Week 3 exercise of Andrew NG Deep learning.ai

Week_3_Deeplearning.ai

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Autonomous driving - Car detection\n",
    "\n",
    "Welcome to your week 3 programming assignment. You will learn about object detection using the very powerful YOLO model. Many of the ideas in this notebook are described in the two YOLO papers: Redmon et al., 2016 (https://arxiv.org/abs/1506.02640) and Redmon and Farhadi, 2016 (https://arxiv.org/abs/1612.08242). \n",
    "\n",
    "**You will learn to**:\n",
    "- Use object detection on a car detection dataset\n",
    "- Deal with bounding boxes\n",
    "\n",
    "Run the following cell to load the packages and dependencies that are going to be useful for your journey!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "import argparse\n",
    "import os\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.pyplot import imshow\n",
    "import scipy.io\n",
    "import scipy.misc\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import PIL\n",
    "import tensorflow as tf\n",
    "from keras import backend as K\n",
    "from keras.layers import Input, Lambda, Conv2D\n",
    "from keras.models import load_model, Model\n",
    "from yolo_utils import read_classes, read_anchors, generate_colors, preprocess_image, draw_boxes, scale_boxes\n",
    "from yad2k.models.keras_yolo import yolo_head, yolo_boxes_to_corners, preprocess_true_boxes, yolo_loss, yolo_body\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Important Note**: As you can see, we import Keras's backend as K. This means that to use a Keras function in this notebook, you will need to write: `K.function(...)`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1 - Problem Statement\n",
    "\n",
    "You are working on a self-driving car. As a critical component of this project, you'd like to first build a car detection system. To collect data, you've mounted a camera to the hood (meaning the front) of the car, which takes pictures of the road ahead every few seconds while you drive around. \n",
    "\n",
    "<center>\n",
    "<video width=\"400\" height=\"200\" src=\"nb_images/road_video_compressed2.mp4\" type=\"video/mp4\" controls>\n",
    "</video>\n",
    "</center>\n",
    "\n",
    "<caption><center> Pictures taken from a car-mounted camera while driving around Silicon Valley. <br> We would like to especially thank [drive.ai](https://www.drive.ai/) for providing this dataset! Drive.ai is a company building the brains of self-driving vehicles.\n",
    "</center></caption>\n",
    "\n",
    "<img src=\"nb_images/driveai.png\" style=\"width:100px;height:100;\">\n",
    "\n",
    "You've gathered all these images into a folder and have labelled them by drawing bounding boxes around every car you found. Here's an example of what your bounding boxes look like.\n",
    "\n",
    "<img src=\"nb_images/box_label.png\" style=\"width:500px;height:250;\">\n",
    "<caption><center> <u> **Figure 1** </u>: **Definition of a box**<br> </center></caption>\n",
    "\n",
    "If you have 80 classes that you want YOLO to recognize, you can represent the class label $c$ either as an integer from 1 to 80, or as an 80-dimensional vector (with 80 numbers) one component of which is 1 and the rest of which are 0. The video lectures had used the latter representation; in this notebook, we will use both representations, depending on which is more convenient for a particular step.  \n",
    "\n",
    "In this exercise, you will learn how YOLO works, then apply it to car detection. Because the YOLO model is very computationally expensive to train, we will load pre-trained weights for you to use. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2 - YOLO"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "YOLO (\"you only look once\") is a popular algoritm because it achieves high accuracy while also being able to run in real-time. This algorithm \"only looks once\" at the image in the sense that it requires only one forward propagation pass through the network to make predictions. After non-max suppression, it then outputs recognized objects together with the bounding boxes.\n",
    "\n",
    "### 2.1 - Model details\n",
    "\n",
    "First things to know:\n",
    "- The **input** is a batch of images of shape (m, 608, 608, 3)\n",
    "- The **output** is a list of bounding boxes along with the recognized classes. Each bounding box is represented by 6 numbers $(p_c, b_x, b_y, b_h, b_w, c)$ as explained above. If you expand $c$ into an 80-dimensional vector, each bounding box is then represented by 85 numbers. \n",
    "\n",
    "We will use 5 anchor boxes. So you can think of the YOLO architecture as the following: IMAGE (m, 608, 608, 3) -> DEEP CNN -> ENCODING (m, 19, 19, 5, 85).\n",
    "\n",
    "Lets look in greater detail at what this encoding represents. \n",
    "\n",
    "<img src=\"nb_images/architecture.png\" style=\"width:700px;height:400;\">\n",
    "<caption><center> <u> **Figure 2** </u>: **Encoding architecture for YOLO**<br> </center></caption>\n",
    "\n",
    "If the center/midpoint of an object falls into a grid cell, that grid cell is responsible for detecting that object."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since we are using 5 anchor boxes, each of the 19 x19 cells thus encodes information about 5 boxes. Anchor boxes are defined only by their width and height.\n",
    "\n",
    "For simplicity, we will flatten the last two last dimensions of the shape (19, 19, 5, 85) encoding. So the output of the Deep CNN is (19, 19, 425).\n",
    "\n",
    "<img src=\"nb_images/flatten.png\" style=\"width:700px;height:400;\">\n",
    "<caption><center> <u> **Figure 3** </u>: **Flattening the last two last dimensions**<br> </center></caption>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, for each box (of each cell) we will compute the following elementwise product and extract a probability that the box contains a certain class.\n",
    "\n",
    "<img src=\"nb_images/probability_extraction.png\" style=\"width:700px;height:400;\">\n",
    "<caption><center> <u> **Figure 4** </u>: **Find the class detected by each box**<br> </center></caption>\n",
    "\n",
    "Here's one way to visualize what YOLO is predicting on an image:\n",
    "- For each of the 19x19 grid cells, find the maximum of the probability scores (taking a max across both the 5 anchor boxes and across different classes). \n",
    "- Color that grid cell according to what object that grid cell considers the most likely.\n",
    "\n",
    "Doing this results in this picture: \n",
    "\n",
    "<img src=\"nb_images/proba_map.png\" style=\"width:300px;height:300;\">\n",
    "<caption><center> <u> **Figure 5** </u>: Each of the 19x19 grid cells colored according to which class has the largest predicted probability in that cell.<br> </center></caption>\n",
    "\n",
