def simple_test(self,
x,
proposal_list,
img_metas,
proposals=None,
rescale=False):
rois = arb2roi(proposal_list, bbox_type=self.bbox_head.start_bbox_type)
bbox_results = self._bbox_forward(x, rois)
img_shape = img_metas[0]['img_shape']
scale_factor = img_metas[0]['scale_factor']
det_bboxes, det_labels = self.bbox_head.get_bboxes(
rois,
bbox_results['cls_score'],
bbox_results['bbox_pred'],
bbox_results['fix_pred'],
bbox_results['ratio_pred'],
img_shape,
scale_factor,
rescale=rescale,
cfg=self.test_cfg)
bbox_results = arb2result(det_bboxes,
det_labels,
self.bbox_head.num_classes,
bbox_type=self.bbox_head.end_bbox_type)
return bbox_results
def aug_test(self, x, 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_mask:
raise NotImplementedError
# recompute feats to save memory
det_bboxes, det_labels = self.aug_test_bboxes(x, img_metas,
proposal_list,
self.test_cfg)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
scale_factor = _det_bboxes.new_tensor(
img_metas[0][0]['scale_factor'])
if self.bbox_head.end_bbox_type == 'poly':
_det_bboxes[:, :8] *= scale_factor.repeat(2)
else:
_det_bboxes[:, :4] *= scale_factor
bbox_results = arb2result(_det_bboxes, det_labels, self.bbox_head.num_classes,
bbox_type=self.bbox_head.end_bbox_type)
return bbox_results
def simple_test(self,
x,
proposal_list,
img_metas,
proposals=None,
rescale=False):
"""Test without augmentation."""
assert self.with_bbox, 'Bbox head must be implemented.'
det_bboxes, det_labels = self.simple_test_bboxes(
x, img_metas, proposal_list, self.test_cfg, rescale=rescale)
bbox_results = arb2result(det_bboxes, det_labels, self.bbox_head.num_classes,
bbox_type=self.bbox_head.end_bbox_type)
if not self.with_mask:
return bbox_results
else:
segm_results = self.simple_test_mask(
x, img_metas, det_bboxes, det_labels, rescale=rescale)
return bbox_results, segm_results
def simple_test(self, img, img_metas, rescale=False):
"""Test function without test time augmentation
Args:
imgs (list[torch.Tensor]): List of multiple images
img_metas (list[dict]): List of image information.
rescale (bool, optional): Whether to rescale the results.
Defaults to False.
Returns:
np.ndarray: proposals
"""
x = self.extract_feat(img)
outs = self.bbox_head(x)
bbox_list = self.bbox_head.get_bboxes(*outs,
img_metas,
rescale=rescale)
bbox_type = getattr(self.bbox_head, 'bbox_type', 'hbb')
bbox_results = [
arb2result(det_bboxes, det_labels, self.bbox_head.num_classes,
bbox_type) for det_bboxes, det_labels in bbox_list
]
return bbox_results[0]
def simple_test(self, x, proposal_list, img_metas, rescale=False):
"""Test without augmentation."""
assert self.with_bbox, 'Bbox head must be implemented.'
