{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Tks9e_G7fzRX"
   },
   "source": [
    "# Model Interpretation Methods"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "0Ioclbd4f4jg"
   },
   "source": [
    "Welcome to the final assignment of course 3! In this assignment we will focus on the interpretation of machine learning and deep learning models. Using the techniques we've learned this week we'll revisit some of the models we've built throughout the course and try to understand a little more about what they're doing.\n",
    "\n",
    "In this assignment you'll use various methods to interpret different types of machine learning models. In particular, you'll learn about the following topics:\n",
    "\n",
    "- Interpreting Deep Learning Models\n",
    "    - Understanding output using GradCAMs\n",
    "- Feature Importance in Machine Learning\n",
    "    - Permutation Method\n",
    "    - SHAP Values\n",
    "\n",
    "Let's get started."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### This assignment covers the folowing topics:\n",
    "\n",
    "- [1. Interpreting Deep Learning Models](#1)\n",
    "  - [1.1 GradCAM](#1-1)\n",
    "    - [1.1.1 Getting Intermediate Layers](#1-1-1)\n",
    "    - [1.1.2 Getting Gradients](#1-1-2)\n",
    "    - [1.1.3 Implementing GradCAM](#1-1-3)\n",
    "      - [Exercise 1](#ex-01)\n",
    "    - [1.1.4 Using GradCAM to Visualize Multiple Labels](#1-1-4)\n",
    "      - [Exercise 2](#ex-02)\n",
    "- [2. Feature Importance in Machine Learning](#2)\n",
    "  - [2.1 Permuation Method for Feature Importance](#2-1)\n",
    "    - [2.1.1 Implementing Permutation](#2-1-1)\n",
    "      - [Exercise 3](#ex-03)\n",
    "    - [2.1.2 Implementing Importance](#2-1-2)\n",
    "      - [Exercise 4](#ex-04)\n",
    "    - [2.1.3 Computing our Feature Importance](#2-1-3)\n",
    "  - [2.2 Shapley Values for Random Forests](#2-2)\n",
    "    - [2.2.1 Visualizing Feature Importance on Specific Individuals](#2-2-1)\n",
    "    - [2.2.2 Visualizing Feature Importance on Aggregate](#2-2-2)\n",
    "    - [2.2.3 Visualizing Interactions between Features](#2-2-3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "p4RvDHBOha2Y"
   },
   "source": [
    "## Packages\n",
    "\n",
    "We'll first import the necessary packages for this assignment.\n",
    "\n",
    "- `keras`: we'll use this framework to interact with our deep learning model\n",
    "- `matplotlib`: standard plotting library\n",
    "- `pandas`: we'll use this to manipulate data\n",
    "- `numpy`: standard python library for numerical operations\n",
    "- `cv2`: library that contains convenience functions for image processing\n",
    "- `sklearn`: standard machine learning library\n",
    "- `lifelines`: we'll use their implementation of the c-index\n",
    "- `shap`: library for interpreting and visualizing machine learning models using shapley values\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 80
    },
    "colab_type": "code",
    "id": "i9OcyAhSesQc",
    "outputId": "b32cbd74-6f95-476e-e0db-c5739e886d21"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "import keras\n",
    "from keras import backend as K\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import cv2\n",
    "import sklearn\n",
    "import lifelines\n",
    "import shap\n",
    "\n",
    "\n",
    "from util import *\n",
    "\n",
    "# This sets a common size for all the figures we will draw.\n",
    "plt.rcParams['figure.figsize'] = [10, 7]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "RaIViDj8khSg"
   },
   "source": [
    "<a name=\"1\"></a>\n",
    "## 1 Interpreting Deep Learning Models\n",
    "\n",
    "To start, let's try understanding our X-ray diagnostic model from Course 1 Week 1. Run the next cell to load in the model (it should take a few seconds to complete)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 632
    },
    "colab_type": "code",
    "id": "vrzRJFrXhi6x",
    "outputId": "1ec745f3-a764-436a-c1cb-74ed4e5c73ae"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Got loss weights\n",
      "Loaded DenseNet\n",
      "Added layers\n",
      "Compiled Model\n",
      "Loaded Weights\n"
     ]
    }
   ],
   "source": [
    "model = load_C3M3_model()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "B07VP7edyb98"
   },
   "source": [
    "Let's load in an X-ray image to develop on. Run the next cell to load and show the image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 432
    },
    "colab_type": "code",
    "id": "cVVXgMweyGtz",
    "outputId": "37992056-b6ea-4316-a44d-6c98b7074423",
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "IMAGE_DIR = 'nih_new/images-small/'\n",
    "df = pd.read_csv(\"nih_new/train-small.csv\")\n",
    "im_path = IMAGE_DIR + '00025288_001.png' \n",
    "x = load_image(im_path, df, preprocess=False)\n",
    "plt.imshow(x, cmap = 'gray')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "1N1_YANDztAo"
   },
   "source": [
    "Next, let's get our predictions. Before we plug the image into our model, we have to normalize it. Run the next cell to compute the mean and standard deviation of the images in our training set. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "s5I91kMHxUiz"
   },
   "outputs": [],
   "source": [
    "mean, std = get_mean_std_per_batch(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "IGX2R05t6ZLA"
   },
   "source": [
    "Now we are ready to normalize and run the image through our model to get predictions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 529
    },
    "colab_type": "code",
    "id": "-UG6DAnUzxk0",
    "outputId": "13fedfec-3aed-4830-e435-827bb1de1a9d"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAFcCAYAAADYnEUIAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8GearUAAAgAElEQVR4nO3deZwlZX3v8c+XAURZJMpohAGGi2gkgMIdEUUjYowgqxgQoiZuIIlGjEaD16gIRnFL9AJRUEFUFMEtExnBKCiigAzKIiJXZBFwwwVERGHwe/946sycPnN6uqfPUz2na77v16tfc06d6l893VP166pnlW0iImLuW2dNFyAiIupIQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPRYq0j6iKS3Nq+fIum6Gcb5gKQ31i1dxGiS0GMsSbpJ0j2SfivpZ00i3qjmMWx/3fajp1GWF0q6aOB7j7R9XM3yRIwqCT3G2X62NwJ2ARYB/9r/oaR110ipIsZUEnqMPdu3AV8EdpBkSS+X9APgBwCS9pV0haQ7JH1T0k6975W0s6RvS7pL0qeADfo+20PSrX3vt5T0WUm3S/qlpBMlPQb4APDE5mnhjmbf5VU3zfvDJV0v6VeSFkvavO8zSzpS0g+aMp4kSc1nj5T0NUl3SvpFU8aIGUlCj7EnaUvgWcB3mk0HAk8Atpe0M3Aq8DLgocDJwGJJD5C0PvB54GPAQ4CzgedMcox5wBeAm4GFwBbAmbavBY4ELra9ke1Nh3zvnsDbgUOARzQxzhzYbV/g8cBOzX7PbLYfB3wJ+BNgAXDCdH8vEYOS0GOcfb65I74I+Brwtmb7223/yvY9wBHAybYvtX2/7dOBPwC7NV/rAe+1fZ/tTwOXTXKsXYHNgdfavtv2721fNMm+g54HnGr727b/ALyecke/sG+f423fYftHwAXA45rt9wFbA5uv5jEjVpKEHuPsQNub2t7a9j80CRzglr59tgZe01Rl3NH8AdiSkpw3B27zxBnobp7kWFsCN9teNoNybt4f1/ZvgV9S7vJ7ftr3+ndAr4H3dYCAb0m6RtKLZ3D8CCAJPeam/gR9C/BvTeLvfT3I9ieBnwBb9OqrG1tNEvMWYKtJGlqnmpL0x5Q/LABI2pBS/XPblD+I/VPbh9venFJt9J+SHjnV90UMk4Qec90HgSMlPUHFhpL2kbQxcDGwDHilpPUkHUSpWhnmW5Q/AMc3MTaQtHvz2c+ABU2d/DCfBF4k6XGSHkCpGrrU9k1TFV7SwZIWNG9/Tfnj8cepf+yIlSWhx5xmeylwOHAiJSFeD7yw+exe4KDm/a+A5wKfnSTO/cB+wCOBHwG3NvsDnA9cA/xU0i+GfO+XgTcCn6H8UdgWOHSaP8LjgUsl/RZYDBxl+4Zpfm/EBMoCFxER3ZA79IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5YY7PVbbbZZl64cOGaOnxExJx0+eWX/8L2/GGfrbGEvnDhQpYuXbqmDh8RMSdJmmz6ilS5RER0RRJ6RERHJKFHRHTElAld0qmSfi7pu5N8Lkn/t1mt5SpJu9QvZkRETGU6d+gfAfZaxed7A9s1X0cA7x+9WBERsbqmTOi2L6TMVDeZA4CPurgE2FTSI2oVMCIipqdGHfoWTFxB5lYmrtSynKQjJC2VtPT222+vcOiIiOiZ1UZR26fYXmR70fz5Q/vFR0TEDNUYWHQbZT3GngVMY+mtWDu957n7rtb+r/nUF1oqSUT31LhDXwz8bdPbZTfgTts/qRA3IiJWw5R36JI+CewBbCbpVuDNwHoAtj8ALAGeRVn663fAi9oqbERETG7KhG77sCk+N/DyaiWKiIgZyUjRiIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIddd0ASIi1gY7nr7jau1/9d9dvdrHmNYduqS9JF0n6XpJRw/5fCtJF0j6jqSrJD1rtUsSEREjmTKhS5oHnATsDWwPHCZp+4Hd/hU4y/bOwKHAf9YuaERErNp07tB3Ba63fYPte4EzgQMG9jGwSfP6wcCP6xUxIiKmYzoJfQvglr73tzbb+h0DPF/SrcAS4B+HBZJ0hKSlkpbefvvtMyhuRERMplYvl8OAj9heADwL+JiklWLbPsX2ItuL5s+fX+nQEREB00votwFb9r1f0Gzr9xLgLADbFwMbAJvVKGBEREzPdBL6ZcB2kraRtD6l0XPxwD4/Ap4OIOkxlISeOpWIiFk0ZUK3vQx4BXAecC2lN8s1ko6VtH+z22uAwyVdCXwSeKFtt1XoiIhY2bQGFtleQmns7N/2pr7X3wN2r1u0iIhYHRn6HxHREUnoEREdkblcIiIAjnnwau5/ZzvlGEHu0CMiOiIJPSKiI5LQIyI6Igk9IqIjktAjIjoiCT0ioiOS0CMiOiIJPSKiI5LQIyI6Igk9IqIjktAjIjoic7lEp9x69Nenve+C45/SYkkiZl/u0CMiOiIJPSKiI5LQIyI6Igk9IqIjktAjIjoiCT0ioiOS0CMiOiIJPSKiI5LQIyI6Igk9IqIjktAjIjoiCT0ioiMyOVdEVLHw6HNWa/+bjt+npZKsvXKHHhHREUnoEREdkYQeEdERSegRER0xrYQuaS9J10m6XtLRk+xziKTvSbpG0ifqFjMiIqYyZS8XSfOAk4BnALcCl0labPt7fftsB7we2N32ryU9rK0CR0TEcNO5Q98VuN72DbbvBc4EDhjY53DgJNu/BrD987rFjIiIqUynH/oWwC19728FnjCwz6MAJH0DmAccY/vcKiWMWXXSkeev1v4v/8CeLZUkIlZXrYFF6wLbAXsAC4ALJe1o+47+nSQdARwBsNVWW1U6dERMx59ecMVq7f/Tpz2upZJEW6ZT5XIbsGXf+wXNtn63Aott32f7RuD/URL8BLZPsb3I9qL58+fPtMwRETHEdBL6ZcB2kraRtD5wKLB4YJ/PU+7OkbQZpQrmhorljIiIKUyZ0G0vA14BnAdcC5xl+xpJx0rav9ntPOCXkr4HXAC81vYv2yp0RESsbFp16LaXAEsGtr2p77WBVzdfERGxBmSkaERERyShR0R0RBJ6RERHJKFHRHREEnpEREckoUdEdEQSekRERyShR0R0RBJ6RERHJKFHRHREEnpEREckoUdEdEQSekRERyShR0R0RBJ6RERHJKFHRHREEnpEREckoUdEdEQSekRERyShR0R0RBJ6RERHJKFHRHREEnpEREckoUdEdEQSekRERyShR0R0RBJ6RERHJKFHRHREEnpEREckoUdEdEQSekRER6y7pgsQETEdC48+Z7X2v+n4fVoqyfjKHXpEREdMK6FL2kvSdZKul3T0KvZ7jiRLWlSviBERMR1TJnRJ84CTgL2B7YHDJG0/ZL+NgaOAS2sXMiIipjadO/Rdgett32D7XuBM4IAh+x0HvAP4fcXyRUTENE0noW8B3NL3/tZm23KSdgG2tL16rRYREVHNyI2iktYB/h14zTT2PULSUklLb7/99lEPHRERfaaT0G8Dtux7v6DZ1rMxsAPwVUk3AbsBi4c1jNo+xfYi24vmz58/81JHRMRKppPQLwO2k7SNpPWBQ4HFvQ9t32l7M9sLbS8ELgH2t720lRJHRMRQUyZ028uAVwDnAdcCZ9m+RtKxkvZvu4ARETE90xopansJsGRg25sm2XeP0YsVk7n2zx6zWvs/5vvXtlSSiBg3GSkaEdERSegRER2RhB4R0RFJ6BERHZGEHhHREUnoEREdkYQeEdERSegRER2RhB4R0RFJ6BERHZGEHhHREUnoEREdkYQeEdERSegRER2RhB4R0RFJ6BERHTGtBS4ion1fOX/b1dr/6Xv+sKWSxFyVO/SIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI4Yu37oC48+Z7X2v+n4fVoqSUTE3JI79IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI4Yu14uEePqmGOOaXX/iFHlDj0ioiOS0CMiOmJaVS6S9gLeB8wDPmT7+IHPXw28FFgG3A682PbNlcs6J+x4+o6rtf/Vf3d1SyWJiLXNlHfokuYBJwF7A9sDh0nafmC37wCLbO8EfBp4Z+2CRkTEqk2nymVX4HrbN9i+FzgTOKB/B9sX2P5d8/YSYEHdYkZExFSmk9C3AG7pe39rs20yLwG+OOwDSUdIWipp6e233z79UkZExJSqNopKej6wCHjXsM9tn2J7ke1F8+fPr3noiIi13nQaRW8Dtux7v6DZNoGkvwTeADzV9h/qFC8iIqZrOnfolwHbSdpG0vrAocDi/h0k7QycDOxv++f1ixkREVOZMqHbXga8AjgPuBY4y/Y1ko6VtH+z27uAjYCzJV0hafEk4SIioiXT6oduewmwZGDbm/pe/2XlckVExGrKSNGIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjkhCj4joiCT0iIiOSEKPiOiIJPSIiI5IQo+I6Igk9IiIjlh3OjtJ2gt4HzAP+JDt4wc+fwDwUeB/A78Enmv7prpFreSYB6/m/ne2U46IiMqmvEOXNA84Cdgb2B44TNL2A7u9BPi17UcC/wG8o3ZBIyJi1aZT5bIrcL3tG2zfC5wJHDCwzwHA6c3rTwNPl6R6xYyIiKnI9qp3kP4a2Mv2S5v3LwCeYPsVfft8t9nn1ub9D5t9fjEQ6wjgiObto4HrVqOsmwG/mHKvmUv8xB/H2Imf+IO2tj1/2AfTqkOvxfYpwCkz+V5JS20vqlykxE/8sY6d+Im/OqZT5XIbsGXf+wXNtqH7SFoXeDClcTQiImbJdBL6ZcB2kraRtD5wKLB4YJ/FwN81r/8aON9T1eVERERVU1a52F4m6RXAeZRui6favkbSscBS24uBDwMfk3Q98CtK0q9tRlU1iZ/4sxB/Lpc98TsUf8pG0YiImBsyUjQioiOS0CMiOiIJPSKiI5LQI0YkaR1Jm1SO+bAh2x5d8xjRPWPdKCrpcuBU4BO2f91C/A0o89D8ObBBb7vtF1eK/wDgOcBC+noU2T62Rvy+4zyMieX/Uc34bZF0MHCu7bsk/SuwC/BW29+uFP9BwGuArWwfLmk74NG2v1Ah9ieAI4H7KV17NwHeZ/tdo8Zu4l8HvNH2Wc371wAvsT04j9Iox7gaGEwAdwJLKf8PMx5L0vyu306Z/6n/3PxfM405EP8o4DTgLuBDwM7A0ba/VCl+q7mhLeN+h/5cYHPgMklnSnpm5TliPgb8KfBM4GuUQVN3VYz/X5R5bpYBd/d9VSFpf0k/AG6klP8m4IsV4x8k6QeS7pT0G0l3SfpNrfiUhHWXpCcDf0np/vr+ivFPA/4APLF5fxvw1kqxt7f9G+BAyu98G+AFlWID7AG8QNLZki4EHkWZV6mmLwLnAM9rvv6bksx/CnxkxNinUf4vlwFPo8zG+vERY/Z7cfP7/yvgTyi/++NX/S2rpbXc0Op1ZXvsvyh/ePanXJA/At4CPKRC3O80/17V/LsecEnFcn+35d/LlcBD+36OpwEfrhj/euAxLZa/V+63A3/Tv61S/KWDMYErK8W+pjlfzgaeWjN23zFeDtzanPNPauH3/+3JtgFXjxj78sE4vW2Vyt67Zt8HPLuFc6e13NDmdTXud+hI2gl4D/Au4DPAwcBvgPMrhL+v+fcOSTtQpixYqe5yBN+UtGPFeIPuc3ksXkfSOrYvAGrOOfEz29dWjDfoNkknU57EljRVVDXPyXslPZCmWkHStpQ79hpOpjwRbQhcKGlrynlZhaQvA08AdgD2Ad4r6d214jfmSVp+1y/p8ZTBg1DurEfxB0nrAD+Q9ApJzwY2GjFmv8slfQl4FnCepI2BP1aM32ZuaO+6auOvRMW/kpcDXwH+BnjAwGefrRD/pZTHtacCNwA/B46sWP7vAfdSZpW8Cria5i9+pfhfplwkJwCfpNytfLNi/PcBnwIOAw7qfVWM/6Am5nbN+0cAf1Ux/jMoj8u3A2dQEvAeteIPOd66FWMdOBibUkVVs7yPb87JG5vfzVWUap0NgUMqxN6IUlVxGvBZYLeKZV+H0uayafP+ocBOFeO3lhvavK7GvVH0f9m+YU2XY6aau7aV2L65UvwNgd8DotSBPhg4wyM0Zg3EP23IZrteo/G2wK22/yBpD2An4KO276gRvznGQ4HdKL+jSzwwpfMM4j3f9sclvXrY57b/fZT4a4KkBwPYHvvluST9me3vS9pl2Oeu1KDepjavq7FM6JNdLD21LhpJmwJ/y8q9UF5ZI35zjMcCT2neft32lbViz3WSrqBUES0EllAakf/c9rNGjDv0Yu8Z5aKX9DLbJ0t68ySx3zLT2APH2Y3y5PUYYH1KVchvba/mGoqrPEb1XliS3mv7VZL+m5V70GB7/5nGbuKfYvsISRcM+di29xwlft9xWs8NbZjV+dBXw8azdJwlwCWUx86a9W/A8q5Vh1MeNwE+3pyQJ4wY9yLbT5Z0FxMvGlFO6ip9oiUtoCSV3ZtNXweOcrOQSQV/dJn87SDgBNsnSPpOhbjvWcVnBmZ80ds+ufm3SuJehRMpk9ydTfmj97eUni41/Relm+Ll1Gtb+Fjzb+36fgBsH9H8+7Q24vdpLTe0el3VqnOai18MaeWvHP8qYMO+9xtSsQ59Fn4//wO8iPKHf13ghcD/VIx/KaUe8bvANs22VnsGVSz7Oyl9z9ejtPPcDjy/YvxeD52r+rZV68Uxl37Xk5T9YGDj5vW/Um6adq4Yv7Xc0OZ1Na536MCsdO7/mKTDgS/Qd4di+1eV4osy8KTn/mZbNc0i3g9n4mNhrYFF82331/d9RNKrKsWGclIfCfyb7RslbcOKO7yRSfrbYdttf7RC+L+y/bqm98ZNlIatC6nX1/p3zfoDV0h6J/AT6o8b+aakHW1fXTkuknYHjgG2ppybvafHKgOLKA3EZ/eNYXgX8AFKz6Aa2swNrV1XY53QKRf39ymd+4+lNPzV7O5zL+VEeAMrqi4M1DrpTgMulfS55v2BlMEzVUj6R+DNwM9Y8VhoSuNiDb+U9HxKDxood9PVVqKy/T3glX3vbwTeUSs+padFzwbA04FvUwa5jKp37ewDnG37zrpj3ngBJYG/Avgnyopgz6l5AODJwAsl3UhJWr2kW+P8+TCl3Jcz8aamll7MfYBTbJ8jqdagMWg3N7R2XY1lo2iPpO/Y3lnSVbZ3krQepWFxt0rxbwB29Yg9H6Y4xi6UCwdK2WvUEfdiX09ZjLuV5f6aXjonUEZaGvgm8MpaTwBtDw8fcrxNgTNt71Uh1vGUP9D3ULr6bQp8wfbId4jNU9dHbT9v1FhTHKe1XliSLq3xu1hF/C9QBho+g9J98R7gW7YfWyl+a7mhzetq3O/QBzv3/5S6A3+uB35XMR4Akjax/RtJD6E8jt/U99lDKlbp3EJp1GpFc2GP1CthCqdRnjD+gzLK9UW0Ox3F3ZQh+iOzfXRTFXKn7fsl3U2Z5qFG7PslbS1pfdv31ojZr3d+Uneai0EXSHoXpW67v8qiVrfCQ4C9gHfbvkPSI4DXVooNLeUGaPe6GveEfoqkPwHeSFm3dCPgTRXj302po7yAiSfdqF2TPgHsS3ncXKkXCvWqdG4AvirpHCaWf6RunZJeZ/udkk5geNezWl23Hmj7K5LUnOTHqEzIVuX/eKDr3DqUJ4GzasRubA78ZdPW01OjOgfK/+03JC2mb/6fUf9vG4PnZ39dUa3zs3d33j9yeaQeRv1s/07SD4FnSnom5em3ysRcjeq5YTauq7FO6LY/1Lz8GvWSYL/PN19V2d63+bfK3eAq/Kj5Wr/5qqXXTrG0YsxhJgwPpzxC1xwe3t91bhlwsyt1uWz6oe9B+SOxBNgbuIh6Cf2Hzdc6VO7GOxvnp1vuVthWl+A+beSG1q+rca9DHzbA6E7KJD9XVDrGAynTq15XI95A7N2BK2zf3TSC7AK8t0Zd2WzUs0o62PbZU20bIf7jKSf5psBxlJGu77R9SY34bVKZevaxlK6Ej5X0cODjtp9R+TgbAdj+bc24ffG3YEVPFJpjXVgh7oMp1Wl/0Wz6GnCsK41GlXQV8ETbdzfvNwQurtSg2ztGK7mhzetq3CfnWkTp1rZF8/UySr3ZByW9btTgkvYDrgDObd4/rnnEreX9lO5nj6XMy/1DKnXLs30/sHXTta0tr5/mthmxfZnt39q+1faLbB9UI5mrmY50sq8aZQfusf1HYJnK4hY/p/REqULSDs0gq2uAayRdLunPa8VvjvEO4BuUftyvbb7+uVL4Uyl19Ic0X7+htJnU0mqX4JZzQ2vX1VhXuVAm9tmld3fSPOaeQ/mrfzllcMcojqH0UPgqgO0rJNWs2llm25IOAE60/WFJL6kYv5V6Vkl7U2ax20LS/+37aBNGn4WPqS4Mjzg83PbGzXGOo/Tf/hgr5rt5xCix+yxtes18kHIu/ha4uFJsgFOAV7vMoInKXDcfBJ5U8RgHUhb8qDVKtN+2tvu7Wb5FZaqHWlrtEkwLuaHt6wrGP6E/jIlDku8DHm77Hkk1TsL7hvQfrjnM9y5JrweeD/xFU1+8XsX4bdWz/phSz7c/JVn13EXpWzyqJ1J66HySMlq0agfuPvsPdGN7v6QrqdDoavsfmpcfkHQusIntq0aN22fDXjJvjvfVplqhphso52MbCf0eSU+2fREsr368p0bg5jq6hJJse12CX1SzSzDt5Ia2r6uxT+hnUP4K/1fzfj/gE82J/b0K8a+R9DeUeaG3owxy+WaFuD3PpUz9+xLbP5W0FWWwQhVu5hOR9CDb1bpYuUwgdqWkT9i+b8pvWH1/Suk/fBjl93MO8Enb11Q+zt2SngecSelVcBiVVoyS9BXbTwewfdPgtgpukPRGVlTRPZ+SgGv6HaUnx1eo28sL4O+B05u6dAG/ogxxH5ntP0o6yfbOlIFibaieG2bhuhrvRlEASYtYMYnNN2xXayFWWXPyDZRlrAScBxxn+/e1jtEmSU+kPGZuZHurpq7+ZX13j6PGb33gj8qMf4dR/tC9xfaJFWMvpMw93Tt/LgJe1UvAM4y5AWUe9wsovVx6t3CbUNZH/bOZxh44zp9QVuZaPigNOMYV19aV9HfDtts+veIxNmli1ly6EJXFPi6mrItQPYm1mRvavK7mQkJ/MmUBhNMkzackrxtbOM48ymNuzVVn+mdDXJ/yeFttClRJlwJ/DSxu7laQ9F3bO1SKfxErBv7sRzPwx/bIVRZNIt+HkswXUsYZnGr7tlFjt6npLvcqSh/021iR0H8DfLDmH6TZ0GJPjlann22urQ0pjaG9JGtXmmm0Ta1eV+Oc0JtG0EWUhptHSdqcMm/G7lN863Tjt7py+8CxRBlJuJvtoyvFvNT2E9RMkdBsu9L1hj9fbvt/S7ra9o7920aM+1HK0mpLKEPxv1uhuMOO09o0pZL+sWKf52HxH0XpcbKQiQmxysCc5hj7Ufrqr297G0mPo3QtHHkUo6RvMmT62Zp3/23QJPO491T63bRyXcH416E/G1heT2b7xyprB9ayvcsQ/edRVkA/mtJYUT2hN4+Fn2/+SFVJ6MAtkp4EWGWem6OoO3lZWwN/nk+pyz4KeGVfw1PV+dwpPSE+QZlqtXfc0yj196P6o6RN3ayu1FSRHGb7PyvEhjIP+geAD9HO5FbQbi+vDWyvcqGaUanMo/9kSgL+uu0aA4F6g9EOorT19GbPPIwyCV4NrQ2oG/eEfm/T7a+3yG/tVv71mkR4IKVb4X29Y9XQnHA961CeNmrWzx9JqSPegnJSfImyUnwtR1Hqi19JGfjzNGBovevqsD1b4x/anP73cNsn9d7Y/rXKdKu1Evoy2++vFGsybfbyanVqakn/CTySFTMWHinpGbZHOv9tf62J/x7b/dMW/LekWu13g9fVnlS4rmD8E/pZKqvCb9qcHC+m9MWtpbdy+5W0sHI7pX6sZ1lzrCoTOAG4zATXykjRpk3hubb/mdLH+kVtHKdlbU7/O0+Seg1yze9r5EFeKhO6QUkg/wB8jnbm6od2e3m1PTX1nsBj+n7/p1MGYdWyofrWNFaZq7/KDaXty5qX1a+rsa5DB5D0DPpamm3/T8XY81xGXPbeC5hne6RO/pLeYftfJB1iu+ZkUL34Qyf36anY8HSJK01VvCaoxWlKVWYS3JpyUwBlFPMttl8zYtwbWXnCrB5X7mHU35MDyhPesTUGGqnlqalVps99uZupfpv/6xNt77fq75x2/L0og7tuoPxfbE3pQXbeCDHbr58f94QOy7s+9TcM1XpsuwH4NHCa7Wp1zyrzfOxEmXNmlQsWzzB+/+PZWygt5svVaniS9H5Kdc7ZTByJ+tlJv2kt0dSBvoyyaAaUZcU+1H+DMGL8DQa7yA3bNuIxXmL7wwPbjq/RaC/pS8CBNcdHNHF7SfHBlAVMvtW8fwJlPvQ9Kh7rAUCvG+r3R/1DJ+mpzcuh9fO2Rx5cNNYJXdLLKAnr95S6varLWDUNrIeyYh7uUym9Lkaqdmnu3g6nNHT0n9C1G/3o7+FSm6Rhc2/Y9ZYAbIWkVXX/su3jKh2nzYndvj14MzBs24jHWAKcYfuM5v2JlCmNR56eQmVI/p9T+utXG7TUlxSH6tWBjxD/dbbf2byeMGGWpLfZ/j+jxG/iLB2onx+6bUaxxzyh/4Ayo1prKwr1HeuplB4Rm1Lu2o+zff0MYz3A9h8k/ZftanXmkxyr6kU+EHt329+Yatu4kc8VPjMAAAx9SURBVDSs2mNDyvq0D7U9co8CSftT6oirdvmT9KeUp6KPU0bR9g9c+oArDVxqjvVAmv7/lEnv7rB9VKXYrQ9aakP/9TR4bdW61iRdC+wzUD+/xPZjRo097o2iP6SlVUNgeUPWPpQ79IXAeyjTDTyF0kf6UTMMfTFlqtyqo+PWgBMoP8dU28aK7ff0XjdPYUdR/o/PpPwf1/BmVu7yV2N+8WdShsgvAPonWbsLGPnuECY0vAK8lDLv9zcoE2hVWVGrrcQt6SLbT9bEQXtQ7+lXk7we9n6m/omyMM2E+vkagcc9ob+esjL5pdSfawLgB5RHwnfZ7m/d/7Skv5jke6Zj/ab3wJMGui4Co9dBD5zMD9KKKWGrnNQqUwo8CZiviXPSbwLMGyX2bGmS1qspvYBOp8zaWW3YPMO7/I38uNskwtMlPcf2Z0aNN4n+lYp6/+7TfFXpidLXuDtBherS5zVxqi760ceTvB72fmYHsM9tehVVq5/vGfeEfjJwPgOjzSrayZMsHDDiH40jKSfepkzsugjlpBgpobd4MvesT6n/X5eJszj+hjLVwFhr2jAOovRS2HGy/+MRtT2x21ck/TstLBDh9lfSgolLz21AGdz1kEn2XR2fo3lClPQZT5yit4bHNjdIAh44cLO0weTfNjVJe9o+f8hN3raSqnQ2GPc69NYa/Jr48ymNlwuZ2IumSqPfsF4Ec4mkrV1hBfjZJumPlCe6ZbTzWN7q5E1N/M8A36U8XQC8AHis7ZWe+EY4xsspjaJtjXYdPF6NaSP6p7loNT/UJukttt/cZmeDcU/ob6MMxvlv2hlt9k3K/B6X0ze8etRH3dloKW/TbPSXjVWTdIXtx021rYVjVEmSkvrbWXqjpP/eI84ztKpGyxj/hD5sVsWa3RarXiB9cVtvKW9T213D5rLZ+mMn6WLgtZ64QMS7bT+xRvwm5tWUasf+0a5X2R55qTtJF/S97Y2SfveoXTwl3U8ZEyHggazoNFG9S3BtGr5G8nIecaUxGPM69Fmo6/uCpGfZXlI57my0lLdmbU7Y0/DuqXeporUFIvqcC3xKZXoNKD0tzq0R2PbTasQZEndONMpPou22r7G/Q1+PcmL3Goa+CpzsEVf76OslIkr/5Hspy9tBnV4ic/0O/SzbhzR3cMN6KlRbWX0ua3NgUd8xWlkgoond2mhXSQ8H3gZsbntvSdtTxpTM2TaluWDcE/qHKItC9DcM3W/7pWuuVFOb4rFwA9s11xWtTtLmLlMVbz3s87nYUFqbWpxLvInf6gIRbZP0RcpUxW+w/VhJ6wLfcTP/99pMLc7TP9ZVLsDjBxpRzldZ5LcatTCn8hx/LIQy