uzh-rpg / rl_vo

Repository relating to "Reinforcement Learning Meets Visual Odometry" (ECCV, 2024).
GNU General Public License v3.0
203 stars 19 forks source link

Segmentation error (on training) #2

Open sadbhavsingh16 opened 3 months ago

XinyiChu commented 2 months ago

do u meet a error like this ?: Traceback (most recent call last): File "/workspace/vo_rl/env/svo_wrapper.py", line 85, in get_images_pose batch = next(self.dataloader_iter) StopIteration

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "train.py", line 104, in main model.learn( File "/workspace/vo_rl/rl_algorithms/ppo.py", line 347, in learn return super().learn( File "/workspace/vo_rl/rl_algorithms/on_policy_algorithm.py", line 274, in learn total_timesteps, callback = self._setup_learn( File "/venv/lib/python3.8/site-packages/stable_baselines3/common/base_class.py", line 423, in _setup_learn self._last_obs = self.env.reset() # type: ignore[assignment] File "/workspace/vo_rl/env/svo_wrapper.py", line 213, in reset images, gt_poses, new_seq = self.get_images_pose() File "/workspace/vo_rl/env/svo_wrapper.py", line 89, in get_images_pose batch = next(self.dataloader_iter) StopIteration