def aug_test(self, img_feats, proposal_list, img_metas, rescale=False):
"""Test with augmentations.
If rescale is False, then returned bboxes and masks will fit the scale
of imgs[0].
"""
if self.with_semantic:
semantic_feats = [
self.semantic_head(feat)[1] for feat in img_feats
]
else:
semantic_feats = [None] * len(img_metas)
# recompute feats to save memory
# proposal_list = self.aug_test_rpn(img_feats, img_metas,
# self.test_cfg.rpn)
rcnn_test_cfg = self.test_cfg
aug_bboxes = []
aug_scores = []
for x, img_meta, semantic in zip(img_feats, img_metas, semantic_feats):
# only one image in the batch
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
proposals = bbox_mapping(proposal_list[0][:, :4], img_shape,
scale_factor, flip)
# "ms" in variable names means multi-stage
ms_scores = []
rois = bbox2roi([proposals])
for i in range(self.num_stages):
bbox_head = self.bbox_head[i]
bbox_results = self._bbox_forward(i,
x,
rois,
semantic_feat=semantic)
ms_scores.append(bbox_results['cls_score'])
if i < self.num_stages - 1:
bbox_label = bbox_results['cls_score'].argmax(dim=1)
rois = bbox_head.regress_by_class(
rois, bbox_label, bbox_results['bbox_pred'],
img_meta[0])
cls_score = sum(ms_scores) / float(len(ms_scores))
bboxes, scores = self.bbox_head[-1].get_bboxes(
rois,
cls_score,
bbox_results['bbox_pred'],
img_shape,
scale_factor,
rescale=False,
cfg=None)
aug_bboxes.append(bboxes)
aug_scores.append(scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = merge_aug_bboxes(
aug_bboxes, aug_scores, img_metas, rcnn_test_cfg)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
rcnn_test_cfg.score_thr,
rcnn_test_cfg.nms,
rcnn_test_cfg.max_per_img)
bbox_result = bbox2result(det_bboxes, det_labels,
self.bbox_head[-1].num_classes)
if self.with_mask:
if det_bboxes.shape[0] == 0:
mask_classes = self.mask_head[-1].num_classes
segm_result = [[] for _ in range(mask_classes - 1)]
mask_scores = [[] for _ in range(mask_classes - 1)]
else:
aug_masks = []
aug_img_metas = []
for x, img_meta, semantic in zip(img_feats, img_metas,
semantic_feats):
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
_bboxes = bbox_mapping(det_bboxes[:, :4], img_shape,
scale_factor, flip)
mask_rois = bbox2roi([_bboxes])
mask_feats = self.mask_roi_extractor[-1](
x[:len(self.mask_roi_extractor[-1].featmap_strides)],
mask_rois)
if self.with_semantic:
semantic_feat = semantic
mask_semantic_feat = self.semantic_roi_extractor(
[semantic_feat], mask_rois)
if mask_semantic_feat.shape[-2:] != mask_feats.shape[
-2:]:
mask_semantic_feat = F.adaptive_avg_pool2d(
mask_semantic_feat, mask_feats.shape[-2:])
mask_feats += mask_semantic_feat
last_feat = None
for i in range(self.num_stages):
mask_head = self.mask_head[i]
if self.mask_info_flow:
mask_pred, last_feat = mask_head(
mask_feats, last_feat)
else:
mask_pred = mask_head(mask_feats)
aug_masks.append(mask_pred.sigmoid().cpu().numpy())
aug_img_metas.append(img_meta)
merged_masks = merge_aug_masks(aug_masks, aug_img_metas,
self.test_cfg)
ori_shape = img_metas[0][0]['ori_shape']
segm_result = self.mask_head[-1].get_seg_masks(
merged_masks,
det_bboxes,
det_labels,
rcnn_test_cfg,
ori_shape,
scale_factor=1.0,
rescale=False)
import numpy as np
merged_masks_torch = torch.from_numpy(merged_masks).to(
torch.float16).cuda()
mask_results = dict(
mask_pred=merged_masks_torch, mask_feats=mask_feats
) # NOTE not sure whether mask features is correct here
mask_iou_pred = self.mask_iou_head(
mask_results['mask_feats'],
mask_results['mask_pred'][range(det_labels.size(0)),
det_labels])
mask_scores = self.mask_iou_head.get_mask_scores(
mask_iou_pred, det_bboxes, det_labels)
return bbox_result, (segm_result, mask_scores)
else:
return bbox_result
def aug_test(self, imgs, img_metas, **kwargs):
"""Test with augmentations.
If rescale is False, then returned bboxes and masks will fit the scale
of imgs[0].
"""
rpn_test_cfg = self.models[0].test_cfg.rpn
imgs_per_gpu = len(img_metas[0])
aug_proposals = [[] for _ in range(imgs_per_gpu)]
for model in self.models:
# recompute feats to save memory
for x, img_meta in zip(model.extract_feats(imgs), img_metas):
proposal_list = model.rpn_head.simple_test_rpn(x, img_meta)
for i, proposals in enumerate(proposal_list):
aug_proposals[i].append(proposals)
# after merging, proposals will be rescaled to the original image size
proposal_list = [
merge_aug_proposals(proposals, img_meta, rpn_test_cfg)
for proposals, img_meta in zip(aug_proposals, img_metas)
]
semantic_feats = [None] * len(img_metas)
rcnn_test_cfg = self.models[0].test_cfg
aug_bboxes = []
aug_scores = []
for model in self.models:
for x, img_meta, semantic in zip(imgs, img_metas, semantic_feats):
# only one image in the batch
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
flip_direction = img_meta[0]['flip_direction']
proposals = bbox_mapping(proposal_list[0][:, :4], img_shape,
scale_factor, flip, flip_direction)
# "ms" in variable names means multi-stage
ms_scores = []
rois = bbox2roi([proposals])
for i in range(model.roi_head.num_stages):
bbox_head = model.roi_head.bbox_head[i]
bbox_results = model.roi_head._bbox_forward(
i, x, rois, semantic_feat=semantic)
ms_scores.append(bbox_results['cls_score'])
if i < model.roi_head.num_stages - 1:
bbox_label = bbox_results['cls_score'].argmax(dim=1)
rois = bbox_head.regress_by_class(
rois, bbox_label, bbox_results['bbox_pred'],
img_meta[0])
cls_score = sum(ms_scores) / float(len(ms_scores))
bboxes, scores = model.bbox_head[-1].get_bboxes(
rois,
cls_score,
bbox_results['bbox_pred'],
img_shape,
scale_factor,
rescale=False,
cfg=None)
aug_bboxes.append(bboxes)
aug_scores.append(scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = merge_aug_bboxes(
aug_bboxes, aug_scores, img_metas, rcnn_test_cfg)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
rcnn_test_cfg.score_thr,
rcnn_test_cfg.nms,
rcnn_test_cfg.max_per_img)
bbox_result = bbox2result(det_bboxes, det_labels,
self.models[0].bbox_head[-1].num_classes)
if self.models[0].with_mask:
if det_bboxes.shape[0] == 0:
segm_result = [[]
for _ in range(self.models[0].mask_head[-1].num_classes -
1)]
else:
aug_masks = []
aug_img_metas = []
for model in self.models:
for x, img_meta, semantic in zip(imgs, img_metas,
semantic_feats):
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
flip_direction = img_meta[0]['flip_direction']
_bboxes = bbox_mapping(det_bboxes[:, :4], img_shape,
scale_factor, flip, flip_direction)
mask_rois = bbox2roi([_bboxes])
mask_feats = model.mask_roi_extractor[-1](
x[:len(model.mask_roi_extractor[-1].featmap_strides)],
mask_rois)
if model.with_semantic:
semantic_feat = semantic
mask_semantic_feat = model.semantic_roi_extractor(
[semantic_feat], mask_rois)
if mask_semantic_feat.shape[-2:] != mask_feats.shape[
-2:]:
mask_semantic_feat = F.adaptive_avg_pool2d(
mask_semantic_feat, mask_feats.shape[-2:])
mask_feats += mask_semantic_feat
last_feat = None
for i in range(model.num_stages):
mask_head = model.mask_head[i]
if model.mask_info_flow:
mask_pred, last_feat = mask_head(
mask_feats, last_feat)
else:
mask_pred = mask_head(mask_feats)
aug_masks.append(mask_pred.sigmoid().cpu().numpy())
aug_img_metas.append(img_meta)
merged_masks = merge_aug_masks(aug_masks, aug_img_metas,
self.models[0].test_cfg)
ori_shape = img_metas[0][0]['ori_shape']
segm_result = self.models[0].mask_head[-1].get_seg_masks(
merged_masks,
det_bboxes,
det_labels,
rcnn_test_cfg,
ori_shape,
scale_factor=1.0,
rescale=False)
return bbox_result, segm_result
else:
return bbox_result
def _get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False):
"""Transform outputs for a single batch item into labeled boxes.
