code-lab-3-chestxray8-curaeaidlhw.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "view-in-github"
   },
   "source": [
    "<a href=\"https://colab.research.google.com/github/mike-holcomb/curaeaidlhw-codelab3-chestxray8/blob/master/code-lab-3-chestxray8-curaeaidlhw.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "H0XQkWTnwWB0"
   },
   "source": [
    "Code Lab 3: ChestX-ray8, National Institutes of Health Chest X-Ray Dataset\n",
    "==="
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "JV3dWdLAwWB2"
   },
   "source": [
    "These are the materials for the third code lab in Curae.ai's Deep Learning in Healthcare Workshop.\n",
    "\n",
    "The notebook in this lab is only a baseline notebook meant to help users download the dataset, document its formatting and discuss multi-label classification. Users will compete using this multilabel classification in the Curae.ai DLWH competition. Class is over! You are ready."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "WUWVX2sNwWB3"
   },
   "source": [
    "# The Problem"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "zih5xpR2wWB4"
   },
   "source": [
    "In this code lab we will investigate the ChestX-ray8 dataset published by the National Institutes of Health (NIH).  From the paper describing the release of the dataset:\n",
    "> The chest X-ray is one of the most commonly accessible radiological examinations for screening and diagnosis of many lung diseases. A tremendous number of X-ray imaging studies accompanied by radiological reports are accumulated and stored in many modern hospitals’ Picture Archiving and Communication Systems (PACS). On the other side, it is still an open question how this type of hospital-size knowledge database containing invaluable imaging informatics (i.e., loosely labeled) can be used to facilitate the data-hungry deep learning paradigms in building truly large-scale high precision computer-aided diagnosis (CAD) systems. [1](http://openaccess.thecvf.com/content_cvpr_2017/papers/Wang_ChestX-ray8_Hospital-Scale_Chest_CVPR_2017_paper.pdf)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "C9sfRuAUwWB4"
   },
   "source": [
    "![xray-cover](https://github.com/mike-holcomb/curaeaidlhw-codelab3-chestxray8/blob/master/imgs/chestx-ray8.png?raw=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "nneYFX31wWB5"
   },
   "source": [
    "The X-rays in this dataset are each labelled with 14 categories.  In contrast to the other exercises, this represents 14 simultaneous binary classifications for each of the categories.  As an example, an X-ray can contain both an \"effusion\" and \"pneumonia\" and would have a \"1\" for both of these labels."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "JRBK0S4ZzIyG"
   },
   "source": [
    "# Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "tf-BScTEzEKU"
   },
   "outputs": [],
   "source": [
    "from __future__ import print_function, division\n",
    "import numpy as np\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "import pandas as pd\n",
    "from IPython.display import display, HTML\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "v-Fv4EUdzVGt",
    "outputId": "47a5c5b0-6659-4335-83b5-a5b9dfd7c26c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tensorflow version:  1.13.1\n",
      "Is GPU available: False\n",
      "Is Eager Execution enabled?: False\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "# tf.enable_eager_execution()\n",
    "\n",
    "tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)\n",
    "print('Tensorflow version: ',tf.__version__)\n",
    "print('Is GPU available: %s' % str(tf.test.is_gpu_available()))\n",
    "print('Is Eager Execution enabled?: %s' % str(tf.executing_eagerly()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "q_4kRUX4wWB6"
   },
   "source": [
    "## Load the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "t2zDER-JwWB7"
   },
   "outputs": [],
   "source": [
    "import boto3\n",
    "import os\n",
    "\n",
    "s3 = boto3.client('s3',\n",
    "endpoint_url = 'https://s3.wasabisys.com',\n",
    "aws_access_key_id = 'VM2WCNG36U812Y1NGCT3',\n",
    "aws_secret_access_key='g3Dqovv3IYlIFDZyNWONXZSU5yhGZvWhKOJrBQRI')\n",
    "\n",
    "def download_files(filenames, save_dir):\n",
    "    for i, filename in enumerate(filenames):\n",
    "         print('Downloading %d: %s' % (i, filename)) \n",
    "         download_file(filename, save_dir)\n",
    "\n",
    "def download_file(filename, save_dir):\n",
    "    full_filename = os.path.join(save_dir,filename)\n",
    "    if os.path.exists(full_filename):\n",
    "        print('\\tAlready have: %s' % full_filename)\n",
    "        return\n",
    "    s3.download_file('curaedlhw',filename,full_filename)\n",
    "    print('\\tCOMPLETE: %s saved to %s' % (filename, save_dir))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "0YKZYB8uw1E7"
   },
   "source": [
    "**NOTE:** Make sure to set the `IS_ONEPANEL` flag to `True` if you are running this notebook from onepanel.io, "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 51
    },
    "colab_type": "code",
    "id": "cOgz9ickwWB-",
    "outputId": "5bd25b45-d87e-44ed-8e92-12fedfd067bf"
   },
   "outputs": [],
   "source": [
    "FILELIST = ['chest_xray_train_val.tar.gz']\n",
    "\n",
    "IS_ONEPANEL = True\n",
    "NEED_DOWNLOAD = False\n",
    "if IS_ONEPANEL:\n",
    "    DATA_DIR='/onepanel/input/datasets/curae/chestx-ray8-mini/1'\n",
    "else:\n",
    "    import os\n",
    "    DATA_DIR = 'data'\n",
    "    if NEED_DOWNLOAD:\n",
    "        if not os.path.exists(DATA_DIR):\n",
    "            os.mkdir(DATA_DIR)\n",
    "        download_files(FILELIST,DATA_DIR)\n",
    "\n",
    "os.environ[\"DATADIR\"] = DATA_DIR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "54BfdvxuxvtA"
   },
   "outputs": [],
   "source": [
    "!tar xf $DATADIR/chest_xray_train_val.tar.gz -C $DATADIR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "1_u0RE1GywTq"
   },
   "outputs": [],
   "source": [
    "meta_file = os.path.join(DATA_DIR,'train_val/train_val.parquet.gz')\n",
    "meta_df = pd.read_parquet(meta_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 272
    },
    "colab_type": "code",
    "id": "yvHd6YA708NP",
    "outputId": "66929eee-3f92-4783-f6de-d4ccb228c3b7"
   },
   "outputs": [
    {
     "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 Index</th>\n",
       "      <th>Finding Labels</th>\n",
       "      <th>Follow-up #</th>\n",
       "      <th>Patient ID</th>\n",
       "      <th>Patient Age</th>\n",
       "      <th>Patient Gender</th>\n",
       "      <th>View Position</th>\n",
       "      <th>OriginalImage[Width</th>\n",
       "      <th>Height]</th>\n",
       "      <th>OriginalImagePixelSpacing[x</th>\n",
       "      <th>...</th>\n",
       "      <th>Mass</th>\n",
       "      <th>Nodule</th>\n",
       "      <th>Atelectasis</th>\n",
       "      <th>Pneumothorax</th>\n",
       "      <th>Pleural_Thickening</th>\n",
       "      <th>Pneumonia</th>\n",
       "      <th>Fibrosis</th>\n",
       "      <th>Edema</th>\n",
       "      <th>Consolidation</th>\n",
       "      <th>group</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>index</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>00000001_000.png</td>\n",
       "      <td>Cardiomegaly</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>58</td>\n",
       "      <td>M</td>\n",
       "      <td>PA</td>\n",
       "      <td>2682</td>\n",
       "      <td>2749</td>\n",
       "      <td>0.143</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>00000001_001.png</td>\n",
