Python tensorflow.device方法代碼示例

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def autosummary(name, value):
    id = name.replace('/', '_')
    if is_tf_expression(value):
        with tf.name_scope('summary_' + id), tf.device(value.device):
            update_op = _create_autosummary_var(name, value)
            with tf.control_dependencies([update_op]):
                return tf.identity(value)
    else: # python scalar or numpy array
        if name not in _autosummary_immediate:
            with absolute_name_scope('Autosummary/' + id), tf.device(None), tf.control_dependencies(None):
                update_value = tf.placeholder(tf.float32)
                update_op = _create_autosummary_var(name, update_value)
                _autosummary_immediate[name] = update_op, update_value
        update_op, update_value = _autosummary_immediate[name]
        run(update_op, {update_value: np.float32(value)})
        return value

# Create the necessary ops to include autosummaries in TensorBoard report.
# Note: This should be done only once per graph. 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def finalize_autosummaries():
    global _autosummary_finalized
    if _autosummary_finalized:
        return
    _autosummary_finalized = True
    init_uninited_vars([var for vars in _autosummary_vars.values() for var in vars])
    with tf.device(None), tf.control_dependencies(None):
        for name, vars in _autosummary_vars.items():
            id = name.replace('/', '_')
            with absolute_name_scope('Autosummary/' + id):
                sum = tf.add_n(vars)
                avg = sum[0] / sum[1]
                with tf.control_dependencies([avg]): # read before resetting
                    reset_ops = [tf.assign(var, tf.zeros(2)) for var in vars]
                    with tf.name_scope(None), tf.control_dependencies(reset_ops): # reset before reporting
                        tf.summary.scalar(name, avg)

# Internal helper for creating autosummary accumulators. 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def undo_loss_scaling(self, value):
        assert is_tf_expression(value)
        if not self.use_loss_scaling:
            return value
        return value * exp2(-self.get_loss_scaling_var(value.device))

#----------------------------------------------------------------------------
# Generic network abstraction.
#
# Acts as a convenience wrapper for a parameterized network construction
# function, providing several utility methods and convenient access to
# the inputs/outputs/weights.
#
# Network objects can be safely pickled and unpickled for long-term
# archival purposes. The pickling works reliably as long as the underlying
# network construction function is defined in a standalone Python module
# that has no side effects or application-specific imports. 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def testPS(self):
    deploy_config = model_deploy.DeploymentConfig(num_clones=1, num_ps_tasks=1)

    self.assertDeviceEqual(deploy_config.clone_device(0),
                           '/job:worker/device:GPU:0')
    self.assertEqual(deploy_config.clone_scope(0), '')
    self.assertDeviceEqual(deploy_config.optimizer_device(),
                           '/job:worker/device:CPU:0')
    self.assertDeviceEqual(deploy_config.inputs_device(),
                           '/job:worker/device:CPU:0')
    with tf.device(deploy_config.variables_device()):
      a = tf.Variable(0)
      b = tf.Variable(0)
      c = tf.no_op()
      d = slim.variable('a', [],
                        caching_device=deploy_config.caching_device())
    self.assertDeviceEqual(a.device, '/job:ps/task:0/device:CPU:0')
    self.assertDeviceEqual(a.device, a.value().device)
    self.assertDeviceEqual(b.device, '/job:ps/task:0/device:CPU:0')
    self.assertDeviceEqual(b.device, b.value().device)
    self.assertDeviceEqual(c.device, '')
    self.assertDeviceEqual(d.device, '/job:ps/task:0/device:CPU:0')
    self.assertDeviceEqual(d.value().device, '') 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def testVariablesPS(self):
    deploy_config = model_deploy.DeploymentConfig(num_ps_tasks=2)

    with tf.device(deploy_config.variables_device()):
      a = tf.Variable(0)
      b = tf.Variable(0)
      c = tf.no_op()
      d = slim.variable('a', [],
                        caching_device=deploy_config.caching_device())

    self.assertDeviceEqual(a.device, '/job:ps/task:0/device:CPU:0')
    self.assertDeviceEqual(a.device, a.value().device)
    self.assertDeviceEqual(b.device, '/job:ps/task:1/device:CPU:0')
    self.assertDeviceEqual(b.device, b.value().device)
    self.assertDeviceEqual(c.device, '')
    self.assertDeviceEqual(d.device, '/job:ps/task:0/device:CPU:0')
    self.assertDeviceEqual(d.value().device, '') 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def testCreateLogisticClassifier(self):
    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(0)
      tf_inputs = tf.constant(self._inputs, dtype=tf.float32)
      tf_labels = tf.constant(self._labels, dtype=tf.float32)

      model_fn = LogisticClassifier
      clone_args = (tf_inputs, tf_labels)
      deploy_config = model_deploy.DeploymentConfig(num_clones=1)

