Code optimizations as per pylint suggestions

seq2seq/contrib/experiment.py

@@ -23,6 +23,7 @@ class Experiment(tf.contrib.learn.Experiment):
   sharing issues."""
 
   def __init__(self, train_steps_per_iteration=None, *args, **kwargs):
+    """Sets number of training steps per iteration"""
     super(Experiment, self).__init__(*args, **kwargs)
     self._train_steps_per_iteration = train_steps_per_iteration
 

seq2seq/data/input_pipeline.py

@@ -157,7 +157,7 @@ def make_data_provider(self, **kwargs):
         items_to_descriptions={})
 
     dataset_target = None
-    if len(self.params["target_files"]) > 0:
+    if self.params["target_files"]:
       decoder_target = split_tokens_decoder.SplitTokensDecoder(
           tokens_feature_name="target_tokens",
           length_feature_name="target_len",

seq2seq/encoders/conv_encoder.py

@@ -66,7 +66,7 @@ def default_params():
         "output_cnn.layers": 5,
         "position_embeddings.enable": True,
         "position_embeddings.combiner_fn": "tensorflow.multiply",
-        "position_embeddings.num_positions": 100,
+        "position_embeddings.num_positions": 100
     }
 
   def encode(self, inputs, sequence_length):

seq2seq/encoders/pooling_encoder.py

@@ -42,12 +42,12 @@ def position_encoding(sentence_size, embedding_size):
     the fixed position encodings for each sentence position.
   """
   encoding = np.ones((sentence_size, embedding_size), dtype=np.float32)
-  ls = sentence_size + 1
-  le = embedding_size + 1
-  for k in range(1, le):
-    for j in range(1, ls):
-      encoding[j-1, k-1] = (1.0 - j/float(ls)) - (
-          k / float(le)) * (1. - 2. * j/float(ls))
+  len_s = sentence_size + 1
+  len_e = embedding_size + 1
+  for k in range(1, len_e):
+    for j in range(1, len_s):
+      encoding[j-1, k-1] = (1.0 - j/float(len_s)) - (
+          k / float(len_e)) * (1. - 2. * j/float(len_s))
   return encoding
 
 
@@ -120,7 +120,7 @@ def default_params():
         "strides": 1,
         "position_embeddings.enable": True,
         "position_embeddings.combiner_fn": "tensorflow.multiply",
-        "position_embeddings.num_positions": 100,
+        "position_embeddings.num_positions": 100
     }
 
   def encode(self, inputs, sequence_length):

seq2seq/encoders/rnn_encoder.py

@@ -32,8 +32,7 @@ def _unpack_cell(cell):
   expects a list of cells, one per layer."""
   if isinstance(cell, tf.contrib.rnn.MultiRNNCell):
     return cell._cells  #pylint: disable=W0212
-  else:
-    return [cell]
+  return [cell]
 
 
 def _default_rnn_cell_params():

seq2seq/metrics/rouge.py

@@ -55,7 +55,7 @@ def _split_into_words(sentences):
 def _get_word_ngrams(n, sentences):
   """Calculates word n-grams for multiple sentences.
   """
-  assert len(sentences) > 0
+  assert sentences
   assert n > 0
 
   words = _split_into_words(sentences)
@@ -126,12 +126,11 @@ def _recon(i, j):
     """private recon calculation"""
     if i == 0 or j == 0:
       return []
-    elif x[i - 1] == y[j - 1]:
+    if x[i - 1] == y[j - 1]:
       return _recon(i - 1, j - 1) + [(x[i - 1], i)]
-    elif table[i - 1, j] > table[i, j - 1]:
+    if table[i - 1, j] > table[i, j - 1]:
       return _recon(i - 1, j)
-    else:
-      return _recon(i, j - 1)
+    return _recon(i, j - 1)
 
   recon_tuple = tuple(map(lambda x: x[0], _recon(i, j)))
   return recon_tuple

seq2seq/models/basic_seq2seq.py

@@ -120,6 +120,5 @@ def decode(self, encoder_output, features, labels):
     if self.mode == tf.contrib.learn.ModeKeys.INFER:
       return self._decode_infer(decoder, bridge, encoder_output, features,
                                 labels)
-    else:
-      return self._decode_train(decoder, bridge, encoder_output, features,
-                                labels)
+    return self._decode_train(decoder, bridge, encoder_output, features,
+                              labels)

seq2seq/models/image2seq.py

@@ -22,8 +22,6 @@
 
 import tensorflow as tf
 
-from seq2seq import graph_utils
-from seq2seq.data import vocab
 from seq2seq.graph_utils import templatemethod
 from seq2seq.models.model_base import ModelBase
 from seq2seq.models.attention_seq2seq import AttentionSeq2Seq
@@ -69,49 +67,3 @@ def encode(self, features, _labels):
 
