melanoma_detection.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "melanoma_detection.ipynb",
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "TPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/dwij2212/melanoma-detection/blob/main/melanoma_detection.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mLyHEWkbVUzu"
      },
      "source": [
        "# This Python 3 environment comes with many helpful analytics libraries installed\n",
        "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
        "# For example, here's several helpful packages to load\n",
        "\n",
        "import numpy as np # linear algebra\n",
        "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
        "\n",
        "# Input data files are available in the read-only \"../input/\" directory\n",
        "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
        "\n",
        "import os\n",
        "\n",
        "# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
        "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BrJ9qi-XO4TJ"
      },
      "source": [
        "!pip install -q efficientnet"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "joCgrhwpOy-s"
      },
      "source": [
        "import re\n",
        "import random\n",
        "import math\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn import metrics\n",
        "from sklearn.model_selection import KFold, StratifiedKFold\n",
        "import tensorflow as tf\n",
        "# from kaggle_datasets import KaggleDatasets\n",
        "import efficientnet.tfkeras as efn\n",
        "import dill\n",
        "from tensorflow.keras import backend as K\n",
        "import tensorflow_addons as tfa\n",
        "from tensorflow.keras.layers import Dense, BatchNormalization, Dropout\n",
        "from sklearn.model_selection import train_test_split"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "v7YV2rigaGy9"
      },
      "source": [
        "K.clear_session()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AbBiakLGTq-Y",
        "outputId": "7f0e048b-546d-4ebd-b78e-d2899e567c87",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 731
        }
      },
      "source": [
        "try:\n",
        "    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n",
        "    print('Running on TPU ', tpu.master())\n",
        "except ValueError:\n",
        "    tpu = None\n",
        "\n",
        "if tpu:\n",
        "    tf.config.experimental_connect_to_cluster(tpu)\n",
        "    tf.tpu.experimental.initialize_tpu_system(tpu)\n",
        "    strategy = tf.distribute.experimental.TPUStrategy(tpu)\n",
        "else:\n",
        "    # Default distribution strategy in Tensorflow. Works on CPU and single GPU.\n",
        "    strategy = tf.distribute.get_strategy()\n",
        "\n",
        "print(\"REPLICAS: \", strategy.num_replicas_in_sync)\n",
        "\n",
        "AUTO = tf.data.experimental.AUTOTUNE"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Running on TPU  grpc://10.80.163.66:8470\n",
            "INFO:tensorflow:Initializing the TPU system: grpc://10.80.163.66:8470\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Initializing the TPU system: grpc://10.80.163.66:8470\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Clearing out eager caches\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Clearing out eager caches\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Finished initializing TPU system.\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Finished initializing TPU system.\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Found TPU system:\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Found TPU system:\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Num TPU Cores: 8\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Num TPU Cores: 8\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Num TPU Workers: 1\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Num TPU Workers: 1\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Num TPU Cores Per Worker: 8\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Num TPU Cores Per Worker: 8\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:localhost/replica:0/task:0/device:CPU:0, CPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:localhost/replica:0/task:0/device:CPU:0, CPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:localhost/replica:0/task:0/device:XLA_CPU:0, XLA_CPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:localhost/replica:0/task:0/device:XLA_CPU:0, XLA_CPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:CPU:0, CPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:CPU:0, CPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:0, TPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:0, TPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:1, TPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:1, TPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