       "      <td>Cardiomegaly|Emphysema</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>58</td>\n",
       "      <td>M</td>\n",
       "      <td>PA</td>\n",
       "      <td>2894</td>\n",
       "      <td>2729</td>\n",
       "      <td>0.143</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>00000001_002.png</td>\n",
       "      <td>Cardiomegaly|Effusion</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>58</td>\n",
       "      <td>M</td>\n",
       "      <td>PA</td>\n",
       "      <td>2500</td>\n",
       "      <td>2048</td>\n",
       "      <td>0.168</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>00000003_000.png</td>\n",
       "      <td>Hernia</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>81</td>\n",
       "      <td>F</td>\n",
       "      <td>PA</td>\n",
       "      <td>2582</td>\n",
       "      <td>2991</td>\n",
       "      <td>0.143</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>00000003_001.png</td>\n",
       "      <td>Hernia</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>74</td>\n",
       "      <td>F</td>\n",
       "      <td>PA</td>\n",
       "      <td>2500</td>\n",
       "      <td>2048</td>\n",
       "      <td>0.168</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            Image Index          Finding Labels  Follow-up #  Patient ID  \\\n",
       "index                                                                      \n",
       "0      00000001_000.png            Cardiomegaly            0           1   \n",
       "1      00000001_001.png  Cardiomegaly|Emphysema            1           1   \n",
       "2      00000001_002.png   Cardiomegaly|Effusion            2           1   \n",
       "3      00000003_000.png                  Hernia            0           3   \n",
       "4      00000003_001.png                  Hernia            1           3   \n",
       "\n",
       "       Patient Age Patient Gender View Position  OriginalImage[Width  Height]  \\\n",
       "index                                                                           \n",
       "0               58              M            PA                 2682     2749   \n",
       "1               58              M            PA                 2894     2729   \n",
       "2               58              M            PA                 2500     2048   \n",
       "3               81              F            PA                 2582     2991   \n",
       "4               74              F            PA                 2500     2048   \n",
       "\n",
       "       OriginalImagePixelSpacing[x  ...  Mass  Nodule  Atelectasis  \\\n",
       "index                               ...                              \n",
       "0                            0.143  ...     0       0            0   \n",
       "1                            0.143  ...     0       0            0   \n",
       "2                            0.168  ...     0       0            0   \n",
       "3                            0.143  ...     0       0            0   \n",
       "4                            0.168  ...     0       0            0   \n",
       "\n",
       "       Pneumothorax  Pleural_Thickening  Pneumonia  Fibrosis  Edema  \\\n",
       "index                                                                 \n",
       "0                 0                   0          0         0      0   \n",
       "1                 0                   0          0         0      0   \n",
       "2                 0                   0          0         0      0   \n",
       "3                 0                   0          0         0      0   \n",
       "4                 0                   0          0         0      0   \n",
       "\n",
       "       Consolidation  group  \n",
       "index                        \n",
       "0                  0      0  \n",
       "1                  0      0  \n",
       "2                  0      0  \n",
       "3                  0      0  \n",
       "4                  0      0  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "meta_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 334
    },
    "colab_type": "code",
    "id": "YWUWhZ-N2qgX",
    "outputId": "cd1521bb-9e7e-4919-f144-1ea76362edeb"
   },
   "outputs": [
    {
     "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>Follow-up #</th>\n",
       "      <th>Patient ID</th>\n",
       "      <th>Patient Age</th>\n",
       "      <th>OriginalImage[Width</th>\n",
       "      <th>Height]</th>\n",
       "      <th>OriginalImagePixelSpacing[x</th>\n",
       "      <th>y]</th>\n",
       "      <th>Cardiomegaly</th>\n",
       "      <th>Emphysema</th>\n",
       "      <th>Effusion</th>\n",
       "      <th>...</th>\n",
       "      <th>Mass</th>\n",
       "      <th>Nodule</th>\n",
       "      <th>Atelectasis</th>\n",
       "      <th>Pneumothorax</th>\n",
       "      <th>Pleural_Thickening</th>\n",
       "      <th>Pneumonia</th>\n",
       "      <th>Fibrosis</th>\n",
       "      <th>Edema</th>\n",
       "      <th>Consolidation</th>\n",
       "      <th>group</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "      <td>46546.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>11.495703</td>\n",
       "      <td>14757.351566</td>\n",
       "      <td>48.473725</td>\n",
       "      <td>2668.238903</td>\n",
       "      <td>2480.345808</td>\n",
       "      <td>0.155148</td>\n",
       "      <td>0.155148</td>\n",
       "      <td>0.053818</td>\n",
       "      <td>0.049070</td>\n",
       "      <td>0.255726</td>\n",
       "      <td>...</td>\n",
       "      <td>0.112727</td>\n",
       "      <td>0.123555</td>\n",
       "      <td>0.221781</td>\n",
       "      <td>0.102136</td>\n",
       "      <td>0.066601</td>\n",
       "      <td>0.027349</td>\n",
       "      <td>0.032785</td>\n",
       "      <td>0.045052</td>\n",
       "      <td>0.089739</td>\n",
       "      <td>0.107249</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>18.062218</td>\n",
       "      <td>8306.197211</td>\n",
       "      <td>16.678009</td>\n",
       "      <td>332.593252</td>\n",
       "      <td>400.402098</td>\n",
       "      <td>0.016008</td>\n",
       "      <td>0.016008</td>\n",
       "      <td>0.225660</td>\n",
       "      <td>0.216016</td>\n",
       "      <td>0.436273</td>\n",
       "      <td>...</td>\n",
       "      <td>0.316262</td>\n",
       "      <td>0.329077</td>\n",
       "      <td>0.415449</td>\n",
       "      <td>0.302830</td>\n",
       "      <td>0.249332</td>\n",
       "      <td>0.163101</td>\n",
       "      <td>0.178075</td>\n",
       "      <td>0.207421</td>\n",
       "      <td>0.285811</td>\n",
       "      <td>0.309433</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1215.000000</td>\n",
       "      <td>966.000000</td>\n",
       "      <td>0.115000</td>\n",
       "      <td>0.115000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>8038.250000</td>\n",
       "      <td>37.000000</td>\n",
       "      <td>2500.000000</td>\n",
       "      <td>2048.000000</td>\n",
       "      <td>0.143000</td>\n",
       "      <td>0.143000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>14617.000000</td>\n",
       "      <td>51.000000</td>\n",
       "      <td>2544.000000</td>\n",
       "      <td>2544.000000</td>\n",
       "      <td>0.143000</td>\n",
       "      <td>0.143000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>14.000000</td>\n",