    "Note that this visualization isn't a core part of the YOLO algorithm itself for making predictions; it's just a nice way of visualizing an intermediate result of the algorithm. \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Another way to visualize YOLO's output is to plot the bounding boxes that it outputs. Doing that results in a visualization like this:  \n",
    "\n",
    "<img src=\"nb_images/anchor_map.png\" style=\"width:200px;height:200;\">\n",
    "<caption><center> <u> **Figure 6** </u>: Each cell gives you 5 boxes. In total, the model predicts: 19x19x5 = 1805 boxes just by looking once at the image (one forward pass through the network)! Different colors denote different classes. <br> </center></caption>\n",
    "\n",
    "In the figure above, we plotted only boxes that the model had assigned a high probability to, but this is still too many boxes. You'd like to filter the algorithm's output down to a much smaller number of detected objects. To do so, you'll use non-max suppression. Specifically, you'll carry out these steps: \n",
    "- Get rid of boxes with a low score (meaning, the box is not very confident about detecting a class)\n",
    "- Select only one box when several boxes overlap with each other and detect the same object.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.2 - Filtering with a threshold on class scores\n",
    "\n",
    "You are going to apply a first filter by thresholding. You would like to get rid of any box for which the class \"score\" is less than a chosen threshold. \n",
    "\n",
    "The model gives you a total of 19x19x5x85 numbers, with each box described by 85 numbers. It'll be convenient to rearrange the (19,19,5,85) (or (19,19,425)) dimensional tensor into the following variables:  \n",
    "- `box_confidence`: tensor of shape $(19 \\times 19, 5, 1)$ containing $p_c$ (confidence probability that there's some object) for each of the 5 boxes predicted in each of the 19x19 cells.\n",
    "- `boxes`: tensor of shape $(19 \\times 19, 5, 4)$ containing $(b_x, b_y, b_h, b_w)$ for each of the 5 boxes per cell.\n",
    "- `box_class_probs`: tensor of shape $(19 \\times 19, 5, 80)$ containing the detection probabilities $(c_1, c_2, ... c_{80})$ for each of the 80 classes for each of the 5 boxes per cell.\n",
    "\n",
    "**Exercise**: Implement `yolo_filter_boxes()`.\n",
    "1. Compute box scores by doing the elementwise product as described in Figure 4. The following code may help you choose the right operator: \n",
    "```python\n",
    "a = np.random.randn(19*19, 5, 1)\n",
    "b = np.random.randn(19*19, 5, 80)\n",
    "c = a * b # shape of c will be (19*19, 5, 80)\n",
    "```\n",
    "2. For each box, find:\n",
    "    - the index of the class with the maximum box score ([Hint](https://keras.io/backend/#argmax)) (Be careful with what axis you choose; consider using axis=-1)\n",
    "    - the corresponding box score ([Hint](https://keras.io/backend/#max)) (Be careful with what axis you choose; consider using axis=-1)\n",
    "3. Create a mask by using a threshold. As a reminder: `([0.9, 0.3, 0.4, 0.5, 0.1] < 0.4)` returns: `[False, True, False, False, True]`. The mask should be True for the boxes you want to keep. \n",
    "4. Use TensorFlow to apply the mask to box_class_scores, boxes and box_classes to filter out the boxes we don't want. You should be left with just the subset of boxes you want to keep. ([Hint](https://www.tensorflow.org/api_docs/python/tf/boolean_mask))\n",
    "\n",
    "Reminder: to call a Keras function, you should use `K.function(...)`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# GRADED FUNCTION: yolo_filter_boxes\n",
    "\n",
    "def yolo_filter_boxes(box_confidence, boxes, box_class_probs, threshold = .6):\n",
    "    \"\"\"Filters YOLO boxes by thresholding on object and class confidence.\n",
    "    \n",
    "    Arguments:\n",
    "    box_confidence -- tensor of shape (19, 19, 5, 1)\n",
    "    boxes -- tensor of shape (19, 19, 5, 4)\n",
    "    box_class_probs -- tensor of shape (19, 19, 5, 80)\n",
    "    threshold -- real value, if [ highest class probability score < threshold], then get rid of the corresponding box\n",
    "    \n",
    "    Returns:\n",
    "    scores -- tensor of shape (None,), containing the class probability score for selected boxes\n",
    "    boxes -- tensor of shape (None, 4), containing (b_x, b_y, b_h, b_w) coordinates of selected boxes\n",
    "    classes -- tensor of shape (None,), containing the index of the class detected by the selected boxes\n",
    "    \n",
    "    Note: \"None\" is here because you don't know the exact number of selected boxes, as it depends on the threshold. \n",
    "    For example, the actual output size of scores would be (10,) if there are 10 boxes.\n",
    "    \"\"\"\n",
    "    \n",
    "    # Step 1: Compute box scores\n",
    "    ### START CODE HERE ### (≈ 1 line)\n",
    "    box_scores = box_confidence * box_class_probs\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    # Step 2: Find the box_classes thanks to the max box_scores, keep track of the corresponding score\n",
    "    ### START CODE HERE ### (≈ 2 lines)\n",
    "    box_classes = K.tf.argmax(box_scores, axis=-1)\n",
    "    box_class_scores = K.max(box_scores, axis=-1)\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    # Step 3: Create a filtering mask based on \"box_class_scores\" by using \"threshold\". The mask should have the\n",
    "    # same dimension as box_class_scores, and be True for the boxes you want to keep (with probability >= threshold)\n",
    "    ### START CODE HERE ### (≈ 1 line)\n",
    "    filtering_mask = box_class_scores >= threshold\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    # Step 4: Apply the mask to scores, boxes and classes\n",
    "    ### START CODE HERE ### (≈ 3 lines)\n",
    "    scores = tf.boolean_mask(box_class_scores,filtering_mask)\n",
    "    boxes = tf.boolean_mask(boxes, filtering_mask)\n",
    "    classes = tf.boolean_mask(box_classes,filtering_mask)\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    #return scores\n",
    "    return scores, boxes, classes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "scores[2] = 10.7506\n",
      "boxes[2] = [ 8.42653275  3.27136683 -0.5313437  -4.94137383]\n",
      "classes[2] = 7\n",
      "scores.shape = (?,)\n",
      "boxes.shape = (?, 4)\n",
      "classes.shape = (?,)\n"
     ]
    }
   ],
   "source": [
    "with tf.Session() as test_a:\n",
    "    box_confidence = tf.random_normal([19, 19, 5, 1], mean=1, stddev=4, seed = 1)\n",
    "    boxes = tf.random_normal([19, 19, 5, 4], mean=1, stddev=4, seed = 1)\n",
    "    box_class_probs = tf.random_normal([19, 19, 5, 80], mean=1, stddev=4, seed = 1)\n",
    "    #scores = yolo_filter_boxes(box_confidence, boxes, box_class_probs, threshold = 0.5)\n",
    "    scores, boxes,classes = yolo_filter_boxes(box_confidence, boxes, box_class_probs, threshold = 0.5) \n",
    "    print(\"scores[2] = \" + str(scores[2].eval()))\n",
    "    print(\"boxes[2] = \" + str(boxes[2].eval()))\n",
