In [31]:

    

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

import collections
import math
import os
import random
import sys
import threading
import time
import zipfile

import numpy as np
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin

import tensorflow as tf
from tensorflow.python.client import device_lib

%matplotlib inline


    

In [2]:

    

local_device_protos = device_lib.list_local_devices()
[x.name for x in local_device_protos if x.device_type == 'GPU']


    

    
Out[2]:





['/gpu:0']

In [3]:

    

word2vec = tf.load_op_library('./word2vec_ops.so')


    

In [4]:

    

flags = tf.app.flags

flags.DEFINE_string("save_path", None, "Directory to write the model and "
                    "training summaries.")
flags.DEFINE_string("train_data", None, "Training text file. "
                    "E.g., unzipped file http://mattmahoney.net/dc/text8.zip.")
flags.DEFINE_string(
    "eval_data", None, "File consisting of analogies of four tokens."
    "embedding 2 - embedding 1 + embedding 3 should be close "
    "to embedding 4."
    "See README.md for how to get 'questions-words.txt'.")
flags.DEFINE_integer("embedding_size", 200, "The embedding dimension size.")
flags.DEFINE_integer(
    "epochs_to_train", 15,
    "Number of epochs to train. Each epoch processes the training data once "
    "completely.")
flags.DEFINE_float("learning_rate", 0.2, "Initial learning rate.")
flags.DEFINE_integer("num_neg_samples", 100,
                     "Negative samples per training example.")
flags.DEFINE_integer("batch_size", 16,
                     "Number of training examples processed per step "
                     "(size of a minibatch).")
flags.DEFINE_integer("concurrent_steps", 12,
                     "The number of concurrent training steps.")
flags.DEFINE_integer("window_size", 5,
                     "The number of words to predict to the left and right "
                     "of the target word.")
flags.DEFINE_integer("min_count", 5,
                     "The minimum number of word occurrences for it to be "
                     "included in the vocabulary.")
flags.DEFINE_float("subsample", 1e-3,
                   "Subsample threshold for word occurrence. Words that appear "
                   "with higher frequency will be randomly down-sampled. Set "
                   "to 0 to disable.")
flags.DEFINE_boolean(
    "interactive", False,
    "If true, enters an IPython interactive session to play with the trained "
    "model. E.g., try model.analogy(b'france', b'paris', b'russia') and "
    "model.nearby([b'proton', b'elephant', b'maxwell'])")
flags.DEFINE_integer("statistics_interval", 5,
                     "Print statistics every n seconds.")
flags.DEFINE_integer("summary_interval", 5,
                     "Save training summary to file every n seconds (rounded "
                     "up to statistics interval).")
flags.DEFINE_integer("checkpoint_interval", 600,
                     "Checkpoint the model (i.e. save the parameters) every n "
                     "seconds (rounded up to statistics interval).")

FLAGS = flags.FLAGS


    

In [6]:

    

class Options(object):
    """Options used by our word2vec model."""

    def __init__(self):
        # Model options.

        # Embedding dimension.
        self.emb_dim = FLAGS.embedding_size

        # Training options.
        # The training text file.
        self.train_data = FLAGS.train_data

        # Number of negative samples per example.
        self.num_samples = FLAGS.num_neg_samples

        # The initial learning rate.
        self.learning_rate = FLAGS.learning_rate

        # Number of epochs to train. After these many epochs, the learning
        # rate decays linearly to zero and the training stops.
        self.epochs_to_train = FLAGS.epochs_to_train

        # Concurrent training steps.
        self.concurrent_steps = FLAGS.concurrent_steps

        # Number of examples for one training step.
        self.batch_size = FLAGS.batch_size

        # The number of words to predict to the left and right of the target word.
        self.window_size = FLAGS.window_size

        # The minimum number of word occurrences for it to be included in the
        # vocabulary.
        self.min_count = FLAGS.min_count

        # Subsampling threshold for word occurrence.
        self.subsample = FLAGS.subsample

        # How often to print statistics.
        self.statistics_interval = FLAGS.statistics_interval

        # How often to write to the summary file (rounds up to the nearest
        # statistics_interval).
        self.summary_interval = FLAGS.summary_interval

        # How often to write checkpoints (rounds up to the nearest statistics
        # interval).
        self.checkpoint_interval = FLAGS.checkpoint_interval

        # Where to write out summaries.
        self.save_path = FLAGS.save_path
        if not os.path.exists(self.save_path):
            os.makedirs(self.save_path)

        # Eval options.
        # The text file for eval.
        self.eval_data = FLAGS.eval_data


    

In [22]:

