def get_rcnn_training_sample_batch(self, index):
sample_id = int(self.sample_id_list[index])
rpn_xyz, rpn_features, rpn_intensity, seg_mask = \
self.get_rpn_features(self.rcnn_training_feature_dir, sample_id)
# load rois and gt_boxes3d for this sample
roi_file = os.path.join(self.rcnn_training_roi_dir, '%06d.txt' % sample_id)
roi_obj_list = kitti_utils.get_objects_from_label(roi_file)
roi_boxes3d = kitti_utils.objs_to_boxes3d(roi_obj_list)
# roi_scores = kitti_utils.objs_to_scores(roi_obj_list)
gt_obj_list = self.filtrate_objects(self.get_label(sample_id))
gt_boxes3d = kitti_utils.objs_to_boxes3d(gt_obj_list)
# calculate original iou
iou3d = kitti_utils.get_iou3d(kitti_utils.boxes3d_to_corners3d(roi_boxes3d),
kitti_utils.boxes3d_to_corners3d(gt_boxes3d))
max_overlaps, gt_assignment = iou3d.max(axis=1), iou3d.argmax(axis=1)
max_iou_of_gt, roi_assignment = iou3d.max(axis=0), iou3d.argmax(axis=0)
roi_assignment = roi_assignment[max_iou_of_gt > 0].reshape(-1)
# sample fg, easy_bg, hard_bg
fg_rois_per_lidar = int(np.round(cfg.RCNN.FG_RATIO * cfg.RCNN.ROI_PER_lidar))
fg_thresh = min(cfg.RCNN.REG_FG_THRESH, cfg.RCNN.CLS_FG_THRESH)
fg_inds = np.nonzero(max_overlaps >= fg_thresh)[0]
fg_inds = np.concatenate((fg_inds, roi_assignment), axis=0) # consider the roi which has max_overlaps with gt as fg
easy_bg_inds = np.nonzero((max_overlaps < cfg.RCNN.CLS_BG_THRESH_LO))[0]
hard_bg_inds = np.nonzero((max_overlaps < cfg.RCNN.CLS_BG_THRESH) &
(max_overlaps >= cfg.RCNN.CLS_BG_THRESH_LO))[0]
fg_num_rois = fg_inds.size
bg_num_rois = hard_bg_inds.size + easy_bg_inds.size
if fg_num_rois > 0 and bg_num_rois > 0:
# sampling fg
fg_rois_per_this_lidar = min(fg_rois_per_lidar, fg_num_rois)
rand_num = np.random.permutation(fg_num_rois)
fg_inds = fg_inds[rand_num[:fg_rois_per_this_lidar]]
# sampling bg
bg_rois_per_this_lidar = cfg.RCNN.ROI_PER_lidar - fg_rois_per_this_lidar
bg_inds = self.sample_bg_inds(hard_bg_inds, easy_bg_inds, bg_rois_per_this_lidar)
elif fg_num_rois > 0 and bg_num_rois == 0:
# sampling fg
rand_num = np.floor(np.random.rand(cfg.RCNN.ROI_PER_lidar ) * fg_num_rois)
rand_num = torch.from_numpy(rand_num).type_as(gt_boxes3d).long()
fg_inds = fg_inds[rand_num]
fg_rois_per_this_lidar = cfg.RCNN.ROI_PER_lidar
bg_rois_per_this_lidar = 0
elif bg_num_rois > 0 and fg_num_rois == 0:
# sampling bg
bg_rois_per_this_lidar = cfg.RCNN.ROI_PER_lidar
bg_inds = self.sample_bg_inds(hard_bg_inds, easy_bg_inds, bg_rois_per_this_lidar)
fg_rois_per_this_lidar = 0
else:
import pdb
pdb.set_trace()
raise NotImplementedError
# augment the rois by noise
roi_list, roi_iou_list, roi_gt_list = [], [], []