    "    print(\"classes[2] = \" + str(classes[2].eval()))\n",
    "    print(\"scores.shape = \" + str(scores.shape))\n",
    "    print(\"boxes.shape = \" + str(boxes.shape))\n",
    "    print(\"classes.shape = \" + str(classes.shape))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Expected Output**:\n",
    "\n",
    "<table>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **scores[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           10.7506\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **boxes[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           [ 8.42653275  3.27136683 -0.5313437  -4.94137383]\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "    <tr>\n",
    "        <td>\n",
    "            **classes[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           7\n",
    "        </td>\n",
    "    </tr>\n",
    "        <tr>\n",
    "        <td>\n",
    "            **scores.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (?,)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **boxes.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (?, 4)\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "    <tr>\n",
    "        <td>\n",
    "            **classes.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (?,)\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.3 - Non-max suppression ###\n",
    "\n",
    "Even after filtering by thresholding over the classes scores, you still end up a lot of overlapping boxes. A second filter for selecting the right boxes is called non-maximum suppression (NMS). "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "<img src=\"nb_images/non-max-suppression.png\" style=\"width:500px;height:400;\">\n",
    "<caption><center> <u> **Figure 7** </u>: In this example, the model has predicted 3 cars, but it's actually 3 predictions of the same car. Running non-max suppression (NMS) will select only the most accurate (highest probabiliy) one of the 3 boxes. <br> </center></caption>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Non-max suppression uses the very important function called **\"Intersection over Union\"**, or IoU.\n",
    "<img src=\"nb_images/iou.png\" style=\"width:500px;height:400;\">\n",
    "<caption><center> <u> **Figure 8** </u>: Definition of \"Intersection over Union\". <br> </center></caption>\n",
    "\n",
    "**Exercise**: Implement iou(). Some hints:\n",
    "- In this exercise only, we define a box using its two corners (upper left and lower right): `(x1, y1, x2, y2)` rather than the midpoint and height/width.\n",
    "- To calculate the area of a rectangle you need to multiply its height `(y2 - y1)` by its width `(x2 - x1)`.\n",
    "- You'll also need to find the coordinates `(xi1, yi1, xi2, yi2)` of the intersection of two boxes. Remember that:\n",
    "    - xi1 = maximum of the x1 coordinates of the two boxes\n",
    "    - yi1 = maximum of the y1 coordinates of the two boxes\n",
    "    - xi2 = minimum of the x2 coordinates of the two boxes\n",
    "    - yi2 = minimum of the y2 coordinates of the two boxes\n",
    "- In order to compute the intersection area, you need to make sure the height and width of the intersection are positive, otherwise the intersection area should be zero. Use `max(height, 0)` and `max(width, 0)`.\n",
    "\n",
    "In this code, we use the convention that (0,0) is the top-left corner of an image, (1,0) is the upper-right corner, and (1,1) the lower-right corner. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# GRADED FUNCTION: iou\n",
    "\n",
    "def iou(box1, box2):\n",
    "    \"\"\"Implement the intersection over union (IoU) between box1 and box2\n",
    "    \n",
    "    Arguments:\n",
    "    box1 -- first box, list object with coordinates (x1, y1, x2, y2)\n",
    "    box2 -- second box, list object with coordinates (x1, y1, x2, y2)\n",
    "    \"\"\"\n",
    "\n",
    "    # Calculate the (y1, x1, y2, x2) coordinates of the intersection of box1 and box2. Calculate its Area.\n",
    "    ### START CODE HERE ### (≈ 5 lines)\n",
    "    xi1 = max(box1[0], box2[0])\n",
    "    yi1 = max(box1[1], box2[1])\n",
    "    xi2 = min(box1[2], box2[2])\n",
    "    yi2 = min(box1[3], box2[3])\n",
    "    inter_area = (yi2 - yi1) * (xi2 - xi1)\n",
    "    ### END CODE HERE ###    \n",
    "\n",
    "    # Calculate the Union area by using Formula: Union(A,B) = A + B - Inter(A,B)\n",
    "    ### START CODE HERE ### (≈ 3 lines)\n",
    "    box1_area = (box1[3] - box1[1]) * (box1[2] - box1[0])\n",
    "    box2_area = (box2[3] - box2[1]) * (box2[2] - box2[0])\n",
    "    union_area = box1_area + box2_area - inter_area\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    # compute the IoU\n",
    "    ### START CODE HERE ### (≈ 1 line)\n",
    "    iou = inter_area / union_area\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    return iou"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "iou = 0.14285714285714285\n"
     ]
    }
   ],
   "source": [
    "box1 = (2, 1, 4, 3)\n",
    "box2 = (1, 2, 3, 4) \n",
    "print(\"iou = \" + str(iou(box1, box2)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Expected Output**:\n",
    "\n",
    "<table>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **iou = **\n",
    "        </td>\n",
    "        <td>\n",
    "           0.14285714285714285\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You are now ready to implement non-max suppression. The key steps are: \n",
    "1. Select the box that has the highest score.\n",
    "2. Compute its overlap with all other boxes, and remove boxes that overlap it more than `iou_threshold`.\n",
    "3. Go back to step 1 and iterate until there's no more boxes with a lower score than the current selected box.\n",
    "\n",
    "This will remove all boxes that have a large overlap with the selected boxes. Only the \"best\" boxes remain.\n",
    "\n",
    "**Exercise**: Implement yolo_non_max_suppression() using TensorFlow. TensorFlow has two built-in functions that are used to implement non-max suppression (so you don't actually need to use your `iou()` implementation):\n",
    "- [tf.image.non_max_suppression()](https://www.tensorflow.org/api_docs/python/tf/image/non_max_suppression)\n",
    "- [K.gather()](https://www.tensorflow.org/api_docs/python/tf/gather)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# GRADED FUNCTION: yolo_non_max_suppression\n",
    "\n",
    "def yolo_non_max_suppression(scores, boxes, classes, max_boxes = 10, iou_threshold = 0.5):\n",
    "    \"\"\"\n",
    "    Applies Non-max suppression (NMS) to set of boxes\n",
    "    \n",
    "    Arguments:\n",
    "    scores -- tensor of shape (None,), output of yolo_filter_boxes()\n",
    "    boxes -- tensor of shape (None, 4), output of yolo_filter_boxes() that have been scaled to the image size (see later)\n",
    "    classes -- tensor of shape (None,), output of yolo_filter_boxes()\n",
    "    max_boxes -- integer, maximum number of predicted boxes you'd like\n",