Args:
cls_scores (list[Tensor]): Box scores for a single scale level
Has shape (num_anchors * num_classes, H, W).
bbox_preds (list[Tensor]): Box energies / deltas for a single
scale level with shape (num_anchors * 4, H, W).
centernesses (list[Tensor]): Centerness for a single scale level
Has shape (num_anchors * 1, H, W).
mlvl_anchors (list[Tensor]): Box reference for a single scale level
with shape (num_total_anchors, 4).
img_shape (tuple[int]): Shape of the input image,
(height, width, 3).
scale_factor (ndarray): Scale factor of the image arange as
(w_scale, h_scale, w_scale, h_scale).
cfg (mmcv.Config | None): Test / postprocessing configuration,
if None, test_cfg would be used.
rescale (bool): If True, return boxes in original image space.
Default: False.
Returns:
tuple(Tensor):
det_bboxes (Tensor): BBox predictions in shape (n, 5), where
the first 4 columns are bounding box positions
(tl_x, tl_y, br_x, br_y) and the 5-th column is a score
between 0 and 1.
det_labels (Tensor): A (n,) tensor where each item is the
predicted class label of the corresponding box.
"""
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, anchors in zip(
cls_scores, bbox_preds, centernesses, mlvl_anchors):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = self.bbox_coder.decode(anchors,
bbox_pred,
max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
def aug_test(self, features, proposal_list, img_metas, rescale=False):
"""Test with augmentations.
If rescale is False, then returned bboxes and masks will fit the scale
of imgs[0].
"""
rcnn_test_cfg = self.test_cfg
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(features, img_metas):
# only one image in the batch
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
flip_direction = img_meta[0]['flip_direction']
proposals = bbox_mapping(proposal_list[0][:, :4], img_shape,
scale_factor, flip, flip_direction)
# "ms" in variable names means multi-stage
ms_scores = []
rois = bbox2roi([proposals])
for i in range(self.num_stages):
bbox_results = self._bbox_forward(i, x, rois)
ms_scores.append(bbox_results['cls_score'])
if i < self.num_stages - 1:
bbox_label = bbox_results['cls_score'][:, :-1].argmax(
dim=1)
rois = self.bbox_head[i].regress_by_class(
rois, bbox_label, bbox_results['bbox_pred'],
img_meta[0])
cls_score = sum(ms_scores) / float(len(ms_scores))
bboxes, scores = self.bbox_head[-1].get_bboxes(
rois,
cls_score,
bbox_results['bbox_pred'],
img_shape,
scale_factor,
rescale=False,
cfg=None)
aug_bboxes.append(bboxes)
aug_scores.append(scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = merge_aug_bboxes(
aug_bboxes, aug_scores, img_metas, rcnn_test_cfg)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
rcnn_test_cfg.score_thr,
rcnn_test_cfg.nms,
rcnn_test_cfg.max_per_img)
bbox_result = bbox2result(det_bboxes, det_labels,
self.bbox_head[-1].num_classes)
if self.with_mask:
if det_bboxes.shape[0] == 0:
segm_result = [[[]
for _ in range(self.mask_head[-1].num_classes)]
]
else:
aug_masks = []
aug_img_metas = []
for x, img_meta in zip(features, img_metas):
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
flip_direction = img_meta[0]['flip_direction']
_bboxes = bbox_mapping(det_bboxes[:, :4], img_shape,
scale_factor, flip, flip_direction)
mask_rois = bbox2roi([_bboxes])
for i in range(self.num_stages):
mask_results = self._mask_forward(i, x, mask_rois)
aug_masks.append(
mask_results['mask_pred'].sigmoid().cpu().numpy())
aug_img_metas.append(img_meta)
merged_masks = merge_aug_masks(aug_masks, aug_img_metas,
self.test_cfg)
ori_shape = img_metas[0][0]['ori_shape']
segm_result = self.mask_head[-1].get_seg_masks(
merged_masks,
det_bboxes,
det_labels,
rcnn_test_cfg,
ori_shape,
scale_factor=1.0,
rescale=False)
return [(bbox_result, segm_result)]
else:
return [bbox_result]
def aug_test(self, imgs, img_metas, proposals=None, rescale=False):
"""Test with augmentations.
If rescale is False, then returned bboxes and masks will fit the scale
of imgs[0].
