How to use Pytorch with Waymo data

[MohammadHossein-Bahari]

Hello,

Thanks for sharing the great work. Since you evaluated your model with Waymo data, I wonder how you could use Waymo dataloader which is in Tensorflow? Is there a way we can bypass that and still have a Pytorch code? Thanks!

[GentleSmile]

Instead of using the waymo dataloader, we use the parsing function provided in the waymo tutorial to parse raw data into a dictionary, and then convert the tf tensors in the dictionary into numpy arrays.

[MohammadHossein-Bahari]

That's a nice idea! So then have you tried using both Waymo and Argo data together? Does it help?

[SwagJ]

Hi @GentleSmile,

I just have a simple follow up question. You used the tf_example set instead of scenario set for waymo dataset, right?