    "    iou_threshold -- real value, \"intersection over union\" threshold used for NMS filtering\n",
    "    \n",
    "    Returns:\n",
    "    scores -- tensor of shape (, None), predicted score for each box\n",
    "    boxes -- tensor of shape (4, None), predicted box coordinates\n",
    "    classes -- tensor of shape (, None), predicted class for each box\n",
    "    \n",
    "    Note: The \"None\" dimension of the output tensors has obviously to be less than max_boxes. Note also that this\n",
    "    function will transpose the shapes of scores, boxes, classes. This is made for convenience.\n",
    "    \"\"\"\n",
    "    \n",
    "    max_boxes_tensor = K.variable(max_boxes, dtype='int32')     # tensor to be used in tf.image.non_max_suppression()\n",
    "    K.get_session().run(tf.variables_initializer([max_boxes_tensor])) # initialize variable max_boxes_tensor\n",
    "    \n",
    "    # Use tf.image.non_max_suppression() to get the list of indices corresponding to boxes you keep\n",
    "    ### START CODE HERE ### (≈ 1 line)\n",
    "    nms_indices = tf.image.non_max_suppression(boxes, scores, max_boxes_tensor, iou_threshold)\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    # Use K.gather() to select only nms_indices from scores, boxes and classes\n",
    "    ### START CODE HERE ### (≈ 3 lines)\n",
    "    scores = K.gather(scores, nms_indices)\n",
    "    boxes = K.gather(boxes, nms_indices)\n",
    "    classes = K.gather(classes, nms_indices)\n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    return scores, boxes, classes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "scores[2] = 6.9384\n",
      "boxes[2] = [-5.299932    3.13798141  4.45036697  0.95942086]\n",
      "classes[2] = -2.24527\n",
      "scores.shape = (10,)\n",
      "boxes.shape = (10, 4)\n",
      "classes.shape = (10,)\n"
     ]
    }
   ],
   "source": [
    "with tf.Session() as test_b:\n",
    "    scores = tf.random_normal([54,], mean=1, stddev=4, seed = 1)\n",
    "    boxes = tf.random_normal([54, 4], mean=1, stddev=4, seed = 1)\n",
    "    classes = tf.random_normal([54,], mean=1, stddev=4, seed = 1)\n",
    "    scores, boxes, classes = yolo_non_max_suppression(scores, boxes, classes)\n",
    "    print(\"scores[2] = \" + str(scores[2].eval()))\n",
    "    print(\"boxes[2] = \" + str(boxes[2].eval()))\n",
    "    print(\"classes[2] = \" + str(classes[2].eval()))\n",
    "    print(\"scores.shape = \" + str(scores.eval().shape))\n",
    "    print(\"boxes.shape = \" + str(boxes.eval().shape))\n",
    "    print(\"classes.shape = \" + str(classes.eval().shape))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Expected Output**:\n",
    "\n",
    "<table>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **scores[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           6.9384\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **boxes[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           [-5.299932    3.13798141  4.45036697  0.95942086]\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "    <tr>\n",
    "        <td>\n",
    "            **classes[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           -2.24527\n",
    "        </td>\n",
    "    </tr>\n",
    "        <tr>\n",
    "        <td>\n",
    "            **scores.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (10,)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **boxes.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (10, 4)\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "    <tr>\n",
    "        <td>\n",
    "            **classes.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (10,)\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.4 Wrapping up the filtering\n",
    "\n",
    "It's time to implement a function taking the output of the deep CNN (the 19x19x5x85 dimensional encoding) and filtering through all the boxes using the functions you've just implemented. \n",
    "\n",
    "**Exercise**: Implement `yolo_eval()` which takes the output of the YOLO encoding and filters the boxes using score threshold and NMS. There's just one last implementational detail you have to know. There're a few ways of representing boxes, such as via their corners or via their midpoint and height/width. YOLO converts between a few such formats at different times, using the following functions (which we have provided): \n",
    "\n",
    "```python\n",
    "boxes = yolo_boxes_to_corners(box_xy, box_wh) \n",
    "```\n",
    "which converts the yolo box coordinates (x,y,w,h) to box corners' coordinates (x1, y1, x2, y2) to fit the input of `yolo_filter_boxes`\n",
    "```python\n",
    "boxes = scale_boxes(boxes, image_shape)\n",
    "```\n",
    "YOLO's network was trained to run on 608x608 images. If you are testing this data on a different size image--for example, the car detection dataset had 720x1280 images--this step rescales the boxes so that they can be plotted on top of the original 720x1280 image.  \n",
    "\n",
    "Don't worry about these two functions; we'll show you where they need to be called.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# GRADED FUNCTION: yolo_eval\n",
    "\n",
    "def yolo_eval(yolo_outputs, image_shape = (720., 1280.), max_boxes=10, score_threshold=.6, iou_threshold=.5):\n",
    "    \"\"\"\n",
    "    Converts the output of YOLO encoding (a lot of boxes) to your predicted boxes along with their scores, box coordinates and classes.\n",
    "    \n",
    "    Arguments:\n",
    "    yolo_outputs -- output of the encoding model (for image_shape of (608, 608, 3)), contains 4 tensors:\n",
    "                    box_confidence: tensor of shape (None, 19, 19, 5, 1)\n",
    "                    box_xy: tensor of shape (None, 19, 19, 5, 2)\n",
    "                    box_wh: tensor of shape (None, 19, 19, 5, 2)\n",
    "                    box_class_probs: tensor of shape (None, 19, 19, 5, 80)\n",
    "    image_shape -- tensor of shape (2,) containing the input shape, in this notebook we use (608., 608.) (has to be float32 dtype)\n",
    "    max_boxes -- integer, maximum number of predicted boxes you'd like\n",
    "    score_threshold -- real value, if [ highest class probability score < threshold], then get rid of the corresponding box\n",
    "    iou_threshold -- real value, \"intersection over union\" threshold used for NMS filtering\n",
    "    \n",
    "    Returns:\n",
    "    scores -- tensor of shape (None, ), predicted score for each box\n",
    "    boxes -- tensor of shape (None, 4), predicted box coordinates\n",
    "    classes -- tensor of shape (None,), predicted class for each box\n",
    "    \"\"\"\n",
    "    \n",
    "    ### START CODE HERE ### \n",
    "    \n",
    "    # Retrieve outputs of the YOLO model (≈1 line)\n",
    "    box_confidence, box_xy, box_wh, box_class_probs = yolo_outputs[0],  yolo_outputs[1], yolo_outputs[2], yolo_outputs[3]\n",
    "\n",
    "    # Convert boxes to be ready for filtering functions \n",
