def box_results_with_nms_and_limit(scores,
boxes): # NOTE: support single-batch
"""Returns bounding-box detection results by thresholding on scores and
applying non-maximum suppression (NMS).
`boxes` has shape (#detections, 4 * #classes), where each row represents
a list of predicted bounding boxes for each of the object classes in the
dataset (including the background class). The detections in each row
originate from the same object proposal.
`scores` has shape (#detection, #classes), where each row represents a list
of object detection confidence scores for each of the object classes in the
dataset (including the background class). `scores[i, j]`` corresponds to the
box at `boxes[i, j * 4:(j + 1) * 4]`.
"""
num_classes = cfg.MODEL.NUM_CLASSES
cls_boxes = [[] for _ in range(num_classes)]
# Apply threshold on detection probabilities and apply NMS
# Skip j = 0, because it's the background class
for j in range(1, num_classes):
inds = np.where(scores[:, j] > cfg.TEST.SCORE_THRESH)[0]
scores_j = scores[inds, j]
boxes_j = boxes[inds, j * 4:(j + 1) * 4]
dets_j = np.hstack((boxes_j, scores_j[:,
np.newaxis])).astype(np.float32,
copy=False)
if cfg.TEST.USE_GT_PROPOSALS:
nms_dets = dets_j
elif cfg.TEST.SOFT_NMS.ENABLED:
nms_dets, _ = box_utils.soft_nms(dets_j,
sigma=cfg.TEST.SOFT_NMS.SIGMA,
overlap_thresh=cfg.TEST.NMS,
score_thresh=0.0001,
method=cfg.TEST.SOFT_NMS.METHOD)
else:
keep = box_utils.nms(dets_j, cfg.TEST.NMS)
nms_dets = dets_j[keep, :]
# Refine the post-NMS boxes using bounding-box voting
if cfg.TEST.BBOX_VOTE.ENABLED:
nms_dets = box_utils.box_voting(
nms_dets,
dets_j,
cfg.TEST.BBOX_VOTE.VOTE_TH,
scoring_method=cfg.TEST.BBOX_VOTE.SCORING_METHOD)
cls_boxes[j] = nms_dets
# Limit to max_per_image detections **over all classes**
if cfg.TEST.DETECTIONS_PER_IM > 0:
image_scores = np.hstack(
[cls_boxes[j][:, -1] for j in range(1, num_classes)])
if len(image_scores) > cfg.TEST.DETECTIONS_PER_IM:
image_thresh = np.sort(image_scores)[-cfg.TEST.DETECTIONS_PER_IM]
for j in range(1, num_classes):
keep = np.where(cls_boxes[j][:, -1] >= image_thresh)[0]
cls_boxes[j] = cls_boxes[j][keep, :]
im_results = np.vstack([cls_boxes[j] for j in range(1, num_classes)])
boxes = im_results[:, :-1]
scores = im_results[:, -1]
return scores, boxes, cls_boxes
def box_results_with_nms_and_limit(scores, boxes): # NOTE: support single-batch
"""Returns bounding-box detection results by thresholding on scores and
applying non-maximum suppression (NMS).
`boxes` has shape (#detections, 4 * #classes), where each row represents
a list of predicted bounding boxes for each of the object classes in the
dataset (including the background class). The detections in each row
originate from the same object proposal.
`scores` has shape (#detection, #classes), where each row represents a list
of object detection confidence scores for each of the object classes in the
dataset (including the background class). `scores[i, j]`` corresponds to the
box at `boxes[i, j * 4:(j + 1) * 4]`.
