Merge pull request #73 from rsepassi/push

v1.0.9

Author: lukaszkaiser

.gitignore

@@ -1,7 +1,5 @@
 # Compiled python modules.
 *.pyc
-# Byte-compiled
-__pycache__/
 
 # Python egg metadata, regenerated from source files by setuptools.
 /*.egg-info

README.md

@@ -57,7 +57,7 @@ t2t-trainer --registry_help
 
 PROBLEM=wmt_ende_tokens_32k
 MODEL=transformer
-HPARAMS=transformer_base
+HPARAMS=transformer_base_single_gpu
 
 DATA_DIR=$HOME/t2t_data
 TMP_DIR=/tmp/t2t_datagen
@@ -209,7 +209,7 @@ and hyperparameter set functions can compose other hyperparameter set functions.
 The **trainer** binary is the main entrypoint for training, evaluation, and
 inference. Users can easily switch between problems, models, and hyperparameter
 sets by using the `--model`, `--problems`, and `--hparams_set` flags. Specific
-hyperparameters can be overriden with the `--hparams` flag. `--schedule` and
+hyperparameters can be overridden with the `--hparams` flag. `--schedule` and
 related flags control local and distributed training/evaluation
 ([distributed training documentation](https://github.com/tensorflow/tensor2tensor/tree/master/tensor2tensor/docs/distributed_training.md)).
 

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name='tensor2tensor',
-    version='1.0.8',
+    version='1.0.9',
     description='Tensor2Tensor',
     author='Google Inc.',
     author_email='[email protected]',

tensor2tensor/bin/make_tf_configs.py

@@ -32,7 +32,6 @@
 
 # Dependency imports
 
-import six
 import tensorflow as tf
 
 flags = tf.flags
@@ -51,7 +50,7 @@ def main(_):
 
   cluster = {"ps": ps, "worker": workers}
 
-  for task_type, jobs in six.iteritems(cluster):
+  for task_type, jobs in (("worker", workers), ("ps", ps)):
     for idx, job in enumerate(jobs):
       if task_type == "worker":
         cmd_line_flags = " ".join([
@@ -77,7 +76,7 @@ def main(_):
               "index": idx
           }
       })
-      print(tf_config + "\t" + cmd_line_flags)
+      print("'%s'\t%s" % (tf_config, cmd_line_flags))
 
 
 if __name__ == "__main__":

tensor2tensor/bin/t2t-datagen

@@ -37,10 +37,10 @@ from tensor2tensor.data_generators import algorithmic_math
 from tensor2tensor.data_generators import audio
 from tensor2tensor.data_generators import generator_utils
 from tensor2tensor.data_generators import image
+from tensor2tensor.data_generators import ptb
 from tensor2tensor.data_generators import snli
 from tensor2tensor.data_generators import wmt
 from tensor2tensor.data_generators import wsj_parsing
-from tensor2tensor.data_generators import ptb
 
 import tensorflow as tf
 
@@ -319,11 +319,11 @@ _SUPPORTED_PROBLEM_GENERATORS = {
             vocab_filename="tokens.vocab.%d" % 2**15,
             vocab_size=2**15)),
     "lmptb_10k": (
-      lambda: ptb.train_generator(
+        lambda: ptb.train_generator(
             FLAGS.tmp_dir,
             FLAGS.data_dir,
             False),
-      lambda: ptb.valid_generator()),
+        ptb.valid_generator),
 }
 
 # pylint: enable=g-long-lambda

tensor2tensor/bin/t2t-trainer

@@ -102,7 +102,7 @@ def zipf_distribution(nbr_symbols, alpha):
       Usually for modelling natural text distribution is in
       the range [1.1-1.6].
 
-  Return:
+  Returns:
     distr_map: list of float, Zipf's distribution over nbr_symbols.
 
   """
@@ -118,7 +118,7 @@ def zipf_random_sample(distr_map, sample_len):
     distr_map: list of float, Zipf's distribution over nbr_symbols.
     sample_len: integer, length of sequence to generate.
 
-  Return:
+  Returns:
     sample: list of integer, Zipf's random sample over nbr_symbols.
 
