Open ywm5 opened 1 year ago
I set the n_proc, num_workers, and n_gpu to 1 and it seems to solve the OOM problem on my device.
Looks like ray
has memory leak issue and up till now there's no fix yet:
https://github.com/ray-project/ray/issues/25779
you need to wait for ray-2.5.0
release
ray.exceptions.RayTaskError(RayOutOfMemoryError): ray::process_with_single_worker() (pid=17640, ip=127.0.0.1) File "python\ray_raylet.pyx", line 623, in ray._raylet.execute_task File "E:\Anaconda\envs\NeuralReconpython39\lib\site-packages\ray_private\memory_monitor.py", line 162, in raise_if_low_memory raise RayOutOfMemoryError( ray._private.memory_monitor.RayOutOfMemoryError: More than 95% of the memory on node yanwm5 is used (15.08 / 15.73 GB). The top 10 memory consumers are:
"I want to know how much memory is generate_gt.py required to run, but I don't have enough 16GB of memory."