"""
num_classes = cfg.MODEL.NUM_CLASSES
cls_boxes = [[] for _ in range(num_classes)]
# Apply threshold on detection probabilities and apply NMS
# Skip j = 0, because it's the background class
for j in range(1, num_classes):
inds = np.where(scores[:, j] > cfg.TEST.SCORE_THRESH)[0]
scores_j = scores[inds, j]
boxes_j = boxes[inds, j * 4:(j + 1) * 4]
dets_j = np.hstack((boxes_j, scores_j[:, np.newaxis])).astype(np.float32, copy=False)
if cfg.TEST.SOFT_NMS.ENABLED:
nms_dets, _ = box_utils.soft_nms(
dets_j,
sigma=cfg.TEST.SOFT_NMS.SIGMA,
overlap_thresh=cfg.TEST.NMS,
score_thresh=0.0001,
method=cfg.TEST.SOFT_NMS.METHOD
)
else:
keep = box_utils.nms(dets_j, cfg.TEST.NMS)
nms_dets = dets_j[keep, :]
# Refine the post-NMS boxes using bounding-box voting
if cfg.TEST.BBOX_VOTE.ENABLED:
nms_dets = box_utils.box_voting(
nms_dets,
dets_j,
cfg.TEST.BBOX_VOTE.VOTE_TH,
scoring_method=cfg.TEST.BBOX_VOTE.SCORING_METHOD
)
cls_boxes[j] = nms_dets
# Limit to max_per_image detections **over all classes**
if cfg.TEST.DETECTIONS_PER_IM > 0:
image_scores = np.hstack(
[cls_boxes[j][:, -1] for j in range(1, num_classes)]
)
if len(image_scores) > cfg.TEST.DETECTIONS_PER_IM:
image_thresh = np.sort(image_scores)[-cfg.TEST.DETECTIONS_PER_IM]
for j in range(1, num_classes):
keep = np.where(cls_boxes[j][:, -1] >= image_thresh)[0]
cls_boxes[j] = cls_boxes[j][keep, :]
im_results = np.vstack([cls_boxes[j] for j in range(1, num_classes)])
boxes = im_results[:, :-1]
scores = im_results[:, -1]
return scores, boxes, cls_boxes
def box_results_with_nms_and_limit(self,
scores,
boxes,
score_thresh=cfg.TEST.SCORE_THRESH):
num_classes = cfg.MODEL.NUM_CLASSES
cls_boxes = [[] for _ in range(num_classes)]
# Apply threshold on detection probabilities and apply NMS
# Skip j = 0, because it's the background class
for j in range(1, num_classes):
inds = np.where(scores[:, j] > score_thresh)[0]
scores_j = scores[inds, j]
boxes_j = boxes[inds, j * 4:(j + 1) * 4]
dets_j = np.hstack(
(boxes_j, scores_j[:, np.newaxis])).astype(np.float32,
copy=False)
if cfg.TEST.SOFT_NMS.ENABLED:
nms_dets, _ = box_utils.soft_nms(
dets_j,
sigma=cfg.TEST.SOFT_NMS.SIGMA,
overlap_thresh=cfg.TEST.NMS,
score_thresh=0.0001,
method=cfg.TEST.SOFT_NMS.METHOD)
else:
keep = box_utils.nms(dets_j, cfg.TEST.NMS)
nms_dets = dets_j[keep, :]
# add labels
label_j = np.ones((nms_dets.shape[0], 1), dtype=np.float32) * j
nms_dets = np.hstack((nms_dets, label_j))
# Refine the post-NMS boxes using bounding-box voting
if cfg.TEST.BBOX_VOTE.ENABLED:
nms_dets = box_utils.box_voting(
nms_dets,
dets_j,
cfg.TEST.BBOX_VOTE.VOTE_TH,
scoring_method=cfg.TEST.BBOX_VOTE.SCORING_METHOD)
cls_boxes[j] = nms_dets
# Limit to max_per_image detections **over all classes**
if cfg.TEST.DETECTIONS_PER_IM > 0:
image_scores = np.hstack(
[cls_boxes[j][:, -2] for j in range(1, num_classes)])
if len(image_scores) > cfg.TEST.DETECTIONS_PER_IM:
image_thresh = np.sort(
image_scores)[-cfg.TEST.DETECTIONS_PER_IM]
for j in range(1, num_classes):
keep = np.where(cls_boxes[j][:, -2] >= image_thresh)[0]
cls_boxes[j] = cls_boxes[j][keep, :]
im_results = np.vstack([cls_boxes[j] for j in range(1, num_classes)])
boxes = im_results[:, :-2]
scores = im_results[:, -2]
labels = im_results[:, -1]
return scores, boxes, labels
def iou_box_nms_and_limit(stage1_box, stage1_iou, dets_cls, scores):
num_classes = cfg.MODEL.NUM_CLASSES
cls_boxes = [[] for _ in range(num_classes)]
for j in range(1, num_classes):
inds = np.array(dets_cls[str(j)], dtype=np.int)
if not inds.tolist():
boxes_j = np.empty((0, 4), dtype=np.float32)
else:
boxes_j = stage1_box[inds]
iou_j = stage1_iou[inds]
score_j = scores[inds]
dets_j = np.hstack((boxes_j, iou_j[:, np.newaxis])).astype(np.float32,
copy=False)
if cfg.TEST.SOFT_NMS.ENABLED:
nms_dets, _ = box_utils.soft_nms(dets_j,
sigma=cfg.TEST.SOFT_NMS.SIGMA,
overlap_thresh=cfg.TEST.NMS,
score_thresh=0.0001,
method=cfg.TEST.SOFT_NMS.METHOD)
else:
keep = box_utils.nms(dets_j, cfg.TEST.NMS)
boxes_j = boxes_j[keep]
score_j = score_j[keep]
nms_dets = np.hstack(
(boxes_j, score_j[:, np.newaxis])).astype(np.float32,
copy=False)
# Refine the post-NMS boxes using bounding-box voting
if cfg.TEST.BBOX_VOTE.ENABLED:
nms_dets = box_utils.box_voting(
nms_dets,
dets_j,
cfg.TEST.BBOX_VOTE.VOTE_TH,
scoring_method=cfg.TEST.BBOX_VOTE.SCORING_METHOD)
cls_boxes[j] = nms_dets
# Limit to max_per_image detections **over all classes**
if cfg.TEST.DETECTIONS_PER_IM > 0:
image_scores = np.hstack(
[cls_boxes[j][:, -1] for j in range(1, num_classes)])
if len(image_scores) > cfg.TEST.DETECTIONS_PER_IM:
image_thresh = np.sort(image_scores)[-cfg.TEST.DETECTIONS_PER_IM]
for j in range(1, num_classes):
keep = np.where(cls_boxes[j][:, -1] >= image_thresh)[0]
cls_boxes[j] = cls_boxes[j][keep, :]
im_results = np.vstack([cls_boxes[j] for j in range(1, num_classes)])
boxes = im_results[:, :-1]
scores = im_results[:, -1]
return scores, boxes, cls_boxes
def box_results_with_nms_and_limit(
scores,
boxes,
num_classes=81,
score_thresh=0.05,
overlap_thresh=0.5,
do_soft_nms=False,
soft_nms_sigma=0.5,
soft_nms_method='linear',
do_bbox_vote=False,
bbox_vote_thresh=0.8,
bbox_vote_method='ID',
max_detections_per_img=100, ### over all classes ###
):
"""Returns bounding-box detection results by thresholding on scores and
applying non-maximum suppression (NMS).
A number of #detections presist after this and are returned, sorted by class
`boxes` has shape (#detections, 4 * #classes), where each row represents
a list of predicted bounding boxes for each of the object classes in the
dataset (including the background class). The detections in each row
originate from the same object proposal.
`scores` has shape (#detection, #classes), where each row represents a list
of object detection confidence scores for each of the object classes in the
dataset (including the background class). `scores[i, j]`` corresponds to the
box at `boxes[i, j * 4:(j + 1) * 4]`.