:2, TPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:2, TPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:3, TPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:3, TPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:4, TPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:4, TPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:5, TPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:5, TPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:6, TPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:6, TPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:7, TPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU:7, TPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU_SYSTEM:0, TPU_SYSTEM, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:TPU_SYSTEM:0, TPU_SYSTEM, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:XLA_CPU:0, XLA_CPU, 0, 0)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:*** Available Device: _DeviceAttributes(/job:worker/replica:0/task:0/device:XLA_CPU:0, XLA_CPU, 0, 0)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "REPLICAS:  8\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SIiDdQayVOT8"
      },
      "source": [
        "EPOCHS = 40\n",
        "BATCH_SIZE = 4 * strategy.num_replicas_in_sync\n",
        "AUG_BATCH = BATCH_SIZE\n",
        "IMAGE_SIZE = [384, 384]\n",
        "# Seed\n",
        "SEED = 123\n",
        "# Learning rate\n",
        "LR = 0.0003\n",
        "# cutmix prob\n",
        "cutmix_rate = 0.30\n",
        "\n",
        "# This changes everytime so i'd need to run a piece of code on kaggle everytime \n",
        "# since cloud buckets url keeps changing\n",
        "GCS_PATH = 'gs://kds-6763fab01fc2e4f17502b8fe494b1880f0979df6b66ea201721f2672'\n",
        "\n",
        "# training filenames directory\n",
        "TRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train*.tfrec')\n",
        "# test filenames directory\n",
        "TEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test*.tfrec')\n",
        "# submission fi"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yHjk22TrPEqG"
      },
      "source": [
        "def decode_image(image_data):\n",
        "    image = tf.image.decode_jpeg(image_data, channels=3)\n",
        "    # convert image to floats in [0, 1] range\n",
        "    image = tf.cast(image, tf.float32) / 255.0 \n",
        "    # explicit size needed for TPU\n",
        "    image = tf.reshape(image, [*IMAGE_SIZE, 3])\n",
        "    return image"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Y_fmG7B_PG84"
      },
      "source": [
        "def read_labeled_tfrecord(example):\n",
        "    features = {\n",
        "        # tf.string means bytestring\n",
        "        \"image\": tf.io.FixedLenFeature([], tf.string), \n",
        "        # shape [] means single element\n",
        "        \"target\": tf.io.FixedLenFeature([], tf.int64),\n",
        "        # meta features\n",
        "        \"age_approx\": tf.io.FixedLenFeature([], tf.int64),\n",
        "        \"sex\": tf.io.FixedLenFeature([], tf.int64),\n",
        "        \"anatom_site_general_challenge\": tf.io.FixedLenFeature([], tf.int64)\n",
        "        \n",
        "    }\n",
        "    example = tf.io.parse_single_example(example, features)\n",
        "    image = decode_image(example['image'])\n",
        "    label = tf.cast(example['target'], tf.float32)\n",
        "    # meta features\n",
        "    data = {}\n",
        "    data['age_approx'] = tf.cast(example['age_approx'], tf.int32)\n",
        "    data['sex'] = tf.cast(example['sex'], tf.int32)\n",
        "    data['anatom_site_general_challenge'] = tf.cast(tf.one_hot(example['anatom_site_general_challenge'], 7), tf.int32)\n",
        "    # returns a dataset of (image, label, data)\n",
        "    return image, label, data"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jYPSFye-VHoS"
      },
      "source": [
        "# this function parse our image and also get our image_name (id) to perform predictions\n",
        "def read_unlabeled_tfrecord(example):\n",
        "    features = {\n",
        "        # tf.string means bytestring\n",
        "        \"image\": tf.io.FixedLenFeature([], tf.string), \n",
        "        # shape [] means single element\n",
        "        \"image_name\": tf.io.FixedLenFeature([], tf.string),\n",
        "        # meta features\n",
        "        \"age_approx\": tf.io.FixedLenFeature([], tf.int64),\n",
        "        \"sex\": tf.io.FixedLenFeature([], tf.int64),\n",
        "        \"anatom_site_general_challenge\": tf.io.FixedLenFeature([], tf.int64)\n",
        "    }\n",
        "    example = tf.io.parse_single_example(example, features)\n",
        "    image = decode_image(example['image'])\n",
        "    image_name = example['image_name']\n",
        "    # meta features\n",
        "    data = {}\n",
