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)
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.
A Tensor of shape [num_classes]. The class biases.
A Tensor of type int64 and shape [batch_size, num_true]. The
A Tensor of shape [batch_size, dim]. The forward activations of
the input network.
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.
An int. The number of possible classes.
An int. The number of target classes per training example.
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)
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
A name for the operation (optional).
A batch_size 1-D tensor of per-example NCE losses.