实现Faster R-CNN的keras代码理解(三)-RPN层

计算RPN网络的输出值

函数为datagenerators.py中的calc_rpn():

输入：配置文件，增强后的图片的信息，图片原宽，图片原高，resize后的宽，resize后的高，网络最后输出的卷积层的大小；

输出：y_rpn_cls前半段是否包含物体，y_rpn_regr回归的梯度

流程如图所示：

代码详解：

def calc_rpn(C, img_data, width, height, resized_width, resized_height, img_length_calc_function):
	#downsacle默认是16，共享卷积层压缩图像的倍数
	downscale = float(C.rpn_stride)
	anchor_sizes = C.anchor_box_scales
	anchor_ratios = C.anchor_box_ratios
	num_anchors = len(anchor_sizes) * len(anchor_ratios)	
	#计算最后一个卷积层输出的feature map的大小
	# calculate the output map size based on the network architecture

	(output_width, output_height) = img_length_calc_function(resized_width, resized_height)

	n_anchratios = len(anchor_ratios)
	
	# initialise empty output objectives
	y_rpn_overlap = np.zeros((output_height, output_width, num_anchors))#anchor是否与gta有overlap，且其IOU>0.7，overlap则为1反之则为0
	y_is_box_valid = np.zeros((output_height, output_width, num_anchors))#anchor是否有效，有效则为1，反之为0
	y_rpn_regr = np.zeros((output_height, output_width, num_anchors * 4))#返回的是与gta有overlap的anchor的梯度

	num_bboxes = len(img_data['bboxes'])

	num_anchors_for_bbox = np.zeros(num_bboxes).astype(int)#返回与每一个gta有overlap的anchor的数量
	best_anchor_for_bbox = -1*np.ones((num_bboxes, 4)).astype(int)#返回与每一个gta置信度最高的anchor的位置
	best_iou_for_bbox = np.zeros(num_bboxes).astype(np.float32)#返回与每一个gta置信度最高的anchor的分数
	best_x_for_bbox = np.zeros((num_bboxes, 4)).astype(int)#返回与每一个gta置信度最高的anchor的坐标
	best_dx_for_bbox = np.zeros((num_bboxes, 4)).astype(np.float32)#返回与每一个gta置信度最高的anchor的梯度
	
	# get the GT box coordinates, and resize to account for image resizing
	#对resized后的图片的bbox进行resize
	gta = np.zeros((num_bboxes, 4))
	for bbox_num, bbox in enumerate(img_data['bboxes']):
		# get the GT box coordinates, and resize to account for image resizing
		gta[bbox_num, 0] = bbox['x1'] * (resized_width / float(width))
		gta[bbox_num, 1] = bbox['x2'] * (resized_width / float(width))
		gta[bbox_num, 2] = bbox['y1'] * (resized_height / float(height))
		gta[bbox_num, 3] = bbox['y2'] * (resized_height / float(height))
	
	# rpn ground truth
	##循环每一个框，在feature map上的位置，并进行操作。返回y_rpn_cls与y_rpn_regr
	for anchor_size_idx in range(len(anchor_sizes)):
		for anchor_ratio_idx in range(n_anchratios):
			anchor_x = anchor_sizes[anchor_size_idx] * anchor_ratios[anchor_ratio_idx][0]
			anchor_y = anchor_sizes[anchor_size_idx] * anchor_ratios[anchor_ratio_idx][1]	
			
			for ix in range(output_width):					
				# x-coordinates of the current anchor box	
				x1_anc = downscale * (ix + 0.5) - anchor_x / 2
				x2_anc = downscale * (ix + 0.5) + anchor_x / 2	
				
				# ignore boxes that go across image boundaries					
				if x1_anc < 0 or x2_anc > resized_width:
					continue
					
				for jy in range(output_height):

					# y-coordinates of the current anchor box
					y1_anc = downscale * (jy + 0.5) - anchor_y / 2
					y2_anc = downscale * (jy + 0.5) + anchor_y / 2

					# ignore boxes that go across image boundaries
					if y1_anc < 0 or y2_anc > resized_height:
						continue

					# bbox_type indicates whether an anchor should be a target 
					bbox_type = 'neg'

					# this is the best IOU for the (x,y) coord and the current anchor
					# note that this is different from the best IOU for a GT bbox
					best_iou_for_loc = 0.0
					#对每一个anchor找与其置信度最大的gta
					for bbox_num in range(num_bboxes):
						
						# get IOU of the current GT box and the current anchor box
						curr_iou = iou([gta[bbox_num, 0], gta[bbox_num, 2], gta[bbox_num, 1], gta[bbox_num, 3]], [x1_anc, y1_anc, x2_anc, y2_anc])
						# calculate the regression targets if they will be needed
						##找到与gta置信度最高的anchor的梯度
						if curr_iou > best_iou_for_bbox[bbox_num] or curr_iou > C.rpn_max_overlap:
							cx = (gta[bbox_num, 0] + gta[bbox_num, 1]) / 2.0
							cy = (gta[bbox_num, 2] + gta[bbox_num, 3]) / 2.0
							cxa = (x1_anc + x2_anc)/2.0
							cya = (y1_anc + y2_anc)/2.0

							tx = (cx - cxa) / (x2_anc - x1_anc)
							ty = (cy - cya) / (y2_anc - y1_anc)
							tw = np.log((gta[bbox_num, 1] - gta[bbox_num, 0]) / (x2_anc - x1_anc))
							th = np.log((gta[bbox_num, 3] - gta[bbox_num, 2]) / (y2_anc - y1_anc))
						
