tf.contrib.nn.sampled_sparse_softmax_loss(
weights,
biases,
labels,
inputs,
num_sampled,
num_classes,
sampled_values=None,
remove_accidental_hits=True,
partition_strategy='mod',
name='sampled_sparse_softmax_loss'
)
Defined in tensorflow/contrib/nn/python/ops/sampling_ops.py
.
Computes and returns the sampled sparse softmax training loss.
This is a faster way to train a softmax classifier over a huge number of classes.
This operation is for training only. It is generally an underestimate of the full softmax loss.
A common use case is to use this method for training, and calculate the full
softmax loss for evaluation or inference. In this case, you must set
partition_strategy="div"
for the two losses to be consistent, as in the
following example:
if mode == "train":
loss = tf.nn.sampled_sparse_softmax_loss(
weights=weights,
biases=biases,
labels=labels,
inputs=inputs,
...,
partition_strategy="div")
elif mode == "eval":
logits = tf.matmul(inputs, tf.transpose(weights))
logits = tf.nn.bias_add(logits, biases)
loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=tf.squeeze(labels),
logits=logits)
See our Candidate Sampling Algorithms Reference
Also see Section 3 of Jean et al., 2014 (pdf) for the math.
Args:
weights
: ATensor
of shape[num_classes, dim]
, or a list ofTensor
objects whose concatenation along dimension 0 has shape [num_classes, dim]. The (possibly-sharded) class embeddings.biases
: ATensor
of shape[num_classes]
. The class biases.labels
: ATensor
of typeint64
and shape[batch_size, 1]
. The index of the single target class for each row of logits. Note that this format differs from thelabels
argument ofnn.sparse_softmax_cross_entropy_with_logits
.inputs
: ATensor
of shape[batch_size, dim]
. The forward activations of the input network.num_sampled
: Anint
. The number of classes to randomly sample per batch.num_classes
: Anint
. The number of possible classes.sampled_values
: a tuple of (sampled_candidates
,true_expected_count
,sampled_expected_count
) returned by a*_candidate_sampler
function. (if None, we default tolog_uniform_candidate_sampler
)remove_accidental_hits
: Abool
. whether to remove "accidental hits" where a sampled class equals one of the target classes. Default is True.partition_strategy
: A string specifying the partitioning strategy, relevant iflen(weights) > 1
. Currently"div"
and"mod"
are supported. Default is"mod"
. Seetf.nn.embedding_lookup
for more details.name
: A name for the operation (optional).
Returns:
A batch_size
1-D tensor of per-example sampled softmax losses.