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

Question about training time of EDAPS #3

Open
Tocmac opened this issue Jan 22, 2024 · 1 comment
Open

Question about training time of EDAPS #3

Tocmac opened this issue Jan 22, 2024 · 1 comment

Comments

@Tocmac
Copy link

Tocmac commented Jan 22, 2024

Hello, thanks for your great work. I noticed that in your paper, you mentioned that the training of EDAPS only requires 21 hours on a single RTX 2080Ti GPU. However, when I trained EDAPS using the default settings and the provided script,

python run_experiments.py --config configs/edaps/syn2cs_uda_warm_dfthings_rcs_croppl_a999_edaps_s0.py

it took almost three days to complete. I used a single RTX 2080Ti GPU as well. Additionally, I trained DAFormer with the default settings, and it only took one day. I would like to know if there is any mistake I made during the training process. I would greatly appreciate any suggestions you could provide. Thank you!

@susaha
Copy link
Owner

susaha commented Feb 8, 2024

@Tocmac : You can check the training and evaluation log here: https://drive.google.com/file/d/1Dqm58cW8l6cWl_uhJ-I0QRx3DaCjp_--/view?usp=sharing, or 20221025_114656.log.

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