Multi-label classification handles the case where each example may have zero
or more associated labels, from a discrete set. This is distinct from
multi_class_head which has exactly one label from a discrete set.
This head by default uses sigmoid cross entropy loss, which expects as input
a multi-hot tensor of shape (batch_size, num_classes).
Integer, number of classes, must be >= 2
String, name of the key in label dict. Can be null if label
is a tensor (single headed models).
A string defining feature column name representing
weights. It is used to down weight or boost examples during training. It
will be multiplied by the loss of the example.
A bool. If True, estimator will learn a centered
bias variable for each class. Rest of the model structure learns the
residual after centered bias.
name of the head. If provided, predictions, summary and metrics
keys will be suffixed by "/" + head_name and the default variable scope
will be head_name.
thresholds for eval metrics, defaults to [.5]
List of class IDs for which we should report per-class
metrics. Must all be in the range [0, n_classes).
Optional function that takes (labels, logits, weights) as
parameter and returns a weighted scalar loss. weights should be
optional. See tf.losses
An instance of Head for multi label classification.