Automated documentation update

PiperOrigin-RevId: 264634671
Anirban6393 · Aug 21, 2019 · a7834f2 · a7834f2
1 parent a7ceac6
commit a7834f2
Show file tree

Hide file tree

Showing 16 changed files with 286 additions and 19 deletions.
diff --git a/docs/api_docs/python/tfds/core/BeamBasedBuilder.md b/docs/api_docs/python/tfds/core/BeamBasedBuilder.md
@@ -87,7 +87,7 @@ source</a>
 as_dataset(
     split=None,
     batch_size=None,
-    shuffle_files=None,
+    shuffle_files=False,
     decoders=None,
     as_supervised=False,
     in_memory=None
@@ -150,7 +150,7 @@ assert isinstance(ds_test_supervised, tf.data.Dataset)
     a custom pipeline. If `batch_size == -1`, will return feature dictionaries
     of the whole dataset with `tf.Tensor`s instead of a `tf.data.Dataset`.
 *   <b>`shuffle_files`</b>: `bool`, whether to shuffle the input files. Defaults
-    to `True` if `split == tfds.Split.TRAIN` and `False` otherwise.
+    to `False`.
 *   <b>`decoders`</b>: Nested dict of `Decoder` objects which allow to customize
     the decoding. The structure should match the feature structure, but only
     customized feature keys need to be present. See

diff --git a/docs/api_docs/python/tfds/core/DatasetBuilder.md b/docs/api_docs/python/tfds/core/DatasetBuilder.md
@@ -118,7 +118,7 @@ source</a>
 as_dataset(
     split=None,
     batch_size=None,
-    shuffle_files=None,
+    shuffle_files=False,
     decoders=None,
     as_supervised=False,
     in_memory=None
@@ -181,7 +181,7 @@ assert isinstance(ds_test_supervised, tf.data.Dataset)
     a custom pipeline. If `batch_size == -1`, will return feature dictionaries
     of the whole dataset with `tf.Tensor`s instead of a `tf.data.Dataset`.
 *   <b>`shuffle_files`</b>: `bool`, whether to shuffle the input files. Defaults
-    to `True` if `split == tfds.Split.TRAIN` and `False` otherwise.
+    to `False`.
 *   <b>`decoders`</b>: Nested dict of `Decoder` objects which allow to customize
     the decoding. The structure should match the feature structure, but only
     customized feature keys need to be present. See

diff --git a/docs/api_docs/python/tfds/core/GeneratorBasedBuilder.md b/docs/api_docs/python/tfds/core/GeneratorBasedBuilder.md
@@ -96,7 +96,7 @@ source</a>
 as_dataset(
     split=None,
     batch_size=None,
-    shuffle_files=None,
+    shuffle_files=False,
     decoders=None,
     as_supervised=False,
     in_memory=None
@@ -159,7 +159,7 @@ assert isinstance(ds_test_supervised, tf.data.Dataset)
     a custom pipeline. If `batch_size == -1`, will return feature dictionaries
     of the whole dataset with `tf.Tensor`s instead of a `tf.data.Dataset`.
 *   <b>`shuffle_files`</b>: `bool`, whether to shuffle the input files. Defaults
-    to `True` if `split == tfds.Split.TRAIN` and `False` otherwise.
+    to `False`.
 *   <b>`decoders`</b>: Nested dict of `Decoder` objects which allow to customize
     the decoding. The structure should match the feature structure, but only
     customized feature keys need to be present. See

diff --git a/docs/api_docs/python/tfds/load.md b/docs/api_docs/python/tfds/load.md
@@ -20,7 +20,7 @@ tfds.load(
     data_dir=None,
     batch_size=None,
     in_memory=None,
-    shuffle_files=None,
+    shuffle_files=False,
     download=True,
     as_supervised=False,
     decoders=None,
@@ -106,8 +106,7 @@ of hundreds of GiB to disk. Refer to the `download` argument.
     dimensions, the features will be padded to the maximum size across the
     dataset.
 *   <b>`shuffle_files`</b>: `bool`, whether to shuffle the input files. Defaults
-    to `True` if `split == tfds.Split.TRAIN` and `False` otherwise. From
-    2019-08-20, will always default to False.
+    to `False`.
 *   <b>`download`</b>: `bool` (optional), whether to call
     <a href="../tfds/core/DatasetBuilder.md#download_and_prepare"><code>tfds.core.DatasetBuilder.download_and_prepare</code></a>
     before calling `tf.DatasetBuilder.as_dataset`. If `False`, data is expected

