tf.contrib.losses.softmax_cross_entropy

tf.contrib.losses.softmax_cross_entropy(
    logits,
    onehot_labels,
    weights=1.0,
    label_smoothing=0,
    scope=None
)

Defined in tensorflow/contrib/losses/python/losses/loss_ops.py.

See the guide: Losses (contrib) > Loss operations for use in neural networks.

Creates a cross-entropy loss using tf.nn.softmax_cross_entropy_with_logits. (deprecated)

THIS FUNCTION IS DEPRECATED. It will be removed after 2016-12-30. Instructions for updating: Use tf.losses.softmax_cross_entropy instead. Note that the order of the logits and labels arguments has been changed.

weights acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If weights is a tensor of size [batch_size], then the loss weights apply to each corresponding sample.

If label_smoothing is nonzero, smooth the labels towards 1/num_classes: new_onehot_labels = onehot_labels * (1 - label_smoothing) + label_smoothing / num_classes

Args:

  • logits: [batch_size, num_classes] logits outputs of the network .
  • onehot_labels: [batch_size, num_classes] one-hot-encoded labels.
  • weights: Coefficients for the loss. The tensor must be a scalar or a tensor of shape [batch_size].
  • label_smoothing: If greater than 0 then smooth the labels.
  • scope: the scope for the operations performed in computing the loss.

Returns:

A scalar Tensor representing the mean loss value.

Raises:

  • ValueError: If the shape of logits doesn't match that of onehot_labels or if the shape of weights is invalid or if weights is None.