        "    data['age_approx'] = tf.cast(example['age_approx'], tf.int32)\n",
        "    data['sex'] = tf.cast(example['sex'], tf.int32)\n",
        "    data['anatom_site_general_challenge'] = tf.cast(tf.one_hot(example['anatom_site_general_challenge'], 7), tf.int32)\n",
        "    # returns a dataset of (image, key, data)\n",
        "    return image, image_name, data\n",
        "  \n",
        "\n",
        "# function to count how many photos we have in\n",
        "def count_data_items(filenames):\n",
        "    # the number of data items is written in the name of the .tfrec files, i.e. flowers00-230.tfrec = 230 data items\n",
        "    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n",
        "    return np.sum(n)\n",
        "\n",
        "def load_dataset(filenames, labeled = True, ordered = False):\n",
        "    # Read from TFRecords\n",
        "    \n",
        "    ignore_order = tf.data.Options()\n",
        "    if not ordered:\n",
        "        # disable order, increase speed\n",
        "        ignore_order.experimental_deterministic = False \n",
        "        \n",
        "    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads = AUTO)\n",
        "    # use data as soon as it streams in, rather than in its original order\n",
        "    dataset = dataset.with_options(ignore_order)\n",
        "    # returns a dataset of (image, label) pairs if labeled = True or (image, id) pair if labeld = False\n",
        "    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls = AUTO) \n",
        "    return dataset\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZWCtULryVAH6",
        "outputId": "15713414-5c85-457d-f44e-a485ec164371",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "NUM_TRAINING_IMAGES = int(count_data_items(TRAINING_FILENAMES) * 0.8)\n",
        "\n",
        "NUM_VALIDATION_IMAGES = int(count_data_items(TRAINING_FILENAMES) * 0.2)\n",
        "NUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\n",
        "STEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n",
        "\n",
        "print('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Dataset: 26153 training images, 6538 validation images, 10982 unlabeled test images\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "K24xwJUwUy4S"
      },
      "source": [
        "def setup_input1(image, label, data):\n",
        "    \n",
        "    # get anatom site general challenge vectors\n",
        "    anatom = [tf.cast(data['anatom_site_general_challenge'][i], dtype = tf.float32) for i in range(7)]\n",
        "    \n",
        "    tab_data = [tf.cast(data[tfeat], dtype = tf.float32) for tfeat in ['age_approx', 'sex']]\n",
        "    \n",
        "    tabular = tf.stack(tab_data + anatom)\n",
        "    \n",
        "    return {'inp1': image, 'inp2':  tabular}, label\n",
        "\n",
        "# function for the test set\n",
        "def setup_input2(image, image_name, data):\n",
        "    \n",
        "    # get anatom site general challenge vectors\n",
        "    anatom = [tf.cast(data['anatom_site_general_challenge'][i], dtype = tf.float32) for i in range(7)]\n",
        "    \n",
        "    tab_data = [tf.cast(data[tfeat], dtype = tf.float32) for tfeat in ['age_approx', 'sex']]\n",
        "    \n",
        "    tabular = tf.stack(tab_data + anatom)\n",
        "    \n",
        "    return {'inp1': image, 'inp2':  tabular}, image_name\n",
        "\n",
        "def setup_input3(image, image_name, target, data):\n",
        "    \n",
        "    # get anatom site general challenge vectors\n",
        "    anatom = [tf.cast(data['anatom_site_general_challenge'][i], dtype = tf.float32) for i in range(7)]\n",
        "    \n",
        "    tab_data = [tf.cast(data[tfeat], dtype = tf.float32) for tfeat in ['age_approx', 'sex']]\n",
        "    \n",
        "    tabular = tf.stack(tab_data + anatom)\n",
        "    \n",
        "    return {'inp1': image, 'inp2':  tabular}, image_name, target\n",
        "\n",
        "def data_augment(data, label):\n",
        "    # data augmentation. Thanks to the dataset.prefetch(AUTO) statement \n",
        "    # in the next function (below), this happens essentially for free on TPU. \n",
        "    # Data pipeline code is executed on the \"CPU\" part\n",
        "    # of the TPU while the TPU itself is computing gradients.\n",
        "    data['inp1'] = tf.image.random_flip_left_right(data['inp1'])\n",
        "    data['inp1'] = tf.image.random_flip_up_down(data['inp1'])\n",
        "    data['inp1'] = tf.image.random_hue(data['inp1'], 0.01)\n",
        "    data['inp1'] = tf.image.random_saturation(data['inp1'], 0.7, 1.3)\n",
        "    data['inp1'] = tf.image.random_contrast(data['inp1'], 0.8, 1.2)\n",
        "    data['inp1'] = tf.image.random_brightness(data['inp1'], 0.1)\n",
        "    \n",
        "    return data, label\n",
        "\n",
        "def get_training_dataset(filenames, labeled = True, ordered = False):\n",
