def _match_priors_gt(self, priors, gt, thresh, num_boxes):
batch_size = gt.size(0)
num_priors = priors.size(0)
overlaps = bbox_overlaps_batch(priors, gt)
# [b, num_objects] best prior for each ground truth
best_prior_overlap, best_prior_idx = overlaps.max(1)
# [b, num_priors] best ground truth for each prior
best_truth_overlap, best_truth_idx = overlaps.max(2)
matches = torch.zeros(batch_size, num_priors, 5).type_as(priors)
for num in range(batch_size):
# select valid best prior idx
best_prior_idx_valid = best_prior_idx[num][:num_boxes[num]]
best_truth_overlap[num].index_fill_(0, best_prior_idx_valid,
2) # ensure best prior
# TODO refactor: index best_prior_idx with long tensor
# ensure every gt matches with its prior of max overlap
for j in range(best_prior_idx_valid.size(0)):
best_truth_idx[num][best_prior_idx_valid[j]] = j
matches[num] = gt[num][best_truth_idx[num]]
loc = matches[:, :, :-1] # Shape: [bs, num_priors,4]
conf = matches[:, :, -1] # Shape: [bs, num_priors]
conf[best_truth_overlap < thresh] = 0 # label as background
encoded_loc = bbox_transform_batch(priors, loc)
if cfg.TRAIN.COMMON.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:
# Optionally normalize targets by a precomputed mean and stdev
encoded_loc = ((encoded_loc -
self.BBOX_NORMALIZE_MEANS.expand_as(encoded_loc)) /
self.BBOX_NORMALIZE_STDS.expand_as(encoded_loc))
return encoded_loc, conf
def _compute_targets_pytorch(self, ex_rois, gt_rois):
assert ex_rois.size(1) == gt_rois.size(1)
assert ex_rois.size(2) == 4
assert gt_rois.size(2) == 4
batch_size = ex_rois.size(0)
rois_per_image = ex_rois.size(1)
targets = bbox_transform_batch(ex_rois, gt_rois)
if cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:
# Optionally normalize targets by a precomputed mean and stdev
targets = (
(targets - self.BBOX_NORMALIZE_MEANS.expand_as(targets)) /
self.BBOX_NORMALIZE_STDS.expand_as(targets))
return targets
def _compute_targets_batch(ex_rois, gt_rois):
"""Compute bounding-box regression targets for an image."""
return bbox_transform_batch(ex_rois, gt_rois[:, :, :4])