"""
cls_boxes = [[] for _ in range(num_classes)]
# Apply threshold on detection probabilities and apply NMS
# Skip j = 0, because it's the background class
for j in range(1, num_classes):
inds = np.where(scores[:, j] > score_thresh)[0]
scores_j = scores[inds, j]
boxes_j = boxes[inds, j * 4:(j + 1) * 4]
dets_j = np.hstack((boxes_j, scores_j[:,
np.newaxis])).astype(np.float32,
copy=False)
if do_soft_nms:
nms_dets, _ = box_utils.soft_nms(dets_j,
sigma=soft_nms_sigma,
overlap_thresh=overlap_thresh,
score_thresh=0.0001,
method=soft_nms_method)
else:
keep = box_utils.nms(dets_j, overlap_thresh)
nms_dets = dets_j[keep, :]
# Refine the post-NMS boxes using bounding-box voting
if do_bbox_vote:
nms_dets = box_utils.box_voting(nms_dets,
dets_j,
bbox_vote_thresh,
scoring_method=bbox_vote_method)
cls_boxes[j] = nms_dets
# Limit to max_per_image detections **over all classes**
if max_detections_per_img > 0:
image_scores = np.hstack(
[cls_boxes[j][:, -1] for j in range(1, num_classes)])
if len(image_scores) > max_detections_per_img:
image_thresh = np.sort(image_scores)[-max_detections_per_img]
for j in range(1, num_classes):
keep = np.where(cls_boxes[j][:, -1] >= image_thresh)[0]
cls_boxes[j] = cls_boxes[j][keep, :]
im_results = np.vstack([cls_boxes[j] for j in range(1, num_classes)])
boxes = im_results[:, :-1]
scores = im_results[:, -1]
return scores, boxes, cls_boxes
def box_results_with_nms_and_limit(scores, boxes, prev_cls_boxes=None): # NOTE: support single-batch
"""Returns bounding-box detection results by thresholding on scores and
applying non-maximum suppression (NMS).
`boxes` has shape (#detections, 4 * #classes), where each row represents
a list of predicted bounding boxes for each of the object classes in the
dataset (including the background class). The detections in each row
originate from the same object proposal.
`scores` has shape (#detection, #classes), where each row represents a list
of object detection confidence scores for each of the object classes in the
dataset (including the background class). `scores[i, j]`` corresponds to the
box at `boxes[i, j * 4:(j + 1) * 4]`.
"""
num_classes = cfg.MODEL.NUM_CLASSES
cls_boxes = [[] for _ in range(num_classes)]
# Apply threshold on detection probabilities and apply NMS
# Skip j = 0, because it's the background class
for j in range(1, num_classes):
inds = np.where(scores[:, j] >= cfg.TEST.SCORE_THRESH)[0]
scores_j = scores[inds, j]
boxes_j = boxes[inds, j * 4:(j + 1) * 4]
dets_j = np.hstack((boxes_j, scores_j[:, np.newaxis])).astype(np.float32, copy=False)
if cfg.TEST.SOFT_NMS.ENABLED:
nms_dets, _ = box_utils.soft_nms(
dets_j,
sigma=cfg.TEST.SOFT_NMS.SIGMA,
overlap_thresh=cfg.TEST.NMS,
score_thresh=0.0001,
method=cfg.TEST.SOFT_NMS.METHOD
)
else:
keep = box_utils.nms(dets_j, cfg.TEST.NMS)
nms_dets = dets_j[keep, :]
# Refine the post-NMS boxes using bounding-box voting
if cfg.TEST.BBOX_VOTE.ENABLED:
nms_dets = box_utils.box_voting(
nms_dets,
dets_j,
cfg.TEST.BBOX_VOTE.VOTE_TH,
scoring_method=cfg.TEST.BBOX_VOTE.SCORING_METHOD
)
cls_boxes[j] = nms_dets
# Limit to max_per_image detections **over all classes**
if cfg.TEST.DETECTIONS_PER_IM > 0:
image_scores = np.hstack(
[cls_boxes[j][:, -1] for j in range(1, num_classes)]
)
if len(image_scores) > cfg.TEST.DETECTIONS_PER_IM:
image_thresh = np.sort(image_scores)[-cfg.TEST.DETECTIONS_PER_IM]
for j in range(1, num_classes):
keep = np.where(cls_boxes[j][:, -1] >= image_thresh)[0]
cls_boxes[j] = cls_boxes[j][keep, :]
# select two best for each class if score is low..
'''
if cfg.TEST.NUM_DET_PER_CLASS_PRE==1:
for j in range(1, num_classes):
keep = np.argsort(-cls_boxes[j][:, -1])[:2]
cls_boxes[j] = cls_boxes[j][keep, :]
# if one has a very strong cls score, we only keep two boxes for weak cls score.
if len(cls_boxes[j])>0 and cls_boxes[j][0,-1]>0.5:
cls_boxes[j] = cls_boxes[j][:1, :]'''
# nms between classes.
if cfg.TEST.NMS_CROSS_CLASS > 0.:
'''
# code to keep some of the dets for which class there is only one det.
all_cls_boxes = []
reserved_cls = []
for j in range(1, num_classes):
tmp_cls_boxes = np.copy(cls_boxes[j])
# if only one det for cls j, we keep it.
if tmp_cls_boxes.shape[0] == 1:
tmp_cls_boxes[:,-1] = 1.0
all_cls_boxes.append(tmp_cls_boxes)
all_dets_for_nms = np.vstack(all_cls_boxes)
'''
all_dets = np.vstack([cls_boxes[j] for j in range(1, num_classes)])
class_ids = np.vstack([np.ones(shape=(len(cls_boxes[j]), 1))*j for j in range(1, num_classes)])
keep = box_utils.nms(all_dets, cfg.TEST.NMS_CROSS_CLASS)
all_dets = all_dets[keep, :]
class_ids = class_ids[keep, :]
for j in range(1, num_classes):
idx_j = np.where(class_ids==j)[0]
cls_boxes[j] = all_dets[idx_j, :]
# select one best for each class.
if cfg.TEST.NUM_DET_PER_CLASS_PRE>0:
for j in range(1, num_classes):
keep = np.argsort(-cls_boxes[j][:, -1])[:cfg.TEST.NUM_DET_PER_CLASS_PRE]
cls_boxes[j] = cls_boxes[j][keep, :]
# nms by previous box.
if cfg.TEST.NMS_SMALL_BOX_IOU>0:
for j in range(1, num_classes):
if prev_cls_boxes is not None:
assert len(prev_cls_boxes[j])<2, 'number of prev boxes should <2.'
if len(prev_cls_boxes[j])==1:
if prev_cls_boxes[j][0][-1]<cfg.TEST.NMS_SMALL_BOX_SCORE_THRESHOLD:
#if not confident about previous box, no nms.
continue
prev_cls_box = prev_cls_boxes[j][0][:-1]
index_to_remove = []
for id_box in range(len(cls_boxes[j])-1,-1,-1):
box = cls_boxes[j][id_box][:-1]
iou = bb_intersection_over_union(prev_cls_box, box)
if iou<cfg.TEST.NMS_SMALL_BOX_IOU:
index_to_remove.append(id_box)
cls_boxes[j] = np.delete(cls_boxes[j], index_to_remove, 0)
im_results = np.vstack([cls_boxes[j] for j in range(1, num_classes)])
boxes = im_results[:, :-1]
scores = im_results[:, -1]
return scores, boxes, cls_boxes
def evaluate_mAP_combine(json_datasets,
roidbs,
all_boxes_list,
output_dir,
cleanup=False):
""" LJY
all_boxes: num_cls x num_images x [num_boxes x 5]
"""
json_dataset = json_datasets[0]
mAP_folder = '/home/liujingyu/code/mAP'
roidb, roidb_part = roidbs[0], roidbs[1]
all_boxes, all_boxes_part = all_boxes_list[0], all_boxes_list[1]
small_classes = ['结节', '肺实变', '膈面异常', '骨折']
for i, (entry, entry_part) in enumerate(zip(
roidb, roidb_part)): # for each pair of images
# print(i, entry['eva_id'], entry['file_name'])
assert entry['file_name'] == entry_part['file_name']
file_name = entry['file_name'][:-4] + '.txt'
