DeepLearning.ai作业:(4-3)-- 目标检测(Object detection)
2018-10-13 14:03
381 查看
title: ‘DeepLearning.ai作业:(4-3)-- 目标检测(Object detection)’
id: dl-ai-4-3h
tags:
- dl.ai
- homework
categories: - AI
- Deep Learning
date: 2018-10-11 20:15:58
首发于个人博客:fangzh.top,欢迎来访
本周的作业实现了YOLO算法,并用于自动驾驶的目标检测中。
Model details
输入: (m, 608, 608, 3)
输出: (m, 19, 19, 5, 85)
IMAGE (m, 608, 608, 3) -> DEEP CNN -> ENCODING (m, 19, 19, 5, 85)
也就是有5个Anchor boxes,一共有80个分类。
所以,每个box的scores也就是等于每个类预测的可能性:
Filtering with a threshold on class scores
这个时候开始创建一个函数,得到每一个box中scores最大的那个类,分数,以及位置,去掉其他没用的。
# GRADED FUNCTION: yolo_filter_boxes def yolo_filter_boxes(box_confidence, boxes, box_class_probs, threshold = .6): """Filters YOLO boxes by thresholding on object and class confidence. Arguments: box_confidence -- tensor of shape (19, 19, 5, 1) boxes -- tensor of shape (19, 19, 5, 4) 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. """ # Step 1: Compute box scores ### START CODE HERE ### (≈ 1 line) box_scores = box_confidence * box_class_probs ### END CODE HERE ### # Step 2: Find the box_classes thanks to the max box_scores, keep track of the corresponding score ### START CODE HERE ### (≈ 2 lines) box_classes = K.argmax(box_scores, axis=-1) #得到box的类别 (19,19,5) box_class_scores = K.max(box_scores, axis=-1, keepdims=False) #得到box这个类别的分数(19,19,5) ### END CODE HERE ### # 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) ### START CODE HERE ### (≈ 1 line) filtering_mask = box_class_scores >= threshold ### END CODE HERE ### # Step 4: Apply the mask to scores, boxes and classes ### START CODE HERE ### (≈ 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 HERE ### return scores, boxes, classes
Non-max suppression
找到了这些boxes后,还需要进行筛选过滤掉。先完成一个IOU算法:
# GRADED FUNCTION: iou def iou(box1, box2): """Implement the intersection over union (IoU) between box1 and box2 Arguments: box1 -- first box, list object with coordinates (x1, y1, x2, y2) box2 -- second box, list object with coordinates (x1, y1, x2, y2) """ # Calculate the (y1, x1, y2, x2) coordinates of the intersection of box1 and box2. Calculate its Area. ### START CODE HERE ### (≈ 5 lines) xi1 = np.maximum(box1[0], box2[0]) yi1 = np.maximum(box1[1], box2[1]) xi2 = np.minimum(box1[2], box2[2]) yi2 = np.minimum(box1[3], box2[3]) inter_area = max(xi2 - xi1,0) * max(yi2 - yi1,0) ### END CODE HERE ### # Calculate the Union area by using Formula: Union(A,B) = A + B - Inter(A,B) ### START CODE HERE ### (≈ 3 lines) box1_area = (box1[2] - box1[0]) * (box1[3] - box1[1]) box2_area = (box2[2] - box2[0]) * (box2[3] - box2[1]) union_area = box1_area + box2_area - inter_area ### END CODE HERE ### # compute the IoU ### START CODE HERE ### (≈ 1 line) iou = inter_area / union_area ### END CODE HERE ### return iou
tensorflow已经帮你实现了iou算法了,不用用自己刚才写的了:
思想就是拿掉IOU比较大的那些box
# GRADED FUNCTION: yolo_non_max_suppression def yolo_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 (4, None), 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 = K.variable(max_boxes, dtype='int32') # tensor to be used in tf.image.non_max_suppression() K.get_session().run(tf.variables_initializer([max_boxes_tensor])) # initialize variable max_boxes_tensor # Use tf.image.non_max_suppression() to get the list of indices corresponding to boxes you keep ### START CODE HERE ### (≈ 1 line) nms_indices = tf.image.non_max_suppression(boxes,scores,max_boxes,iou_threshold) ### END CODE HERE ### # Use K.gather() to select only nms_indices from scores, boxes and classes ### START CODE HERE ### (≈ 3 lines) scores = K.gather(scores,nms_indices) boxes = K.gather(boxes,nms_indices) classes = K.gather(classes,nms_indices) ### END CODE HERE ### return scores, boxes, classes
而后结合刚才的函数,先去掉scores低的,然后运算NMS算法