diff --git a/docs/api_docs/python/tfds/testing/DummyDatasetSharedGenerator.md b/docs/api_docs/python/tfds/testing/DummyDatasetSharedGenerator.md
@@ -89,7 +89,7 @@ source</a>
 as_dataset(
     split=None,
     batch_size=None,
-    shuffle_files=None,
+    shuffle_files=False,
     decoders=None,
     as_supervised=False,
     in_memory=None
@@ -152,7 +152,7 @@ assert isinstance(ds_test_supervised, tf.data.Dataset)
     a custom pipeline. If `batch_size == -1`, will return feature dictionaries
     of the whole dataset with `tf.Tensor`s instead of a `tf.data.Dataset`.
 *   <b>`shuffle_files`</b>: `bool`, whether to shuffle the input files. Defaults
-    to `True` if `split == tfds.Split.TRAIN` and `False` otherwise.
+    to `False`.
 *   <b>`decoders`</b>: Nested dict of `Decoder` objects which allow to customize
     the decoding. The structure should match the feature structure, but only
     customized feature keys need to be present. See

diff --git a/docs/api_docs/python/tfds/testing/DummyMnist.md b/docs/api_docs/python/tfds/testing/DummyMnist.md
@@ -89,7 +89,7 @@ source</a>
 as_dataset(
     split=None,
     batch_size=None,
-    shuffle_files=None,
+    shuffle_files=False,
     decoders=None,
     as_supervised=False,
     in_memory=None
@@ -152,7 +152,7 @@ assert isinstance(ds_test_supervised, tf.data.Dataset)
     a custom pipeline. If `batch_size == -1`, will return feature dictionaries
     of the whole dataset with `tf.Tensor`s instead of a `tf.data.Dataset`.
 *   <b>`shuffle_files`</b>: `bool`, whether to shuffle the input files. Defaults
-    to `True` if `split == tfds.Split.TRAIN` and `False` otherwise.
+    to `False`.
 *   <b>`decoders`</b>: Nested dict of `Decoder` objects which allow to customize
     the decoding. The structure should match the feature structure, but only
     customized feature keys need to be present. See

diff --git a/docs/catalog/_toc.yaml b/docs/catalog/_toc.yaml
@@ -86,6 +86,8 @@ toc:
     title: lfw
   - path: /datasets/catalog/lsun
     title: lsun
+  - path: /datasets/catalog/malaria
+    title: malaria
   - path: /datasets/catalog/mnist
     title: mnist
   - path: /datasets/catalog/mnist_corrupted

diff --git a/docs/catalog/deep_weeds.md b/docs/catalog/deep_weeds.md
@@ -25,7 +25,6 @@ Range", "Kelso", "McKinlay" and "Paluma".
 *   Size: `?? GiB`
 
 ## Features
-
 ```python
 FeaturesDict({
     'image': Image(shape=(256, 256, 3), dtype=tf.uint8),
@@ -34,19 +33,16 @@ FeaturesDict({
 ```
 
 ## Statistics
-
 None computed
 
 ## Urls
 
 *   [https://nextcloud.qriscloud.org.au/index.php/s/a3KxPawpqkiorST/download](https://nextcloud.qriscloud.org.au/index.php/s/a3KxPawpqkiorST/download)
 
