MarkFzp / act-plus-plus

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN
https://mobile-aloha.github.io/
MIT License
3.06k stars 563 forks source link

Use the Real Environment dataset to train the model, Program running Error #20

Open VDuZane opened 10 months ago

VDuZane commented 10 months ago

Hi, thanks for your brilliant work and open-source code! I tried your dataset files to generate mp4 file, or to train the model. [https://drive.google.com/drive/folders/1vhKa4tNPfMkeK7SW86vKorb39epTYW39] —— aloha_mobile_chair_truncated program running error, error code is : Traceback (most recent call last): File "visualize_episodes.py", line 160, in main(vars(parser.parse_args())) File "visualize_episodes.py", line 44, in main save_videos(image_dict , DT, video_path=os.path.join(dataset_dir, dataset_name + '_video.mp4')) File "visualize_episodes.py", line 78, in save_videos all_cam_videos = np.concatenate(all_cam_videos, axis=2) # width dimension File "<__array_function__ internals>", line 200, in concatenate numpy.AxisError: axis 2 is out of bounds for array of dimension 2 The real environment file data format is not same as simulation generated data files especially the camera data. How to solve this problem? sim_env real_env

tanxr00 commented 10 months ago

采集数据中,图像压缩模式关掉

huiwenzhang commented 10 months ago

You shold use the visualize_episodes.py script hosted in https://github.com/MarkFzp/mobile-aloha/tree/main/aloha_scripts if you want to visualize real-world collected data from the author. The visualize_episodes.py in this repo only used for visualize simulated task like sim_tansfer_cube and sim_insertion_scripted.

Edisonhimself commented 5 months ago

Hello, may I ask how to modify the data format of my robotic arm to training format, and can the data of a six axis robotic arm be trained