   def batch_size(self, features, _labels):
     return tf.shape(features["image"])[0]
-
-  def _preprocess(self, features, labels):
-    """Model-specific preprocessing for features and labels:
-
-    - Creates vocabulary lookup tables for target vocab
-    - Converts tokens into vocabulary ids
-    - Prepends a speical "SEQUENCE_START" token to the target
-    - Appends a speical "SEQUENCE_END" token to the target
-    """
-
-    # Create vocabulary look for target
-    target_vocab_to_id, target_id_to_vocab, target_word_to_count, _ = \
-      vocab.create_vocabulary_lookup_table(self.target_vocab_info.path)
-
-    # Add vocab tables to graph colection so that we can access them in
-    # other places.
-    graph_utils.add_dict_to_collection({
-        "target_vocab_to_id": target_vocab_to_id,
-        "target_id_to_vocab": target_id_to_vocab,
-        "target_word_to_count": target_word_to_count
-    }, "vocab_tables")
-
-    if labels is None:
-      return features, None
-
-    labels = labels.copy()
-
-    # Slices targets to max length
-    if self.params["target.max_seq_len"] is not None:
-      labels["target_tokens"] = labels["target_tokens"][:, :self.params[
-          "target.max_seq_len"]]
-      labels["target_len"] = tf.minimum(labels["target_len"],
-                                        self.params["target.max_seq_len"])
-
-    # Look up the target ids in the vocabulary
-    labels["target_ids"] = target_vocab_to_id.lookup(labels["target_tokens"])
-
-    labels["target_len"] = tf.to_int32(labels["target_len"])
-    tf.summary.histogram("target_len", tf.to_float(labels["target_len"]))
-
-    # Add to graph collection for later use
-    graph_utils.add_dict_to_collection(features, "features")
-    if labels:
-      graph_utils.add_dict_to_collection(labels, "labels")
-
-    return features, labels

seq2seq/test/hooks_test.py

@@ -23,7 +23,6 @@
 import os
 import tempfile
 import shutil
-import time
 
 import tensorflow as tf
 from tensorflow.python.training import monitored_session  # pylint: disable=E0611
@@ -39,16 +38,16 @@ class TestPrintModelAnalysisHook(tf.test.TestCase):
   def test_begin(self):
     model_dir = tempfile.mkdtemp()
     outfile = tempfile.NamedTemporaryFile()
-    tf.get_variable("weigths", [128, 128])
+    tf.get_variable("weights", [128, 128])
     hook = hooks.PrintModelAnalysisHook(
         params={}, model_dir=model_dir, run_config=tf.contrib.learn.RunConfig())
     hook.begin()
 
     with gfile.GFile(os.path.join(model_dir, "model_analysis.txt")) as file:
-      file_contents = file.read().strip()
+      file_contents = tf.compat.as_text(file.read()).strip()
 
-    self.assertEqual(file_contents.decode(), "_TFProfRoot (--/16.38k params)\n"
-                     "  weigths (128x128, 16.38k/16.38k params)")
+    self.assertEqual(file_contents, "_TFProfRoot (--/16.38k params)\n"
+                     "  weights (128x128, 16.38k/16.38k params)")
     outfile.close()
 
 
@@ -94,7 +93,7 @@ def test_sampling(self):
       outfile = os.path.join(self.sample_dir, "samples_000000.txt")
       with open(outfile, "rb") as readfile:
         self.assertIn("Prediction followed by Target @ Step 0",
-                      readfile.read().decode("utf-8"))
+                      tf.compat.as_text(readfile.read()))
 
       # Should not trigger for step 9
       sess.run(tf.assign(global_step, 9))
@@ -108,7 +107,7 @@ def test_sampling(self):
       outfile = os.path.join(self.sample_dir, "samples_000010.txt")
       with open(outfile, "rb") as readfile:
         self.assertIn("Prediction followed by Target @ Step 10",
-                      readfile.read().decode("utf-8"))
+                      tf.compat.as_text(readfile.read()))
 
 
 class TestMetadataCaptureHook(tf.test.TestCase):

seq2seq/test/pooling_encoder_test.py

@@ -74,4 +74,4 @@ def test_encode_without_pos(self):
     })
 
 if __name__ == "__main__":
-  tf.test.main()
+  tf.test.main()

seq2seq/training/hooks.py

@@ -23,7 +23,6 @@
 import abc
 import os
 
-import numpy as np
 import six
 import yaml
 
@@ -97,10 +96,9 @@ def before_run(self, _run_context):
       return
     if not self._active:
       return tf.train.SessionRunArgs(self._global_step)
-    else:
-      tf.logging.info("Performing full trace on next step.")
-      run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE) #pylint: disable=E1101
-      return tf.train.SessionRunArgs(self._global_step, options=run_options)
+    tf.logging.info("Performing full trace on next step.")
+    run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE) #pylint: disable=E1101
+    return tf.train.SessionRunArgs(self._global_step, options=run_options)
 
   def after_run(self, _run_context, run_values):
     if not self.is_chief or self._done: