Function init_distributed_mode

utils/utils.py:315–340

(args)

def init_distributed_mode(args):
    if "RANK" in os.environ and "WORLD_SIZE" in os.environ:
        args.rank = int(os.environ["RANK"])
        args.world_size = int(os.environ["WORLD_SIZE"])
        args.gpu = int(os.environ["LOCAL_RANK"])
    elif "SLURM_PROCID" in os.environ:
        args.rank = int(os.environ["SLURM_PROCID"])
        args.gpu = args.rank % torch.cuda.device_count()
    else:
        print("Not using distributed mode")
        args.distributed = False
        return

    args.distributed = True

    torch.cuda.set_device(args.gpu)
    args.dist_backend = "nccl"
    print("| distributed init (rank {}): {}".format(args.rank, args.dist_url), flush=True)
    torch.distributed.init_process_group(
        backend=args.dist_backend,
        init_method=args.dist_url,
        world_size=args.world_size,
        rank=args.rank,
    )
    torch.distributed.barrier()
    setup_for_distributed(args.rank == 0)


# -------------------------------------------------------- #