def build_rpn_targets(image_shape, anchors, gt_class_ids, gt_boxes, config):
# 1代表正样本
# -1代表负样本
# 0代表忽略
rpn_match = np.zeros([anchors.shape[0]], dtype=np.int32)
# 创建该部分内容利用先验框和真实框进行编码
rpn_bbox = np.zeros((config.RPN_TRAIN_ANCHORS_PER_IMAGE, 4))
'''
iscrowd=0的时候，表示这是一个单独的物体，轮廓用Polygon(多边形的点)表示，
iscrowd=1的时候表示两个没有分开的物体，轮廓用RLE编码表示，比如说一张图片里面有三个人，
一个人单独站一边，另外两个搂在一起（标注的时候距离太近分不开了），这个时候，
单独的那个人的注释里面的iscrowing=0,segmentation用Polygon表示，
而另外两个用放在同一个anatation的数组里面用一个segmention的RLE编码形式表示
'''
crowd_ix = np.where(gt_class_ids < 0)[0]
if crowd_ix.shape[0] > 0:
non_crowd_ix = np.where(gt_class_ids > 0)[0]
crowd_boxes = gt_boxes[crowd_ix]
gt_class_ids = gt_class_ids[non_crowd_ix]
gt_boxes = gt_boxes[non_crowd_ix]
crowd_overlaps = utils.compute_overlaps(anchors, crowd_boxes)
crowd_iou_max = np.amax(crowd_overlaps, axis=1)
no_crowd_bool = (crowd_iou_max < 0.001)
else:
no_crowd_bool = np.ones([anchors.shape[0]], dtype=bool)
# 计算先验框和真实框的重合程度 [num_anchors, num_gt_boxes]
overlaps = utils.compute_overlaps(anchors, gt_boxes)
# 1. 重合程度小于0.3则代表为负样本
anchor_iou_argmax = np.argmax(overlaps, axis=1)
anchor_iou_max = overlaps[np.arange(overlaps.shape[0]), anchor_iou_argmax]
rpn_match[(anchor_iou_max < 0.3) & (no_crowd_bool)] = -1
# 2. 每个真实框重合度最大的先验框是正样本
gt_iou_argmax = np.argwhere(overlaps == np.max(overlaps, axis=0))[:, 0]
rpn_match[gt_iou_argmax] = 1
# 3. 重合度大于0.7则代表为正样本
rpn_match[anchor_iou_max >= 0.7] = 1
# 正负样本平衡
# 找到正样本的索引
ids = np.where(rpn_match == 1)[0]
# 如果大于(config.RPN_TRAIN_ANCHORS_PER_IMAGE // 2)则删掉一些
extra = len(ids) - (config.RPN_TRAIN_ANCHORS_PER_IMAGE // 2)
if extra > 0:
ids = np.random.choice(ids, extra, replace=False)
rpn_match[ids] = 0
# 找到负样本的索引
ids = np.where(rpn_match == -1)[0]
# 使得总数为config.RPN_TRAIN_ANCHORS_PER_IMAGE
extra = len(ids) - (config.RPN_TRAIN_ANCHORS_PER_IMAGE -
np.sum(rpn_match == 1))
if extra > 0:
# Rest the extra ones to neutral
ids = np.random.choice(ids, extra, replace=False)
rpn_match[ids] = 0
# 找到内部真实存在物体的先验框，进行编码
ids = np.where(rpn_match == 1)[0]
ix = 0
for i, a in zip(ids, anchors[ids]):
gt = gt_boxes[anchor_iou_argmax[i]]
# 计算真实框的中心，高宽
gt_h = gt[2] - gt[0]
gt_w = gt[3] - gt[1]
gt_center_y = gt[0] + 0.5 * gt_h
gt_center_x = gt[1] + 0.5 * gt_w
# 计算先验框中心，高宽
a_h = a[2] - a[0]
a_w = a[3] - a[1]
a_center_y = a[0] + 0.5 * a_h
a_center_x = a[1] + 0.5 * a_w
# 编码运算
rpn_bbox[ix] = [
(gt_center_y - a_center_y) / np.maximum(a_h, 1),
(gt_center_x - a_center_x) / np.maximum(a_w, 1),
np.log(np.maximum(gt_h / np.maximum(a_h, 1), 1e-5)),
np.log(np.maximum(gt_w / np.maximum(a_w, 1), 1e-5)),
]
# 改变数量级
rpn_bbox[ix] /= config.RPN_BBOX_STD_DEV
ix += 1
return rpn_match, rpn_bbox
def build_rpn_targets(image_shape, anchors, gt_class_ids, gt_boxes, config):
"""Given the anchors and GT boxes, compute overlaps and identify positive
anchors and deltas to refine them to match their corresponding GT boxes.
anchors: [num_anchors, (y1, x1, y2, x2)]
gt_class_ids: [num_gt_boxes] Integer class IDs.
gt_boxes: [num_gt_boxes, (y1, x1, y2, x2)]
Returns:
rpn_match: [N] (int32) matches between anchors and GT boxes.
