Python tensorflow.minimum方法代码示例

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def minibatch_stddev_layer(x, group_size=4):
    with tf.variable_scope('MinibatchStddev'):
        group_size = tf.minimum(group_size, tf.shape(x)[0])     # Minibatch must be divisible by (or smaller than) group_size.
        s = x.shape                                             # [NCHW]  Input shape.
        y = tf.reshape(x, [group_size, -1, s[1], s[2], s[3]])   # [GMCHW] Split minibatch into M groups of size G.
        y = tf.cast(y, tf.float32)                              # [GMCHW] Cast to FP32.
        y -= tf.reduce_mean(y, axis=0, keep_dims=True)           # [GMCHW] Subtract mean over group.
        y = tf.reduce_mean(tf.square(y), axis=0)                # [MCHW]  Calc variance over group.
        y = tf.sqrt(y + 1e-8)                                   # [MCHW]  Calc stddev over group.
        y = tf.reduce_mean(y, axis=[1,2,3], keep_dims=True)      # [M111]  Take average over fmaps and pixels.
        y = tf.cast(y, x.dtype)                                 # [M111]  Cast back to original data type.
        y = tf.tile(y, [group_size, 1, s[2], s[3]])             # [N1HW]  Replicate over group and pixels.
        return tf.concat([x, y], axis=1)                        # [NCHW]  Append as new fmap.

#----------------------------------------------------------------------------
# Generator network used in the paper. 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def apply_perturbations(i, j, X, increase, theta, clip_min, clip_max):
    """
    TensorFlow implementation for apply perturbations to input features based
    on salency maps
    :param i: index of first selected feature
    :param j: index of second selected feature
    :param X: a matrix containing our input features for our sample
    :param increase: boolean; true if we are increasing pixels, false otherwise
    :param theta: delta for each feature adjustment
    :param clip_min: mininum value for a feature in our sample
    :param clip_max: maximum value for a feature in our sample
    : return: a perturbed input feature matrix for a target class
    """

    # perturb our input sample
    if increase:
        X[0, i] = np.minimum(clip_max, X[0, i] + theta)
        X[0, j] = np.minimum(clip_max, X[0, j] + theta)
    else:
        X[0, i] = np.maximum(clip_min, X[0, i] - theta)
        X[0, j] = np.maximum(clip_min, X[0, j] - theta)

    return X 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
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.

    """
    # get hash of query vecs
    hash_slot_idxs = self.get_hash_slots(normalized_query)

    # grab mem idxs in the hash slots
    hint_pool_idxs = [
        tf.maximum(tf.minimum(
            tf.gather(self.hash_slots[i], idxs),
            self.memory_size - 1), 0)
        for i, idxs in enumerate(hash_slot_idxs)]

    return tf.concat(axis=1, values=hint_pool_idxs) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def intersection(boxlist1, boxlist2, scope=None):
  """Compute pairwise intersection areas between boxes.

  Args:
    boxlist1: BoxList holding N boxes
    boxlist2: BoxList holding M boxes
    scope: name scope.

  Returns:
    a tensor with shape [N, M] representing pairwise intersections
  """
  with tf.name_scope(scope, 'Intersection'):
    y_min1, x_min1, y_max1, x_max1 = tf.split(
        value=boxlist1.get(), num_or_size_splits=4, axis=1)
    y_min2, x_min2, y_max2, x_max2 = tf.split(
        value=boxlist2.get(), num_or_size_splits=4, axis=1)
    all_pairs_min_ymax = tf.minimum(y_max1, tf.transpose(y_max2))
    all_pairs_max_ymin = tf.maximum(y_min1, tf.transpose(y_min2))
    intersect_heights = tf.maximum(0.0, all_pairs_min_ymax - all_pairs_max_ymin)
    all_pairs_min_xmax = tf.minimum(x_max1, tf.transpose(x_max2))
    all_pairs_max_xmin = tf.maximum(x_min1, tf.transpose(x_min2))
    intersect_widths = tf.maximum(0.0, all_pairs_min_xmax - all_pairs_max_xmin)
    return intersect_heights * intersect_widths 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def matched_intersection(boxlist1, boxlist2, scope=None):
  """Compute intersection areas between corresponding boxes in two boxlists.

  Args:
    boxlist1: BoxList holding N boxes
    boxlist2: BoxList holding N boxes
    scope: name scope.

