Function init_distributed_mode

util/misc.py:230–272

(args)

        torch.save(*args, **kwargs)

def init_distributed_mode(args):
    if args.dist_on_itp:
        args.rank = int(os.environ['OMPI_COMM_WORLD_RANK'])
        args.world_size = int(os.environ['OMPI_COMM_WORLD_SIZE'])
        args.gpu = int(os.environ['OMPI_COMM_WORLD_LOCAL_RANK'])
        args.dist_url = "tcp://%s:%s" % (os.environ['MASTER_ADDR'], os.environ['MASTER_PORT'])
        os.environ['LOCAL_RANK'] = str(args.gpu)
        os.environ['RANK'] = str(args.rank)
        os.environ['WORLD_SIZE'] = str(args.world_size)
        # ["RANK", "WORLD_SIZE", "MASTER_ADDR", "MASTER_PORT", "LOCAL_RANK"]
    elif '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:
        os.environ['MASTER_PORT'] = '8994'
        while 'MASTER_ADDR' not in os.environ or len(os.environ['MASTER_ADDR'].strip()) == 0:
            os.environ['MASTER_ADDR'] = subprocess.check_output('sinfo -Nh -n %s | head -n 1 | awk \'{print $1}\'' % os.environ['SLURM_NODELIST'], shell=True, ).decode().strip()
            time.sleep(1)
        print(os.environ['MASTER_ADDR'])
        args.world_size = int(os.environ['SLURM_NPROCS'])
        args.rank = int(os.environ['SLURM_PROCID'])
        args.gpu = args.rank % torch.cuda.device_count()
        args.local_rank = args.gpu
        os.environ['LOCAL_RANK'] = str(args.gpu)
        os.environ['WORLD_SIZE'] = str(args.world_size)
        os.environ['RANK'] = str(args.rank)
    else:
        print('Not using distributed mode')
        setup_for_distributed(is_master=True)  # hack
        args.distributed = False
        return

    args.distributed = True

    torch.cuda.set_device(args.gpu)
    args.dist_backend = 'nccl'
    print('| distributed init (rank {}): {}, gpu {}'.format(
        args.rank, args.dist_url, args.gpu), 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)


def init_distributed_mode1(args):