      self.assertEqual(slim.get_variables(), [])
      clones = model_deploy.create_clones(deploy_config, model_fn, clone_args)
      clone = clones[0]
      self.assertEqual(len(slim.get_variables()), 2)
      for v in slim.get_variables():
        self.assertDeviceEqual(v.device, 'CPU:0')
        self.assertDeviceEqual(v.value().device, 'CPU:0')
      self.assertEqual(clone.outputs.op.name,
                       'LogisticClassifier/fully_connected/Sigmoid')
      self.assertEqual(clone.scope, '')
      self.assertDeviceEqual(clone.device, 'GPU:0')
      self.assertEqual(len(slim.losses.get_losses()), 1)
      update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
      self.assertEqual(update_ops, []) 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def testCreateSingleclone(self):
    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(0)
      tf_inputs = tf.constant(self._inputs, dtype=tf.float32)
      tf_labels = tf.constant(self._labels, dtype=tf.float32)

      model_fn = BatchNormClassifier
      clone_args = (tf_inputs, tf_labels)
      deploy_config = model_deploy.DeploymentConfig(num_clones=1)

      self.assertEqual(slim.get_variables(), [])
      clones = model_deploy.create_clones(deploy_config, model_fn, clone_args)
      clone = clones[0]
      self.assertEqual(len(slim.get_variables()), 5)
      for v in slim.get_variables():
        self.assertDeviceEqual(v.device, 'CPU:0')
        self.assertDeviceEqual(v.value().device, 'CPU:0')
      self.assertEqual(clone.outputs.op.name,
                       'BatchNormClassifier/fully_connected/Sigmoid')
      self.assertEqual(clone.scope, '')
      self.assertDeviceEqual(clone.device, 'GPU:0')
      self.assertEqual(len(slim.losses.get_losses()), 1)
      update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
      self.assertEqual(len(update_ops), 2) 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def testCreateOnecloneWithPS(self):
    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(0)
      tf_inputs = tf.constant(self._inputs, dtype=tf.float32)
      tf_labels = tf.constant(self._labels, dtype=tf.float32)

      model_fn = BatchNormClassifier
      clone_args = (tf_inputs, tf_labels)
      deploy_config = model_deploy.DeploymentConfig(num_clones=1,
                                                    num_ps_tasks=1)

      self.assertEqual(slim.get_variables(), [])
      clones = model_deploy.create_clones(deploy_config, model_fn, clone_args)
      self.assertEqual(len(clones), 1)
      clone = clones[0]
      self.assertEqual(clone.outputs.op.name,
                       'BatchNormClassifier/fully_connected/Sigmoid')
      self.assertDeviceEqual(clone.device, '/job:worker/device:GPU:0')
      self.assertEqual(clone.scope, '')
      self.assertEqual(len(slim.get_variables()), 5)
      for v in slim.get_variables():
        self.assertDeviceEqual(v.device, '/job:ps/task:0/CPU:0')
        self.assertDeviceEqual(v.device, v.value().device) 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def testNoSummariesOnGPUForEvals(self):
    with tf.Graph().as_default():
      deploy_config = model_deploy.DeploymentConfig(num_clones=2)

      # clone function creates a fully_connected layer with a regularizer loss.
      def ModelFn():
        inputs = tf.constant(1.0, shape=(10, 20), dtype=tf.float32)
        reg = tf.contrib.layers.l2_regularizer(0.001)
        tf.contrib.layers.fully_connected(inputs, 30, weights_regularizer=reg)

      # No optimizer here, it's an eval.
      model = model_deploy.deploy(deploy_config, ModelFn)
      # The model summary op should have a few summary inputs and all of them
      # should be on the CPU.
      self.assertTrue(model.summary_op.op.inputs)
      for inp in  model.summary_op.op.inputs:
        self.assertEqual('/device:CPU:0', inp.device) 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def _optimize_clone(optimizer, clone, num_clones, regularization_losses,
                    **kwargs):
  """Compute losses and gradients for a single clone.

  Args:
    optimizer: A tf.Optimizer  object.
    clone: A Clone namedtuple.
    num_clones: The number of clones being deployed.
    regularization_losses: Possibly empty list of regularization_losses
      to add to the clone losses.
    **kwargs: Dict of kwarg to pass to compute_gradients().

