Merge branch 'master' into master

CODEOWNERS

@@ -39,6 +39,8 @@
 /research/video_prediction/ @cbfinn
 /research/fivo/ @dieterichlawson
 /samples/ @MarkDaoust
+/samples/languages/java/ @asimshankar
 /tutorials/embedding/ @zffchen78 @a-dai
 /tutorials/image/ @sherrym @shlens
+/tutorials/image/cifar10_estimator/ @tfboyd @protoget
 /tutorials/rnn/ @lukaszkaiser @ebrevdo

official/README.md

 # TensorFlow Official Models
 
-The TensorFlow official models are a collection of example models that use TensorFlow's high-level APIs. They are intended to be well-maintained, tested, and kept up to date with the latest stable TensorFlow API. They should also be reasonably optimized for fast performance while still being easy to read.
+The TensorFlow official models are a collection of example models that use TensorFlow's high-level APIs. They are intended to be well-maintained, tested, and kept up to date with the latest TensorFlow API. They should also be reasonably optimized for fast performance while still being easy to read.
+
+The master branch of the models are **in development**, and they target the [nightly binaries](https://github.com/tensorflow/tensorflow#installation) built from the [master branch of TensorFlow](https://github.com/tensorflow/tensorflow/tree/master).
+
+**Stable versions** of the official models targeting releases of TensorFlow are available as tagged branches or [downloadable releases](https://github.com/tensorflow/models/releases). Model repository version numbers match the target TensorFlow release, such that [branch r1.4.0](https://github.com/tensorflow/models/tree/r1.4.0) and [release v1.4.0](https://github.com/tensorflow/models/releases/tag/v1.4.0) are compatible with [TensorFlow v1.4.0](https://github.com/tensorflow/tensorflow/releases/tag/v1.4.0).
+
+If you are on a version of TensorFlow earlier than v1.4, please [update your installation](https://www.tensorflow.org/install/).
 
-Currently the models are compatible with TensorFlow 1.4. If you are on an earlier version please [update your installation](https://www.tensorflow.org/install/).
 
 ---
 

official/mnist/dataset.py

@@ -33,7 +33,7 @@ def read32(bytestream):
 
 def check_image_file_header(filename):
   """Validate that filename corresponds to images for the MNIST dataset."""
-  with tf.gfile.Open(filename) as f:
+  with tf.gfile.Open(filename, 'rb') as f:
     magic = read32(f)
     num_images = read32(f)
     rows = read32(f)
@@ -49,7 +49,7 @@ def check_image_file_header(filename):
 
 def check_labels_file_header(filename):
   """Validate that filename corresponds to labels for the MNIST dataset."""
-  with tf.gfile.Open(filename) as f:
+  with tf.gfile.Open(filename, 'rb') as f:
     magic = read32(f)
     num_items = read32(f)
     if magic != 2049:
@@ -58,12 +58,12 @@ def check_labels_file_header(filename):
 
 
 def download(directory, filename):
-  """Download (and unzip) a file from the MNIST dataset, if it doesn't already exist."""
-  if not tf.gfile.Exists(directory):
-    tf.gfile.MakeDirs(directory)
+  """Download (and unzip) a file from the MNIST dataset if not already done."""
   filepath = os.path.join(directory, filename)
   if tf.gfile.Exists(filepath):
     return filepath
+  if not tf.gfile.Exists(directory):
+    tf.gfile.MakeDirs(directory)
   # CVDF mirror of http://yann.lecun.com/exdb/mnist/
   url = 'https://storage.googleapis.com/cvdf-datasets/mnist/' + filename + '.gz'
   zipped_filepath = filepath + '.gz'

official/mnist/mnist.py

@@ -96,6 +96,11 @@ def model_fn(features, labels, mode, params):
         })
   if mode == tf.estimator.ModeKeys.TRAIN:
     optimizer = tf.train.AdamOptimizer(learning_rate=1e-4)
+
+    # If we are running multi-GPU, we need to wrap the optimizer.
+    if params.get('multi_gpu'):
+      optimizer = tf.contrib.estimator.TowerOptimizer(optimizer)
+
     logits = model(image, training=True)
     loss = tf.losses.softmax_cross_entropy(onehot_labels=labels, logits=logits)
     accuracy = tf.metrics.accuracy(
@@ -122,16 +127,53 @@ def model_fn(features, labels, mode, params):
         })
 
