Python array_ops.squeeze方法代码示例

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def call(self, inputs):
    # There is no TF op for 1D pooling, hence we make the inputs 4D.
    if self.data_format == 'channels_last':
      inputs = array_ops.expand_dims(inputs, 2)
      pool_shape = (1,) + self.pool_size + (1, 1)
      strides = (1,) + self.strides + (1, 1)
      data_format = 'NHWC'
    else:
      inputs = array_ops.expand_dims(inputs, 1)
      pool_shape = (1, 1) + self.pool_size + (1,)
      strides = (1, 1) + self.strides + (1,)
      data_format = 'NCHW'

    outputs = self.pool_function(
        inputs,
        ksize=pool_shape,
        strides=strides,
        padding=self.padding.upper(),
        data_format=data_format)

    if self.data_format == 'channels_last':
      return array_ops.squeeze(outputs, 2)
    else:
      return array_ops.squeeze(outputs, 1) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def _define_diag_covariance_probs(self, shard_id, shard):
    """Defines the diagonal covariance probabilities per example in a class.

    Args:
      shard_id: id of the current shard.
      shard: current data shard, 1 X num_examples X dimensions.

    Returns a matrix num_examples * num_classes.
    """
    # num_classes X 1
    # TODO(xavigonzalvo): look into alternatives to log for
    # reparametrization of variance parameters.
    det_expanded = math_ops.reduce_sum(
        math_ops.log(self._covs + 1e-3), 1, keep_dims=True)
    diff = shard - self._means
    x2 = math_ops.square(diff)
    cov_expanded = array_ops.expand_dims(1.0 / (self._covs + 1e-3), 2)
    # num_classes X num_examples
    x2_cov = math_ops.matmul(x2, cov_expanded)
    x2_cov = array_ops.transpose(array_ops.squeeze(x2_cov, [2]))
    self._probs[shard_id] = -0.5 * (
        math_ops.to_float(self._dimensions) * math_ops.log(2.0 * np.pi) +
        array_ops.transpose(det_expanded) + x2_cov) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def _define_partial_maximization_operation(self, shard_id, shard):
    """Computes the partial statistics of the means and covariances.

    Args:
      shard_id: current shard id.
      shard: current data shard, 1 X num_examples X dimensions.
    """
    # Soft assignment of each data point to each of the two clusters.
    self._points_in_k[shard_id] = math_ops.reduce_sum(
        self._w[shard_id], 0, keep_dims=True)
    # Partial means.
    w_mul_x = array_ops.expand_dims(
        math_ops.matmul(
            self._w[shard_id], array_ops.squeeze(shard, [0]), transpose_a=True),
        1)
    self._w_mul_x.append(w_mul_x)
    # Partial covariances.
    x = array_ops.concat([shard for _ in range(self._num_classes)], 0)
    x_trans = array_ops.transpose(x, perm=[0, 2, 1])
    x_mul_w = array_ops.concat([
        array_ops.expand_dims(x_trans[k, :, :] * self._w[shard_id][:, k], 0)
        for k in range(self._num_classes)
    ], 0)
    self._w_mul_x2.append(math_ops.matmul(x_mul_w, x)) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def loss(self, data, labels):
    """The loss to minimize while training."""

    if self.is_regression:
      diff = self.training_inference_graph(data) - math_ops.to_float(labels)
      mean_squared_error = math_ops.reduce_mean(diff * diff)
      root_mean_squared_error = math_ops.sqrt(mean_squared_error, name="loss")
      loss = root_mean_squared_error
    else:
      loss = math_ops.reduce_mean(
          nn_ops.sparse_softmax_cross_entropy_with_logits(
              labels=array_ops.squeeze(math_ops.to_int32(labels)),
              logits=self.training_inference_graph(data)),
          name="loss")
    if self.regularizer:
      loss += layers.apply_regularization(self.regularizer,
                                          variables.trainable_variables())
    return loss 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def average_impurity(self):
    """Constructs a TF graph for evaluating the average leaf impurity of a tree.

