Class TaskSpecDef

tensorlayer/distributed.py:231–363

Specification for a distributed task. It contains the job name, index of the task, the parameter servers and the worker servers. If you want to use the last worker for continuous evaluation you can call the method `use_last_worker_as_evaluator` which returns a new :class:`TaskSpecDe

@deprecated(date="2018-10-30", instructions="Using the TensorLayer distributed trainer.")
class TaskSpecDef(object):
    """Specification for a distributed task.

    It contains the job name, index of the task,
    the parameter servers and the worker servers. If you want to use the last worker
    for continuous evaluation you can call the method `use_last_worker_as_evaluator`
    which returns a new :class:`TaskSpecDef` object without the last worker in the
    cluster specification.

    Parameters
    ----------
    task_type : str
        Task type. One of `master`, `worker` or `ps`.
    index : int
        The zero-based index of the task. Distributed training jobs will have a single
        master task, one or more parameter servers, and one or more workers.
    trial : int
        The identifier of the trial being run.
    ps_hosts : str OR list of str
        A string with a coma separate list of hosts for the parameter servers
        or a list of hosts.
    worker_hosts : str OR list of str
        A string with a coma separate list of hosts for the worker servers
        or a list of hosts.
    master : str
        A string with the master hosts

    Notes
    ----------
    master might not be included in TF_CONFIG and can be None. The shard_index is adjusted
    in any case to assign 0 to master and >= 1 to workers.
    This implementation doesn't support sparse arrays in the `TF_CONFIG` variable as the
    official TensorFlow documentation shows, as it is not a supported by the json
    definition.

    References
    ----------
    - `ML-engine trainer considerations <https://cloud.google.com/ml-engine/docs/trainer-considerations#use_tf_config>`__

    """

    def __init__(self, task_type='master', index=0, trial=None, ps_hosts=None, worker_hosts=None, master=None):
        self.type = task_type
        self._index = int(index)
        self._cluster_spec = None
        self.num_workers = 1
        self.num_ps = 0
        self.shard_index = int(index)
        self._master = True
        self.trial = trial
        self.ps_hosts = ps_hosts
        self.worker_hosts = worker_hosts
        self.master = master
        self._server = None

        if ps_hosts and worker_hosts:
            self.ps_hosts = ps_hosts if isinstance(ps_hosts, list) else ps_hosts.split(',')
            self.num_ps = len(self.ps_hosts)