{"cells":[{"metadata":{},"cell_type":"markdown","source":"\n# Introduction #\n\nThis is my second notebook for this competition - don't expect any revelations, I'm still learning. This is a copy of the getting-started notebook by @ryanholbrook. I wanted to check one thing in particular: What is the effect of the learning rate scheduler? This part of the original notebook was not explained at all, unfortunately. So let's take the original model twice and train it with and without the scheduler and see the effect."},{"metadata":{},"cell_type":"markdown","source":"# Imports, Distribution Strategy, Data Loading#\n\nFirst, let's get the boiler plate stuff out of the way"},{"metadata":{"trusted":true},"cell_type":"code","source":"import math, re, os\nimport numpy as np\nimport tensorflow as tf\n\nprint(\"Tensorflow version \" + tf.__version__)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"A TPU has eight different *cores* and each of these cores acts as its own accelerator. (A TPU is sort of like having eight GPUs in one machine.) We tell TensorFlow how to make use of all these cores at once through a **distribution strategy**. Run the following cell to create the distribution strategy that we'll later apply to our model."},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"We'll use the distribution strategy when we create our neural network model. Then, TensorFlow will distribute the training among the eight TPU cores by creating eight different *replicas* of the model, one for each core.\n\nWhen used with TPUs, datasets need to be stored in a [Google Cloud Storage bucket](https://cloud.google.com/storage/). You can use data from any public GCS bucket by giving its path just like you would data from `'/kaggle/input'`. The following will retrieve the GCS path for this competition's dataset."},{"metadata":{"trusted":true},"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nprint(GCS_DS_PATH) # what do gcs paths look like?","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"You can use data from any public dataset here on Kaggle in just the same way. If you'd like to use data from one of your private datasets, see [here](https://www.kaggle.com/docs/tpu#tpu3pt5).\n\n## Load Data ##\n\nWhen used with TPUs, datasets are often serialized into [TFRecords](https://www.kaggle.com/ryanholbrook/tfrecords-basics). This is a format convenient for distributing data to each of the TPUs cores. We've hidden the cell that reads the TFRecords for our dataset since the process is a bit long. You could come back to it later for some guidance on using your own datasets with TPUs."},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"\nIMAGE_SIZE = [512, 512]\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-512x512'\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\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","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Create Data Pipelines ##\n\nIn this final step we'll use the `tf.data` API to define an efficient data pipeline for each of the training, validation, and test splits."},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"\ndef data_augment(image, label):\n    # Thanks to the dataset.prefetch(AUTO)\n    # statement in the next function (below), this happens essentially\n    # for free on TPU. Data pipeline code is executed on the \"CPU\"\n    # part of the TPU while the TPU itself is computing gradients.\n    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():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n    dataset = dataset.repeat() # the training dataset must repeat for several epochs\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\ndef get_validation_dataset(ordered=False):\n    dataset = load_dataset(VALIDATION_FILENAMES, labeled=True, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(TEST_FILENAMES, labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec\n    # files, i.e. flowers00-230.tfrec = 230 data items\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"This next cell will create the datasets that we'll use with Keras during training and inference. Notice how we scale the size of the batches to the number of TPU cores."},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"These datasets are `tf.data.Dataset` objects. You can think about a dataset in TensorFlow as a *stream* of data records. The training and validation sets are streams of `(image, label)` pairs."},{"metadata":{"trusted":true},"cell_type":"code","source":"np.set_printoptions(threshold=15, linewidth=80)\n\nprint(\"Training data shapes:\")\nfor image, label in ds_train.take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training data label examples:\", label.numpy())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The test set is a stream of `(image, idnum)` pairs; `idnum` here is the unique identifier given to the image that we'll use later when we make our submission as a `csv` file."},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Test data shapes:\")\nfor image, idnum in ds_test.take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test data IDs:\", idnum.numpy().astype('U')) # U=unicode string","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Let's take a moment to look at some of the images in the dataset."