def visualize(self, visual_fld, num_visualize):
""" run "'tensorboard --logdir='visualization'" to see the embeddings """
# create the list of num_variable most common words to visualize
word2vec_utils.most_common_words(visual_fld, num_visualize)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(os.path.dirname('checkpoints/checkpoint'))
# if that checkpoint exists, restore from checkpoint
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
final_embed_matrix = sess.run(self.embed_matrix)
# you have to store embeddings in a new variable
embedding_var = tf.Variable(final_embed_matrix[:num_visualize], name='embedding')
sess.run(embedding_var.initializer)
config = projector.ProjectorConfig()
summary_writer = tf.summary.FileWriter(visual_fld)
# add embedding to the config file
embedding = config.embeddings.add()
embedding.tensor_name = embedding_var.name
# link this tensor to its metadata file, in this case the first NUM_VISUALIZE words of vocab
embedding.metadata_path = 'vocab_' + str(num_visualize) + '.tsv'
# saves a configuration file that TensorBoard will read during startup.
projector.visualize_embeddings(summary_writer, config)
saver_embed = tf.train.Saver([embedding_var])
saver_embed.save(sess, os.path.join(visual_fld, 'model.ckpt'), 1)
def visualize(self, visual_fld, num_visualize):
word2vec_utils.most_common_words(visual_fld, num_visualize)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(os.path.dirname('checkpoints/checkpoint'))
# if that checkpoint exists, restore from checkpoint
# if ckpt and ckpt.model_checkpoint_path:
# saver.restore(sess, ckpt.model_checkpoint_path)
final_embed_matrix = sess.run(self.embed_matrix)
embedding_var = tf.Variable(final_embed_matrix[:num_visualize], name='embedding')
sess.run(embedding_var.initializer)
config = projector.ProjectorConfig()
summary_writer = tf.summary.FileWriter(visual_fld)
embedding = config.embeddings.add()
embedding.tensor_name = embedding_var.name
embedding.metadata_path = 'vocab_' + str(num_visualize) + '.tsv'
projector.visualize_embeddings(summary_writer, config)
saver_embed = tf.train.Saver([embedding_var])
saver_embed.save(sess, os.path.join(visual_fld, 'model.ckpt'), 1)
def visualize(self, visual_fd, num_visualize):
"""Run `tensorboard --logdir visualization` to get embeddings"""
# ceate a list of most common words to visualize
word2vec_utils.most_common_words(visual_fd, num_visualize)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(
os.path.dirname('checkpoints/checkpoint'))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
final_embed_matrix = sess.run(self.embed_matrix)
# Must store embedding in a new variable
embeddings = tf.Variable(final_embed_matrix[:num_visualize],
name='embedding')
sess.run(embeddings.initializer)
config = projector.ProjectorConfig()
summary_writer = tf.summary.FileWriter(visual_fd)
# add embedding to config file
embedding = config.embeddings.add()
embedding.tensor_name = embeddings.name
# link this tensor to its metadata file
embedding_metadata_file = f'vocab_{str(num_visualize)}.tsv'
# save the config file that the tensorboard will read
projector.visualize_embeddings(summary_writer, config)
saver_embed = tf.train.Saver([embeddings])
saver_embed.save(sess, os.path.join(visual_fd, 'model.ckpt'), 1)
def visualize(self, visual_fld, num_visualize):
""" run "'tensorboard --logdir='visualization'" to see the embeddings """
# create the list of num_variable most common words to visualize
word2vec_utils.most_common_words(visual_fld, num_visualize)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(os.path.dirname('checkpoints/checkpoint'))
# if that checkpoint exists, restore from checkpoint
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
final_embed_matrix = sess.run(self.embed_matrix)
# you have to store embeddings in a new variable
embedding_var = tf.Variable(final_embed_matrix[:num_visualize], name='embedding')
sess.run(embedding_var.initializer)
config = projector.ProjectorConfig()
summary_writer = tf.summary.FileWriter(visual_fld)
# add embedding to the config file
embedding = config.embeddings.add()
embedding.tensor_name = embedding_var.name
# link this tensor to its metadata file, in this case the first NUM_VISUALIZE words of vocab
embedding.metadata_path = 'vocab_' + str(num_visualize) + '.tsv'
# saves a configuration file that TensorBoard will read during startup.
projector.visualize_embeddings(summary_writer, config)
saver_embed = tf.train.Saver([embedding_var])
saver_embed.save(sess, os.path.join(visual_fld, 'model.ckpt'), 1)
def visualize2(visual_fld, num_visualize):
word2vec_utils.most_common_words(visual_fld, num_visualize)
embed_matrix = tf.get_variable('embed_matrix',
shape=[VOCAB_SIZE, EMBED_SIZE],
initializer=tf.random_uniform_initializer())
saver = tf.train.Saver([embed_matrix])
with tf.Session() as sess:
saver.restore(sess, './embed_saved/')
final_embed_matrix = sess.run(embed_matrix)
embedding_var = tf.Variable(final_embed_matrix[:num_visualize],
name='embedding')
sess.run(embedding_var.initializer)
config = projector.ProjectorConfig()
summary_writer = tf.summary.FileWriter(visual_fld)
embedding = config.embeddings.add()
embedding.tensor_name = embedding_var.name
embedding.metadata_path = 'vocab_' + str(num_visualize) + '.tsv'
projector.visualize_embeddings(summary_writer, config)
saver_embed = tf.train.Saver([embedding_var])
saver_embed.save(sess, os.path.join(visual_fld, 'model.ckpt'), 1)