if fg_rois_per_this_lidar > 0:
fg_rois_src = roi_boxes3d[fg_inds].copy()
gt_of_fg_rois = gt_boxes3d[gt_assignment[fg_inds]]
fg_rois, fg_iou3d = self.aug_roi_by_noise_batch(fg_rois_src, gt_of_fg_rois, aug_times=10)
roi_list.append(fg_rois)
roi_iou_list.append(fg_iou3d)
roi_gt_list.append(gt_of_fg_rois)
if bg_rois_per_this_lidar > 0:
bg_rois_src = roi_boxes3d[bg_inds].copy()
gt_of_bg_rois = gt_boxes3d[gt_assignment[bg_inds]]
bg_rois, bg_iou3d = self.aug_roi_by_noise_batch(bg_rois_src, gt_of_bg_rois, aug_times=1)
roi_list.append(bg_rois)
roi_iou_list.append(bg_iou3d)
roi_gt_list.append(gt_of_bg_rois)
rois = np.concatenate(roi_list, axis=0)
iou_of_rois = np.concatenate(roi_iou_list, axis=0)
gt_of_rois = np.concatenate(roi_gt_list, axis=0)
# collect extra features for point cloud pooling
if cfg.RCNN.USE_INTENSITY:
pts_extra_input_list = [rpn_intensity.reshape(-1, 1), seg_mask.reshape(-1, 1)]
else:
pts_extra_input_list = [seg_mask.reshape(-1, 1)]
if cfg.RCNN.USE_DEPTH:
pts_depth = (np.linalg.norm(rpn_xyz, ord=2, axis=1) / 70.0) - 0.5
pts_extra_input_list.append(pts_depth.reshape(-1, 1))
pts_extra_input = np.concatenate(pts_extra_input_list, axis=1)
pts_input, pts_features, pts_empty_flag = roipool3d_utils.roipool3d_cpu(rois, rpn_xyz, rpn_features,
pts_extra_input,
cfg.RCNN.POOL_EXTRA_WIDTH,
sampled_pt_num=cfg.RCNN.NUM_POINTS,
canonical_transform=False)
valid_mask = (pts_empty_flag == 0).astype(np.int32)
# regression valid mask
reg_valid_mask = (iou_of_rois > cfg.RCNN.REG_FG_THRESH).astype(np.int32) & valid_mask
# classification label
cls_label = (iou_of_rois > cfg.RCNN.CLS_FG_THRESH).astype(np.int32)
invalid_mask = (iou_of_rois > cfg.RCNN.CLS_BG_THRESH) & (iou_of_rois < cfg.RCNN.CLS_FG_THRESH)
cls_label[invalid_mask] = -1
cls_label[valid_mask == 0] = -1
# canonical transform and sampling
pts_input_ct, gt_boxes3d_ct = self.canonical_transform_batch(pts_input, rois, gt_of_rois)
sample_info = {'sample_id': sample_id,
'pts_input': pts_input_ct,
'pts_features': pts_features,
'cls_label': cls_label,
'reg_valid_mask': reg_valid_mask,
'gt_boxes3d_ct': gt_boxes3d_ct,
'roi_boxes3d': rois,
'roi_size': rois[:, 3:6],
'gt_boxes3d': gt_of_rois}
return sample_info
def get_proposal_from_file(self, index):
sample_id = int(self.lidar_idx_list[index])
proposal_file = os.path.join(self.rcnn_eval_roi_dir, '%06d.txt' % sample_id)
roi_obj_list = kitti_utils.get_objects_from_label(proposal_file)
rpn_xyz, rpn_features, rpn_intensity, seg_mask = self.get_rpn_features(self.rcnn_eval_feature_dir, sample_id)
pts_rect, pts_rpn_features, pts_intensity = rpn_xyz, rpn_features, rpn_intensity
roi_box3d_list, roi_scores = [], []
for obj in roi_obj_list:
box3d = np.array([obj.pos[0], obj.pos[1], obj.pos[2], obj.h, obj.w, obj.l, obj.ry], dtype=np.float32)
roi_box3d_list.append(box3d.reshape(1, 7))
roi_scores.append(obj.score)
roi_boxes3d = np.concatenate(roi_box3d_list, axis=0) # (N, 7)
roi_scores = np.array(roi_scores, dtype=np.float32) # (N)
if cfg.RCNN.ROI_SAMPLE_JIT:
sample_dict = {'sample_id': sample_id,
'rpn_xyz': rpn_xyz,
'rpn_features': rpn_features,
'seg_mask': seg_mask,
'roi_boxes3d': roi_boxes3d,
'roi_scores': roi_scores,
'pts_depth': np.linalg.norm(rpn_xyz, ord=2, axis=1)}
if self.mode != 'TEST':
gt_obj_list = self.filtrate_objects(self.get_label(sample_id))
gt_boxes3d = kitti_utils.objs_to_boxes3d(gt_obj_list)
roi_corners = kitti_utils.boxes3d_to_corners3d(roi_boxes3d)
gt_corners = kitti_utils.boxes3d_to_corners3d(gt_boxes3d)
iou3d = kitti_utils.get_iou3d(roi_corners, gt_corners)
if gt_boxes3d.shape[0] > 0:
gt_iou = iou3d.max(axis=1)
else:
gt_iou = np.zeros(roi_boxes3d.shape[0]).astype(np.float32)
sample_dict['gt_boxes3d'] = gt_boxes3d
sample_dict['gt_iou'] = gt_iou
return sample_dict
if cfg.RCNN.USE_INTENSITY:
pts_extra_input_list = [pts_intensity.reshape(-1, 1), seg_mask.reshape(-1, 1)]
else:
pts_extra_input_list = [seg_mask.reshape(-1, 1)]
if cfg.RCNN.USE_DEPTH:
cur_depth = np.linalg.norm(pts_rect, axis=1, ord=2)
cur_depth_norm = (cur_depth / 70.0) - 0.5
pts_extra_input_list.append(cur_depth_norm.reshape(-1, 1))
pts_extra_input = np.concatenate(pts_extra_input_list, axis=1)
pts_input, pts_features = roipool3d_utils.roipool3d_cpu(roi_boxes3d, pts_rect, pts_rpn_features,
pts_extra_input, cfg.RCNN.POOL_EXTRA_WIDTH,
sampled_pt_num=cfg.RCNN.NUM_POINTS)
sample_dict = {'sample_id': sample_id,
'pts_input': pts_input,
'pts_features': pts_features,
'roi_boxes3d': roi_boxes3d,
'roi_scores': roi_scores,
'roi_size': roi_boxes3d[:, 3:6]}
if self.mode == 'TEST':
return sample_dict
gt_obj_list = self.filtrate_objects(self.get_label(sample_id))
gt_boxes3d = np.zeros((gt_obj_list.__len__(), 7), dtype=np.float32)
for k, obj in enumerate(gt_obj_list):
gt_boxes3d[k, 0:3], gt_boxes3d[k, 3], gt_boxes3d[k, 4], gt_boxes3d[k, 5], gt_boxes3d[k, 6] \
= obj.pos, obj.h, obj.w, obj.l, obj.ry
if gt_boxes3d.__len__() == 0:
gt_iou = np.zeros((roi_boxes3d.shape[0]), dtype=np.float32)
else:
roi_corners = kitti_utils.boxes3d_to_corners3d(roi_boxes3d)
gt_corners = kitti_utils.boxes3d_to_corners3d(gt_boxes3d)
iou3d = kitti_utils.get_iou3d(roi_corners, gt_corners)
gt_iou = iou3d.max(axis=1)
sample_dict['gt_boxes3d'] = gt_boxes3d
sample_dict['gt_iou'] = gt_iou
return sample_dict