def aug_test_mask(self, feats, img_metas, det_bboxes, det_labels):
if det_bboxes.shape[0] == 0:
segm_result = [[] for _ in range(self.mask_head.num_classes - 1)]
else:
aug_masks = []
for x, img_meta in zip(feats, img_metas):
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(
x[:len(self.mask_roi_extractor.featmap_strides)],
mask_rois)
if self.with_shared_head:
mask_feats = self.shared_head(mask_feats)
mask_pred = self.mask_head(mask_feats)
# convert to numpy array to save memory
aug_masks.append(mask_pred.sigmoid().cpu().numpy())
merged_masks = merge_aug_masks(aug_masks, img_metas,
self.test_cfg.rcnn)
ori_shape = img_metas[0][0]['ori_shape']
segm_result = self.mask_head.get_seg_masks(merged_masks,
det_bboxes,
det_labels,
self.test_cfg.rcnn,
ori_shape,
scale_factor=1.0,
rescale=False)
return segm_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].
"""
if self.with_semantic:
semantic_feats = [
self.semantic_head(feat)[1]
for feat in self.extract_feats(imgs)
]
else:
semantic_feats = [None] * len(img_metas)
# 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, semantic in zip(self.extract_feats(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']
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, semantic_feat=semantic)
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)
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, semantic in zip(self.extract_feats(imgs),
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.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 simple_test(self, img, img_meta, proposals=None, rescale=False):
x = self.extract_feat(img)
proposal_list = self.simple_test_rpn(
x, img_meta, self.test_cfg.rpn) if proposals is None else proposals
if self.with_semantic:
_, semantic_feat = self.semantic_head(x)
else:
semantic_feat = None
img_shape = img_meta[0]['img_shape']
ori_shape = img_meta[0]['ori_shape']
scale_factor = img_meta[0]['scale_factor']
# "ms" in variable names means multi-stage
ms_bbox_result = {}
ms_segm_result = {}
ms_scores = []
rcnn_test_cfg = self.test_cfg.rcnn
rois = bbox2roi(proposal_list)
for i in range(self.num_stages):
bbox_head = self.bbox_head[i]
cls_score, bbox_pred = self._bbox_forward_test(
i, x, rois, semantic_feat=semantic_feat)
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))
det_bboxes, det_labels = self.bbox_head[-1].get_det_bboxes(
rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=rescale,
cfg=rcnn_test_cfg)
bbox_result = bbox2result(det_bboxes, det_labels,
self.bbox_head[-1].num_classes)
ms_bbox_result['ensemble'] = bbox_result
if self.with_mask:
if det_bboxes.shape[0] == 0:
mask_classes = self.mask_head[-1].num_classes - 1
segm_result = [[] for _ in range(mask_classes)]
else:
_bboxes = (det_bboxes[:, :4] *
scale_factor if rescale else det_bboxes)
mask_rois = bbox2roi([_bboxes])
aug_masks = []
mask_roi_extractor = self.mask_roi_extractor[-1]
mask_feats = mask_roi_extractor(
x[:len(mask_roi_extractor.featmap_strides)], mask_rois)
if self.with_semantic and 'mask' in self.semantic_fusion:
mask_semantic_feat = self.semantic_roi_extractor(
[semantic_feat], mask_rois)
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())
merged_masks = merge_aug_masks(aug_masks,
[img_meta] * self.num_stages,
self.test_cfg.rcnn)
segm_result = self.mask_head[-1].get_seg_masks(
merged_masks, _bboxes, det_labels, rcnn_test_cfg,
ori_shape, scale_factor, rescale)
ms_segm_result['ensemble'] = segm_result
if self.with_mask:
results = (ms_bbox_result['ensemble'], ms_segm_result['ensemble'])
else:
results = ms_bbox_result['ensemble']
return results
def simple_test(self, img, img_meta, proposals=None, rescale=False):
"""Run inference on a single image.
Args:
img (Tensor): must be in shape (N, C, H, W)
img_meta (list[dict]): a list with one dictionary element.
See `mmdet/datasets/pipelines/formatting.py:Collect` for
details of meta dicts.
proposals : if specified overrides rpn proposals
rescale (bool): if True returns boxes in original image space
Returns:
dict: results
"""
x = self.extract_feat(img)
proposal_list = self.simple_test_rpn(
x, img_meta, self.test_cfg.rpn) if proposals is None else proposals
img_shape = img_meta[0]['img_shape']
ori_shape = img_meta[0]['ori_shape']
scale_factor = img_meta[0]['scale_factor']
# "ms" in variable names means multi-stage
ms_bbox_result = {}
ms_segm_result = {}
ms_scores = []
rcnn_test_cfg = self.test_cfg.rcnn
rois = bbox2roi(proposal_list)
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_meta[0])
cls_score = sum(ms_scores) / self.num_stages
det_bboxes, det_labels = self.bbox_head[-1].get_det_bboxes(
rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=rescale,
cfg=rcnn_test_cfg)
bbox_result = bbox2result(det_bboxes, det_labels,
self.bbox_head[-1].num_classes)
ms_bbox_result['ensemble'] = bbox_result
if self.with_mask:
if det_bboxes.shape[0] == 0:
mask_classes = self.mask_head[-1].num_classes - 1
segm_result = [[] for _ in range(mask_classes)]
else:
if isinstance(scale_factor, float): # aspect ratio fixed
_bboxes = (
det_bboxes[:, :4] *
scale_factor if rescale else det_bboxes)
else:
_bboxes = (
det_bboxes[:, :4] *
torch.from_numpy(scale_factor).to(det_bboxes.device)
if rescale else det_bboxes)
mask_rois = bbox2roi([_bboxes])
aug_masks = []
for i in range(self.num_stages):
mask_roi_extractor = self.mask_roi_extractor[i]
mask_feats = mask_roi_extractor(
x[:len(mask_roi_extractor.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())
merged_masks = merge_aug_masks(aug_masks,
[img_meta] * self.num_stages,
self.test_cfg.rcnn)
segm_result = self.mask_head[-1].get_seg_masks(
merged_masks, _bboxes, det_labels, rcnn_test_cfg,
ori_shape, scale_factor, rescale)
ms_segm_result['ensemble'] = segm_result
if self.with_mask:
results = (ms_bbox_result['ensemble'], ms_segm_result['ensemble'])
else:
results = ms_bbox_result['ensemble']
return results