def aug_test_bboxes(self, feats, img_metas, rescale=False):
"""Test det bboxes with test time augmentation.
Args:
feats (list[Tensor]): the outer list indicates test-time
augmentations and inner Tensor should have a shape NxCxHxW,
which contains features for all images in the batch.
img_metas (list[list[dict]]): the outer list indicates test-time
augs (multiscale, flip, etc.) and the inner list indicates
images in a batch. each dict has image information.
rescale (bool, optional): Whether to rescale the results.
Defaults to False.
Returns:
list[ndarray]: bbox results of each class
"""
# check with_nms argument
gb_sig = signature(self.get_bboxes)
gb_args = [p.name for p in gb_sig.parameters.values()]
gbs_sig = signature(self._get_bboxes_single)
gbs_args = [p.name for p in gbs_sig.parameters.values()]
assert ('with_nms' in gb_args) and ('with_nms' in gbs_args), \
f'{self.__class__.__name__}' \
' does not support test-time augmentation'
aug_bboxes = []
aug_scores = []
aug_factors = [] # score_factors for NMS
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
outs = self.forward(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
bbox_outputs = self.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(bbox_outputs[0])
aug_scores.append(bbox_outputs[1])
# bbox_outputs of some detectors (e.g., ATSS, FCOS, YOLOv3)
# contains additional element to adjust scores before NMS
if len(bbox_outputs) >= 3:
aug_factors.append(bbox_outputs[2])
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_bboxes(
aug_bboxes, aug_scores, img_metas)
merged_factors = torch.cat(aug_factors, dim=0) if aug_factors else None
det_bboxes, det_labels = multiclass_nms(
merged_bboxes,
merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img,
score_factors=merged_factors)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= det_bboxes.new_tensor(
img_metas[0][0]['scale_factor'])
bbox_results = bbox2result(_det_bboxes, det_labels, self.num_classes)
return bbox_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:
list[list[np.ndarray]]: BBox results of each image and classes.
The outer list corresponds to each image. The inner list
corresponds to each class.
"""
x = self.extract_feat(img)
outs = self.bbox_head(x)
bbox_list = self.bbox_head.get_bboxes(
*outs, img_metas, rescale=rescale)
# skip post-processing when exporting to ONNX
if torch.onnx.is_in_onnx_export():
return bbox_list
bbox_results = [
bbox2result(det_bboxes, det_labels, self.bbox_head.num_classes)
for det_bboxes, det_labels in bbox_list
]
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].
"""
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()
_det_bboxes[:, :4] *= det_bboxes.new_tensor(
img_metas[0][0]['scale_factor'])
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
# det_bboxes always keep the original scale
if self.with_mask:
segm_results = self.aug_test_mask(x, img_metas, det_bboxes,
det_labels)
return [(bbox_results, segm_results)]
else:
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 = [
bbox2result(det_bboxes[i], det_labels[i],
self.bbox_head.num_classes)
for i in range(len(det_bboxes))
]
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 list(zip(bbox_results, segm_results))
async def async_simple_test(self,
x,
proposal_list,
img_metas,
proposals=None,
rescale=False):
"""Async test without augmentation."""
assert self.with_bbox, 'Bbox head must be implemented.'
det_bboxes, det_labels = await self.async_test_bboxes(
x, img_metas, proposal_list, self.test_cfg, rescale=rescale)
bbox_results = bbox2result(det_bboxes, det_labels,
self.bbox_head.num_classes)
if not self.with_mask:
return bbox_results
else:
segm_results = await self.async_test_mask(
x,
img_metas,
det_bboxes,
det_labels,
rescale=rescale,
mask_test_cfg=self.test_cfg.get('mask'))
return bbox_results, segm_results
def aug_test(self, imgs, img_metas, rescale=False):
"""Augment testing of CornerNet.
Args:
imgs (list[Tensor]): Augmented images.
img_metas (list[list[dict]]): Meta information of each image, e.g.,
image size, scaling factor, etc.
rescale (bool): If True, return boxes in original image space.
Default: False.
Note:
``imgs`` must including flipped image pairs.
Returns:
list[list[np.ndarray]]: BBox results of each image and classes.
The outer list corresponds to each image. The inner list
corresponds to each class.
