def detected_bboxes(
self,
predictions,
localisations, #通过SSD网络，得到检测到的bbox
select_threshold=None,
nms_threshold=0.5,
clipping_bbox=None,
top_k=400,
keep_top_k=200):
"""Get the detected bounding boxes from the SSD network output.
"""
# Select top_k bboxes from predictions, and clip #选取top_k=400个框，并对框做修建（超出原图尺寸范围的切掉）
# 得到对应某个类别的得分值以及bbox
rscores, rbboxes = \
ssd_common.tf_ssd_bboxes_select(predictions, localisations,
select_threshold=select_threshold,
num_classes=self.params.num_classes)
# 按照得分高低，筛选出400个bbox和对应得分
rscores, rbboxes = \
tfe.bboxes_sort(rscores, rbboxes, top_k=top_k)
# Apply NMS algorithm. #应用非极大值抑制，筛选掉与得分最高bbox重叠率大于0.5的，保留200个
rscores, rbboxes = \
tfe.bboxes_nms_batch(rscores, rbboxes,
nms_threshold=nms_threshold,
keep_top_k=keep_top_k)
if clipping_bbox is not None:
rbboxes = tfe.bboxes_clip(clipping_bbox, rbboxes)
return rscores, rbboxes #返回裁剪好的bbox和对应得分
def detected_bboxes(self,
predictions,
localisations,
select_threshold=None,
nms_threshold=0.5,
clipping_bbox=None,
top_k=400,
keep_top_k=200):
"""Get the detected bounding boxes from the SSD network output.
"""
# Select top_k bboxes from predictions, and clip
rscores, rbboxes = \
ssd_common.tf_ssd_bboxes_select(predictions, localisations,
select_threshold=select_threshold,
num_classes=self.params.num_classes)
rscores, rbboxes = \
tfe.bboxes_sort(rscores, rbboxes, top_k=top_k)
# Apply NMS algorithm.
rscores, rbboxes = \
tfe.bboxes_nms_batch(rscores, rbboxes,
nms_threshold=nms_threshold,
keep_top_k=keep_top_k)
if clipping_bbox is not None:
rbboxes = tfe.bboxes_clip(clipping_bbox, rbboxes)
return rscores, rbboxes
def detected_bboxes(self, predictions, localisations,
select_threshold=None, nms_threshold=0.5,
clipping_bbox=None, top_k=400, keep_top_k=200):
"""Get the detected bounding boxes from the SSD network output.
"""
# Select top_k bboxes from predictions, and clip
rscores, rbboxes = \
ssd_common.tf_ssd_bboxes_select(predictions, localisations,
select_threshold=select_threshold,
num_classes=self.params.num_classes)
rscores, rbboxes = \
tfe.bboxes_sort(rscores, rbboxes, top_k=top_k)
# Apply NMS algorithm.
rscores, rbboxes = \
tfe.bboxes_nms_batch(rscores, rbboxes,
nms_threshold=nms_threshold,
keep_top_k=keep_top_k)
if clipping_bbox is not None:
rbboxes = tfe.bboxes_clip(clipping_bbox, rbboxes)
return rscores, rbboxes
"""Get the detected bounding boxes from the SSD network output.
"""
# Select top_k bboxes from predictions, and clip #选取top_k=400个框，并对框做修建（超出原图尺寸范围的切掉）
rscores, rbboxes = \ #得到对应某个类别的得分值以及bbox
ssd_common.tf_ssd_bboxes_select(predictions, localisations,
select_threshold=select_threshold,
num_classes=self.params.num_classes)
rscores, rbboxes = \ #按照得分高低，筛选出400个bbox和对应得分
tfe.bboxes_sort(rscores, rbboxes, top_k=top_k)
# Apply NMS algorithm. #应用非极大值抑制，筛选掉与得分最高bbox重叠率大于0.5的，保留200个
rscores, rbboxes = \
tfe.bboxes_nms_batch(rscores, rbboxes,
nms_threshold=nms_threshold,
keep_top_k=keep_top_k)
if clipping_bbox is not None:
rbboxes = tfe.bboxes_clip(clipping_bbox, rbboxes)
return rscores, rbboxes #返回裁剪好的bbox和对应得分
#尽管一个ground truth可以与多个先验框匹配，但是ground truth相对先验框还是太少了，
#所以负样本相对正样本会很多。为了保证正负样本尽量平衡，SSD采用了hard negative mining，
#就是对负样本进行抽样，抽样时按照置信度误差（预测背景的置信度越小，误差越大）进行降序排列，
#选取误差的较大的top-k作为训练的负样本，以保证正负样本比例接近1:3
def losses(self, logits, localisations,
gclasses, glocalisations, gscores,
match_threshold=0.5,
negative_ratio=3.,
alpha=1.,
label_smoothing=0.,
scope='ssd_losses'):
"""Define the SSD network losses.
"""
return ssd_losses(logits, localisations,