 
+def validate_batch_size_for_multi_gpu(batch_size):
+  """For multi-gpu, batch-size must be a multiple of the number of
+  available GPUs.
+
+  Note that this should eventually be handled by replicate_model_fn
+  directly. Multi-GPU support is currently experimental, however,
+  so doing the work here until that feature is in place.
+  """
+  from tensorflow.python.client import device_lib
+
+  local_device_protos = device_lib.list_local_devices()
+  num_gpus = sum([1 for d in local_device_protos if d.device_type == 'GPU'])
+  if not num_gpus:
+    raise ValueError('Multi-GPU mode was specified, but no GPUs '
+      'were found. To use CPU, run without --multi_gpu.')
+    
+  remainder = batch_size % num_gpus
+  if remainder:
+    err = ('When running with multiple GPUs, batch size '
+      'must be a multiple of the number of available GPUs. '
+      'Found {} GPUs with a batch size of {}; try --batch_size={} instead.'
+      ).format(num_gpus, batch_size, batch_size - remainder)
+    raise ValueError(err)
+
+
 def main(unused_argv):
+  model_function = model_fn
+
+  if FLAGS.multi_gpu:
+    validate_batch_size_for_multi_gpu(FLAGS.batch_size)
+
+    # There are two steps required if using multi-GPU: (1) wrap the model_fn,
+    # and (2) wrap the optimizer. The first happens here, and (2) happens
+    # in the model_fn itself when the optimizer is defined.
+    model_function = tf.contrib.estimator.replicate_model_fn(
+        model_fn, loss_reduction=tf.losses.Reduction.MEAN)
+
   data_format = FLAGS.data_format
   if data_format is None:
     data_format = ('channels_first'
                    if tf.test.is_built_with_cuda() else 'channels_last')
   mnist_classifier = tf.estimator.Estimator(
-      model_fn=model_fn,
+      model_fn=model_function,
       model_dir=FLAGS.model_dir,
       params={
-          'data_format': data_format
+          'data_format': data_format,
+          'multi_gpu': FLAGS.multi_gpu
       })
 
   # Train the model
@@ -169,39 +211,52 @@ def main(unused_argv):
     mnist_classifier.export_savedmodel(FLAGS.export_dir, input_fn)
 
 
-if __name__ == '__main__':
-  parser = argparse.ArgumentParser()
-  parser.add_argument(
+class MNISTArgParser(argparse.ArgumentParser):
+
+  def __init__(self):
+    super(MNISTArgParser, self).__init__()
+
+    self.add_argument(
+        '--multi_gpu', action='store_true',
+        help='If set, run across all available GPUs.')
+    self.add_argument(
         '--batch_size',
         type=int,
         default=100,
         help='Number of images to process in a batch')
-  parser.add_argument(
+    self.add_argument(
         '--data_dir',
         type=str,
         default='/tmp/mnist_data',
         help='Path to directory containing the MNIST dataset')
-  parser.add_argument(
+    self.add_argument(
         '--model_dir',
         type=str,
         default='/tmp/mnist_model',
         help='The directory where the model will be stored.')
-  parser.add_argument(
-      '--train_epochs', type=int, default=40, help='Number of epochs to train.')
-  parser.add_argument(
+    self.add_argument(
+        '--train_epochs',
+        type=int,
+        default=40,
+        help='Number of epochs to train.')
+    self.add_argument(
         '--data_format',
         type=str,
         default=None,
         choices=['channels_first', 'channels_last'],
-      help='A flag to override the data format used in the model. channels_first '
-      'provides a performance boost on GPU but is not always compatible '
-      'with CPU. If left unspecified, the data format will be chosen '
-      'automatically based on whether TensorFlow was built for CPU or GPU.')
-  parser.add_argument(
+        help='A flag to override the data format used in the model. '
+        'channels_first provides a performance boost on GPU but is not always '
+        'compatible with CPU. If left unspecified, the data format will be '
+        'chosen automatically based on whether TensorFlow was built for CPU or '
+        'GPU.')
+    self.add_argument(
         '--export_dir',
         type=str,
         help='The directory where the exported SavedModel will be stored.')
 
