Feature Column Pre-trained Embedding

Question

How to use pre-trained embedding with tf.feature_column.embedding_column.

I used pre_trained embedding in tf.feature_column.embedding_co

Answer 1

You can also wrap your array into a function like this:

some_matrix = np.array([[0,1,2],[0,2,3],[5,6,7]])

def custom_init(shape, dtype):
    return some_matrix

embedding_feature = tf.feature_column.embedding_column(itemx_vocab, 
                                                       dimension=3, 
                                                       initializer=custom_init
                                                       )

It's an hacky way but does the job.

Answer 2

I also take a issue here https://github.com/tensorflow/tensorflow/issues/20663

finally I got a right way with to solve it. although. i'm not clear why answer above is not effective!! if you know the question, Thanks to give some suggestion to me!!

ok~~~~here is current solvement. Actually from here Feature Columns Embedding lookup

code:

itemx_vocab = tf.feature_column.categorical_column_with_vocabulary_file(
    key='itemx',
    vocabulary_file=FLAGS.vocabx)

embedding_initializer_x = tf.contrib.framework.load_embedding_initializer(
    ckpt_path='model.ckpt',
    embedding_tensor_name='w_in',
    new_vocab_size=itemx_vocab.vocabulary_size,
    embedding_dim=emb_size,
    old_vocab_file='FLAGS.vocab_emb',
    new_vocab_file=FLAGS.vocabx
)
itemx_emb = tf.feature_column.embedding_column(itemx_vocab,
                                               dimension=128,
                                               initializer=embedding_initializer_x,
                                               trainable=False)