"""
# recompute feats to save memory
proposal_list = self.aug_test_rpn(self.extract_feats(imgs), img_metas,
self.test_cfg.rpn)
rcnn_test_cfg = self.test_cfg.rcnn
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(self.extract_feats(imgs), img_metas):
# only one image in the batch
img_shape = img_metas[0]['img_shape']
scale_factor = img_metas[0]['scale_factor']
flip = img_metas[0]['flip']
proposals = bbox_mapping(proposal_list[0][:, :4], img_shape,
scale_factor, flip)
# "ms" in variable names means multi-stage
ms_scores = []
rois = bbox2roi([proposals])
for i in range(self.num_stages):
bbox_roi_extractor = self.bbox_roi_extractor[i]
bbox_head = self.bbox_head[i]
bbox_feats = bbox_roi_extractor(
x[:len(bbox_roi_extractor.featmap_strides)], rois)
if self.with_shared_head:
bbox_feats = self.shared_head(bbox_feats)
cls_score, bbox_pred = bbox_head(bbox_feats)
ms_scores.append(cls_score)
if i < self.num_stages - 1:
bbox_label = cls_score.argmax(dim=1)
rois = bbox_head.regress_by_class(rois, bbox_label,
bbox_pred, img_metas[0])
cls_score = sum(ms_scores) / float(len(ms_scores))
bboxes, scores = self.bbox_head[-1].get_det_bboxes(rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=False,
cfg=None)
aug_bboxes.append(bboxes)
aug_scores.append(scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = merge_aug_bboxes(
aug_bboxes, aug_scores, img_metas, rcnn_test_cfg)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
rcnn_test_cfg.score_thr,
rcnn_test_cfg.nms,
rcnn_test_cfg.max_per_img)
bbox_result = bbox2result(det_bboxes, det_labels,
self.bbox_head[-1].num_classes)
if self.with_mask:
if det_bboxes.shape[0] == 0:
segm_result = [[]
for _ in range(self.mask_head[-1].num_classes -
1)]
else:
aug_masks = []
aug_img_metas = []
for x, img_meta in zip(self.extract_feats(imgs), img_metas):
img_shape = img_metas[0]['img_shape']
scale_factor = img_metas[0]['scale_factor']
flip = img_metas[0]['flip']
_bboxes = bbox_mapping(det_bboxes[:, :4], img_shape,
scale_factor, flip)
mask_rois = bbox2roi([_bboxes])
for i in range(self.num_stages):
mask_feats = self.mask_roi_extractor[i](
x[:len(self.mask_roi_extractor[i].featmap_strides
)], mask_rois)
if self.with_shared_head:
mask_feats = self.shared_head(mask_feats)
mask_pred = self.mask_head[i](mask_feats)
aug_masks.append(mask_pred.sigmoid().cpu().numpy())
aug_img_metas.append(img_meta)
merged_masks = merge_aug_masks(aug_masks, aug_img_metas,
self.test_cfg.rcnn)
ori_shape = img_metas[0][0]['ori_shape']
segm_result = self.mask_head[-1].get_seg_masks(
merged_masks,
det_bboxes,
det_labels,
rcnn_test_cfg,
ori_shape,
scale_factor=1.0,
rescale=False)
return bbox_result, segm_result
else:
return bbox_result
def _bbox_post_process(self,
mlvl_scores,
mlvl_bboxes,
scale_factor,
cfg,
rescale=False,
with_nms=True,
mlvl_score_factors=None,
**kwargs):
"""bbox post-processing method.
The boxes would be rescaled to the original image scale and do
the nms operation. Usually with_nms is False is used for aug test.
Args:
mlvl_scores (list[Tensor]): Box scores from all scale
levels of a single image, each item has shape
(num_bboxes, num_class).
mlvl_bboxes (list[Tensor]): Decoded bboxes from all scale
levels of a single image, each item has shape (num_bboxes, 4).
scale_factor (ndarray, optional): Scale factor of the image arange
as (w_scale, h_scale, w_scale, h_scale).
cfg (mmcv.Config): Test / postprocessing configuration,
if None, test_cfg would be used.
rescale (bool): If True, return boxes in original image space.
Default: False.
with_nms (bool): If True, do nms before return boxes.
Default: True.
mlvl_score_factors (list[Tensor], optional): Score factor from
all scale levels of a single image, each item has shape
(num_bboxes, ). Default: None.
Returns:
tuple[Tensor]: Results of detected bboxes and labels. If with_nms
is False and mlvl_score_factor is None, return mlvl_bboxes and
mlvl_scores, else return mlvl_bboxes, mlvl_scores and
mlvl_score_factor. Usually with_nms is False is used for aug
test. If with_nms is True, then return the following format
- det_bboxes (Tensor): Predicted bboxes with shape \
[num_bboxes, 5], where the first 4 columns are bounding \
box positions (tl_x, tl_y, br_x, br_y) and the 5-th \
column are scores between 0 and 1.
- det_labels (Tensor): Predicted labels of the corresponding \
box with shape [num_bboxes].
"""
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
mlvl_iou_preds = torch.cat(mlvl_score_factors)
mlvl_nms_scores = (mlvl_scores * mlvl_iou_preds[:, None]).sqrt()
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes,
mlvl_nms_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=None)
if self.with_score_voting and len(det_bboxes) > 0:
det_bboxes, det_labels = self.score_voting(det_bboxes, det_labels,
mlvl_bboxes,
mlvl_nms_scores,
cfg.score_thr)
return det_bboxes, det_labels
def _get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_anchors,
mlvl_masks,
img_shape,
scale_factor,
cfg,
rescale=False):
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, anchors, mask in zip(cls_scores, bbox_preds,
mlvl_anchors,
mlvl_masks):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
# if no location is kept, end.
if mask.sum() == 0:
continue
# reshape scores and bbox_pred
cls_score = cls_score.permute(1, 2,
0).reshape(-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
# filter scores, bbox_pred w.r.t. mask.
# anchors are filtered in get_anchors() beforehand.
scores = scores[mask, :]
bbox_pred = bbox_pred[mask, :]
if scores.dim() == 0:
anchors = anchors.unsqueeze(0)
scores = scores.unsqueeze(0)
bbox_pred = bbox_pred.unsqueeze(0)
# filter anchors, bbox_pred, scores w.r.t. scores
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
# remind that we set FG labels to [0, num_class-1]
# since mmdet v2.0
# BG cat_id: num_class
max_scores, _ = scores[:, :-1].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = self.bbox_coder.decode(anchors,
bbox_pred,
max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
if self.use_sigmoid_cls:
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
# multi class NMS
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
def _get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False,
nms=True):
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
for i_lvl, (cls_score, bbox_pred, points) in enumerate(
zip(cls_scores, bbox_preds, mlvl_points)):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
cls_score = cls_score.permute(1, 2,
0).reshape(-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
# remind that we set FG labels to [0, num_class-1]
# since mmdet v2.0
# BG cat_id: num_class
max_scores, _ = scores[:, :-1].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bbox_pos_center = torch.cat([points[:, :2], points[:, :2]], dim=1)
bboxes = bbox_pred * self.point_strides[i_lvl] + bbox_pos_center
x1 = bboxes[:, 0].clamp(min=0, max=img_shape[1])
y1 = bboxes[:, 1].clamp(min=0, max=img_shape[0])
x2 = bboxes[:, 2].clamp(min=0, max=img_shape[1])
y2 = bboxes[:, 3].clamp(min=0, max=img_shape[0])
bboxes = torch.stack([x1, y1, x2, y2], dim=-1)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
if self.use_sigmoid_cls:
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
if nms:
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
else:
return mlvl_bboxes, mlvl_scores
def get_bboxes_single(self, results_raw, scale_factor, cfg, rescale=False):
assert len(results_raw) == self.num_scales
multi_lvl_bboxes = []
multi_lvl_cls_scores = []
multi_lvl_conf_scores = []
for i_scale in range(self.num_scales):
result_raw = results_raw[i_scale]
num_grid_h = result_raw.size(1)
num_grid_w = result_raw.size(2)
# (anchors*(cxcywh+conf+class), h, w ) -- > (anchors, h, w, cxcywh+conf+class)
prediction_raw = result_raw.view(self.num_anchors_per_scale,
self.num_attrib,
num_grid_h, num_grid_w).permute(
0, 2, 3, 1).contiguous()
# grid x y offset, with stride step included
stride = self.anchor_strides[i_scale]
grid_x, grid_y = self._get_anchors_grid_xy(num_grid_h, num_grid_w,
stride,
result_raw.device)
# Get outputs x, y
x_center_pred = torch.sigmoid(
prediction_raw[..., 0]) * stride + grid_x # Center x
y_center_pred = torch.sigmoid(
prediction_raw[..., 1]) * stride + grid_y # Center y
anchors = torch.tensor(self.anchor_base_sizes[i_scale],
device=result_raw.device,
dtype=torch.float32)
anchor_w = anchors[:, 0:1].view((-1, 1, 1))
anchor_h = anchors[:, 1:2].view((-1, 1, 1))
w_pred = torch.exp(prediction_raw[..., 2]) * anchor_w # Width
h_pred = torch.exp(prediction_raw[..., 3]) * anchor_h # Height
x1_pred = x_center_pred - w_pred / 2
y1_pred = y_center_pred - h_pred / 2
x2_pred = x_center_pred + w_pred / 2
y2_pred = y_center_pred + h_pred / 2
bbox_pred = torch.stack((x1_pred, y1_pred, x2_pred, y2_pred),
dim=3).view((-1, 4)) # cxcywh
conf_pred = torch.sigmoid(prediction_raw[..., 4]).view(-1) # Conf
if self.hierarchical_label:
cls_pred = self.loss_cls.parase_output(prediction_raw[..., 5:])
else:
cls_pred = torch.sigmoid(prediction_raw[..., 5:]).view(
-1, self.num_classes_no_bkg) # Cls pred one-hot.
