{"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":"markdown","source":"# Step 1: Imports #\n\nWe begin by importing several Python packages.","metadata":{}},{"cell_type":"code","source":"import math, re, os\nimport numpy as np\nimport tensorflow as tf\n\nprint(\"Tensorflow version \" + tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2021-06-09T23:47:19.529124Z","iopub.execute_input":"2021-06-09T23:47:19.529941Z","iopub.status.idle":"2021-06-09T23:47:25.614412Z","shell.execute_reply.started":"2021-06-09T23:47:19.529795Z","shell.execute_reply":"2021-06-09T23:47:25.613356Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 2: Distribution Strategy #\n\nThe following code chunk defines a distribution strategy for use in our model","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-06-09T23:48:10.706100Z","iopub.execute_input":"2021-06-09T23:48:10.706471Z","iopub.status.idle":"2021-06-09T23:48:16.005218Z","shell.execute_reply.started":"2021-06-09T23:48:10.706433Z","shell.execute_reply":"2021-06-09T23:48:16.004023Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 3: Loading the Competition Data #\n\n## Get GCS Path ##\n\nWhen used with TPUs, datasets need to be stored in a [Google Cloud Storage bucket](https://cloud.google.com/storage/). The following will retrieve the GCS path for this competition's dataset.","metadata":{}},{"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nprint(GCS_DS_PATH) ","metadata":{"execution":{"iopub.status.busy":"2021-06-09T23:48:20.010707Z","iopub.execute_input":"2021-06-09T23:48:20.011085Z","iopub.status.idle":"2021-06-09T23:48:20.453282Z","shell.execute_reply.started":"2021-06-09T23:48:20.011055Z","shell.execute_reply":"2021-06-09T23:48:20.452310Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 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. ","metadata":{}},{"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","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-06-09T23:48:24.179470Z","iopub.execute_input":"2021-06-09T23:48:24.179847Z","iopub.status.idle":"2021-06-09T23:48:24.416876Z","shell.execute_reply.started":"2021-06-09T23:48:24.179815Z","shell.execute_reply":"2021-06-09T23:48:24.415984Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{}},{"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_flip_up_down(image)\n    image = tf.image.random_brightness(image, 0.2)\n    # image = tf.image.random_saturation(image, 0.1)\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","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-06-09T23:48:28.491530Z","iopub.execute_input":"2021-06-09T23:48:28.491915Z","iopub.status.idle":"2021-06-09T23:48:28.507700Z","shell.execute_reply.started":"2021-06-09T23:48:28.491883Z","shell.execute_reply":"2021-06-09T23:48:28.506132Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This next cell will create the datasets that we'll use with Keras during training and inference.","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2021-06-09T23:48:38.389689Z","iopub.execute_input":"2021-06-09T23:48:38.390080Z","iopub.status.idle":"2021-06-09T23:48:38.744162Z","shell.execute_reply.started":"2021-06-09T23:48:38.390047Z","shell.execute_reply":"2021-06-09T23:48:38.743132Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{}},{"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())","metadata":{"execution":{"iopub.status.busy":"2021-06-09T23:48:43.255362Z","iopub.execute_input":"2021-06-09T23:48:43.255715Z","iopub.status.idle":"2021-06-09T23:48:48.467972Z","shell.execute_reply.started":"2021-06-09T23:48:43.255686Z","shell.execute_reply":"2021-06-09T23:48:48.466752Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{}},{"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","metadata":{"execution":{"iopub.status.busy":"2021-06-09T23:48:52.999616Z","iopub.execute_input":"2021-06-09T23:48:53.000006Z","iopub.status.idle":"2021-06-09T23:48:56.730640Z","shell.execute_reply.started":"2021-06-09T23:48:52.999971Z","shell.execute_reply":"2021-06-09T23:48:56.729857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 4: Explore Data #\n\nLet's take a moment to look at some of the images in the dataset.","metadata":{}},{"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.'