This is an official repository of our paper "HRNeXt: High-Resolution Context Network for Crowd Pose Estimation" (published in IEEE Transactions on Multimedia)
python tools/train.py ${CONFIG_FILE} [optional arguments]
直接使用该指令会出现
RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.
需要加上-m torch.distributed.launch
但是我并不想每次都初始化分布式处理的进程组,有取消掉分布式训练的方法吗,这样不方便debug