Merge branch 'master' of github.com:fchollet/keras into pr_7508

* 'master' of github.com:fchollet/keras: (57 commits)
  Minor README edit
  Speed up Travis tests (keras-team#9386)
  fix typo (keras-team#9391)
  Fix style issue in docstring
  Prepare 2.1.4 release.
  Fix activity regularizer + model composition test
  Corrected copyright years (keras-team#9375)
  Change default interpolation from nearest to bilinear. (keras-team#8849)
  a capsule cnn on cifar-10 (keras-team#9193)
  Enable us to use sklearn to do cv for functional api (keras-team#9320)
  Add support for stateful metrics. (keras-team#9253)
  The type of list keys was float (keras-team#9324)
  Fix mnist sklearn wrapper example (keras-team#9317)
  keras-team#9287 Fix most of the file-handle resource leaks. (keras-team#9309)
  Pass current learning rate to schedule() in LearningRateScheduler (keras-team#8865)
  Simplify with from six.moves import input (keras-team#9216)
  fixed RemoteMonitor: Json to handle np.float32 and np.int32 types (keras-team#9261)
  Update tweet length from 140 to 280 in docs
  Add `depthconv_conv2d` tests (keras-team#9225)
  Remove `force` option in progbar
  ...

.coveragerc

@@ -1,6 +1,16 @@
 [report]
-fail_under = 84
+# Regexes for lines to exclude from consideration
+exclude_lines =
+    # Don't complain if tests don't hit defensive assertion code:
+    raise ImportError
+    raise NotImplementedError
+
+    # Don't complain if legacy support codes are not performed:
+    if original_keras_version == '1':
+
+fail_under = 85
 show_missing = True
 omit =
     keras/applications/*
     keras/datasets/*
+    keras/legacy/*

.travis.yml

@@ -38,10 +38,10 @@ install:
   # Useful for debugging any issues with conda
   - conda info -a
 
-  - conda create -q -n test-environment python=$TRAVIS_PYTHON_VERSION numpy nose scipy matplotlib pandas pytest h5py
+  - conda create -q -n test-environment python=$TRAVIS_PYTHON_VERSION pytest pandas
   - source activate test-environment
+  - pip install --only-binary=numpy,scipy numpy nose scipy matplotlib h5py theano
   - conda install mkl mkl-service
-  - pip install theano
 
   # set library path
   - export LD_LIBRARY_PATH=$HOME/miniconda/envs/test-environment/lib/:$LD_LIBRARY_PATH
@@ -111,5 +111,5 @@ script:
     elif [[ "$TEST_MODE" == "DOC" ]]; then
       PYTHONPATH=$PWD:$PYTHONPATH py.test tests/test_documentation.py;
     else
-      PYTHONPATH=$PWD:$PYTHONPATH py.test tests/ --ignore=tests/integration_tests --ignore=tests/test_documentation.py --cov-config .coveragerc --cov=keras tests/;
+      PYTHONPATH=$PWD:$PYTHONPATH py.test tests/ --ignore=tests/integration_tests --ignore=tests/test_documentation.py --ignore=tests/keras/legacy/layers_test.py --cov-config .coveragerc --cov=keras tests/;
     fi

LICENSE

@@ -1,19 +1,19 @@
 COPYRIGHT
 
 All contributions by François Chollet:
-Copyright (c) 2015, François Chollet.
+Copyright (c) 2015 - 2018, François Chollet.
 All rights reserved.
 
 All contributions by Google:
-Copyright (c) 2015, Google, Inc.
+Copyright (c) 2015 - 2018, Google, Inc.
 All rights reserved.
 
 All contributions by Microsoft:
-Copyright (c) 2017, Microsoft, Inc.
+Copyright (c) 2017 - 2018, Microsoft, Inc.
 All rights reserved.
 
 All other contributions:
-Copyright (c) 2015 - 2017, the respective contributors.
+Copyright (c) 2015 - 2018, the respective contributors.
 All rights reserved.
 
 Each contributor holds copyright over their respective contributions.

README.md

@@ -155,7 +155,7 @@ sudo python setup.py install
 ------------------
 
 
-## Switching from TensorFlow to CNTK or Theano
+## Using a different backend than TensorFlow
 
 By default, Keras will use TensorFlow as its tensor manipulation library. [Follow these instructions](https://keras.io/backend/) to configure the Keras backend.
 

docker/Dockerfile

@@ -1,5 +1,5 @@
-ARG cuda_version=8.0
-ARG cudnn_version=6
+ARG cuda_version=9.0
+ARG cudnn_version=7
 FROM nvidia/cuda:${cuda_version}-cudnn${cudnn_version}-devel
 
 ENV CONDA_DIR /opt/conda

docker/Makefile

@@ -7,8 +7,8 @@ DOCKER_FILE=Dockerfile
 DOCKER=GPU=$(GPU) nvidia-docker
 BACKEND=tensorflow
 PYTHON_VERSION?=3.6
-CUDA_VERSION?=8.0
-CUDNN_VERSION?=6
+CUDA_VERSION?=9.0
+CUDNN_VERSION?=7
 TEST=tests/
 SRC?=$(shell dirname `pwd`)
 

docs/autogen.py

@@ -489,13 +489,18 @@ def process_docstring(docstring):
             new_fpath = fpath.replace('templates', 'sources')
             shutil.copy(fpath, new_fpath)
 
+
 # Take care of index page.
-readme = open('../README.md').read()
-index = open('templates/index.md').read()
+def read_file(path):
+    with open(path) as f:
+        return f.read()
+
+
+readme = read_file('../README.md')
+index = read_file('templates/index.md')
 index = index.replace('{{autogenerated}}', readme[readme.find('##'):])
-f = open('sources/index.md', 'w')
-f.write(index)
-f.close()
+with open('sources/index.md', 'w') as f:
+    f.write(index)
 
 print('Starting autogeneration.')
 for page_data in PAGES:
@@ -564,7 +569,7 @@ def process_docstring(docstring):
     page_name = page_data['page']
     path = os.path.join('sources', page_name)
     if os.path.exists(path):
-        template = open(path).read()
+        template = read_file(path)
         assert '{{autogenerated}}' in template, ('Template found for ' + path +
                                                  ' but missing {{autogenerated}} tag.')
         mkdown = template.replace('{{autogenerated}}', mkdown)
@@ -574,6 +579,7 @@ def process_docstring(docstring):
     subdir = os.path.dirname(path)
     if not os.path.exists(subdir):
         os.makedirs(subdir)
-    open(path, 'w').write(mkdown)
+    with open(path, 'w') as f:
+        f.write(mkdown)
 
 shutil.copyfile('../CONTRIBUTING.md', 'sources/contributing.md')

docs/templates/getting-started/functional-api-guide.md

@@ -168,15 +168,15 @@ One way to achieve this is to build a model that encodes two tweets into two vec
 
 Because the problem is symmetric, the mechanism that encodes the first tweet should be reused (weights and all) to encode the second tweet. Here we use a shared LSTM layer to encode the tweets.
 
-Let's build this with the functional API. We will take as input for a tweet a binary matrix of shape `(140, 256)`, i.e. a sequence of 140 vectors of size 256, where each dimension in the 256-dimensional vector encodes the presence/absence of a character (out of an alphabet of 256 frequent characters).
+Let's build this with the functional API. We will take as input for a tweet a binary matrix of shape `(280, 256)`, i.e. a sequence of 280 vectors of size 256, where each dimension in the 256-dimensional vector encodes the presence/absence of a character (out of an alphabet of 256 frequent characters).
 
 ```python
 import keras
 from keras.layers import Input, LSTM, Dense
 from keras.models import Model
 
-tweet_a = Input(shape=(140, 256))
-tweet_b = Input(shape=(140, 256))
+tweet_a = Input(shape=(280, 256))
+tweet_b = Input(shape=(280, 256))
 ```
 
 To share a layer across different inputs, simply instantiate the layer once, then call it on as many inputs as you want:
@@ -222,7 +222,7 @@ In previous versions of Keras, you could obtain the output tensor of a layer ins
 As long as a layer is only connected to one input, there is no confusion, and `.output` will return the one output of the layer:
 
 ```python
-a = Input(shape=(140, 256))
+a = Input(shape=(280, 256))
 
 lstm = LSTM(32)
 encoded_a = lstm(a)
@@ -232,8 +232,8 @@ assert lstm.output == encoded_a
 
 Not so if the layer has multiple inputs:
 ```python
-a = Input(shape=(140, 256))
-b = Input(shape=(140, 256))
+a = Input(shape=(280, 256))
+b = Input(shape=(280, 256))
 
 lstm = LSTM(32)
 encoded_a = lstm(a)

docs/templates/preprocessing/image.md

@@ -82,15 +82,15 @@ Generate batches of tensor image data with real-time data augmentation. The data
             - __batch_size__: int (default: 32).
             - __shuffle__: boolean (default: True).
             - __seed__: int (default: None).
-            - __save_to_dir__: None or str (default: None). This allows you to optimally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing).
+            - __save_to_dir__: None or str (default: None). This allows you to optionally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing).
             - __save_prefix__: str (default: `''`). Prefix to use for filenames of saved pictures (only relevant if `save_to_dir` is set).
             - __save_format__: one of "png", "jpeg" (only relevant if `save_to_dir` is set). Default: "png".
         - __yields__: Tuples of `(x, y)` where `x` is a numpy array of image data and `y` is a numpy array of corresponding labels.
             The generator loops indefinitely.
     - __flow_from_directory(directory)__: Takes the path to a directory, and generates batches of augmented/normalized data. Yields batches indefinitely, in an infinite loop.
         - __Arguments__:
             - __directory__: path to the target directory. It should contain one subdirectory per class.
-                Any PNG, JPG, BMP or PPM images inside each of the subdirectories directory tree will be included in the generator.
+                Any PNG, JPG, BMP, PPM or TIF images inside each of the subdirectories directory tree will be included in the generator.
                 See [this script](https://gist.github.com/fchollet/0830affa1f7f19fd47b06d4cf89ed44d) for more details.
             - __target_size__: tuple of integers `(height, width)`, default: `(256, 256)`. 
                 The dimensions to which all images found will be resized.
@@ -100,7 +100,7 @@ Generate batches of tensor image data with real-time data augmentation. The data
             - __batch_size__: size of the batches of data (default: 32).
             - __shuffle__: whether to shuffle the data (default: True)
             - __seed__: optional random seed for shuffling and transformations.
-            - __save_to_dir__: None or str (default: None). This allows you to optimally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing).
+            - __save_to_dir__: None or str (default: None). This allows you to optionally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing).
             - __save_prefix__: str. Prefix to use for filenames of saved pictures (only relevant if `save_to_dir` is set).
             - __save_format__: one of "png", "jpeg" (only relevant if `save_to_dir` is set). Default: "png".
             - __follow_links__: whether to follow symlinks inside class subdirectories (default: False).

