{"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":"import math\nimport re\n\n!pip install -q efficientnet\nimport efficientnet.tfkeras as efn\nimport numpy as np\nimport tensorflow as tf\nfrom kaggle_datasets import KaggleDatasets\nfrom matplotlib import pyplot as plt\nfrom sklearn.metrics import confusion_matrix, f1_score, precision_score, recall_score","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","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    strategy = tf.distribute.get_strategy()\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load dataset\nIMAGE_SIZE = [512, 512]\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nGCS_PATH_SELECT = {\n    192: GCS_DS_PATH + '/tfrecords-jpeg-192x192',\n    224: GCS_DS_PATH + '/tfrecords-jpeg-224x224',\n    331: GCS_DS_PATH + '/tfrecords-jpeg-331x331',\n    512: GCS_DS_PATH + '/tfrecords-jpeg-512x512'\n}\nGCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]]\nAUTO = tf.data.experimental.AUTOTUNE\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec')\n\nCLASSES = ['pink primrose', 'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea', 'wild geranium', 'tiger lily', 'moon orchid', 'bird of paradise', 'monkshood', 'globe thistle',  # 00 - 09\n           'snapdragon', \"colt's foot\", 'king protea', 'spear thistle', 'yellow iris', 'globe-flower', 'purple coneflower', 'peruvian lily', 'balloon flower', 'giant white arum lily',  # 10 - 19\n           'fire lily', 'pincushion flower', 'fritillary', 'red ginger', 'grape hyacinth', 'corn poppy', 'prince of wales feathers', 'stemless gentian', 'artichoke', 'sweet william',  # 20 - 29\n           'carnation', 'garden phlox', 'love in the mist', 'cosmos', 'alpine sea holly', 'ruby-lipped cattleya', 'cape flower', 'great masterwort', 'siam tulip', 'lenten rose',  # 30 - 39\n           'barberton daisy', 'daffodil', 'sword lily', 'poinsettia', 'bolero deep blue', 'wallflower', 'marigold', 'buttercup', 'daisy', 'common dandelion',  # 40 - 49\n           'petunia', 'wild pansy', 'primula', 'sunflower', 'lilac hibiscus', 'bishop of llandaff', 'gaura', 'geranium', 'orange dahlia', 'pink-yellow dahlia',  # 50 - 59\n           'cautleya spicata', 'japanese anemone', 'black-eyed susan', 'silverbush', 'californian poppy', 'osteospermum', 'spring crocus', 'iris', 'windflower', 'tree poppy',  # 60 - 69\n           'gazania', 'azalea', 'water lily', 'rose', 'thorn apple', 'morning glory', 'passion flower', 'lotus', 'toad lily', 'anthurium',  # 70 - 79\n           'frangipani', 'clematis', 'hibiscus', 'columbine', 'desert-rose', 'tree mallow', 'magnolia', 'cyclamen ', 'watercress', 'canna lily',  # 80 - 89\n           'hippeastrum ', 'bee balm', 'pink quill', 'foxglove', 'bougainvillea', 'camellia', 'mallow', 'mexican petunia', 'bromelia', 'blanket flower',  # 90 - 99\n           'trumpet creeper', 'blackberry lily', 'common tulip', 'wild rose']  # 100 - 102\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\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\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\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\n    # Returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Data augmentation\ndef random_blockout(img, sl=0.1, sh=0.2, rl=0.4):\n    p = np.random.random()\n    if p >= 0.25:\n        w, h, c = IMAGE_SIZE[0], IMAGE_SIZE[1], 3\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    else:\n        return tf.cast(img, img.dtype)\n\n\ndef data_augment(image, label):\n    image = tf.image.random_flip_left_right(image)\n    image = tf.image.random_brightness(image, 0.1)\n    image = tf.image.random_contrast(image, 0.8, 1.2)\n    image = tf.image.random_saturation(image, 0.7, 1.3)\n    image = random_blockout(image)\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\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\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\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\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: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","metadata":{"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\nds_train = get_training_dataset()\nds_valid = get_validation_dataset()\nds_test = get_test_dataset()\n\nprint(\"Training:\", ds_train)\nprint(\"Validation:\", ds_valid)\nprint(\"Test:\", ds_test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Explore training dataset\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 the case for test data)\n    return numpy_images, numpy_labels\n\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(\n        CLASSES[label],\n        'OK' if correct else 'NO',\n        u\"\\u2192\" if not correct else '',\n        CLASSES[correct_label] if not correct else ''\n    ), correct\n\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,\n                  fontsize=int(titlesize) if not red else int(titlesize / 1.2),\n                  color='red' if red else 'black',\n                  fontdict={'verticalalignment': 'center'},\n                  pad=int(titlesize / 1.5))\n    return subplot[0], subplot[1], subplot[2] + 1\n\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\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        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\n# Peek at training data\nds_iter = iter(ds_train.unbatch().batch(20))\none_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Explore test dataset\ntest_dataset = get_test_dataset()\ntest_dataset = test_dataset.unbatch().batch(20)\ntest_batch = iter(test_dataset)\ndisplay_batch_of_images(next(test_batch))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define model with pretrained weights\nwith strategy.scope():\n    eff_net = efn.EfficientNetB7(input_shape=[*IMAGE_SIZE, 3], weights='imagenet', include_top=False)\n    eff_net.trainable = True\n\n    model = tf.keras.Sequential([\n        eff_net,\n        tf.keras.layers.Dropout(0.3),\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.BatchNormalization(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\nmodel.compile(\n    optimizer='adam',\n    loss='sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n)\n\nmodel.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define training epochs\nEPOCHS = 35\n\n# Learning Rate Schedule for Fine Tuning #\ndef exponential_lr(epoch, start_lr=0.00001, min_lr=0.00001, max_lr=0.00005, rampup_epochs=5, sustain_epochs=0, exp_decay=0.8):\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) / 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) * exp_decay ** (epoch - rampup_epochs - sustain_epochs) + min_lr)\n        return lr\n\n    return lr(epoch, start_lr, min_lr, max_lr, rampup_epochs, sustain_epochs, exp_decay)\n\n\nlr_callback = tf.keras.callbacks.LearningRateScheduler(exponential_lr, verbose=True)\n\nrng = [i for i in range(EPOCHS)]\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":"# Training\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(ds_train, validation_data=ds_valid, epochs=EPOCHS, steps_per_epoch=STEPS_PER_EPOCH, callbacks=[lr_callback])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Display model accuracy and loss\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_xlabel('epoch')\n    ax.legend(['train', 'valid.'])\n\n    \ndisplay_training_curves(history.history['sparse_categorical_accuracy'], history.history['val_sparse_categorical_accuracy'], 'accuracy', 211)\ndisplay_training_curves(history.history['loss'], history.history['val_loss'], 'loss', 212)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Construct confusion matrix\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\n\ncmdataset = 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(cm_correct_labels, cm_predictions, labels=labels)\ncmat = (cmat.T / cmat.sum(axis=1)).T  # normalize\n\nscore = f1_score(cm_correct_labels, cm_predictions, labels=labels, average='macro')\nprecision = precision_score(cm_correct_labels, cm_predictions, labels=labels, average='macro')\nrecall = recall_score(cm_correct_labels, cm_predictions, labels=labels, average='macro')\ndisplay_confusion_matrix(cmat, score, precision, recall)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Display one batch of validation\ndataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)\n\nimages, labels = next(batch)\nprobabilities = model.predict(images)\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Predict test dataset\ntest_ds = get_test_dataset(ordered=True)\n\ntest_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = model.predict(test_images_ds)\npredictions = np.argmax(probabilities, axis=-1)\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('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}