zijianzhang / carla_invs Goto Github PK

Is there a docker available? or a similar docker？ Thanks

I put the sample dateset from the README link in $ROOT_PATH/data and did python3 PCDet/INVS_main.py, but I get the following error

$ python3 PCDet/INVS_main.py
/home/atusi/CARLA_INVS/PCDet/fed.py
===================== 0 =====================
Traceback (most recent call last):
File "PCDet/INVS_main.py", line 24, in
sp.run([ENTRY_FILE, counter])
File "/usr/lib/python3.7/subprocess.py", line 488, in run
with Popen(*popenargs, **kwargs) as process:
File "/usr/lib/python3.7/subprocess.py", line 800, in init
restore_signals, start_new_session)
File "/usr/lib/python3.7/subprocess.py", line 1482, in _execute_child
restore_signals, start_new_session, preexec_fn)
TypeError: expected str, bytes or os.PathLike object, not int

How can I fix this?
The content of the sample dateset is as follows. Is this in KITTI format or PCDet format?

data
└── record2020_1027_1957
├── fusion
├── global_label
├── vehicle.tesla.model3_713
│ ├── ImageSets
│ ├── gt_database
│ └── training
│ ├── calib
│ ├── image_2
│ ├── label_2
│ └── velodyne
└── vehicle.tesla.model3_714
├── ImageSets
├── gt_database
└── training
├── calib
├── image_2
├── label_2
└── velodyne

19 directories

Hi,

In Scenario.py, there is ROI, initial_spawn_roi, and additional_spawn_roi with some given value. But it seems that it only works well with Town 02. I guess the reason may because that each town has its own ROI since they have different map structures. However, I have no idea how to get the ROI in CARLA, could you please give some advice?

Thanks!

I would like to create the same environment as yours, so please let me know what versions of pytorch and cuda,llvm you have.
Also, is carla available as a downloadable version? (Does it have to be the built one?).

What is your running environment? (e.g. CUDA, pytorch, llvm)
I am running on ubuntu 18.04,carla0.9.8 , python3.7, CUDA10.1 , pytorch1.4.0 llvm10.0 and I am getting errors during make dependency.
In addition, the following statement is displayed during the process.

Please ensure you have CUDA 9.0+ and cuDNN installed! (press ENTER to continue...)

Hello, it seems that the download link for the sample dataset is outdated (https://cloud.189.cn/web/share?code=jQJvuimquaEj) Are there any other links available? Thanks a lot!

I have a question about Training for federated models.
I don't understand the difference between the Custom Dataset and the distributed Training for federated model.
Am I correct in assuming that the Training for federated model in the readme link is the KITTI format data that you created in Custom Dataset Generation?
Thank you very much for your help.

when I run python PCDet/INVS_main.py
there is an error FileNotFoundError: [Errno 2] No such file or directory: 'cfgs/tesla714.yaml'
could you tell me where I can find this file?
Thanks very much!