   """
@@ -131,8 +131,8 @@ def zipf_random_sample(distr_map, sample_len):
   return [t+1 if t > 0 else t+2 for t in np.searchsorted(distr_map, u)]
 
 
-def reverse_generator_nlplike(nbr_symbols, max_length, nbr_cases, \
-  scale_std_dev=100, alpha=1.5):
+def reverse_generator_nlplike(nbr_symbols, max_length, nbr_cases,
+                              scale_std_dev=100, alpha=1.5):
   """Generator for the reversing nlp-like task on sequences of symbols.
 
   The length of the sequence is drawn from a Gaussian(Normal) distribution
@@ -141,6 +141,7 @@ def reverse_generator_nlplike(nbr_symbols, max_length, nbr_cases, \
   nbr_cases sequences have been produced.
 
   Args:
+    nbr_symbols: integer, number of symbols.
     max_length: integer, maximum length of sequences to generate.
     nbr_cases: the number of cases to generate.
     scale_std_dev: float, Normal distribution's standard deviation scale factor

tensor2tensor/data_generators/algorithmic.py

@@ -41,14 +41,13 @@ def testReverseGenerator(self):
       self.assertEqual(list(reversed(d["inputs"])) + [1], d["targets"])
     self.assertEqual(counter, 10)
 
-  def  testZipfDistribution(self):
-  # Following Zipf's Law with alpha equals 1: the first in rank is two times
-  # more probable/frequent that the second in rank, three times more prob/freq
-  # that the third in rank and so on.
+  def testZipfDistribution(self):
+    # Following Zipf's Law with alpha equals 1: the first in rank is two times
+    # more probable/frequent that the second in rank, three times more prob/freq
+    # that the third in rank and so on.
     d = algorithmic.zipf_distribution(10, 1.0001)
     for i in xrange(len(d[1:])-1):
-      self.assertEqual("%.4f" % (abs(d[i+1]-d[i+2])*(i+2)), \
-       "%.4f" % d[1])
+      self.assertEqual("%.4f" % (abs(d[i+1]-d[i+2])*(i+2)), "%.4f" % d[1])
 
   def testReverseGeneratorNlpLike(self):
     counter = 0

tensor2tensor/data_generators/algorithmic_test.py

@@ -244,7 +244,8 @@ def get_or_generate_vocab(tmp_dir, vocab_filename, vocab_size):
       if ".gz" in lang_file:
         new_filepath = os.path.join(tmp_dir, lang_file[:-3])
         if os.path.exists(new_filepath):
-          tf.logging.info("Subdirectory %s already exists, skipping unpacking" % filepath)
+          tf.logging.info("Subdirectory %s already exists, skipping unpacking"
+                          % filepath)
         else:
           tf.logging.info("Unpacking subdirectory %s" % filepath)
           gunzip_file(filepath, new_filepath)

tensor2tensor/data_generators/generator_utils.py

@@ -340,24 +340,6 @@ def lm1b_16k(model_hparams):
   p.target_space_id = 3
   return p
 
-def lmptb_10k(model_hparams):
-  """Penn Tree Bank language-modeling benchmark, 10k token vocabulary."""
-  p = default_problem_hparams()
-  p.input_modality = {}
-  p.target_modality = (registry.Modalities.SYMBOL, 10000)
-
-  vocabulary = text_encoder.TokenTextEncoder(
-                  os.path.join(model_hparams.data_dir,
-                    "lmptb_10k.vocab"))
-
-  p.vocabulary = {
-      "inputs": vocabulary,
-      "targets": vocabulary,
-  }
-
-  p.input_space_id = 3
-  p.target_space_id = 3
-  return p
 
 def lm1b_64k(model_hparams):
   """Billion-word language-modeling benchmark, 64k subtoken vocabulary."""
@@ -374,6 +356,22 @@ def lm1b_64k(model_hparams):
   p.target_space_id = 3
   return p
 
+
+def lmptb_10k(model_hparams):
+  """Penn Tree Bank language-modeling benchmark, 10k token vocabulary."""
+  p = default_problem_hparams()
+  p.input_modality = {}
+  p.target_modality = (registry.Modalities.SYMBOL, 10000)
+  vocabulary = text_encoder.TokenTextEncoder(
+      os.path.join(model_hparams.data_dir, "lmptb_10k.vocab"))
+  p.vocabulary = {
+      "targets": vocabulary,
+  }
+  p.input_space_id = 3
+  p.target_space_id = 3
+  return p
+
+
 def wmt_enfr_characters(unused_model_hparams):
   """English to French translation benchmark."""
   p = default_problem_hparams()