+
+if __name__ == '__main__':
+  parser = MNISTArgParser()
   tf.logging.set_verbosity(tf.logging.INFO)
   FLAGS, unparsed = parser.parse_known_args()
   tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

official/mnist/mnist_test.py

@@ -62,11 +62,12 @@ class Tests(tf.test.TestCase):
       self.assertEqual(predictions['probabilities'].shape, (10,))
       self.assertEqual(predictions['classes'].shape, ())
 
-  def mnist_model_fn_helper(self, mode):
+  def mnist_model_fn_helper(self, mode, multi_gpu=False):
     features, labels = dummy_input_fn()
     image_count = features.shape[0]
     spec = mnist.model_fn(features, labels, mode, {
-        'data_format': 'channels_last'
+        'data_format': 'channels_last',
+        'multi_gpu': multi_gpu
     })
 
     if mode == tf.estimator.ModeKeys.PREDICT:
@@ -91,6 +92,9 @@ class Tests(tf.test.TestCase):
   def test_mnist_model_fn_train_mode(self):
     self.mnist_model_fn_helper(tf.estimator.ModeKeys.TRAIN)
 
+  def test_mnist_model_fn_train_mode_multi_gpu(self):
+    self.mnist_model_fn_helper(tf.estimator.ModeKeys.TRAIN, multi_gpu=True)
+
   def test_mnist_model_fn_eval_mode(self):
     self.mnist_model_fn_helper(tf.estimator.ModeKeys.EVAL)
 

official/mnist/mnist_tpu.py

@@ -133,6 +133,7 @@ def main(argv):
   # Note that the number of examples used during evaluation is
   # --eval_steps * --batch_size.
   # So if you change --batch_size then change --eval_steps too.
+  if FLAGS.eval_steps:
     estimator.evaluate(input_fn=eval_input_fn, steps=FLAGS.eval_steps)
 
 

official/testing/docker_test.sh

@@ -35,9 +35,9 @@ EXIT=0
 export WORKSPACE=${PWD}
 
 if [ "$PYTHON_VERSION" = "PYTHON3" ]; then
-  DOCKER_IMG_NAME="tensorflow/tensorflow:1.4.0-py3"
+  DOCKER_IMG_NAME="tensorflow/tensorflow:nightly-py3"
 else
-  DOCKER_IMG_NAME="tensorflow/tensorflow:1.4.0"
+  DOCKER_IMG_NAME="tensorflow/tensorflow:nightly"
   if [ "$PYTHON_VERSION" != "PYTHON2" ]; then
     echo "WARNING: Python version was not specified. Using Python2 by default."
     sleep 5
@@ -56,6 +56,9 @@ fi
 # Specify which test is to be run
 COMMAND="./official/testing/test_models.sh"
 
+# Check the recency of the desired image
+${DOCKER_BINARY} pull ${DOCKER_IMG_NAME}
+
 # RUN
 ${DOCKER_BINARY} run \
     -v ${WORKSPACE}:/workspace \

research/astronet/README.md

+# Coming Soon!
+
+This directory will soon be populated with TensorFlow models and data
+processing code for identifying exoplanets in astrophysical light curves.
+
+For full details, see the following paper:
+
+*Identifying Exoplanets With Deep Learning: A Five Planet Resonant Chain Around
+Kepler-80 And An Eighth Planet Around Kepler-90*
+
+Christopher J Shallue and Andrew Vanderburg
+
+To appear in the Astronomical Journal
+
+Preprint available at https://www.cfa.harvard.edu/~avanderb/kepler90i.pdf
+
+Contact: Chris Shallue (@cshallue)

research/brain_coder/README.md

 # Brain Coder
 
-*Authors: Daniel Abolafia, Quoc Le, Mohammad Norouzi*
+*Authors: Daniel Abolafia, Mohammad Norouzi, Quoc Le*
 
-Brain coder is a code synthesis experimental environment. We provide code that reproduces the results from our recent paper [Code Synthesis with Priority Queue Training](https://openreview.net/forum?id=r1AoGNlC-). See single_task/README.md for details on how to build and reproduce those experiments.
+Brain coder is a code synthesis experimental environment. We provide code that reproduces the results from our recent paper [Neural Program Synthesis with Priority Queue Training](https://arxiv.org/abs/1801.03526). See single_task/README.md for details on how to build and reproduce those experiments.
 
