{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"!pip install -q efficientnet\nimport math, re, os\nimport tensorflow as tf\nimport numpy as np\nimport efficientnet.tfkeras as efn\nfrom matplotlib import pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\nprint(\"Tensorflow version \" + tf.__version__)\nAUTO = tf.data.experimental.AUTOTUNE","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Detect hardware, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()  # TPU detection. No parameters necessary if TPU_NAME environment variable is set. On Kaggle this is always the case.\n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() # default distribution strategy in Tensorflow. Works on CPU and single GPU.\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Loading Dataset"},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path('flower-classification-with-tpus')\n\nIMAGE_SIZE = [512, 512] # at this size, a GPU will run out of memory. Use the TPU\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nGCS_PATH_SELECT = { # available image sizes\n    192: GCS_DS_PATH + '/tfrecords-jpeg-192x192',\n    224: GCS_DS_PATH + '/tfrecords-jpeg-224x224',\n    331: GCS_DS_PATH + '/tfrecords-jpeg-331x331',\n    512: GCS_DS_PATH + '/tfrecords-jpeg-512x512'\n}\nGCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]]\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') # predictions on this dataset should be submitted for the competition","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_DS_PATH","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#GCS_DS_PATH = KaggleDatasets().get_gcs_path('oxford-flowers-tfrecords')\n#IMAGE_SIZE = [512, 512] # at this size, a GPU will run out of memory. Use the TPU\n#BATCH_SIZE = 32 * strategy.num_replicas_in_sync\n\n#GCS_PATH_SELECT = { # available image sizes\n#    192: GCS_DS_PATH + '/oxford/tfrecords-jpeg-192x192',\n#    224: GCS_DS_PATH + '/oxford/tfrecords-jpeg-224x224',\n#    331: GCS_DS_PATH + '/oxford/tfrecords-jpeg-331x331',\n #   512: GCS_DS_PATH + '/oxford/tfrecords-jpeg-512x512'\n#}\n#GCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]]\n\n#TRAINING_FILENAMES += tf.io.gfile.glob(GCS_PATH + '*.tfrec')\n# VALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\n# TEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec')\n#count_data_items(TRAINING_FILENAMES)","execution_count":null,"outputs":[]},{"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":{"trusted":true},"cell_type":"code","source":"# using validation set for training to inch out last marginal performance improvement\nVALIDATION = False\nif not VALIDATION:\n    TRAINING_FILENAMES = TRAINING_FILENAMES+VALIDATION_FILENAMES","execution_count":null,"outputs":[]},{"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    # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from multiple files\n    dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset\n\ndef data_augment(image, label):\n    # data augmentation. Thanks to the dataset.prefetch(AUTO) statement in the next function (below),\n    # this happens essentially for free on TPU. Data pipeline code is executed on the \"CPU\" part\n    # of the TPU while the TPU itself is computing gradients.\n    image = tf.image.random_flip_left_right(image)\n    #image = tf.image.random_saturation(image, 0, 2)\n    return image, label   \n\ndef get_training_dataset():\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) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(TEST_FILENAMES, labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec files, i.e. flowers00-230.tfrec = 230 data items\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# data dump\nprint(\"Training data shapes:\")\nfor image, label in get_training_dataset().take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training data label examples:\", label.numpy())\nprint(\"Validation data shapes:\")\nfor image, label in get_validation_dataset().take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Validation data label examples:\", label.numpy())\nprint(\"Test data shapes:\")\nfor image, idnum in get_test_dataset().