conf_thr = cfg.get('conf_thr', -1)
conf_inds = conf_pred.ge(conf_thr).nonzero().flatten()
bbox_pred = bbox_pred[conf_inds, :]
cls_pred = cls_pred[conf_inds, :]
conf_pred = conf_pred[conf_inds]
nms_pre = cfg.get('nms_pre', -1)
if 0 < nms_pre < conf_pred.size(0):
_, topk_inds = conf_pred.topk(nms_pre)
bbox_pred = bbox_pred[topk_inds, :]
cls_pred = cls_pred[topk_inds, :]
conf_pred = conf_pred[topk_inds]
multi_lvl_bboxes.append(bbox_pred)
multi_lvl_cls_scores.append(cls_pred)
multi_lvl_conf_scores.append(conf_pred)
multi_lvl_bboxes = torch.cat(multi_lvl_bboxes)
multi_lvl_cls_scores = torch.cat(multi_lvl_cls_scores)
multi_lvl_conf_scores = torch.cat(multi_lvl_conf_scores)
if multi_lvl_conf_scores.size(0) == 0:
return torch.zeros((0, 5)), torch.zeros((0, ))
if rescale:
multi_lvl_bboxes /= multi_lvl_bboxes.new_tensor(scale_factor)
padding = multi_lvl_cls_scores.new_zeros(multi_lvl_cls_scores.shape[0],
1)
multi_lvl_cls_scores = torch.cat([padding, multi_lvl_cls_scores],
dim=1)
det_bboxes, det_labels = multiclass_nms(
multi_lvl_bboxes,
multi_lvl_cls_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=multi_lvl_conf_scores)
return det_bboxes, det_labels
def _get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False,
with_nms=True):
"""Transform outputs for a single batch item into labeled boxes.
Args:
cls_scores (list[Tensor]): Box scores for a single scale level
has shape (num_classes, H, W).
bbox_preds (list[Tensor]): Box distribution logits for a single
scale level with shape (4*(n+1), H, W), n is max value of
integral set.
mlvl_anchors (list[Tensor]): Box reference for a single scale level
with shape (num_total_anchors, 4).
img_shape (tuple[int]): Shape of the input image,
(height, width, 3).
scale_factor (ndarray): Scale factor of the image arange as
(w_scale, h_scale, w_scale, h_scale).
cfg (mmcv.Config | None): Test / postprocessing configuration,
if None, test_cfg would be used.
rescale (bool): If True, return boxes in original image space.
Default: False.
with_nms (bool): If True, do nms before return boxes.
Default: True.
Returns:
tuple(Tensor):
det_bboxes (Tensor): Bbox predictions in shape (N, 5), where
the first 4 columns are bounding box positions
(tl_x, tl_y, br_x, br_y) and the 5-th column is a score
between 0 and 1.
det_labels (Tensor): A (N,) tensor where each item is the
predicted class label of the corresponding box.
"""
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, stride, anchors in zip(
cls_scores, bbox_preds, self.anchor_generator.strides,
mlvl_anchors):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
assert stride[0] == stride[1]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0)
if self.use_dfl:
bbox_pred = self.integral(bbox_pred) * stride[0]
else:
bbox_pred = bbox_pred.reshape( (-1,4) ) * stride[0]
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = scores.max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = distance2bbox(
self.anchor_center(anchors), bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
if with_nms:
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
else:
return mlvl_bboxes, mlvl_scores
def single_gpu_test(args, cfg, model):
testImgList = os.listdir(args.testImgpath)
for imgfile in testImgList:
imgfile = imgfile.strip()
img = Image.open(os.path.join(args.testImgpath, imgfile))
image = img.convert('RGB')
img = np.array(image)
width, height, channel = img.shape
rows = int(math.ceil(1.0 * (width - args.cropsize) / args.stride)) + 1
cols = int(math.ceil(1.0 * (height - args.cropsize) / args.stride)) + 1
multi_bboxes = list()
multi_scores = list()
for row in range(rows):
if width > args.cropsize:
y_start = min(row * args.stride, width - args.cropsize)
y_end = y_start + args.cropsize
else:
y_start = 0
y_end = width
for col in range(cols):
if height > args.cropsize:
x_start = min(col * args.stride, height - args.cropsize)
x_end = x_start + args.cropsize
else:
x_start = 0
x_end = height
subimg = copy.deepcopy(img[y_start:y_end, x_start:x_end, :])
w, h, c = np.shape(subimg)
outimg = np.zeros((args.cropsize, args.cropsize, 3))
outimg[0:w, 0:h, :] = subimg
result = inference_detector(model, outimg) #15
bboxes = np.vstack(result)
labels = [ #0-15
np.full(bbox.shape[0], i + 1, dtype=np.int32)
for i, bbox in enumerate(result)
]
labels = np.concatenate(labels)
if len(bboxes) > 0:
bboxes[:, :4] += [x_start, y_start, x_start, y_start]
multi_bboxes.append(bboxes[:, :4])
scores = np.zeros(
(bboxes.shape[0], len(ODAI_LABEL_MAP.keys()))) #0-15
for i, j in zip(range(bboxes.shape[0]), labels):
scores[i, j] = bboxes[i, 4]
multi_scores.append(scores)
crop_num = len(multi_bboxes)
if crop_num > 0:
multi_bboxes = np.vstack(multi_bboxes)
multi_scores = np.vstack(multi_scores)
multi_bboxes = torch.Tensor(multi_bboxes)
multi_scores = torch.Tensor(multi_scores)
score_thr = 0.1
nms = dict(type='nms', iou_thr=0.5)
max_per_img = 2000
det_bboxes, det_labels = multiclass_nms(multi_bboxes, multi_scores,
score_thr, nms,
max_per_img)
if det_bboxes.shape[0] > 0:
det_bboxes = np.array(det_bboxes)
det_labels = np.array(det_labels) #0-14
image = draw_boxes_with_label_and_scores(
img, det_bboxes[:, :4], det_bboxes[:, 4], det_labels, 0)
image.save(os.path.join(args.saveImgpath, imgfile))
CLASS_DOTA = ODAI_LABEL_MAP.keys()
LABEl_NAME_MAP = get_label_name_map()
write_handle_r = {}
osp(args.saveTxtpath)
for sub_class in CLASS_DOTA:
if sub_class == 'back-ground':
continue
write_handle_r[sub_class] = open(
os.path.join(args.saveTxtpath,
'Task2_%s.txt' % sub_class), 'a+')
"""
:det_bboxes: format [x_c, y_c, w, h, theta, score]
:det_labels: [label]
"""
boxes = []
for rect in det_bboxes[:, :4]:
boxes.append([rect[0], rect[1], rect[2], rect[3]])
rboxes = np.array(boxes, dtype=np.float32)
for i, rbox in enumerate(rboxes):
command = '%s %.5f %.5f %.5f %.5f %.5f\n' % (
imgfile[:-4], det_bboxes[i, 4], rbox[0], rbox[1],
rbox[2], rbox[3])
write_handle_r[LABEl_NAME_MAP[int(det_labels[i]) +
1]].write(command)
for sub_class in CLASS_DOTA:
if sub_class == 'back-ground':
continue
write_handle_r[sub_class].close()
def aug_test(self,
imgs,
img_metas,
templates,
proposals=None,
rescale=False):
"""Test with augmentations.
