search

Tsinghua-MARS-Lab / M2I

M2I is a simple but effective joint motion prediction framework through marginal and conditional predictions by exploiting the factorized relations between interacting agents.
https://tsinghua-mars-lab.github.io/M2I/
MIT License
187 stars 24 forks source link

Marginal trajectory prediction error. #16

Closed BJHYZJ closed 1 year ago

BJHYZJ commented 1 year ago

When I want to evaluation at step2 which named marginal trajectory predictoin , I meet a error about tensor. The script I ran can be seen at the top of the image. image

larksq commented 1 year ago

Thank you for your feedback. I checked the pre-trained model. This model did not match the parameter setting in the readme leading to your error. I have updated the model on google drive. Could you please update the pre-trained model and try the evaluation again? Sorry for the previous mismatch.

BJHYZJ commented 1 year ago

That's great, thank you very much for your serious reply.

BJHYZJ commented 1 year ago

I meet another error at evaluation step2 and step3, because of len(prediction_trajectory.shape) != 4. image