 ## Supervised keys (for `as_supervised=True`)
-
 `(u'image', u'label')`
 
 ## Citation
-
 ```
 @article{DeepWeeds2019,
   author = {Alex Olsen and

diff --git a/docs/catalog/malaria.md b/docs/catalog/malaria.md
@@ -0,0 +1,62 @@
+<div itemscope itemtype="http://schema.org/Dataset">
+  <div itemscope itemprop="includedInDataCatalog" itemtype="http://schema.org/DataCatalog">
+    <meta itemprop="name" content="TensorFlow Datasets" />
+  </div>
+  <meta itemprop="name" content="malaria" />
+  <meta itemprop="description" content="The Malaria dataset contains a total of 27,558 cell images&#10;with equal instances of parasitized and uninfected cells from the thin blood &#10;smear slide images of segmented cells." />
+  <meta itemprop="url" content="https://www.tensorflow.org/datasets/catalog/malaria" />
+  <meta itemprop="sameAs" content="https://ceb.nlm.nih.gov/proj/malaria/cell_images.zip" />
+</div>
+
+# `malaria`
+
+The Malaria dataset contains a total of 27,558 cell images with equal instances
+of parasitized and uninfected cells from the thin blood smear slide images of
+segmented cells.
+
+*   URL:
+    [https://ceb.nlm.nih.gov/proj/malaria/cell_images.zip](https://ceb.nlm.nih.gov/proj/malaria/cell_images.zip)
+*   `DatasetBuilder`:
+    [`tfds.image.malaria.Malaria`](https://github.com/tensorflow/datasets/tree/master/tensorflow_datasets/image/malaria.py)
+*   Version: `v1.0.0`
+*   Size: `?? GiB`
+
+## Features
+
+```python
+FeaturesDict({
+    'image': Image(shape=(None, None, 3), dtype=tf.uint8),
+    'label': ClassLabel(shape=(), dtype=tf.int64, num_classes=2),
+})
+```
+
+## Statistics
+
+None computed
+
+## Urls
+
+*   [https://ceb.nlm.nih.gov/proj/malaria/cell_images.zip](https://ceb.nlm.nih.gov/proj/malaria/cell_images.zip)
+
+## Supervised keys (for `as_supervised=True`)
+
+`(u'image', u'label')`
+
+## Citation
+
+```
+@article{rajaraman2018pre,
+  title={Pre-trained convolutional neural networks as feature extractors toward
+  improved malaria parasite detection in thin blood smear images},
+  author={Rajaraman, Sivaramakrishnan and Antani, Sameer K and Poostchi, Mahdieh
+  and Silamut, Kamolrat and Hossain, Md A and Maude, Richard J and Jaeger,
+  Stefan and Thoma, George R},
+  journal={PeerJ},
+  volume={6},
+  pages={e4568},
+  year={2018},
+  publisher={PeerJ Inc.}
+}
+```
+
+--------------------------------------------------------------------------------
diff --git a/docs/catalog/overview.md b/docs/catalog/overview.md
@@ -76,6 +76,7 @@ np_datasets = tfds.as_numpy(datasets)
     *   [`kmnist`](kmnist.md)
     *   [`lfw`](lfw.md)
     *   [`lsun`](lsun.md)
+    *   [`malaria`](malaria.md)
     *   [`mnist`](mnist.md)
     *   [`mnist_corrupted`](mnist_corrupted.md)
     *   [`omniglot`](omniglot.md)

diff --git a/docs/catalog/stanford_online_products.md b/docs/catalog/stanford_online_products.md
@@ -17,18 +17,35 @@ Stanford Online Products Dataset
 *   `DatasetBuilder`:
     [`tfds.image.stanford_online_products.StanfordOnlineProducts`](https://github.com/tensorflow/datasets/tree/master/tensorflow_datasets/image/stanford_online_products.py)
 *   Version: `v1.0.0`
+*   Size: `2.87 GiB`
 
+## Features
+
+```python
+FeaturesDict({
+    'class_id': ClassLabel(shape=(), dtype=tf.int64, num_classes=22634),
+    'image': Image(shape=(None, None, 3), dtype=tf.uint8),
+    'super_class_id': ClassLabel(shape=(), dtype=tf.int64, num_classes=12),
+    'super_class_id/num': ClassLabel(shape=(), dtype=tf.int64, num_classes=12),
+})
+```
+
+## Statistics
+
+Split | Examples
+:---- | -------:
+ALL   | 120,053
+TEST  | 60,502
+TRAIN | 59,551
 
 ## Urls
 
 *   [http://cvgl.stanford.edu/projects/lifted_struct/](http://cvgl.stanford.edu/projects/lifted_struct/)
 
 ## Supervised keys (for `as_supervised=True`)
-
 `None`
 
 ## Citation
-
 ```
 @inproceedings{song2016deep,
  author    = {Song, Hyun Oh and Xiang, Yu and Jegelka, Stefanie and Savarese, Silvio},

diff --git a/tensorflow_datasets/testing/metadata/missing.txt b/tensorflow_datasets/testing/metadata/missing.txt
@@ -50,6 +50,7 @@ bigearthnet/all/0.0.2
 bigearthnet/rgb/0.0.2
 caltech_birds2010/0.1.0
 caltech_birds2011/0.1.0
+deep_weeds/1.0.0
 diabetic_retinopathy_detection/btgraham-300/1.0.0
 diabetic_retinopathy_detection/btgraham-300/2.0.0
 eurosat/all/0.0.1
@@ -102,6 +103,7 @@ lm1b/bytes/1.0.0
 lm1b/plain_text/1.0.0
 lm1b/subwords32k/1.0.0
 lm1b/subwords8k/1.0.0
+malaria/1.0.0
 mnist_corrupted/canny_edges/1.0.0
 oxford_iiit_pet/1.2.0
 so2sat/all/0.0.1