Python v1.identity方法代码示例

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def _build_aux_head(net, end_points, num_classes, hparams, scope):
  """Auxiliary head used for all models across all datasets."""
  with tf.variable_scope(scope):
    aux_logits = tf.identity(net)
    with tf.variable_scope('aux_logits'):
      aux_logits = slim.avg_pool2d(
          aux_logits, [5, 5], stride=3, padding='VALID')
      aux_logits = slim.conv2d(aux_logits, 128, [1, 1], scope='proj')
      aux_logits = slim.batch_norm(aux_logits, scope='aux_bn0')
      aux_logits = tf.nn.relu(aux_logits)
      # Shape of feature map before the final layer.
      shape = aux_logits.shape
      if hparams.data_format == 'NHWC':
        shape = shape[1:3]
      else:
        shape = shape[2:4]
      aux_logits = slim.conv2d(aux_logits, 768, shape, padding='VALID')
      aux_logits = slim.batch_norm(aux_logits, scope='aux_bn1')
      aux_logits = tf.nn.relu(aux_logits)
      aux_logits = contrib_layers.flatten(aux_logits)
      aux_logits = slim.fully_connected(aux_logits, num_classes)
      end_points['AuxLogits'] = aux_logits 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def simulate(self, action):

    # There is subtlety here. We need to collect data
    # obs, action = policy(obs), done, reward = env(abs, action)
    # Thus we need to enqueue data before assigning new observation

    reward, done = self._batch_env.simulate(action)

    with tf.control_dependencies([reward, done]):
      enqueue_op = self.speculum.enqueue(
          [self._observ.read_value(), reward, done, action])

    with tf.control_dependencies([enqueue_op]):
      assign = self._observ.assign(self._batch_env.observ)

    with tf.control_dependencies([assign]):
      return tf.identity(reward), tf.identity(done) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def simulate(self, action):
    reward, done = self._batch_env.simulate(action)
    with tf.control_dependencies([reward, done]):
      new_observ = tf.expand_dims(self._batch_env.observ, axis=1)

      # If we shouldn't stack, i.e. self.history == 1, then just assign
      # new_observ to self._observ and return from here.
      if self.history == 1:
        with tf.control_dependencies([self._observ.assign(new_observ)]):
          return tf.identity(reward), tf.identity(done)

      # If we should stack, then do the required work.
      old_observ = tf.gather(
          self._observ.read_value(),
          list(range(1, self.history)),
          axis=1)
      with tf.control_dependencies([new_observ, old_observ]):
        with tf.control_dependencies([self._observ.assign(
            tf.concat([old_observ, new_observ], axis=1))]):
          return tf.identity(reward), tf.identity(done) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def weight_decay_and_noise(loss, hparams, learning_rate, var_list=None):
  """Apply weight decay and weight noise."""
  if var_list is None:
    var_list = tf.trainable_variables()

  decay_vars = [v for v in var_list]
  noise_vars = [v for v in var_list if "/body/" in v.name]

  weight_decay_loss = weight_decay(hparams.weight_decay, decay_vars)
  if hparams.weight_decay and common_layers.should_generate_summaries():
    tf.summary.scalar("losses/weight_decay", weight_decay_loss)
  weight_noise_ops = weight_noise(hparams.weight_noise, learning_rate,
                                  noise_vars)

  with tf.control_dependencies(weight_noise_ops):
    loss = tf.identity(loss)

  loss += weight_decay_loss
  return loss 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def infer(self,
            features=None,
            decode_length=1,
            beam_size=1,
            top_beams=1,
            alpha=0.0,
            use_tpu=False):
    """Predict."""
    features["targets"] = tf.identity(features["inputs"])
    logits, _ = self(features)
    log_probs = common_layers.log_prob_from_logits(logits)
    predictions, scores = common_layers.argmax_with_score(log_probs)
    return {
        "outputs": predictions,
        "scores": scores,
    } 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def post_attention(self, token, x):
    """Called after self-attention. The memory can be updated here.

    Args:
      token: Data returned by pre_attention, which can be used to carry over
        state related to the current memory operation.
      x: a Tensor of data after self-attention and feed-forward
    Returns:
      a (possibly modified) version of the input x
    """
    with tf.control_dependencies([
        self.previous_segment.assign(token[0]),
        self.previous_vals.assign(token[1]),
        self.previous_bias.assign(token[2]),
        ]):
      return tf.identity(x) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def _finalize(self, _, contents):
    """Structure output and compute segment and position metadata."""

    # The output shape information is lost during the filter; however we can
    # guarantee the shape. (That's the point of this exercise, after all!)
    contents.set_shape((self._packed_length, self._num_sequences * 2))

    # Both the dummy branch of the scan step function and the eviction dataset
    # use vectors of minus one. The cost of this check is negligible and the
    # leakage of such dummy sequences would be difficult to debug downstream.
    check_leaks = tf.assert_none_equal(contents, -tf.ones_like(contents))
    with tf.control_dependencies([check_leaks]):
      contents = tf.identity(contents)

    segment, position = self._compute_auxiliary_structure(contents)
    return {"contents": contents[:, :self._num_sequences],
            "segment": segment, "position": position} 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def write_to_variable(tensor, fail_if_exists=True):
  """Saves a tensor for later retrieval on CPU."""
  # Only relevant for debugging.
  debug_name = 'tpu_util__' + tensor.name.split(':')[0]

  reuse = False if fail_if_exists else tf.compat.v1.AUTO_REUSE
  with tf.variable_scope(top_level_scope, reuse=reuse):
    variable = tf.get_variable(
        name=debug_name,
        shape=tensor.shape,
        dtype=tensor.dtype,
        trainable=False,
        use_resource=True)

  var_store[tensor] = variable
  with tf.control_dependencies([variable.assign(tensor)]):
    tensor_copy = tf.identity(tensor)
  var_store[tensor_copy] = variable
  return tensor_copy 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def test_resource_variable(self):
    with tf.variable_scope('', use_resource=True):
      relu = self.build_model()
    gamma_tensor, gamma_source_op = self.get_gamma(relu)
    variable = tpu_util.maybe_convert_to_variable(gamma_tensor)

    # First assert that we didn't return the original tensor
    self.assertNotEqual(variable, gamma_tensor)

    # Now check that the variable created by maybe_convert_to_variable is
    # driven by the same op as the tensor passed as input.
    self.assertEqual(variable.op, gamma_source_op)

    # If input tensor is separated from a variable by an extra hop of Identity,
    # maybe_read_variable pretends the Identity op isn't there.
    identity_tensor = tf.identity(gamma_tensor)
    self.assertEqual(
        tpu_util.maybe_convert_to_variable(identity_tensor), variable) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def test_assign_grouping_no_neighbor_groups(self):
    # No ops have groups.
    self.op_group_dict = {}

    # Call handler to assign grouping.
    handler = depth_to_space_op_handler.DepthToSpaceOpHandler()
    handler.assign_grouping(self.dts_op, self.mock_op_reg_manager)

    # Verify manager looks up OpSlice for ops of interest.
    self.mock_op_reg_manager.get_op_slices.assert_has_calls(
        [mock.call(self.id1_op),
         mock.call(self.id2_op)])

    # Verify manager does not group.
    self.mock_op_reg_manager.group_op_slices.assert_not_called()

    # Verify manager processes grouping for identity ops.
    self.mock_op_reg_manager.process_ops.assert_called_once_with(
        [self.id1_op]) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def testGetRegularizerForConcatWithNone(self, test_concat, depth):
    image = tf.constant(0.0, shape=[1, 17, 19, 3])
    conv2 = layers.conv2d(image, 5, [1, 1], padding='SAME', scope='conv2')
    other_input = tf.add(
        tf.identity(tf.constant(3.0, shape=[1, 17, 19, depth])), 3.0)
    # other_input has None as regularizer.
    concat = tf.concat([other_input, conv2], 3)
    output = tf.add(concat, concat, name='output_out')
    op = concat.op if test_concat else output.op

