Help protect the Great Barrier Reef with TensorFlow on Kaggle Join Challenge

tf.estimator.BinaryClassHead

Creates a Head for single label binary classification.

Inherits From: Head

Used in the notebooks

Used in the guide

Uses sigmoid_cross_entropy_with_logits loss.

The head expects logits with shape [D0, D1, ... DN, 1]. In many applications, the shape is [batch_size, 1].

labels must be a dense Tensor with shape matching logits, namely [D0, D1, ... DN, 1]. If label_vocabulary given, labels must be a string Tensor with values from the vocabulary. If label_vocabulary is not given, labels must be float Tensor with values in the interval [0, 1].

If weight_column is specified, weights must be of shape [D0, D1, ... DN], or [D0, D1, ... DN, 1].

The loss is the weighted sum over the input dimensions. Namely, if the input labels have shape [batch_size, 1], the loss is the weighted sum over batch_size.

Also supports custom loss_fn. loss_fn takes (labels, logits) or (labels, logits, features, loss_reduction) as arguments and returns loss with shape [D0, D1, ... DN, 1]. loss_fn must support float labels with shape [D0, D1, ... DN, 1]. Namely, the head applies label_vocabulary to the input labels before passing them to loss_fn.

Usage:

head = tf.estimator.BinaryClassHead()
logits = np.array(((45,), (-41,),), dtype=np.float32)
labels = np.array(((1,), (1,),), dtype=np.int32)
features = {'x': np.array(((42,),), dtype=np.float32)}
# expected_loss = sum(cross_entropy(labels, logits)) / batch_size
#               = sum(0, 41) / 2 = 41 / 2 = 20.50
loss = head.loss(labels, logits, features=features)
print('{:.2f}'.format(loss.numpy()))
20.50
eval_metrics = head.metrics()
updated_metrics = head.update_metrics(
  eval_metrics, features, logits, labels)
for k in sorted(updated_metrics):
 print('{} : {:.2f}'.format(k, updated_metrics[k].result().numpy()))
  accuracy : 0.50
  accuracy_baseline : 1.00
  auc : 0.00
  auc_precision_recall : 1.00
  average_loss : 20.50
  label/mean : 1.00
  precision : 1.00
  prediction/mean : 0.50
  recall : 0.50
preds = head.predictions(logits)
print(preds['logits'])
tf.Tensor(
  [[ 45.]
   [-41.]], shape=(2, 1), dtype=float32)

Usage with a canned estimator:

my_head = tf.estimator.BinaryClassHead()
my_estimator = tf.estimator.DNNEstimator(
    head=my_head,
    hidden_units=...,
    feature_columns=...)

It can also be used with a custom model_fn. Example:

def _my_model_fn(features, labels, mode):
  my_head = tf.estimator.BinaryClassHead()
  logits = tf.keras.Model(...)(features)

  return my_head.create_estimator_spec(
      features=features,
      mode=mode,
      labels=labels,
      optimizer=tf.keras.optimizers.Adagrad(lr=0.1),
      logits=logits)

my_estimator = tf.estimator.Estimator(model_fn=_my_model_fn)

weight_column A string or a NumericColumn created by tf.feature_column.numeric_column defining feature column representing weights. It is used to down weight or boost examples during training. It will be multiplied by the loss of the example.
thresholds Iterable of floats in the range (0, 1). For binary classification metrics such as precision and recall, an eval metric is generated for each threshold value. This threshold is applied to the logistic values to determine the binary classification (i.e., above the threshold is true, below is false.
label_vocabulary A list or tuple of strings representing possible label values. If it is not given, that means labels are already encoded within [0, 1]. If given, labels must be string type and have any value in label_vocabulary. Note that errors will be raised if label_vocabulary is not provided but labels are strings.
loss_reduction One of