tf.contrib.losses.sparse_softmax_cross_entropy( logits, labels, weights=1.0, scope=None )
Cross-entropy loss using
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
logits: [batch_size, num_classes] logits outputs of the network .
labels: [batch_size, 1] or [batch_size] labels of dtype
int64in the range
weights: Coefficients for the loss. The tensor must be a scalar or a tensor of shape [batch_size] or [batch_size, 1].
scope: the scope for the operations performed in computing the loss.
Tensor representing the mean loss value.
ValueError: If the shapes of
weightsare incompatible, or if