    "    boxes = yolo_boxes_to_corners(box_xy, box_wh)\n",
    "\n",
    "    # Use one of the functions you've implemented to perform Score-filtering with a threshold of score_threshold (≈1 line)\n",
    "    scores, boxes, classes = yolo_filter_boxes(box_confidence, boxes, box_class_probs, score_threshold) \n",
    "    \n",
    "    # Scale boxes back to original image shape.\n",
    "    boxes = scale_boxes(boxes, image_shape)\n",
    "\n",
    "    # Use one of the functions you've implemented to perform Non-max suppression with a threshold of iou_threshold (≈1 line)\n",
    "    scores, boxes, classes = yolo_non_max_suppression(scores, boxes, classes, max_boxes, iou_threshold)\n",
    "    \n",
    "    ### END CODE HERE ###\n",
    "    \n",
    "    return scores, boxes, classes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "scores[2] = 138.791\n",
      "boxes[2] = [ 1292.32971191  -278.52166748  3876.98925781  -835.56494141]\n",
      "classes[2] = 54\n",
      "scores.shape = (10,)\n",
      "boxes.shape = (10, 4)\n",
      "classes.shape = (10,)\n"
     ]
    }
   ],
   "source": [
    "with tf.Session() as test_b:\n",
    "    yolo_outputs = (tf.random_normal([19, 19, 5, 1], mean=1, stddev=4, seed = 1),\n",
    "                    tf.random_normal([19, 19, 5, 2], mean=1, stddev=4, seed = 1),\n",
    "                    tf.random_normal([19, 19, 5, 2], mean=1, stddev=4, seed = 1),\n",
    "                    tf.random_normal([19, 19, 5, 80], mean=1, stddev=4, seed = 1))\n",
    "    scores, boxes, classes = yolo_eval(yolo_outputs)\n",
    "    print(\"scores[2] = \" + str(scores[2].eval()))\n",
    "    print(\"boxes[2] = \" + str(boxes[2].eval()))\n",
    "    print(\"classes[2] = \" + str(classes[2].eval()))\n",
    "    print(\"scores.shape = \" + str(scores.eval().shape))\n",
    "    print(\"boxes.shape = \" + str(boxes.eval().shape))\n",
    "    print(\"classes.shape = \" + str(classes.eval().shape))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "**Expected Output**:\n",
    "\n",
    "<table>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **scores[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           138.791\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **boxes[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           [ 1292.32971191  -278.52166748  3876.98925781  -835.56494141]\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "    <tr>\n",
    "        <td>\n",
    "            **classes[2]**\n",
    "        </td>\n",
    "        <td>\n",
    "           54\n",
    "        </td>\n",
    "    </tr>\n",
    "        <tr>\n",
    "        <td>\n",
    "            **scores.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (10,)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **boxes.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (10, 4)\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "    <tr>\n",
    "        <td>\n",
    "            **classes.shape**\n",
    "        </td>\n",
    "        <td>\n",
    "           (10,)\n",
    "        </td>\n",
    "    </tr>\n",
    "\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='blue'>\n",
    "**Summary for YOLO**:\n",
    "- Input image (608, 608, 3)\n",
    "- The input image goes through a CNN, resulting in a (19,19,5,85) dimensional output. \n",
    "- After flattening the last two dimensions, the output is a volume of shape (19, 19, 425):\n",
    "    - Each cell in a 19x19 grid over the input image gives 425 numbers. \n",
    "    - 425 = 5 x 85 because each cell contains predictions for 5 boxes, corresponding to 5 anchor boxes, as seen in lecture. \n",
    "    - 85 = 5 + 80 where 5 is because $(p_c, b_x, b_y, b_h, b_w)$ has 5 numbers, and and 80 is the number of classes we'd like to detect\n",
    "- You then select only few boxes based on:\n",
    "    - Score-thresholding: throw away boxes that have detected a class with a score less than the threshold\n",
    "    - Non-max suppression: Compute the Intersection over Union and avoid selecting overlapping boxes\n",
    "- This gives you YOLO's final output. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 3 - Test YOLO pretrained model on images"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this part, you are going to use a pretrained model and test it on the car detection dataset. As usual, you start by **creating a session to start your graph**. Run the following cell."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sess = K.get_session()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.1 - Defining classes, anchors and image shape."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Recall that we are trying to detect 80 classes, and are using 5 anchor boxes. We have gathered the information about the 80 classes and 5 boxes in two files \"coco_classes.txt\" and \"yolo_anchors.txt\". Let's load these quantities into the model by running the next cell. \n",
    "\n",
    "The car detection dataset has 720x1280 images, which we've pre-processed into 608x608 images. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class_names = read_classes(\"model_data/coco_classes.txt\")\n",
    "anchors = read_anchors(\"model_data/yolo_anchors.txt\")\n",
    "image_shape = (720., 1280.)    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.2 - Loading a pretrained model\n",
    "\n",
    "Training a YOLO model takes a very long time and requires a fairly large dataset of labelled bounding boxes for a large range of target classes. You are going to load an existing pretrained Keras YOLO model stored in \"yolo.h5\". (These weights come from the official YOLO website, and were converted using a function written by Allan Zelener. References are at the end of this notebook. Technically, these are the parameters from the \"YOLOv2\" model, but we will more simply refer to it as \"YOLO\" in this notebook.) Run the cell below to load the model from this file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.6/site-packages/keras/models.py:251: UserWarning: No training configuration found in save file: the model was *not* compiled. Compile it manually.\n",
      "  warnings.warn('No training configuration found in save file: '\n"
     ]
    }
   ],
   "source": [
    "yolo_model = load_model(\"model_data/yolo.h5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This loads the weights of a trained YOLO model. Here's a summary of the layers your model contains."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "____________________________________________________________________________________________________\n",
      "Layer (type)                     Output Shape          Param #     Connected to                     \n",
      "====================================================================================================\n",
