variable_mgr.py 文件源码

def savable_variables(self):
    """Returns a list/dict of savable variables to pass to tf.train.Saver."""
    params = {}
    for v in tf.global_variables():
      assert (v.name.startswith(variable_mgr_util.PS_SHADOW_VAR_PREFIX + '/v0/')
              or v.name in ('global_step:0', 'loss_scale:0',
                            'loss_scale_normal_steps:0')), (
                                'Invalid global variable: %s' % v)
      # We store variables in the checkpoint with the shadow variable prefix
      # removed so we can evaluate checkpoints in non-distributed replicated
      # mode. The checkpoints can also be loaded for training in
      # distributed_replicated mode.
      name = self._strip_port(self._remove_shadow_var_prefix_if_present(v.name))
      params[name] = v
    for v in tf.local_variables():
      # Non-trainable variables, such as batch norm moving averages, do not have
      # corresponding global shadow variables, so we add them here. Trainable
      # local variables have corresponding global shadow variables, which were
      # added in the global variable loop above.
      if v.name.startswith('v0/') and v not in tf.trainable_variables():
        params[self._strip_port(v.name)] = v
    return params