Implement YOLO model from scratch as described in the two YOLO papers: Redmon et al., 2016 and Redmon and Farhadi, 2016.
Problem Statement
You are working on a self-driving car. Go you! 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 as you drive around.
You've gathered all these images into a folder and labelled them by drawing bounding boxes around every car you found. Here's an example of what your bounding boxes look like:
If there are 80 classes you want the object detector 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 used the latter representation; in this notebook, you'll use both representations, depending on which is more convenient for a particular step.
In this project, you'll discover how YOLO ("You Only Look Once") performs object detection, and then apply it to car detection. Because the YOLO model is very computationally expensive to train, the pre-trained weights are already loaded for you to use.
YOLO
"You Only Look Once" (YOLO) is a popular algorithm 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.
Model Details
Inputs and outputs
The input is a batch of images, and each image has the shape (608, 608, 3)
The output is a list of bounding boxes along with the recognized classes. Each bounding box is represented by 6 numbers (pc,bx,by,bh,bw,c) as explained above. If you expand c into an 80-dimensional vector, each bounding box is then represented by 85 numbers.
Anchor Boxes
Anchor boxes are chosen by exploring the training data to choose reasonable height/width ratios that represent the different classes. For this assignment, 5 anchor boxes were chosen for you (to cover the 80 classes), and stored in the file './model_data/yolo_anchors.txt'
The dimension of the encoding tensor of the second to last dimension based on the anchor boxes is (m,nH,nW,anchors,classes).
The YOLO architecture is: IMAGE (m, 608, 608, 3) -> DEEP CNN -> ENCODING (m, 19, 19, 5, 85).
Let's look in greater detail at what this encoding represents.
If the center/midpoint of an object falls into a grid cell, that grid cell is responsible for detecting that object.
Since you're 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.
For simplicity, you'll flatten the last two dimensions of the shape (19, 19, 5, 85) encoding, so the output of the Deep CNN is (19, 19, 425).
Class score
Now, for each box (of each cell) you'll compute the following element-wise product and extract a probability that the box contains a certain class.
The class score is scorec,i=pc×ci: the probability that there is an object pc times the probability that the object is a certain class ci.
Example of figure 4
In figure 4, let's say for box 1 (cell 1), the probability that an object exists is p1=0.60. So there's a 60% chance that an object exists in box 1 (cell 1).
The probability that the object is the class "category 3 (a car)" is c3=0.73.
The score for box 1 and for category "3" is score1,3=0.60×0.73=0.44.
Let's say you calculate the score for all 80 classes in box 1, and find that the score for the car class (class 3) is the maximum. So you'll assign the score 0.44 and class "3" to this box "1".
Visualizing classes
Here's one way to visualize what YOLO is predicting on an image:
For each of the 19x19 grid cells, find the maximum of the probability scores (taking a max across the 80 classes, one maximum for each of the 5 anchor boxes).
Color that grid cell according to what object that grid cell considers the most likely.
Doing this results in this picture:
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.
Visualizing bounding boxes
Another way to visualize YOLO's output is to plot the bounding boxes that it outputs. Doing that results in a visualization like this:
Non-Max suppression
In the figure above, the only boxes plotted are ones for which the model had assigned a high probability, but this is still too many boxes. You'd like to reduce the algorithm's output to a much smaller number of detected objects.
To do so, you'll use non-max suppression. Specifically, you'll carry out these steps:
Get rid of boxes with a low score. Meaning, the box is not very confident about detecting a class, either due to the low probability of any object, or low probability of this particular class.
Select only one box when several boxes overlap with each other and detect the same object.
Filtering with a Threshold on Class Scores
You're going to first apply a filter by thresholding, meaning you'll get rid of any box for which the class "score" is less than a chosen threshold.
The model gives you a total of 19x19x5x85 numbers, with each box described by 85 numbers. It's convenient to rearrange the (19,19,5,85) (or (19,19,425)) dimensional tensor into the following variables:
box_confidence: tensor of shape (19,19,5,1)(19,19,5,1) containing pc(confidence probability that there's some object) for each of the 5 boxes predicted in each of the 19x19 cells.
boxes: tensor of shape (19,19,5,4)(19,19,5,4) containing the midpoint and dimensions (bx,by,bh,bw)for each of the 5 boxes in each cell.
box_class_probs: tensor of shape (19,19,5,80)(19,19,5,80) containing the "class probabilities" (c1,c2,...c80) for each of the 80 classes for each of the 5 boxes per cell.
