train_inputs = tf.placeholder(tf.int32, shape=[batch_size])train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])embeddings = tf.Variable( tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))embed = tf.nn.embedding_lookup(embeddings, train_inputs)def nce_loss(weights, biases, labels, inputs, num_sampled, num_classes, num_true=1, sampled_values=None, remove_accidental_hits=False, partition_strategy= mod , name= nce_loss )

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.

def log_uniform_candidate_sampler(true_classes, num_true, num_sampled, unique, range_max, seed=None, name=None):

所以，默认情况下，他会用log_uniform_candidate_sampler去采样。那么log_uniform_candidate_sampler是怎么采样的呢？他的实现在这里：

他会在[0, range_max)中采样出一个整数kP(k) = (log(k + 2) - log(k + 1)) / log(range_max + 1)