    

class Word2Vec(object):
    """Word2Vec model (Skipgram)."""

    def __init__(self, options, session):
        self._options = options
        self._session = session
        self._word2id = {}
        self._id2word = []
        self.build_graph()
        self.build_eval_graph()
        self.save_vocab()

    def read_analogies(self):
        """Reads through the analogy question file.
        Returns:
          questions: a [n, 4] numpy array containing the analogy question's
                     word ids.
          questions_skipped: questions skipped due to unknown words.
        """
        questions = []
        questions_skipped = 0
        with open(self._options.eval_data, "rb") as analogy_f:
            for line in analogy_f:
                if line.startswith(b":"):  # Skip comments.
                    continue
                words = line.strip().lower().split(b" ")
                ids = [self._word2id.get(w.strip()) for w in words]

                if None in ids or len(ids) != 4:
                    questions_skipped += 1
                else:
                    questions.append(np.array(ids))

        print("Eval analogy file: ", self._options.eval_data)
        print("Questions: ", len(questions))
        print("Skipped: ", questions_skipped)
        self._analogy_questions = np.array(questions, dtype=np.int32)

    def forward(self, examples, labels):
        """Build the graph for the forward pass."""
        opts = self._options

        # Declare all variables we need.
        # Embedding: [vocab_size, emb_dim]
        init_width = 0.5 / opts.emb_dim
        emb = tf.Variable(
            tf.random_uniform(
                [opts.vocab_size, opts.emb_dim], -init_width, init_width),
            name="emb")
        self._emb = emb

        # Softmax weight: [vocab_size, emb_dim]. Transposed.
        sm_w_t = tf.Variable(
            tf.zeros([opts.vocab_size, opts.emb_dim]),
            name="sm_w_t")

        # Softmax bias: [vocab_size].
        sm_b = tf.Variable(tf.zeros([opts.vocab_size]), name="sm_b")

        # Global step: scalar, i.e., shape [].
        self.global_step = tf.Variable(0, name="global_step")

        # Nodes to compute the nce loss w/ candidate sampling.
        labels_matrix = tf.reshape(
            tf.cast(labels,
                    dtype=tf.int64),
            [opts.batch_size, 1])

        # Negative sampling.
        sampled_ids, _, _ = (tf.nn.fixed_unigram_candidate_sampler(
            true_classes=labels_matrix,
            num_true=1,
            num_sampled=opts.num_samples,
            unique=True,
            range_max=opts.vocab_size,
            distortion=0.75,
            unigrams=opts.vocab_counts.tolist()))

        # Embeddings for examples: [batch_size, emb_dim]
        example_emb = tf.nn.embedding_lookup(emb, examples)

        # Weights for labels: [batch_size, emb_dim]
        true_w = tf.nn.embedding_lookup(sm_w_t, labels)
        # Biases for labels: [batch_size, 1]
        true_b = tf.nn.embedding_lookup(sm_b, labels)

        # Weights for sampled ids: [num_sampled, emb_dim]
        sampled_w = tf.nn.embedding_lookup(sm_w_t, sampled_ids)
        # Biases for sampled ids: [num_sampled, 1]
        sampled_b = tf.nn.embedding_lookup(sm_b, sampled_ids)

        # True logits: [batch_size, 1]
        true_logits = tf.reduce_sum(tf.multiply(example_emb, true_w), 1) + true_b

        # Sampled logits: [batch_size, num_sampled]
        # We replicate sampled noise labels for all examples in the batch
        # using the matmul.
        sampled_b_vec = tf.reshape(sampled_b, [opts.num_samples])
        sampled_logits = tf.matmul(example_emb,
                                   sampled_w,
                                   transpose_b=True) + sampled_b_vec
        return true_logits, sampled_logits

    def nce_loss(self, true_logits, sampled_logits):
        """Build the graph for the NCE loss."""

        # cross-entropy(logits, labels)
        opts = self._options
        true_xent = tf.nn.sigmoid_cross_entropy_with_logits(
            labels=tf.ones_like(true_logits), logits=true_logits)
        sampled_xent = tf.nn.sigmoid_cross_entropy_with_logits(
            labels=tf.zeros_like(sampled_logits), logits=sampled_logits)

        # NCE-loss is the sum of the true and noise (sampled words)
        # contributions, averaged over the batch.
        nce_loss_tensor = (tf.reduce_sum(true_xent) +
                           tf.reduce_sum(sampled_xent)) / opts.batch_size
        return nce_loss_tensor

    def optimize(self, loss):
        """Build the graph to optimize the loss function."""