Non-max Suppression
Even after filtering by thresholding over the class scores, you still end up with a lot of overlapping boxes. A second filter for selecting the right boxes is called non-maximum suppression (NMS).
Non-max suppression uses the very important function called "Intersection over Union", or IoU.
YOLO Non-max Suppression
You are now ready to implement non-max suppression. The key steps are:
Select the box that has the highest score.
Compute the overlap of this box with all other boxes, and remove boxes that overlap significantly (iou >= iou_threshold).
Go back to step 1 and iterate until there are no more boxes with a lower score than the currently selected box.
This will remove all boxes that have a large overlap with the selected boxes. Only the "best" boxes remain.
Test YOLO Pre-trained Model on Images
Defining Classes, Anchors and Image Shape
You're trying to detect 80 classes, and are using 5 anchor boxes. The information on the 80 classes and 5 boxes is gathered in two files: "coco_classes.txt" and "yolo_anchors.txt". You'll read class names and anchors from text files. The car detection dataset has 720x1280 images, which are pre-processed into 608x608 images.
Loading a Pre-trained Model
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 pre-trained 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 are simply referred to as "YOLO" in this notebook.
This loads the weights of a trained YOLO model. Here's a summary of the layers your model contains:
Note: On some computers, you may see a warning message from Keras. Don't worry about it if you do -- this is fine!
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).
Convert Output of the Model to Usable Bounding Box Tensors
The output of yolo_model is a (m, 19, 19, 5, 85) tensor that needs to pass through non-trivial processing and conversion. You will need to call yolo_head to format the encoding of the model you got from yolo_model into something decipherable:
yolo_model_outputs = yolo_model(image_data) yolo_outputs = yolo_head(yolo_model_outputs, anchors, len(class_names)) The variable yolo_outputs will be defined as a set of 4 tensors that you can then use as input by your yolo_eval function. If you are curious about how yolo_head is implemented, you can find the function definition in the file keras_yolo.py. The file is also located in your workspace in this path: yad2k/models/keras_yolo.py.
Filtering Boxes
yolo_outputs gave you all the predicted boxes of yolo_model in the correct format. To perform filtering and select only the best boxes, you will call yolo_eval, which you had previously implemented, to do so:
Let the fun begin! You will create a graph that can be summarized as follows:
yolo_model.input is given to yolo_model. The model is used to compute the output yolo_model.outputyolo_model.output is processed by yolo_head. It gives you yolo_outputsyolo_outputs goes through a filtering function, yolo_eval. It outputs your predictions: out_scores, out_boxes, out_classes.
Now, we have implemented for you the predict(image_file) function, which runs the graph to test YOLO on an image to compute out_scores, out_boxes, out_classes.
which opens the image file and scales, reshapes and normalizes the image. It returns the outputs:
image: a python (PIL) representation of your image used for drawing boxes. You won't need to use it.
image_data: a numpy-array representing the image. This will be the input to the CNN.
Output
Found 10 boxes for images/test.jpg
car 0.89 (367, 300) (745, 648)
car 0.80 (761, 282) (942, 412)
car 0.74 (159, 303) (346, 440)
car 0.70 (947, 324) (1280, 705)
bus 0.67 (5, 266) (220, 407)
car 0.66 (706, 279) (786, 350)
car 0.60 (925, 285) (1045, 374)
car 0.44 (336, 296) (378, 335)
car 0.37 (965, 273) (1022, 292)
traffic light 0.36 (681, 195) (692, 214)
Code
import argparseimport osimport matplotlib.pyplot as pltfrom matplotlib.pyplot import imshowimport scipy.ioimport scipy.miscimport numpy as npimport pandas as pdimport PILfrom PIL import ImageFont, ImageDraw, Imageimport tensorflow as tffrom tensorflow.python.framework.ops import EagerTensorfrom tensorflow.keras.models import load_modelfrom yad2k.models.keras_yolo import yolo_headfrom yad2k.utils.utils import draw_boxes, get_colors_for_classes, scale_boxes, read_classes, read_anchors, preprocess_image
%matplotlib inlinedefyolo_filter_boxes(boxes,box_confidence,box_class_probs,threshold=.6):"""Filters YOLO boxes by thresholding on object and class confidence. Arguments: boxes -- tensor of shape (19, 19, 5, 4) box_confidence -- tensor of shape (19, 19, 5, 1) box_class_probs -- tensor of shape (19, 19, 5, 80) threshold -- real value, if [ highest class probability score < threshold], then get rid of the corresponding box Returns: scores -- tensor of shape (None,), containing the class probability score for selected boxes boxes -- tensor of shape (None, 4), containing (b_x, b_y, b_h, b_w) coordinates of selected boxes classes -- tensor of shape (None,), containing the index of the class detected by the selected boxes Note: "None" is here because you don't know the exact number of selected boxes, as it depends on the threshold. For example, the actual output size of scores would be (10,) if there are 10 boxes. """### START CODE HERE# Step 1: Compute box scores##(≈ 1 line) box_scores = box_confidence * box_class_probs# Step 2: Find the box_classes using the max box_scores, keep track of the corresponding score##(≈ 2 lines)# IMPORTANT: set axis to -1 box_classes = tf.math.argmax(box_scores, axis=-1) box_class_scores = tf.math.reduce_max(box_scores, axis=-1)# Step 3: Create a filtering mask based on "box_class_scores" by using "threshold". The mask should have the# same dimension as box_class_scores, and be True for the boxes you want to keep (with probability >= threshold)## (≈ 1 line) filtering_mask = box_class_scores > threshold# Step 4: Apply the mask to box_class_scores, boxes and box_classes## (≈ 3 lines) scores = tf.boolean_mask(box_class_scores, filtering_mask) boxes = tf.boolean_mask(boxes, filtering_mask) classes = tf.boolean_mask(box_classes, filtering_mask)### END CODE HEREreturn scores, boxes, classesdefiou(box1,box2):"""Implement the intersection over union (IoU) between box1 and box2 Arguments: box1 -- first box, list object with coordinates (box1_x1, box1_y1, box1_x2, box_1_y2) box2 -- second box, list object with coordinates (box2_x1, box2_y1, box2_x2, box2_y2) """ (box1_x1, box1_y1, box1_x2, box1_y2) = box1 (box2_x1, box2_y1, box2_x2, box2_y2) = box2### START CODE HERE# Calculate the (yi1, xi1, yi2, xi2) coordinates of the intersection of box1 and box2. Calculate its Area.##(≈ 7 lines) xi1 =max(box1_x1, box2_x1) yi1 =max(box1_y1, box2_y1) xi2 =min(box1_x2, box2_x2) yi2 =min(box1_y2, box2_y2) inter_width = xi2 - xi1 inter_height = yi2 - yi1 inter_area =max(inter_height, 0)*max(inter_width, 0)# Calculate the Union area by using Formula: Union(A,B) = A + B - Inter(A,B)## (≈ 3 lines) box1_area = (box1_y2 - box1_y1)*(box1_x2 - box1_x1) box2_area = (box2_y2 - box2_y1)*(box2_x2 - box2_x1) union_area = box1_area + box2_area - inter_area# compute the IoU iou = inter_area / union_area### END CODE HEREreturn ioudefyolo_non_max_suppression(scores,boxes,classes,max_boxes=10,iou_threshold=0.5):""" Applies Non-max suppression (NMS) to set of boxes Arguments: scores -- tensor of shape (None,), output of yolo_filter_boxes() boxes -- tensor of shape (None, 4), output of yolo_filter_boxes() that have been scaled to the image size (see later)
classes -- tensor of shape (None,), output of yolo_filter_boxes() max_boxes -- integer, maximum number of predicted boxes you'd like iou_threshold -- real value, "intersection over union" threshold used for NMS filtering Returns: scores -- tensor of shape (None, ), predicted score for each box boxes -- tensor of shape (None, 4), predicted box coordinates classes -- tensor of shape (None, ), predicted class for each box Note: The "None" dimension of the output tensors has obviously to be less than max_boxes. Note also that this function will transpose the shapes of scores, boxes, classes. This is made for convenience. """ max_boxes_tensor = tf.Variable(max_boxes, dtype='int32')# tensor to be used in tf.image.non_max_suppression()### START CODE HERE# Use tf.image.non_max_suppression() to get the list of indices corresponding to boxes you keep##(≈ 1 line) nms_indices = tf.image.non_max_suppression(boxes, scores, max_boxes_tensor, iou_threshold)# Use tf.gather() to select only nms_indices from scores, boxes and classes##(≈ 3 lines) scores = tf.gather(scores, nms_indices) boxes = tf.gather(boxes, nms_indices) classes = tf.gather(classes, nms_indices)### END CODE HEREreturn scores, boxes, classesdefyolo_boxes_to_corners(box_xy,box_wh):"""Convert YOLO box predictions to bounding box corners.""" box_mins = box_xy - (box_wh /2.) box_maxes = box_xy + (box_wh /2.)return tf.keras.backend.concatenate([ box_mins[..., 1:2], # y_min box_mins[..., 0:1], # x_min box_maxes[..., 1:2], # y_max box_maxes[..., 0:1] # x_max ])defyolo_eval(yolo_outputs,image_shape= (720,1280),max_boxes=10,score_threshold=.6,iou_threshold=.5):""" Converts the output of YOLO encoding (a lot of boxes) to your predicted boxes along with their scores, box coordinates and classes.