1 = positive anchor, -1 = negative anchor, 0 = neutral
rpn_bbox: [N, (dy, dx, log(dh), log(dw))] Anchor bbox deltas.
"""
# RPN Match: 1 = positive anchor, -1 = negative anchor, 0 = neutral
rpn_match = np.zeros([anchors.shape[0]], dtype=np.int32)
# RPN bounding boxes: [max anchors per image, (dy, dx, log(dh), log(dw))]
rpn_bbox = np.zeros((config.RPN.TRAIN_ANCHORS_PER_IMAGE, 4))
# Handle COCO crowds
# A crowd box in COCO is a bounding box around several instances. Exclude
# them from training. A crowd box is given a negative class ID.
crowd_ix = np.where(gt_class_ids < 0)[0]
if crowd_ix.shape[0] > 0:
# Filter out crowds from ground truth class IDs and boxes
non_crowd_ix = np.where(gt_class_ids > 0)[0]
crowd_boxes = gt_boxes[crowd_ix]
gt_class_ids = gt_class_ids[non_crowd_ix]
gt_boxes = gt_boxes[non_crowd_ix]
# Compute overlaps with crowd boxes [anchors, crowds]
crowd_overlaps = utils.compute_overlaps(anchors, crowd_boxes)
crowd_iou_max = np.amax(crowd_overlaps, axis=1)
no_crowd_bool = (crowd_iou_max < 0.001)
else:
# All anchors don't intersect a crowd
no_crowd_bool = np.ones([anchors.shape[0]], dtype=bool)
# Compute overlaps [num_anchors, num_gt_boxes]
overlaps = utils.compute_overlaps(anchors, gt_boxes)
# Match anchors to GT Boxes
# If an anchor overlaps a GT box with IoU >= 0.7 then it's positive.
# If an anchor overlaps a GT box with IoU < 0.3 then it's negative.
# Neutral anchors are those that don't match the conditions above,
# and they don't influence the loss function.
# However, don't keep any GT box unmatched (rare, but happens). Instead,
# match it to the closest anchor (even if its max IoU is < 0.3).
#
# 1. Set negative anchors first. They get overwritten below if a GT box is
# matched to them. Skip boxes in crowd areas.
anchor_iou_argmax = np.argmax(overlaps, axis=1)
anchor_iou_max = overlaps[np.arange(overlaps.shape[0]), anchor_iou_argmax]
rpn_match[(anchor_iou_max < 0.3) & (no_crowd_bool)] = -1
# 2. Set an anchor for each GT box (regardless of IoU value).
# TODO: If multiple anchors have the same IoU match all of them
gt_iou_argmax = np.argmax(overlaps, axis=0)
rpn_match[gt_iou_argmax] = 1
# 3. Set anchors with high overlap as positive.
rpn_match[anchor_iou_max >= 0.7] = 1
# Subsample to balance positive and negative anchors
# Don't let positives be more than half the anchors
ids = np.where(rpn_match == 1)[0]
extra = len(ids) - (config.RPN.TRAIN_ANCHORS_PER_IMAGE // 2)
if extra > 0:
# Reset the extra ones to neutral
ids = np.random.choice(ids, extra, replace=False)
rpn_match[ids] = 0
# Same for negative proposals
ids = np.where(rpn_match == -1)[0]
extra = len(ids) - (config.RPN.TRAIN_ANCHORS_PER_IMAGE -
np.sum(rpn_match == 1))
if extra > 0:
# Rest the extra ones to neutral
ids = np.random.choice(ids, extra, replace=False)
rpn_match[ids] = 0
# For positive anchors, compute shift and scale needed to transform them
# to match the corresponding GT boxes.
ids = np.where(rpn_match == 1)[0]
ix = 0 # index into rpn_bbox
# TODO: use box_refinment() rather than duplicating the code here
for i, a in zip(ids, anchors[ids]):
# Closest gt box (it might have IoU < 0.7)
gt = gt_boxes[anchor_iou_argmax[i]]
# Convert coordinates to center plus width/height.
# GT Box
gt_h = gt[2] - gt[0]
gt_w = gt[3] - gt[1]
gt_center_y = gt[0] + 0.5 * gt_h
gt_center_x = gt[1] + 0.5 * gt_w
# Anchor
a_h = a[2] - a[0]
a_w = a[3] - a[1]
a_center_y = a[0] + 0.5 * a_h
a_center_x = a[1] + 0.5 * a_w
# Compute the bbox refinement that the RPN should predict.
rpn_bbox[ix] = [
(gt_center_y - a_center_y) / a_h,
(gt_center_x - a_center_x) / a_w,
np.log(gt_h / a_h),
np.log(gt_w / a_w),
]
# Normalize
rpn_bbox[ix] /= config.RPN.BBOX_STD_DEV
ix += 1
return rpn_match, rpn_bbox