Is there an easy way to lighten the model? #26
Description
I have a video card with 12 GB of memory, but I can train only with batch size 1, if try increase batch 1 I get an error CUDA out of memory
{{ message }}
I have a video card with 12 GB of memory, but I can train only with batch size 1, if try increase batch 1 I get an error CUDA out of memory