August0424
Results
3
comments of
August0424
I applied mixed precision training. Is this the main reason for the high CPU utility rate?
> > > You may use `CPUS_PER_TASK=2` to set the number of CPUs. Do you mean that adding environment variable `CPUS_PER_TASK` in the training bash script? It seems that this...
> > > 在yolov5-v4那里 我使用基础训练和稀疏训练在coco上都是正常的，一到剪枝这就出现了很奇怪的问题，一个是剪枝前测试模型的map几乎为0（训练时已经到0.5了），另一个是，对于我这边稀疏训练的模型，700万参数，它总是给我剪到600多万。很奇怪。方便加个QQ请教一下吗？