      "input_1 (InputLayer)             (None, 608, 608, 3)   0                                            \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_1 (Conv2D)                (None, 608, 608, 32)  864         input_1[0][0]                    \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_1 (BatchNorm (None, 608, 608, 32)  128         conv2d_1[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_1 (LeakyReLU)        (None, 608, 608, 32)  0           batch_normalization_1[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "max_pooling2d_1 (MaxPooling2D)   (None, 304, 304, 32)  0           leaky_re_lu_1[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_2 (Conv2D)                (None, 304, 304, 64)  18432       max_pooling2d_1[0][0]            \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_2 (BatchNorm (None, 304, 304, 64)  256         conv2d_2[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_2 (LeakyReLU)        (None, 304, 304, 64)  0           batch_normalization_2[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "max_pooling2d_2 (MaxPooling2D)   (None, 152, 152, 64)  0           leaky_re_lu_2[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_3 (Conv2D)                (None, 152, 152, 128) 73728       max_pooling2d_2[0][0]            \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_3 (BatchNorm (None, 152, 152, 128) 512         conv2d_3[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_3 (LeakyReLU)        (None, 152, 152, 128) 0           batch_normalization_3[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_4 (Conv2D)                (None, 152, 152, 64)  8192        leaky_re_lu_3[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_4 (BatchNorm (None, 152, 152, 64)  256         conv2d_4[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_4 (LeakyReLU)        (None, 152, 152, 64)  0           batch_normalization_4[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_5 (Conv2D)                (None, 152, 152, 128) 73728       leaky_re_lu_4[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_5 (BatchNorm (None, 152, 152, 128) 512         conv2d_5[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_5 (LeakyReLU)        (None, 152, 152, 128) 0           batch_normalization_5[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "max_pooling2d_3 (MaxPooling2D)   (None, 76, 76, 128)   0           leaky_re_lu_5[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_6 (Conv2D)                (None, 76, 76, 256)   294912      max_pooling2d_3[0][0]            \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_6 (BatchNorm (None, 76, 76, 256)   1024        conv2d_6[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_6 (LeakyReLU)        (None, 76, 76, 256)   0           batch_normalization_6[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_7 (Conv2D)                (None, 76, 76, 128)   32768       leaky_re_lu_6[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_7 (BatchNorm (None, 76, 76, 128)   512         conv2d_7[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_7 (LeakyReLU)        (None, 76, 76, 128)   0           batch_normalization_7[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_8 (Conv2D)                (None, 76, 76, 256)   294912      leaky_re_lu_7[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_8 (BatchNorm (None, 76, 76, 256)   1024        conv2d_8[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_8 (LeakyReLU)        (None, 76, 76, 256)   0           batch_normalization_8[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "max_pooling2d_4 (MaxPooling2D)   (None, 38, 38, 256)   0           leaky_re_lu_8[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_9 (Conv2D)                (None, 38, 38, 512)   1179648     max_pooling2d_4[0][0]            \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_9 (BatchNorm (None, 38, 38, 512)   2048        conv2d_9[0][0]                   \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_9 (LeakyReLU)        (None, 38, 38, 512)   0           batch_normalization_9[0][0]      \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_10 (Conv2D)               (None, 38, 38, 256)   131072      leaky_re_lu_9[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_10 (BatchNor (None, 38, 38, 256)   1024        conv2d_10[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_10 (LeakyReLU)       (None, 38, 38, 256)   0           batch_normalization_10[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_11 (Conv2D)               (None, 38, 38, 512)   1179648     leaky_re_lu_10[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_11 (BatchNor (None, 38, 38, 512)   2048        conv2d_11[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_11 (LeakyReLU)       (None, 38, 38, 512)   0           batch_normalization_11[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_12 (Conv2D)               (None, 38, 38, 256)   131072      leaky_re_lu_11[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_12 (BatchNor (None, 38, 38, 256)   1024        conv2d_12[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_12 (LeakyReLU)       (None, 38, 38, 256)   0           batch_normalization_12[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_13 (Conv2D)               (None, 38, 38, 512)   1179648     leaky_re_lu_12[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_13 (BatchNor (None, 38, 38, 512)   2048        conv2d_13[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_13 (LeakyReLU)       (None, 38, 38, 512)   0           batch_normalization_13[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "max_pooling2d_5 (MaxPooling2D)   (None, 19, 19, 512)   0           leaky_re_lu_13[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_14 (Conv2D)               (None, 19, 19, 1024)  4718592     max_pooling2d_5[0][0]            \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_14 (BatchNor (None, 19, 19, 1024)  4096        conv2d_14[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_14 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_14[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_15 (Conv2D)               (None, 19, 19, 512)   524288      leaky_re_lu_14[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_15 (BatchNor (None, 19, 19, 512)   2048        conv2d_15[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_15 (LeakyReLU)       (None, 19, 19, 512)   0           batch_normalization_15[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_16 (Conv2D)               (None, 19, 19, 1024)  4718592     leaky_re_lu_15[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_16 (BatchNor (None, 19, 19, 1024)  4096        conv2d_16[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_16 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_16[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_17 (Conv2D)               (None, 19, 19, 512)   524288      leaky_re_lu_16[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_17 (BatchNor (None, 19, 19, 512)   2048        conv2d_17[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_17 (LeakyReLU)       (None, 19, 19, 512)   0           batch_normalization_17[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_18 (Conv2D)               (None, 19, 19, 1024)  4718592     leaky_re_lu_17[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_18 (BatchNor (None, 19, 19, 1024)  4096        conv2d_18[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_18 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_18[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_19 (Conv2D)               (None, 19, 19, 1024)  9437184     leaky_re_lu_18[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_19 (BatchNor (None, 19, 19, 1024)  4096        conv2d_19[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_21 (Conv2D)               (None, 38, 38, 64)    32768       leaky_re_lu_13[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_19 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_19[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_21 (BatchNor (None, 38, 38, 64)    256         conv2d_21[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_20 (Conv2D)               (None, 19, 19, 1024)  9437184     leaky_re_lu_19[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_21 (LeakyReLU)       (None, 38, 38, 64)    0           batch_normalization_21[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_20 (BatchNor (None, 19, 19, 1024)  4096        conv2d_20[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "space_to_depth_x2 (Lambda)       (None, 19, 19, 256)   0           leaky_re_lu_21[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_20 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_20[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "concatenate_1 (Concatenate)      (None, 19, 19, 1280)  0           space_to_depth_x2[0][0]          \n",
      "                                                                   leaky_re_lu_20[0][0]             \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_22 (Conv2D)               (None, 19, 19, 1024)  11796480    concatenate_1[0][0]              \n",
      "____________________________________________________________________________________________________\n",
      "batch_normalization_22 (BatchNor (None, 19, 19, 1024)  4096        conv2d_22[0][0]                  \n",
      "____________________________________________________________________________________________________\n",
      "leaky_re_lu_22 (LeakyReLU)       (None, 19, 19, 1024)  0           batch_normalization_22[0][0]     \n",
      "____________________________________________________________________________________________________\n",
      "conv2d_23 (Conv2D)               (None, 19, 19, 425)   435625      leaky_re_lu_22[0][0]             \n",
      "====================================================================================================\n",
      "Total params: 50,983,561\n",
      "Trainable params: 50,962,889\n",
      "Non-trainable params: 20,672\n",
      "____________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "yolo_model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Note**: On some computers, you may see a warning message from Keras. Don't worry about it if you do--it is fine.\n",
    "\n",
    "**Reminder**: this model converts a preprocessed batch of input images (shape: (m, 608, 608, 3)) into a tensor of shape (m, 19, 19, 5, 85) as explained in Figure (2)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.3 - Convert output of the model to usable bounding box tensors\n",
    "\n",
    "The output of `yolo_model` is a (m, 19, 19, 5, 85) tensor that needs to pass through non-trivial processing and conversion. The following cell does that for you."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "yolo_outputs = yolo_head(yolo_model.output, anchors, len(class_names))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You added `yolo_outputs` to your graph. This set of 4 tensors is ready to be used as input by your `yolo_eval` function."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.4 - Filtering boxes\n",
    "\n",
    "`yolo_outputs` gave you all the predicted boxes of `yolo_model` in the correct format. You're now ready to perform filtering and select only the best boxes. Lets now call `yolo_eval`, which you had previously implemented, to do this. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "scores, boxes, classes = yolo_eval(yolo_outputs, image_shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.5 - Run the graph on an image\n",
    "\n",
    "Let the fun begin. You have created a (`sess`) graph that can be summarized as follows:\n",
    "\n",
    "1. <font color='purple'> yolo_model.input </font> is given to `yolo_model`. The model is used to compute the output <font color='purple'> yolo_model.output </font>\n",
    "2. <font color='purple'> yolo_model.output </font> is processed by `yolo_head`. It gives you <font color='purple'> yolo_outputs </font>\n",
    "3. <font color='purple'> yolo_outputs </font> goes through a filtering function, `yolo_eval`. It outputs your predictions: <font color='purple'> scores, boxes, classes </font>\n",
    "\n",
    "**Exercise**: Implement predict() which runs the graph to test YOLO on an image.\n",
    "You will need to run a TensorFlow session, to have it compute `scores, boxes, classes`.\n",
    "\n",
    "The code below also uses the following function:\n",
    "```python\n",
    "image, image_data = preprocess_image(\"images/\" + image_file, model_image_size = (608, 608))\n",
    "```\n",
    "which outputs:\n",
    "- image: a python (PIL) representation of your image used for drawing boxes. You won't need to use it.\n",
    "- image_data: a numpy-array representing the image. This will be the input to the CNN.\n",
    "\n",
    "**Important note**: when a model uses BatchNorm (as is the case in YOLO), you will need to pass an additional placeholder in the feed_dict {K.learning_phase(): 0}."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def predict(sess, image_file):\n",
    "    \"\"\"\n",
    "    Runs the graph stored in \"sess\" to predict boxes for \"image_file\". Prints and plots the predictions.\n",
    "    \n",
    "    Arguments:\n",
    "    sess -- your tensorflow/Keras session containing the YOLO graph\n",
    "    image_file -- name of an image stored in the \"images\" folder.\n",
    "    \n",
    "    Returns:\n",
    "    out_scores -- tensor of shape (None, ), scores of the predicted boxes\n",
    "    out_boxes -- tensor of shape (None, 4), coordinates of the predicted boxes\n",
    "    out_classes -- tensor of shape (None, ), class index of the predicted boxes\n",
    "    \n",
    "    Note: \"None\" actually represents the number of predicted boxes, it varies between 0 and max_boxes. \n",
    "    \"\"\"\n",
    "\n",
    "    # Preprocess your image\n",
    "    image, image_data = preprocess_image(\"images/\" + image_file, model_image_size = (608, 608))\n",
    "\n",
    "    # Run the session with the correct tensors and choose the correct placeholders in the feed_dict.\n",
    "    # You'll need to use feed_dict={yolo_model.input: ... , K.learning_phase(): 0})\n",
    "    ### START CODE HERE ### (≈ 1 line)\n",
    "    out_scores, out_boxes, out_classes = sess.run([scores, boxes, classes], feed_dict={yolo_model.input:image_data, K.learning_phase():0})\n",
    "    ### END CODE HERE ###\n",
    "\n",
    "    # Print predictions info\n",
    "    print('Found {} boxes for {}'.format(len(out_boxes), image_file))\n",
    "    # Generate colors for drawing bounding boxes.\n",
    "    colors = generate_colors(class_names)\n",
    "    # Draw bounding boxes on the image file\n",
    "    draw_boxes(image, out_scores, out_boxes, out_classes, class_names, colors)\n",
    "    # Save the predicted bounding box on the image\n",
    "    image.save(os.path.join(\"out\", image_file), quality=90)\n",
    "    # Display the results in the notebook\n",
    "    output_image = scipy.misc.imread(os.path.join(\"out\", image_file))\n",
    "    imshow(output_image)\n",
    "    \n",
    "    return out_scores, out_boxes, out_classes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Run the following cell on the \"test.jpg\" image to verify that your function is correct."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 5 boxes for F100528GY08-e1389827273894-1024x640.jpg\n",
      "bus 0.62 (764, 264) (1009, 528)\n",
      "car 0.65 (158, 412) (344, 547)\n",
      "car 0.69 (609, 435) (900, 640)\n",
      "car 0.78 (15, 439) (278, 601)\n",
      "car 0.79 (319, 420) (472, 528)\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXwAAAD0CAYAAACYc53LAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAnr0zVWyJOtGAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f171ee1c470>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "out_scores, out_boxes, out_classes = predict(sess, \"F100528GY08-e1389827273894-1024x640.jpg\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Expected Output**:\n",
    "\n",
    "<table>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **Found 7 boxes for test.jpg**\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **car**\n",
    "        </td>\n",
    "        <td>\n",
    "           0.60 (925, 285) (1045, 374)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **car**\n",
    "        </td>\n",
    "        <td>\n",
    "           0.66 (706, 279) (786, 350)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **bus**\n",
    "        </td>\n",
    "        <td>\n",
    "           0.67 (5, 266) (220, 407)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **car**\n",
    "        </td>\n",
    "        <td>\n",
    "           0.70 (947, 324) (1280, 705)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **car**\n",
    "        </td>\n",
    "        <td>\n",
    "           0.74 (159, 303) (346, 440)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **car**\n",
    "        </td>\n",
    "        <td>\n",
    "           0.80 (761, 282) (942, 412)\n",
    "        </td>\n",
    "    </tr>\n",
    "    <tr>\n",
    "        <td>\n",
    "            **car**\n",
    "        </td>\n",
    "        <td>\n",
    "           0.89 (367, 300) (745, 648)\n",
    "        </td>\n",
    "    </tr>\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The model you've just run is actually able to detect 80 different classes listed in \"coco_classes.txt\". To test the model on your own images:\n",
    "    1. Click on \"File\" in the upper bar of this notebook, then click \"Open\" to go on your Coursera Hub.\n",
    "    2. Add your image to this Jupyter Notebook's directory, in the \"images\" folder\n",
    "    3. Write your image's name in the cell above code\n",
    "    4. Run the code and see the output of the algorithm!\n",
    "\n",
    "If you were to run your session in a for loop over all your images. Here's what you would get:\n",
    "\n",
    "<center>\n",
    "<video width=\"400\" height=\"200\" src=\"nb_images/pred_video_compressed2.mp4\" type=\"video/mp4\" controls>\n",
    "</video>\n",
    "</center>\n",
    "\n",
    "<caption><center> Predictions of the YOLO model on pictures taken from a camera while driving around the Silicon Valley <br> Thanks [drive.ai](https://www.drive.ai/) for providing this dataset! </center></caption>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "<font color='blue'>\n",
    "**What you should remember**:\n",
    "- YOLO is a state-of-the-art object detection model that is fast and accurate\n",
    "- It runs an input image through a CNN which outputs a 19x19x5x85 dimensional volume. \n",
    "- The encoding can be seen as a grid where each of the 19x19 cells contains information about 5 boxes.\n",
    "- You filter through all the boxes using non-max suppression. Specifically: \n",
    "    - Score thresholding on the probability of detecting a class to keep only accurate (high probability) boxes\n",
    "    - Intersection over Union (IoU) thresholding to eliminate overlapping boxes\n",
    "- Because training a YOLO model from randomly initialized weights is non-trivial and requires a large dataset as well as lot of computation, we used previously trained model parameters in this exercise. If you wish, you can also try fine-tuning the YOLO model with your own dataset, though this would be a fairly non-trivial exercise. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**References**: The ideas presented in this notebook came primarily from the two YOLO papers. The implementation here also took significant inspiration and used many components from Allan Zelener's github repository. The pretrained weights used in this exercise came from the official YOLO website. \n",
    "- Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi - [You Only Look Once: Unified, Real-Time Object Detection](https://arxiv.org/abs/1506.02640) (2015)\n",
    "- Joseph Redmon, Ali Farhadi - [YOLO9000: Better, Faster, Stronger](https://arxiv.org/abs/1612.08242) (2016)\n",
    "- Allan Zelener - [YAD2K: Yet Another Darknet 2 Keras](https://github.com/allanzelener/YAD2K)\n",
    "- The official YOLO website (https://pjreddie.com/darknet/yolo/) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Car detection dataset**:\n",
    "<a rel=\"license\" href=\"http://creativecommons.org/licenses/by/4.0/\"><img alt=\"Creative Commons License\" style=\"border-width:0\" src=\"https://i.creativecommons.org/l/by/4.0/88x31.png\" /></a><br /><span xmlns:dct=\"http://purl.org/dc/terms/\" property=\"dct:title\">The Drive.ai Sample Dataset</span> (provided by drive.ai) is licensed under a <a rel=\"license\" href=\"http://creativecommons.org/licenses/by/4.0/\">Creative Commons Attribution 4.0 International License</a>. We are especially grateful to Brody Huval, Chih Hu and Rahul Patel for collecting and providing this dataset. "
   ]
  }
 ],
 "metadata": {
  "coursera": {
   "course_slug": "convolutional-neural-networks",
   "graded_item_id": "OMdut",
   "launcher_item_id": "bbBOL"
  },
  "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}