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":"## Vizualization"},{"metadata":{"trusted":true},"cell_type":"code","source":"# numpy and matplotlib defaults\nnp.set_printoptions(threshold=15, linewidth=80)\n\ndef batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    if numpy_labels.dtype == object: # binary string in this case, these are image ID strings\n        numpy_labels = [None for _ in enumerate(numpy_images)]\n    # If no labels, only image IDs, return None for labels (this is the case for test data)\n    return numpy_images, numpy_labels\n\ndef title_from_label_and_target(label, correct_label):\n    if correct_label is None:\n        return CLASSES[label], True\n    correct = (label == correct_label)\n    return \"{} [{}{}{}]\".format(CLASSES[label], 'OK' if correct else 'NO', u\"\\u2192\" if not correct else '',\n                                CLASSES[correct_label] if not correct else ''), correct\n\ndef display_one_flower(image, title, subplot, red=False, titlesize=16):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n    return (subplot[0], subplot[1], subplot[2]+1)\n    \ndef display_batch_of_images(databatch, predictions=None):\n    \"\"\"This will work with:\n    display_batch_of_images(images)\n    display_batch_of_images(images, predictions)\n    display_batch_of_images((images, labels))\n    display_batch_of_images((images, labels), predictions)\n    \"\"\"\n    # data\n    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n        \n    # auto-squaring: this will drop data that does not fit into square or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n        \n    # size and spacing\n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[label]\n        correct = True\n        if predictions is not None:\n            title, correct = title_from_label_and_target(predictions[i], label)\n        dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n        subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n    \n    #layout\n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspace=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n    plt.show()\n\ndef display_confusion_matrix(cmat, score, precision, recall):\n    plt.figure(figsize=(15,15))\n    ax = plt.gca()\n    ax.matshow(cmat, cmap='Reds')\n    ax.set_xticks(range(len(CLASSES)))\n    ax.set_xticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"left\", rotation_mode=\"anchor\")\n    ax.set_yticks(range(len(CLASSES)))\n    ax.set_yticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_yticklabels(), rotation=45, ha=\"right\", rotation_mode=\"anchor\")\n    titlestring = \"\"\n    if score is not None:\n        titlestring += 'f1 = {:.3f} '.format(score)\n    if precision is not None:\n        titlestring += '\\nprecision = {:.3f} '.format(precision)\n    if recall is not None:\n        titlestring += '\\nrecall = {:.3f} '.format(recall)\n    if len(titlestring) > 0:\n        ax.text(101, 1, titlestring, fontdict={'fontsize': 18, 'horizontalalignment':'right', 'verticalalignment':'top', 'color':'#804040'})\n    plt.show()\n    \ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Peek at training data\ntraining_dataset = get_training_dataset()\ntraining_dataset = training_dataset.unbatch().batch(20)\ntrain_batch = iter(training_dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# run this cell again for next set of images\n#display_batch_of_images(next(train_batch))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# peer at test data\ntest_dataset = get_test_dataset()\ntest_dataset = test_dataset.unbatch().batch(20)\ntest_batch = iter(test_dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# run this cell again for next set of images\n#display_batch_of_images(next(test_batch))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## LR Scheduler "},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 20\nLR_START = 0.0001\nLR_MAX = 0.00005 * strategy.num_replicas_in_sync\nLR_MIN = 0.00001\nLR_RAMPUP_EPOCHS = 4\nLR_SUSTAIN_EPOCHS = 6\nLR_EXP_DECAY = .8\n\ndef lrfn(epoch):\n    if epoch < LR_RAMPUP_EPOCHS:\n        lr = np.random.random_sample() * 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)\nes_callback = tf.keras.callbacks.EarlyStopping(min_delta=0, patience=10, verbose=1, mode='auto', restore_best_weights=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":"## Building Models"},{"metadata":{},"cell_type":"markdown","source":"### DenseNET201"},{"metadata":{"trusted":true},"cell_type":"code","source":"\nwith strategy.scope():\n    dn201 = tf.keras.applications.DenseNet201(weights='imagenet', include_top=False, input_shape=[*IMAGE_SIZE, 3])\n    dn201.trainable = True # Full Training\n    \n    model1 = tf.keras.Sequential([\n        dn201,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n        \nmodel1.compile(\n    optimizer = tf.keras.optimizers.Adam(learning_rate=0.001),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\nmodel1.summary()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### EfficientNET B7"},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    enb7 = efn.EfficientNetB7(weights='noisy-student', include_top=False, input_shape=[*IMAGE_SIZE, 3])\n    enb7.trainable = True # Full Training\n    \n    model2 = tf.keras.Sequential([\n        enb7,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n        \nmodel2.compile(\n    optimizer = tf.keras.optimizers.Adam(learning_rate=0.001),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)\nmodel2.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### InceptionResNetV2"},{"metadata":{"trusted":true},"cell_type":"code","source":"# with strategy.scope():\n#     Inet = tf.keras.applications.InceptionResNetV2(weights='imagenet', include_top=False, input_shape=[*IMAGE_SIZE, 3])\n#     Inet.trainable = True # Full Training\n    \n#     model3 = tf.keras.Sequential([\n#         Inet,\n#         tf.keras.layers.GlobalAveragePooling2D(),\n#         tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n#     ])\n        \n# model3.compile(\n#     optimizer = tf.keras.optimizers.Adam(learning_rate=0.001),\n#     loss = 'sparse_categorical_crossentropy',\n#     metrics=['sparse_categorical_accuracy']\n# )\n# model3.summary()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Training"},{"metadata":{"trusted":true},"cell_type":"code","source":"history1 = model1.fit(\n    get_training_dataset(), \n    steps_per_epoch=STEPS_PER_EPOCH, \n    epochs=EPOCHS, \n    validation_data= None if not VALIDATION else get_validation_dataset(), \n    callbacks = [lr_callback])    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history2 = model2.fit(\n    get_training_dataset(), \n    steps_per_epoch=128, \n    epochs=EPOCHS, \n    validation_data= None if not VALIDATION else get_validation_dataset(), \n    callbacks = [lr_callback] )   ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#history3 = model3.fit(\n #   get_training_dataset(), \n  #  steps_per_epoch=STEPS_PER_EPOCH, \n   # epochs=EPOCHS, \n    #validation_data= None if not VALIDATION else get_validation_dataset(), \n    #callbacks = [lr_callback] )   ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Training_curves"},{"metadata":{"trusted":true},"cell_type":"code","source":"if VALIDATION:\n    display_training_curves(history1.history['loss'], history1.history['val_loss'], 'loss', 211)\n    display_training_curves(history2.history['loss'], history2.history['val_loss'], 'loss', 211)\n    display_training_curves(history3.history['loss'], history3.history['val_loss'], 'loss', 211)\n\n    display_training_curves(history1.history['sparse_categorical_accuracy'], history1.history['val_sparse_categorical_accuracy'], 'accuracy', 212)\n    display_training_curves(history2.history['sparse_categorical_accuracy'], history2.history['val_sparse_categorical_accuracy'], 'accuracy', 212)\n    display_training_curves(history3.history['sparse_categorical_accuracy'], history3.history['val_sparse_categorical_accuracy'], 'accuracy', 212)\n    ","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Finding best alpha\nOur final model is just mix of two presented above. Note that using validation data as training will fit your model with accuracy equal 1.0. Thus formula presented below of linear combination of models will work only with validation data:\n\nprob = alpha prob(model) + (1 - alpha) prob(model2)"},{"metadata":{},"cell_type":"markdown","source":"## Model-1 & Model-2"},{"metadata":{"trusted":true},"cell_type":"code","source":"if VALIDATION:\n    cmdataset = get_validation_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and labels, order matters.