Tensorflow One Hot Encoder?

Question

Does tensorflow have something similar to scikit learn\'s one hot encoder for processing categorical data? Would using a placeholder of tf.string behave as categorical data

Answer 1

In [7]: one_hot = tf.nn.embedding_lookup(np.eye(5), [1,2])

In [8]: one_hot.eval()
Out[8]: 
array([[ 0.,  1.,  0.,  0.,  0.],
       [ 0.,  0.,  1.,  0.,  0.]])

works on TF version 1.3.0. As of Sep 2017.