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-06-09T23:49:00.245470Z","iopub.execute_input":"2021-06-09T23:49:00.245986Z","iopub.status.idle":"2021-06-09T23:49:00.265310Z","shell.execute_reply.started":"2021-06-09T23:49:00.245955Z","shell.execute_reply":"2021-06-09T23:49:00.264180Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{}},{"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(20))","metadata":{"execution":{"iopub.status.busy":"2021-06-09T23:49:04.414669Z","iopub.execute_input":"2021-06-09T23:49:04.415084Z","iopub.status.idle":"2021-06-09T23:49:04.429841Z","shell.execute_reply.started":"2021-06-09T23:49:04.415048Z","shell.execute_reply":"2021-06-09T23:49:04.428710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{}},{"cell_type":"code","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{"execution":{"iopub.status.busy":"2021-06-09T23:49:06.256430Z","iopub.execute_input":"2021-06-09T23:49:06.256819Z","iopub.status.idle":"2021-06-09T23:49:10.511298Z","shell.execute_reply.started":"2021-06-09T23:49:06.256780Z","shell.execute_reply":"2021-06-09T23:49:10.508962Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 5: Define Model #\n\nNow we're ready to create a neural network for classifying images! We'll use **transfer learning** to do this.\n\nI will use the **Xception** model as my base. ","metadata":{}},{"cell_type":"code","source":"EPOCHS = 12\n\nwith strategy.scope():\n    pretrained_model = tf.keras.applications.Xception(\n        weights='imagenet',\n        include_top=False ,\n        input_shape=[*IMAGE_SIZE, 3]\n    )\n    pretrained_model.trainable = False\n    \n    model = tf.keras.Sequential([\n        # To a base pretrained on ImageNet to extract features from images...\n        pretrained_model,\n        # ... attach a new head to act as a classifier.\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dropout(rate=0.25),\n        tf.keras.layers.BatchNormalization(),\n        tf.keras.layers.Dense(units=512, activation='selu'),\n        tf.keras.layers.Dropout(rate=0.25),\n        tf.keras.layers.BatchNormalization(),\n        tf.keras.layers.Dense(units=256, activation='selu'),\n        #tf.keras.layers.BatchNormalization(),\n        # tf.keras.layers.Dense(units=128, activation='selu'),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])","metadata":{"execution":{"iopub.status.busy":"2021-06-10T00:47:03.031008Z","iopub.execute_input":"2021-06-10T00:47:03.031408Z","iopub.status.idle":"2021-06-10T00:47:10.624977Z","shell.execute_reply.started":"2021-06-10T00:47:03.031372Z","shell.execute_reply":"2021-06-10T00:47:10.624126Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{}},{"cell_type":"code","source":"model.compile(\n    optimizer='adam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n)\n\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2021-06-10T00:47:13.846961Z","iopub.execute_input":"2021-06-10T00:47:13.847489Z","iopub.status.idle":"2021-06-10T00:47:13.897407Z","shell.execute_reply.started":"2021-06-10T00:47:13.847441Z","shell.execute_reply":"2021-06-10T00:47:13.896333Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 6: Training #\n\n## Learning Rate Schedule ##\n\nWe'll train this network with a special learning rate schedule.","metadata":{}},{"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 = 0.0001,\n                   rampup_epochs = 6, sustain_epochs = 0,\n                   exp_decay = 0.7):\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]))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-06-10T01:05:43.093920Z","iopub.execute_input":"2021-06-10T01:05:43.094378Z","iopub.status.idle":"2021-06-10T01:05:43.237784Z","shell.execute_reply.started":"2021-06-10T01:05:43.094332Z","shell.execute_reply":"2021-06-10T01:05:43.236966Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{}},{"cell_type":"code","source":"# Define training epochs\nEPOCHS = 12\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    steps_per_epoch=STEPS_PER_EPOCH,\n    callbacks=[lr_callback],\n)","metadata":{"execution":{"iopub.status.busy":"2021-06-10T01:05:48.635736Z","iopub.execute_input":"2021-06-10T01:05:48.636147Z","iopub.status.idle":"2021-06-10T01:06:01.849863Z","shell.execute_reply.started":"2021-06-10T01:05:48.636114Z","shell.execute_reply":"2021-06-10T01:06:01.847751Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This next cell shows how the loss and metrics progressed during training. Thankfully, it converges!","metadata":{}},{"cell_type":"code","source":"display_training_curves(\n    history.history['loss'],\n    history.history['val_loss'],\n    'loss',\n    211,\n)\ndisplay_training_curves(\n    history.history['sparse_categorical_accuracy'],\n    history.history['val_sparse_categorical_accuracy'],\n    'accuracy',\n    212,\n)","metadata":{"execution":{"iopub.status.busy":"2021-06-10T00:51:45.515866Z","iopub.execute_input":"2021-06-10T00:51:45.516250Z","iopub.status.idle":"2021-06-10T00:51:45.961597Z","shell.execute_reply.started":"2021-06-10T00:51:45.516207Z","shell.execute_reply":"2021-06-10T00:51:45.960694Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 7: 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":{}},{"cell_type":"code","source":"\nimport matplotlib.pyplot as plt\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\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.'