About Code release for "SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling" (NeurIPS 2023 Spotlight), https://arxiv.org/abs/2302.00861
Thanks for the nice paper and opensourcing the code.
I am trying to run the code in multi gpu fashion using 8 gpus, but I get the below error RuntimeError: grad can be implicitly created only for scalar outputs
Hi team,
Thanks for the nice paper and opensourcing the code.
I am trying to run the code in multi gpu fashion using 8 gpus, but I get the below error
RuntimeError: grad can be implicitly created only for scalar outputs
Does the current code support Multi-GPU ?