吴恩达深度学习编程作业答案

# -*- coding: utf-8 -* import os import scipy.io import scipy.misc import tensorflow as tf from keras import backend as K from keras.models import load_model, Model from yolo_utils import read_classes, read_anchors, generate_colors, preprocess_image, draw_boxes, scale_boxes from yad2k.models.keras_yolo import yolo_head, yolo_boxes_to_corners, preprocess_true_boxes, yolo_loss, yolo_body # 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) box_class_scores = K.max(box_scores, axis=-1, keepdims=False) ### 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 # 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 # 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 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, 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)