        # Optimizer nodes.
        # Linear learning rate decay.
        opts = self._options
        words_to_train = float(opts.words_per_epoch * opts.epochs_to_train)
        lr = opts.learning_rate * tf.maximum(
            0.0001, 1.0 - tf.cast(self._words, tf.float32) / words_to_train)
        self._lr = lr
        optimizer = tf.train.GradientDescentOptimizer(lr)
        train = optimizer.minimize(loss,
                                   global_step=self.global_step,
                                   gate_gradients=optimizer.GATE_NONE)
        self._train = train

    def build_eval_graph(self):
        """Build the eval graph."""
        # Eval graph

        # Each analogy task is to predict the 4th word (d) given three
        # words: a, b, c.  E.g., a=italy, b=rome, c=france, we should
        # predict d=paris.

        # The eval feeds three vectors of word ids for a, b, c, each of
        # which is of size N, where N is the number of analogies we want to
        # evaluate in one batch.
        analogy_a = tf.placeholder(dtype=tf.int32)  # [N]
        analogy_b = tf.placeholder(dtype=tf.int32)  # [N]
        analogy_c = tf.placeholder(dtype=tf.int32)  # [N]

        # Normalized word embeddings of shape [vocab_size, emb_dim].
        nemb = tf.nn.l2_normalize(self._emb, 1)

        # Each row of a_emb, b_emb, c_emb is a word's embedding vector.
        # They all have the shape [N, emb_dim]
        a_emb = tf.gather(nemb, analogy_a)  # a's embs
        b_emb = tf.gather(nemb, analogy_b)  # b's embs
        c_emb = tf.gather(nemb, analogy_c)  # c's embs

        # We expect that d's embedding vectors on the unit hyper-sphere is
        # near: c_emb + (b_emb - a_emb), which has the shape [N, emb_dim].
        target = c_emb + (b_emb - a_emb)

        # Compute cosine distance between each pair of target and vocab.
        # dist has shape [N, vocab_size].
        dist = tf.matmul(target, nemb, transpose_b=True)

        # For each question (row in dist), find the top 4 words.
        _, pred_idx = tf.nn.top_k(dist, 4)

        # Nodes for computing neighbors for a given word according to
        # their cosine distance.
        nearby_word = tf.placeholder(dtype=tf.int32)  # word id
        nearby_emb = tf.gather(nemb, nearby_word)
        nearby_dist = tf.matmul(nearby_emb, nemb, transpose_b=True)
        nearby_val, nearby_idx = tf.nn.top_k(nearby_dist,
                                             min(1000, self._options.vocab_size))

        # Nodes in the construct graph which are used by training and
        # evaluation to run/feed/fetch.
        self._analogy_a = analogy_a
        self._analogy_b = analogy_b
        self._analogy_c = analogy_c
        self._analogy_pred_idx = pred_idx
        self._nearby_word = nearby_word
        self._nearby_val = nearby_val
        self._nearby_idx = nearby_idx

    def build_graph(self):
        """Build the graph for the full model."""
        opts = self._options
        # The training data. A text file.
        (words, counts, words_per_epoch, self._epoch, self._words, examples,
         labels) = word2vec.skipgram_word2vec(filename=opts.train_data,
                                              batch_size=opts.batch_size,
                                              window_size=opts.window_size,
                                              min_count=opts.min_count,
                                              subsample=opts.subsample)
        (opts.vocab_words, opts.vocab_counts,
         opts.words_per_epoch) = self._session.run([words, counts, words_per_epoch])
        opts.vocab_size = len(opts.vocab_words)

        print("Data file: ", opts.train_data)
        print("Vocab size: ", opts.vocab_size - 1, " + UNK")
        print("Words per epoch: ", opts.words_per_epoch)

        self._examples = examples
        self._labels = labels
        self._id2word = opts.vocab_words

        for i, w in enumerate(self._id2word):
            self._word2id[w] = i

        true_logits, sampled_logits = self.forward(examples, labels)
        loss = self.nce_loss(true_logits, sampled_logits)
        tf.summary.scalar("NCE loss", loss)
        self._loss = loss
        self.optimize(loss)