  Returns:
    A tuple (clone_loss, clone_grads_and_vars).
      - clone_loss: A tensor for the total loss for the clone.  Can be None.
      - clone_grads_and_vars: List of (gradient, variable) for the clone.
        Can be empty.
  """
  sum_loss = _gather_clone_loss(clone, num_clones, regularization_losses)
  clone_grad = None
  if sum_loss is not None:
    with tf.device(clone.device):
      clone_grad = optimizer.compute_gradients(sum_loss, **kwargs)
  return sum_loss, clone_grad 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def _add_train_op(self):
    """Sets self._train_op, op to run for training."""
    hps = self._hps

    self._lr_rate = tf.maximum(
        hps.min_lr,  # min_lr_rate.
        tf.train.exponential_decay(hps.lr, self.global_step, 30000, 0.98))

    tvars = tf.trainable_variables()
    with tf.device(self._get_gpu(self._num_gpus-1)):
      grads, global_norm = tf.clip_by_global_norm(
          tf.gradients(self._loss, tvars), hps.max_grad_norm)
    tf.summary.scalar('global_norm', global_norm)
    optimizer = tf.train.GradientDescentOptimizer(self._lr_rate)
    tf.summary.scalar('learning rate', self._lr_rate)
    self._train_op = optimizer.apply_gradients(
        zip(grads, tvars), global_step=self.global_step, name='train_step') 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def main(_):
  """Train a word2vec model."""
  if not FLAGS.train_data or not FLAGS.eval_data or not FLAGS.save_path:
    print("--train_data --eval_data and --save_path must be specified.")
    sys.exit(1)
  opts = Options()
  with tf.Graph().as_default(), tf.Session() as session:
    with tf.device("/cpu:0"):
      model = Word2Vec(opts, session)
      model.read_analogies() # Read analogy questions
    for _ in xrange(opts.epochs_to_train):
      model.train()  # Process one epoch
      model.eval()  # Eval analogies.
    # Perform a final save.
    model.saver.save(session, os.path.join(opts.save_path, "model.ckpt"),
                     global_step=model.global_step)
    if FLAGS.interactive:
      # E.g.,
      # [0]: model.analogy(b'france', b'paris', b'russia')
      # [1]: model.nearby([b'proton', b'elephant', b'maxwell'])
      _start_shell(locals()) 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def main(_):
  """Train a word2vec model."""
  if not FLAGS.train_data or not FLAGS.eval_data or not FLAGS.save_path:
    print("--train_data --eval_data and --save_path must be specified.")
    sys.exit(1)
  opts = Options()
  with tf.Graph().as_default(), tf.Session() as session:
    with tf.device("/cpu:0"):
      model = Word2Vec(opts, session)
      model.read_analogies() # Read analogy questions
    for _ in xrange(opts.epochs_to_train):
      model.train()  # Process one epoch
      model.eval()  # Eval analogies.
    # Perform a final save.
    model.saver.save(session,
                     os.path.join(opts.save_path, "model.ckpt"),
                     global_step=model.global_step)
    if FLAGS.interactive:
      # E.g.,
      # [0]: model.analogy(b'france', b'paris', b'russia')
      # [1]: model.nearby([b'proton', b'elephant', b'maxwell'])
      _start_shell(locals()) 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def get_hint_pool_idxs(self, normalized_query):
    """Get small set of idxs to compute nearest neighbor queries on.

    This is an expensive look-up on the whole memory that is used to
    avoid more expensive operations later on.

    Args:
      normalized_query: A Tensor of shape [None, key_dim].

    Returns:
      A Tensor of shape [None, choose_k] of indices in memory
      that are closest to the queries.

    """
    # look up in large memory, no gradients
    with tf.device(self.nn_device):
      similarities = tf.matmul(tf.stop_gradient(normalized_query),
                               self.mem_keys, transpose_b=True, name='nn_mmul')
    _, hint_pool_idxs = tf.nn.top_k(
        tf.stop_gradient(similarities), k=self.choose_k, name='nn_topk')
    return hint_pool_idxs 

# 需要導入模塊: import tensorflow [as 別名]
# 或者: from tensorflow import device [as 別名]
def testVariableWithVariableDeviceChooser(self):

    with tf.Graph().as_default():
      device_fn = variables.VariableDeviceChooser(num_parameter_servers=2)
      with scopes.arg_scope([variables.variable], device=device_fn):
        a = variables.variable('a', [])
        b = variables.variable('b', [])
        c = variables.variable('c', [], device='cpu:12')
        d = variables.variable('d', [])
        with tf.device('cpu:99'):
          e_init = tf.constant(12)
        e = variables.variable('e', initializer=e_init)
      # The values below highlight how the VariableDeviceChooser puts initial
      # values on the same device as the variable job.
      self.assertDeviceEqual(a.device, '/job:ps/task:0/cpu:0')
      self.assertDeviceEqual(a.initial_value.device, a.device)
      self.assertDeviceEqual(b.device, '/job:ps/task:1/cpu:0')
      self.assertDeviceEqual(b.initial_value.device, b.device)
      self.assertDeviceEqual(c.device, '/cpu:12')
      self.assertDeviceEqual(c.initial_value.device, c.device)
      self.assertDeviceEqual(d.device, '/job:ps/task:0/cpu:0')
      self.assertDeviceEqual(d.initial_value.device, d.device)
      self.assertDeviceEqual(e.device, '/job:ps/task:1/cpu:0')
      self.assertDeviceEqual(e.initial_value.device, '/cpu:99')