def _create_coco_gt_results(dataset):
from mmdet.core import bbox2result
from mmtrack.core import track2result
results = defaultdict(list)
for img_info in dataset.data_infos:
ann = dataset.get_ann_info(img_info)
scores = np.ones((ann['bboxes'].shape[0], 1), dtype=np.float)
bboxes = np.concatenate((ann['bboxes'], scores), axis=1)
bbox_results = bbox2result(bboxes, ann['labels'], len(dataset.CLASSES))
track_results = track2result(bboxes, ann['labels'],
ann['instance_ids'].astype(np.int),
len(dataset.CLASSES))
results['bbox_results'].append(bbox_results)
results['track_results'].append(track_results)
return results
def test_track2result():
from mmtrack.core import track2result
# pseudo data
num_objects, num_classes = 8, 4
bboxes = random_boxes(num_objects, 640)
scores = torch.FloatTensor(num_objects, 1).uniform_(0, 1)
bboxes = torch.cat([bboxes, scores], dim=1)
# leave the results of the last class as empty
labels = torch.randint(0, num_classes - 1, (num_objects, ))
ids = torch.arange(num_objects)
# run
result = track2result(bboxes, labels, ids, num_classes)
# test
assert len(result) == num_classes
assert result[-1].shape == (0, 6)
assert isinstance(result[0], np.ndarray)
for i in range(num_classes):
assert result[i].shape[0] == (labels == i).sum()
assert result[i].shape[1] == 6
def simple_test(self,
img,
img_metas,
rescale=False,
public_bboxes=None,
**kwargs):
"""Test without augmentations.
Args:
img (Tensor): of shape (N, C, H, W) encoding input images.
Typically these should be mean centered and std scaled.
img_metas (list[dict]): list of image info dict where each dict
has: 'img_shape', 'scale_factor', 'flip', and may also contain
'filename', 'ori_shape', 'pad_shape', and 'img_norm_cfg'.
rescale (bool, optional): If False, then returned bboxes and masks
will fit the scale of img, otherwise, returned bboxes and masks
will fit the scale of original image shape. Defaults to False.
public_bboxes (list[Tensor], optional): Public bounding boxes from
the benchmark. Defaults to None.
Returns:
dict[str : list(ndarray)]: The tracking results.
"""
frame_id = img_metas[0].get('frame_id', -1)
if frame_id == 0:
self.tracker.reset()
x = self.detector.extract_feat(img)
if hasattr(self.detector, 'roi_head'):
# TODO: check whether this is the case
if public_bboxes is not None:
public_bboxes = [_[0] for _ in public_bboxes]
proposals = public_bboxes
else:
proposals = self.detector.rpn_head.simple_test_rpn(
x, img_metas)
det_bboxes, det_labels = self.detector.roi_head.simple_test_bboxes(
x,
img_metas,
proposals,
self.detector.roi_head.test_cfg,
rescale=rescale)
# TODO: support batch inference
det_bboxes = det_bboxes[0]
det_labels = det_labels[0]
num_classes = self.detector.roi_head.bbox_head.num_classes
elif hasattr(self.detector, 'bbox_head'):
outs = self.detector.bbox_head(x)
result_list = self.detector.bbox_head.get_bboxes(
*outs, img_metas=img_metas, rescale=rescale)
# TODO: support batch inference
det_bboxes = result_list[0][0]
det_labels = result_list[0][1]
num_classes = self.detector.bbox_head.num_classes
else:
raise TypeError('detector must has roi_head or bbox_head.')
bboxes, labels, ids = self.tracker.track(img=img,
img_metas=img_metas,
model=self,
feats=x,
bboxes=det_bboxes,
labels=det_labels,
frame_id=frame_id,
rescale=rescale,
**kwargs)
track_result = track2result(bboxes, labels, ids, num_classes)
bbox_result = bbox2result(det_bboxes, det_labels, num_classes)
return dict(bbox_results=bbox_result, track_results=track_result)