-
-
Save prakritidev/52087c187ecbcc31416f6f589d91cba6 to your computer and use it in GitHub Desktop.
Convert gensim word2vec to tensorboard visualized model, detail: https://eliyar.biz/using-pre-trained-gensim-word2vector-in-a-keras-model-and-visualizing/
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# encoding: utf-8 | |
""" | |
@author: BrikerMan | |
@contact: [email protected] | |
@blog: https://eliyar.biz | |
@version: 1.0 | |
@license: Apache Licence | |
@file: w2v_visualizer.py | |
@time: 2017/7/30 上午9:37 | |
""" | |
import sys, os | |
from gensim.models import Word2Vec | |
import tensorflow as tf | |
import numpy as np | |
from tensorflow.contrib.tensorboard.plugins import projector | |
def visualize(model, output_path): | |
meta_file = "w2x_metadata.tsv" | |
placeholder = np.zeros((len(model.wv.index2word), 100)) | |
with open(os.path.join(output_path,meta_file), 'wb') as file_metadata: | |
for i, word in enumerate(model.wv.index2word): | |
placeholder[i] = model[word] | |
# temporary solution for https://github.com/tensorflow/tensorflow/issues/9094 | |
if word == '': | |
print("Emply Line, should replecaed by any thing else, or will cause a bug of tensorboard") | |
file_metadata.write("{0}".format('<Empty Line>').encode('utf-8') + b'\n') | |
else: | |
file_metadata.write("{0}".format(word).encode('utf-8') + b'\n') | |
# define the model without training | |
sess = tf.InteractiveSession() | |
embedding = tf.Variable(placeholder, trainable = False, name = 'w2x_metadata') | |
tf.global_variables_initializer().run() | |
saver = tf.train.Saver() | |
writer = tf.summary.FileWriter(output_path, sess.graph) | |
# adding into projector | |
config = projector.ProjectorConfig() | |
embed = config.embeddings.add() | |
embed.tensor_name = 'w2x_metadata' | |
embed.metadata_path = meta_file | |
# Specify the width and height of a single thumbnail. | |
projector.visualize_embeddings(writer, config) | |
saver.save(sess, os.path.join(output_path,'w2x_metadata.ckpt')) | |
print('Run `tensorboard --logdir={0}` to run visualize result on tensorboard'.format(output_path)) | |
if __name__ == "__main__": | |
""" | |
Just run `python w2v_visualizer.py word2vec.model visualize_result` | |
""" | |
try: | |
model_path = sys.argv[1] | |
output_path = sys.argv[2] | |
except: | |
print("Please provice model path and output path") | |
model = Word2Vec.load(model_path) | |
visualize(model, output_path) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment