{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import random, re, math\nimport numpy as np, pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\nimport tensorflow as tf, tensorflow.keras.backend as K\nfrom kaggle_datasets import KaggleDatasets\nprint('Tensorflow version ' + tf.__version__)\nfrom sklearn.model_selection import KFold","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"try:\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":{"trusted":true},"cell_type":"code","source":"AUTO = tf.data.experimental.AUTOTUNE\n# Configuration\nIMAGE_SIZE = [224, 224]\nEPOCHS = 5\nFOLDS = 3\nSEED = 777\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\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}\n\nGCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]]\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec') + tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**CLASSES**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"CLASSES = ['pink primrose',    'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea',     'wild geranium',     'tiger lily',           'moon orchid',              'bird of paradise', 'monkshood',        'globe thistle',         # 00 - 09\n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily', # 10 - 19\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',         # 20 - 29\n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',           # 30 - 39\n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',      # 40 - 49\n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',    # 50 - 59\n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',            # 60 - 69\n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',             # 70 - 79\n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',            # 80 - 89\n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',        # 90 - 99\n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']                                                                                                                                               # 100 - 102","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**CUSTOM LR SHEDULER**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# 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 = 5\nLR_SUSTAIN_EPOCHS = 0\nLR_EXP_DECAY = .8\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(25 if EPOCHS<25 else 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":{},"cell_type":"markdown","source":"**DATASET FUNCTIONS**","execution_count":null},{"metadata":{"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    # Diregarding 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) # use 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) # returns a dataset of (image, label) pairs if labeled = True or (image, id) pair if labeld = 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    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 = int( count_data_items(TRAINING_FILENAMES) * (FOLDS-1.)/FOLDS )\nNUM_VALIDATION_IMAGES = int( count_data_items(TRAINING_FILENAMES) * (1./FOLDS) )\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\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":"**DATA AUGMENTATION**","execution_count":null},{"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))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"row = 3; col = 4;\nall_elements = get_training_dataset(load_dataset(TRAINING_FILENAMES),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":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.applications import DenseNet201\n\ndef get_model():\n    with strategy.scope():\n        rnet = DenseNet201(\n            input_shape=(IMAGE_SIZE[0], IMAGE_SIZE[1], 3),\n            weights='imagenet',\n            include_top=False\n        )\n        # trainable rnet\n        rnet.trainable = True\n        model = tf.keras.Sequential([\n            rnet,\n            tf.keras.layers.GlobalAveragePooling2D(),\n            tf.keras.layers.Dense(len(CLASSES), activation='softmax',dtype='float32')\n        ])\n    model.compile(\n        optimizer='adam',\n        loss = 'sparse_categorical_crossentropy',\n        metrics=['sparse_categorical_accuracy']\n    )\n    return model\n\ndef train_cross_validate(folds = 5):\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 = 5):\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('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')\n    return histories, models\n    \n# run train and predict\nhistories, models = train_and_predict(folds = FOLDS)","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}