Autonomous_driving_application_Car_detectio_YOLO.ipynb

{
 "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.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, 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, 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))\n",
    "    #tf.Print(box_confidence, [box_confidence], \"haha\")"
   ]
  },
  {
   "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 = max(xi2-xi1, 0) * max(yi2-yi1, 0)\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[2] - box1[0])*(box1[3] - box1[1])\n",
    "    box2_area = (box2[2] - box2[0])*(box2[3] - box2[1])\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=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\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": 22,
   "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 preditions.\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": 26,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 8 boxes for traffic.jpeg\n",
      "person 0.61 (1005, 598) (286, 176)\n",
      "car 0.61 (87, 437) (228, 176)\n",
      "motorbike 0.62 (1008, 668) (286, 176)\n",
      "person 0.63 (823, 667) (286, 176)\n",
      "car 0.66 (339, 667) (286, 176)\n",
      "car 0.68 (54, 502) (258, 176)\n",
      "car 0.71 (707, 485) (286, 176)\n",
      "car 0.77 (420, 518) (286, 176)\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAADwCAYAAAAO/K+aAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nirkAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f068b043668>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "out_scores, out_boxes, out_classes = predict(sess, \"traffic.jpeg\")"
   ]
  },
  {
   "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
}