Merge branch 'master' of https://github.com/tensorflow/datasets into document_dataset_bug

Author: us

docs/api_docs/python/tfds/_api_cache.json

@@ -139,8 +139,6 @@
     "tfds.core": false, 
     "tfds.core.BeamBasedBuilder": false, 
     "tfds.core.BeamBasedBuilder.BUILDER_CONFIGS": true, 
-    "tfds.core.BeamBasedBuilder.GOOGLE_DISABLED": true, 
-    "tfds.core.BeamBasedBuilder.IN_DEVELOPMENT": true, 
     "tfds.core.BeamBasedBuilder.SUPPORTED_VERSIONS": true, 
     "tfds.core.BeamBasedBuilder.VERSION": true, 
     "tfds.core.BeamBasedBuilder.__init__": true, 
@@ -160,8 +158,6 @@
     "tfds.core.BuilderConfig.version": true, 
     "tfds.core.DatasetBuilder": false, 
     "tfds.core.DatasetBuilder.BUILDER_CONFIGS": true, 
-    "tfds.core.DatasetBuilder.GOOGLE_DISABLED": true, 
-    "tfds.core.DatasetBuilder.IN_DEVELOPMENT": true, 
     "tfds.core.DatasetBuilder.SUPPORTED_VERSIONS": true, 
     "tfds.core.DatasetBuilder.VERSION": true, 
     "tfds.core.DatasetBuilder.__init__": true, 
@@ -197,10 +193,9 @@
     "tfds.core.DatasetInfo.write_to_directory": true, 
     "tfds.core.Experiment": false, 
     "tfds.core.Experiment.DUMMY": true, 
+    "tfds.core.Experiment.S3": true, 
     "tfds.core.GeneratorBasedBuilder": false, 
     "tfds.core.GeneratorBasedBuilder.BUILDER_CONFIGS": true, 
-    "tfds.core.GeneratorBasedBuilder.GOOGLE_DISABLED": true, 
-    "tfds.core.GeneratorBasedBuilder.IN_DEVELOPMENT": true, 
     "tfds.core.GeneratorBasedBuilder.SUPPORTED_VERSIONS": true, 
     "tfds.core.GeneratorBasedBuilder.VERSION": true, 
     "tfds.core.GeneratorBasedBuilder.__init__": true, 
@@ -598,10 +593,10 @@
     "tfds.testing.DatasetBuilderTestCase.DATASET_CLASS": true, 
     "tfds.testing.DatasetBuilderTestCase.DL_EXTRACT_RESULT": true, 
     "tfds.testing.DatasetBuilderTestCase.EXAMPLE_DIR": true, 
-    "tfds.testing.DatasetBuilderTestCase.INTERNAL_DATASET": true, 
     "tfds.testing.DatasetBuilderTestCase.MOCK_MONARCH": true, 
     "tfds.testing.DatasetBuilderTestCase.MOCK_OUT_FORBIDDEN_OS_FUNCTIONS": true, 
     "tfds.testing.DatasetBuilderTestCase.OVERLAPPING_SPLITS": true, 
+    "tfds.testing.DatasetBuilderTestCase.VERSION": true, 
     "tfds.testing.DatasetBuilderTestCase.__call__": true, 
     "tfds.testing.DatasetBuilderTestCase.__eq__": true, 
     "tfds.testing.DatasetBuilderTestCase.__init__": true, 
@@ -743,8 +738,6 @@
     "tfds.testing.DatasetBuilderTestCase.test_session": true, 
     "tfds.testing.DummyDatasetSharedGenerator": false, 
     "tfds.testing.DummyDatasetSharedGenerator.BUILDER_CONFIGS": true, 
-    "tfds.testing.DummyDatasetSharedGenerator.GOOGLE_DISABLED": true, 
-    "tfds.testing.DummyDatasetSharedGenerator.IN_DEVELOPMENT": true, 
     "tfds.testing.DummyDatasetSharedGenerator.SUPPORTED_VERSIONS": true, 
     "tfds.testing.DummyDatasetSharedGenerator.VERSION": true, 
     "tfds.testing.DummyDatasetSharedGenerator.__init__": true, 
@@ -758,8 +751,6 @@
     "tfds.testing.DummyDatasetSharedGenerator.version": true, 
     "tfds.testing.DummyMnist": false, 
     "tfds.testing.DummyMnist.BUILDER_CONFIGS": true, 
-    "tfds.testing.DummyMnist.GOOGLE_DISABLED": true, 
-    "tfds.testing.DummyMnist.IN_DEVELOPMENT": true, 
     "tfds.testing.DummyMnist.SUPPORTED_VERSIONS": true, 
     "tfds.testing.DummyMnist.VERSION": true, 
     "tfds.testing.DummyMnist.__init__": true, 
@@ -1197,7 +1188,6 @@
     "tfds.units.MiB": true, 
     "tfds.units.PiB": true, 
     "tfds.units.TiB": true, 
-    "tfds.units.absolute_import": true, 
     "tfds.units.division": true, 
     "tfds.units.print_function": true, 
     "tfds.units.size_str": false

