Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error training using the nuscenes-mini dataset #34

Open
Cxb0219 opened this issue Jul 24, 2024 · 1 comment
Open

Error training using the nuscenes-mini dataset #34

Cxb0219 opened this issue Jul 24, 2024 · 1 comment

Comments

@Cxb0219
Copy link

Cxb0219 commented Jul 24, 2024

Thank you for your excellent work!
I am running "nusc_newsplit_480_60x30_24e.py" using the nuscenes-mini dataset to change to single-card training, but there is no result when the training goes to "evaluating 3 categories". And I can't find the "tmp_gts_nusc_60*30_newsplit.pkl" file. Do you know what's wrong?

[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>]81/81, 3.9 task/s, elapsed: 21s, ETA:0slen of the results 81
saving submissions results to ./work_dirs/nusc_newsplit_480_60x30_24e/submission_vector.jsoncollected 81 samples in 0.00s
loading cached gts from ./tmp_gts_nusc_60x30_newsplit.pkl
evaluating 3 categories...
[ ]0/3, elapsed: 0s, ETA:

@yuantianyuan01
Copy link
Owner

Hi, thanks for your interest in our work!

If you find your program stuck at evaluating 3 categories, it could be due to your device not supporting multi-processing. Try disabling multi-processing in the evaluation code. Additionally, the message 'loading cached gts from ./tmp_gts_nusc_60x30_newsplit.pkl' suggests that the program expects this file to exist.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants