Missed TensorFlow World? Check out the recap. Learn more

tf.contrib.seq2seq.hardmax

tf.contrib.seq2seq.hardmax(
    logits,
    name=None
)

Defined in tensorflow/contrib/seq2seq/python/ops/attention_wrapper.py.

Returns batched one-hot vectors.

The depth index containing the 1 is that of the maximum logit value.

Args:

  • logits: A batch tensor of logit values.
  • name: Name to use when creating ops.

Returns:

A batched one-hot tensor.