\n    images_ds = cmdataset.map(lambda image, label: image)\n    labels_ds = cmdataset.map(lambda image, label: label).unbatch()\n    cm_correct_labels = next(iter(labels_ds.batch(NUM_VALIDATION_IMAGES))).numpy() # get everything as one batch\n    m = model1.predict(images_ds)\n    m2 = model2.predict(images_ds)\n    scores = []\n    for alpha in np.linspace(0,1,100):\n        cm_probabilities = alpha*m+(1-alpha)*m2\n        cm_predictions = np.argmax(cm_probabilities, axis=-1)\n        scores.append(f1_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro'))\n        \n    print(\"Correct   labels: \", cm_correct_labels.shape, cm_correct_labels)\n    print(\"Predicted labels: \", cm_predictions.shape, cm_predictions)\n    plt.plot(scores)\n    best_alpha = np.argmax(scores)/100\n    cm_probabilities = best_alpha*m+(1-best_alpha)*m2\n    cm_predictions = np.argmax(cm_probabilities, axis=-1)\nelse:\n    best_alpha = 0.44\n    \n    print(best_alpha)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if VALIDATION: \n    cmat = confusion_matrix(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)))\n    score = f1_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\n    precision = precision_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\n    recall = recall_score(cm_correct_labels, cm_predictions, labels=range(len(CLASSES)), average='macro')\n    #cmat = (cmat.T / cmat.sum(axis=1)).T # normalized\n    display_confusion_matrix(cmat, score, precision, recall)\n    print('f1 score: {:.3f}, precision: {:.3f}, recall: {:.3f}'.format(score, precision, recall))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Predictions Using TTA Technique"},{"metadata":{},"cell_type":"markdown","source":"#### Model1"},{"metadata":{"trusted":true},"cell_type":"code","source":"TTA_NUM = 10\nprobabilities = []\nfor i in range(TTA_NUM):\n    #print(f'TTA Number: {i}\\n')\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    probabilities.append(model1.predict(test_images_ds,verbose =1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prob1 = np.mean(probabilities,axis =0)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Model2"},{"metadata":{"trusted":true},"cell_type":"code","source":"TTA_NUM = 10\nprobabilities = []\nfor i in range(TTA_NUM):\n    print('TTA Number: ',i)\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    probabilities.append(model2.predict(test_images_ds,verbose =1))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prob2 = np.mean(probabilities,axis =0)\nprob2","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#### Model 3"},{"metadata":{"trusted":true},"cell_type":"code","source":"#TTA_NUM = 10\n#probabilities = []\n#for i in range(TTA_NUM):\n    #print('TTA Number: ',i)\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    #probabilities.append(model3.predict(test_images_ds,verbose =1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#prob3 = np.mean(probabilities,axis =0)\n#prob3","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#2\n#test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\n\n#print('Computing predictions...')\n#test_images_ds = test_ds.map(lambda image, idnum: image)\n##probabilities = (model1.predict(test_images_ds)+model2.predict(test_images_ds))/2 # using average model probability\n##probabilities = model.predict(test_images_ds)\nbest_alpha=0.56\nprobabilities = best_alpha*prob1 + (1-best_alpha)*prob2\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#3\n#test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\n\n#print('Computing predictions...')\n#test_images_ds = test_ds.map(lambda image, idnum: image)\n##probabilities = (model1.predict(test_images_ds)+model2.predict(test_images_ds))/2 # using average model probability\n##probabilities = model.predict(test_images_ds)\n#probabilities = best_alpha * (prob1) + best_beta * (prob2) + (1-best_alpha-best_beta) * (prob3)\n#predictions = np.argmax(probabilities, axis=-1)\n#print(predictions)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('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":"from IPython.display import FileLink, FileLinks\nFileLinks('.')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Visual validation\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"if VALIDATION:\n    dataset = get_validation_dataset()\n    dataset = dataset.unbatch().batch(20)\n    batch = iter(dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# run this cell again for next set of images\nif VALIDATION:\n    images, labels = next(batch)\n    #probabilities = (model1.predict(images)+model2.predict(images))/2\n    #probabilities = model1.predict(images) \n    probabilities = (model1.predict(images)*0.50505)+model2.predict(images)*0.44444+model3.predict(images)*0.05050\n    predictions = np.argmax(probabilities, axis=-1)\n    display_batch_of_images((images, labels), predictions)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":4}