search

JOP-Lee / READ

AAAI2023，implementation of "READ: Large-Scale Neural Scene Rendering for Autonomous Driving", the experimental results are significantly better than Nerf-based methods
https://github.com/JOP-Lee/READ-Large-Scale-Neural-Scene-Rendering-for-Autonomous-Driving
GNU General Public License v2.0
449 stars 55 forks source link

NaN or Inf found in input tensor. #32

Open vfishc opened 1 year ago

vfishc commented 1 year ago

Thanks for your excellent work!!!

But during running the codes in the folder src with the data offered by you(because I don't have a monitor), the evaluate loss are NAN. The printed logs are:

image. If any opearations of mine are wrong or there are some issues in the data or code?

Best wishes

JOP-Lee commented 1 year ago

I think your training data is too small to be divided into test sets

vfishc commented 1 year ago

But I use the data and config files offered by the authors? What should I revise to include all of the training data?

Thanks~

booker-max commented 1 year ago

But I use the data and config files offered by the authors? What should I revise to include all of the training data?

Thanks~

Hi, I encountered the same problem as you, I also used the data and config files provided by the author, did you solve the problem?

yixionghuo commented 1 year ago

Hi, I had the same problem as you, did you solve it?

baekhyun77 commented 11 months ago

Hi，Has anyone solved this problem?

zZH1222hui commented 11 months ago

Did you solve this problem?

dyzxzeng commented 10 months ago

The data is not placed in the right path. You can refer to the path.yaml.

VerseWei commented 9 months ago

Hello, I am sure I placed the sample data in the path indicated by path.yaml, but I still encountered this issue. How did you do it? Can you explain in detail? Thank you @dyzxzeng

VerseWei commented 9 months ago

I am in the same situation as you. Have you solved this problem? @booker-max