fgt = open(osp.join(mAP_folder, 'ground-truth', file_name), 'w')
fpred = open(osp.join(mAP_folder, 'predicted', file_name), 'w')
for cls_ind, cls in enumerate(json_dataset.classes): # for each cls
if cls == '__background__':
continue
if cls_ind >= len(all_boxes):
break
gt_classes = roidb[i]['gt_classes']
ind = np.where(gt_classes == cls_ind)
gt_boxes = roidb[i]['boxes'][ind]
dets = all_boxes[cls_ind][i] # N x 5, [x1, y1, x2, y2, score]
dets_part = all_boxes_part[cls_ind][i] # N x 5
# offset the dets_part based on offset
dets_part[:, 0] += entry_part['offset_x']
dets_part[:, 2] += entry_part['offset_x']
dets_part[:, 1] += entry_part['offset_y']
dets_part[:, 3] += entry_part['offset_y']
# select
# if cls in small_classes:
# dets = dets_part
# merge
dets = np.vstack((dets, dets_part))
# NMS on dets and dets_part
if cfg.TEST.SOFT_NMS.ENABLED:
nms_dets, _ = box_utils.soft_nms(
dets,
sigma=cfg.TEST.SOFT_NMS.SIGMA,
overlap_thresh=cfg.TEST.NMS,
score_thresh=0.0001,
method=cfg.TEST.SOFT_NMS.METHOD)
else:
keep = box_utils.nms(dets, cfg.TEST.NMS)
nms_dets = dets[keep, :]
# Refine the post-NMS boxes using bounding-box voting
if cfg.TEST.BBOX_VOTE.ENABLED:
nms_dets = box_utils.box_voting(
nms_dets,
dets,
cfg.TEST.BBOX_VOTE.VOTE_TH,
scoring_method=cfg.TEST.BBOX_VOTE.SCORING_METHOD)
dets = nms_dets
# write gt boxes, format: tvmonitor 2 10 173 238
for k in range(gt_boxes.shape[0]):
s = '{} {:f} {:f} {:f} {:f}'.format(cls, gt_boxes[k, 0],
gt_boxes[k, 1],
gt_boxes[k,
2], gt_boxes[k,
3])
fgt.write(s)
fgt.write('\n')
if cls == '肿块' or cls == '结节' or cls == '钙化' or cls == '乳头影':
s = '{} {:f} {:f} {:f} {:f}'.format(
'肿块结节钙化', gt_boxes[k, 0], gt_boxes[k, 1],
gt_boxes[k, 2], gt_boxes[k, 3])
fgt.write(s)
fgt.write('\n')
if cls == '纤维化表现' or cls == '肺实变' or cls == '肺纹理增多' or cls == '肿块' or cls == '弥漫性结节':
s = '{} {:f} {:f} {:f} {:f}'.format(
'高密度影', gt_boxes[k, 0], gt_boxes[k, 1], gt_boxes[k, 2],
gt_boxes[k, 3])
fgt.write(s)
fgt.write('\n')
if cls == '气胸' or cls == '气肿':
s = '{} {:f} {:f} {:f} {:f}'.format(
'低密度影', gt_boxes[k, 0], gt_boxes[k, 1], gt_boxes[k, 2],
gt_boxes[k, 3])
fgt.write(s)
fgt.write('\n')
# write pred boxes, format: tvmonitor 0.471781 0 13 174 244
for k in range(dets.shape[0]):
s = '{} {:f} {:f} {:f} {:f} {:f}'.format(
cls, dets[k, -1], dets[k, 0], dets[k, 1], dets[k, 2],
dets[k, 3])
fpred.write(s)
fpred.write('\n')
if cls == '肿块' or cls == '结节' or cls == '钙化' or cls == '乳头影':
s = '{} {:f} {:f} {:f} {:f} {:f}'.format(
'肿块结节钙化', dets[k, -1], dets[k, 0], dets[k, 1],
dets[k, 2], dets[k, 3])
fpred.write(s)
fpred.write('\n')
if cls == '纤维化表现' or cls == '肺实变' or cls == '肺纹理增多' or cls == '肿块' or cls == '弥漫性结节':
s = '{} {:f} {:f} {:f} {:f} {:f}'.format(
'高密度影', dets[k, -1], dets[k, 0], dets[k, 1],
dets[k, 2], dets[k, 3])
fpred.write(s)
fpred.write('\n')
if cls == '气胸' or cls == '气肿':
s = '{} {:f} {:f} {:f} {:f} {:f}'.format(