If rescale is False, then returned bboxes will fit the scale
of imgs[0].
"""
# recompute feats to save memory
#y = self.extract_feats(imgs, templates)
proposal_list = self.aug_test_rpn(self.extract_feats(imgs, templates),
img_metas, self.test_cfg.rpn)
rcnn_test_cfg = self.test_cfg.rcnn
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(self.extract_feats(imgs, templates), img_metas):
# only one image in the batch
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
proposals = bbox_mapping(proposal_list[0][:, :4], img_shape,
scale_factor, flip)
# "ms" in variable names means multi-stage
ms_scores = []
rois = bbox2roi([proposals])
for i in range(self.num_stages):
bbox_head = self.bbox_head[i]
cls_score, bbox_pred = self._bbox_forward_test(i, x, rois)
ms_scores.append(cls_score)
if i < self.num_stages - 1:
bbox_label = cls_score.argmax(dim=1)
rois = bbox_head.regress_by_class(rois, bbox_label,
bbox_pred, img_meta[0])
cls_score = sum(ms_scores) / float(len(ms_scores))
bboxes, scores = self.bbox_head[-1].get_det_bboxes(rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=False,
cfg=None)
aug_bboxes.append(bboxes)
aug_scores.append(scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = merge_aug_bboxes(
aug_bboxes, aug_scores, img_metas, rcnn_test_cfg)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
rcnn_test_cfg.score_thr,
rcnn_test_cfg.nms,
rcnn_test_cfg.max_per_img)
bbox_result = bbox2result(det_bboxes, det_labels,
self.bbox_head[-1].num_classes)
return bbox_result
def _get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False,
with_nms=True):
"""Transform outputs for a single batch item into bbox predictions.
Args:
cls_scores (list[Tensor]): Box iou-aware scores for a single scale
level with shape (num_points * num_classes, H, W).
bbox_preds (list[Tensor]): Box offsets for a single scale
level with shape (num_points * 4, H, W).
mlvl_points (list[Tensor]): Box reference for a single scale level
with shape (num_total_points, 4).
img_shape (tuple[int]): Shape of the input image,
(height, width, 3).
scale_factor (ndarray): Scale factor of the image arrange as
(w_scale, h_scale, w_scale, h_scale).
cfg (mmcv.Config | None): Test / postprocessing configuration,
if None, test_cfg would be used.
rescale (bool): If True, return boxes in original image space.
Default: False.
with_nms (bool): If True, do nms before returning boxes.
Default: True.
Returns:
tuple(Tensor):
det_bboxes (Tensor): BBox predictions in shape (n, 5), where
the first 4 columns are bounding box positions
(tl_x, tl_y, br_x, br_y) and the 5-th column is a score
between 0 and 1.
det_labels (Tensor): A (n,) tensor where each item is the
predicted class label of the corresponding box.
"""
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, points in zip(cls_scores, bbox_preds,
mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).contiguous().sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).contiguous()
nms_pre = cfg.get('nms_pre', -1)
if 0 < nms_pre < scores.shape[0]:
max_scores, _ = scores.max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
if with_nms:
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
else:
return mlvl_bboxes, mlvl_scores
def get_bboxes(self,
rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=False,
cfg=None):
"""Transform network output for a batch into bbox predictions.
Args:
rois (Tensor): Boxes to be transformed. Has shape (num_boxes, 5).
last dimension 5 arrange as (batch_index, x1, y1, x2, y2).
cls_score (Tensor): Box scores, has shape
(num_boxes, num_classes + 1).
bbox_pred (Tensor, optional): Box energies / deltas.
has shape (num_boxes, num_classes * 4).
img_shape (Sequence[int], optional): Maximum bounds for boxes,
specifies (H, W, C) or (H, W).
scale_factor (ndarray): Scale factor of the
image arrange as (w_scale, h_scale, w_scale, h_scale).
rescale (bool): If True, return boxes in original image space.
Default: False.
cfg (obj:`ConfigDict`): `test_cfg` of Bbox Head. Default: None
Returns:
tuple[Tensor, Tensor]:
Fisrt tensor is `det_bboxes`, has the shape
(num_boxes, 5) and last
dimension 5 represent (tl_x, tl_y, br_x, br_y, score).
Second tensor is the labels with shape (num_boxes, ).
