CUDA error

[z-jiaming]

Thanks for your great work! I try the eval_davis.py with adm model after create with conda env create -f environment.yml.

But it raise a cuda error:

I passed CUDA_LAUNCH_BLOCKING=1, then:

I try to delete codes which may have an effect, including gc.collect() and 'torch.cuda.empty_cache()',. but it doesn't work.

Would you mind help me to slove this? Thanks a lot!

[Tsingularity]

This seems to imply GPU is out of memory. Could you try decrease the n_last_frames argument? This would lead to very marginal performance drop though.

[z-jiaming]

Thanks for your reply! I decrease the n_last_framesargument and it works. Could you please tell me the GPU memory requires in your standard setup?

[Tsingularity]

The video experiments are done on A100.

[z-jiaming]

Is it the 80G version?

[Tsingularity]

yes