5ekuwFttv2BNF2ZMHUM7A4t6ljBkgYgaZukJbDPbZ6ksko7tZc2NTrQ4T/+4J/T7JW1r+4cAKpPvVzsp1NKcyh3Q6sCojmhlYFGfNheI6A3v37el+FAW6H4oze9E0m7AyH3oO6K1efrHPaG/FrhgYIhszfmD255Tea5qdWBUR7Q9sKi1BSJs/6T5t82qs1dT5onZVtI3gPnMgUFps6S1efrHug4d6E1h+ejm7XW1hsg2sVudU3mum+sDo9qklecS7w0sqnJ+NoN+/g24g74FImp12W2OcRDwDuBhlBumql3/mnrzRzdxrxu1M0NXaOI8/VDm0akzT/84JvRVDJEF6j3yS/oaK+ZUpnm9lObRMANoQGXN0oVMbJj76Bor0JgYHDA22bYR4re6QERzjOuB/VxxLYCB+Dl3Ztm4Vrk8lTKHy7A75ZqP/KuaN3utJ+ljwLbAFaxouzCQi7JMHDeYvIdtm6nraXGm0cbPWkzmOXcmIemdwFuBeyj9/ncC/sn2x1f5jdOJPY536LNNLa2INNepzNu8vXOSLCdpb+BZwCHAp/o+2pjyu3pCpeO0skBEE7v35PtUyso5nx84xuiTROXcmVRvhLqkZ1Mapl8NXDjqtAgwpnfoszFEtjnOEcCxDKyIRL2FbOe671Iu+J+s6YKMkR9T5v7Zv/m3Z2vq3lF/vvlqQ/+T7+9Y0Q4A9Z6Ac+5Mrpd39wHOHtJbauTA46Y3RPbRlHrtxc37/VhR313Da4Ed2qynnOM2A74n6VtMvINba9sWbF8JXCnpDGAHyqpCBwM3AtXmL3e7K/tcbvvEFuNDzp1V+YKk71OqXP6+mfW1ziyd4/xEJOlCylJNdzXvNwbOsT3K4hP98c8FDnLlhWy7YrJJutbmuV4kPYrSzeww4BeUapd/tj10VO0Ix2lrgYhZmX4i586qqSzAcqft+5seU5vY/umoccf1Dr3n4ZR5VnrubbbV0vaKSHNaLr6hvk8Zqr2vmzVnJY28WvsQbS0Q0SpJG1DGMTySMsr1w7aXrdlSjaU/AxY2XTt7Rm4wHveE/lHgW00DEcCBwEcqxm97RaQ5SSuv17j8I8Z8itJZcBBwKGXA27mUdUqrz6Bpe3CgyXslXU6dnlk7acVKPP1q/P+eTpno7uvA3sD2rBiZGrTbA2hsq1xUWgkWUEaYPaXZfKHt71Q8xpxa8STGh6QNgQMoVS97Ui7Gz9n+UqX4rSwQ0cRu7byXdHVvAq7m7vNb4z676GxrswfQ2N6h27akJc3J8e2WDvPFpqdLKysiRXfZvpsywdInVJZuOxj4F6BKQgfe0/e6t0DEIZVit2n5aNBmQq41WZZx1VoPoLG9Q4flc6ucaPuyluK3uiJSxDiS9H9sv20a+73e9ttXM3Zv6miYOH10qusaKqs5PY7SY69qD6BxT+jfpzSu3MyK+cWdBRai68ZhgYi5sBjLXNRmD6B1Rg3QsmdSGg/2pPRB35fh0wGsFkmv63t98MBnU965RMyCj1Am/Nq8ef//gCpTrK6G1Je0oEnc36eMt9kYuLZWj7KxTui2b25mQryH0grc+xrVoX2vXz/w2V4V4keMajPbZ9H0vmq6/s32AhHj+/g+h0k6hFLdcjClXeRSSVWmFh7bRlEASftTGoc2B35OGV59LWWOi5FCT/J62PuINWEcFojItdCON1BWY/s5QDNS9MvAp0cNPNYJHTgO2A34su2dJT2NslzTqDzJ62HvI9aEcVggotbMkTHROr1k3vgllWpLxr1RdKntRc06ojvb/qOkK0fti6s5vohzrB3aWiBC0gms4sYlI6XbJeldlClzeysWPRe4yva/jBp73O/Q75C0EXAhcIakn7OiS9SMee4v4hxrh11ZsUDELpJqLRCxtEKMWE2SHgk83PZr+xanB7gYOKPKMcbxDr33g1OGxt5DeRx5HqUO/Rzbl6/i2yPmvMmGh+fuee5qlrx8ve2rB7bvCLytxtKX45rQW//BI8bZbCwQ0TTG/QtlvpUNettt79nWMddmki6z/fhJPls+ZcIoxrXb4sMHkzlAs23h7BcnYtb1hoe36QxKr7FtgLdQphdoZVR2ALDpKj57YI0DjGsdeus/eMSYm40FIh5q+8OSjmoGtnxNUhJ6e5ZKOtz2B/s3SnopE1e/mrFxTeit/+ARY+6YWThGr9fMTyTtQ1leb+znXJ/DXgV8TtLzWJHHFgHrA8+ucYBxrUN/OPA5yoIWK/3gNVb2iBhHs7lAhKR9KfOWbwmcAGwCvMX24lV+Y4ykGU+zQ/P2GtvnV4s9jgm9p80fPGIcSfoUExeIuNl29QUiJM0DXmn7P2rHjjVnrBN6xNpmNheIkPQt27u2ETvWjHGtQ49YW83mAhHfkHQiZaHr5QP2bLe1oEy0LHfoEWNkNheIaBZaGOT0Q5+7ktAjIjoiVS4RaylJbxq23faxs12WqCMJPWLt1T/R3QaUFcGuXUNliQpS5RIRAEh6AHCe7T3WdFliZsZ1LpeImH0PAhas6ULEzKXKJWItJelqVix0MY+yKlLqz+ewVLlErKUkbd33dhnws7amGYjZkSqXiLWU7Zsp87jsafs2YFNJ26zhYsUIcocesZaS9GbKpHePtv0oSZsDZ9vefQ0XLWYod+gRa69nA/vTdF+0/WNg4zVaohhJEnrE2uveZok7A0jacA2XJ0aUhB6x9jpL0smUuvPDgS8DH5zie2KMpQ49Yi0m6RnAX1Em/zrP9v+s4SLFCJLQIyI6IgOLItYyku6i1JuLFQOLoIUpemN25Q49IqIjcocesZYZWIj6KuDUjBDthtyhR6xlZmsh6ph9SegRa5nZXIg6Zlf6oUesfSYsRL0mCxJ15Q49Yi0zmwtRx+xKQo+I6IhUuUREdEQSekRERyShR0R0RBJ6RERHJKFHRHTE/wdZv7AvX4/0jwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "labels = ['Cardiomegaly', 'Emphysema', 'Effusion', 'Hernia', 'Infiltration', 'Mass', 'Nodule', 'Atelectasis',\n",
    "              'Pneumothorax', 'Pleural_Thickening', 'Pneumonia', 'Fibrosis', 'Edema', 'Consolidation']\n",
    "\n",
    "processed_image = load_image_normalize(im_path, mean, std)\n",
    "preds = model.predict(processed_image)\n",
    "pred_df = pd.DataFrame(preds, columns = labels)\n",
    "pred_df.loc[0, :].plot.bar()\n",
    "plt.title(\"Predictions\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "UpNVTzl6002K"
   },
   "source": [
    "We see, for example, that the model predicts Mass (abnormal spot or area in the lungs that are more than 3 centimeters) with high probability. Indeed, this patient was diagnosed with mass. However, we don't know where the model is looking when it's making its own diagnosis. To gain more insight into what the model is looking at, we can use GradCAMs."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "iKeH6_eBDCho"
   },
   "source": [
    "<a name=\"1-1\"></a>\n",
    "### 1.1 GradCAM"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "GradCAM is a technique to visualize the impact of each region of an image on a specific output for a Convolutional Neural Network model. Through GradCAM, we can generate a heatmap by computing gradients of the specific class scores we are interested in visualizing."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "pbKwnYWRHmxa"
   },
   "source": [
    "<a name=\"1-1-1\"></a>\n",
    "#### 1.1.1 Getting Intermediate Layers\n",
    "\n",
    "Perhaps the most complicated part of computing GradCAM is accessing intermediate activations in our deep learning model and computing gradients with respect to the class output. Now we'll go over one pattern to accomplish this, which you can use when implementing GradCAM.\n",
    "\n",
    "In order to understand how to access intermediate layers in a computation, first let's see the layers that our model is composed of. This can be done by calling Keras convenience function `model.summary()`. Do this in the cell below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "__________________________________________________________________________________________________\n",
      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      "input_1 (InputLayer)            (None, None, None, 3 0                                            \n",
      "__________________________________________________________________________________________________\n",
      "zero_padding2d_1 (ZeroPadding2D (None, None, None, 3 0           input_1[0][0]                    \n",
      "__________________________________________________________________________________________________\n",
      "conv1/conv (Conv2D)             (None, None, None, 6 9408        zero_padding2d_1[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "conv1/bn (BatchNormalization)   (None, None, None, 6 256         conv1/conv[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "conv1/relu (Activation)         (None, None, None, 6 0           conv1/bn[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "zero_padding2d_2 (ZeroPadding2D (None, None, None, 6 0           conv1/relu[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "pool1 (MaxPooling2D)            (None, None, None, 6 0           zero_padding2d_2[0][0]           \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block1_0_bn (BatchNormali (None, None, None, 6 256         pool1[0][0]                      \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block1_0_relu (Activation (None, None, None, 6 0           conv2_block1_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block1_1_conv (Conv2D)    (None, None, None, 1 8192        conv2_block1_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block1_1_bn (BatchNormali (None, None, None, 1 512         conv2_block1_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block1_1_relu (Activation (None, None, None, 1 0           conv2_block1_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block1_2_conv (Conv2D)    (None, None, None, 3 36864       conv2_block1_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block1_concat (Concatenat (None, None, None, 9 0           pool1[0][0]                      \n",
      "                                                                 conv2_block1_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block2_0_bn (BatchNormali (None, None, None, 9 384         conv2_block1_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block2_0_relu (Activation (None, None, None, 9 0           conv2_block2_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block2_1_conv (Conv2D)    (None, None, None, 1 12288       conv2_block2_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block2_1_bn (BatchNormali (None, None, None, 1 512         conv2_block2_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block2_1_relu (Activation (None, None, None, 1 0           conv2_block2_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block2_2_conv (Conv2D)    (None, None, None, 3 36864       conv2_block2_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block2_concat (Concatenat (None, None, None, 1 0           conv2_block1_concat[0][0]        \n",
      "                                                                 conv2_block2_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block3_0_bn (BatchNormali (None, None, None, 1 512         conv2_block2_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block3_0_relu (Activation (None, None, None, 1 0           conv2_block3_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block3_1_conv (Conv2D)    (None, None, None, 1 16384       conv2_block3_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block3_1_bn (BatchNormali (None, None, None, 1 512         conv2_block3_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block3_1_relu (Activation (None, None, None, 1 0           conv2_block3_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block3_2_conv (Conv2D)    (None, None, None, 3 36864       conv2_block3_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block3_concat (Concatenat (None, None, None, 1 0           conv2_block2_concat[0][0]        \n",
      "                                                                 conv2_block3_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block4_0_bn (BatchNormali (None, None, None, 1 640         conv2_block3_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block4_0_relu (Activation (None, None, None, 1 0           conv2_block4_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block4_1_conv (Conv2D)    (None, None, None, 1 20480       conv2_block4_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block4_1_bn (BatchNormali (None, None, None, 1 512         conv2_block4_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block4_1_relu (Activation (None, None, None, 1 0           conv2_block4_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block4_2_conv (Conv2D)    (None, None, None, 3 36864       conv2_block4_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block4_concat (Concatenat (None, None, None, 1 0           conv2_block3_concat[0][0]        \n",
      "                                                                 conv2_block4_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block5_0_bn (BatchNormali (None, None, None, 1 768         conv2_block4_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block5_0_relu (Activation (None, None, None, 1 0           conv2_block5_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block5_1_conv (Conv2D)    (None, None, None, 1 24576       conv2_block5_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block5_1_bn (BatchNormali (None, None, None, 1 512         conv2_block5_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block5_1_relu (Activation (None, None, None, 1 0           conv2_block5_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block5_2_conv (Conv2D)    (None, None, None, 3 36864       conv2_block5_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block5_concat (Concatenat (None, None, None, 2 0           conv2_block4_concat[0][0]        \n",
      "                                                                 conv2_block5_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block6_0_bn (BatchNormali (None, None, None, 2 896         conv2_block5_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block6_0_relu (Activation (None, None, None, 2 0           conv2_block6_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block6_1_conv (Conv2D)    (None, None, None, 1 28672       conv2_block6_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block6_1_bn (BatchNormali (None, None, None, 1 512         conv2_block6_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block6_1_relu (Activation (None, None, None, 1 0           conv2_block6_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block6_2_conv (Conv2D)    (None, None, None, 3 36864       conv2_block6_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv2_block6_concat (Concatenat (None, None, None, 2 0           conv2_block5_concat[0][0]        \n",
      "                                                                 conv2_block6_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "pool2_bn (BatchNormalization)   (None, None, None, 2 1024        conv2_block6_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "pool2_relu (Activation)         (None, None, None, 2 0           pool2_bn[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "pool2_conv (Conv2D)             (None, None, None, 1 32768       pool2_relu[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "pool2_pool (AveragePooling2D)   (None, None, None, 1 0           pool2_conv[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block1_0_bn (BatchNormali (None, None, None, 1 512         pool2_pool[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block1_0_relu (Activation (None, None, None, 1 0           conv3_block1_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block1_1_conv (Conv2D)    (None, None, None, 1 16384       conv3_block1_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block1_1_bn (BatchNormali (None, None, None, 1 512         conv3_block1_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block1_1_relu (Activation (None, None, None, 1 0           conv3_block1_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block1_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block1_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block1_concat (Concatenat (None, None, None, 1 0           pool2_pool[0][0]                 \n",
      "                                                                 conv3_block1_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block2_0_bn (BatchNormali (None, None, None, 1 640         conv3_block1_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block2_0_relu (Activation (None, None, None, 1 0           conv3_block2_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block2_1_conv (Conv2D)    (None, None, None, 1 20480       conv3_block2_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block2_1_bn (BatchNormali (None, None, None, 1 512         conv3_block2_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block2_1_relu (Activation (None, None, None, 1 0           conv3_block2_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block2_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block2_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block2_concat (Concatenat (None, None, None, 1 0           conv3_block1_concat[0][0]        \n",
      "                                                                 conv3_block2_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block3_0_bn (BatchNormali (None, None, None, 1 768         conv3_block2_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block3_0_relu (Activation (None, None, None, 1 0           conv3_block3_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block3_1_conv (Conv2D)    (None, None, None, 1 24576       conv3_block3_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block3_1_bn (BatchNormali (None, None, None, 1 512         conv3_block3_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block3_1_relu (Activation (None, None, None, 1 0           conv3_block3_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block3_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block3_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block3_concat (Concatenat (None, None, None, 2 0           conv3_block2_concat[0][0]        \n",
      "                                                                 conv3_block3_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block4_0_bn (BatchNormali (None, None, None, 2 896         conv3_block3_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block4_0_relu (Activation (None, None, None, 2 0           conv3_block4_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block4_1_conv (Conv2D)    (None, None, None, 1 28672       conv3_block4_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block4_1_bn (BatchNormali (None, None, None, 1 512         conv3_block4_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block4_1_relu (Activation (None, None, None, 1 0           conv3_block4_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block4_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block4_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block4_concat (Concatenat (None, None, None, 2 0           conv3_block3_concat[0][0]        \n",
      "                                                                 conv3_block4_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block5_0_bn (BatchNormali (None, None, None, 2 1024        conv3_block4_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block5_0_relu (Activation (None, None, None, 2 0           conv3_block5_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block5_1_conv (Conv2D)    (None, None, None, 1 32768       conv3_block5_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block5_1_bn (BatchNormali (None, None, None, 1 512         conv3_block5_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block5_1_relu (Activation (None, None, None, 1 0           conv3_block5_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block5_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block5_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block5_concat (Concatenat (None, None, None, 2 0           conv3_block4_concat[0][0]        \n",
      "                                                                 conv3_block5_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block6_0_bn (BatchNormali (None, None, None, 2 1152        conv3_block5_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block6_0_relu (Activation (None, None, None, 2 0           conv3_block6_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block6_1_conv (Conv2D)    (None, None, None, 1 36864       conv3_block6_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block6_1_bn (BatchNormali (None, None, None, 1 512         conv3_block6_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block6_1_relu (Activation (None, None, None, 1 0           conv3_block6_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block6_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block6_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block6_concat (Concatenat (None, None, None, 3 0           conv3_block5_concat[0][0]        \n",
      "                                                                 conv3_block6_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block7_0_bn (BatchNormali (None, None, None, 3 1280        conv3_block6_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block7_0_relu (Activation (None, None, None, 3 0           conv3_block7_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block7_1_conv (Conv2D)    (None, None, None, 1 40960       conv3_block7_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block7_1_bn (BatchNormali (None, None, None, 1 512         conv3_block7_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block7_1_relu (Activation (None, None, None, 1 0           conv3_block7_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block7_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block7_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block7_concat (Concatenat (None, None, None, 3 0           conv3_block6_concat[0][0]        \n",
      "                                                                 conv3_block7_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block8_0_bn (BatchNormali (None, None, None, 3 1408        conv3_block7_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block8_0_relu (Activation (None, None, None, 3 0           conv3_block8_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block8_1_conv (Conv2D)    (None, None, None, 1 45056       conv3_block8_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block8_1_bn (BatchNormali (None, None, None, 1 512         conv3_block8_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block8_1_relu (Activation (None, None, None, 1 0           conv3_block8_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block8_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block8_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block8_concat (Concatenat (None, None, None, 3 0           conv3_block7_concat[0][0]        \n",
      "                                                                 conv3_block8_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block9_0_bn (BatchNormali (None, None, None, 3 1536        conv3_block8_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block9_0_relu (Activation (None, None, None, 3 0           conv3_block9_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block9_1_conv (Conv2D)    (None, None, None, 1 49152       conv3_block9_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block9_1_bn (BatchNormali (None, None, None, 1 512         conv3_block9_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block9_1_relu (Activation (None, None, None, 1 0           conv3_block9_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block9_2_conv (Conv2D)    (None, None, None, 3 36864       conv3_block9_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block9_concat (Concatenat (None, None, None, 4 0           conv3_block8_concat[0][0]        \n",
      "                                                                 conv3_block9_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block10_0_bn (BatchNormal (None, None, None, 4 1664        conv3_block9_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block10_0_relu (Activatio (None, None, None, 4 0           conv3_block10_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block10_1_conv (Conv2D)   (None, None, None, 1 53248       conv3_block10_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block10_1_bn (BatchNormal (None, None, None, 1 512         conv3_block10_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block10_1_relu (Activatio (None, None, None, 1 0           conv3_block10_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block10_2_conv (Conv2D)   (None, None, None, 3 36864       conv3_block10_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block10_concat (Concatena (None, None, None, 4 0           conv3_block9_concat[0][0]        \n",
      "                                                                 conv3_block10_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block11_0_bn (BatchNormal (None, None, None, 4 1792        conv3_block10_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block11_0_relu (Activatio (None, None, None, 4 0           conv3_block11_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block11_1_conv (Conv2D)   (None, None, None, 1 57344       conv3_block11_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block11_1_bn (BatchNormal (None, None, None, 1 512         conv3_block11_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block11_1_relu (Activatio (None, None, None, 1 0           conv3_block11_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block11_2_conv (Conv2D)   (None, None, None, 3 36864       conv3_block11_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block11_concat (Concatena (None, None, None, 4 0           conv3_block10_concat[0][0]       \n",
      "                                                                 conv3_block11_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block12_0_bn (BatchNormal (None, None, None, 4 1920        conv3_block11_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block12_0_relu (Activatio (None, None, None, 4 0           conv3_block12_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block12_1_conv (Conv2D)   (None, None, None, 1 61440       conv3_block12_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block12_1_bn (BatchNormal (None, None, None, 1 512         conv3_block12_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block12_1_relu (Activatio (None, None, None, 1 0           conv3_block12_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block12_2_conv (Conv2D)   (None, None, None, 3 36864       conv3_block12_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv3_block12_concat (Concatena (None, None, None, 5 0           conv3_block11_concat[0][0]       \n",
      "                                                                 conv3_block12_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "pool3_bn (BatchNormalization)   (None, None, None, 5 2048        conv3_block12_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "pool3_relu (Activation)         (None, None, None, 5 0           pool3_bn[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "pool3_conv (Conv2D)             (None, None, None, 2 131072      pool3_relu[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "pool3_pool (AveragePooling2D)   (None, None, None, 2 0           pool3_conv[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block1_0_bn (BatchNormali (None, None, None, 2 1024        pool3_pool[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block1_0_relu (Activation (None, None, None, 2 0           conv4_block1_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block1_1_conv (Conv2D)    (None, None, None, 1 32768       conv4_block1_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block1_1_bn (BatchNormali (None, None, None, 1 512         conv4_block1_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block1_1_relu (Activation (None, None, None, 1 0           conv4_block1_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block1_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block1_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block1_concat (Concatenat (None, None, None, 2 0           pool3_pool[0][0]                 \n",
      "                                                                 conv4_block1_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block2_0_bn (BatchNormali (None, None, None, 2 1152        conv4_block1_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block2_0_relu (Activation (None, None, None, 2 0           conv4_block2_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block2_1_conv (Conv2D)    (None, None, None, 1 36864       conv4_block2_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block2_1_bn (BatchNormali (None, None, None, 1 512         conv4_block2_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block2_1_relu (Activation (None, None, None, 1 0           conv4_block2_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block2_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block2_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block2_concat (Concatenat (None, None, None, 3 0           conv4_block1_concat[0][0]        \n",
      "                                                                 conv4_block2_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block3_0_bn (BatchNormali (None, None, None, 3 1280        conv4_block2_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block3_0_relu (Activation (None, None, None, 3 0           conv4_block3_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block3_1_conv (Conv2D)    (None, None, None, 1 40960       conv4_block3_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block3_1_bn (BatchNormali (None, None, None, 1 512         conv4_block3_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block3_1_relu (Activation (None, None, None, 1 0           conv4_block3_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block3_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block3_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block3_concat (Concatenat (None, None, None, 3 0           conv4_block2_concat[0][0]        \n",
      "                                                                 conv4_block3_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block4_0_bn (BatchNormali (None, None, None, 3 1408        conv4_block3_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block4_0_relu (Activation (None, None, None, 3 0           conv4_block4_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block4_1_conv (Conv2D)    (None, None, None, 1 45056       conv4_block4_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block4_1_bn (BatchNormali (None, None, None, 1 512         conv4_block4_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block4_1_relu (Activation (None, None, None, 1 0           conv4_block4_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block4_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block4_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block4_concat (Concatenat (None, None, None, 3 0           conv4_block3_concat[0][0]        \n",
      "                                                                 conv4_block4_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block5_0_bn (BatchNormali (None, None, None, 3 1536        conv4_block4_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block5_0_relu (Activation (None, None, None, 3 0           conv4_block5_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block5_1_conv (Conv2D)    (None, None, None, 1 49152       conv4_block5_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block5_1_bn (BatchNormali (None, None, None, 1 512         conv4_block5_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block5_1_relu (Activation (None, None, None, 1 0           conv4_block5_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block5_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block5_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block5_concat (Concatenat (None, None, None, 4 0           conv4_block4_concat[0][0]        \n",
      "                                                                 conv4_block5_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block6_0_bn (BatchNormali (None, None, None, 4 1664        conv4_block5_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block6_0_relu (Activation (None, None, None, 4 0           conv4_block6_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block6_1_conv (Conv2D)    (None, None, None, 1 53248       conv4_block6_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block6_1_bn (BatchNormali (None, None, None, 1 512         conv4_block6_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block6_1_relu (Activation (None, None, None, 1 0           conv4_block6_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block6_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block6_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block6_concat (Concatenat (None, None, None, 4 0           conv4_block5_concat[0][0]        \n",
      "                                                                 conv4_block6_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block7_0_bn (BatchNormali (None, None, None, 4 1792        conv4_block6_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block7_0_relu (Activation (None, None, None, 4 0           conv4_block7_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block7_1_conv (Conv2D)    (None, None, None, 1 57344       conv4_block7_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block7_1_bn (BatchNormali (None, None, None, 1 512         conv4_block7_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block7_1_relu (Activation (None, None, None, 1 0           conv4_block7_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block7_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block7_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block7_concat (Concatenat (None, None, None, 4 0           conv4_block6_concat[0][0]        \n",
      "                                                                 conv4_block7_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block8_0_bn (BatchNormali (None, None, None, 4 1920        conv4_block7_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block8_0_relu (Activation (None, None, None, 4 0           conv4_block8_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block8_1_conv (Conv2D)    (None, None, None, 1 61440       conv4_block8_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block8_1_bn (BatchNormali (None, None, None, 1 512         conv4_block8_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block8_1_relu (Activation (None, None, None, 1 0           conv4_block8_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block8_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block8_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block8_concat (Concatenat (None, None, None, 5 0           conv4_block7_concat[0][0]        \n",
      "                                                                 conv4_block8_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block9_0_bn (BatchNormali (None, None, None, 5 2048        conv4_block8_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block9_0_relu (Activation (None, None, None, 5 0           conv4_block9_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block9_1_conv (Conv2D)    (None, None, None, 1 65536       conv4_block9_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block9_1_bn (BatchNormali (None, None, None, 1 512         conv4_block9_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block9_1_relu (Activation (None, None, None, 1 0           conv4_block9_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block9_2_conv (Conv2D)    (None, None, None, 3 36864       conv4_block9_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block9_concat (Concatenat (None, None, None, 5 0           conv4_block8_concat[0][0]        \n",
      "                                                                 conv4_block9_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block10_0_bn (BatchNormal (None, None, None, 5 2176        conv4_block9_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block10_0_relu (Activatio (None, None, None, 5 0           conv4_block10_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block10_1_conv (Conv2D)   (None, None, None, 1 69632       conv4_block10_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block10_1_bn (BatchNormal (None, None, None, 1 512         conv4_block10_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block10_1_relu (Activatio (None, None, None, 1 0           conv4_block10_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block10_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block10_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block10_concat (Concatena (None, None, None, 5 0           conv4_block9_concat[0][0]        \n",
      "                                                                 conv4_block10_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block11_0_bn (BatchNormal (None, None, None, 5 2304        conv4_block10_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block11_0_relu (Activatio (None, None, None, 5 0           conv4_block11_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block11_1_conv (Conv2D)   (None, None, None, 1 73728       conv4_block11_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block11_1_bn (BatchNormal (None, None, None, 1 512         conv4_block11_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block11_1_relu (Activatio (None, None, None, 1 0           conv4_block11_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block11_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block11_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block11_concat (Concatena (None, None, None, 6 0           conv4_block10_concat[0][0]       \n",
