I run neural nets in libtorch.
(我在libtorch中运行神经网络。)
For optimal performance, should I call at::init_num_threads before calling anything else on Torch?
(为了获得最佳性能,在Torch上调用其他任何功能之前,我应该先调用::: init_num_threads吗?)
In what circumstances should I call it?(在什么情况下应该称呼它?)
ask by user31264 translate from so