Python tensorflow.python.ops.nn_ops.softmax_cross_entropy_with_logits() Examples

The following are 10 code examples of tensorflow.python.ops.nn_ops.softmax_cross_entropy_with_logits(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow.python.ops.nn_ops , or try the search function .
Example #1
Source File: onehot_categorical.py    From lambda-packs with MIT License 6 votes vote down vote up 
def _log_prob(self, x):
    x = self._assert_valid_sample(x)
    # broadcast logits or x if need be.
    logits = self.logits
    if (not x.get_shape().is_fully_defined() or
        not logits.get_shape().is_fully_defined() or
        x.get_shape() != logits.get_shape()):
      logits = array_ops.ones_like(x, dtype=logits.dtype) * logits
      x = array_ops.ones_like(logits, dtype=x.dtype) * x

    logits_shape = array_ops.shape(math_ops.reduce_sum(logits, -1))
    logits_2d = array_ops.reshape(logits, [-1, self.event_size])
    x_2d = array_ops.reshape(x, [-1, self.event_size])
    ret = -nn_ops.softmax_cross_entropy_with_logits(labels=x_2d,
                                                    logits=logits_2d)
    # Reshape back to user-supplied batch and sample dims prior to 2D reshape.
    ret = array_ops.reshape(ret, logits_shape)
    return ret
Example #2
Source File: onehot_categorical.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def _log_prob(self, x):
    x = ops.convert_to_tensor(x, name="x")
    # broadcast logits or x if need be.
    logits = self.logits
    if (not x.get_shape().is_fully_defined() or
        not logits.get_shape().is_fully_defined() or
        x.get_shape() != logits.get_shape()):
      logits = array_ops.ones_like(x, dtype=logits.dtype) * logits
      x = array_ops.ones_like(logits, dtype=x.dtype) * x

    logits_shape = array_ops.shape(logits)
    if logits.get_shape().ndims == 2:
      logits_2d = logits
      x_2d = x
    else:
      logits_2d = array_ops.reshape(logits, [-1, self.num_classes])
      x_2d = array_ops.reshape(x, [-1, self.num_classes])
    ret = -nn_ops.softmax_cross_entropy_with_logits(labels=x_2d,
                                                    logits=logits_2d)
    ret = array_ops.reshape(ret, logits_shape)
    return ret
Example #3
Source File: nn_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def test_binary_ops(self):
    ops = [
        ('sigmoid_cross_entropy_with_logits',
         nn_impl.sigmoid_cross_entropy_with_logits,
         nn.sigmoid_cross_entropy_with_logits),
        ('softmax_cross_entropy_with_logits',
         nn_ops.softmax_cross_entropy_with_logits,
         nn.softmax_cross_entropy_with_logits),
        ('sparse_softmax_cross_entropy_with_logits',
         nn_ops.sparse_softmax_cross_entropy_with_logits,
         nn.sparse_softmax_cross_entropy_with_logits),
    ]
    for op_name, tf_op, lt_op in ops:
      golden_tensor = tf_op(self.original_lt.tensor, self.other_lt.tensor)
      golden_lt = core.LabeledTensor(golden_tensor, self.axes)
      actual_lt = lt_op(self.original_lt, self.other_lt)
      self.assertIn(op_name, actual_lt.name)
      self.assertLabeledTensorsEqual(golden_lt, actual_lt)
Example #4
Source File: onehot_categorical.py    From keras-lambda with MIT License 6 votes vote down vote up 
def _log_prob(self, x):
    x = ops.convert_to_tensor(x, name="x")
    # broadcast logits or x if need be.
    logits = self.logits
    if (not x.get_shape().is_fully_defined() or
        not logits.get_shape().is_fully_defined() or
        x.get_shape() != logits.get_shape()):
      logits = array_ops.ones_like(x, dtype=logits.dtype) * logits
      x = array_ops.ones_like(logits, dtype=x.dtype) * x

