DriveLM

DriveLM copied to clipboard

Steering and Speed

1

Thank you for your detailed work. From your previous replies, I understand that ADE, FDE, and collision rate can be obtained from the UniAD project. However, could you clarify how...

greenlight2124

could not convert string to float: 'The'

3

 I met this error when running eval on the test server. I don't know why because I can't see the full error log. I have successfully run the evaluation...

Leo-Yuyang

TypeError: cannot pickle '_thread.RLock' object

3

I met an error when running evaluation.py： Traceback (most recent call last): File "evaluation.py", line 189, in output = evaluation.evaluation() File "evaluation.py", line 146, in evaluation scores["chatgpt"] = self.eval_chatGPT(self.GPT) File...

Cynthia11281128

ADE、FDE、collision rate

1

Thanks for your understanding work, could you point out how to get ADE、FDE、 collision rate on planning, besides VQA-metric in [challenge](https://github.com/OpenDriveLab/DriveLM/tree/main/challenge)

123456000xzw

Questions Regarding Prompt Generation and Motion Dataset Availability

1

Hello! I have two questions: Regarding the open-source code you provided, it seems to only cover the part of a single query. I didn’t see the generation and transmission of...

HarrykingZLH

About the Processing of Trajectory Data

1

Could you kindly provide a detailed explanation of how the trajectory data is processed? Specifically, could you share more details about the process of discretizing the trajectory data? Thank you...

zhangye0402

BLIP-2 Baseline

1

Hi OpenDriveLab thanks for releasing this project it is very helpful. In the paper you mention BLIP-2 baseline, but code so far only has Llama-Adapter. I saw previously that you...

LCTPalmer

pre_checkpoint

1

What do the three pre_checkpoints represent? 

yuxr-smile

Wrong evaluation reply using ChatGPT

1

Hi, When I use my `output.json` and the repo's `test_eval.json`, it worked the first two times. However, now I see ChatGPT replies such as: > I would rate your answer...

anirudh-chakravarthy

How to run evaluation on the validation set?

1

Hi, Is is possible to provide a set of instructions to run evaluation on the validation set? From the README: > [test_eval.json](https://github.com/OpenDriveLab/DriveLM/blob/main/challenge/test_eval.json) is used for evaluation. [test_llama.json](https://github.com/OpenDriveLab/DriveLM/blob/main/challenge/test_llama.json) is used for...

anirudh-chakravarthy