I'm trying to visualize my word embedding with tensorboard, but can't solve problem with label. The problem is, that I have variable like this:
word_embeddings = tf.Variable(tf.random_uniform([vocabulary_size,word_embedding_size],-1.0,1.0))
and when I save it for next use in tensorboard:
saver = tf.train.Saver({"word_embeddings": word_embeddings})
embeddings_save_path = os.path.join(os.getcwd(), folder_name, 'name.ckpt')
save_embeddings = saver.save(sess, embeddings_save_path)
print('Model saved')
as label I see only index(1...vocabulary_size)
When I print word_embeddings variable I see only numbers ie:
[0.000 0.000 ...]
[0.000 0.000 ...]
[0.000 0.000 ...]
How do I add the label ie:
blue: (0.01359, 0.00075997, 0.24608, ..., -0.2524, 1.0048, 0.06259) (https://www.tensorflow.org/guide/embedding )
I'm not very familiar with this area so if I don't add here all the necessary information let me know.
I do some search here but answer like this was not very helpful