 ## Installation
 

research/brain_coder/common/config_lib.py

@@ -10,6 +10,7 @@ else that may be specific to a particular run.
 
 import ast
 import itertools
+from six.moves import xrange
 
 
 class Config(dict):

research/brain_coder/common/schedules_test.py

@@ -7,6 +7,7 @@ from __future__ import print_function
 from math import exp
 from math import sqrt
 import numpy as np
+from six.moves import xrange
 import tensorflow as tf
 
 from common import config_lib  # brain coder

research/brain_coder/common/utils.py

@@ -12,6 +12,8 @@ import random
 
 from absl import logging
 import numpy as np
+import six
+from six.moves import xrange
 import tensorflow as tf
 
 
@@ -137,7 +139,7 @@ def stack_pad(tensors, pad_axes=None, pad_to_lengths=None, dtype=np.float32,
   same_axes = dict(enumerate(max_lengths))
   if pad_axes is None:
     pad_axes = []
-  if isinstance(pad_axes, (int, long)):
+  if isinstance(pad_axes, six.integer_types):
     if pad_to_lengths is not None:
       max_lengths[pad_axes] = pad_to_lengths
     del same_axes[pad_axes]

research/brain_coder/single_task/README.md

 # Experiments for ICLR 2018 paper.
 
-[Code Synthesis with Priority Queue Training](https://openreview.net/forum?id=r1AoGNlC-).
+[Neural Program Synthesis with Priority Queue Training](https://arxiv.org/abs/1801.03526).
 
 Runs policy gradient (REINFORCE), priority queue training, genetic algorithm,
 and uniform random search.

research/brain_coder/single_task/code_tasks.py

@@ -11,6 +11,7 @@ import random
 
 from absl import logging
 import numpy as np
+from six.moves import xrange
 
 from common import bf  # brain coder
 from common import reward as r  # brain coder

research/brain_coder/single_task/ga_lib.py

@@ -14,6 +14,7 @@ import random
 from absl import flags
 from absl import logging
 import numpy as np
+from six.moves import xrange
 
 from common import bf  # brain coder
 from common import utils  # brain coder
@@ -469,4 +470,3 @@ class Individual(list):
 
 def random_individual(genome_size):
   return lambda: Individual(np.random.choice(GENES, genome_size).tolist())
-

research/brain_coder/single_task/ga_train.py

@@ -18,6 +18,7 @@ from time import sleep
 from absl import flags
 from absl import logging
 import numpy as np
+from six.moves import xrange
 import tensorflow as tf
 
 from common import utils  # brain coder
@@ -321,4 +322,3 @@ def run_random_search(max_num_programs, checkpoint_dir, task_eval_fn,
       solution_found=found_solution, generations=num_programs_seen,
       num_programs=num_programs_seen, max_generations=max_num_programs,
       max_num_programs=max_num_programs)
-

research/brain_coder/single_task/pg_agent.py

@@ -15,6 +15,7 @@ import time
 
 from absl import logging
 import numpy as np
+from six.moves import xrange
 import tensorflow as tf
 
 from common import rollout as rollout_lib  # brain coder
@@ -1294,4 +1295,3 @@ def process_episodes(
     batch_targets = np.array([], dtype=np.float32)
 
   return (batch_targets, batch_returns)
-

research/brain_coder/single_task/pg_agent_test.py

@@ -8,6 +8,7 @@ from collections import Counter
 
 from absl import logging
 import numpy as np
+from six.moves import xrange
 import tensorflow as tf
 
 from common import utils  # brain coder

research/brain_coder/single_task/results_lib.py

@@ -8,6 +8,7 @@ import ast
 from collections import namedtuple
 import os
 import re
+from six.moves import xrange
 import tensorflow as tf
 
 
@@ -152,4 +153,3 @@ class Results(object):
           r for shard_results in results_per_shard for r in shard_results]
 
     return aggregate, shard_stats
-

research/brain_coder/single_task/results_lib_test.py

@@ -8,6 +8,7 @@ import contextlib
 import os
 import shutil
 import tempfile
+from six.moves import xrange
 import tensorflow as tf
 
 from single_task import results_lib  # brain coder