    If in regression mode, this is the leaf variance. If in classification mode,
    this is the gini impurity.

    Returns:
      The last op in the graph.
    """
    children = array_ops.squeeze(array_ops.slice(
        self.variables.tree, [0, 0], [-1, 1]), squeeze_dims=[1])
    is_leaf = math_ops.equal(constants.LEAF_NODE, children)
    leaves = math_ops.to_int32(array_ops.squeeze(array_ops.where(is_leaf),
                                                 squeeze_dims=[1]))
    counts = array_ops.gather(self.variables.node_sums, leaves)
    gini = self._weighted_gini(counts)
    # Guard against step 1, when there often are no leaves yet.
    def impurity():
      return gini
    # Since average impurity can be used for loss, when there's no data just
    # return a big number so that loss always decreases.
    def big():
      return array_ops.ones_like(gini, dtype=dtypes.float32) * 10000000.
    return control_flow_ops.cond(math_ops.greater(
        array_ops.shape(leaves)[0], 0), impurity, big) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def _apply_transform(self, input_tensors, **kwargs):
    """Applies the transformation to the `transform_input`.

    Args:
      input_tensors: a list of Tensors representing the input to
        the Transform.
      **kwargs: Additional keyword arguments, unused here.

    Returns:
        A namedtuple of Tensors representing the transformed output.
    """
    input_tensor = input_tensors[0]
    mask = input_tensors[1]
    if mask.get_shape().ndims > 1:
      mask = array_ops.squeeze(mask)

    if isinstance(input_tensor, sparse_tensor_py.SparseTensor):
      mask_fn = sparse_boolean_mask
    else:
      mask_fn = array_ops.boolean_mask

    # pylint: disable=not-callable
    return self.return_type(mask_fn(input_tensor, mask)) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def _softmax_cross_entropy_loss(labels, logits, weights=None):
  with ops.name_scope(
      None, "softmax_cross_entropy_loss", (logits, labels,)) as name:
    labels = ops.convert_to_tensor(labels)
    # Check that we got integer for classification.
    if not labels.dtype.is_integer:
      raise ValueError("Labels dtype should be integer "
                       "Instead got %s." % labels.dtype)

    # sparse_softmax_cross_entropy_with_logits requires [batch_size] labels.
    is_squeezed_labels = False
    # TODO(ptucker): This will break for dynamic shapes.
    if len(labels.get_shape()) == 2:
      labels = array_ops.squeeze(labels, squeeze_dims=(1,))
      is_squeezed_labels = True

    loss = nn.sparse_softmax_cross_entropy_with_logits(
        labels=labels, logits=logits, name=name)

    # Restore squeezed dimension, if necessary, so loss matches weights shape.
    if is_squeezed_labels:
      loss = array_ops.expand_dims(loss, axis=(1,))

    return _compute_weighted_loss(loss, weights) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def call(self, inputs):
    inputs = ops.convert_to_tensor(inputs, dtype=self.dtype)
    ndim = self._input_rank

    shape = self.gamma.get_shape().as_list()
    gamma = array_ops.reshape(self.gamma, (ndim - 2) * [1] + shape)

    # Compute normalization pool.
    if self.data_format == 'channels_first':
      norm_pool = nn.convolution(
          math_ops.square(inputs),
          gamma,
          'VALID',
          data_format='NC' + 'DHW' [-(ndim - 2):])
      if ndim == 3:
        norm_pool = array_ops.expand_dims(norm_pool, 2)
        norm_pool = nn.bias_add(norm_pool, self.beta, data_format='NCHW')
        norm_pool = array_ops.squeeze(norm_pool, [2])
      elif ndim == 5:
        shape = array_ops.shape(norm_pool)
        norm_pool = array_ops.reshape(norm_pool, shape[:3] + [-1])
        norm_pool = nn.bias_add(norm_pool, self.beta, data_format='NCHW')
        norm_pool = array_ops.reshape(norm_pool, shape)
      else:  # ndim == 4
        norm_pool = nn.bias_add(norm_pool, self.beta, data_format='NCHW')
    else:  # channels_last
      norm_pool = nn.convolution(math_ops.square(inputs), gamma, 'VALID')
      norm_pool = nn.bias_add(norm_pool, self.beta, data_format='NHWC')
    norm_pool = math_ops.sqrt(norm_pool)

