Stay organized with collections Save and categorize content based on your preferences.

TensorFlow 1 version View source on GitHub

Computes and returns the noise-contrastive estimation training loss.

See Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. Also see our Candidate Sampling Algorithms Reference

A common use case is to use this method for training, and calculate the full sigmoid loss for evaluation or inference as in the following example:

if mode == "train":
  loss = tf.nn.nce_loss(
elif mode == "eval":
  logits = tf.matmul(inputs, tf.transpose(weights))
  logits = tf.nn.bias_add(logits, biases)
  labels_one_hot = tf.one_hot(labels, n_classes)
  loss = tf.nn.sigmoid_cross_entropy_with_logits(
  loss = tf.reduce_sum(loss, axis=1)

weights A Tensor of shape [num_classes, dim], or a list of Tensor objects whose concatenation along dimension 0 has shape [num_classes, dim]. The (possibly-partitioned) class embeddings.
biases A Tensor of shape [num_classes]. The class biases.
labels A Tensor of type int64 and shape [batch_size, num_true]. The target classes.
inputs A Tensor of shape [batch_size, dim]. The forward activations of the input network.
num_sampled An int. The number of negative classes to randomly sample per batch. This single sample of negative classes is evaluated for each element in the batch.
num_classes An int. The number of possible classes.
num_true An int. The number of target classes per training example.
sampled_values a tuple of (sampled_candidates, true_expected_count, sampled_expected_count) returned by a *_candidate_sampler function. (if None, we default to log_uniform_candidate_sampler)
remove_accidental_hits A bool. Whether to remove "accidental hits" where a sampled class equals one of the target classes. If set to True, this is a "Sampled Logistic" loss instead of NCE, and we are learning to generate log-odds instead of log probabilities. See our Candidate Sampling Algorithms Reference. Default is False.
name A name for the operation (optional).

A batch_size 1-D tensor of per-example NCE losses.