        "    dataset = load_dataset(filenames, labeled = labeled, ordered = ordered)\n",
        "    dataset = dataset.map(setup_input1, num_parallel_calls = AUTO)\n",
        "    dataset = dataset.map(data_augment, num_parallel_calls = AUTO)\n",
        "#     dataset = dataset.map(transform, num_parallel_calls = AUTO)\n",
        "    # the training dataset must repeat for several epochs\n",
        "    dataset = dataset.repeat()\n",
        "    dataset = dataset.shuffle(2048)\n",
        "    dataset = dataset.batch(BATCH_SIZE)\n",
        "    # prefetch next batch while training (autotune prefetch buffer size)\n",
        "    dataset = dataset.prefetch(AUTO)\n",
        "    return dataset\n",
        "\n",
        "def get_validation_dataset(filenames, labeled = True, ordered = True, tta=False):\n",
        "    dataset = load_dataset(filenames, labeled = labeled, ordered = ordered)\n",
        "    dataset = dataset.map(setup_input1, num_parallel_calls = AUTO)\n",
        "    if tta:\n",
        "      dataset = dataset.map(data_augment_test, num_parallel_calls = AUTO)\n",
        "    dataset = dataset.batch(BATCH_SIZE)\n",
        "    # it gives oom error due to huge batch size (not really huge but number of \n",
        "    # parameters is too large)\n",
        "    # using gpu, not enought memory to use cache\n",
        "    # dataset = dataset.cache()\n",
        "    # prefetch next batch while training (autotune prefetch buffer size)\n",
        "    dataset = dataset.prefetch(AUTO) \n",
        "    return dataset\n",
        "\n",
        "def get_test_dataset(filenames, labeled = False, ordered = True, tta=False):\n",
        "    dataset = load_dataset(filenames, labeled = labeled, ordered = ordered)\n",
        "    dataset = dataset.map(setup_input2, num_parallel_calls = AUTO)\n",
        "    if tta:\n",
        "      dataset = dataset.map(data_augment, num_parallel_calls = AUTO)\n",
        "    dataset = dataset.batch(BATCH_SIZE)\n",
        "    # prefetch next batch while training (autotune prefetch buffer size)\n",
        "    dataset = dataset.prefetch(AUTO) \n",
        "    return dataset"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IGv_AXnLty2W"
      },
      "source": [
        "# Super huge model consisting of 5 effnets and one MLP all bundled up in one single\n",
        "# neural net\n",
        "def make_giant_model():\n",
        "    # Store on TPU to utilize TPU\n",
        "    with strategy.scope():\n",
        "        # Creating two different input layers\n",
        "        img_inp = tf.keras.layers.Input(shape = (*IMAGE_SIZE, 3), name = 'inp1')\n",
        "        mlp_inp = tf.keras.layers.Input(shape = 9, name = 'inp2')\n",
        "        \n",
        "        dummy = tf.keras.layers.Lambda(lambda x:x)(img_inp)\n",
        "    \n",
        "        outputs = []    \n",
        "        for i in range(7):\n",
        "            constructor = getattr(efn, f'EfficientNetB{i}')\n",
        "            \n",
        "            x = constructor(include_top=False, weights='imagenet', \n",
        "                            input_shape=(*IMAGE_SIZE, 3), \n",
        "                            pooling='avg')(dummy)\n",
        "            \n",
        "            x = tf.keras.layers.Dense(1, activation='sigmoid')(x)\n",
        "            outputs.append(x)\n",
        "\n",
        "        outputs = tf.keras.layers.concatenate(outputs)\n",
        "        y = Dense(128)(mlp_inp)\n",
        "        y = BatchNormalization()(y)\n",
        "        y = tf.keras.layers.Activation('relu')(y)\n",
        "        \n",
        "        # Concat. two layers\n",
        "        mix = tf.keras.layers.concatenate([outputs, y])\n",
        "        \n",
        "        mix = Dense(512, activation='relu')(mix)\n",
        "        mix = BatchNormalization()(mix)\n",
        "        mix = Dropout(0.3)(mix)\n",
        "        \n",
        "        mix = Dense(128, activation='relu')(mix)\n",
        "        mix = BatchNormalization()(mix)\n",
        "        mix = Dropout(0.3)(mix)\n",
        "        \n",
        "        # Output layer\n",
        "        output = Dense(1, activation='sigmoid')(mix)\n",
        "        \n",
        "        # Assemble model\n",
        "        model = tf.keras.models.Model(inputs = [img_inp, mlp_inp], outputs = [output])\n",
        "\n",
        "        opt = tf.keras.optimizers.Adam(learning_rate = 0.0005)\n",
        "\n",
        "        model.compile(\n",
        "            optimizer = opt,\n",
        "            loss = tf.keras.losses.BinaryCrossentropy(),\n",
        "            metrics = [tf.keras.metrics.AUC()]\n",
        "        )\n",
        "        \n",
        "        return model"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vglRHMnzvHPe"
      },
      "source": [
        "def train_giant_model(model):\n",