						if img_data['bboxes'][bbox_num]['class'] != 'bg':
							##找到与gta置信度最高的anchor的梯度
							# all GT boxes should be mapped to an anchor box, so we keep track of which anchor box was best
							if curr_iou > best_iou_for_bbox[bbox_num]:
								best_anchor_for_bbox[bbox_num] = [jy, ix, anchor_ratio_idx, anchor_size_idx]
								best_iou_for_bbox[bbox_num] = curr_iou
								best_x_for_bbox[bbox_num,:] = [x1_anc, x2_anc, y1_anc, y2_anc]
								best_dx_for_bbox[bbox_num,:] = [tx, ty, tw, th]

							# we set the anchor to positive if the IOU is >0.7 (it does not matter if there was another better box, it just indicates overlap)
							if curr_iou > C.rpn_max_overlap:
								bbox_type = 'pos'
								num_anchors_for_bbox[bbox_num] += 1
								# we update the regression layer target if this IOU is the best for the current (x,y) and anchor position
								if curr_iou > best_iou_for_loc:
									best_iou_for_loc = curr_iou
									best_regr = (tx, ty, tw, th)

							# if the IOU is >0.3 and <0.7, it is ambiguous and no included in the objective
							if C.rpn_min_overlap < curr_iou < C.rpn_max_overlap:
								# gray zone between neg and pos
								if bbox_type != 'pos':
									bbox_type = 'neutral'

					# turn on or off outputs depending on IOUs
					if bbox_type == 'neg':
						y_is_box_valid[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 1
						y_rpn_overlap[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 0
					elif bbox_type == 'neutral':
						y_is_box_valid[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 0
						y_rpn_overlap[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 0
					elif bbox_type == 'pos':
						y_is_box_valid[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 1
						y_rpn_overlap[jy, ix, anchor_ratio_idx + n_anchratios * anchor_size_idx] = 1
						start = 4 * (anchor_ratio_idx + n_anchratios * anchor_size_idx)
						y_rpn_regr[jy, ix, start:start+4] = best_regr

	# we ensure that every bbox has at least one positive RPN region

	for idx in range(num_anchors_for_bbox.shape[0]):
		if num_anchors_for_bbox[idx] == 0:
			# no box with an IOU greater than zero ...
			if best_anchor_for_bbox[idx, 0] == -1:
				continue
			y_is_box_valid[
				best_anchor_for_bbox[idx,0], best_anchor_for_bbox[idx,1], best_anchor_for_bbox[idx,2] + n_anchratios *
				best_anchor_for_bbox[idx,3]] = 1
			y_rpn_overlap[
				best_anchor_for_bbox[idx,0], best_anchor_for_bbox[idx,1], best_anchor_for_bbox[idx,2] + n_anchratios *
				best_anchor_for_bbox[idx,3]] = 1
			start = 4 * (best_anchor_for_bbox[idx,2] + n_anchratios * best_anchor_for_bbox[idx,3])
			y_rpn_regr[
				best_anchor_for_bbox[idx,0], best_anchor_for_bbox[idx,1], start:start+4] = best_dx_for_bbox[idx, :]

	y_rpn_overlap = np.transpose(y_rpn_overlap, (2, 0, 1))
	y_rpn_overlap = np.expand_dims(y_rpn_overlap, axis=0)

	y_is_box_valid = np.transpose(y_is_box_valid, (2, 0, 1))
	y_is_box_valid = np.expand_dims(y_is_box_valid, axis=0)

	y_rpn_regr = np.transpose(y_rpn_regr, (2, 0, 1))
	y_rpn_regr = np.expand_dims(y_rpn_regr, axis=0)

	pos_locs = np.where(np.logical_and(y_rpn_overlap[0, :, :, :] == 1, y_is_box_valid[0, :, :, :] == 1))
	neg_locs = np.where(np.logical_and(y_rpn_overlap[0, :, :, :] == 0, y_is_box_valid[0, :, :, :] == 1))

	num_pos = len(pos_locs[0])

	# one issue is that the RPN has many more negative than positive regions, so we turn off some of the negative
	# regions. We also limit it to 256 regions.
	num_regions = 256

	if len(pos_locs[0]) > num_regions/2:
		val_locs = random.sample(range(len(pos_locs[0])), len(pos_locs[0]) - num_regions/2)
		y_is_box_valid[0, pos_locs[0][val_locs], pos_locs[1][val_locs], pos_locs[2][val_locs]] = 0
		num_pos = num_regions/2

	if len(neg_locs[0]) + num_pos > num_regions:
		val_locs = random.sample(range(len(neg_locs[0])), len(neg_locs[0]) - num_pos)
		y_is_box_valid[0, neg_locs[0][val_locs], neg_locs[1][val_locs], neg_locs[2][val_locs]] = 0

	y_rpn_cls = np.concatenate([y_is_box_valid, y_rpn_overlap], axis=1)
	y_rpn_regr = np.concatenate([np.repeat(y_rpn_overlap, 4, axis=1), y_rpn_regr], axis=1)

	return np.copy(y_rpn_cls), np.copy(y_rpn_regr)

参考博客：

https://zhuanlan.zhihu.com/p/31538483

https://blog.csdn.net/u011311291/article/details/81221893