"""
# some loss (Seesaw loss..) may have custom activation
if self.custom_cls_channels:
scores = self.loss_cls.get_activation(cls_score)
else:
scores = F.softmax(cls_score,
dim=-1) if cls_score is not None else None
# bbox_pred would be None in some detector when with_reg is False,
# e.g. Grid R-CNN.
if bbox_pred is not None:
bboxes = self.bbox_coder.decode(rois[..., 1:],
bbox_pred,
max_shape=img_shape)
else:
bboxes = rois[:, 1:].clone()
if img_shape is not None:
bboxes[:, [0, 2]].clamp_(min=0, max=img_shape[1])
bboxes[:, [1, 3]].clamp_(min=0, max=img_shape[0])
if rescale and bboxes.size(0) > 0:
scale_factor = bboxes.new_tensor(scale_factor)
bboxes = (bboxes.view(bboxes.size(0), -1, 4) / scale_factor).view(
bboxes.size()[0], -1)
if cfg is None:
return bboxes, scores
else:
det_bboxes, det_labels = multiclass_nms(bboxes, scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
def get_bboxes_single(self,
cls_scores,
bbox_cls_preds,
bbox_reg_preds,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False):
cfg = self.test_cfg if cfg is None else cfg
mlvl_bboxes = []
mlvl_scores = []
mlvl_confids = []
assert len(cls_scores) == len(bbox_cls_preds) == len(
bbox_reg_preds) == len(mlvl_anchors)
for cls_score, bbox_cls_pred, bbox_reg_pred, anchors in zip(
cls_scores, bbox_cls_preds, bbox_reg_preds, mlvl_anchors):
assert cls_score.size()[-2:] == bbox_cls_pred.size(
)[-2:] == bbox_reg_pred.size()[-2::]
cls_score = cls_score.permute(1, 2,
0).reshape(-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_cls_pred = bbox_cls_pred.permute(1, 2, 0).reshape(
-1, self.side_num * 4)
bbox_reg_pred = bbox_reg_pred.permute(1, 2, 0).reshape(
-1, self.side_num * 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
max_scores, _ = scores[:, :-1].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_cls_pred = bbox_cls_pred[topk_inds, :]
bbox_reg_pred = bbox_reg_pred[topk_inds, :]
scores = scores[topk_inds, :]
bbox_preds = [
bbox_cls_pred.contiguous(),
bbox_reg_pred.contiguous()
]
bboxes, confids = self.bbox_coder.decode(
anchors.contiguous(), bbox_preds, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_confids.append(confids)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
mlvl_confids = torch.cat(mlvl_confids)
if self.use_sigmoid_cls:
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_confids)
return det_bboxes, det_labels
def get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_anchors,
mlvl_masks,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, anchors, mask in zip(cls_scores, bbox_preds,
mlvl_anchors,
mlvl_masks):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
# if no centeration is kept, end.
if mask.sum() == 0:
continue
# reshape scores and bbox_pred
cls_score = cls_score.permute(1, 2,
0).reshape(-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
# filter scores, bbox_pred w.r.t. mask.
# anchors are filtered in get_anchors() beforehand.
scores = scores[mask, :]
bbox_pred = bbox_pred[mask, :]
if scores.dim() == 0:
anchors = anchors.unsqueeze(0)
scores = scores.unsqueeze(0)
bbox_pred = bbox_pred.unsqueeze(0)
# filter anchors, bbox_pred, scores w.r.t. scores
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
max_scores, _ = scores[:, 1:].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = delta2bbox(anchors, bbox_pred, self.target_means,
self.target_stds, img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
if self.use_sigmoid_cls:
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
# multi class NMS
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
def aug_test(self, imgs, img_metas, rescale=False, **kwargs):
"""
Test with augmentations.
If rescale is False, then returned bboxes and masks will fit the scale
of imgs[0].
"""
rpn_test_cfg = self.models[0].test_cfg.rpn
rcnn_test_cfg = self.models[0].test_cfg.rcnn
# For each model, compute detections
aug_bboxes = []
aug_scores = []
aug_img_metas = []
for model in self.models:
for x, img_meta in zip(model.extract_feats(imgs), img_metas):
proposal_list = model.simple_test_rpn(x, img_meta,
rpn_test_cfg)
_, semantic_feat = model.semantic_head(x)
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
ms_scores = []
rois = bbox2roi(proposal_list)
for i in range(model.num_stages):
bbox_head = model.bbox_head[i]
cls_score, bbox_pred = model._bbox_forward_test(
i, x, rois, semantic_feat=semantic_feat)
ms_scores.append(cls_score)
if i < model.num_stages - 1:
bbox_label = cls_score.argmax(dim=1)
rois = bbox_head.regress_by_class(
rois, bbox_label, bbox_pred, img_meta[0])
cls_score = sum(ms_scores) / float(len(ms_scores))
bboxes, scores = model.bbox_head[-1].get_det_bboxes(
rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=False,
cfg=None)
aug_bboxes.append(bboxes)
aug_scores.append(scores)
aug_img_metas.append(img_meta)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = merge_aug_bboxes(aug_bboxes,
aug_scores,
aug_img_metas,
rcnn_test_cfg,
type='concat')
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
rcnn_test_cfg.score_thr,
rcnn_test_cfg.nms,
rcnn_test_cfg.max_per_img)
bbox_result = bbox2result(det_bboxes, det_labels,
self.models[0].bbox_head[-1].num_classes)
if self.models[0].with_mask:
if det_bboxes.shape[0] == 0:
segm_result = [
[]
for _ in range(self.models[0].mask_head[-1].num_classes -
1)
]
else:
aug_masks = []
aug_img_metas = []
for model in [self.models[0]]:
for x, img_meta in\
zip(model.extract_feats(imgs), img_metas):
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
img_shape = img_meta[0]['img_shape']
_bboxes = (det_bboxes[:, :4] *
scale_factor if rescale else det_bboxes)
mask_rois = bbox2roi([_bboxes])
mask_roi_extractor = model.mask_roi_extractor[-1]
mask_feats = mask_roi_extractor(
x[:len(mask_roi_extractor.featmap_strides)],
mask_rois)
_, semantic_feat = model.semantic_head(x)
mask_semantic_feat = model.semantic_roi_extractor(
[semantic_feat], mask_rois)
mask_feats += mask_semantic_feat
last_feat = None
for i in range(model.num_stages):
mask_head = model.mask_head[i]
if model.mask_info_flow:
mask_pred, last_feat = mask_head(
mask_feats, last_feat)
else:
mask_pred = mask_head(mask_feats)
aug_masks.append(mask_pred.sigmoid().cpu().numpy())
aug_img_metas.append(img_meta)
merged_masks = merge_aug_masks(aug_masks, aug_img_metas,
rcnn_test_cfg)
ori_shape = img_metas[0][0]['ori_shape']
scale_factor = img_metas[0][0]['scale_factor']
segm_result = self.models[0].mask_head[-1].get_seg_masks(
merged_masks,
det_bboxes,
det_labels,
rcnn_test_cfg,
ori_shape,
scale_factor=1.0,
rescale=rescale)
# compute relations
rel_model = self.models[0]
for x, img_meta in zip(rel_model.extract_feats(imgs),
img_metas):
_, semantic_feat = rel_model.semantic_head(x)
filename = img_meta[0]['filename']
im_height, im_width, _ = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
ori_shape = img_meta[0]['ori_shape']
relation_preds = rel_model._rel_forward_test(
x,
det_bboxes,
det_labels,
merged_masks,
scale_factor,
ori_shape,
semantic_feat=semantic_feat,
im_width=im_width,
im_height=im_height)
if rel_model.rel_save_folder is not None:
np.save(
os.path.join(rel_model.rel_save_folder,
filename + '.npy'), relation_preds)
return bbox_result, segm_result
else:
return bbox_result
def _get_bboxes_single(self,
cls_score_list,
bbox_pred_list,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False,
with_nms=True):
"""Transform outputs for a single batch item into bbox predictions.
