d224739be29b","_cell_guid":"5c56cf1a-e431-476e-9279-3e0146cbd0aa","trusted":true},"cell_type":"markdown","source":"# Training","execution_count":null},{"metadata":{"_uuid":"bc65eb6e-36e7-4197-a9c0-e805af56075c","_cell_guid":"b463b716-4b20-4fec-b97b-6fe683c836a3","trusted":true},"cell_type":"code","source":"# tf.keras.backend.clear_session()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b4fa73e5-1eec-4a9a-b9ef-0cbcc072baa7","_cell_guid":"99d5f30d-d724-4f75-99d3-3cbae50b4c9d","trusted":true},"cell_type":"code","source":"# history = model.fit(get_training_dataset(),\n#                     steps_per_epoch=STEPS_PER_EPOCH,\n#                     epochs=10,\n#                     validation_data=get_validation_dataset(),\n#                     callbacks=[lr_schedule]\n#                    )","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"618192ed-9d6b-402d-b763-2e0f7d38d85a","_cell_guid":"5baa9043-8aea-4e77-a2a8-978f3227b05e","trusted":true},"cell_type":"code","source":"# plt.semilogx(history.history[\"lr\"], history.history[\"loss\"])\n# plt.axis([1e-4, 3e-4, 0, 5])","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"edb111d9-a114-4afd-b67d-cad500c7e068","_cell_guid":"92047f0d-bc03-4651-b2f1-ab756090d556","trusted":true},"cell_type":"code","source":"tf.keras.backend.clear_session()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"954eeec5-a9dd-4c3b-8e93-3325085e0c16","_cell_guid":"2b567cc5-784d-4b34-bc15-e3cd509fbfa4","trusted":true},"cell_type":"code","source":"# optimizer = tf.keras.optimizers.Adam(lr=0.0001, beta_1=0.9, beta_2=0.999, amsgrad=False)\n    \n# model.compile(\n#     optimizer=optimizer,\n#     loss = 'sparse_categorical_crossentropy',\n#     metrics=['sparse_categorical_accuracy']\n# )\n\nlr_schedule = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=1)\n\nearly_stopping = tf.keras.callbacks.EarlyStopping(\n    monitor='val_loss', min_delta=0, patience=3, verbose=1, mode='auto',\n    baseline=None, restore_best_weights=True)\n\nhistory = model.fit(get_training_dataset(),\n                    steps_per_epoch=STEPS_PER_EPOCH,\n                    epochs=EPOCHS,\n                    validation_data=get_validation_dataset(),\n                   callbacks=[lr_schedule, early_stopping])","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"230fe5fc-cc94-440b-9392-9a1191b45ecd","_cell_guid":"d204dd54-5e8c-4cf8-9b03-16884617f611","trusted":true},"cell_type":"code","source":"display_training_curves(history.history['loss'], history.history['val_loss'], 'loss', 211)\ndisplay_training_curves(history.history['sparse_categorical_accuracy'], history.history['val_sparse_categorical_accuracy'], 'accuracy', 212)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"c786a410-eae1-43d3-a89a-076921237023","_cell_guid":"2a894111-39ac-41d8-a653-f459da62860b","trusted":true},"cell_type":"markdown","source":"# Confusion matrix","execution_count":null},{"metadata":{"_uuid":"d77a26f2-0275-4a4e-958f-9a9ef741cd08","_cell_guid":"8864b5ce-a34b-42a8-ab9c-d0af9de8b909","trusted":true},"cell_type":"code","source":"cmdataset = get_validation_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and labels, order matters.\nimages_ds = cmdataset.map(lambda image, label: image)\nlabels_ds = cmdataset.map(lambda image, label: label).unbatch()\ncm_correct_labels = next(iter(labels_ds.batch(NUM_VALIDATION_IMAGES))).numpy() # get everything as one batch\ncm_probabilities = model.predict(images_ds)\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)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"f7dc3baf-8efd-46b8-afbe-fbb761818a69","_cell_guid":"853254b0-06b8-4c79-af31-abffc136939b","trusted":true},"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 # normalized\ndisplay_confusion_matrix(cmat, score, precision, recall)\nprint('f1 score: {:.3f}, precision: {:.3f}, recall: {:.3f}'.format(score, precision, recall))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f095a85-9211-41f2-a2b5-73e69ae7d7af","_cell_guid":"6f14dd23-6f38-4835-9ab0-4536998d5bc5","trusted":true},"cell_type":"markdown","source":"# Predictions","execution_count":null},{"metadata":{"_uuid":"22d72dae-d91a-4b53-b6c3-a8795d8e83c7","_cell_guid":"69c534dd-2a03-4ec8-b14a-2025cce00ef8","trusted":true},"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\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)\n\nprint('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') # all in one batch\nnp.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')\n!head submission.csv","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d8bbc150-1c3f-4f4b-9e47-adcf84f62c0f","_cell_guid":"64a6b251-46f9-4a65-8b4f-ced553068d8b","trusted":true},"cell_type":"markdown","source":"# Visual validation","execution_count":null},{"metadata":{"_uuid":"4970e37f-b661-4679-9f0e-9f10ecc43c98","_cell_guid":"3759529d-3b7c-48d0-ac43-b3d3d54de6ac","trusted":true},"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"f1a7036d-5314-4275-857b-0383ce85d819","_cell_guid":"c922c348-a134-4206-9d8a-985b85958c4c","trusted":true},"cell_type":"code","source":"# run this cell again for next set of images\nimages, labels = next(batch)\nprobabilities = model.predict(images)\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"5ec17fe0-5034-490c-b1c1-a8e6ebe450af","_cell_guid":"194ec425-8219-45a2-9b98-bd53a711fe67","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}