        "    print('\\n')\n",
        "    print('-'*50)\n",
        "    print('Training fold')\n",
        "    from sklearn.model_selection import train_test_split\n",
        "\n",
        "    print(\"Getting filenames...\")\n",
        "    filenames = tf.io.gfile.glob(GCS_PATH + '/train*.tfrec')\n",
        "    TRAINING_FILENAMES, VALIDATION_FILENAMES = train_test_split(filenames, test_size=0.1)\n",
        "\n",
        "    print(\"Making datasets...\")\n",
        "    train_dataset = get_training_dataset([TRAINING_FILENAMES], labeled = True, ordered = False)\n",
        "    val_dataset = get_validation_dataset([VALIDATION_FILENAMES], labeled = True, ordered = True)\n",
        "\n",
        "    print(\"Clearing backend session...\")\n",
        "    K.clear_session()\n",
        "\n",
        "    if model is None:\n",
        "      print(\"Making model...\")\n",
        "      model = make_giant_model()\n",
        "\n",
        "    early_stopping = tf.keras.callbacks.EarlyStopping(monitor = 'val_auc', mode = 'max', patience = 5, \n",
        "                                                  verbose = 1, min_delta = 0.0001, restore_best_weights = True)\n",
        "\n",
        "    cb_lr_schedule = tf.keras.callbacks.ReduceLROnPlateau(monitor = 'val_auc', factor = 0.4, patience = 2, verbose = 1, min_delta = 0.0001, mode = 'max')\n",
        "\n",
        "    ckpt = tf.keras.callbacks.ModelCheckpoint('fkn-efnet-{val_auc:.3f}.hdf5', monitor='val_auc', verbose=1, save_best_only=False,\n",
        "                                              save_weights_only=False, mode='max', save_freq='epoch')\n",
        "    print('Beginning training')\n",
        "    history = model.fit(train_dataset, \n",
        "                        steps_per_epoch = STEPS_PER_EPOCH,\n",
        "                        epochs = EPOCHS,\n",
        "                        callbacks = [early_stopping, cb_lr_schedule, ckpt],\n",
        "                        validation_data = val_dataset,\n",
        "                        verbose = 1)\n",
        "    print('\\n')\n",
        "    print('-'*50)\n",
        "\n",
        "    return model\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_qNnBhxv_lbg",
        "outputId": "b9095523-3592-47ad-ea27-f9e1e4ddfc78",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 275
        }
      },
      "source": [
        "model = make_giant_model()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://github.com/Callidior/keras-applications/releases/download/efficientnet/efficientnet-b0_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5\n",
            "16809984/16804768 [==============================] - 0s 0us/step\n",
            "Downloading data from https://github.com/Callidior/keras-applications/releases/download/efficientnet/efficientnet-b1_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5\n",
            "27164672/27164032 [==============================] - 0s 0us/step\n",
            "Downloading data from https://github.com/Callidior/keras-applications/releases/download/efficientnet/efficientnet-b2_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5\n",
            "31940608/31936256 [==============================] - 1s 0us/step\n",
            "Downloading data from https://github.com/Callidior/keras-applications/releases/download/efficientnet/efficientnet-b3_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5\n",
            "44113920/44107200 [==============================] - 1s 0us/step\n",
            "Downloading data from https://github.com/Callidior/keras-applications/releases/download/efficientnet/efficientnet-b4_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5\n",
            "71892992/71892840 [==============================] - 1s 0us/step\n",
            "Downloading data from https://github.com/Callidior/keras-applications/releases/download/efficientnet/efficientnet-b5_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5\n",
            "115515392/115515256 [==============================] - 46s 0us/step\n",
            "Downloading data from https://github.com/Callidior/keras-applications/releases/download/efficientnet/efficientnet-b6_weights_tf_dim_ordering_tf_kernels_autoaugment_notop.h5\n",
            "165527552/165527152 [==============================] - 2s 0us/step\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "i5hDuA5t_oiL",
        "outputId": "2f4965ce-a4ca-42f0-ce63-5195f1db796f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 522
        }
      },
      "source": [
        "tf.keras.utils.plot_model(\n",
        "    model, to_file='model.png', show_shapes=True, show_layer_names=True,\n",
        "    rankdir='TB', expand_nested=False, dpi=96\n",
        ")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<IPython.core.display.Image object>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UI-Vj2aVUwmD"
      },
      "source": [