  Returns:
    a tensor with shape [N] representing pairwise intersections
  """
  with tf.name_scope(scope, 'MatchedIntersection'):
    y_min1, x_min1, y_max1, x_max1 = tf.split(
        value=boxlist1.get(), num_or_size_splits=4, axis=1)
    y_min2, x_min2, y_max2, x_max2 = tf.split(
        value=boxlist2.get(), num_or_size_splits=4, axis=1)
    min_ymax = tf.minimum(y_max1, y_max2)
    max_ymin = tf.maximum(y_min1, y_min2)
    intersect_heights = tf.maximum(0.0, min_ymax - max_ymin)
    min_xmax = tf.minimum(x_max1, x_max2)
    max_xmin = tf.maximum(x_min1, x_min2)
    intersect_widths = tf.maximum(0.0, min_xmax - max_xmin)
    return tf.reshape(intersect_heights * intersect_widths, [-1]) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def _value_function_loss_for(self, policy, q_function, q_function2, value_function):
        ### Problem 1.2.A
        ### YOUR CODE HERE
        actions, log_pis = policy(self._observations_ph)
        if q_function2 is None:
            q_n = tf.squeeze(q_function((self._observations_ph, actions)), axis=1)
        else:
            q_n = tf.minimum(
                tf.squeeze(q_function((self._observations_ph, actions)), axis=1),
                tf.squeeze(q_function2((self._observations_ph, actions)), axis=1)
            )
        v_n = tf.squeeze(value_function(self._observations_ph), axis=1)
        value_function_loss = tf.losses.mean_squared_error(
            q_n - self._alpha * log_pis,
            v_n
        )
        return value_function_loss 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def padded_accuracy_topk(predictions,
                         labels,
                         k,
                         weights_fn=common_layers.weights_nonzero):
  """Percentage of times that top-k predictions matches labels on non-0s."""
  with tf.variable_scope("padded_accuracy_topk", values=[predictions, labels]):
    padded_predictions, padded_labels = common_layers.pad_with_zeros(
        predictions, labels)
    weights = weights_fn(padded_labels)
    effective_k = tf.minimum(k,
                             common_layers.shape_list(padded_predictions)[-1])
    _, outputs = tf.nn.top_k(padded_predictions, k=effective_k)
    outputs = tf.to_int32(outputs)
    padded_labels = tf.to_int32(padded_labels)
    padded_labels = tf.expand_dims(padded_labels, axis=-1)
    padded_labels += tf.zeros_like(outputs)  # Pad to same shape.
    same = tf.to_float(tf.equal(outputs, padded_labels))
    same_topk = tf.reduce_sum(same, axis=-1)
    return same_topk, weights 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def _quantize(x, params, randomize=True):
  """Quantize x according to params, optionally randomizing the rounding."""
  if not params.quantize:
    return x

  if not randomize:
    return tf.bitcast(
        tf.cast(x / params.quantization_scale, tf.int16), tf.float16)

  abs_x = tf.abs(x)
  sign_x = tf.sign(x)
  y = abs_x / params.quantization_scale
  y = tf.floor(y + tf.random_uniform(common_layers.shape_list(x)))
  y = tf.minimum(y, tf.int16.max) * sign_x
  q = tf.bitcast(tf.cast(y, tf.int16), tf.float16)
  return q 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def learning_rate_factor(name, step_num, hparams):
  """Compute the designated learning rate factor from hparams."""
  if name == "constant":
    tf.logging.info("Base learning rate: %f", hparams.learning_rate_constant)
    return hparams.learning_rate_constant
  elif name == "linear_warmup":
    return tf.minimum(1.0, step_num / hparams.learning_rate_warmup_steps)
  elif name == "linear_decay":
    ret = (hparams.train_steps - step_num) / hparams.learning_rate_decay_steps
    return tf.minimum(1.0, tf.maximum(0.0, ret))
  elif name == "rsqrt_decay":
    return tf.rsqrt(tf.maximum(step_num, hparams.learning_rate_warmup_steps))
  elif name == "rsqrt_hidden_size":
    return hparams.hidden_size ** -0.5
  elif name == "legacy":
    return legacy_learning_rate_schedule(hparams)
  else:
    raise ValueError("unknown learning rate factor %s" % name) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def compute_interpolation_weights(inputs, keypoints, lengths):
  """Computes weights for PWL calibration.

  Args:
    inputs: Tensor of shape: `(D0, D1, ..., DN, 1)` which represents inputs to
      to the pwl function. A typical shape is: `(batch_size, 1)`.
    keypoints: Rank-1 tensor of shape `(num_keypoints - 1)` which represents
      left keypoint of pieces of piecewise linear function along X axis.
    lengths: Rank-1 tensor of shape `(num_keypoints - 1)` which represents
      lengths of pieces of piecewise linear function along X axis.

