tf.estimator.BinaryClassHead

Creates a Head for single label binary classification.

Inherits From: Head

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)
Args
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 tf.losses.Reduction except NONE. Decides how to reduce training loss over batch. Defaults to SUM_OVER_BATCH_SIZE, namely weighted sum of losses divided by batch size * label_dimension.
loss_fn Optional loss function.
name Name of the head. If provided, summary and metrics keys will be suffixed by "/" + name. Also used as name_scope when creating ops.
Attributes
logits_dimension See base_head.Head for details.
loss_reduction See base_head.Head for details.
name See base_head.Head for details.

Methods

create_estimator_spec

View source

Returns EstimatorSpec that a model_fn can return.

It is recommended to pass all args via name.

Args
features Input dict mapping string feature names to Tensor or SparseTensor objects containing the values for that feature in a minibatch. Often to be used to fetch example-weight tensor.
mode Estimator's ModeKeys.
logits Logits Tensor to be used by the head.
labels Labels Tensor, or dict mapping string label names to Tensor objects of the label values.
optimizer An tf.keras.optimizers.Optimizer instance to optimize the loss in TRAIN mode. Namely, sets train_op = optimizer.get_updates(loss, trainable_variables), which updates variables to minimize loss.
trainable_variables A list or tuple of Variable objects to update to minimize loss. In Tensorflow 1.x, by default these are the list of variables collected in the graph under the key GraphKeys.TRAINABLE_VARIABLES. As Tensorflow 2.x doesn't have collections and GraphKeys, trainable_variables need to be passed explicitly here.
train_op_fn Function that takes a scalar loss Tensor and returns an op to optimize the model with the loss in TRAIN mode. Used if optimizer is None. Exactly one of train_op_fn and optimizer must be set in TRAIN mode. By default, it is None in other modes. If you want to optimize loss yourself, you can pass lambda _: tf.no_op() and then use EstimatorSpec.loss to compute and apply gradients.
update_ops A list or tuple of update ops to be run at training time. For example, layers such as BatchNormalization create mean and variance update ops that need to be run at training time. In Tensorflow 1.x, these are thrown into an UPDATE_OPS collection. As Tensorflow 2.x doesn't have collections, update_ops need to be passed explicitly here.
regularization_losses A list of additional scalar losses to be added to the training loss, such as regularization losses.
Returns
EstimatorSpec.

loss

View source

Returns regularized training loss. See base_head.Head for details.

metrics

View source

Creates metrics. See base_head.Head for details.

predictions

View source

Return predictions based on keys.

See base_head.Head for details.

Args
logits logits Tensor with shape [D0, D1, ... DN, logits_dimension]. For many applications, the shape is [batch_size, logits_dimension].
keys a list or tuple of prediction keys. Each key can be either the class variable of prediction_keys.PredictionKeys or its string value, such as: prediction_keys.PredictionKeys.CLASSES or 'classes'. If not specified, it will return the predictions for all valid keys.
Returns
A dict of predictions.

update_metrics

View source

Updates eval metrics. See base_head.Head for details.

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.4/api_docs/python/tf/estimator/BinaryClassHead