Args:
cls_score_list (list[Tensor]): Box scores for a single scale level
Has shape (num_anchors * num_classes, H, W).
bbox_pred_list (list[Tensor]): Box energies / deltas for a single
scale level with shape (num_anchors * 4, H, W).
mlvl_anchors (list[Tensor]): Box reference for a single scale level
with shape (num_total_anchors, 4).
img_shape (tuple[int]): Shape of the input image,
(height, width, 3).
scale_factor (ndarray): Scale factor of the image arange as
(w_scale, h_scale, w_scale, h_scale).
cfg (mmcv.Config): Test / postprocessing configuration,
if None, test_cfg would be used.
rescale (bool): If True, return boxes in original image space.
Default: False.
with_nms (bool): If True, do nms before return boxes.
Default: True.
Returns:
Tensor: Labeled boxes in shape (n, 5), where the first 4 columns
are bounding box positions (tl_x, tl_y, br_x, br_y) and the
5-th column is a score between 0 and 1.
"""
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_score_list) == len(bbox_pred_list) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, anchors in zip(cls_score_list,
bbox_pred_list, mlvl_anchors):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
cls_score = cls_score.permute(1, 2,
0).reshape(-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
# Get maximum scores for foreground classes.
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
# remind that we set FG labels to [0, num_class-1]
# since mmdet v2.0
# BG cat_id: num_class
max_scores, _ = scores[:, :-1].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = self.bbox_coder.decode(anchors,
bbox_pred,
max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
if self.use_sigmoid_cls:
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
if with_nms:
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
else:
return mlvl_bboxes, mlvl_scores
def _get_bboxes_single(self,
pred_maps_list,
scale_factor,
cfg,
rescale=False,
with_nms=True):
"""Transform outputs for a single batch item into bbox predictions.
Args:
pred_maps_list (list[Tensor]): Prediction maps for different scales
of each single image in the batch.
scale_factor (ndarray): Scale factor of the image arrange as
(w_scale, h_scale, w_scale, h_scale).
cfg (mmcv.Config | None): Test / postprocessing configuration,
if None, test_cfg would be used.
rescale (bool): If True, return boxes in original image space.
Default: False.
with_nms (bool): If True, do nms before return boxes.
Default: True.
Returns:
tuple(Tensor):
det_bboxes (Tensor): BBox predictions in shape (n, 5), where
the first 4 columns are bounding box positions
(tl_x, tl_y, br_x, br_y) and the 5-th column is a score
between 0 and 1.
det_labels (Tensor): A (n,) tensor where each item is the
predicted class label of the corresponding box.
"""
cfg = self.test_cfg if cfg is None else cfg
assert len(pred_maps_list) == self.num_levels
multi_lvl_bboxes = []
multi_lvl_cls_scores = []
multi_lvl_conf_scores = []
num_levels = len(pred_maps_list)
featmap_sizes = [
pred_maps_list[i].shape[-2:] for i in range(num_levels)
]
multi_lvl_anchors = self.anchor_generator.grid_anchors(
featmap_sizes, pred_maps_list[0][0].device)
for i in range(self.num_levels):
# get some key info for current scale
pred_map = pred_maps_list[i]
stride = self.featmap_strides[i]
# (h, w, num_anchors*num_attrib) -> (h*w*num_anchors, num_attrib)
pred_map = pred_map.permute(1, 2, 0).reshape(-1, self.num_attrib)
pred_map[..., :2] = torch.sigmoid(pred_map[..., :2])
bbox_pred = self.bbox_coder.decode(multi_lvl_anchors[i],
pred_map[..., :4], stride)
# conf and cls
conf_pred = torch.sigmoid(pred_map[..., 4]).view(-1)
cls_pred = torch.sigmoid(pred_map[..., 5:]).view(
-1, self.num_classes) # Cls pred one-hot.
# Filtering out all predictions with conf < conf_thr
conf_thr = cfg.get('conf_thr', -1)
if conf_thr > 0:
# add as_tuple=False for compatibility in Pytorch 1.6
conf_inds = conf_pred.ge(conf_thr).nonzero(
as_tuple=False).flatten()
bbox_pred = bbox_pred[conf_inds, :]
cls_pred = cls_pred[conf_inds, :]
conf_pred = conf_pred[conf_inds]
# Get top-k prediction
nms_pre = cfg.get('nms_pre', -1)
if 0 < nms_pre < conf_pred.size(0):
_, topk_inds = conf_pred.topk(nms_pre)
bbox_pred = bbox_pred[topk_inds, :]
cls_pred = cls_pred[topk_inds, :]
conf_pred = conf_pred[topk_inds]
# Save the result of current scale
multi_lvl_bboxes.append(bbox_pred)
multi_lvl_cls_scores.append(cls_pred)
multi_lvl_conf_scores.append(conf_pred)
# Merge the results of different scales together
multi_lvl_bboxes = torch.cat(multi_lvl_bboxes)
multi_lvl_cls_scores = torch.cat(multi_lvl_cls_scores)
multi_lvl_conf_scores = torch.cat(multi_lvl_conf_scores)
if with_nms and (multi_lvl_conf_scores.size(0) == 0):
return torch.zeros((0, 5)), torch.zeros((0, ))
if rescale:
multi_lvl_bboxes /= multi_lvl_bboxes.new_tensor(scale_factor)
# In mmdet 2.x, the class_id for background is num_classes.
# i.e., the last column.
padding = multi_lvl_cls_scores.new_zeros(multi_lvl_cls_scores.shape[0],
1)
multi_lvl_cls_scores = torch.cat([multi_lvl_cls_scores, padding],
dim=1)
# Support exporting to onnx without nms
if with_nms and cfg.get('nms', None) is not None:
det_bboxes, det_labels = multiclass_nms(
multi_lvl_bboxes,
multi_lvl_cls_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=multi_lvl_conf_scores)
return det_bboxes, det_labels
else:
return (multi_lvl_bboxes, multi_lvl_cls_scores,
multi_lvl_conf_scores)
def _get_bboxes_single(self,
cls_scores,
bbox_preds,
iou_preds,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False,
with_nms=True):
"""Transform outputs for a single batch item into labeled boxes.
This method is almost same as `ATSSHead._get_bboxes_single()`.
We use sqrt(iou_preds * cls_scores) in NMS process instead of just
cls_scores. Besides, score voting is used when `` score_voting``
is set to True.
"""
assert with_nms, 'PAA only supports "with_nms=True" now'
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
mlvl_iou_preds = []
for cls_score, bbox_pred, iou_preds, anchors in zip(
cls_scores, bbox_preds, iou_preds, mlvl_anchors):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
iou_preds = iou_preds.permute(1, 2, 0).reshape(-1).sigmoid()
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * iou_preds[:, None]).sqrt().max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
iou_preds = iou_preds[topk_inds]
bboxes = self.bbox_coder.decode(anchors,
bbox_pred,
max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_iou_preds.append(iou_preds)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
mlvl_iou_preds = torch.cat(mlvl_iou_preds)
mlvl_nms_scores = (mlvl_scores * mlvl_iou_preds[:, None]).sqrt()
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes,
mlvl_nms_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=None)
if self.with_score_voting:
det_bboxes, det_labels = self.score_voting(det_bboxes, det_labels,
mlvl_bboxes,
mlvl_nms_scores,
cfg.score_thr)
return det_bboxes, det_labels
def aug_test(self, features, proposal_list, img_metas, rescale=False):
"""Test with augmentations.