},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"\nfrom matplotlib import pyplot as plt\n\ndef batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    if numpy_labels.dtype == object: # binary string in this case,\n                                     # these are image ID strings\n        numpy_labels = [None for _ in enumerate(numpy_images)]\n    # If no labels, only image IDs, return None for labels (this is\n    # the case for test data)\n    return numpy_images, numpy_labels\n\ndef title_from_label_and_target(label, correct_label):\n    if correct_label is None:\n        return CLASSES[label], True\n    correct = (label == correct_label)\n    return \"{} [{}{}{}]\".format(CLASSES[label], 'OK' if correct else 'NO', u\"\\u2192\" if not correct else '',\n                                CLASSES[correct_label] if not correct else ''), correct\n\ndef display_one_flower(image, title, subplot, red=False, titlesize=16):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n    return (subplot[0], subplot[1], subplot[2]+1)\n    \ndef display_batch_of_images(databatch, predictions=None):\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\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":"You can display a single batch of images from a dataset with another of our helper functions. The next cell will turn the dataset into an iterator of batches of 20 images."},{"metadata":{"trusted":true},"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(20))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Use the Python `next` function to pop out the next batch in the stream and display it with the helper function."},{"metadata":{"trusted":true},"cell_type":"code","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"By defining `ds_iter` and `one_batch` in separate cells, you only need to rerun the cell above to see a new batch of images."},{"metadata":{},"cell_type":"markdown","source":"# 1: Get baseline performance with VGG16 model #\n\nThis is the model that is included in the getting started notebook - it's just a headless VGG16 with a GlobalAveragePooling2D and a Dense output layer. The very modest goal here is to improve upon this."},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 12\n\nwith strategy.scope():\n    pretrained_model_vgg16 = tf.keras.applications.VGG16(\n        weights='imagenet',\n        include_top=False ,\n        input_shape=[*IMAGE_SIZE, 3]\n    )\n    pretrained_model_vgg16.trainable = False\n    \n    model_1 = tf.keras.Sequential([\n        # To a base pretrained on ImageNet to extract features from images...\n        pretrained_model_vgg16,\n        # ... attach a new head to act as a classifier.\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The `'sparse_categorical'` versions of the loss and metrics are appropriate for a classification task with more than two labels, like this one."},{"metadata":{"trusted":true},"cell_type":"code","source":"model_1.compile(\n    optimizer='adam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n)\n\nmodel_1.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Training\n\n### Learning Rate Schedule\n\nWe'll train this network with a special learning rate schedule."},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"\n# Learning Rate Schedule for Fine Tuning #\ndef exponential_lr(epoch,\n                   start_lr = 0.00001, min_lr = 0.00001, max_lr = 0.00005,\n                   rampup_epochs = 5, sustain_epochs = 0,\n                   exp_decay = 0.8):\n\n    def lr(epoch, start_lr, min_lr, max_lr, rampup_epochs, sustain_epochs, exp_decay):\n        # linear increase from start to rampup_epochs\n        if epoch < rampup_epochs:\n            lr = ((max_lr - start_lr) /\n                  rampup_epochs * epoch + start_lr)\n        # constant max_lr during sustain_epochs\n        elif epoch < rampup_epochs + sustain_epochs:\n            lr = max_lr\n        # exponential decay towards min_lr\n        else:\n            lr = ((max_lr - min_lr) *\n                  exp_decay**(epoch - rampup_epochs - sustain_epochs) +\n                  min_lr)\n        return lr\n    return lr(epoch,\n              start_lr,\n              min_lr,\n              max_lr,\n              rampup_epochs,\n              sustain_epochs,\n              exp_decay)\n\nlr_callback = tf.keras.callbacks.LearningRateScheduler(exponential_lr, verbose=True)\n\nrng = [i for i in range(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]))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Fit Model ##\n\nAnd now we're ready to train the model. After defining a few parameters, we're good to go!"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Define training epochs\nEPOCHS = 12\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory_1 = model_1.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    steps_per_epoch=STEPS_PER_EPOCH,\n    callbacks=[lr_callback],\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"This next cell shows how the loss and metrics progressed during training. Thankfully, it converges!"