In [ ]:

    

embedding_var = tf.Variable(....)


    

In [ ]:

    

saver = tf.train.Saver()
saver.save(session, os.path.join(LOG_DIR, "model.ckpt"), step)


    

In [ ]:

    

embeddings {
  tensor_name: 'word_embedding'
  metadata_path: '$LOG_DIR/metadata.tsv'
}


    

In [2]:

    

from tensorflow.contrib.tensorboard.plugins import projector

# Create randomly initialized embedding weights which will be trained.
N = 10000 # Number of items (vocab size).
D = 200 # Dimensionality of the embedding.
embedding_var = tf.Variable(tf.random_normal([N,D]), name='word_embedding')

# Format: tensorflow/contrib/tensorboard/plugins/projector/projector_config.proto
config = projector.ProjectorConfig()

# You can add multiple embeddings. Here we add only one.
embedding = config.embeddings.add()
embedding.tensor_name = embedding_var.name
# Link this tensor to its metadata file (e.g. labels).
embedding.metadata_path = os.path.join(LOG_DIR, 'metadata.tsv')

# Use the same LOG_DIR where you stored your checkpoint.
summary_writer = tf.summary.FileWriter(LOG_DIR)

# The next line writes a projector_config.pbtxt in the LOG_DIR. TensorBoard will
# read this file during startup.
projector.visualize_embeddings(summary_writer, config)


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-2-ef55ac1f96e0> in <module>()
     13 embedding.tensor_name = embedding_var.name
     14 # Link this tensor to its metadata file (e.g. labels).
---> 15 embedding.metadata_path = os.path.join(LOG_DIR, 'metadata.tsv')
     16 
     17 # Use the same LOG_DIR where you stored your checkpoint.

NameError: name 'LOG_DIR' is not defined

In [ ]:

    

embedding.sprite.image_path = PATH_TO_SPRITE_IMAGE
# Specify the width and height of a single thumbnail.
embedding.sprite.single_image_dim.extend([w, h])