    logits_shape = array_ops.shape(logits)
    if logits.get_shape().ndims == 2:
      logits_2d = logits
      x_2d = x
    else:
      logits_2d = array_ops.reshape(logits, [-1, self.num_classes])
      x_2d = array_ops.reshape(x, [-1, self.num_classes])
    ret = -nn_ops.softmax_cross_entropy_with_logits(labels=x_2d,
                                                    logits=logits_2d)
    ret = array_ops.reshape(ret, logits_shape)
    return ret
Example #5
Source File: nn_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def test_binary_ops(self):
    ops = [
        ('sigmoid_cross_entropy_with_logits',
         nn_impl.sigmoid_cross_entropy_with_logits,
         nn.sigmoid_cross_entropy_with_logits),
        ('softmax_cross_entropy_with_logits',
         nn_ops.softmax_cross_entropy_with_logits,
         nn.softmax_cross_entropy_with_logits),
        ('sparse_softmax_cross_entropy_with_logits',
         nn_ops.sparse_softmax_cross_entropy_with_logits,
         nn.sparse_softmax_cross_entropy_with_logits),
    ]
    for op_name, tf_op, lt_op in ops:
      golden_tensor = tf_op(self.original_lt.tensor, self.other_lt.tensor)
      golden_lt = core.LabeledTensor(golden_tensor, self.axes)
      actual_lt = lt_op(self.original_lt, self.other_lt)
      self.assertIn(op_name, actual_lt.name)
      self.assertLabeledTensorsEqual(golden_lt, actual_lt)
Example #6
Source File: onehot_categorical.py    From auto-alt-text-lambda-api with MIT License 5 votes vote down vote up 
def _entropy(self):
    if self.logits.get_shape().ndims == 2:
      logits_2d = self.logits
    else:
      logits_2d = array_ops.reshape(self.logits, [-1, self.num_classes])
    histogram_2d = nn_ops.softmax(logits_2d)
    ret = array_ops.reshape(
        nn_ops.softmax_cross_entropy_with_logits(labels=histogram_2d,
                                                 logits=logits_2d),
        self.batch_shape())
    ret.set_shape(self.get_batch_shape())
    return ret
Example #7
Source File: categorical.py    From auto-alt-text-lambda-api with MIT License 5 votes vote down vote up 
def _entropy(self):
    if self.logits.get_shape().ndims == 2:
      logits_2d = self.logits
    else:
      logits_2d = array_ops.reshape(self.logits, [-1, self.num_classes])
    histogram_2d = nn_ops.softmax(logits_2d)
    ret = array_ops.reshape(
        nn_ops.softmax_cross_entropy_with_logits(labels=histogram_2d,
                                                 logits=logits_2d),
        self.batch_shape())
    ret.set_shape(self.get_batch_shape())
    return ret
Example #8
Source File: categorical.py    From deep_image_model with Apache License 2.0 5 votes vote down vote up 
def _entropy(self):
    if self.logits.get_shape().ndims == 2:
      logits_2d = self.logits
    else:
      logits_2d = array_ops.reshape(self.logits, [-1, self.num_classes])
    histogram_2d = nn_ops.softmax(logits_2d)
    ret = array_ops.reshape(
        nn_ops.softmax_cross_entropy_with_logits(logits_2d, histogram_2d),
        self.batch_shape())
    ret.set_shape(self.get_batch_shape())
    return ret
Example #9
Source File: onehot_categorical.py    From keras-lambda with MIT License 5 votes vote down vote up 
def _entropy(self):
    if self.logits.get_shape().ndims == 2:
      logits_2d = self.logits
    else:
      logits_2d = array_ops.reshape(self.logits, [-1, self.num_classes])
    histogram_2d = nn_ops.softmax(logits_2d)
    ret = array_ops.reshape(
        nn_ops.softmax_cross_entropy_with_logits(labels=histogram_2d,
                                                 logits=logits_2d),
        self.batch_shape())
    ret.set_shape(self.get_batch_shape())
    return ret
Example #10
Source File: categorical.py    From keras-lambda with MIT License 5 votes vote down vote up 
def _entropy(self):
    if self.logits.get_shape().ndims == 2:
      logits_2d = self.logits
    else:
      logits_2d = array_ops.reshape(self.logits, [-1, self.num_classes])
    histogram_2d = nn_ops.softmax(logits_2d)
    ret = array_ops.reshape(
        nn_ops.softmax_cross_entropy_with_logits(labels=histogram_2d,
                                                 logits=logits_2d),
        self.batch_shape())
    ret.set_shape(self.get_batch_shape())
    return ret