docs/api_docs/python/tfds/core/BeamBasedBuilder.md

@@ -9,8 +9,6 @@
 <meta itemprop="property" content="as_dataset"/>
 <meta itemprop="property" content="download_and_prepare"/>
 <meta itemprop="property" content="BUILDER_CONFIGS"/>
-<meta itemprop="property" content="GOOGLE_DISABLED"/>
-<meta itemprop="property" content="IN_DEVELOPMENT"/>
 <meta itemprop="property" content="SUPPORTED_VERSIONS"/>
 <meta itemprop="property" content="VERSION"/>
 <meta itemprop="property" content="builder_configs"/>
@@ -80,7 +78,8 @@ as_dataset(
     split=None,
     batch_size=None,
     shuffle_files=None,
-    as_supervised=False
+    as_supervised=False,
+    in_memory=None
 )
 ```
 
@@ -105,6 +104,10 @@ Callers must pass arguments as keyword arguments.
     will have a 2-tuple structure `(input, label)` according to
     `builder.info.supervised_keys`. If `False`, the default, the returned
     `tf.data.Dataset` will have a dictionary with all the features.
+*   <b>`in_memory`</b>: `bool`, if `True`, loads the dataset in memory which
+    increases iteration speeds. Note that if `True` and the dataset has unknown
+    dimensions, the features will be padded to the maximum size across the
+    dataset.
 
 #### Returns:
 
@@ -142,8 +145,6 @@ Downloads and prepares dataset for reading.
 ## Class Members
 
 *   `BUILDER_CONFIGS` <a id="BUILDER_CONFIGS"></a>
-*   `GOOGLE_DISABLED = False` <a id="GOOGLE_DISABLED"></a>
-*   `IN_DEVELOPMENT = False` <a id="IN_DEVELOPMENT"></a>
 *   `SUPPORTED_VERSIONS` <a id="SUPPORTED_VERSIONS"></a>
 *   `VERSION = None` <a id="VERSION"></a>
 *   `builder_configs` <a id="builder_configs"></a>

docs/api_docs/python/tfds/core/DatasetBuilder.md

@@ -9,8 +9,6 @@
 <meta itemprop="property" content="as_dataset"/>
 <meta itemprop="property" content="download_and_prepare"/>
 <meta itemprop="property" content="BUILDER_CONFIGS"/>
-<meta itemprop="property" content="GOOGLE_DISABLED"/>
-<meta itemprop="property" content="IN_DEVELOPMENT"/>
 <meta itemprop="property" content="SUPPORTED_VERSIONS"/>
 <meta itemprop="property" content="VERSION"/>
 <meta itemprop="property" content="builder_configs"/>
@@ -111,7 +109,8 @@ as_dataset(
     split=None,
     batch_size=None,
     shuffle_files=None,
-    as_supervised=False
+    as_supervised=False,
+    in_memory=None
 )
 ```
 
@@ -136,6 +135,10 @@ Callers must pass arguments as keyword arguments.
     will have a 2-tuple structure `(input, label)` according to
     `builder.info.supervised_keys`. If `False`, the default, the returned
     `tf.data.Dataset` will have a dictionary with all the features.
+*   <b>`in_memory`</b>: `bool`, if `True`, loads the dataset in memory which
+    increases iteration speeds. Note that if `True` and the dataset has unknown
+    dimensions, the features will be padded to the maximum size across the
+    dataset.
 