img_shape = img_metas[0]['img_shape']
ori_shape = img_metas[0]['ori_shape']
scale_factor = img_metas[0]['scale_factor']
# "ms" in variable names means multi-stage
ms_scores = []
rcnn_test_cfg = self.test_cfg
rois = arb2roi(proposal_list, bbox_type=self.bbox_head[0].start_bbox_type)
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'].argmax(dim=1)
rois = self.bbox_head[i].regress_by_class(
rois, bbox_label, bbox_results['bbox_pred'], img_metas[0])
score_weights = rcnn_test_cfg.score_weights
assert len(score_weights) == len(ms_scores)
cls_score = sum([w * s for w, s in zip(score_weights, ms_scores)]) \
/ sum(score_weights)
det_bboxes, det_labels = self.bbox_head[-1].get_bboxes(
rois,
cls_score,
bbox_results['bbox_pred'],
img_shape,
scale_factor,
rescale=rescale,
cfg=rcnn_test_cfg)
results = arb2result(det_bboxes, det_labels, self.bbox_head[-1].num_classes,
bbox_type=self.bbox_head[-1].end_bbox_type)
return results
def aug_test(self, features, proposal_list, img_metas, rescale=False):
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']
angle = img_meta[0].get('angle', 0)
matrix = img_meta[0].get('matrix', np.eye(3))
rotate_after_flip = img_meta[0].get('rotate_after_flip', True)
if 'flip' in img_meta[0]:
direction = img_meta[0]['flip_direction']
h_flip = img_meta[0]['flip'] if direction == 'horizontal' else False
v_flip = img_meta[0]['flip'] if direction == 'vertical' else False
else:
h_flip, v_flip = img_meta[0]['h_flip'], img_meta[0]['v_flip']
proposals = hbb_mapping(proposal_list[0][:, :4], img_shape, scale_factor,
h_flip, v_flip, rotate_after_flip, angle, matrix)
# "ms" in variable names means multi-stage
ms_scores = []
rois = arb2roi([proposals], bbox_type=self.bbox_head[0].start_bbox_type)
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'].argmax(dim=1)
rois = self.bbox_head[i].regress_by_class(
rois, bbox_label, bbox_results['bbox_pred'],
img_meta[0])
score_weights = rcnn_test_cfg.score_weights
assert len(score_weights) == len(ms_scores)
cls_score = sum([w * s for w, s in zip(score_weights, ms_scores)]) \
/ sum(score_weights)
cls_score = ms_scores[0]
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
end_bbox_type = self.bbox_head[-1].end_bbox_type
merged_bboxes, merged_scores = merge_rotate_aug_arb(
aug_bboxes, aug_scores, img_metas, rcnn_test_cfg,
merge_type='avg', bbox_type=end_bbox_type)
det_bboxes, det_labels = multiclass_arb_nms(
merged_bboxes, merged_scores, rcnn_test_cfg.score_thr,
rcnn_test_cfg.nms, rcnn_test_cfg.max_per_img,
bbox_type=end_bbox_type)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
scale_factor = _det_bboxes.new_tensor(
img_metas[0][0]['scale_factor'])
if end_bbox_type == 'poly':
_det_bboxes[:, :8] *= scale_factor.repeat(2)
else:
_det_bboxes[:, :4] *= scale_factor
bbox_result = arb2result(
det_bboxes, det_labels, self.bbox_head[-1].num_classes,
bbox_type=self.bbox_head[-1].end_bbox_type)
return bbox_result
def aug_test(self, feats, proposal_list, img_metas, rescale=False):
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
img_shape = img_meta[0]['img_shape']
scale_factor = img_meta[0]['scale_factor']
angle = img_meta[0].get('angle', 0)
matrix = img_meta[0].get('matrix', np.eye(3))
rotate_after_flip = img_meta[0].get('rotate_after_flip', True)
if 'flip' in img_meta[0]:
direction = img_meta[0]['flip_direction']
h_flip = img_meta[0][
'flip'] if direction == 'horizontal' else False
v_flip = img_meta[0][
'flip'] if direction == 'vertical' else False
else:
h_flip, v_flip = img_meta[0]['h_flip'], img_meta[0]['v_flip']
# TODO more flexible
proposals = arb_mapping(proposal_list[0][:, :-1],
img_shape,
scale_factor,
h_flip,
v_flip,
rotate_after_flip,
angle,
matrix,
bbox_type=self.bbox_head.start_bbox_type)
rois = arb2roi([proposals],
bbox_type=self.bbox_head.start_bbox_type)
# recompute feature maps to save GPU memory
bbox_results = self._bbox_forward(x, rois)
bboxes, scores = self.bbox_head.get_bboxes(
rois,
bbox_results['cls_score'],
bbox_results['bbox_pred'],
bbox_results['fix_pred'],
bbox_results['ratio_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_rotate_aug_arb(
aug_bboxes,
aug_scores,
img_metas,
self.test_cfg,
merge_type='avg',
bbox_type=self.bbox_head.end_bbox_type)
det_bboxes, det_labels = multiclass_arb_nms(
merged_bboxes,
merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img,
bbox_type=self.bbox_head.end_bbox_type)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
scale_factor = _det_bboxes.new_tensor(
img_metas[0][0]['scale_factor'])
_det_bboxes[:, :8] *= scale_factor.repeat(2)
bbox_result = arb2result(det_bboxes,
det_labels,
self.bbox_head.num_classes,
bbox_type='poly')
return bbox_result