Arguments: yolo_outputs -- output of the encoding model (for image_shape of (608, 608, 3)), contains 4 tensors: box_xy: tensor of shape (None, 19, 19, 5, 2) box_wh: tensor of shape (None, 19, 19, 5, 2) box_confidence: tensor of shape (None, 19, 19, 5, 1) box_class_probs: tensor of shape (None, 19, 19, 5, 80) image_shape -- tensor of shape (2,) containing the input shape, in this notebook we use (608., 608.) (has to be float32 dtype)
max_boxes -- integer, maximum number of predicted boxes you'd like score_threshold -- real value, if [ highest class probability score < threshold], then get rid of the corresponding box
iou_threshold -- real value, "intersection over union" threshold used for NMS filtering Returns: scores -- tensor of shape (None, ), predicted score for each box boxes -- tensor of shape (None, 4), predicted box coordinates classes -- tensor of shape (None,), predicted class for each box """### START CODE HERE# Retrieve outputs of the YOLO model (≈1 line) box_xy, box_wh, box_confidence, box_class_probs = yolo_outputs# Convert boxes to be ready for filtering functions (convert boxes box_xy and box_wh to corner coordinates) boxes =yolo_boxes_to_corners(box_xy, box_wh) # Use one of the functions you've implemented to perform Score-filtering with a threshold of score_threshold (≈1 line)
scores, boxes, classes =yolo_filter_boxes(boxes,box_confidence, box_class_probs, score_threshold)# Scale boxes back to original image shape. boxes =scale_boxes(boxes, image_shape)# Use one of the functions you've implemented to perform Non-max suppression with # maximum number of boxes set to max_boxes and a threshold of iou_threshold (≈1 line) scores, boxes, classes =yolo_non_max_suppression(scores, boxes, classes, max_boxes, iou_threshold)### END CODE HEREreturn scores, boxes, classesclass_names =read_classes("model_data/coco_classes.txt")anchors =read_anchors("model_data/yolo_anchors.txt")model_image_size = (608,608) # Same as yolo_model input layer sizeyolo_model =load_model("model_data/", compile=False)yolo_model.summary()defpredict(image_file):""" Runs the graph to predict boxes for "image_file". Prints and plots the predictions. Arguments: image_file -- name of an image stored in the "images" folder. Returns: out_scores -- tensor of shape (None, ), scores of the predicted boxes out_boxes -- tensor of shape (None, 4), coordinates of the predicted boxes out_classes -- tensor of shape (None, ), class index of the predicted boxes Note: "None" actually represents the number of predicted boxes, it varies between 0 and max_boxes. """# Preprocess your image image, image_data =preprocess_image("images/"+ image_file, model_image_size = (608, 608)) yolo_model_outputs =yolo_model(image_data) yolo_outputs =yolo_head(yolo_model_outputs, anchors, len(class_names)) out_scores, out_boxes, out_classes =yolo_eval(yolo_outputs, [image.size[1], image.size[0]], 10, 0.3, 0.5)# Print predictions infoprint('Found {} boxes for {}'.format(len(out_boxes), "images/"+ image_file))# Generate colors for drawing bounding boxes. colors =get_colors_for_classes(len(class_names))# Draw bounding boxes on the image file#draw_boxes2(image, out_scores, out_boxes, out_classes, class_names, colors, image_shape)draw_boxes(image, out_boxes, out_classes, class_names, out_scores)# Save the predicted bounding box on the image image.save(os.path.join("out", image_file), quality=100)# Display the results in the notebook output_image = Image.open(os.path.join("out", image_file))imshow(output_image)return out_scores, out_boxes, out_classesout_scores, out_boxes, out_classes =predict("test.jpg")