If rescale is False, then returned bboxes and masks will fit the scale
of imgs[0].
"""
rcnn_test_cfg = self.test_cfg
aug_bboxes = []
aug_scores = []
aug_bboxes_tail = []
aug_scores_tail = []
for x, img_meta in zip(features, img_metas):
# only one image in the batch
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
flip_direction = img_meta[0]['flip_direction']
proposals = bbox_mapping(proposal_list[0][:, :4], img_shape,
scale_factor, flip, flip_direction)
# "ms" in variable names means multi-stage
ms_scores = []
ms_scores_tail = []
rois = bbox2roi([proposals])
rois_tail = bbox2roi([proposals])
for i in range(self.num_stages):
bbox_results = self._bbox_forward(i, x, rois)
ms_scores.append(bbox_results['cls_score'])
bbox_results_tail = self._bbox_forward_tail(i, x, rois_tail)
ms_scores_tail.append(bbox_results_tail['cls_score'])
if i < self.num_stages - 1:
bbox_label = bbox_results['cls_score'][:, :-1].argmax(
dim=1)
rois = self.bbox_head[i].regress_by_class(
rois, bbox_label, bbox_results['bbox_pred'],
img_meta[0])
bbox_label_tail = bbox_results_tail[
'cls_score'][:, :-1].argmax(dim=1)
rois_tail = self.bbox_head_tail[i].regress_by_class(
rois_tail, bbox_label_tail,
bbox_results_tail['bbox_pred'], img_meta[0])
cls_score = sum(ms_scores) / float(len(ms_scores))
bboxes, scores = self.bbox_head[-1].get_bboxes(
rois,
cls_score,
bbox_results['bbox_pred'],
img_shape,
scale_factor,
rescale=False,
cfg=None)
# print('a', bboxes.shape, scores.shape)
cls_score_tail = sum(ms_scores_tail) / float(len(ms_scores_tail))
bboxes_tail, scores_tail = self.bbox_head_tail[-1].get_bboxes(
rois_tail,
cls_score_tail,
bbox_results_tail['bbox_pred'],
img_shape,
scale_factor,
rescale=False,
cfg=None)
# print('b', bboxes_tail.shape, scores_tail.shape)
# print(scores_tail)
# print(scores)
# if self.labels is not None:
# inds = []
# for label in self.labels:
# inds.append(torch.nonzero(scores == label, as_tuple=False).squeeze(1))
# inds = torch.cat(inds)
# bboxes = bboxes[inds]
# scores = scores[inds]
# if self.labels_tail is not None:
# inds = []
# for label in self.labels_tail:
# inds.append(torch.nonzero(scores_tail == label, as_tuple=False).squeeze(1))
# inds = torch.cat(inds)
# bboxes_tail = bboxes_tail[inds]
# scores_tail = scores_tail[inds]
# print(bboxes,bboxes.shape)
# print(bboxes_tail, bboxes_tail.shape)
# if bboxes.shape[0] == 0:
# det_bboxes = bboxes_tail
# det_labels = scores_tail
# elif bboxes_tail.shape[0] == 0:
# det_bboxes = bboxes
# det_labels = scores
# else:
# det_bboxes = torch.cat((bboxes, bboxes_tail))
# det_labels = torch.cat((scores, scores_tail))
# aug_bboxes.append(det_bboxes)
# aug_scores.append(det_labels)
# print('c', det_bboxes.shape)
# print('d', det_labels.shape)
det_bboxes = torch.cat((bboxes, bboxes_tail))
det_labels = torch.cat((scores, scores_tail))
aug_bboxes.append(det_bboxes)
aug_scores.append(det_labels)
# aug_bboxes_tail.append(bboxes_tail)
# aug_scores_tail.append(scores_tail)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = merge_aug_bboxes(
aug_bboxes, aug_scores, img_metas, rcnn_test_cfg)
# print('e', merged_bboxes.shape, merged_scores.shape)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
rcnn_test_cfg.score_thr,
rcnn_test_cfg.nms,
rcnn_test_cfg.max_per_img)
# # after merging, bboxes will be rescaled to the original image size
# merged_bboxes_tail, merged_scores_tail = merge_aug_bboxes(
# aug_bboxes_tail, aug_scores_tail, img_metas, rcnn_test_cfg)
# # print('e', merged_bboxes.shape, merged_scores.shape)
# det_bboxes_tail, det_labels_tail = multiclass_nms(merged_bboxes_tail, merged_scores_tail,
# rcnn_test_cfg.score_thr,
# rcnn_test_cfg.nms,
# rcnn_test_cfg.max_per_img)
# if self.labels is not None:
# inds = []
# for label in self.labels:
# inds.append(torch.nonzero(det_labels == label, as_tuple=False).squeeze(1))
# inds = torch.cat(inds)
# det_bboxes_post = det_bboxes[inds]
# det_labels_post = det_labels[inds]
# if self.labels_tail is not None:
# inds = []
# for label in self.labels_tail:
# inds.append(torch.nonzero(det_labels_tail == label, as_tuple=False).squeeze(1))
# inds = torch.cat(inds)
# det_bboxes_tail_post = det_bboxes_tail[inds]
# det_labels_tail_post = det_labels_tail[inds]
# det_bboxes = torch.cat((det_bboxes_post, det_bboxes_tail_post))
# det_labels = torch.cat((det_labels_post, det_labels_tail_post))
bbox_result = bbox2result(det_bboxes, det_labels,
self.bbox_head[-1].num_classes)
if self.with_mask:
if det_bboxes.shape[0] == 0:
segm_result = [[]
for _ in range(self.mask_head[-1].num_classes)]
else:
aug_masks = []
aug_img_metas = []
for x, img_meta in zip(features, img_metas):
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
flip = img_meta[0]['flip']
flip_direction = img_meta[0]['flip_direction']
_bboxes = bbox_mapping(det_bboxes[:, :4], img_shape,
scale_factor, flip, flip_direction)
mask_rois = bbox2roi([_bboxes])
for i in range(self.num_stages):
mask_results = self._mask_forward(i, x, mask_rois)
aug_masks.append(
mask_results['mask_pred'].sigmoid().cpu().numpy())
aug_img_metas.append(img_meta)
merged_masks = merge_aug_masks(aug_masks, aug_img_metas,
self.test_cfg)
ori_shape = img_metas[0][0]['ori_shape']
segm_result = self.mask_head[-1].get_seg_masks(
merged_masks,
det_bboxes,
det_labels,
rcnn_test_cfg,
ori_shape,
scale_factor=1.0,
rescale=False)
return [(bbox_result, segm_result)]
else:
return [bbox_result]