},{"metadata":{"trusted":true},"cell_type":"code","source":"display_training_curves(\n    history_1.history['loss'],\n    history_1.history['val_loss'],\n    'loss',\n    211,\n)\ndisplay_training_curves(\n    history_1.history['sparse_categorical_accuracy'],\n    history_1.history['val_sparse_categorical_accuracy'],\n    'accuracy',\n    212,\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history_1.history['val_sparse_categorical_accuracy'][-1]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Evaluate Predictions\n\nBefore making your final predictions on the test set, it's a good idea to evaluate your model's predictions on the validation set. This can help you diagnose problems in training or suggest ways your model could be improved. We'll look at two common ways of validation: plotting the **confusion matrix** and **visual validation**."},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"\nimport matplotlib.pyplot as plt\nfrom sklearn.metrics import f1_score, precision_score, recall_score, accuracy_score, confusion_matrix\n\ndef display_confusion_matrix(cmat, accuracy, 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 accuracy is not None:\n        titlestring += 'accuracy = {:.3f} '.format(accuracy)\n    if score is not None:\n        titlestring += '\\nf1 = {:.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":"You might be familiar with metrics like [F1-score](https://en.wikipedia.org/wiki/F1_score) or [precision and recall](https://en.wikipedia.org/wiki/Precision_and_recall). This cell will compute these metrics and display them with a plot of the confusion matrix. (These metrics are defined in the Scikit-learn module `sklearn.metrics`; we've imported them in the helper script for you.)"},{"metadata":{"trusted":true},"cell_type":"code","source":"def make_confusion_matrix(model):\n    cmdataset = get_validation_dataset(ordered=True)\n    images_ds = cmdataset.map(lambda image, label: image)\n    labels_ds = cmdataset.map(lambda image, label: label).unbatch()\n\n    cm_correct_labels = next(iter(labels_ds.batch(NUM_VALIDATION_IMAGES))).numpy()\n    cm_probabilities = model.predict(images_ds)\n    cm_predictions = np.argmax(cm_probabilities, axis=-1)\n\n    labels = range(len(CLASSES))\n    cmat = confusion_matrix(\n        cm_correct_labels,\n        cm_predictions,\n        labels=labels\n    )\n    cmat = (cmat.T / cmat.sum(axis=1)).T\n    accuracy = accuracy_score(\n        cm_correct_labels,\n        cm_predictions\n    )\n    score = f1_score(\n        cm_correct_labels,\n        cm_predictions,\n        labels=labels,\n        average='macro',\n    )\n    precision = precision_score(\n        cm_correct_labels,\n        cm_predictions,\n        labels=labels,\n        average='macro',\n    )\n    recall = recall_score(\n        cm_correct_labels,\n        cm_predictions,\n        labels=labels,\n        average='macro',\n    )\n    display_confusion_matrix(cmat, accuracy, score, precision, recall)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"make_confusion_matrix(model_1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Looking at the confusion matrix, the model is not doing a good job - there should be a clear diagonal visible, but there is not.**"},{"metadata":{},"cell_type":"markdown","source":"# 2: Check what the learning rate scheduler does\n\nUnfortunately, the learning rate scheduler in the getting-started notebook was not explained. So let's find out what happens if we train the same model without it."},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 50\n\nwith strategy.scope():\n    pretrained_model_vgg16 = tf.keras.applications.VGG16(\n        weights='imagenet',\n        include_top=False ,\n        input_shape=[*IMAGE_SIZE, 3]\n    )\n    pretrained_model_vgg16.trainable = False\n    \n    model_1a = tf.keras.Sequential([\n        # To a base pretrained on ImageNet to extract features from images...\n        pretrained_model_vgg16,\n        # ... attach a new head to act as a classifier.\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nmodel_1a.compile(\n    optimizer='adam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n)\n\nhistory_1a = model_1a.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    steps_per_epoch=STEPS_PER_EPOCH\n    # got rid of learning rate callback here\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"display_training_curves(\n    history_1a.history['loss'],\n    history_1a.history['val_loss'],\n    'loss',\n    211,\n)\ndisplay_training_curves(\n    history_1a.history['sparse_categorical_accuracy'],\n    history_1a.history['val_sparse_categorical_accuracy'],\n    'accuracy',\n    212,\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"make_confusion_matrix(model_1a)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Conclusion\n**It seems that ditching the learning rate scheduler (and increasing the number of epochs) really helps to increase the performance!**"},{"metadata":{},"cell_type":"markdown","source":"# Submit a prediction using the improved model"},{"metadata":{"trusted":true},"cell_type":"code","source":"def to_float32(image, label):\n    return tf.cast(image, tf.float32), label\n\ntest_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\ntest_ds = test_ds.map(to_float32)\n\nprint('Computing predictions...')\ntest_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = model_1a.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":{"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}