       "      <td>20907.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>2992.000000</td>\n",
       "      <td>2991.000000</td>\n",
       "      <td>0.168000</td>\n",
       "      <td>0.168000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>183.000000</td>\n",
       "      <td>30795.000000</td>\n",
       "      <td>414.000000</td>\n",
       "      <td>3827.000000</td>\n",
       "      <td>3567.000000</td>\n",
       "      <td>0.198800</td>\n",
       "      <td>0.198800</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Follow-up #    Patient ID   Patient Age  OriginalImage[Width  \\\n",
       "count  46546.000000  46546.000000  46546.000000         46546.000000   \n",
       "mean      11.495703  14757.351566     48.473725          2668.238903   \n",
       "std       18.062218   8306.197211     16.678009           332.593252   \n",
       "min        0.000000      1.000000      1.000000          1215.000000   \n",
       "25%        1.000000   8038.250000     37.000000          2500.000000   \n",
       "50%        5.000000  14617.000000     51.000000          2544.000000   \n",
       "75%       14.000000  20907.000000     60.000000          2992.000000   \n",
       "max      183.000000  30795.000000    414.000000          3827.000000   \n",
       "\n",
       "            Height]  OriginalImagePixelSpacing[x            y]  Cardiomegaly  \\\n",
       "count  46546.000000                 46546.000000  46546.000000  46546.000000   \n",
       "mean    2480.345808                     0.155148      0.155148      0.053818   \n",
       "std      400.402098                     0.016008      0.016008      0.225660   \n",
       "min      966.000000                     0.115000      0.115000      0.000000   \n",
       "25%     2048.000000                     0.143000      0.143000      0.000000   \n",
       "50%     2544.000000                     0.143000      0.143000      0.000000   \n",
       "75%     2991.000000                     0.168000      0.168000      0.000000   \n",
       "max     3567.000000                     0.198800      0.198800      1.000000   \n",
       "\n",
       "          Emphysema      Effusion  ...          Mass        Nodule  \\\n",
       "count  46546.000000  46546.000000  ...  46546.000000  46546.000000   \n",
       "mean       0.049070      0.255726  ...      0.112727      0.123555   \n",
       "std        0.216016      0.436273  ...      0.316262      0.329077   \n",
       "min        0.000000      0.000000  ...      0.000000      0.000000   \n",
       "25%        0.000000      0.000000  ...      0.000000      0.000000   \n",
       "50%        0.000000      0.000000  ...      0.000000      0.000000   \n",
       "75%        0.000000      1.000000  ...      0.000000      0.000000   \n",
       "max        1.000000      1.000000  ...      1.000000      1.000000   \n",
       "\n",
       "        Atelectasis  Pneumothorax  Pleural_Thickening     Pneumonia  \\\n",
       "count  46546.000000  46546.000000        46546.000000  46546.000000   \n",
       "mean       0.221781      0.102136            0.066601      0.027349   \n",
       "std        0.415449      0.302830            0.249332      0.163101   \n",
       "min        0.000000      0.000000            0.000000      0.000000   \n",
       "25%        0.000000      0.000000            0.000000      0.000000   \n",
       "50%        0.000000      0.000000            0.000000      0.000000   \n",
       "75%        0.000000      0.000000            0.000000      0.000000   \n",
       "max        1.000000      1.000000            1.000000      1.000000   \n",
       "\n",
       "           Fibrosis         Edema  Consolidation         group  \n",
       "count  46546.000000  46546.000000   46546.000000  46546.000000  \n",
       "mean       0.032785      0.045052       0.089739      0.107249  \n",
       "std        0.178075      0.207421       0.285811      0.309433  \n",
       "min        0.000000      0.000000       0.000000      0.000000  \n",
       "25%        0.000000      0.000000       0.000000      0.000000  \n",
       "50%        0.000000      0.000000       0.000000      0.000000  \n",
       "75%        0.000000      0.000000       0.000000      0.000000  \n",
       "max        1.000000      1.000000       1.000000      1.000000  \n",
       "\n",
       "[8 rows x 22 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "meta_df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "1kzeIVj715Mt"
   },
   "outputs": [],
   "source": [
    "class_map = {'Cardiomegaly': 0,\n",
    "             'Emphysema': 1,\n",
    "             'Effusion': 2,\n",
    "             'Hernia': 3,\n",
    "             'Infiltration': 4,\n",
    "             'Mass': 5,\n",
    "             'Nodule': 6,\n",
    "             'Atelectasis': 7,\n",
    "             'Pneumothorax' : 8,\n",
    "             'Pleural_Thickening': 9,\n",
    "             'Pneumonia' : 10,\n",
    "             'Fibrosis' : 11,\n",
    "             'Edema': 12,\n",
    "             'Consolidation': 13}\n",
    "class_list = [''] * 14\n",
    "for class_name, class_index in class_map.items():\n",
    "  class_list[class_index] = class_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "lczkkiK-GLLT"
   },
   "outputs": [],
   "source": [
    "def convert_to_label_string(arr):\n",
    "  label = []\n",
    "  for i, val in enumerate(arr):\n",
    "    if val == 1:\n",
    "      label.append(class_list[i])\n",
    "  return '|'.join(label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ZAb5GKdI2cU7"
   },
   "outputs": [],
   "source": [
    "train_y = meta_df[meta_df['group']==0][class_map.keys()].values\n",
    "test_y = meta_df[meta_df['group']==1][class_map.keys()].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "jxbyxWm73SPu",
    "outputId": "1921ca2d-4bb1-4ecd-e0ca-464aea77ce7d"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Size of train set: 41554, test set: 4992\n"
     ]
    }
   ],
   "source": [
    "print(\"Size of train set: %d, test set: %d\" % (len(train_y),len(test_y)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "2qx_ijrNATgq"
   },
   "outputs": [],
   "source": [
    "train_x = meta_df[meta_df['group']==0]['Image Index'].values\n",
    "test_x = meta_df[meta_df['group']==1]['Image Index'].values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "t5pnWY0M5eJy"
   },
   "source": [
    "## Build dataloader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "c1yQLt9b_2YE"
   },
   "outputs": [],
   "source": [
    "from skimage.io import imread\n",
    "from skimage.transform import resize\n",
    "import numpy as np\n",
    "from tensorflow.keras.utils import Sequence\n",
    "from tensorflow.keras.applications.mobilenet_v2 import preprocess_input\n",
    "\n",
    "class ChestXraySequence(Sequence):\n",
    "    def __init__(self, x_set, y_set, batch_size,folder):\n",
    "        self.x, self.y = x_set, y_set\n",
    "        self.batch_size = batch_size\n",
    "        self.folder = folder\n",
    "\n",
    "    def __len__(self):\n",
    "        return int(np.ceil(len(self.x) / float(self.batch_size)))\n",
    "\n",
    "    def __getitem__(self, idx):\n",
    "        batch_x = self.x[idx * self.batch_size:(idx + 1) * self.batch_size]\n",
    "        batch_y = self.y[idx * self.batch_size:(idx + 1) * self.batch_size]\n",
    "\n",
    "        count = len(batch_x)\n",
    "\n",
    "        img_batch = np.repeat((np.array([ imread(os.path.join(self.folder, file_name),as_gray=True) for file_name in batch_x],\n",
    "                                         dtype=np.float32)).reshape(count,224,224,1),3,3)\n",