 #### Returns:
 
@@ -173,8 +176,6 @@ Downloads and prepares dataset for reading.
 ## Class Members
 
 *   `BUILDER_CONFIGS` <a id="BUILDER_CONFIGS"></a>
-*   `GOOGLE_DISABLED = False` <a id="GOOGLE_DISABLED"></a>
-*   `IN_DEVELOPMENT = False` <a id="IN_DEVELOPMENT"></a>
 *   `SUPPORTED_VERSIONS` <a id="SUPPORTED_VERSIONS"></a>
 *   `VERSION = None` <a id="VERSION"></a>
 *   `builder_configs` <a id="builder_configs"></a>

docs/api_docs/python/tfds/core/Experiment.md

@@ -2,6 +2,7 @@
 <meta itemprop="name" content="tfds.core.Experiment" />
 <meta itemprop="path" content="Stable" />
 <meta itemprop="property" content="DUMMY"/>
+<meta itemprop="property" content="S3"/>
 </div>
 
 # tfds.core.Experiment
@@ -30,3 +31,4 @@ tfds.core.Experiment.EXP_A: True, })
 ## Class Members
 
 *   `DUMMY` <a id="DUMMY"></a>
+*   `S3` <a id="S3"></a>

docs/api_docs/python/tfds/core/GeneratorBasedBuilder.md

@@ -9,8 +9,6 @@
 <meta itemprop="property" content="as_dataset"/>
 <meta itemprop="property" content="download_and_prepare"/>
 <meta itemprop="property" content="BUILDER_CONFIGS"/>
-<meta itemprop="property" content="GOOGLE_DISABLED"/>
-<meta itemprop="property" content="IN_DEVELOPMENT"/>
 <meta itemprop="property" content="SUPPORTED_VERSIONS"/>
 <meta itemprop="property" content="VERSION"/>
 <meta itemprop="property" content="builder_configs"/>
@@ -89,7 +87,8 @@ as_dataset(
     split=None,
     batch_size=None,
     shuffle_files=None,
-    as_supervised=False
+    as_supervised=False,
+    in_memory=None
 )
 ```
 
@@ -114,6 +113,10 @@ Callers must pass arguments as keyword arguments.
     will have a 2-tuple structure `(input, label)` according to
     `builder.info.supervised_keys`. If `False`, the default, the returned
     `tf.data.Dataset` will have a dictionary with all the features.
+*   <b>`in_memory`</b>: `bool`, if `True`, loads the dataset in memory which
+    increases iteration speeds. Note that if `True` and the dataset has unknown
+    dimensions, the features will be padded to the maximum size across the
+    dataset.
 
 #### Returns:
 
@@ -151,8 +154,6 @@ Downloads and prepares dataset for reading.
 ## Class Members
 
 *   `BUILDER_CONFIGS` <a id="BUILDER_CONFIGS"></a>
-*   `GOOGLE_DISABLED = False` <a id="GOOGLE_DISABLED"></a>
-*   `IN_DEVELOPMENT = False` <a id="IN_DEVELOPMENT"></a>
 *   `SUPPORTED_VERSIONS` <a id="SUPPORTED_VERSIONS"></a>
 *   `VERSION = None` <a id="VERSION"></a>
 *   `builder_configs` <a id="builder_configs"></a>

docs/api_docs/python/tfds/disable_progress_bar.md

@@ -14,7 +14,13 @@ tfds.disable_progress_bar()
 Defined in
 [`core/utils/tqdm_utils.py`](https://github.com/tensorflow/datasets/tree/master/tensorflow_datasets/core/utils/tqdm_utils.py).
 
-<!-- Placeholder for "Used in" -->
+### Used in the tutorials:
+
+*   [CycleGAN](https://www.tensorflow.org/beta/tutorials/generative/cyclegan)
+*   [Distributed training with Keras](https://www.tensorflow.org/beta/tutorials/distribute/keras)
+*   [Multi-worker Training with Estimator](https://www.tensorflow.org/beta/tutorials/distribute/multi_worker_with_estimator)
+*   [Multi-worker Training with Keras](https://www.tensorflow.org/beta/tutorials/distribute/multi_worker_with_keras)
+*   [Transfer Learning Using Pretrained ConvNets](https://www.tensorflow.org/beta/tutorials/images/transfer_learning)
 
 #### Usage:
 

docs/api_docs/python/tfds/features/Sequence.md

@@ -43,16 +43,32 @@ Note that `SequenceDict` do not support features which are of type
 tfds.features.Sequence(tfds.features.Image(), length=NB_FRAME)
 ```
 