        "model = train_giant_model(model)\n",
        "model.save_weights(\"huge_effnet_model.h5\")"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "J8TM0daR4n8M",
        "outputId": "0668a9a9-8693-4895-a685-0aaf7c55dc14",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        }
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/gdrive')\n",
        "%cd gdrive/My Drive/"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&response_type=code&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly\n",
            "\n",
            "Enter your authorization code:\n",
            "··········\n",
            "Mounted at /content/gdrive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DnWmCuI19ePu"
      },
      "source": [
        "Making predictions"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "siAC0OLF8U6X",
        "outputId": "3b955033-f9a6-4c46-cb67-6b9657b5e5e9",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 136
        }
      },
      "source": [
        "test_ds = get_test_dataset(TEST_FILENAMES, labeled = False, ordered = True)\n",
        "test_images_ds = test_ds.map(lambda image, image_name: image)\n",
        "\n",
        "print('Computing predictions...')\n",
        "probabilities = np.average(model.predict(test_images_ds, verbose=1), axis = 0)\n",
        "print('Generating submission.csv file...')\n",
        "test_ids_ds = test_ds.map(lambda image, image_name: image_name).unbatch()\n",
        "# all in one batch\n",
        "test_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U') # all in one batch\n",
        "pred_df = pd.DataFrame({'image_name': test_ids, 'target': probabilities})"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Computing predictions...\n",
            "86/86 [==============================] - 9s 108ms/step\n",
            "86/86 [==============================] - 16s 189ms/step\n",
            "86/86 [==============================] - 16s 190ms/step\n",
            "86/86 [==============================] - 16s 191ms/step\n",
            "86/86 [==============================] - 16s 190ms/step\n",
            "Generating submission.csv file...\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "iJrrbc42NIzG"
      },
      "source": [
        "# Submission process"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "qAW25JRJ81Gi",
        "outputId": "cc51c018-7668-40e9-a18c-c4588c7bdd82",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "source": [
        "sub = pd.read_csv('sample_submission.csv')\n",
        "sub.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>image_name</th>\n",
              "      <th>target</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ISIC_0052060</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ISIC_0052349</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ISIC_0058510</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ISIC_0073313</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ISIC_0073502</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     image_name  target\n",
              "0  ISIC_0052060       0\n",
              "1  ISIC_0052349       0\n",
              "2  ISIC_0058510       0\n",
              "3  ISIC_0073313       0\n",
              "4  ISIC_0073502       0"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TzUzZLw-9Lbf",
        "outputId": "2d7ea70b-50f4-4c11-a24e-73d15367e78b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        }
      },
      "source": [
        "del sub['target']\n",
        "sub = sub.merge(pred_df, on='image_name')\n",
        "sub.to_csv('multi_inp.csv', index=False)\n",
        "sub.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>image_name</th>\n",
              "      <th>target</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>ISIC_0052060</td>\n",
              "      <td>0.001498</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>ISIC_0052349</td>\n",
              "      <td>0.000330</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ISIC_0058510</td>\n",
              "      <td>0.001635</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ISIC_0073313</td>\n",
              "      <td>0.002888</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>ISIC_0073502</td>\n",
              "      <td>0.009865</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     image_name    target\n",
              "0  ISIC_0052060  0.001498\n",
              "1  ISIC_0052349  0.000330\n",
              "2  ISIC_0058510  0.001635\n",
              "3  ISIC_0073313  0.002888\n",
              "4  ISIC_0073502  0.009865"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kxdihBXEWecc",
        "outputId": "99c7e6f3-6c23-44d0-cf1a-bf927de50ed3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "import gc\n",
        "gc.collect()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "154431"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 38
        }
      ]
    }
  ]
}