def _suppress(raw_bbox, raw_score, nms_thresh, score_thresh):
xp = cuda.get_array_module(raw_bbox, raw_score)
bbox = []
label = []
score = []
for l in range(raw_score.shape[1] - 1):
bbox_l = raw_bbox[:, l + 1]
score_l = raw_score[:, l + 1]
mask = score_l >= score_thresh
bbox_l = bbox_l[mask]
score_l = score_l[mask]
order = argsort(-score_l)
bbox_l = bbox_l[order]
score_l = score_l[order]
indices = utils.non_maximum_suppression(bbox_l, nms_thresh)
bbox_l = bbox_l[indices]
score_l = score_l[indices]
bbox.append(bbox_l)
label.append(xp.array((l, ) * len(bbox_l)))
score.append(score_l)
bbox = xp.vstack(bbox).astype(np.float32)
label = xp.hstack(label).astype(np.int32)
score = xp.hstack(score).astype(np.float32)
return bbox, label, score
def decode(self, locs, confs, anchors, in_shape):
"""Decodes back to coordinates of RoIs.
This method decodes :obj:`locs` and :obj:`confs` returned
by a FPN network back to :obj:`rois` and :obj:`roi_indices`.
Args:
locs (list of arrays): A list of arrays whose shape is
:math:`(N, K_l, 4)`, where :math:`N` is the size of batch and
:math:`K_l` is the number of the anchor boxes
of the :math:`l`-th level.
confs (list of arrays): A list of array whose shape is
:math:`(N, K_l)`.
anchors (list of arrays): Anchor boxes returned by :meth:`anchors`.
in_shape (tuple of ints): The shape of input of array
the feature extractor.
Returns:
tuple of two arrays:
:obj:`rois` and :obj:`roi_indices`.
* **rois**: An array of shape :math:`(R, 4)`, \
where :math:`R` is the total number of RoIs in the given batch.
* **roi_indices** : An array of shape :math:`(R,)`.
"""
if chainer.config.train:
nms_limit_pre = self._train_nms_limit_pre
nms_limit_post = self._train_nms_limit_post
else:
nms_limit_pre = self._test_nms_limit_pre
nms_limit_post = self._test_nms_limit_post
rois = []
roi_indices = []
for i in range(in_shape[0]):
roi = []
conf = []
for l in range(len(self._scales)):
loc_l = locs[l].array[i]
conf_l = confs[l].array[i]
roi_l = anchors[l].copy()
# tlbr -> yxhw
roi_l[:, 2:] -= roi_l[:, :2]
roi_l[:, :2] += roi_l[:, 2:] / 2
# offset
roi_l[:, :2] += loc_l[:, :2] * roi_l[:, 2:]
roi_l[:, 2:] *= self.xp.exp(
self.xp.minimum(loc_l[:, 2:], exp_clip))
# yxhw -> tlbr
roi_l[:, :2] -= roi_l[:, 2:] / 2
roi_l[:, 2:] += roi_l[:, :2]
# clip
roi_l[:, :2] = self.xp.maximum(roi_l[:, :2], 0)
roi_l[:, 2:] = self.xp.minimum(roi_l[:, 2:],
self.xp.array(in_shape[2:]))
order = argsort(-conf_l)[:nms_limit_pre]
roi_l = roi_l[order]
conf_l = conf_l[order]
mask = (roi_l[:, 2:] - roi_l[:, :2] > 0).all(axis=1)
roi_l = roi_l[mask]
conf_l = conf_l[mask]
indices = utils.non_maximum_suppression(roi_l,
self._nms_thresh,
limit=nms_limit_post)
roi_l = roi_l[indices]
conf_l = conf_l[indices]
roi.append(roi_l)
conf.append(conf_l)
roi = self.xp.vstack(roi).astype(np.float32)
conf = self.xp.hstack(conf).astype(np.float32)
order = argsort(-conf)[:nms_limit_post]
roi = roi[order]
rois.append(roi)
roi_indices.append(self.xp.array((i, ) * len(roi)))
rois = self.xp.vstack(rois).astype(np.float32)
roi_indices = self.xp.hstack(roi_indices).astype(np.int32)
return rois, roi_indices