AlonZhao

### problem 1： launch rviz and get errors like“lack goal3D tools" Fixed: get rviz plugin package somewhere and add it as a package into the workspace ,catkin_make again.source and roslaunch...

ops are decreased after simplification but onnx inference time increases ,is that reasonable?

Hello Zhiyu, What is the meaning of ego regularization, which is the output of ego_traj_decoder: ``` agents_trajecotries = torch.stack(agents_trajecotries, dim=2) scores, weights = self.scorer(ego_traj_inputs, encoding[:, 0], agents_trajecotries, current_states, timesteps) ego_traj_regularization...

为什么交叉熵计算时目标标签都是0

3

zhiyu 你好， label = torch.zeros(scores.shape[0], dtype=torch.long).to(scores.device) # why zeros？ irl_loss = F.cross_entropy(scores, label) 在计算损失函数时，交叉熵计算为什么设定label 标签都为零呢？