Open lelouedec opened 4 years ago
When the class Point_Rcnn which is if I understand correctly the model class, calls RCNNNet it is using a dict created as folllow :
rcnn_input_info = {'rpn_xyz': backbone_xyz, 'rpn_features': backbone_features.permute((0, 2, 1)), 'seg_mask': seg_mask, 'roi_boxes3d': rois, 'pts_depth': pts_depth} if self.training: rcnn_input_info['gt_boxes3d'] = input_data['gt_boxes3d']
But in RCNNNet forward the input is used with the following keys and code:
pts_input = input_data['pts_input'] target_dict = {} target_dict['pts_input'] = input_data['pts_input'] target_dict['roi_boxes3d'] = input_data['roi_boxes3d'] if self.training: target_dict['cls_label'] = input_data['cls_label'] target_dict['reg_valid_mask'] = input_data['reg_valid_mask'] target_dict['gt_of_rois'] = input_data['gt_boxes3d_ct']
Am I missing something there?
Emmm, I met the same pazzel, is there anyone any ideas?
maybe you could reference /PointRCNN/lib/datasets/kitti_rcnn_dataset.py
When the class Point_Rcnn which is if I understand correctly the model class, calls RCNNNet it is using a dict created as folllow :
But in RCNNNet forward the input is used with the following keys and code:
Am I missing something there?