"""
img_inds = list(range(len(imgs)))
assert img_metas[0][0]['flip'] + img_metas[1][0]['flip'], (
'aug test must have flipped image pair')
aug_results = []
for ind, flip_ind in zip(img_inds[0::2], img_inds[1::2]):
img_pair = torch.cat([imgs[ind], imgs[flip_ind]])
x = self.extract_feat(img_pair)
outs = self.bbox_head(x)
bbox_list = self.bbox_head.get_bboxes(
*outs, [img_metas[ind], img_metas[flip_ind]], False, False)
aug_results.append(bbox_list[0])
aug_results.append(bbox_list[1])
bboxes, labels = self.merge_aug_results(aug_results, img_metas)
bbox_results = bbox2result(bboxes, labels, self.bbox_head.num_classes)
return [bbox_results]
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 simple_test(self, x, proposal_list, img_metas, rescale=False):
"""Test without augmentation."""
assert self.with_bbox, 'Bbox head must be implemented.'
num_imgs = len(proposal_list)
img_shapes = tuple(meta['img_shape'] for meta in img_metas)
ori_shapes = tuple(meta['ori_shape'] for meta in img_metas)
scale_factors = tuple(meta['scale_factor'] for meta in img_metas)
# "ms" in variable names means multi-stage
ms_bbox_result = {}
ms_segm_result = {}
ms_scores = []
rcnn_test_cfg = self.test_cfg
rois = bbox2roi(proposal_list)
for i in range(self.num_stages):
bbox_results = self._bbox_forward(i, x, rois)
# split batch bbox prediction back to each image
cls_score = bbox_results['cls_score']
bbox_pred = bbox_results['bbox_pred']
num_proposals_per_img = tuple(
len(proposals) for proposals in proposal_list)
rois = rois.split(num_proposals_per_img, 0)
cls_score = cls_score.split(num_proposals_per_img, 0)
if isinstance(bbox_pred, torch.Tensor):
bbox_pred = bbox_pred.split(num_proposals_per_img, 0)
else:
bbox_pred = self.bbox_head[i].bbox_pred_split(
bbox_pred, num_proposals_per_img)
ms_scores.append(cls_score)
if i < self.num_stages - 1:
bbox_label = [s[:, :-1].argmax(dim=1) for s in cls_score]
rois = torch.cat([
self.bbox_head[i].regress_by_class(rois[j], bbox_label[j],
bbox_pred[j],
img_metas[j])
for j in range(num_imgs)
])
# average scores of each image by stages
cls_score = [
sum([score[i] for score in ms_scores]) / float(len(ms_scores))
for i in range(num_imgs)
]
# apply bbox post-processing to each image individually
det_bboxes = []
det_labels = []
for i in range(num_imgs):
det_bbox, det_label = self.bbox_head[-1].get_bboxes(
rois[i],
cls_score[i],
bbox_pred[i],
img_shapes[i],
scale_factors[i],
rescale=rescale,
cfg=rcnn_test_cfg)
det_bboxes.append(det_bbox)
det_labels.append(det_label)
bbox_results = [
bbox2result(det_bboxes[i], det_labels[i],
self.bbox_head[-1].num_classes)
for i in range(num_imgs)
]
ms_bbox_result['ensemble'] = bbox_results
if self.with_mask:
if all(det_bbox.shape[0] == 0 for det_bbox in det_bboxes):
mask_classes = self.mask_head[-1].num_classes
segm_results = [[[] for _ in range(mask_classes)]
for _ in range(num_imgs)]
else:
if rescale and not isinstance(scale_factors[0], float):
scale_factors = [
torch.from_numpy(scale_factor).to(det_bboxes[0].device)
for scale_factor in scale_factors
]
_bboxes = [
det_bboxes[i][:, :4] *
scale_factors[i] if rescale else det_bboxes[i][:, :4]
for i in range(len(det_bboxes))
]
mask_rois = bbox2roi(_bboxes)
num_mask_rois_per_img = tuple(
_bbox.size(0) for _bbox in _bboxes)
aug_masks = []
for i in range(self.num_stages):
mask_results = self._mask_forward(i, x, mask_rois)
mask_pred = mask_results['mask_pred']
# split batch mask prediction back to each image
mask_pred = mask_pred.split(num_mask_rois_per_img, 0)
aug_masks.append(
[m.sigmoid().cpu().numpy() for m in mask_pred])
# apply mask post-processing to each image individually
segm_results = []
for i in range(num_imgs):
if det_bboxes[i].shape[0] == 0:
segm_results.append(
[[]
for _ in range(self.mask_head[-1].num_classes)])
else:
aug_mask = [mask[i] for mask in aug_masks]
merged_masks = merge_aug_masks(
aug_mask, [[img_metas[i]]] * self.num_stages,
rcnn_test_cfg)
segm_result = self.mask_head[-1].get_seg_masks(
merged_masks, _bboxes[i], det_labels[i],
rcnn_test_cfg, ori_shapes[i], scale_factors[i],
rescale)
segm_results.append(segm_result)
ms_segm_result['ensemble'] = segm_results
if self.with_mask:
results = list(
zip(ms_bbox_result['ensemble'], ms_segm_result['ensemble']))
else:
results = ms_bbox_result['ensemble']
return results