      "                                                                 conv4_block11_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block12_0_bn (BatchNormal (None, None, None, 6 2432        conv4_block11_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block12_0_relu (Activatio (None, None, None, 6 0           conv4_block12_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block12_1_conv (Conv2D)   (None, None, None, 1 77824       conv4_block12_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block12_1_bn (BatchNormal (None, None, None, 1 512         conv4_block12_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block12_1_relu (Activatio (None, None, None, 1 0           conv4_block12_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block12_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block12_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block12_concat (Concatena (None, None, None, 6 0           conv4_block11_concat[0][0]       \n",
      "                                                                 conv4_block12_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block13_0_bn (BatchNormal (None, None, None, 6 2560        conv4_block12_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block13_0_relu (Activatio (None, None, None, 6 0           conv4_block13_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block13_1_conv (Conv2D)   (None, None, None, 1 81920       conv4_block13_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block13_1_bn (BatchNormal (None, None, None, 1 512         conv4_block13_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block13_1_relu (Activatio (None, None, None, 1 0           conv4_block13_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block13_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block13_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block13_concat (Concatena (None, None, None, 6 0           conv4_block12_concat[0][0]       \n",
      "                                                                 conv4_block13_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block14_0_bn (BatchNormal (None, None, None, 6 2688        conv4_block13_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block14_0_relu (Activatio (None, None, None, 6 0           conv4_block14_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block14_1_conv (Conv2D)   (None, None, None, 1 86016       conv4_block14_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block14_1_bn (BatchNormal (None, None, None, 1 512         conv4_block14_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block14_1_relu (Activatio (None, None, None, 1 0           conv4_block14_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block14_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block14_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block14_concat (Concatena (None, None, None, 7 0           conv4_block13_concat[0][0]       \n",
      "                                                                 conv4_block14_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block15_0_bn (BatchNormal (None, None, None, 7 2816        conv4_block14_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block15_0_relu (Activatio (None, None, None, 7 0           conv4_block15_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block15_1_conv (Conv2D)   (None, None, None, 1 90112       conv4_block15_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block15_1_bn (BatchNormal (None, None, None, 1 512         conv4_block15_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block15_1_relu (Activatio (None, None, None, 1 0           conv4_block15_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block15_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block15_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block15_concat (Concatena (None, None, None, 7 0           conv4_block14_concat[0][0]       \n",
      "                                                                 conv4_block15_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block16_0_bn (BatchNormal (None, None, None, 7 2944        conv4_block15_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block16_0_relu (Activatio (None, None, None, 7 0           conv4_block16_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block16_1_conv (Conv2D)   (None, None, None, 1 94208       conv4_block16_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block16_1_bn (BatchNormal (None, None, None, 1 512         conv4_block16_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block16_1_relu (Activatio (None, None, None, 1 0           conv4_block16_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block16_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block16_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block16_concat (Concatena (None, None, None, 7 0           conv4_block15_concat[0][0]       \n",
      "                                                                 conv4_block16_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block17_0_bn (BatchNormal (None, None, None, 7 3072        conv4_block16_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block17_0_relu (Activatio (None, None, None, 7 0           conv4_block17_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block17_1_conv (Conv2D)   (None, None, None, 1 98304       conv4_block17_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block17_1_bn (BatchNormal (None, None, None, 1 512         conv4_block17_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block17_1_relu (Activatio (None, None, None, 1 0           conv4_block17_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block17_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block17_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block17_concat (Concatena (None, None, None, 8 0           conv4_block16_concat[0][0]       \n",
      "                                                                 conv4_block17_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block18_0_bn (BatchNormal (None, None, None, 8 3200        conv4_block17_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block18_0_relu (Activatio (None, None, None, 8 0           conv4_block18_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block18_1_conv (Conv2D)   (None, None, None, 1 102400      conv4_block18_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block18_1_bn (BatchNormal (None, None, None, 1 512         conv4_block18_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block18_1_relu (Activatio (None, None, None, 1 0           conv4_block18_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block18_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block18_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block18_concat (Concatena (None, None, None, 8 0           conv4_block17_concat[0][0]       \n",
      "                                                                 conv4_block18_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block19_0_bn (BatchNormal (None, None, None, 8 3328        conv4_block18_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block19_0_relu (Activatio (None, None, None, 8 0           conv4_block19_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block19_1_conv (Conv2D)   (None, None, None, 1 106496      conv4_block19_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block19_1_bn (BatchNormal (None, None, None, 1 512         conv4_block19_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block19_1_relu (Activatio (None, None, None, 1 0           conv4_block19_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block19_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block19_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block19_concat (Concatena (None, None, None, 8 0           conv4_block18_concat[0][0]       \n",
      "                                                                 conv4_block19_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block20_0_bn (BatchNormal (None, None, None, 8 3456        conv4_block19_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block20_0_relu (Activatio (None, None, None, 8 0           conv4_block20_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block20_1_conv (Conv2D)   (None, None, None, 1 110592      conv4_block20_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block20_1_bn (BatchNormal (None, None, None, 1 512         conv4_block20_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block20_1_relu (Activatio (None, None, None, 1 0           conv4_block20_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block20_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block20_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block20_concat (Concatena (None, None, None, 8 0           conv4_block19_concat[0][0]       \n",
      "                                                                 conv4_block20_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block21_0_bn (BatchNormal (None, None, None, 8 3584        conv4_block20_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block21_0_relu (Activatio (None, None, None, 8 0           conv4_block21_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block21_1_conv (Conv2D)   (None, None, None, 1 114688      conv4_block21_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block21_1_bn (BatchNormal (None, None, None, 1 512         conv4_block21_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block21_1_relu (Activatio (None, None, None, 1 0           conv4_block21_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block21_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block21_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block21_concat (Concatena (None, None, None, 9 0           conv4_block20_concat[0][0]       \n",
      "                                                                 conv4_block21_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block22_0_bn (BatchNormal (None, None, None, 9 3712        conv4_block21_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block22_0_relu (Activatio (None, None, None, 9 0           conv4_block22_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block22_1_conv (Conv2D)   (None, None, None, 1 118784      conv4_block22_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block22_1_bn (BatchNormal (None, None, None, 1 512         conv4_block22_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block22_1_relu (Activatio (None, None, None, 1 0           conv4_block22_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block22_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block22_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block22_concat (Concatena (None, None, None, 9 0           conv4_block21_concat[0][0]       \n",
      "                                                                 conv4_block22_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block23_0_bn (BatchNormal (None, None, None, 9 3840        conv4_block22_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block23_0_relu (Activatio (None, None, None, 9 0           conv4_block23_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block23_1_conv (Conv2D)   (None, None, None, 1 122880      conv4_block23_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block23_1_bn (BatchNormal (None, None, None, 1 512         conv4_block23_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block23_1_relu (Activatio (None, None, None, 1 0           conv4_block23_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block23_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block23_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block23_concat (Concatena (None, None, None, 9 0           conv4_block22_concat[0][0]       \n",
      "                                                                 conv4_block23_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block24_0_bn (BatchNormal (None, None, None, 9 3968        conv4_block23_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block24_0_relu (Activatio (None, None, None, 9 0           conv4_block24_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block24_1_conv (Conv2D)   (None, None, None, 1 126976      conv4_block24_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block24_1_bn (BatchNormal (None, None, None, 1 512         conv4_block24_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block24_1_relu (Activatio (None, None, None, 1 0           conv4_block24_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block24_2_conv (Conv2D)   (None, None, None, 3 36864       conv4_block24_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv4_block24_concat (Concatena (None, None, None, 1 0           conv4_block23_concat[0][0]       \n",
      "                                                                 conv4_block24_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "pool4_bn (BatchNormalization)   (None, None, None, 1 4096        conv4_block24_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "pool4_relu (Activation)         (None, None, None, 1 0           pool4_bn[0][0]                   \n",
      "__________________________________________________________________________________________________\n",
      "pool4_conv (Conv2D)             (None, None, None, 5 524288      pool4_relu[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "pool4_pool (AveragePooling2D)   (None, None, None, 5 0           pool4_conv[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block1_0_bn (BatchNormali (None, None, None, 5 2048        pool4_pool[0][0]                 \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block1_0_relu (Activation (None, None, None, 5 0           conv5_block1_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block1_1_conv (Conv2D)    (None, None, None, 1 65536       conv5_block1_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block1_1_bn (BatchNormali (None, None, None, 1 512         conv5_block1_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block1_1_relu (Activation (None, None, None, 1 0           conv5_block1_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block1_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block1_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block1_concat (Concatenat (None, None, None, 5 0           pool4_pool[0][0]                 \n",
      "                                                                 conv5_block1_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block2_0_bn (BatchNormali (None, None, None, 5 2176        conv5_block1_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block2_0_relu (Activation (None, None, None, 5 0           conv5_block2_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block2_1_conv (Conv2D)    (None, None, None, 1 69632       conv5_block2_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block2_1_bn (BatchNormali (None, None, None, 1 512         conv5_block2_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block2_1_relu (Activation (None, None, None, 1 0           conv5_block2_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block2_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block2_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block2_concat (Concatenat (None, None, None, 5 0           conv5_block1_concat[0][0]        \n",
      "                                                                 conv5_block2_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block3_0_bn (BatchNormali (None, None, None, 5 2304        conv5_block2_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block3_0_relu (Activation (None, None, None, 5 0           conv5_block3_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block3_1_conv (Conv2D)    (None, None, None, 1 73728       conv5_block3_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block3_1_bn (BatchNormali (None, None, None, 1 512         conv5_block3_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block3_1_relu (Activation (None, None, None, 1 0           conv5_block3_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block3_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block3_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block3_concat (Concatenat (None, None, None, 6 0           conv5_block2_concat[0][0]        \n",
      "                                                                 conv5_block3_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block4_0_bn (BatchNormali (None, None, None, 6 2432        conv5_block3_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block4_0_relu (Activation (None, None, None, 6 0           conv5_block4_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block4_1_conv (Conv2D)    (None, None, None, 1 77824       conv5_block4_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block4_1_bn (BatchNormali (None, None, None, 1 512         conv5_block4_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block4_1_relu (Activation (None, None, None, 1 0           conv5_block4_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block4_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block4_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block4_concat (Concatenat (None, None, None, 6 0           conv5_block3_concat[0][0]        \n",