    "\n",
    "        return preprocess_input(img_batch), np.array(batch_y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "6Cq0362U_2d3"
   },
   "outputs": [],
   "source": [
    "BATCH_SIZE=32\n",
    "train_seq = ChestXraySequence(x_set=train_x,\n",
    "                              y_set=train_y,\n",
    "                              batch_size=BATCH_SIZE,\n",
    "                              folder=os.path.join(DATA_DIR,'train_val','images','train'))\n",
    "test_seq = ChestXraySequence(x_set=test_x,\n",
    "                              y_set=test_y,\n",
    "                             batch_size=BATCH_SIZE,\n",
    "                              folder=os.path.join(DATA_DIR,'train_val','images','val'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "L5d4_pVp_2gQ"
   },
   "outputs": [],
   "source": [
    "x, y = test_seq[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "lpAy-kTAFSSu",
    "outputId": "7ca1d04a-0e63-401c-ef43-41bbc74ed375"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((32, 224, 224, 3), (32, 14))"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.shape, y.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "rb2uJPupFTOw"
   },
   "source": [
    "## Inspect the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "y8DhrWiuFQO0"
   },
   "outputs": [],
   "source": [
    "sample_img, sample_y = x[:10], y[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "colab_type": "code",
    "id": "vV4akGC0_2j3",
    "outputId": "e6431f4e-b462-4829-812d-b3829a740555"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n",
      "Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x1440 with 10 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(5,2, figsize=(20,20))\n",
    "for i, (img, label) in enumerate(zip(sample_img, sample_y)):\n",
    "    ax[i//2,i%2].title.set_text(convert_to_label_string(label))\n",
    "    ax[i//2,i%2].imshow(img+0.5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "EIcOEte1HbVI"
   },
   "source": [
    "## Baseline Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 105
    },
    "colab_type": "code",
    "id": "msKlbB6FFMLQ",
    "outputId": "ef8dd7d4-120d-4796-8130-4f8e5b07fdbe"
   },
   "outputs": [],
   "source": [
    "from tensorflow.keras.models import Model\n",
    "pretrained_model = tf.keras.applications.MobileNetV2(include_top=False, pooling='avg')\n",
    "for layer in pretrained_model.layers:\n",
    "  layer.trainable = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 221
    },
    "colab_type": "code",
    "id": "y51n14gLHnW3",
    "outputId": "1c90c8be-77bf-4ccb-c643-f0a554d1261c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "__________________________________________________________________________________________________\n",
      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      "input_2 (InputLayer)            (None, None, None, 3 0                                            \n",
      "__________________________________________________________________________________________________\n",
      "Conv1_pad (ZeroPadding2D)       (None, None, None, 3 0           input_2[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "Conv1 (Conv2D)                  (None, None, None, 3 864         Conv1_pad[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "bn_Conv1 (BatchNormalizationV1) (None, None, None, 3 128         Conv1[0][0]                      \n",
      "__________________________________________________________________________________________________\n",
      "Conv1_relu (ReLU)               (None, None, None, 3 0           bn_Conv1[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "expanded_conv_depthwise (Depthw (None, None, None, 3 288         Conv1_relu[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "expanded_conv_depthwise_BN (Bat (None, None, None, 3 128         expanded_conv_depthwise[0][0]    \n",
      "__________________________________________________________________________________________________\n",
      "expanded_conv_depthwise_relu (R (None, None, None, 3 0           expanded_conv_depthwise_BN[0][0] \n",
      "__________________________________________________________________________________________________\n",
      "expanded_conv_project (Conv2D)  (None, None, None, 1 512         expanded_conv_depthwise_relu[0][0\n",
      "__________________________________________________________________________________________________\n",
      "expanded_conv_project_BN (Batch (None, None, None, 1 64          expanded_conv_project[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "block_1_expand (Conv2D)         (None, None, None, 9 1536        expanded_conv_project_BN[0][0]   \n",
      "__________________________________________________________________________________________________\n",
      "block_1_expand_BN (BatchNormali (None, None, None, 9 384         block_1_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_1_expand_relu (ReLU)      (None, None, None, 9 0           block_1_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_1_pad (ZeroPadding2D)     (None, None, None, 9 0           block_1_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_1_depthwise (DepthwiseCon (None, None, None, 9 864         block_1_pad[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_1_depthwise_BN (BatchNorm (None, None, None, 9 384         block_1_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_1_depthwise_relu (ReLU)   (None, None, None, 9 0           block_1_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_1_project (Conv2D)        (None, None, None, 2 2304        block_1_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_1_project_BN (BatchNormal (None, None, None, 2 96          block_1_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_2_expand (Conv2D)         (None, None, None, 1 3456        block_1_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_2_expand_BN (BatchNormali (None, None, None, 1 576         block_2_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_2_expand_relu (ReLU)      (None, None, None, 1 0           block_2_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_2_depthwise (DepthwiseCon (None, None, None, 1 1296        block_2_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_2_depthwise_BN (BatchNorm (None, None, None, 1 576         block_2_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_2_depthwise_relu (ReLU)   (None, None, None, 1 0           block_2_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_2_project (Conv2D)        (None, None, None, 2 3456        block_2_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_2_project_BN (BatchNormal (None, None, None, 2 96          block_2_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_2_add (Add)               (None, None, None, 2 0           block_1_project_BN[0][0]         \n",
