search

GRAPH-0 / GraphGDP

Implementation for the paper: GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation
MIT License
22 stars 6 forks source link

CUDA error: out of memory #1

Closed lihuiliullh closed 1 year ago

lihuiliullh commented 1 year ago

Have you encountered this problem before? I think it is caused by dataParallel "score_model = torch.nn.DataParallel(score_model)".

CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

GRAPH-0 commented 1 year ago

CUDA error: out of memory Try to set lower batch_size in config when training or evaluation