{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import math, re, os, random\nimport tensorflow as tf, tensorflow.keras.backend as K\nimport numpy as np, pandas as pd\nfrom matplotlib import pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\nfrom sklearn.model_selection import KFold\nprint(\"Tensorflow version \" + tf.__version__)\nAUTO = tf.data.experimental.AUTOTUNE","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# TPU or GPU detection"},{"metadata":{"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":{},"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."},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path() # you can list the bucket with \"!gsutil ls $GCS_DS_PATH\"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Configuration"},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE = [512, 512] # at this size, a GPU will run out of memory. Use the TPU\nBATCH_SIZE = 16 * 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":{},"cell_type":"markdown","source":"## Visualization utilities\ndata -> pixels, nothing of much interest for the machine learning practitioner in this section."},{"metadata":{"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":{},"cell_type":"markdown","source":"# Dataset Functions"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","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_saturation(image, 0, 2)\n    return image, label   \n\ndef get_training_dataset(dataset, do_aug=True):\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n    if do_aug: dataset = dataset.map(transform, 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(dataset):\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)\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":{},"cell_type":"markdown","source":"From https://www.kaggle.com/cdeotte/rotation-augmentation-gpu-tpu-0-96\n# Data Augmentation\n\nThe following code does random rotations, shear, zoom, and shift using the GPU/TPU. When an image gets moved away from an edge revealing blank space, the blank space is filled by stretching the colors on the original edge. Change the variables in function transform() below to control the desired amount of augmentation. Here's a diagram illustrating the mathematics."},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_mat(rotation, shear, height_zoom, width_zoom, height_shift, width_shift):\n    # returns 3x3 transformmatrix which transforms indicies\n        \n    # CONVERT DEGREES TO RADIANS\n    rotation = math.pi * rotation / 180.\n    shear = math.pi * shear / 180.\n    \n    # ROTATION MATRIX\n    c1 = tf.math.cos(rotation)\n    s1 = tf.math.sin(rotation)\n    one = tf.constant([1],dtype='float32')\n    zero = tf.constant([0],dtype='float32')\n    rotation_matrix = tf.reshape( tf.concat([c1,s1,zero, -s1,c1,zero, zero,zero,one],axis=0),[3,3] )\n        \n    # SHEAR MATRIX\n    c2 = tf.math.cos(shear)\n    s2 = tf.math.sin(shear)\n    shear_matrix = tf.reshape( tf.concat([one,s2,zero, zero,c2,zero, zero,zero,one],axis=0),[3,3] )    \n    \n    # ZOOM MATRIX\n    zoom_matrix = tf.reshape( tf.concat([one/height_zoom,zero,zero, zero,one/width_zoom,zero, zero,zero,one],axis=0),[3,3] )\n    \n    # SHIFT MATRIX\n    shift_matrix = tf.reshape( tf.concat([one,zero,height_shift, zero,one,width_shift, zero,zero,one],axis=0),[3,3] )\n    \n    return K.dot(K.dot(rotation_matrix, shear_matrix), K.dot(zoom_matrix, shift_matrix))\n\ndef transform(image,label):\n    # input image - is one image of size [dim,dim,3] not a batch of [b,dim,dim,3]\n    # output - image randomly rotated, sheared, zoomed, and shifted\n    DIM = IMAGE_SIZE[0]\n    XDIM = DIM%2 #fix for size 331\n    \n    rot = 15. * tf.random.normal([1],dtype='float32')\n    shr = 5. * tf.random.normal([1],dtype='float32') \n    h_zoom = 1.0 + tf.random.normal([1],dtype='float32')/10.\n    w_zoom = 1.0 + tf.random.normal([1],dtype='float32')/10.\n    h_shift = 16. * tf.random.normal([1],dtype='float32') \n    w_shift = 16. * tf.random.normal([1],dtype='float32') \n  \n    # GET TRANSFORMATION MATRIX\n    m = get_mat(rot,shr,h_zoom,w_zoom,h_shift,w_shift) \n\n    # LIST DESTINATION PIXEL INDICES\n    x = tf.repeat( tf.range(DIM//2,-DIM//2,-1), DIM )\n    y = tf.tile( tf.range(-DIM//2,DIM//2),[DIM] )\n    z = tf.ones([DIM*DIM],dtype='int32')\n    idx = tf.stack( [x,y,z] )\n    \n    # ROTATE DESTINATION PIXELS ONTO ORIGIN PIXELS\n    idx2 = K.dot(m,tf.cast(idx,dtype='float32'))\n    idx2 = K.cast(idx2,dtype='int32')\n    idx2 = K.clip(idx2,-DIM//2+XDIM+1,DIM//2)\n    \n    # FIND ORIGIN PIXEL VALUES           \n    idx3 = tf.stack( [DIM//2-idx2[0,], DIM//2-1+idx2[1,]] )\n    d = tf.gather_nd(image,tf.transpose(idx3))\n        \n    return tf.reshape(d,[DIM,DIM,3]),label","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Display Example Augmentation\n\nBelow are examples of 3 training images where each is randomly augmented 12 different times."},{"metadata":{"trusted":true},"cell_type":"code","source":"row = 3; col = 4;\nall_elements = get_training_dataset(load_dataset(TRAINING_FILENAMES), \n                                    do_aug=False).unbatch()\none_element = tf.data.Dataset.from_tensors(next(iter(all_elements)))\naugmented_element = one_element.repeat().map(transform).batch(row*col)\n\nfor (img,label) in augmented_element:\n    plt.figure(figsize=(15,int(15*row/col)))\n    for j in range(row*col):\n        plt.subplot(row,col,j+1)\n        plt.axis('off')\n        plt.imshow(img[j,])\n    plt.show()\n    break","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Model with EfficientNetB7"},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -q efficientnet\n\nimport efficientnet.tfkeras as efn\n\n# Need this line so Google will recite some incantations\n# for Turing to magically load the model onto the TPU\ndef get_model():\n    with strategy.scope():\n        enet = efn.EfficientNetB7(\n            input_shape=(IMAGE_SIZE[0], IMAGE_SIZE[1], 3),\n            weights='imagenet',\n            include_top=False\n        )\n    \n        enet.trainable = True\n\n        model = tf.keras.Sequential([\n            enet,\n            tf.keras.layers.GlobalAveragePooling2D(),\n            tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n        ])\n            \n    model.compile(\n        optimizer=tf.keras.optimizers.Adam(lr=0.0001),\n        loss = 'sparse_categorical_crossentropy',\n        metrics=['sparse_categorical_accuracy']\n    )\n    return model\n\nget_model().summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Custom LR schedule\n\nBorrowed from five flowers in TPU doc"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Model config\n# Reduced number of EPOCHS and FOLDS so that everything fits in memory\n# If we could summarise the model and free memory as we go, then we could increase them again\nEPOCHS = 10\nFOLDS = 2\nSEED = 777\n\n# Learning rate schedule for TPU, GPU and CPU.\n# Using an LR ramp up because fine-tuning a pre-trained model.\n# Starting with a high LR would break the pre-trained weights.\n\nLR_START = 0.00001\nLR_MAX = 0.00005 * strategy.num_replicas_in_sync\nLR_MIN = 0.00001\nLR_RAMPUP_EPOCHS = 3\nLR_SUSTAIN_EPOCHS = 0\nLR_EXP_DECAY = .67\n\ndef lrfn(epoch):\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\n\nlr_callback = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=True)\n\nrng = [i for i in range(EPOCHS)]\ny = [lrfn(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]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"From https://www.kaggle.com/cdeotte/rotation-augmentation-gpu-tpu-0-96\n# Build, Train, Infer Model\n\nThis is the 5-Fold workflow copied from Ragnar's notebook here. Now we add data augmentation to the training images on the fly! Notice how his notebook completes epochs in 70 seconds using TPU. This notebook also completes epochs in 70 seconds (when we turn on TPU) and we are augmentating every image! Augmenting a single image requires 5,000,000 calculations (a batch requires 600,000,000 calculations!) We see that our augmentation is occuring as fast as the GPU/TPU training! We are augmenting 200+ images per second. In other words we are performing 1,000,000,000 calculations per second in addition to normal training computation! Wow!"