    if self.inverse:
      outputs = inputs * norm_pool
    else:
      outputs = inputs / norm_pool
    outputs.set_shape(inputs.get_shape())
    return outputs 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def _SoftmaxCrossEntropyWithLogitsGrad(op, grad_loss, grad_grad):
  """Gradient function for SoftmaxCrossEntropyWithLogits."""
  # grad_loss is the backprop for cost, and we multiply it with the gradients
  # (which is output[1])
  # grad_grad is the backprop for softmax gradient.
  # There is no gradient for the labels
  #
  # Second derivative is just softmax derivative w.r.t. logits.
  softmax_grad = op.outputs[1]
  grad = _BroadcastMul(grad_loss, softmax_grad)

  def IsZero(g):
    # Some introspection to check if the gradient is feeding zeros
    if g.op.type in ("ZerosLike", "Zeros"):
      return True
    const_fill_value = tensor_util.constant_value(g)
    return const_fill_value is not None and (const_fill_value == 0).all()

  if not IsZero(grad_grad):
    logits = op.inputs[0]
    softmax = nn_ops.softmax(logits)

    grad += ((grad_grad - array_ops.squeeze(
        math_ops.matmul(grad_grad[:, None, :],
                        softmax[:, :, None]), axis=1)) * softmax)

  return grad, None 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def _restore_sparse_tensors(stored_list, sparse_info_list):
  """Restore SparseTensors after dequeue in batch, batch_join, etc."""
  received_sequence = isinstance(stored_list, collections.Sequence)
  if not received_sequence:
    stored_list = (stored_list,)
  tensors = [
      _restore_sparse(sparse_map_op=info.map_op,
                      sparse_handles=array_ops.squeeze(s, [1]),
                      rank=(info.rank + 1).value)
      if info.sparse else s
      for (s, info) in zip(stored_list, sparse_info_list)]
  return tensors if received_sequence else tensors[0] 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def _smart_select(pred, fn_then, fn_else):
  """Selects fn_then() or fn_else() based on the value of pred.

  The purpose of this function is the same as `utils.smart_cond`. However, at
  the moment there is a bug (b/36297356) that seems to kick in only when
  `smart_cond` delegates to `tf.cond`, which sometimes results in the training
  hanging when using parameter servers. This function will output the result
  of `fn_then` or `fn_else` if `pred` is known at graph construction time.
  Otherwise, it will use `tf.where` which will result in some redundant work
  (both branches will be computed but only one selected). However, the tensors
  involved will usually be small (means and variances in batchnorm), so the
  cost will be small and will not be incurred at all if `pred` is a constant.

  Args:
    pred: A boolean scalar `Tensor`.
    fn_then: A callable to use when pred==True.
    fn_else: A callable to use when pred==False.

  Returns:
    A `Tensor` whose value is fn_then() or fn_else() based on the value of pred.
  """
  pred_value = utils.constant_value(pred)
  if pred_value:
    return fn_then()
  elif pred_value is False:
    return fn_else()
  t_then = array_ops.expand_dims(fn_then(), 0)
  t_else = array_ops.expand_dims(fn_else(), 0)
  pred = array_ops.reshape(pred, [1])
  result = array_ops.where(pred, t_then, t_else)
  return array_ops.squeeze(result, [0]) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def _infer_graph(self, inputs, clusters):
    """Maps input to closest cluster and the score.

    Args:
      inputs: list of input Tensors.
      clusters: Tensor of cluster centers.

    Returns:
      List of tuple, where each value in tuple corresponds to a value in inp.
      The tuple has following three elements:
      all_scores: distance of each input to each cluster center.
      score: distance of each input to closest cluster center.
      cluster_idx: index of cluster center closest to the corresponding input.
    """
    assert isinstance(inputs, list)
    # Pairwise distances are used only by transform(). In all other cases, this
    # sub-graph is not evaluated.
    scores = self._distance_graph(inputs, clusters, self._distance_metric)
    output = []
    if (self._distance_metric == COSINE_DISTANCE and
        not self._clusters_l2_normalized()):
      # The cosine distance between normalized vectors x and y is the same as
      # 2 * squared_euclidian_distance. We are using this fact and reusing the
      # nearest_neighbors op.
      # TODO(ands): Support COSINE distance in nearest_neighbors and remove
      # this.
      with ops.colocate_with(clusters):
        clusters = nn_impl.l2_normalize(clusters, dim=1)
    for inp, score in zip(inputs, scores):
      with ops.colocate_with(inp):
        (indices,
         distances) = gen_clustering_ops.nearest_neighbors(inp, clusters, 1)
        if self._distance_metric == COSINE_DISTANCE:
          distances *= 0.5
        output.append(
            (score, array_ops.squeeze(distances), array_ops.squeeze(indices)))
    return zip(*output) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def squeeze(x, axis):
  """Removes a 1-dimension from the tensor at index "axis".

  Arguments:
      x: A tensor or variable.
      axis: Axis to drop.

  Returns:
      A tensor with the same data as `x` but reduced dimensions.
  """
  return array_ops.squeeze(x, [axis]) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def ctc_batch_cost(y_true, y_pred, input_length, label_length):
  """Runs CTC loss algorithm on each batch element.

  Arguments:
      y_true: tensor `(samples, max_string_length)`
          containing the truth labels.
      y_pred: tensor `(samples, time_steps, num_categories)`
          containing the prediction, or output of the softmax.
      input_length: tensor `(samples, 1)` containing the sequence length for
          each batch item in `y_pred`.
      label_length: tensor `(samples, 1)` containing the sequence length for
          each batch item in `y_true`.

  Returns:
      Tensor with shape (samples,1) containing the
          CTC loss of each element.
  """
  label_length = math_ops.to_int32(array_ops.squeeze(label_length))
  input_length = math_ops.to_int32(array_ops.squeeze(input_length))
  sparse_labels = math_ops.to_int32(
      ctc_label_dense_to_sparse(y_true, label_length))

  y_pred = math_ops.log(array_ops.transpose(y_pred, perm=[1, 0, 2]) + 1e-8)

  return array_ops.expand_dims(
      ctc.ctc_loss(
          inputs=y_pred, labels=sparse_labels, sequence_length=input_length), 1) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import squeeze [as 别名]
def crf_log_norm(inputs, sequence_lengths, transition_params):
  """Computes the normalization for a CRF.

  Args:
    inputs: A [batch_size, max_seq_len, num_tags] tensor of unary potentials
        to use as input to the CRF layer.
    sequence_lengths: A [batch_size] vector of true sequence lengths.
    transition_params: A [num_tags, num_tags] transition matrix.
  Returns:
    log_norm: A [batch_size] vector of normalizers for a CRF.
  """
  # Split up the first and rest of the inputs in preparation for the forward
  # algorithm.
  first_input = array_ops.slice(inputs, [0, 0, 0], [-1, 1, -1])
  first_input = array_ops.squeeze(first_input, [1])
  rest_of_input = array_ops.slice(inputs, [0, 1, 0], [-1, -1, -1])

  # Compute the alpha values in the forward algorithm in order to get the
  # partition function.
  forward_cell = CrfForwardRnnCell(transition_params)
  _, alphas = rnn.dynamic_rnn(
      cell=forward_cell,
      inputs=rest_of_input,
      sequence_length=sequence_lengths - 1,
      initial_state=first_input,
      dtype=dtypes.float32)
  log_norm = math_ops.reduce_logsumexp(alphas, [1])
  return log_norm