New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Minor errors regarding the released dataset #3
Comments
I double-checked and it is a bug in my conversion script. Thank you for letting me know and I will fix it and update the dataset soon. In the meantime you can use the data collection script to generate data.
Those are the lanes for lane changing
No, but it runs much faster in Carla than OpenGL. The errors you see however is because there is no results folder. Simply Closing the issue for now. |
@SunHaoOne I have updated the dataset link, should be fixed. Let me know if you have any more questions. |
Thanks for your reply. Besides, I found there are 200 lbl images, however, the number of rgb cameras is only 195. For example, the last images of wide camera is |
|
@SunHaoOne Hey, were you able to make the data collector work? If you enable the wandb, you can see the logs for rails.data_phase0. I did that and I can see two errors coming up. There is no speed sensor in CARLA_0.9.10.1. Should I make any API changes to use the Speed sensor? @dotchen Any suggestions here? |
Sorry for the late reply. I also meet this problem now, do you have any idea?(I successfully collected data for about 1400 frames before, now I cannot collect data, and I have tried to run carla again but also failed )It shows as follows:
|
It looks like you are passing the fps argument wrong! Check the value properly! Also try to pull the latest code from the repo. |
Thanks for your reply, I run carla with
|
@SunHaoOne reinstall |
Thanks you again! Wow, I fixed it and now I can collected the data. |
Make sure you have read FAQ before posting.
Thanks!
Hello,
Sorry to disrupt you again. After reading the FAQ carefully, I downloaded your released datasets, there are some small mistakes here. And there is some problem about launching carla, I guess this problem leads to the errors about training the ego model.
1 datasets lose key and value
For example,
It seems that the
narr_rgb_{}
key and value is lost, and the file name does not correspond to the value in this json file. Besides, the value ofwide_rgb_{}
is also needs to be changed. So the code here is provided:And for testing, we set a random number, the code is following:
And finally the datasets can be loaded.
2 what does 6+:lane centers mean?
I found 6-11 are lane centers,what is the difference between them or how to collect it? I thought the direction of no.11 images seems different, I guess it maybe the people's lane center?
3 Is Vulcan necessary for Carla?
I failed to launch Carla by running the launch Carla shell. In FAQ, it might be the error of Vulcan, However, I can still launch Carla using the OpenGL. And I successfully test the examples in PythonAPI. After launching Carla, I decided to train the ego_model. And first of all, I need to collect the datasets.
Then I tried
I am not sure how to fix this problem, I just do as follows:(Did I set the right scenario_class?)
After that, there is no error and it seems that the code is running at
ray.wait(jobs, num_returns=args.num_runners)
, and no data are saved. Then I turned to phase1,The same error can be seen in the phase2. I guess these errors are caused by the
ray
.Now I am confused by these data collecting errors. And I would appreciate it if you could help me fixed these errors. Thank you again!The text was updated successfully, but these errors were encountered: