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

Training time of Unpaired Day2night #35

Open
wenyi-li opened this issue Apr 25, 2024 · 1 comment
Open

Training time of Unpaired Day2night #35

wenyi-li opened this issue Apr 25, 2024 · 1 comment

Comments

@wenyi-li
Copy link

Thanks for your impressive work! I'm curious about the training time required for the Unpaired Day2Night model on the BDD100K.

It took me around 1 day on a single A100 GPU for only 1k steps. This training time seems pretty long, and I have a feeling there might be some problems causing it to take so much time. Could you help me figure out what's going on?

Here are some of the training parameters:
--learning_rate="1e-5" --max_train_steps=25000
--train_batch_size=1 --gradient_accumulation_steps=1
--enable_xformers_memory_efficient_attention --validation_steps 250
--lambda_gan 0.5 --lambda_idt 1 --lambda_cycle 1

@ShenZheng2000
Copy link

ShenZheng2000 commented Jun 29, 2024

I'm also training BDD100K Day2Night. It takes about 16 hours on four 4090 GPUs to complete 25,000 training steps.

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