carla-simulator/imitation-learning

Question about the provided dataset

AliBaheri opened this issue · 3 comments

AliBaheri commented

Thanks for sharing the great work.

I have a question abut the dataset. I understand that each .h5 consists of 200 images, but my question how these .h5 have been collected? Particularly, I mean these files starts from data_03663.h5 and ends by data_06951.h5. Dose all of these files have been collected sequentially? Does it mean these files are part of sequence or episodes?

Thanks for clarification.
Best.

AliBaheri commented

Solved.

kimna4 commented

@AliBaheri
I checked some .h5 files and it consisted of 200 sequential images.
However, I'am not sure that all of these files have one sequential episode.
I think that some .h5 files are likely to contain multiple episodes.
I want to know the answer to your question.

Thank you.

ryanwang522 commented

Hi @kimna4 @AliBaheri
I also have a similar question about how the data have been collected.
Should we extract all the images from these .h5 files and train our model with batched data?