Python Examples of tensorflow.constant

Source File: component.py From DOTA_models with Apache License 2.0

6 votes

def build_structured_training(self, state, network_states):
    """Builds a beam search based training loop for this component.

    The default implementation builds a dummy graph and raises a
    TensorFlow runtime exception to indicate that structured training
    is not implemented.

    Args:
      state: MasterState from the 'AdvanceMaster' op that advances the
        underlying master to this component.
      network_states: dictionary of component NetworkState objects.

    Returns:
      (handle, cost, correct, total) -- These are TF ops corresponding
      to the final handle after unrolling, the total cost, and the
      total number of actions. Since the number of correctly predicted
      actions is not applicable in the structured training setting, a
      dummy value should returned.
    """
    del network_states  # Unused.
    with tf.control_dependencies([tf.Assert(False, ['Not implemented.'])]):
      handle = tf.identity(state.handle)
    cost = tf.constant(0.)
    correct, total = tf.constant(0), tf.constant(0)
    return handle, cost, correct, total

Source File: preview.py From cwavegan with MIT License

6 votes

def noise_input_fn(params):
    """Input function for generating samples for PREDICT mode.

  Generates a single Tensor of fixed random noise. Use tf.data.Dataset to
  signal to the estimator when to terminate the generator returned by
  predict().

  Args:
    params: param `dict` passed by TPUEstimator.

  Returns:
    1-element `dict` containing the randomly generated noise.
  """

    # random noise
    np.random.seed(0)
    noise_dataset = tf.data.Dataset.from_tensors(tf.constant(
        np.random.randn(params['batch_size'], FLAGS.noise_dim), dtype=tf.float32))
    noise = noise_dataset.make_one_shot_iterator().get_next()
    return {'random_noise': noise}, None

Source File: face_attack.py From Adversarial-Face-Attack with GNU General Public License v3.0

6 votes

def structure(self, input_tensor):
        """
        Args:
            input_tensor: NHWC
        """
        rnd = tf.random_uniform((), 135, 160, dtype=tf.int32)
        rescaled = tf.image.resize_images(
            input_tensor, [rnd, rnd], method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
        h_rem = 160 - rnd
        w_rem = 160 - rnd
        pad_left = tf.random_uniform((), 0, w_rem, dtype=tf.int32)
        pad_right = w_rem - pad_left
        pad_top = tf.random_uniform((), 0, h_rem, dtype=tf.int32)
        pad_bottom = h_rem - pad_top
        padded = tf.pad(rescaled, [[0, 0], [pad_top, pad_bottom], [
                        pad_left, pad_right], [0, 0]])
        padded.set_shape((input_tensor.shape[0], 160, 160, 3))
        output = tf.cond(tf.random_uniform(shape=[1])[0] < tf.constant(0.9),
                         lambda: padded, lambda: input_tensor)
        return output

Source File: face_attack.py From Adversarial-Face-Attack with GNU General Public License v3.0

6 votes

def build_pgd_attack(self, eps):
        victim_embeddings = tf.constant(self.victim_embeddings, dtype=tf.float32)

        def one_step_attack(image, grad):
            """
            core components of this attack are:
            (a) PGD adversarial attack (https://arxiv.org/pdf/1706.06083.pdf)
            (b) momentum (https://arxiv.org/pdf/1710.06081.pdf)
            (c) input diversity (https://arxiv.org/pdf/1803.06978.pdf)
            """
            orig_image = image
            image = self.structure(image)
            image = (image - 127.5) / 128.0
            image = image + tf.random_uniform(tf.shape(image), minval=-1e-2, maxval=1e-2)
            prelogits, _ = self.network.inference(image, 1.0, False, bottleneck_layer_size=512)
            embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')

            embeddings = tf.reshape(embeddings[0], [512, 1])
            objective = tf.reduce_mean(tf.matmul(victim_embeddings, embeddings))  # to be maximized

            noise, = tf.gradients(objective, orig_image)

            noise = noise / tf.reduce_mean(tf.abs(noise), [1, 2, 3], keep_dims=True)
            noise = 0.9 * grad + noise

            adv = tf.clip_by_value(orig_image + tf.sign(noise) * 1.0, lower_bound, upper_bound)
            return adv, noise

        input = tf.to_float(self.image_batch)
        lower_bound = tf.clip_by_value(input - eps, 0, 255.)
        upper_bound = tf.clip_by_value(input + eps, 0, 255.)

        with tf.variable_scope(tf.get_variable_scope(), reuse=tf.AUTO_REUSE):
            adv, _ = tf.while_loop(
                lambda _, __: True, one_step_attack,
                (input, tf.zeros_like(input)),
                back_prop=False,
                maximum_iterations=100,
                parallel_iterations=1)
        self.adv_image = adv
        return adv

Source File: test_utils_tf.py From neural-fingerprinting with BSD 3-Clause "New" or "Revised" License

6 votes

def test_clip_eta_goldilocks(self):
        # Test that the clipping handles perturbations that are
        # too small, just right, and too big correctly
        eta = tf.constant([[2.], [3.], [4.]])
        assert eta.dtype == tf.float32, eta.dtype
        eps = 3.
        for ord_arg in [np.inf, 1, 2]:
            for sign in [-1., 1.]:
                clipped = clip_eta(eta * sign, ord_arg, eps)
                clipped_value = self.sess.run(clipped)
                gold = sign * np.array([[2.], [3.], [3.]])
                self.assertClose(clipped_value, gold)
                grad, = tf.gradients(clipped, eta)
                grad_value = self.sess.run(grad)
                # Note: the second 1. is debatable (the left-sided derivative
                # and the right-sided derivative do not match, so formally
                # the derivative is not defined). This test makes sure that
                # we at least handle this oddity consistently across all the
                # argument values we test
                gold = sign * np.array([[1.], [1.], [0.]])
                assert np.allclose(grad_value, gold)

Source File: test_dropout.py From neural-fingerprinting with BSD 3-Clause "New" or "Revised" License

6 votes

def test_drop():
    # Make sure dropout is activated successfully

    # We would like to configure the test to deterministically drop,
    # so that the test does not need to use multiple runs.
    # However, tf.nn.dropout divides by include_prob, so zero or
    # infinitesimal include_prob causes NaNs.
    # 1e-8 does not cause NaNs and shouldn't be a significant source
    # of test flakiness relative to dependency downloads failing, etc.
    model = MLP(input_shape=[1, 1], layers=[Dropout(name='output',
                                                    include_prob=1e-8)])
    x = tf.constant([[1]], dtype=tf.float32)
    y = model.get_layer(x, 'output', dropout=True)
    sess = tf.Session()
    y_value = sess.run(y)
    # Subject to very rare random failure because include_prob is not exact 0
    assert y_value == 0., y_value

Source File: tensor.py From spleeter with MIT License

6 votes

def check_tensor_shape(tensor_tf, target_shape):
    """ Return a Tensorflow boolean graph that indicates whether
    sample[features_key] has the specified target shape. Only check
    not None entries of target_shape.

    :param tensor_tf: Tensor to check shape for.
    :param target_shape: Target shape to compare tensor to.
    :returns: True if shape is valid, False otherwise (as TF boolean).
    """
    result = tf.constant(True)
    for i, target_length in enumerate(target_shape):
        if target_length:
            result = tf.logical_and(
                result,
                tf.equal(tf.constant(target_length), tf.shape(tensor_tf)[i]))
    return result