Esempio n. 1
0
  def _batch_norm_ops(self, test=False):
    name = "batch_norm"

    g = tf.Graph()
    with g.as_default():
      tf.compat.v1.set_random_seed(self.name_to_seed(name))
      input_tensor = tf.compat.v1.get_variable(
          "input_tensor", dtype=tf.float32,
          initializer=tf.random.uniform((32, 16, 16, 3), maxval=1)
      )
      layer = resnet_model.batch_norm(
          inputs=input_tensor, data_format=DATA_FORMAT, training=True)

    self._save_or_test_ops(
        name=name, graph=g, ops_to_eval=[input_tensor, layer], test=test,
        correctness_function=self.default_correctness_function
    )
  def _batch_norm_ops(self, test=False):
    name = "batch_norm"

    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(self.name_to_seed(name))
      input_tensor = tf.get_variable(
          "input_tensor", dtype=tf.float32,
          initializer=tf.random_uniform((32, 16, 16, 3), maxval=1)
      )
      layer = resnet_model.batch_norm(
          inputs=input_tensor, data_format=DATA_FORMAT, training=True)

    self._save_or_test_ops(
        name=name, graph=g, ops_to_eval=[input_tensor, layer], test=test,
        correctness_function=self.default_correctness_function
    )