def _suppress(self, raw_cls_bbox, raw_prob, nms_thresh, score_thresh):
# bbox = list()
# score = list()
mask = raw_prob > score_thresh
bbox = raw_cls_bbox[mask]
scores = raw_prob[mask]
keep = non_maximum_suppression(cp.array(bbox), nms_thresh, scores)
keep = cp.asnumpy(keep)
bbox = bbox[keep]
scores = scores[keep]
# bbox.append(cls_bbox_l[keep])
# score.append(prob_l[keep])
# bbox = np.concatenate(bbox, axis=0).astype(np.float32)
# score = np.concatenate(score, axis=0).astype(np.float32)
return bbox, scores
def __call__(self, loc, score, anchor, img_size, scale=1.):
if self.parent_model.training:
n_pre_nms = self.n_train_pre_nms
n_post_nms = self.n_train_post_nms
else:
n_pre_nms = self.n_test_pre_nms
n_post_nms = self.n_test_post_nms
roi = loc2bbox(anchor, loc)
roi[:, slice(0, 4, 2)] = np.clip(roi[:, slice(0, 4, 2)], 0,
img_size[0])
roi[:, slice(1, 4, 2)] = np.clip(roi[:, slice(1, 4, 2)], 0,
img_size[1])
min_size = self.min_size * scale
hs = roi[:, 2] - roi[:, 0]
ws = roi[:, 3] - roi[:, 1]
min_size = np.array(min_size)
hs = np.array(hs)
ws = np.array(ws)
keep = np.where((hs >= min_size) & (ws >= min_size))[0]
roi = roi[keep, :]
score = score[keep]
order = score.ravel().argsort()[::-1]
if n_pre_nms > 0:
order = order[:n_pre_nms]
roi = roi[order, :]
score = score[order]
keep = non_maximum_suppression(cp.ascontiguousarray(cp.asarray(roi)),
thresh=self.nms_thresh)
if n_post_nms > 0:
keep = keep[:n_post_nms]
roi = roi[keep, :]
score = score[keep]
return roi, score