AutoBots

AutoBots copied to clipboard

Thanks for your excellent work! In the following objective, the approximating posterior of the latent variable is p_old(z|y,x1:t).The paper has said it can be calculated because the latent variable z...

ChengkaiYang

Thank you for open-sourcing your great work! We are currently looking for transformer-based forecasting models that work well on the ETH-UCY dataset. Do you know how AutoBots performs on the...

YuejiangLIU

I have one question about the visualization of prediction results. After I have the prediction of joint mode, how can I plot both ego and agents in the ego's map?...

GilgameshD

Hey, Thanks for open sourcing the code. I had few doubts regarding the computation of marginal and joint errors in train.py. 1. agent masking is different for computing [marginal error](https://github.com/roggirg/AutoBots/blob/master/train.py#L154)...

Dhagash4

The loss calculation in the paper includes log p(Z | X) and log p(Y|Z,X), but in the code https://github.com/roggirg/AutoBots/blob/3a61ad9f80603f99ab1e9cc535acccf72c5d6bea/utils/train_helpers.py#L72 only the p(Y|Z,X) participates in the loss calculation. Please give me...

liuyueChang

Hi there, Could you share the pre-trained model weights for the NuScecnes dataset? Thanks in advance! Maarten

MaartenHugenholtz

create_h5_nusc.py then error came out

2

i use the mini data of nusecene and orgnize the file dir as you showed in readme.. but it errored like this: Traceback (most recent call last): File ".\datasets\nuscenes\create_h5_nusc.py", line...

KYYOnull

Efficiency about MapEncoders

1

Dear Author, It has been two years ago since Autobots published. I've trained Autobots on AV2 dataset recently but found it didn't get competitive result on official test dataset of...

ChengkaiYang

Hi @roggirg @fgolemo, Thanks for providing the code for this project! I use Autobots as a backbone in my project. To ensure I use the proper LICENSE, could you please...

GilgameshD