docs/templates/preprocessing/text.md

@@ -81,14 +81,16 @@ keras.preprocessing.text.Tokenizer(num_words=None,
                                    filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n',
                                    lower=True,
                                    split=" ",
-                                   char_level=False)
+                                   char_level=False,
+                                   oov_token=None)
 ```
 
 Class for vectorizing texts, or/and turning texts into sequences (=list of word indexes, where the word of rank i in the dataset (starting at 1) has index i).
 
 - __Arguments__: Same as `text_to_word_sequence` above.
     - __num_words__: None or int. Maximum number of words to work with (if set, tokenization will be restricted to the top num_words most common words in the dataset).
     - __char_level__: if True, every character will be treated as a token.
+    - __oov_token__: None or str. If given, it will be added to word_index and used to replace out-of-vocabulary words during text_to_sequence calls.
 
 - __Methods__:
 

docs/templates/why-use-keras.md

@@ -34,7 +34,7 @@ Your Keras models can be easily deployed across a greater range of platforms tha
 - On Android, via the TensorFlow Android runtime. Example: [Not Hotdog app](https://medium.com/@timanglade/how-hbos-silicon-valley-built-not-hotdog-with-mobile-tensorflow-keras-react-native-ef03260747f3)
 - In the browser, via GPU-accelerated JavaScript runtimes such as [Keras.js](https://transcranial.github.io/keras-js/#/) and [WebDNN](https://mil-tokyo.github.io/webdnn/)
 - On Google Cloud, via [TensorFlow-Serving](https://www.tensorflow.org/serving/)
-- In a Python webapp backend (such as a Flask app)
+- [In a Python webapp backend (such as a Flask app)](https://blog.keras.io/building-a-simple-keras-deep-learning-rest-api.html)
 - On the JVM, via [DL4J model import provided by SkyMind](https://deeplearning4j.org/model-import-keras)
 - On Raspberry Pi
 
@@ -54,7 +54,7 @@ As such, your Keras model can be trained on a number of different hardware platf
 
 - [NVIDIA GPUs](https://developer.nvidia.com/deep-learning)
 - [Google TPUs](https://cloud.google.com/tpu/), via the TensorFlow backend and Google Cloud
-- OpenGL-enabled GPUs, such as those from AMD, via [the PlaidML Keras backend](https://github.com/plaidml/plaidml)
+- OpenCL-enabled GPUs, such as those from AMD, via [the PlaidML Keras backend](https://github.com/plaidml/plaidml)
 
 ---
 

examples/babi_memnn.py

@@ -100,7 +100,7 @@ def vectorize_stories(data):
           '$ wget http://www.thespermwhale.com/jaseweston/babi/tasks_1-20_v1-2.tar.gz\n'
           '$ mv tasks_1-20_v1-2.tar.gz ~/.keras/datasets/babi-tasks-v1-2.tar.gz')
     raise
-tar = tarfile.open(path)
+
 
 challenges = {
     # QA1 with 10,000 samples
@@ -112,8 +112,9 @@ def vectorize_stories(data):
 challenge = challenges[challenge_type]
 
 print('Extracting stories for the challenge:', challenge_type)
-train_stories = get_stories(tar.extractfile(challenge.format('train')))
-test_stories = get_stories(tar.extractfile(challenge.format('test')))
+with tarfile.open(path) as tar:
+    train_stories = get_stories(tar.extractfile(challenge.format('train')))
+    test_stories = get_stories(tar.extractfile(challenge.format('test')))
 
 vocab = set()
 for story, q, answer in train_stories + test_stories:

examples/babi_rnn.py

@@ -160,7 +160,7 @@ def vectorize_stories(data, word_idx, story_maxlen, query_maxlen):
           '$ wget http://www.thespermwhale.com/jaseweston/babi/tasks_1-20_v1-2.tar.gz\n'
           '$ mv tasks_1-20_v1-2.tar.gz ~/.keras/datasets/babi-tasks-v1-2.tar.gz')
     raise
-tar = tarfile.open(path)
+
 # Default QA1 with 1000 samples
 # challenge = 'tasks_1-20_v1-2/en/qa1_single-supporting-fact_{}.txt'
 # QA1 with 10,000 samples
@@ -169,8 +169,9 @@ def vectorize_stories(data, word_idx, story_maxlen, query_maxlen):
 challenge = 'tasks_1-20_v1-2/en/qa2_two-supporting-facts_{}.txt'
 # QA2 with 10,000 samples
 # challenge = 'tasks_1-20_v1-2/en-10k/qa2_two-supporting-facts_{}.txt'
-train = get_stories(tar.extractfile(challenge.format('train')))
-test = get_stories(tar.extractfile(challenge.format('test')))
+with tarfile.open(path) as tar:
+    train = get_stories(tar.extractfile(challenge.format('train')))
+    test = get_stories(tar.extractfile(challenge.format('test')))
 
 vocab = set()
 for story, q, answer in train + test: