tf.contrib.losses.compute_weighted_loss( losses, weights=1.0, scope=None )
Computes the weighted loss. (deprecated)
losses: A tensor of size [batch_size, d1, ... dN].
weights: A tensor of size  or [batch_size, d1, ... dK] where K < N.
scope: the scope for the operations performed in computing the loss.
Tensor that returns the weighted loss.
Noneor the shape is not compatible with
losses, or if the number of dimensions (rank) of either