ConvKB
LemonQC opened this issue · comments
- TorchKGE version:
- Python version:
- Operating System:
Description
How to run ConvKB, OUT_OF_CUDA
What I Did
Hi, your issue description is not very detailed.
I assume you get a "RuntimeError: CUDA error: out of memory". You should try to reduce the batch size of the evaluate method. ConvKB with 500 filters might create a too big evaluation batch for your GPU.