      "                                                                 block_2_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_3_expand (Conv2D)         (None, None, None, 1 3456        block_2_add[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_3_expand_BN (BatchNormali (None, None, None, 1 576         block_3_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_3_expand_relu (ReLU)      (None, None, None, 1 0           block_3_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_3_pad (ZeroPadding2D)     (None, None, None, 1 0           block_3_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_3_depthwise (DepthwiseCon (None, None, None, 1 1296        block_3_pad[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_3_depthwise_BN (BatchNorm (None, None, None, 1 576         block_3_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_3_depthwise_relu (ReLU)   (None, None, None, 1 0           block_3_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_3_project (Conv2D)        (None, None, None, 3 4608        block_3_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_3_project_BN (BatchNormal (None, None, None, 3 128         block_3_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_4_expand (Conv2D)         (None, None, None, 1 6144        block_3_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_4_expand_BN (BatchNormali (None, None, None, 1 768         block_4_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_4_expand_relu (ReLU)      (None, None, None, 1 0           block_4_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_4_depthwise (DepthwiseCon (None, None, None, 1 1728        block_4_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_4_depthwise_BN (BatchNorm (None, None, None, 1 768         block_4_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_4_depthwise_relu (ReLU)   (None, None, None, 1 0           block_4_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_4_project (Conv2D)        (None, None, None, 3 6144        block_4_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_4_project_BN (BatchNormal (None, None, None, 3 128         block_4_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_4_add (Add)               (None, None, None, 3 0           block_3_project_BN[0][0]         \n",
      "                                                                 block_4_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_5_expand (Conv2D)         (None, None, None, 1 6144        block_4_add[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_5_expand_BN (BatchNormali (None, None, None, 1 768         block_5_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_5_expand_relu (ReLU)      (None, None, None, 1 0           block_5_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_5_depthwise (DepthwiseCon (None, None, None, 1 1728        block_5_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_5_depthwise_BN (BatchNorm (None, None, None, 1 768         block_5_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_5_depthwise_relu (ReLU)   (None, None, None, 1 0           block_5_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_5_project (Conv2D)        (None, None, None, 3 6144        block_5_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_5_project_BN (BatchNormal (None, None, None, 3 128         block_5_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_5_add (Add)               (None, None, None, 3 0           block_4_add[0][0]                \n",
      "                                                                 block_5_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_6_expand (Conv2D)         (None, None, None, 1 6144        block_5_add[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_6_expand_BN (BatchNormali (None, None, None, 1 768         block_6_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_6_expand_relu (ReLU)      (None, None, None, 1 0           block_6_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_6_pad (ZeroPadding2D)     (None, None, None, 1 0           block_6_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_6_depthwise (DepthwiseCon (None, None, None, 1 1728        block_6_pad[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_6_depthwise_BN (BatchNorm (None, None, None, 1 768         block_6_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_6_depthwise_relu (ReLU)   (None, None, None, 1 0           block_6_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_6_project (Conv2D)        (None, None, None, 6 12288       block_6_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_6_project_BN (BatchNormal (None, None, None, 6 256         block_6_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_7_expand (Conv2D)         (None, None, None, 3 24576       block_6_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_7_expand_BN (BatchNormali (None, None, None, 3 1536        block_7_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_7_expand_relu (ReLU)      (None, None, None, 3 0           block_7_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_7_depthwise (DepthwiseCon (None, None, None, 3 3456        block_7_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_7_depthwise_BN (BatchNorm (None, None, None, 3 1536        block_7_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_7_depthwise_relu (ReLU)   (None, None, None, 3 0           block_7_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_7_project (Conv2D)        (None, None, None, 6 24576       block_7_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_7_project_BN (BatchNormal (None, None, None, 6 256         block_7_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_7_add (Add)               (None, None, None, 6 0           block_6_project_BN[0][0]         \n",
      "                                                                 block_7_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_8_expand (Conv2D)         (None, None, None, 3 24576       block_7_add[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_8_expand_BN (BatchNormali (None, None, None, 3 1536        block_8_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_8_expand_relu (ReLU)      (None, None, None, 3 0           block_8_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_8_depthwise (DepthwiseCon (None, None, None, 3 3456        block_8_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_8_depthwise_BN (BatchNorm (None, None, None, 3 1536        block_8_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_8_depthwise_relu (ReLU)   (None, None, None, 3 0           block_8_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_8_project (Conv2D)        (None, None, None, 6 24576       block_8_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_8_project_BN (BatchNormal (None, None, None, 6 256         block_8_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_8_add (Add)               (None, None, None, 6 0           block_7_add[0][0]                \n",
      "                                                                 block_8_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_9_expand (Conv2D)         (None, None, None, 3 24576       block_8_add[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_9_expand_BN (BatchNormali (None, None, None, 3 1536        block_9_expand[0][0]             \n",
      "__________________________________________________________________________________________________\n",
      "block_9_expand_relu (ReLU)      (None, None, None, 3 0           block_9_expand_BN[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_9_depthwise (DepthwiseCon (None, None, None, 3 3456        block_9_expand_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_9_depthwise_BN (BatchNorm (None, None, None, 3 1536        block_9_depthwise[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "block_9_depthwise_relu (ReLU)   (None, None, None, 3 0           block_9_depthwise_BN[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_9_project (Conv2D)        (None, None, None, 6 24576       block_9_depthwise_relu[0][0]     \n",
      "__________________________________________________________________________________________________\n",
      "block_9_project_BN (BatchNormal (None, None, None, 6 256         block_9_project[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_9_add (Add)               (None, None, None, 6 0           block_8_add[0][0]                \n",