  Returns:
    Interpolation weights tensor of shape: `(D0, D1, ..., DN, num_keypoints)`.
  """
  weights = (inputs - keypoints) / lengths
  weights = tf.minimum(weights, 1.0)
  weights = tf.maximum(weights, 0.0)
  # Prepend 1.0 at the beginning to add bias unconditionally.
  return tf.concat([tf.ones_like(inputs), weights], axis=-1) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def learning_rate_decay(init_lr, global_step, warmup_steps = 4000.0):
    '''Noam scheme from tensor2tensor'''
    step = tf.to_float(global_step + 1)
    return init_lr * warmup_steps**0.5 * tf.minimum(step * warmup_steps**-1.5, step**-0.5) 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def vatm(model,
         x,
         logits,
         eps,
         num_iterations=1,
         xi=1e-6,
         clip_min=None,
         clip_max=None,
         scope=None):
    """
    Tensorflow implementation of the perturbation method used for virtual
    adversarial training: https://arxiv.org/abs/1507.00677
    :param model: the model which returns the network unnormalized logits
    :param x: the input placeholder
    :param logits: the model's unnormalized output tensor (the input to
                   the softmax layer)
    :param eps: the epsilon (input variation parameter)
    :param num_iterations: the number of iterations
    :param xi: the finite difference parameter
    :param clip_min: optional parameter that can be used to set a minimum
                    value for components of the example returned
    :param clip_max: optional parameter that can be used to set a maximum
                    value for components of the example returned
    :param seed: the seed for random generator
    :return: a tensor for the adversarial example
    """
    with tf.name_scope(scope, "virtual_adversarial_perturbation"):
        d = tf.random_normal(tf.shape(x), dtype=tf_dtype)
        for i in range(num_iterations):
            d = xi * utils_tf.l2_batch_normalize(d)
            logits_d = model.get_logits(x + d)
            kl = utils_tf.kl_with_logits(logits, logits_d)
            Hd = tf.gradients(kl, d)[0]
            d = tf.stop_gradient(Hd)
        d = eps * utils_tf.l2_batch_normalize(d)
        adv_x = x + d
        if (clip_min is not None) and (clip_max is not None):
            adv_x = tf.clip_by_value(adv_x, clip_min, clip_max)
        return adv_x 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def clip_eta(eta, ord, eps):
    """
    Helper function to clip the perturbation to epsilon norm ball.
    :param eta: A tensor with the current perturbation.
    :param ord: Order of the norm (mimics Numpy).
                Possible values: np.inf, 1 or 2.
    :param eps: Epilson, bound of the perturbation.
    """

    # Clipping perturbation eta to self.ord norm ball
    if ord not in [np.inf, 1, 2]:
        raise ValueError('ord must be np.inf, 1, or 2.')
    reduc_ind = list(xrange(1, len(eta.get_shape())))
    avoid_zero_div = 1e-12
    if ord == np.inf:
        eta = tf.clip_by_value(eta, -eps, eps)
    else:
        if ord == 1:
            norm = tf.maximum(avoid_zero_div,
                              reduce_sum(tf.abs(eta),
                                         reduc_ind, keepdims=True))
        elif ord == 2:
            # avoid_zero_div must go inside sqrt to avoid a divide by zero
            # in the gradient through this operation
            norm = tf.sqrt(tf.maximum(avoid_zero_div,
                                      reduce_sum(tf.square(eta),
                                                 reduc_ind,
                                                 keepdims=True)))
        # We must *clip* to within the norm ball, not *normalize* onto the
        # surface of the ball
        factor = tf.minimum(1., eps / norm)
        eta = eta * factor
    return eta 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def convolve(image, kernels, rgb=True, strides=[1, 3, 3, 1], padding='SAME'):
    images = [image[0]]
    for i, kernel in enumerate(kernels):
        filtered_image = tf.nn.conv2d(image,
                                      kernel,
                                      strides=strides,
                                      padding=padding)[0]
        if i == 2:
            filtered_image = tf.minimum(tf.nn.relu(filtered_image), 255)
        images.append(filtered_image)
    return images 

# 需要导入模块: import tensorflow [as 别名]
# 或者: from tensorflow import minimum [as 别名]
def _reduced_kernel_size_for_small_input(input_tensor, kernel_size):
  """Define kernel size which is automatically reduced for small input.

  If the shape of the input images is unknown at graph construction time this
  function assumes that the input images are is large enough.

  Args:
    input_tensor: input tensor of size [batch_size, height, width, channels].
    kernel_size: desired kernel size of length 2: [kernel_height, kernel_width]

  Returns:
    a tensor with the kernel size.

  TODO(jrru): Make this function work with unknown shapes. Theoretically, this
  can be done with the code below. Problems are two-fold: (1) If the shape was
  known, it will be lost. (2) inception.slim.ops._two_element_tuple cannot
  handle tensors that define the kernel size.
      shape = tf.shape(input_tensor)
      return = tf.pack([tf.minimum(shape[1], kernel_size[0]),
                        tf.minimum(shape[2], kernel_size[1])])

  """
  shape = input_tensor.get_shape().as_list()
  if shape[1] is None or shape[2] is None:
    kernel_size_out = kernel_size
  else:
    kernel_size_out = [min(shape[1], kernel_size[0]),
                       min(shape[2], kernel_size[1])]
  return kernel_size_out