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2021-06-08T21:07:02.91463Z","iopub.execute_input":"2021-06-08T21:07:02.915012Z","iopub.status.idle":"2021-06-08T21:07:03.695177Z","shell.execute_reply.started":"2021-06-08T21:07:02.91498Z","shell.execute_reply":"2021-06-08T21:07:03.694153Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Confusion Matrix ##\n\nA [confusion matrix](https://en.wikipedia.org/wiki/Confusion_matrix) shows the actual class of an image tabulated against its predicted class. It is one of the best tools you have for evaluating the performance of a classifier.\n\nThe following cell does some processing on the validation data and then creates the matrix with the `confusion_matrix` function included in [`scikit-learn`](https://scikit-learn.org/stable/index.html).","metadata":{}},{"cell_type":"code","source":"cmdataset = 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(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n)\ncmat = (cmat.T / cmat.sum(axis=1)).T # normalize","metadata":{"execution":{"iopub.status.busy":"2021-06-08T21:07:17.41006Z","iopub.execute_input":"2021-06-08T21:07:17.410487Z","iopub.status.idle":"2021-06-08T21:07:28.265012Z","shell.execute_reply.started":"2021-06-08T21:07:17.410451Z","shell.execute_reply":"2021-06-08T21:07:28.263989Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{}},{"cell_type":"code","source":"score = f1_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nprecision = precision_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nrecall = recall_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\ndisplay_confusion_matrix(cmat, score, precision, recall)","metadata":{"execution":{"iopub.status.busy":"2021-06-08T21:07:43.353937Z","iopub.execute_input":"2021-06-08T21:07:43.354332Z","iopub.status.idle":"2021-06-08T21:07:48.860264Z","shell.execute_reply.started":"2021-06-08T21:07:43.354282Z","shell.execute_reply":"2021-06-08T21:07:48.859409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Visual Validation ##\n\nIt can also be helpful to look at some examples from the validation set and see what class your model predicted. This can help reveal patterns in the kinds of images your model has trouble with.\n\nThis cell will set up the validation set to display 20 images at a time -- you can change this to display more or fewer, if you like.","metadata":{}},{"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","metadata":{"execution":{"iopub.status.busy":"2021-06-08T21:08:03.673621Z","iopub.execute_input":"2021-06-08T21:08:03.674328Z","iopub.status.idle":"2021-06-08T21:08:03.714954Z","shell.execute_reply.started":"2021-06-08T21:08:03.674262Z","shell.execute_reply":"2021-06-08T21:08:03.713533Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"And here is a set of flowers with their predicted species. Run the cell again to see another set.","metadata":{}},{"cell_type":"code","source":"images, labels = next(batch)\nprobabilities = model.predict(images)\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions)","metadata":{"execution":{"iopub.status.busy":"2021-06-08T21:08:08.666055Z","iopub.execute_input":"2021-06-08T21:08:08.666439Z","iopub.status.idle":"2021-06-08T21:08:18.485508Z","shell.execute_reply.started":"2021-06-08T21:08:08.666405Z","shell.execute_reply":"2021-06-08T21:08:18.48461Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Step 8: Make Test Predictions #\n\nOnce you're satisfied with everything, you're ready to make predictions on the test set.","metadata":{}},{"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True)\n\nprint('Computing predictions...')\ntest_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = model.predict(test_images_ds)\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)","metadata":{"execution":{"iopub.status.busy":"2021-06-08T21:08:39.086638Z","iopub.execute_input":"2021-06-08T21:08:39.087175Z","iopub.status.idle":"2021-06-08T21:08:49.265389Z","shell.execute_reply.started":"2021-06-08T21:08:39.087129Z","shell.execute_reply":"2021-06-08T21:08:49.264602Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We'll generate a file `submission.csv`. This file is what you'll submit to get your score on the leaderboard.","metadata":{}},{"cell_type":"code","source":"print('Generating submission.csv file...')\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(\n    'submission.csv',\n    np.rec.fromarrays([test_ids, predictions]),\n    fmt=['%s', '%d'],\n    delimiter=',',\n    header='id,label',\n    comments='',\n)\n\n# Look at the first few predictions\n!head submission.csv","metadata":{"execution":{"iopub.status.busy":"2021-06-08T21:09:43.540843Z","iopub.execute_input":"2021-06-08T21:09:43.541381Z","iopub.status.idle":"2021-06-08T21:09:46.491985Z","shell.execute_reply.started":"2021-06-08T21:09:43.541349Z","shell.execute_reply":"2021-06-08T21:09:46.490977Z"},"trusted":true},"execution_count":null,"outputs":[]}]}