      "                                                                 block_9_project_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_10_expand (Conv2D)        (None, None, None, 3 24576       block_9_add[0][0]                \n",
      "__________________________________________________________________________________________________\n",
      "block_10_expand_BN (BatchNormal (None, None, None, 3 1536        block_10_expand[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_10_expand_relu (ReLU)     (None, None, None, 3 0           block_10_expand_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_10_depthwise (DepthwiseCo (None, None, None, 3 3456        block_10_expand_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_10_depthwise_BN (BatchNor (None, None, None, 3 1536        block_10_depthwise[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_10_depthwise_relu (ReLU)  (None, None, None, 3 0           block_10_depthwise_BN[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "block_10_project (Conv2D)       (None, None, None, 9 36864       block_10_depthwise_relu[0][0]    \n",
      "__________________________________________________________________________________________________\n",
      "block_10_project_BN (BatchNorma (None, None, None, 9 384         block_10_project[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "block_11_expand (Conv2D)        (None, None, None, 5 55296       block_10_project_BN[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_11_expand_BN (BatchNormal (None, None, None, 5 2304        block_11_expand[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_11_expand_relu (ReLU)     (None, None, None, 5 0           block_11_expand_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_11_depthwise (DepthwiseCo (None, None, None, 5 5184        block_11_expand_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_11_depthwise_BN (BatchNor (None, None, None, 5 2304        block_11_depthwise[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_11_depthwise_relu (ReLU)  (None, None, None, 5 0           block_11_depthwise_BN[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "block_11_project (Conv2D)       (None, None, None, 9 55296       block_11_depthwise_relu[0][0]    \n",
      "__________________________________________________________________________________________________\n",
      "block_11_project_BN (BatchNorma (None, None, None, 9 384         block_11_project[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "block_11_add (Add)              (None, None, None, 9 0           block_10_project_BN[0][0]        \n",
      "                                                                 block_11_project_BN[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_12_expand (Conv2D)        (None, None, None, 5 55296       block_11_add[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "block_12_expand_BN (BatchNormal (None, None, None, 5 2304        block_12_expand[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_12_expand_relu (ReLU)     (None, None, None, 5 0           block_12_expand_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_12_depthwise (DepthwiseCo (None, None, None, 5 5184        block_12_expand_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_12_depthwise_BN (BatchNor (None, None, None, 5 2304        block_12_depthwise[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_12_depthwise_relu (ReLU)  (None, None, None, 5 0           block_12_depthwise_BN[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "block_12_project (Conv2D)       (None, None, None, 9 55296       block_12_depthwise_relu[0][0]    \n",
      "__________________________________________________________________________________________________\n",
      "block_12_project_BN (BatchNorma (None, None, None, 9 384         block_12_project[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "block_12_add (Add)              (None, None, None, 9 0           block_11_add[0][0]               \n",
      "                                                                 block_12_project_BN[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_13_expand (Conv2D)        (None, None, None, 5 55296       block_12_add[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "block_13_expand_BN (BatchNormal (None, None, None, 5 2304        block_13_expand[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_13_expand_relu (ReLU)     (None, None, None, 5 0           block_13_expand_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_13_pad (ZeroPadding2D)    (None, None, None, 5 0           block_13_expand_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_13_depthwise (DepthwiseCo (None, None, None, 5 5184        block_13_pad[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "block_13_depthwise_BN (BatchNor (None, None, None, 5 2304        block_13_depthwise[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_13_depthwise_relu (ReLU)  (None, None, None, 5 0           block_13_depthwise_BN[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "block_13_project (Conv2D)       (None, None, None, 1 92160       block_13_depthwise_relu[0][0]    \n",
      "__________________________________________________________________________________________________\n",
      "block_13_project_BN (BatchNorma (None, None, None, 1 640         block_13_project[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "block_14_expand (Conv2D)        (None, None, None, 9 153600      block_13_project_BN[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_14_expand_BN (BatchNormal (None, None, None, 9 3840        block_14_expand[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_14_expand_relu (ReLU)     (None, None, None, 9 0           block_14_expand_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_14_depthwise (DepthwiseCo (None, None, None, 9 8640        block_14_expand_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_14_depthwise_BN (BatchNor (None, None, None, 9 3840        block_14_depthwise[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_14_depthwise_relu (ReLU)  (None, None, None, 9 0           block_14_depthwise_BN[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "block_14_project (Conv2D)       (None, None, None, 1 153600      block_14_depthwise_relu[0][0]    \n",
      "__________________________________________________________________________________________________\n",
      "block_14_project_BN (BatchNorma (None, None, None, 1 640         block_14_project[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "block_14_add (Add)              (None, None, None, 1 0           block_13_project_BN[0][0]        \n",
      "                                                                 block_14_project_BN[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_15_expand (Conv2D)        (None, None, None, 9 153600      block_14_add[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "block_15_expand_BN (BatchNormal (None, None, None, 9 3840        block_15_expand[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_15_expand_relu (ReLU)     (None, None, None, 9 0           block_15_expand_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_15_depthwise (DepthwiseCo (None, None, None, 9 8640        block_15_expand_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_15_depthwise_BN (BatchNor (None, None, None, 9 3840        block_15_depthwise[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_15_depthwise_relu (ReLU)  (None, None, None, 9 0           block_15_depthwise_BN[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "block_15_project (Conv2D)       (None, None, None, 1 153600      block_15_depthwise_relu[0][0]    \n",
      "__________________________________________________________________________________________________\n",
      "block_15_project_BN (BatchNorma (None, None, None, 1 640         block_15_project[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "block_15_add (Add)              (None, None, None, 1 0           block_14_add[0][0]               \n",
      "                                                                 block_15_project_BN[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "block_16_expand (Conv2D)        (None, None, None, 9 153600      block_15_add[0][0]               \n",
      "__________________________________________________________________________________________________\n",
      "block_16_expand_BN (BatchNormal (None, None, None, 9 3840        block_16_expand[0][0]            \n",
      "__________________________________________________________________________________________________\n",
      "block_16_expand_relu (ReLU)     (None, None, None, 9 0           block_16_expand_BN[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_16_depthwise (DepthwiseCo (None, None, None, 9 8640        block_16_expand_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "block_16_depthwise_BN (BatchNor (None, None, None, 9 3840        block_16_depthwise[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "block_16_depthwise_relu (ReLU)  (None, None, None, 9 0           block_16_depthwise_BN[0][0]      \n",
      "__________________________________________________________________________________________________\n",
      "block_16_project (Conv2D)       (None, None, None, 3 307200      block_16_depthwise_relu[0][0]    \n",
      "__________________________________________________________________________________________________\n",
      "block_16_project_BN (BatchNorma (None, None, None, 3 1280        block_16_project[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "Conv_1 (Conv2D)                 (None, None, None, 1 409600      block_16_project_BN[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "Conv_1_bn (BatchNormalizationV1 (None, None, None, 1 5120        Conv_1[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "out_relu (ReLU)                 (None, None, None, 1 0           Conv_1_bn[0][0]                  \n",
      "__________________________________________________________________________________________________\n",
      "global_average_pooling2d_1 (Glo (None, 1280)         0           out_relu[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "dense_1 (Dense)                 (None, 14)           17934       global_average_pooling2d_1[0][0] \n",
      "==================================================================================================\n",
      "Total params: 2,275,918\n",
      "Trainable params: 17,934\n",
      "Non-trainable params: 2,257,984\n",
      "__________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "def build_model(base):\n",
    "    predictions = tf.keras.layers.Dense(len(class_list), activation='sigmoid')(base.output)\n",
    "    return Model(inputs=base.input,outputs=predictions)\n",
    "    \n",
    "model = build_model(pretrained_model)\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "oqCKIUqiKMWT"
   },
   "source": [
    "## Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "kIROeM18Kd3h"
   },
   "outputs": [],
   "source": [
    "LEARNING_RATE = 0.0001\n",
    "EPOCHS = 10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "UUD19CtAKK60"
   },
   "outputs": [],
   "source": [
    "model.compile(\n",
    "  optimizer= tf.keras.optimizers.Adam(LEARNING_RATE),\n",
    "  loss='binary_crossentropy',\n",
    "  metrics=['acc'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "QMOFY0dcKSwY"
   },
   "outputs": [],
   "source": [
    "save_best = tf.keras.callbacks.ModelCheckpoint('best_model',save_best_only=True)\n",
    "early_stopping = tf.keras.callbacks.EarlyStopping(patience=5)\n",
    "reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(patience=3,min_lr=LEARNING_RATE/1000)\n",
    "tb_cb = tf.keras.callbacks.TensorBoard(log_dir='/onepanel/output/model4')\n",
    "hist = tf.keras.callbacks.History()\n",
    "callbacks = [save_best, early_stopping, reduce_lr, hist, tb_cb]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Sse96iWcKbJ-"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "156/156 [==============================] - 17s 108ms/step - loss: 0.3255 - acc: 0.8789\n",
      "1299/1299 [==============================] - 166s 127ms/step - loss: 0.3225 - acc: 0.8806 - val_loss: 0.3255 - val_acc: 0.8789\n",
      "Epoch 2/10\n",
      "156/156 [==============================] - 16s 105ms/step - loss: 0.3218 - acc: 0.8809\n",
      "1299/1299 [==============================] - 175s 135ms/step - loss: 0.3063 - acc: 0.8862 - val_loss: 0.3218 - val_acc: 0.8809\n",
      "Epoch 3/10\n",
      "  82/1299 [>.............................] - ETA: 2:22 - loss: 0.2992 - acc: 0.8869"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Process ForkPoolWorker-6:\n",
      "Traceback (most recent call last):\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/multiprocessing/process.py\", line 258, in _bootstrap\n",
      "    self.run()\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/multiprocessing/process.py\", line 93, in run\n",
      "    self._target(*self._args, **self._kwargs)\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/multiprocessing/pool.py\", line 119, in worker\n",
      "    result = (True, func(*args, **kwds))\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/tensorflow/python/keras/utils/data_utils.py\", line 445, in get_index\n",
      "    return _SHARED_SEQUENCES[uid][i]\n",
      "  File \"<ipython-input-13-95c5675e4ef3>\", line 22, in __getitem__\n",
      "    img_batch = np.repeat((np.array([ imread(os.path.join(self.folder, file_name),as_gray=True) for file_name in batch_x],\n",
      "  File \"<ipython-input-13-95c5675e4ef3>\", line 22, in <listcomp>\n",
      "    img_batch = np.repeat((np.array([ imread(os.path.join(self.folder, file_name),as_gray=True) for file_name in batch_x],\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/skimage/io/_io.py\", line 61, in imread\n",
      "    img = call_plugin('imread', fname, plugin=plugin, **plugin_args)\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/skimage/io/manage_plugins.py\", line 210, in call_plugin\n",
      "    return func(*args, **kwargs)\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/imageio/core/functions.py\", line 221, in imread\n",
      "    reader = read(uri, format, \"i\", **kwargs)\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/imageio/core/functions.py\", line 143, in get_reader\n",
      "    return format.get_reader(request)\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/imageio/core/format.py\", line 164, in get_reader\n",
      "    return self.Reader(self, request)\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/imageio/core/format.py\", line 214, in __init__\n",
      "    self._open(**self.request.kwargs.copy())\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/imageio/plugins/pillow.py\", line 293, in _open\n",
      "    return PillowFormat.Reader._open(self, pilmode=pilmode, as_gray=as_gray)\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/imageio/plugins/pillow.py\", line 137, in _open\n",
      "    pil_try_read(self._im)\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/imageio/plugins/pillow.py\", line 518, in pil_try_read\n",
      "    im.getdata()[0]\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/PIL/Image.py\", line 1277, in getdata\n",
      "    self.load()\n",
      "  File \"/home/onepanel/.conda/lib/python3.6/site-packages/PIL/ImageFile.py\", line 242, in load\n",
      "    n, err_code = decoder.decode(b)\n",
      "KeyboardInterrupt\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-27-665fb57f87f9>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      6\u001b[0m                               \u001b[0mvalidation_steps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtest_seq\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m                               \u001b[0mmax_queue_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m4\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 8\u001b[0;31m                               use_multiprocessing=True)\n\u001b[0m",
      "\u001b[0;32m~/.conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mfit_generator\u001b[0;34m(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)\u001b[0m\n\u001b[1;32m   1424\u001b[0m         \u001b[0muse_multiprocessing\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0muse_multiprocessing\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1425\u001b[0m         \u001b[0mshuffle\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mshuffle\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1426\u001b[0;31m         initial_epoch=initial_epoch)\n\u001b[0m\u001b[1;32m   1427\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1428\u001b[0m   def evaluate_generator(self,\n",
      "\u001b[0;32m~/.conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py\u001b[0m in \u001b[0;36mmodel_iteration\u001b[0;34m(model, data, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch, mode, batch_size, **kwargs)\u001b[0m\n\u001b[1;32m    175\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    176\u001b[0m     \u001b[0;32mfor\u001b[0m \u001b[0mstep\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msteps_per_epoch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 177\u001b[0;31m       \u001b[0mbatch_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_get_next_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput_generator\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    178\u001b[0m       \u001b[0;32mif\u001b[0m \u001b[0mbatch_data\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    179\u001b[0m         \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstop_training\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/.conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py\u001b[0m in \u001b[0;36m_get_next_batch\u001b[0;34m(output_generator, mode)\u001b[0m\n\u001b[1;32m    256\u001b[0m   \u001b[0;34m\"\"\"Retrieves the next batch of input data.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    257\u001b[0m   \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 258\u001b[0;31m     \u001b[0mgenerator_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput_generator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    259\u001b[0m   \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0merrors\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mOutOfRangeError\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    260\u001b[0m     \u001b[0;31m# Returning `None` will trigger looping to stop.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/.conda/lib/python3.6/site-packages/tensorflow/python/keras/utils/data_utils.py\u001b[0m in \u001b[0;36mget\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    647\u001b[0m     \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    648\u001b[0m       \u001b[0;32mwhile\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_running\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 649\u001b[0;31m         \u001b[0minputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mqueue\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mblock\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    650\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mqueue\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtask_done\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    651\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0minputs\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/.conda/lib/python3.6/multiprocessing/pool.py\u001b[0m in \u001b[0;36mget\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    636\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    637\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 638\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    639\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mready\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    640\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mTimeoutError\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/.conda/lib/python3.6/multiprocessing/pool.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    633\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    634\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 635\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_event\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    636\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    637\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/.conda/lib/python3.6/threading.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    549\u001b[0m             \u001b[0msignaled\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_flag\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    550\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0msignaled\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 551\u001b[0;31m                 \u001b[0msignaled\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_cond\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    552\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0msignaled\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    553\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/.conda/lib/python3.6/threading.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    293\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m    \u001b[0;31m# restore state no matter what (e.g., KeyboardInterrupt)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    294\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mtimeout\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 295\u001b[0;31m                 \u001b[0mwaiter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0macquire\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    296\u001b[0m                 \u001b[0mgotit\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    297\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "history = model.fit_generator(train_seq,\n",
    "                              steps_per_epoch=len(train_seq),\n",
    "                              epochs=EPOCHS,\n",
    "                              callbacks=callbacks,\n",
    "                              validation_data=test_seq,\n",
    "                              validation_steps=len(test_seq),\n",
    "                              max_queue_size=4,\n",
    "                              use_multiprocessing=True)"
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "include_colab_link": true,
   "machine_shape": "hm",
   "name": "code-lab-3-chestxray8-curaeaidlhw.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}