'低密度影', dets[k, -1], dets[k, 0], dets[k, 1],
dets[k, 2], dets[k, 3])
fpred.write(s)
fpred.write('\n')
if gt_boxes.shape[0] > 0: # then we draw gt boxes and pred boxes
im = cv2.imread(entry['image'])
more_text = str(entry['eva_id']) + ' ' + entry['doc_name']
im = vis_boxes_ljy(im, gt_boxes, dets[:, :-1], more_text)
out_path = os.path.join(
'/data5/liujingyu/mask_rcnn_Outputs/vis', cls,
entry['file_name'])
cv2.imwrite(out_path, im)
pdb.set_trace()
def box_results_with_nms_and_limit(scores, boxes,
num_classes=81,
score_thresh=0.05,
overlap_thresh=0.5,
do_soft_nms=False,
soft_nms_sigma=0.5,
soft_nms_method='linear',
do_bbox_vote=False,
bbox_vote_thresh=0.8,
bbox_vote_method='ID',
max_detections_per_img=100, ### over all classes ###
):
"""Returns bounding-box detection results by thresholding on scores and
applying non-maximum suppression (NMS).
A number of #detections presist after this and are returned, sorted by class
`boxes` has shape (#detections, 4 * #classes), where each row represents
a list of predicted bounding boxes for each of the object classes in the
dataset (including the background class). The detections in each row
originate from the same object proposal.
`scores` has shape (#detection, #classes), where each row represents a list
of object detection confidence scores for each of the object classes in the
dataset (including the background class). `scores[i, j]`` corresponds to the
box at `boxes[i, j * 4:(j + 1) * 4]`.
"""
cls_boxes = [[] for _ in range(num_classes)]
# Apply threshold on detection probabilities and apply NMS
# Skip j = 0, because it's the background class
for j in range(1, num_classes):
inds = np.where(scores[:, j] > score_thresh)[0]
scores_j = scores[inds, j]
boxes_j = boxes[inds, j * 4:(j + 1) * 4]
dets_j = np.hstack((boxes_j, scores_j[:, np.newaxis])).astype(
np.float32, copy=False
)
if do_soft_nms:
nms_dets, _ = box_utils.soft_nms(
dets_j,
sigma=soft_nms_sigma,
overlap_thresh=overlap_thresh,
score_thresh=0.0001,
method=soft_nms_method
)
else:
keep = box_utils.nms(dets_j, overlap_thresh)
nms_dets = dets_j[keep, :]
# Refine the post-NMS boxes using bounding-box voting
if do_bbox_vote:
nms_dets = box_utils.box_voting(
nms_dets,
dets_j,
bbox_vote_thresh,
scoring_method=bbox_vote_method
)
cls_boxes[j] = nms_dets
# Limit to max_per_image detections **over all classes**
if max_detections_per_img > 0:
image_scores = np.hstack(
[cls_boxes[j][:, -1] for j in range(1, num_classes)]
)
if len(image_scores) > max_detections_per_img:
image_thresh = np.sort(image_scores)[-max_detections_per_img]
for j in range(1, num_classes):
keep = np.where(cls_boxes[j][:, -1] >= image_thresh)[0]
cls_boxes[j] = cls_boxes[j][keep, :]
im_results = np.vstack([cls_boxes[j] for j in range(1, num_classes)])
boxes = im_results[:, :-1]
scores = im_results[:, -1]
return scores, boxes, cls_boxes