TF model template: https://github.com/chiphuyen/tf-stanford-tutorials/blob/master/examples/04_word2vec_visualize.py

model.py

"""
"""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

class Model:
    """ Build the graph for model """
    def __init__(self, vocab_size, embed_size, batch_size, num_sampled, learning_rate):
        self.vocab_size = vocab_size
        self.embed_size = embed_size
        self.batch_size = batch_size
        self.num_sampled = num_sampled
        self.lr = learning_rate
        self.global_step = tf.Variable(0, dtype=tf.int32, trainable=False, name='global_step')

    def _create_placeholders(self):
        """ Step 1: define the placeholders for input and output """
        with tf.name_scope("data"):


    def _create_embedding(self):
        """ Step 2: define weights. In word2vec, it's actually the weights that we care about """
        # Assemble this part of the graph on the CPU. You can change it to GPU if you have GPU
        with tf.name_scope("embed"):

    def _create_loss(self):
        """ Step 3 + 4: define the model + the loss function """
        with tf.name_scope("loss"):

    def _create_optimizer(self):
        """ Step 5: define optimizer """

    def _create_summaries(self):
        with tf.name_scope("summaries"):

    def build_graph(self):
        """ Build the graph for our model """
        self._create_placeholders()
        self._create_embedding()
        self._create_loss()
        self._create_optimizer()
        self._create_summaries()