-or: `tfds.features.Sequence({ 'frame': tfds.features.Image(shape=(64, 64, 3))
-'action': tfds.features.ClassLabel(['up', 'down', 'left', 'right']) },
-length=NB_FRAME)`
+or:
 
-During data generation: `yield { 'frame': np.ones(shape=(NB_FRAME, 64, 64, 3)),
-'action': ['left', 'left', 'up', ...], }`
+```
+tfds.features.Sequence({
+    'frame': tfds.features.Image(shape=(64, 64, 3))
+    'action': tfds.features.ClassLabel(['up', 'down', 'left', 'right'])
+}, length=NB_FRAME)
+```
+
+During data generation:
 
-Tensor returned by `.as_dataset()`: `{ 'frame': tf.Tensor(shape=(NB_FRAME, 64,
-64, 3), dtype=tf.uint8), 'action': tf.Tensor(shape=(NB_FRAME,), dtype=tf.int64),
-}`
+```
+yield {
+    'frame': np.ones(shape=(NB_FRAME, 64, 64, 3)),
+    'action': ['left', 'left', 'up', ...],
+}
+```
+
+Tensor returned by `.as_dataset()`:
+
+```
+{
+    'frame': tf.Tensor(shape=(NB_FRAME, 64, 64, 3), dtype=tf.uint8),
+    'action': tf.Tensor(shape=(NB_FRAME,), dtype=tf.int64),
+}
+```
 
 At generation time, you can specify a list of features dict, a dict of list
 values or a stacked numpy array. The lists will automatically be distributed

docs/api_docs/python/tfds/features/text/SubwordTextEncoder.md

@@ -23,7 +23,9 @@ Inherits From: [`TextEncoder`](../../../tfds/features/text/TextEncoder.md)
 
 Defined in [`core/features/text/subword_text_encoder.py`](https://github.com/tensorflow/datasets/tree/master/tensorflow_datasets/core/features/text/subword_text_encoder.py).
 
-<!-- Placeholder for "Used in" -->
+### Used in the tutorials:
+
+*   [Transformer model for language understanding](https://www.tensorflow.org/beta/tutorials/text/transformer)
 
 Encoding is fully invertible because all out-of-vocab wordpieces are
 byte-encoded.

docs/api_docs/python/tfds/features/text/TokenTextEncoder.md

@@ -25,7 +25,9 @@ Inherits From: [`TextEncoder`](../../../tfds/features/text/TextEncoder.md)
 
 Defined in [`core/features/text/text_encoder.py`](https://github.com/tensorflow/datasets/tree/master/tensorflow_datasets/core/features/text/text_encoder.py).
 
-<!-- Placeholder for "Used in" -->
+### Used in the tutorials:
+
+*   [Load text with tf.data](https://www.tensorflow.org/beta/tutorials/load_data/text)
 
 Tokenization splits on (and drops) non-alphanumeric characters with
 regex "\W+".
@@ -44,8 +46,10 @@ __init__(
 
 Constructs a TokenTextEncoder.
 
-To load from a file saved with `TokenTextEncoder.save_to_file`, use
-`TokenTextEncoder.load_from_file`.
+To load from a file saved with
+<a href="../../../tfds/features/text/TokenTextEncoder.md#save_to_file"><code>TokenTextEncoder.save_to_file</code></a>,
+use
+<a href="../../../tfds/features/text/TokenTextEncoder.md#load_from_file"><code>TokenTextEncoder.load_from_file</code></a>.
 
 #### Args:
 

docs/api_docs/python/tfds/features/text/Tokenizer.md

@@ -18,8 +18,9 @@ Splits a string into tokens, and joins them back.
 
 Defined in [`core/features/text/text_encoder.py`](https://github.com/tensorflow/datasets/tree/master/tensorflow_datasets/core/features/text/text_encoder.py).
 
-<!-- Placeholder for "Used in" -->
+### Used in the tutorials:
 
+*   [Load text with tf.data](https://www.tensorflow.org/beta/tutorials/load_data/text)
 
 <h2 id="__init__"><code>__init__</code></h2>