        # Properly initialize all variables.
        tf.global_variables_initializer().run()

        self.saver = tf.train.Saver()

    def save_vocab(self):
        """Save the vocabulary to a file so the model can be reloaded."""
        opts = self._options

        with open(os.path.join(opts.save_path, "vocab.txt"), "w") as f:

            for i in xrange(opts.vocab_size):
                vocab_word = tf.compat.as_text(opts.vocab_words[i]).encode("utf-8")
                f.write("%s %d\n" % (vocab_word,
                                 opts.vocab_counts[i]))

    def _train_thread_body(self):
        initial_epoch, = self._session.run([self._epoch])
        while True:
            _, epoch = self._session.run([self._train, self._epoch])

            if epoch != initial_epoch:
                break

    def train(self):
        """Train the model."""
        opts = self._options

        initial_epoch, initial_words = self._session.run([self._epoch, self._words])

        summary_op = tf.summary.merge_all()
        summary_writer = tf.summary.FileWriter(opts.save_path, self._session.graph)
        workers = []
        for _ in xrange(opts.concurrent_steps):
            t = threading.Thread(target=self._train_thread_body)
            t.start()
            workers.append(t)

        last_words, last_time, last_summary_time = initial_words, time.time(), 0
        last_checkpoint_time = 0

        while True:
            time.sleep(opts.statistics_interval)  # Reports our progress once a while.
            (epoch, step, loss, words, lr) = self._session.run(
              [self._epoch, self.global_step, self._loss, self._words, self._lr])

            now = time.time()
            last_words, last_time, rate = words, now, (words - last_words) / (
              now - last_time)

            print("Epoch %4d Step %8d: lr = %5.3f loss = %6.2f words/sec = %8.0f\r" %
                (epoch, step, lr, loss, rate), end="")
            sys.stdout.flush()

            if now - last_summary_time > opts.summary_interval:
                summary_str = self._session.run(summary_op)
                summary_writer.add_summary(summary_str, step)
                last_summary_time = now

            if now - last_checkpoint_time > opts.checkpoint_interval:
                self.saver.save(self._session,
                            os.path.join(opts.save_path, "model.ckpt"),
                            global_step=step.astype(int))
                last_checkpoint_time = now

            if epoch != initial_epoch:
                break

        for t in workers:
            t.join()

        return epoch

    def _predict(self, analogy):
        """Predict the top 4 answers for analogy questions."""
        idx, = self._session.run([self._analogy_pred_idx], {
            self._analogy_a: analogy[:, 0],
            self._analogy_b: analogy[:, 1],
            self._analogy_c: analogy[:, 2]
        })
        return idx

    def eval(self):
        """Evaluate analogy questions and reports accuracy."""

        # How many questions we get right at precision@1.
        correct = 0

        try:
            total = self._analogy_questions.shape[0]
        except AttributeError as e:
            raise AttributeError("Need to read analogy questions.")

        start = 0
        while start < total:
            limit = start + 2500
            sub = self._analogy_questions[start:limit, :]
            idx = self._predict(sub)
            start = limit

            for question in xrange(sub.shape[0]):
                for j in xrange(4):
                    if idx[question, j] == sub[question, 3]:
                        # Bingo! We predicted correctly. E.g., [italy, rome, france, paris].
                        correct += 1
                        break
                    elif idx[question, j] in sub[question, :3]:
                        # We need to skip words already in the question.
                        continue
                    else:
                        # The correct label is not the precision@1
                        break
        print()
        print("Eval %4d/%d accuracy = %4.1f%%" % (correct, total,
                                                  correct * 100.0 / total))


    def analogy(self, w0, w1, w2):
        """Predict word w3 as in w0:w1 vs w2:w3."""
        wid = np.array([[self._word2id.get(w, 0) for w in [w0, w1, w2]]])
        idx = self._predict(wid)

        for c in [self._id2word[i] for i in idx[0, :]]:
            if c not in [w0, w1, w2]:
                print(c)
                break
        print("unknown")

    def nearby(self, words, num=20):
        """Prints out nearby words given a list of words."""
        ids = np.array([self._word2id.get(x, 0) for x in words])
        vals, idx = self._session.run(
            [self._nearby_val, self._nearby_idx], {self._nearby_word: ids})
        for i in xrange(len(words)):

            print("\n%s\n=====================================" % (words[i]))

            for (neighbor, distance) in zip(idx[i, :num], vals[i, :num]):
                print("%-20s %6.4f" % (self._id2word[neighbor], distance))


    

In [23]:

    

def _start_shell(local_ns=None):
    # An interactive shell is useful for debugging/development.
    import IPython
    user_ns = {}
    
    if local_ns:
        user_ns.update(local_ns)
        user_ns.update(globals())
        
    IPython.start_ipython(argv=[], user_ns=user_ns)


    

In [32]:

    

def main(_):
    """Train a word2vec model."""
    