      "                                                                 conv5_block4_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block5_0_bn (BatchNormali (None, None, None, 6 2560        conv5_block4_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block5_0_relu (Activation (None, None, None, 6 0           conv5_block5_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block5_1_conv (Conv2D)    (None, None, None, 1 81920       conv5_block5_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block5_1_bn (BatchNormali (None, None, None, 1 512         conv5_block5_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block5_1_relu (Activation (None, None, None, 1 0           conv5_block5_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block5_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block5_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block5_concat (Concatenat (None, None, None, 6 0           conv5_block4_concat[0][0]        \n",
      "                                                                 conv5_block5_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block6_0_bn (BatchNormali (None, None, None, 6 2688        conv5_block5_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block6_0_relu (Activation (None, None, None, 6 0           conv5_block6_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block6_1_conv (Conv2D)    (None, None, None, 1 86016       conv5_block6_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block6_1_bn (BatchNormali (None, None, None, 1 512         conv5_block6_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block6_1_relu (Activation (None, None, None, 1 0           conv5_block6_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block6_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block6_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block6_concat (Concatenat (None, None, None, 7 0           conv5_block5_concat[0][0]        \n",
      "                                                                 conv5_block6_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block7_0_bn (BatchNormali (None, None, None, 7 2816        conv5_block6_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block7_0_relu (Activation (None, None, None, 7 0           conv5_block7_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block7_1_conv (Conv2D)    (None, None, None, 1 90112       conv5_block7_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block7_1_bn (BatchNormali (None, None, None, 1 512         conv5_block7_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block7_1_relu (Activation (None, None, None, 1 0           conv5_block7_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block7_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block7_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block7_concat (Concatenat (None, None, None, 7 0           conv5_block6_concat[0][0]        \n",
      "                                                                 conv5_block7_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block8_0_bn (BatchNormali (None, None, None, 7 2944        conv5_block7_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block8_0_relu (Activation (None, None, None, 7 0           conv5_block8_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block8_1_conv (Conv2D)    (None, None, None, 1 94208       conv5_block8_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block8_1_bn (BatchNormali (None, None, None, 1 512         conv5_block8_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block8_1_relu (Activation (None, None, None, 1 0           conv5_block8_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block8_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block8_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block8_concat (Concatenat (None, None, None, 7 0           conv5_block7_concat[0][0]        \n",
      "                                                                 conv5_block8_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block9_0_bn (BatchNormali (None, None, None, 7 3072        conv5_block8_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block9_0_relu (Activation (None, None, None, 7 0           conv5_block9_0_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block9_1_conv (Conv2D)    (None, None, None, 1 98304       conv5_block9_0_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block9_1_bn (BatchNormali (None, None, None, 1 512         conv5_block9_1_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block9_1_relu (Activation (None, None, None, 1 0           conv5_block9_1_bn[0][0]          \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block9_2_conv (Conv2D)    (None, None, None, 3 36864       conv5_block9_1_relu[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block9_concat (Concatenat (None, None, None, 8 0           conv5_block8_concat[0][0]        \n",
      "                                                                 conv5_block9_2_conv[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block10_0_bn (BatchNormal (None, None, None, 8 3200        conv5_block9_concat[0][0]        \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block10_0_relu (Activatio (None, None, None, 8 0           conv5_block10_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block10_1_conv (Conv2D)   (None, None, None, 1 102400      conv5_block10_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block10_1_bn (BatchNormal (None, None, None, 1 512         conv5_block10_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block10_1_relu (Activatio (None, None, None, 1 0           conv5_block10_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block10_2_conv (Conv2D)   (None, None, None, 3 36864       conv5_block10_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block10_concat (Concatena (None, None, None, 8 0           conv5_block9_concat[0][0]        \n",
      "                                                                 conv5_block10_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block11_0_bn (BatchNormal (None, None, None, 8 3328        conv5_block10_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block11_0_relu (Activatio (None, None, None, 8 0           conv5_block11_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block11_1_conv (Conv2D)   (None, None, None, 1 106496      conv5_block11_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block11_1_bn (BatchNormal (None, None, None, 1 512         conv5_block11_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block11_1_relu (Activatio (None, None, None, 1 0           conv5_block11_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block11_2_conv (Conv2D)   (None, None, None, 3 36864       conv5_block11_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block11_concat (Concatena (None, None, None, 8 0           conv5_block10_concat[0][0]       \n",
      "                                                                 conv5_block11_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block12_0_bn (BatchNormal (None, None, None, 8 3456        conv5_block11_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block12_0_relu (Activatio (None, None, None, 8 0           conv5_block12_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block12_1_conv (Conv2D)   (None, None, None, 1 110592      conv5_block12_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block12_1_bn (BatchNormal (None, None, None, 1 512         conv5_block12_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block12_1_relu (Activatio (None, None, None, 1 0           conv5_block12_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block12_2_conv (Conv2D)   (None, None, None, 3 36864       conv5_block12_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block12_concat (Concatena (None, None, None, 8 0           conv5_block11_concat[0][0]       \n",
      "                                                                 conv5_block12_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block13_0_bn (BatchNormal (None, None, None, 8 3584        conv5_block12_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block13_0_relu (Activatio (None, None, None, 8 0           conv5_block13_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block13_1_conv (Conv2D)   (None, None, None, 1 114688      conv5_block13_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block13_1_bn (BatchNormal (None, None, None, 1 512         conv5_block13_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block13_1_relu (Activatio (None, None, None, 1 0           conv5_block13_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block13_2_conv (Conv2D)   (None, None, None, 3 36864       conv5_block13_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block13_concat (Concatena (None, None, None, 9 0           conv5_block12_concat[0][0]       \n",
      "                                                                 conv5_block13_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block14_0_bn (BatchNormal (None, None, None, 9 3712        conv5_block13_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block14_0_relu (Activatio (None, None, None, 9 0           conv5_block14_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block14_1_conv (Conv2D)   (None, None, None, 1 118784      conv5_block14_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block14_1_bn (BatchNormal (None, None, None, 1 512         conv5_block14_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block14_1_relu (Activatio (None, None, None, 1 0           conv5_block14_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block14_2_conv (Conv2D)   (None, None, None, 3 36864       conv5_block14_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block14_concat (Concatena (None, None, None, 9 0           conv5_block13_concat[0][0]       \n",
      "                                                                 conv5_block14_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block15_0_bn (BatchNormal (None, None, None, 9 3840        conv5_block14_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block15_0_relu (Activatio (None, None, None, 9 0           conv5_block15_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block15_1_conv (Conv2D)   (None, None, None, 1 122880      conv5_block15_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block15_1_bn (BatchNormal (None, None, None, 1 512         conv5_block15_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block15_1_relu (Activatio (None, None, None, 1 0           conv5_block15_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block15_2_conv (Conv2D)   (None, None, None, 3 36864       conv5_block15_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block15_concat (Concatena (None, None, None, 9 0           conv5_block14_concat[0][0]       \n",
      "                                                                 conv5_block15_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block16_0_bn (BatchNormal (None, None, None, 9 3968        conv5_block15_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block16_0_relu (Activatio (None, None, None, 9 0           conv5_block16_0_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block16_1_conv (Conv2D)   (None, None, None, 1 126976      conv5_block16_0_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block16_1_bn (BatchNormal (None, None, None, 1 512         conv5_block16_1_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block16_1_relu (Activatio (None, None, None, 1 0           conv5_block16_1_bn[0][0]         \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block16_2_conv (Conv2D)   (None, None, None, 3 36864       conv5_block16_1_relu[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "conv5_block16_concat (Concatena (None, None, None, 1 0           conv5_block15_concat[0][0]       \n",
      "                                                                 conv5_block16_2_conv[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "bn (BatchNormalization)         (None, None, None, 1 4096        conv5_block16_concat[0][0]       \n",
      "__________________________________________________________________________________________________\n",
      "global_average_pooling2d_1 (Glo (None, 1024)         0           bn[0][0]                         \n",
      "__________________________________________________________________________________________________\n",
      "dense_1 (Dense)                 (None, 14)           14350       global_average_pooling2d_1[0][0] \n",
      "==================================================================================================\n",
      "Total params: 7,051,854\n",
      "Trainable params: 6,968,206\n",
      "Non-trainable params: 83,648\n",
      "__________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "CvyTsSRdJ2TP"
   },
   "source": [
    "There are a lot of layers, but typically we'll only be extracting one of the last few. Remember that the last few layers usually have more abstract information. To access a layer, we can use `model.get_layer(layer).output`, which takes in the name of the layer in question. Let's try getting the `conv5_block16_concat` layer, the raw output of the last convolutional layer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "icUrvQF7KUJp",
    "outputId": "611d75e5-1345-489f-a01a-bb566ae230cf"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tensor(\"conv5_block16_concat/concat:0\", shape=(?, ?, ?, 1024), dtype=float32)\n"
     ]
    }
   ],
   "source": [
    "spatial_maps =  model.get_layer('conv5_block16_concat').output\n",
    "print(spatial_maps)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "kCsIMf08KrWi"
   },
   "source": [
    "Now, this tensor is just a placeholder, it doesn't contain the actual activations for a particular image. To get this we will use [Keras.backend.function](https://www.tensorflow.org/api_docs/python/tf/keras/backend/function) to return intermediate computations while the model is processing a particular input. This method takes in an input and output placeholders and returns a function. This function will compute the intermediate output (until it reaches the given placeholder) evaluated given the input. For example, if you want the layer that you just retrieved (conv5_block16_concat), you could write the following:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "U4JEE37ALl-N",
    "outputId": "1de337cf-bec5-4edf-fb6d-4bbbe672bad8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<keras.backend.tensorflow_backend.Function object at 0x7faf4fe307b8>\n"
     ]
    }
   ],
   "source": [
    "get_spatial_maps = K.function([model.input], [spatial_maps])\n",
    "print(get_spatial_maps)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "B2-soRaiL8xA"
   },
   "source": [
    "We see that we now have a `Function` object. Now, to get the actual intermediate output evaluated with a particular input, we just plug in an image to this function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x is of type <class 'numpy.ndarray'>\n",
      "x is of shape (1, 320, 320, 3)\n"
     ]
    }
   ],
   "source": [
    "# get an image\n",
    "x = load_image_normalize(im_path, mean, std)\n",
    "print(f\"x is of type {type(x)}\")\n",
    "print(f\"x is of shape {x.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "spatial_maps_x_l is of type <class 'list'>\n",
      "spatial_maps_x_l is has length 1\n"
     ]
    }
   ],
   "source": [
    "# get the spatial maps layer activations (a list of numpy arrays)\n",
    "spatial_maps_x_l = get_spatial_maps([x])\n",
    "\n",
    "print(f\"spatial_maps_x_l is of type {type(spatial_maps_x_l)}\")\n",
    "print(f\"spatial_maps_x_l is has length {len(spatial_maps_x_l)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "spatial_maps_x is of type <class 'numpy.ndarray'>\n",
      "spatial_maps_x is of shape (1, 10, 10, 1024)\n"
     ]
    }
   ],
   "source": [
    "# get the 0th item in the list\n",
    "spatial_maps_x = spatial_maps_x_l[0]\n",
    "print(f\"spatial_maps_x is of type {type(spatial_maps_x)}\")\n",
    "print(f\"spatial_maps_x is of shape {spatial_maps_x.shape}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice that the shape is (1, 10, 10, 1024).  The 0th dimension of size 1 is the batch dimension.  Remove the batch dimension for later calculations by taking the 0th index of spatial_maps_x."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "spatial_maps_x without the batch dimension has shape (10, 10, 1024)\n",
      "Output some of the content:\n",
      "[[-0.46017444  0.20640776 -0.63506377 ...  0.1264174  -0.06400048\n",
      "   0.15870997]\n",
      " [-0.8125281  -0.29398838 -0.8967887  ...  0.21837974 -0.0994716\n",
      "   0.26966757]\n",
      " [-0.508806   -0.14127392 -0.5690727  ...  0.27967227 -0.11622357\n",
      "   0.318372  ]\n",
      " ...\n",
      " [-0.34813794 -0.3922896  -1.0565547  ...  0.17491409 -0.08235557\n",
      "   0.25179753]\n",
      " [-0.4438535  -0.32872048 -0.65662026 ...  0.21583238 -0.10991383\n",
      "   0.31518462]\n",
      " [-0.29580766  0.4920513  -0.2233113  ...  0.08722244 -0.04751847\n",
      "   0.17896183]]\n"
     ]
    }
   ],
   "source": [
    "# Get rid of the batch dimension\n",
    "spatial_maps_x = spatial_maps_x[0] # equivalent to spatial_maps_x[0,:]\n",
    "print(f\"spatial_maps_x without the batch dimension has shape {spatial_maps_x.shape}\")\n",
    "print(\"Output some of the content:\")\n",
    "print(spatial_maps_x[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "aRCSdXfRO6KI"
   },
   "source": [
    "We now have the activations for that particular image, and we can use it for interpretation. The function that is returned by calling `K.function([model.input], [spatial_maps])` (saved here in the variable `get_spatial_maps`) is sometimes referred to as a \"hook\", letting you peek into the intermediate computations in the model. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "FJlxNWRyPQqV"
   },
   "source": [
    "<a name=\"1-1-2\"></a>\n",
    "#### 1.1.2 Getting Gradients"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "G12g9fOeaqyM"
   },
   "source": [
    "The other major step in computing GradCAMs is getting gradients with respect to the output for a particular class. Luckily, Keras makes getting gradients simple. We can use the [Keras.backend.gradients](https://www.tensorflow.org/api_docs/python/tf/keras/backend/gradients) function. The first parameter is the value you are taking the gradient of, and the second is the parameter you are taking that gradient with respect to. We illustrate below: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model output includes batch dimension, has shape (?, 14)\n"
     ]
    }
   ],
   "source": [
    "# get the output of the model\n",
    "output_with_batch_dim = model.output\n",
    "print(f\"Model output includes batch dimension, has shape {output_with_batch_dim.shape}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To get the output without the batch dimension, you can take the 0th index of the tensor. Note that because the batch dimension is 'None', you could actually enter any integer index, but let's just use 0."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The output for all 14 categories of disease has shape (14,)\n"
     ]
    }
   ],
   "source": [
    "# Get the output without the batch dimension\n",
    "output_all_categories = output_with_batch_dim[0]\n",
    "print(f\"The output for all 14 categories of disease has shape {output_all_categories.shape}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The output has 14 categories, one for each disease category, indexed from 0 to 13. Cardiomegaly is the disease category at index 0."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The Cardiomegaly output is at index 0, and has shape ()\n"
     ]
    }
   ],
   "source": [
    "# Get the first category's output (Cardiomegaly) at index 0\n",
    "y_category_0 = output_all_categories[0]\n",
    "print(f\"The Cardiomegaly output is at index 0, and has shape {y_category_0.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "gdnX8taUbF7h",
    "outputId": "646e7c7c-0ab6-492d-f6b5-26b30f4c1125"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "gradient_l is of type <class 'list'> and has length 1\n",
      "Tensor(\"gradients/AddN:0\", shape=(?, ?, ?, 1024), dtype=float32)\n"
     ]
    }
   ],
   "source": [
    "# Get gradient of y_category_0 with respect to spatial_maps\n",
    "\n",
    "gradient_l = K.gradients(y_category_0, spatial_maps)\n",
    "print(f\"gradient_l is of type {type(gradient_l)} and has length {len(gradient_l)}\")\n",
    "\n",
    "# gradient_l is a list of size 1.  Get the gradient at index 0\n",
    "gradient = gradient_l[0]\n",
    "print(gradient)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "fj-b8lqHbrM5"
   },
   "source": [
    "Again, this is just a placeholder. Just like for intermediate layers, we can use `K.function` to compute the value of the gradient for a particular input.  \n",
    "\n",
    "The K.function() takes in\n",
    "- a list of inputs: in this case, one input, 'model.input'\n",
    "- a list of tensors: in this case, one output tensor 'gradient'\n",
    "\n",
    "It returns a function that calculates the activations of the list of tensors.\n",
    "- This returned function returns a list of the activations, one for each tensor that was passed into K.function()."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "keras.backend.tensorflow_backend.Function"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create the function that gets the gradient\n",
    "get_gradient = K.function([model.input], [gradient])\n",
    "type(get_gradient)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X-ray image has shape (1, 320, 320, 3)\n"
     ]
    }
   ],
   "source": [
    "# get an input x-ray image\n",
    "x = load_image_normalize(im_path, mean, std)\n",
    "print(f\"X-ray image has shape {x.shape}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `get_gradient` function takes in a list of inputs, and returns a list of the gradients, one for each image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "grad_x_l is of type <class 'list'> and length 1\n",
      "grad_x_with_batch_dim is type <class 'numpy.ndarray'> and shape (1, 10, 10, 1024)\n",
      "grad_x is type <class 'numpy.ndarray'> and shape (10, 10, 1024)\n",
      "Gradient grad_x (show some of its content:\n",
      "[[-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " ...\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]]\n"
     ]
    }
   ],
   "source": [
    "# use the get_gradient function to get the gradient (pass in the input image inside a list)\n",
    "grad_x_l = get_gradient([x])\n",
    "print(f\"grad_x_l is of type {type(grad_x_l)} and length {len(grad_x_l)}\")\n",
    "\n",
    "# get the gradient at index 0 of the list.\n",
    "grad_x_with_batch_dim = grad_x_l[0]\n",
    "print(f\"grad_x_with_batch_dim is type {type(grad_x_with_batch_dim)} and shape {grad_x_with_batch_dim.shape}\")\n",
    "\n",
    "# To remove the batch dimension, take the value at index 0 of the batch dimension\n",
    "grad_x = grad_x_with_batch_dim[0]\n",
    "print(f\"grad_x is type {type(grad_x)} and shape {grad_x.shape}\")\n",
    "\n",
    "print(\"Gradient grad_x (show some of its content:\")\n",
    "print(grad_x[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "aw7DVK2Xc8gv"
   },
   "source": [
    "Just like we had a hook into the penultimate layer, we now have a hook into the gradient! This allows us to easily compute pretty much anything relevant to our model output. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "ssEQgnCLdXcr"
   },
   "source": [
    "We can also combine the two to have one function call which gives us both the gradient and the last layer (this might come in handy when implementing GradCAM in the next section)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'keras.backend.tensorflow_backend.Function'>\n"
     ]
    }
   ],
   "source": [
    "# Use K.function to generate a single function\n",
    "# Notice that a list of two tensors, is passed in as the second argument of K.function()\n",
    "get_spatial_maps_and_gradient = K.function([model.input], [spatial_maps, gradient])\n",
    "print(type(get_spatial_maps_and_gradient))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor_eval_l is type <class 'list'> and length 2\n"
     ]
    }
   ],
   "source": [
    "# The returned function returns a list of the evaluated tensors\n",
    "tensor_eval_l = get_spatial_maps_and_gradient([x])\n",
    "print(f\"tensor_eval_l is type {type(tensor_eval_l)} and length {len(tensor_eval_l)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "spatial_maps_x_with_batch_dim has shape (1, 10, 10, 1024)\n",
      "grad_x_with_batch_dim has shape (1, 10, 10, 1024)\n"
     ]
    }
   ],
   "source": [
    "# store the two numpy arrays from index 0 and 1 into their own variables\n",
    "spatial_maps_x_with_batch_dim, grad_x_with_batch_dim = tensor_eval_l\n",
    "print(f\"spatial_maps_x_with_batch_dim has shape {spatial_maps_x_with_batch_dim.shape}\")\n",
    "print(f\"grad_x_with_batch_dim has shape {grad_x_with_batch_dim.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "spatial_maps_x_with_batch_dim has shape (1, 10, 10, 1024)\n",
      "grad_x_with_batch_dim has shape (1, 10, 10, 1024)\n"
     ]
    }
   ],
   "source": [
    "# Note: you could also do this directly from the function call:\n",
    "spatial_maps_x_with_batch_dim, grad_x_with_batch_dim = get_spatial_maps_and_gradient([x])\n",
    "print(f\"spatial_maps_x_with_batch_dim has shape {spatial_maps_x_with_batch_dim.shape}\")\n",
    "print(f\"grad_x_with_batch_dim has shape {grad_x_with_batch_dim.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "spatial_maps_x shape (10, 10, 1024)\n",
      "grad_x shape (10, 10, 1024)\n",
      "\n",
      "Spatial maps (print some content):\n",
      "[[-0.46017444  0.20640776 -0.63506377 ...  0.1264174  -0.06400048\n",
      "   0.15870997]\n",
      " [-0.8125281  -0.29398838 -0.8967887  ...  0.21837974 -0.0994716\n",
      "   0.26966757]\n",
      " [-0.508806   -0.14127392 -0.5690727  ...  0.27967227 -0.11622357\n",
      "   0.318372  ]\n",
      " ...\n",
      " [-0.34813794 -0.3922896  -1.0565547  ...  0.17491409 -0.08235557\n",
      "   0.25179753]\n",
      " [-0.4438535  -0.32872048 -0.65662026 ...  0.21583238 -0.10991383\n",
      "   0.31518462]\n",
      " [-0.29580766  0.4920513  -0.2233113  ...  0.08722244 -0.04751847\n",
      "   0.17896183]]\n",
      "\n",
      "Gradient (print some content:\n",
      "[[-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " ...\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]\n",
      " [-1.4058211e-09  2.8323848e-09  3.3191864e-07 ...  9.2680755e-05\n",
      "  -6.2032734e-05  6.4634791e-05]]\n"
     ]
    }
   ],
   "source": [
    "# Remove the batch dimension by taking the 0th index at the batch dimension\n",
    "spatial_maps_x = spatial_maps_x_with_batch_dim[0]\n",
    "grad_x = grad_x_with_batch_dim[0]\n",
    "print(f\"spatial_maps_x shape {spatial_maps_x.shape}\")\n",
    "print(f\"grad_x shape {grad_x.shape}\")\n",
    "\n",
    "print(\"\\nSpatial maps (print some content):\")\n",
    "print(spatial_maps_x[0])\n",
    "print(\"\\nGradient (print some content:\")\n",
    "print(grad_x[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "bdLxNcp9dD3i"
   },
   "source": [
    "<a name=\"1-1-3\"></a>\n",
    "#### 1.1.3 Implementing GradCAM"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "3QHMAogf2HbD"
   },
   "source": [
    "<a name='ex-01'></a>\n",
    "### Exercise 1\n",
    "\n",
    "In the next cell, fill in the `grad_cam` method to produce GradCAM visualizations for an input model and image. This is fairly complicated, so it might help to break it down into these steps:\n",
    "\n",
    "1. Hook into model output and last layer activations.\n",
    "2. Get gradients of last layer activations with respect to output.\n",
    "3. Compute value of last layer and gradients for input image.\n",
    "4. Compute weights from gradients by global average pooling.\n",
    "5. Compute the dot product between the last layer and weights to get the score for each pixel.\n",
    "6. Resize, take ReLU, and return cam. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<details>\n",
    "    <summary>\n",
    "    <font size=\"3\" color=\"darkgreen\"><b>Hints</b></font>\n",
    "</summary>\n",
    "    \n",
    " The following hints follow the order of the sections described above.\n",
    " 1. Remember that the output shape of our model will be [1, class_amount]. \n",
    "     1. The input in this case will always have batch_size = 1\n",
    " 2. See [K.gradients](https://www.tensorflow.org/api_docs/python/tf/keras/backend/gradients)\n",
    " 3. Follow the procedure we used in the previous two sections.\n",
    " 4. Check the axis; make sure weights have shape (C)!\n",
    " 5. See [np.dot](https://docs.scipy.org/doc/numpy/reference/generated/numpy.dot.html)\n",
    "     </details>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "nAJnlx2T7C78"
   },
   "source": [
    "To test, you will compare your output on an image to the output from a correct implementation of GradCAM. You will receive full credit if the pixel-wise mean squared error is less than 0.05."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "TYwp5kvT8ZfR"
   },
   "outputs": [],
   "source": [
    "# UNQ_C1 (UNIQUE CELL IDENTIFIER, DO NOT EDIT)\n",
    "def grad_cam(input_model, image, category_index, layer_name):\n",
    "    \"\"\"\n",
    "    GradCAM method for visualizing input saliency.\n",
    "    \n",
    "    Args:\n",
    "        input_model (Keras.model): model to compute cam for\n",
    "        image (tensor): input to model, shape (1, H, W, 3)\n",
    "        cls (int): class to compute cam with respect to\n",
    "        layer_name (str): relevant layer in model\n",
    "        H (int): input height\n",
    "        W (int): input width\n",
    "    Return:\n",
    "        cam ()\n",
    "    \"\"\"\n",
    "    cam = None\n",
    "    \n",
    "    ### START CODE HERE (REPLACE INSTANCES OF 'None' with your code) ###\n",
    "\n",
    "    # 1. Get placeholders for class output and last layer\n",
    "    # Get the model's output\n",
    "    output_with_batch_dim = input_model.output\n",
    "    \n",
    "    # Remove the batch dimension\n",
    "    output_all_categories = output_with_batch_dim[0]\n",
    "    \n",
    "    # Retrieve only the disease category at the given category index\n",
    "    y_c = output_all_categories[category_index]\n",
    "    \n",
    "    # Get the input model's layer specified by layer_name, and retrive the layer's output tensor\n",
    "    spatial_map_layer = input_model.get_layer(layer_name).output\n",
    "\n",
    "    # 2. Get gradients of last layer with respect to output\n",
    "\n",
    "    # get the gradients of y_c with respect to the spatial map layer (it's a list of length 1)\n",
    "    grads_l = K.gradients(y_c,spatial_map_layer)\n",
    "    \n",
    "    # Get the gradient at index 0 of the list\n",
    "    grads = grads_l[0]\n",
    "        \n",
    "    # 3. Get hook for the selected layer and its gradient, based on given model's input\n",
    "    # Hint: Use the variables produced by the previous two lines of code\n",
    "    spatial_map_and_gradient_function = K.function([input_model.input],[spatial_map_layer, grads])\n",
    "    \n",
    "    # Put in the image to calculate the values of the spatial_maps (selected layer) and values of the gradients\n",
    "    spatial_map_all_dims, grads_val_all_dims = spatial_map_and_gradient_function([image])\n",
    "\n",
    "    # Reshape activations and gradient to remove the batch dimension\n",
    "    # Shape goes from (B, H, W, C) to (H, W, C)\n",
    "    # B: Batch. H: Height. W: Width. C: Channel    \n",
    "    # Reshape spatial map output to remove the batch dimension\n",
    "    spatial_map_val = spatial_map_all_dims[0]\n",
    "    \n",
    "    # Reshape gradients to remove the batch dimension\n",
    "    grads_val = grads_val_all_dims[0]\n",
    "    \n",
    "    # 4. Compute weights using global average pooling on gradient \n",
    "    # grads_val has shape (Height, Width, Channels) (H,W,C)\n",
    "    # Take the mean across the height and also width, for each channel\n",
    "    # Make sure weights have shape (C)\n",
    "    weights = np.mean(grads_val,axis=(0,1))\n",
    "    \n",
    "    # 5. Compute dot product of spatial map values with the weights\n",
    "    cam = np.dot(spatial_map_val, weights)\n",
    "\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    # We'll take care of the postprocessing.\n",
    "    H, W = image.shape[1], image.shape[2]\n",
    "    cam = np.maximum(cam, 0) # ReLU so we only get positive importance\n",
    "    cam = cv2.resize(cam, (W, H), cv2.INTER_NEAREST)\n",
    "    cam = cam / cam.max()\n",
    "\n",
    "    return cam"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "GBi4c71M7OVY"
   },
   "source": [
    "Below we generate the CAM for the image and compute the error (pixel-wise mean squared difference) from the expected values according to our reference. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "4yAC5xBo8J3L",
    "outputId": "0bb46d16-07c6-4211-8312-5b3de8ba06a7"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Error from reference: 0.0302, should be less than 0.05\n"
     ]
    }
   ],
   "source": [
    "im = load_image_normalize(im_path, mean, std)\n",
    "cam = grad_cam(model, im, 5, 'conv5_block16_concat') # Mass is class 5\n",
    "\n",
    "# Loads reference CAM to compare our implementation with.\n",
    "reference = np.load(\"reference_cam.npy\")\n",
    "error = np.mean((cam-reference)**2)\n",
    "\n",
    "print(f\"Error from reference: {error:.4f}, should be less than 0.05\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Tnl0D5pN8MvE"
   },
   "source": [
    "Run the next cell to visualize the CAM and the original image. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 837
    },
    "colab_type": "code",
    "id": "m1kqthIt5AOs",
    "outputId": "5d486156-ada6-4670-fe70-ae928b7baef3"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(load_image(im_path, df, preprocess=False), cmap='gray')\n",
    "plt.title(\"Original\")\n",
    "plt.axis('off')\n",
    "\n",
    "plt.show()\n",
    "\n",
    "plt.imshow(load_image(im_path, df, preprocess=False), cmap='gray')\n",
    "plt.imshow(cam, cmap='magma', alpha=0.5)\n",
    "plt.title(\"GradCAM\")\n",
    "plt.axis('off')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "1Lx0lCu-5DeF"
   },
   "source": [
    "We can see that it focuses on the large (white) empty area on the right lung. Indeed this is a clear case of Mass."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a name=\"1-1-4\"></a>\n",
    "#### 1.1.4 Using GradCAM to Visualize Multiple Labels"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "LUQSkaHsBsUn"
   },
   "source": [
    "<a name='ex-02'></a>\n",
    "### Exercise 2\n",
    "\n",
    "We can use GradCAMs for multiple labels on the same image. Let's do it for the labels with best AUC for our model, Cardiomegaly, Mass, and Edema. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# UNQ_C2 (UNIQUE CELL IDENTIFIER, DO NOT EDIT)\n",
    "def compute_gradcam(model, img, mean, std, data_dir, df, \n",
    "                    labels, selected_labels, layer_name='conv5_block16_concat'):\n",
    "    \"\"\"\n",
    "    Compute GradCAM for many specified labels for an image. \n",
    "    This method will use the `grad_cam` function.\n",
    "    \n",
    "    Args:\n",
    "        model (Keras.model): Model to compute GradCAM for\n",
    "        img (string): Image name we want to compute GradCAM for.\n",
    "        mean (float): Mean to normalize to image.\n",
    "        std (float): Standard deviation to normalize the image.\n",
    "        data_dir (str): Path of the directory to load the images from.\n",
    "        df(pd.Dataframe): Dataframe with the image features.\n",
    "        labels ([str]): All output labels for the model.\n",
    "        selected_labels ([str]): All output labels we want to compute the GradCAM for.\n",
    "        layer_name: Intermediate layer from the model we want to compute the GradCAM for.\n",
    "    \"\"\"\n",
    "    img_path = data_dir + img\n",
    "    preprocessed_input = load_image_normalize(img_path, mean, std)\n",
    "    predictions = model.predict(preprocessed_input)\n",
    "    print(\"Ground Truth: \", \", \".join(np.take(labels, np.nonzero(df[df[\"Image\"] == img][labels].values[0]))[0]))\n",
    "\n",
    "    plt.figure(figsize=(15, 10))\n",
    "    plt.subplot(151)\n",
    "    plt.title(\"Original\")\n",
    "    plt.axis('off')\n",
    "    plt.imshow(load_image(img_path, df, preprocess=False), cmap='gray')\n",
    "    \n",
    "    j = 1\n",
    "    \n",
    "    ### START CODE HERE (REPLACE INSTANCES OF 'None' with your code) ###    \n",
    "    # Loop through all labels\n",
    "    for i in range(len(labels)): # complete this line\n",
    "        # Compute CAM and show plots for each selected label.\n",
    "        \n",
    "        # Check if the label is one of the selected labels\n",
    "        if labels[i] in selected_labels: # complete this line\n",
    "            \n",
    "            # Use the grad_cam function to calculate gradcam\n",
    "            gradcam = grad_cam(model,preprocessed_input,i,layer_name)\n",
    "            \n",
    "            ### END CODE HERE ###\n",
    "            \n",
    "            print(\"Generating gradcam for class %s (p=%2.2f)\" % (labels[i], round(predictions[0][i], 3)))\n",
    "            plt.subplot(151 + j)\n",
    "            plt.title(labels[i] + \": \" + str(round(predictions[0][i], 3)))\n",
    "            plt.axis('off')\n",
    "            plt.imshow(load_image(img_path, df, preprocess=False), cmap='gray')\n",
    "            plt.imshow(gradcam, cmap='magma', alpha=min(0.5, predictions[0][i]))\n",
    "            j +=1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "MIB7qyZ6_eu4"
   },
   "source": [
    "Run the following cells to print the ground truth diagnosis for a given case and show the original x-ray as well as GradCAMs for Cardiomegaly, Mass, and Edema."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 259
    },
    "colab_type": "code",
    "id": "zCh0tNn_6Wmu",
    "outputId": "26e0692b-af47-46f0-f749-8e007e252fba"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ground Truth:  Cardiomegaly\n",
      "Generating gradcam for class Cardiomegaly (p=0.98)\n",
      "Generating gradcam for class Mass (p=0.30)\n",
      "Generating gradcam for class Edema (p=0.13)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x720 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df = pd.read_csv(\"nih_new/train-small.csv\")\n",
    "\n",
    "image_filename = '00016650_000.png'\n",
    "labels_to_show = ['Cardiomegaly', 'Mass', 'Edema']\n",
    "compute_gradcam(model, image_filename, mean, std, IMAGE_DIR, df, labels, labels_to_show)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "cvPOHJeb6HkD"
   },
   "source": [
    "The model correctly predicts absence of mass or edema. The probability for mass is higher, and we can see that it may be influenced by the shapes in the middle of the chest cavity, as well as around the shoulder. We'll run it for two more images. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 259
    },
    "colab_type": "code",
    "id": "4eiXeIXWCCTf",
    "outputId": "90838ee8-7843-4a7f-9268-ad6b36833b94"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ground Truth:  Mass\n",
      "Generating gradcam for class Cardiomegaly (p=0.02)\n",
      "Generating gradcam for class Mass (p=0.99)\n",
      "Generating gradcam for class Edema (p=0.32)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x720 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "image_filename = '00005410_000.png'\n",
    "compute_gradcam(model, image_filename, mean, std, IMAGE_DIR, df, labels, labels_to_show)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "v8Wx5u3t6fiE"
   },
   "source": [
    "In the example above, the model correctly focuses on the mass near the center of the chest cavity. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 259
    },
    "colab_type": "code",
    "id": "V5ViYPuIqM3H",
    "outputId": "1bf4aa59-bb4a-49ad-8b8a-eb654a97dcaa"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ground Truth:  Edema\n",
      "Generating gradcam for class Cardiomegaly (p=0.71)\n",
      "Generating gradcam for class Mass (p=0.23)\n",
      "Generating gradcam for class Edema (p=0.99)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x720 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "image_name = '00004090_002.png'\n",
    "compute_gradcam(model, image_name, mean, std, IMAGE_DIR, df, labels, labels_to_show)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "FroGFoB98A26"
   },
   "source": [
    "Here the model correctly picks up the signs of edema near the bottom of the chest cavity. We can also notice that Cardiomegaly has a high score for this image, though the ground truth doesn't include it. This visualization might be helpful for error analysis; for example, we can notice that the model is indeed looking at the expected area to make the prediction."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "sN_laVv3DHVp"
   },
   "source": [
    "This concludes the section on GradCAMs. We hope you've gained an appreciation for the importance of interpretation when it comes to deep learning models in medicine. Interpretation tools like this one can be helpful for discovery of markers, error analysis, and even in deployment. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "hBR1ML_8pEXe"
   },
   "source": [
    "<a name=\"2\"></a>\n",
    "## 2 Feature Importance in Machine Learning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "jqq5oDOuLjrB"
   },
   "source": [
    "When developing predictive models and risk measures, it's often helpful to know which features are making the most difference. This is easy to determine in simpler models such as linear models and decision trees. However as we move to more complex models to achieve high performance, we usually sacrifice some interpretability. In this assignment we'll try to regain some of that interpretability using Shapley values, a technique which has gained popularity in recent years, but which is based on classic results in cooperative game theory. \n",
    "\n",
    "We'll revisit our random forest model from course 2 module 2 and try to analyze it more closely using Shapley values. Run the next cell to load in the data and model from that assignment and recalculate the test set c-index."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 122
    },
    "colab_type": "code",
    "id": "VrCZoOmJVF_U",
    "outputId": "9251d060-baed-440d-d4a2-cd206b60e3a3"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model C-index on test: 0.7776169781865744\n"
     ]
    }
   ],
   "source": [
    "rf = pickle.load(open('nhanes_rf.sav', 'rb')) # Loading the model\n",
    "test_df = pd.read_csv('nhanest_test.csv')\n",
    "test_df = test_df.drop(test_df.columns[0], axis=1)\n",
    "X_test = test_df.drop('y', axis=1)\n",
    "y_test = test_df.loc[:, 'y']\n",
    "cindex_test = cindex(y_test, rf.predict_proba(X_test)[:, 1])\n",
    "\n",
    "print(\"Model C-index on test: {}\".format(cindex_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "w4-TT-8VXJxW"
   },
   "source": [
    "Run the next cell to print out the riskiest individuals according to our model. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 258
    },
    "colab_type": "code",
    "id": "y_7aDY6rWsbS",
    "outputId": "f296fd3f-37c5-4834-d0f1-19f93758ab63"
   },
   "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>Age</th>\n",
       "      <th>Diastolic BP</th>\n",
       "      <th>Poverty index</th>\n",
       "      <th>Race</th>\n",
       "      <th>Red blood cells</th>\n",
       "      <th>Sedimentation rate</th>\n",
       "      <th>Serum Albumin</th>\n",
       "      <th>Serum Cholesterol</th>\n",
       "      <th>Serum Iron</th>\n",
       "      <th>Serum Magnesium</th>\n",
       "      <th>Serum Protein</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Systolic BP</th>\n",
       "      <th>TIBC</th>\n",
       "      <th>TS</th>\n",
       "      <th>White blood cells</th>\n",
       "      <th>BMI</th>\n",
       "      <th>Pulse pressure</th>\n",
       "      <th>risk</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>572</th>\n",
       "      <td>70.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>312.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>54.8</td>\n",
       "      <td>7.0</td>\n",
       "      <td>4.4</td>\n",
       "      <td>222.0</td>\n",
       "      <td>52.0</td>\n",
       "      <td>1.57</td>\n",
       "      <td>7.2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>417.0</td>\n",
       "      <td>12.5</td>\n",
       "      <td>7.5</td>\n",
       "      <td>45.770473</td>\n",
       "      <td>100.0</td>\n",
       "      <td>0.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>69.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>316.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>77.7</td>\n",
       "      <td>26.0</td>\n",
       "      <td>4.2</td>\n",
       "      <td>197.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>1.49</td>\n",
       "      <td>7.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>165.0</td>\n",
       "      <td>298.0</td>\n",
       "      <td>21.8</td>\n",
       "      <td>8.8</td>\n",
       "      <td>22.129018</td>\n",
       "      <td>65.0</td>\n",
       "      <td>0.69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1300</th>\n",
       "      <td>73.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>999.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>52.6</td>\n",
       "      <td>35.0</td>\n",
       "      <td>3.9</td>\n",
       "      <td>258.0</td>\n",
       "      <td>61.0</td>\n",
       "      <td>1.66</td>\n",
       "      <td>6.8</td>\n",
       "      <td>1.0</td>\n",
       "      <td>150.0</td>\n",
       "      <td>314.0</td>\n",
       "      <td>19.4</td>\n",
       "      <td>9.4</td>\n",
       "      <td>26.466850</td>\n",
       "      <td>70.0</td>\n",
       "      <td>0.69</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>634</th>\n",
       "      <td>66.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>42.9</td>\n",
       "      <td>47.0</td>\n",
       "      <td>3.8</td>\n",
       "      <td>233.0</td>\n",
       "      <td>170.0</td>\n",
       "      <td>1.42</td>\n",
       "      <td>8.6</td>\n",
       "      <td>1.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>411.0</td>\n",
       "      <td>41.4</td>\n",
       "      <td>7.2</td>\n",
       "      <td>22.129498</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0.68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1221</th>\n",
       "      <td>74.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>40.3</td>\n",
       "      <td>24.0</td>\n",
       "      <td>3.7</td>\n",
       "      <td>139.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>1.91</td>\n",
       "      <td>6.4</td>\n",
       "      <td>2.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>495.0</td>\n",
       "      <td>5.7</td>\n",
       "      <td>4.1</td>\n",
       "      <td>22.066389</td>\n",
       "      <td>60.0</td>\n",
       "      <td>0.68</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Age  Diastolic BP  Poverty index  Race  Red blood cells  \\\n",
       "572   70.0          80.0          312.0   1.0             54.8   \n",
       "190   69.0         100.0          316.0   1.0             77.7   \n",
       "1300  73.0          80.0          999.0   1.0             52.6   \n",
       "634   66.0         100.0           69.0   2.0             42.9   \n",
       "1221  74.0          80.0           67.0   1.0             40.3   \n",
       "\n",
       "      Sedimentation rate  Serum Albumin  Serum Cholesterol  Serum Iron  \\\n",
       "572                  7.0            4.4              222.0        52.0   \n",
       "190                 26.0            4.2              197.0        65.0   \n",
       "1300                35.0            3.9              258.0        61.0   \n",
       "634                 47.0            3.8              233.0       170.0   \n",
       "1221                24.0            3.7              139.0        28.0   \n",
       "\n",
       "      Serum Magnesium  Serum Protein  Sex  Systolic BP   TIBC    TS  \\\n",
       "572              1.57            7.2  1.0        180.0  417.0  12.5   \n",
       "190              1.49            7.5  1.0        165.0  298.0  21.8   \n",
       "1300             1.66            6.8  1.0        150.0  314.0  19.4   \n",
       "634              1.42            8.6  1.0        180.0  411.0  41.4   \n",
       "1221             1.91            6.4  2.0        140.0  495.0   5.7   \n",
       "\n",
       "      White blood cells        BMI  Pulse pressure  risk  \n",
       "572                 7.5  45.770473           100.0  0.77  \n",
       "190                 8.8  22.129018            65.0  0.69  \n",
       "1300                9.4  26.466850            70.0  0.69  \n",
       "634                 7.2  22.129498            80.0  0.68  \n",
       "1221                4.1  22.066389            60.0  0.68  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test_risky = X_test.copy(deep=True)\n",
    "X_test_risky.loc[:, 'risk'] = rf.predict_proba(X_test)[:, 1] # Predicting our risk.\n",
    "X_test_risky = X_test_risky.sort_values(by='risk', ascending=False) # Sorting by risk value.\n",
    "X_test_risky.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "egBagzTuLduV"
   },
   "source": [
    "<a name=\"2-1\"></a>\n",
    "### 2.1 Permuation Method for Feature Importance\n",
    "\n",
    "First we'll try to determine feature importance using the permutation method. In the permutation method, the importance of feature $i$ would be the regular performance of the model minus the performance with the values for feature $i$ permuted in the dataset. This way we can assess how well a model without that feature would do without having to train a new model for each feature. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a name=\"2-1-1\"></a>\n",
    "#### 2.1.1 Implementing Permutation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a name='ex-03'></a>\n",
    "### Exercise 3\n",
    "\n",
    "Complete the implementation of the function below, which given a feature name returns a dataset with those feature values randomly permuted. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<details>\n",
    "    <summary>\n",
    "    <font size=\"3\" color=\"darkgreen\"><b>Hints</b></font>\n",
    "</summary>\n",
    "    <ul>\n",
    "        <li>\n",
    "            See <a href=https://numpy.org/devdocs/reference/random/generated/numpy.random.permutation.html> np.random.permutation</a>\n",
    "        </li>\n",
    "    </ul>\n",
    "</details>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 306
    },
    "colab_type": "code",
    "id": "iKTpkaRgP-dz",
    "outputId": "bc74170d-deac-444c-cd6d-7223f0545c87"
   },
   "outputs": [],
   "source": [
    "# UNQ_C3 (UNIQUE CELL IDENTIFIER, DO NOT EDIT)\n",
    "def permute_feature(df, feature):\n",
    "    \"\"\"\n",
    "    Given dataset, returns version with the values of\n",
    "    the given feature randomly permuted. \n",
    "\n",
    "    Args:\n",
    "        df (dataframe): The dataset, shape (num subjects, num features)\n",
    "        feature (string): Name of feature to permute\n",
    "    Returns:\n",
    "        permuted_df (dataframe): Exactly the same as df except the values\n",
    "                                of the given feature are randomly permuted.\n",
    "    \"\"\"\n",
    "    permuted_df = df.copy(deep=True) # Make copy so we don't change original df\n",
    "\n",
    "    ### START CODE HERE (REPLACE INSTANCES OF 'None' with your code) ###\n",
    "\n",
    "    # Permute the values of the column 'feature'\n",
    "    permuted_features = df.copy(deep=True)\n",
    "    \n",
    "    # Set the column 'feature' to its permuted values.\n",
    "    permuted_df[feature] = np.random.permutation(permuted_df[feature])\n",
    "    \n",
    "    ### END CODE HERE ###\n",
    "\n",
    "    return permuted_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test Case\n",
      "Original dataframe:\n",
      "   col1 col2\n",
      "0     0    A\n",
      "1     1    B\n",
      "2     2    C\n",
      "\n",
      "\n",
      "col1 permuted:\n",
      "   col1 col2\n",
      "0     2    A\n",
      "1     1    B\n",
      "2     0    C\n",
      "\n",
      "\n",
      "Compute average values over 1000 runs to get expected values:\n",
      "Average of col1: [0.976 1.03  0.994], expected value: [0.976, 1.03, 0.994]\n"
     ]
    }
   ],
   "source": [
    "print(\"Test Case\")\n",
    "\n",
    "example_df = pd.DataFrame({'col1': [0, 1, 2], 'col2':['A', 'B', 'C']})\n",
    "print(\"Original dataframe:\")\n",
    "print(example_df)\n",
    "print(\"\\n\")\n",
    "\n",