# GRADED FUNCTION: yolo_eval def yolo_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_confidence: tensor of shape (None, 19, 19, 5, 1) box_xy: tensor of shape (None, 19, 19, 5, 2) box_wh: tensor of shape (None, 19, 19, 5, 2) 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_confidence, box_xy, box_wh, box_class_probs = yolo_outputs # Convert boxes to be ready for filtering functions 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(box_confidence, boxes, 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 a threshold of iou_threshold (≈1 line) scores, boxes, classes = yolo_non_max_suppression(scores, boxes, classes, max_boxes, iou_threshold ) ### END CODE HERE ### return scores, boxes, classes
进行预测:
def predict(sess, image_file): """ Runs the graph stored in "sess" to predict boxes for "image_file". Prints and plots the preditions. Arguments: sess -- your tensorflow/Keras session containing the YOLO graph 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)) # Run the session with the correct tensors and choose the correct placeholders in the feed_dict. # You'll need to use feed_dict={yolo_model.input: ... , K.learning_phase(): 0}) ### START CODE HERE ### (≈ 1 line) out_scores, out_boxes, out_classes = sess.run([scores, boxes, 1bb8c classes], feed_dict = {yolo_model.input:image_data, K.learning_phase(): 0}) ### END CODE HERE ### # Print predictions info print('Found {} boxes for {}'.format(len(out_boxes), image_file)) # Generate colors for drawing bounding boxes. colors = generate_colors(class_names) # Draw bounding boxes on the image file draw_boxes(image, out_scores, out_boxes, out_classes, class_names, colors) # Save the predicted bounding box on the image image.save(os.path.join("out", image_file), quality=90) # Display the results in the notebook output_image = scipy.misc.imread(os.path.join("out", image_file)) imshow(output_image) return out_scores, out_boxes, out_classes
阅读更多
相关文章推荐
- 目标检测“Object Detection Using Generalization and Efficiency Balanced Co-occurrence Features”
- 视频目标检测--Flow-Guided Feature Aggregation for Video Object Detection
- 目标检测之LibPaBOD(a LIBrary for PArt-Based Object Detection in C++)
- 基于ROS 目标检测与识别-Object Detection and Recognition
- 目标检测-- DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
- 目标检测 - Tensorflow Object Detection API
- 对抗学习用于目标检测--A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
- 目标检测“A MultiPath Network for Object Detection”
- 目标检测--R-FCN: Object Detection via Region-based Fully Convolutional Networks
- 视频目标检测 - Object Detection from Video Tubelets with Convolutional Neural Networks
- 使用判别训练的部件模型进行目标检测 Object Detection with Discriminatively Trained Part Based Models
- 目标检测(Object Detection)原理与实现
- 使用sklearn-theano来做object detection目标检测 (OverFeat)
- 目标检测(Object Detection)的整理
- (三论文)目标检测 - Tensorflow Object Detection API几种模型的对比
- 图像目标检测(Object Detection)原理与实现(一)
- 目标检测(二)--Hough Forests for Object Detection
- 基于视频的移动目标检测 Moving Object Detection
- 使用判别训练的部件模型进行目标检测 Object Detection with Discriminatively Trained Part Based Models
- 目标检测“Perceptual Generative Adversarial Networks for Small Object Detection”