    # Instantiate OpRegularizerManager.
    op_handler_dict = self._default_op_handler_dict
    op_handler_dict['Conv2D'] = StubConvSourceOpHandler(add_concat_model_stub)
    op_reg_manager = orm.OpRegularizerManager([output.op], op_handler_dict)

    expected_alive = add_concat_model_stub.expected_alive()
    alive = op_reg_manager.get_regularizer(op).alive_vector
    self.assertAllEqual([True] * depth, alive[:depth])
    self.assertAllEqual(expected_alive['conv2'], alive[depth:]) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def testAddN(self):
    inputs = tf.zeros([2, 4, 4, 3])
    identity1 = tf.identity(inputs)
    identity2 = tf.identity(inputs)
    identity3 = tf.identity(inputs)
    identity4 = tf.identity(inputs)
    add_n = tf.add_n([identity1, identity2, identity3, identity4])
    batch_norm = layers.batch_norm(add_n)

    manager = orm.OpRegularizerManager(
        [batch_norm.op], op_handler_dict=self._default_op_handler_dict)

    op_slices = manager.get_op_slices(identity1.op)
    self.assertLen(op_slices, 1)
    op_group = manager.get_op_group(op_slices[0]).op_slices

    # Verify all ops are in the same group.
    for test_op in (identity1.op, identity2.op, identity3.op, identity4.op,
                    add_n.op, batch_norm.op):
      test_op_slices = manager.get_op_slices(test_op)
      self.assertLen(test_op_slices, 1)
      self.assertIn(test_op_slices[0], op_group) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def testAddN_Duplicates(self):
    inputs = tf.zeros([2, 4, 4, 3])
    identity = tf.identity(inputs)
    add_n = tf.add_n([identity, identity, identity, identity])
    batch_norm = layers.batch_norm(add_n)

    manager = orm.OpRegularizerManager(
        [batch_norm.op], op_handler_dict=self._default_op_handler_dict)

    op_slices = manager.get_op_slices(identity.op)
    self.assertLen(op_slices, 1)
    op_group = manager.get_op_group(op_slices[0]).op_slices

    # Verify all ops are in the same group.
    for test_op in (identity.op, add_n.op, batch_norm.op):
      test_op_slices = manager.get_op_slices(test_op)
      self.assertLen(test_op_slices, 1)
      self.assertIn(test_op_slices[0], op_group) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def testInit_AddConcat_AllOps(self):
    with arg_scope(self._batch_norm_scope()):
      inputs = tf.zeros([2, 4, 4, 3])
      c1 = layers.conv2d(inputs, num_outputs=10, kernel_size=3, scope='conv1')
      c2 = layers.conv2d(inputs, num_outputs=10, kernel_size=3, scope='conv2')
      add = c1 + c2
      c3 = layers.conv2d(add, num_outputs=10, kernel_size=3, scope='conv3')
      out = tf.identity(c3)
      concat = tf.concat([c1, c2], axis=3)
      c4 = layers.conv2d(concat, num_outputs=10, kernel_size=3, scope='conv4')

    manager = orm.OpRegularizerManager(
        [out.op], self._default_op_handler_dict, SumGroupingRegularizer)

    # Op c4 is not in the DFS path of out.  Verify that OpRegularizerManager
    # does not process c4.
    self.assertNotIn(c4.op, manager.ops)
    self.assertNotIn(concat.op, manager.ops) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import identity [as 别名]
def testProcessOps_DuplicatesRemoved(self):
    inputs = tf.zeros([2, 4, 4, 3])
    batch_norm = layers.batch_norm(inputs)
    identity1 = tf.identity(batch_norm)
    identity2 = tf.identity(batch_norm)

    manager = orm.OpRegularizerManager(
        [identity1.op, identity2.op],
        op_handler_dict=self._default_op_handler_dict)
    manager.process_ops([identity1.op, identity2.op, batch_norm.op])
    # Try to process the same ops again.
    manager.process_ops([identity1.op, identity2.op, batch_norm.op])

    self.assertLen(manager._op_deque, 3)
    self.assertEqual(batch_norm.op, manager._op_deque.pop())
    self.assertEqual(identity2.op, manager._op_deque.pop())
    self.assertEqual(identity1.op, manager._op_deque.pop())