search

bradyz / 2020_CARLA_challenge

"Learning by Cheating" (CoRL 2019) submission for the 2020 CARLA Challenge
182 stars 50 forks source link

Some issue in Data collection for Carla 0.9.10 #24

Closed t27 closed 4 years ago

t27 commented 4 years ago

While running the data collection code on 0.9.10 we found some issues that mostly seem like they were caused due to some breaking changes in Carla 0.9.9 -> 0.9.10

This one seems like an issue in the scenario runner import where the name of the AgentPool was changed to DataProvider, https://github.com/bradyz/leaderboard/blob/35fb5f2d1e7d8884d20d92e492f5d49ecbae2b65/team_code/map_agent.py#L1

Over here the semantic segmentation remapping is not compatible with the larger semantic segmentation outputs in carla 0.9.10 (Old vs New) https://github.com/bradyz/carla_project/blob/2f0c166167a8d44b8b720cdbcd5d56983fa71602/src/common.py#L4

I can submit a PR for the above changes if needed as well, I would just need some help with the new segmentation class mappings, do let me know if I can help,

Thanks!

bradyz commented 4 years ago

thanks for the detailed issue!

I've fixed these in the newest commit a05ab7b and the data collection should work in 0.9.10.1 now

omerXfaruq commented 4 years ago

Hello @t27 can you currently collect data, I have problems in data_collection here: https://github.com/bradyz/2020_CARLA_challenge/issues/31 Is your problem solved, how do you currently collect data, I want to collect segmentation_data. Thank you very much!

t27 commented 4 years ago

Yeah, I was able to collect data. Although at the time i posted the issue, we chose to collect data from Carla 0.9.9 instead of 0.9.10 as we were short of time and using 0.9.9 in that version of the repository was the fastest way. Although the code is updated now and it should be working with 0.9.10 now.

I faced a similar issue as #31, I've commented there with what worked for me