Marcel Hallgarten
Marcel Hallgarten
Additionally, the dataset page does not mention in which folder the test set belongs. I assume it belongs in the trainval folder as well since there is a dedicated splitter...
Hi @patk-motional, 3. Can you elaborate more precisely, what exactly a scenario consists of and how it can be distinguished from a sample? As far as I can see, for...
Thank you. How about the validity condition of the agents feature? As far as I can see, this was not updated so far.
I did the same check again (slightly different code since `scenario_builder._db.get_all_scenario_types()` does not exist anymore). I found out that only ~10k samples are tagged with a scenario_type while all the...
Hi @gianmarco-motional. is there an update on this ? The issue still persists with the version 0.3 of the devkit.
The error occured using the current devkit-0.6 version. I recreated the environment after updating to this version.
Hi @patk-motional, Yes, it has been! - Thank you
> You are correct, the scenario name was added to the cache during that release. If you regenerate the cache, it should have the proper structure. > > At the...
Hi @bazyagami, Did you make any modifications to the transfuser code, the training script or any other part of navsim before starting the training? Can you please share which versions...
It seems like you used the same cache directory to also train the ego_status_mlp_agent. Could you try to generate a new training cache into a separate directory only for the...