    FLAGS.train_data = "text8"
    FLAGS.eval_data = "questions-words.txt"
    FLAGS.save_path="/tmp"
    
    if not FLAGS.train_data or not FLAGS.eval_data or not FLAGS.save_path:
        print("--train_data --eval_data and --save_path must be specified.")
        sys.exit(1)
        
    opts = Options()
    
    with tf.Graph().as_default(), tf.Session() as session:
        with tf.device("/cpu:0"):
            model = Word2Vec(opts, session)
            model.read_analogies() # Read analogy questions
            
        for _ in xrange(opts.epochs_to_train):
            model.train()  # Process one epoch
            model.eval()  # Eval analogies.
            
        # Perform a final save.
        model.saver.save(session,
                         os.path.join(opts.save_path, "model.ckpt"),
                         global_step=model.global_step)
        
        if FLAGS.interactive:
            # E.g.,
            # [0]: model.analogy(b'france', b'paris', b'russia')
            # [1]: model.nearby([b'proton', b'elephant', b'maxwell'])
            _start_shell(locals())


    

In [33]:

    

# sys.argv = [sys.argv[0], 'argument1', 'argument2', 'argument2']
tf.app.run()


    

    




Data file:  text8
Vocab size:  71290  + UNK
Words per epoch:  17005207
INFO:tensorflow:Summary name NCE loss is illegal; using NCE_loss instead.
Eval analogy file:  questions-words.txt
Questions:  17827
Skipped:  1717
Epoch    1 Step  4715964: lr = 0.190 loss =   4.08 words/sec =    16828
Eval 1797/17827 accuracy = 10.1%
Epoch    1 Step  5258636: lr = 0.189 loss =   4.51 words/sec =    16877






    




Exception in thread Thread-40:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.

Exception in thread Thread-43:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
Exception in thread Thread-32:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
Exception in thread Thread-37:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
Exception in thread Thread-42:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
Exception in thread Thread-33:
Traceback (most recent call last):
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1022, in _do_call
    return fn(*args)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1004, in _run_fn
    status, run_metadata)
  File "/usr/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.CancelledError: Run call was cancelled

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 965, in _run
    feed_dict_string, options, run_metadata)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1015, in _do_run
    target_list, options, run_metadata)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1035, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.CancelledError: Run call was cancelled
Exception in thread Thread-41:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
Exception in thread Thread-36:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
Exception in thread Thread-39:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
Exception in thread Thread-35:
Traceback (most recent call last):
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1022, in _do_call
    return fn(*args)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1004, in _run_fn
    status, run_metadata)
  File "/usr/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.CancelledError: Run call was cancelled

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 965, in _run
    feed_dict_string, options, run_metadata)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1015, in _do_run
    target_list, options, run_metadata)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1035, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.CancelledError: Run call was cancelled
Exception in thread Thread-38:
Traceback (most recent call last):
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1022, in _do_call
    return fn(*args)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1004, in _run_fn
    status, run_metadata)
  File "/usr/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.CancelledError: Run call was cancelled

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 965, in _run
    feed_dict_string, options, run_metadata)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1015, in _do_run
    target_list, options, run_metadata)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1035, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.CancelledError: Run call was cancelled
Exception in thread Thread-34:
Traceback (most recent call last):
  File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.5/threading.py", line 862, in run
    self._target(*self._args, **self._kwargs)
  File "<ipython-input-22-bf037ee0cc03>", line 239, in _train_thread_body
    _, epoch = self._session.run([self._train, self._epoch])
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 767, in run
    run_metadata_ptr)
  File "/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 903, in _run
    raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.

















    




--------------------------------------------------------------
KeyboardInterrupt            Traceback (most recent call last)
<ipython-input-33-f72f060252e3> in <module>()
      1 # sys.argv = [sys.argv[0], 'argument1', 'argument2', 'argument2']
----> 2 tf.app.run()

/home/felipe/auto-tagger/venv3-tf/lib/python3.5/site-packages/tensorflow/python/platform/app.py in run(main, argv)
     42   # Call the main function, passing through any arguments
     43   # to the final program.
---> 44   _sys.exit(main(_sys.argv[:1] + flags_passthrough))
     45 
     46 

<ipython-input-32-b1f118d52e08> in main(_)
     18 
     19         for _ in xrange(opts.epochs_to_train):
---> 20             model.train()  # Process one epoch
     21             model.eval()  # Eval analogies.
     22 

<ipython-input-22-bf037ee0cc03> in train(self)
    260 
    261         while True:
--> 262             time.sleep(opts.statistics_interval)  # Reports our progress once a while.
    263             (epoch, step, loss, words, lr) = self._session.run(
    264               [self._epoch, self.global_step, self._loss, self._words, self._lr])

KeyboardInterrupt: 

In [ ]:

    




    

In [ ]:

    




    

In [ ]: