Error in Preprocessing Data about fusiondepth HOT 5 CLOSED

And is the preprocess necessary for the work of training? When I run the "python trainer.py", it seems another document is needed:
'/data/Kitti_RAW_Data/2011_09_30/2011_09_30_drive_0028_sync/2channel/5001_r_False.npy'

I'm puzzeled about how to get these data.

from fusiondepth.

Hi Renatusphere:

Thank you for your interest in our work, yes this preprocess is necessary for the training.

The file '4beam/xxx.bin' is generated by the sparsify.py, which samples 4 LiDAR lines from the KITTI original 64-beam data. I think the problem is that the output path here does not match your data path (/data/Kitti_RAW_Data/...).

You can either soft link your data path to the FusionDepth root folder as "kitti_data" or feed it to the sparsify.py.

I hope this will solve your problem, thank you again for your interest!

from fusiondepth.

Thank you for your response!

It seems that the error happens in the process of loading the velodyne data. In the code below, it tries to load raw data from velo_filename: "/data/Kitti_RAW_Data/2011_09_26/2011_09_26_drive_0002_sync/4beam/0000000069.bin"

However, I assume that this file should have been the output file, so the velo_filename is incorrect.

I tried to modify my output path, but it didn't work. It turned out to be the same error.

Should I modify the code of splicing velo_filename? Thank you again!

from fusiondepth.

The raw 64-beam Velodyne data is 'velodyne_points/data/xxx.bin' while the sparsified data is '4beam/xxx.bin'. The variable name "velo_filename" here is not clear enough, you are welcome to modify it and submit a pull request.

Could you check where your sparsify.py outputted the '4beam/xxx.bin' files? that's what the code in your screenshot supposed to load.

from fusiondepth.

It turned out that I missed a "/" in the end of ptc_path, which lead to no output.

Thanks a lot for your great work and enthusiastic response!

from fusiondepth.