darkforestgo train cuda runtime error (2) : out of memory at …

reduced batchsize from 256 to 64 and num_forward_models to 512 then it’s ok.

The GPU memory cap is 8G and this setting uses about 4G.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s