},{"metadata":{"trusted":true},"cell_type":"code","source":"def train_cross_validate(folds=FOLDS):\n    histories = []\n    models = []\n    early_stopping = tf.keras.callbacks.EarlyStopping(monitor = 'val_loss', patience = 3)\n    kfold = KFold(folds, shuffle = True, random_state = SEED)\n    for f, (trn_ind, val_ind) in enumerate(kfold.split(TRAINING_FILENAMES)):\n        print(); print('#'*25)\n        print('### FOLD',f+1)\n        print('#'*25)\n        train_dataset = load_dataset(list(pd.DataFrame({'TRAINING_FILENAMES': TRAINING_FILENAMES}).loc[trn_ind]['TRAINING_FILENAMES']), labeled = True)\n        val_dataset = load_dataset(list(pd.DataFrame({'TRAINING_FILENAMES': TRAINING_FILENAMES}).loc[val_ind]['TRAINING_FILENAMES']), labeled = True, ordered = True)\n        model = get_model()\n        history = model.fit(\n            get_training_dataset(train_dataset), \n            steps_per_epoch = STEPS_PER_EPOCH,\n            epochs = EPOCHS,\n            callbacks = [lr_callback],#, early_stopping],\n            validation_data = get_validation_dataset(val_dataset),\n            verbose=2\n        )\n        models.append(model)\n        histories.append(history)\n    return histories, models\n\ndef train_and_predict(folds=FOLDS):\n    test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\n    test_images_ds = test_ds.map(lambda image, idnum: image)\n    print('Start training %i folds'%folds)\n    histories, models = train_cross_validate(folds=folds)\n    print('Computing predictions...')\n    # get the mean probability of the folds models\n    probabilities = np.average([models[i].predict(test_images_ds) for i in range(folds)], axis = 0)\n    predictions = np.argmax(probabilities, axis=-1)\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(\n        'submission.csv', \n        np.rec.fromarrays([test_ids, predictions]), \n        fmt=['%s', '%d'], delimiter=',', \n        header='id,label', \n        comments=''\n    )\n    return histories, models\n    \n# run train and predict\nhistories, models = train_and_predict(folds=FOLDS)\n!head submission.csv","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Confusion Matrix and Validation Score\nTry forking and modifying this notebook to maximize validation score below. Tune the data augmentation and/or train for more epochs to increase accuracy. Good luck! (Code below is from starter kernel)."},{"metadata":{"trusted":true},"cell_type":"code","source":"def display_confusion_matrix(cmat, score, precision, recall):\n    plt.figure(figsize=(15,15))\n    ax = plt.gca()\n    ax.matshow(cmat, cmap='Reds')\n    ax.set_xticks(range(len(CLASSES)))\n    ax.set_xticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"left\", rotation_mode=\"anchor\")\n    ax.set_yticks(range(len(CLASSES)))\n    ax.set_yticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_yticklabels(), rotation=45, ha=\"right\", rotation_mode=\"anchor\")\n    titlestring = \"\"\n    if score is not None:\n        titlestring += 'f1 = {:.3f} '.format(score)\n    if precision is not None:\n        titlestring += '\\nprecision = {:.3f} '.format(precision)\n    if recall is not None:\n        titlestring += '\\nrecall = {:.3f} '.format(recall)\n    if len(titlestring) > 0:\n        ax.text(101, 1, titlestring, fontdict={'fontsize': 18, 'horizontalalignment':'right', 'verticalalignment':'top', 'color':'#804040'})\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nall_labels = []; all_prob = []; all_pred = []\nkfold = KFold(FOLDS, shuffle = True, random_state = SEED)\nfor j, (trn_ind, val_ind) in enumerate( kfold.split(TRAINING_FILENAMES) ):\n    print('Inferring fold',j+1,'validation images...')\n    VAL_FILES = list(pd.DataFrame({'TRAINING_FILENAMES': TRAINING_FILENAMES}).loc[val_ind]['TRAINING_FILENAMES'])\n    NUM_VALIDATION_IMAGES = count_data_items(VAL_FILES)\n    cmdataset = get_validation_dataset(load_dataset(VAL_FILES, labeled = True, ordered = True))\n    images_ds = cmdataset.map(lambda image, label: image)\n    labels_ds = cmdataset.map(lambda image, label: label).unbatch()\n    all_labels.append( next(iter(labels_ds.batch(NUM_VALIDATION_IMAGES))).numpy() ) # get everything as one batch\n    prob = models[j].predict(images_ds)\n    all_prob.append( prob )\n    all_pred.append( np.argmax(prob, axis=-1) )\ncm_correct_labels = np.concatenate(all_labels)\ncm_probabilities = np.concatenate(all_prob)\ncm_predictions = np.concatenate(all_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Correct   labels: \", cm_correct_labels.shape, cm_correct_labels)\nprint(\"Predicted labels: \", cm_predictions.shape, cm_predictions)","execution_count":null,"outputs":[]},{"metadata":{"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')\ndisplay_confusion_matrix(cmat, score, precision, recall)\nprint('f1 score: {:.3f}, precision: {:.3f}, recall: {:.3f}'.format(score, precision, recall))","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":1}