    "print(\"col1 permuted:\")\n",
    "print(permute_feature(example_df, 'col1'))\n",
    "\n",
    "print(\"\\n\")\n",
    "print(\"Compute average values over 1000 runs to get expected values:\")\n",
    "col1_values = np.zeros((3, 1000))\n",
    "np.random.seed(0) # Adding a constant seed so we can always expect the same values and evaluate correctly. \n",
    "for i in range(1000):\n",
    "    col1_values[:, i] = permute_feature(example_df, 'col1')['col1'].values\n",
    "\n",
    "print(\"Average of col1: {}, expected value: [0.976, 1.03, 0.994]\".format(np.mean(col1_values, axis=1)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a name=\"2-1-2\"></a>\n",
    "#### 2.1.2 Implementing Importance"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "YNH7oo7jQVo6"
   },
   "source": [
    "<a name='ex-04'></a>\n",
    "### Exercise 4\n",
    "\n",
    "Now we will use the function we just created to compute feature importances (according to the permutation method) in the function below."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<details>\n",
    "    <summary>\n",
    "    <font size=\"3\" color=\"darkgreen\"><b>Hints</b></font>\n",
    "</summary>\n",
    "\\begin{align}\n",
    "I_x  = \\left\\lvert perf - perf_x  \\right\\rvert\n",
    "\\end{align}\n",
    "\n",
    "where $I_x$ is the importance of feature $x$ and\n",
    "\\begin{align}\n",
    "perf_x  = \\frac{1}{n}\\cdot \\sum_{i=1}^{n} perf_i^{sx}\n",
    "\\end{align}\n",
    "\n",
    "where $perf_i^{sx}$ is the performance with the feature $x$ shuffled in the $i$th permutation.\n",
    "</details>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 289
    },
    "colab_type": "code",
    "id": "R_PP-DEz04hp",
    "outputId": "a8fb98da-d513-43cd-d349-b2265beb270c"
   },
   "outputs": [],
   "source": [
    "# UNQ_C4 (UNIQUE CELL IDENTIFIER, DO NOT EDIT)\n",
    "def permutation_importance(X, y, model, metric, num_samples = 100):\n",
    "    \"\"\"\n",
    "    Compute permutation importance for each feature.\n",
    "\n",
    "    Args:\n",
    "        X (dataframe): Dataframe for test data, shape (num subject, num features)\n",
    "        y (np.array): Labels for each row of X, shape (num subjects,)\n",
    "        model (object): Model to compute importances for, guaranteed to have\n",
    "                        a 'predict_proba' method to compute probabilistic \n",
    "                        predictions given input\n",
    "        metric (function): Metric to be used for feature importance. Takes in ground\n",
    "                           truth and predictions as the only two arguments\n",
    "        num_samples (int): Number of samples to average over when computing change in\n",
    "                           performance for each feature\n",
    "    Returns:\n",
    "        importances (dataframe): Dataframe containing feature importance for each\n",
    "                                 column of df with shape (1, num_features)\n",
    "    \"\"\"\n",
    "\n",
    "    importances = pd.DataFrame(index = ['importance'], columns = X.columns)\n",
    "    \n",
    "    # Get baseline performance (note, you'll use this metric function again later)\n",
    "    baseline_performance = metric(y, model.predict_proba(X)[:, 1])\n",
    "\n",
    "    ### START CODE HERE (REPLACE INSTANCES OF 'None' with your code) ###\n",
    "\n",
    "    # Iterate over features (the columns in the importances dataframe)\n",
    "    for feature in importances.columns: # complete this line\n",
    "        \n",
    "        # Compute 'num_sample' performances by permutating that feature\n",
    "        \n",
    "        # You'll see how the model performs when the feature is permuted\n",
    "        # You'll do this num_samples number of times, and save the performance each time\n",
    "        # To store the feature performance,\n",
    "        # create a numpy array of size num_samples, initialized to all zeros\n",
    "        feature_performance_arr = np.zeros(num_samples)\n",
    "        \n",
    "        # Loop through each sample\n",
    "        for i in range(num_samples): # complete this line\n",
    "            \n",
    "            # permute the column of dataframe X\n",
    "            perm_X = permute_feature(X,feature)\n",
    "            \n",
    "            # calculate the performance with the permuted data\n",
    "            # Use the same metric function that was used earlier\n",
    "            feature_performance_arr[i] = metric(y, model.predict_proba(perm_X)[:, 1])\n",
    "    \n",
    "    \n",
    "        # Compute importance: absolute difference between \n",
    "        # the baseline performance and the average across the feature performance\n",
    "        importances[feature]['importance'] = np.abs(baseline_performance - np.mean(feature_performance_arr))\n",
    "        \n",
    "    ### END CODE HERE ###\n",
    "\n",
    "    return importances"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Test Case**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test Case\n",
      "\n",
      "\n",
      "We check our answers on a Logistic Regression on a dataset\n",
      "where y is given by a sigmoid applied to the important feature.\n",
      "The unimportant feature is random noise.\n",
      "\n",
      "\n",
      "Computed importances:\n",
      "           important  unimportant\n",
      "importance  0.496674  2.89012e-05\n",
      "\n",
      "\n",
      "Expected importances (approximate values):\n",
      "            important  unimportant\n",
      "importance        0.5          0.0\n",
      "If you round the actual values, they will be similar to the expected values\n"
     ]
    }
   ],
   "source": [
    "print(\"Test Case\")\n",
    "print(\"\\n\")\n",
    "print(\"We check our answers on a Logistic Regression on a dataset\")\n",
    "print(\"where y is given by a sigmoid applied to the important feature.\") \n",
    "print(\"The unimportant feature is random noise.\")\n",
    "print(\"\\n\")\n",
    "example_df = pd.DataFrame({'important': np.random.normal(size=(1000)), 'unimportant':np.random.normal(size=(1000))})\n",
    "example_y = np.round(1 / (1 + np.exp(-example_df.important)))\n",
    "example_model = sklearn.linear_model.LogisticRegression(fit_intercept=False).fit(example_df, example_y)\n",
    "\n",
    "example_importances = permutation_importance(example_df, example_y, example_model, cindex, num_samples=100)\n",
    "print(\"Computed importances:\")\n",
    "print(example_importances)\n",
    "print(\"\\n\")\n",
    "print(\"Expected importances (approximate values):\")\n",
    "print(pd.DataFrame({\"important\": 0.50, \"unimportant\": 0.00}, index=['importance']))\n",
    "print(\"If you round the actual values, they will be similar to the expected values\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a name=\"2-1-3\"></a>\n",
    "#### 2.1.3 Computing our Feature Importance"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "47iozBppkTwl"
   },
   "source": [
    "Next, we compute importances on our dataset. Since we are computing the permutation importance for all the features, it might take a few minutes to run."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 134
    },
    "colab_type": "code",
    "id": "uhxor87eYEKt",
    "outputId": "0e98bf36-4691-484c-bb5e-6ceda74de971"
   },
   "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>Age</th>\n",
       "      <th>Diastolic BP</th>\n",
       "      <th>Poverty index</th>\n",
       "      <th>Race</th>\n",
       "      <th>Red blood cells</th>\n",
       "      <th>Sedimentation rate</th>\n",
       "      <th>Serum Albumin</th>\n",
       "      <th>Serum Cholesterol</th>\n",
       "      <th>Serum Iron</th>\n",
       "      <th>Serum Magnesium</th>\n",
       "      <th>Serum Protein</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Systolic BP</th>\n",
       "      <th>TIBC</th>\n",
       "      <th>TS</th>\n",
       "      <th>White blood cells</th>\n",
       "      <th>BMI</th>\n",
       "      <th>Pulse pressure</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>importance</th>\n",
       "      <td>0.147772</td>\n",
       "      <td>0.0113034</td>\n",
       "      <td>0.0111148</td>\n",
       "      <td>0.000449158</td>\n",
       "      <td>0.000805694</td>\n",
       "      <td>0.006285</td>\n",
       "      <td>0.00527172</td>\n",
       "      <td>0.000848118</td>\n",
       "      <td>0.000203789</td>\n",
       "      <td>0.00274019</td>\n",
       "      <td>0.00154867</td>\n",
       "      <td>0.0272337</td>\n",
       "      <td>0.00618949</td>\n",
       "      <td>0.00225922</td>\n",
       "      <td>0.000425288</td>\n",
       "      <td>0.00256128</td>\n",
       "      <td>0.00304884</td>\n",
       "      <td>0.00379624</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 Age Diastolic BP Poverty index         Race Red blood cells  \\\n",
       "importance  0.147772    0.0113034     0.0111148  0.000449158     0.000805694   \n",
       "\n",
       "           Sedimentation rate Serum Albumin Serum Cholesterol   Serum Iron  \\\n",
       "importance           0.006285    0.00527172       0.000848118  0.000203789   \n",
       "\n",
       "           Serum Magnesium Serum Protein        Sex Systolic BP        TIBC  \\\n",
       "importance      0.00274019    0.00154867  0.0272337  0.00618949  0.00225922   \n",
       "\n",
       "                     TS White blood cells         BMI Pulse pressure  \n",
       "importance  0.000425288        0.00256128  0.00304884     0.00379624  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "importances = permutation_importance(X_test, y_test, rf, cindex, num_samples=100)\n",
    "importances"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "pQ-d-X6VlQ2T"
   },
   "source": [
    "Let's plot these in a bar chart for easier comparison."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 515
    },
    "colab_type": "code",
    "id": "YOpUIt32lQZW",
    "outputId": "fa872d44-da2f-4517-c2e1-8f5e54080522"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "importances.T.plot.bar()\n",
    "plt.ylabel(\"Importance\")\n",
    "l = plt.legend()\n",
    "l.remove()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "yFbnsXMTnmRI"
   },
   "source": [
    "You should see age as by far the best prediction of near term mortality, as one might expect. Next is sex, followed by diastolic blood pressure. Interestingly, the poverty index also has a large impact, despite the fact that it is not directly related to an individual's health. This alludes to the importance of social determinants of health in our model. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "-wiIIOV0Xgyn"
   },
   "source": [
    "<a name=\"2-2\"></a>\n",
    "### 2.2 Shapley Values for Random Forests"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "I-MzbzsnXaGI"
   },
   "source": [
    "We'll contrast the permutation method with a more recent technique known as Shapley values (actually, Shapley values date back to the mid 20th century, but have only been applied to machine learning very recently). "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a name=\"2-2-1\"></a>\n",
    "#### 2.2.1 Visualizing Feature Importance on Specific Individuals"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can use Shapley values to try and understand the model output on specific individuals. In general Shapley values take exponential time to compute, but luckily there are faster approximations for forests in particular that run in polynomial time. Run the next cell to display a 'force plot' showing how each feature influences the output for the first person in our dataset. If you want more information about 'force plots' and other decision plots, please take a look at [this notebook](https://github.com/slundberg/shap/blob/master/notebooks/plots/decision_plot.ipynb) by the `shap` library creators."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 310
    },
    "colab_type": "code",
    "id": "iVPZg-I_XjFJ",
    "outputId": "4fde0bf6-6cd6-44b5-dcfb-c906eda2066b"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting feature_perturbation = \"tree_path_dependent\" because no background data was given.\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x216 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "explainer = shap.TreeExplainer(rf)\n",
    "i = 0 # Picking an individual\n",
    "shap_value = explainer.shap_values(X_test.loc[X_test_risky.index[i], :])[1]\n",
    "shap.force_plot(explainer.expected_value[1], shap_value, feature_names=X_test.columns, matplotlib=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "5EIPLm1hAunF"
   },
   "source": [
    "For this individual, their age, pulse pressure, and sex were the biggest contributors to their high risk prediction. Note how shapley values give us greater granularity in our interpretations. \n",
    "\n",
    "Feel free to change the `i` value above to explore the feature influences for different individuals."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a name=\"2-2-2\"></a>\n",
    "#### 2.2.2 Visualizing Feature Importance on Aggregate"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "BH1p21GpY-0Y"
   },
   "source": [
    "Just like with the permutation method, we might also want to understand model output in aggregate. Shapley values allow us to do this as well. Run the next cell to initialize the shapley values for each example in the test set (this may also take a few minutes). "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "gFXBwZesYkRb",
    "outputId": "69846d78-f974-4299-82f6-fa0823345c16"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting feature_perturbation = \"tree_path_dependent\" because no background data was given.\n"
     ]
    }
   ],
   "source": [
    "shap_values = shap.TreeExplainer(rf).shap_values(X_test)[1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can ignore the `setting feature_perturbation` message."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "RzPYyknlZR3N"
   },
   "source": [
    "Run the next cell to see a summary plot of the shapley values for each feature on each of the test examples. The colors indicate the value of the feature. The features are listed in terms of decreasing absolute average shapley value over all the individuals in the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 542
    },
    "colab_type": "code",
    "id": "msyIjYJxZMwn",
    "outputId": "cbfd0b81-e4c5-42ff-e073-4943257b921d"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x626.4 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "shap.summary_plot(shap_values, X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the above plot, you might be able to notice a high concentration of points on specific SHAP value ranges. This means that a high proportion of our test set lies on those ranges.\n",
    "\n",
    "As with the permutation method, age, sex, poverty index, and diastolic BP seem to be the most important features. Being older has a negative impact on mortality, and being a woman (sex=2.0) has a positive effect. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a name=\"2-2-3\"></a>\n",
    "#### 2.2.3 Visualizing Interactions between Features"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "srQhm3NLZo_I"
   },
   "source": [
    "The `shap` library also lets you visualize interactions between features using dependence plots. These plot the Shapley value for a given feature for each data point, and color the points in using the value for another feature. This lets us begin to explain the variation in shapley value for a single value of the main feature."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "UZ8XWDYcZtKr"
   },
   "source": [
    "Run the next cell to see the interaction between Age and Sex. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 341
    },
    "colab_type": "code",
    "id": "RnaiY5h3Zh4s",
    "outputId": "a3bff772-dc60-4fa2-f1d7-19b67c551208"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 540x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "shap.dependence_plot('Age', shap_values, X_test, interaction_index = 'Sex')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We see that while Age > 50 is generally bad (positive Shapley value), being a woman (red points) generally reduces the impact of age. This makes sense since we know that women generally live longer than men. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "CwHcYZFXZ1R0"
   },
   "source": [
    "Run the next cell to see the interaction between Poverty index and Age "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 337
    },
    "colab_type": "code",
    "id": "xzfw5itbZwAQ",
    "outputId": "f9f229f0-4316-4687-9fe2-4d3461d4dad0"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 540x360 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "shap.dependence_plot('Poverty index', shap_values, X_test, interaction_index='Age')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We see that the impact of poverty index drops off quickly, and for higher income individuals age begins to explain much of variation in the impact of poverty index. We encourage you to try some other pairs and see what other interesting relationships you can find!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "a1tzI8JrBVa6"
   },
   "source": [
    "Congratulations! You've completed the final assignment of course 3, well done! "
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "include_colab_link": true,
   "name": "C3M2_Assignment.ipynb",
   "provenance": [],
   "toc_visible": true
  },
  "coursera": {
   "schema_names": [
    "AI4MC3-3"
   ]
  },
  "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}