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.
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.