tfds new template

Author: Ekhao

tensorflow_datasets/image_classification/__init__.py

@@ -96,3 +96,4 @@
 from tensorflow_datasets.image_classification.svhn import SvhnCropped
 from tensorflow_datasets.image_classification.uc_merced import UcMerced
 from tensorflow_datasets.image_classification.visual_domain_decathlon import VisualDomainDecathlon
+from tensorflow_datasets.image_classification.wake_vision import WakeVision

tensorflow_datasets/image_classification/wake_vision/CITATIONS.bib

@@ -0,0 +1 @@
+// TODO(wake_vision): To be added after dataset upload and paper publishing.

tensorflow_datasets/image_classification/wake_vision/README.md

@@ -0,0 +1,5 @@
+TODO(wake_vision): Markdown description of that will appear on the catalog page.
+Description is **formatted** as markdown.
+
+It should also contain any processing which has been applied (if any),
+(e.g. corrupted example skipped, images cropped,...):

tensorflow_datasets/image_classification/wake_vision/TAGS.txt

@@ -0,0 +1,3 @@
+# TODO(wake_vision): If your dataset downloads files, then the checksums
+# will be automatically added here when running
+# `tfds build --register_checksums`.

tensorflow_datasets/image_classification/wake_vision/__init__.py

@@ -0,0 +1,47 @@
+"""wake_vision dataset."""
+
+import tensorflow_datasets.public_api as tfds
+
+
+class Builder(tfds.core.GeneratorBasedBuilder):
+  """DatasetBuilder for wake_vision dataset."""
+
+  VERSION = tfds.core.Version('1.0.0')
+  RELEASE_NOTES = {
+      '1.0.0': 'Initial release.',
+  }
+
+  def _info(self) -> tfds.core.DatasetInfo:
+    """Returns the dataset metadata."""
+    # TODO(wake_vision): Specifies the tfds.core.DatasetInfo object
+    return self.dataset_info_from_configs(
+        features=tfds.features.FeaturesDict({
+            # These are the features of your dataset like images, labels ...
+            'image': tfds.features.Image(shape=(None, None, 3)),
+            'label': tfds.features.ClassLabel(names=['no', 'yes']),
+        }),
+        # If there's a common (input, target) tuple from the
+        # features, specify them here. They'll be used if
+        # `as_supervised=True` in `builder.as_dataset`.
+        supervised_keys=('image', 'label'),  # Set to `None` to disable
+        homepage='https://dataset-homepage/',
+    )
+
+  def _split_generators(self, dl_manager: tfds.download.DownloadManager):
+    """Returns SplitGenerators."""
+    # TODO(wake_vision): Downloads the data and defines the splits
+    path = dl_manager.download_and_extract('https://todo-data-url')
+
+    # TODO(wake_vision): Returns the Dict[split names, Iterator[Key, Example]]
+    return {
+        'train': self._generate_examples(path / 'train_imgs'),
+    }
+
+  def _generate_examples(self, path):
+    """Yields examples."""
+    # TODO(wake_vision): Yields (key, example) tuples from the dataset
+    for f in path.glob('*.jpeg'):
+      yield 'key', {
+          'image': f,
+          'label': 'yes',
+      }

tensorflow_datasets/image_classification/wake_vision/checksums.tsv

@@ -0,0 +1,23 @@
+"""wake_vision dataset."""
+
+from tensorflow_datasets.image_classification.wake_vision import wake_vision_dataset_builder
+import tensorflow_datasets.public_api as tfds
+
+class WakeVisionTest(tfds.testing.DatasetBuilderTestCase):
+  """Tests for wake_vision dataset."""
+  # TODO(wake_vision):
+  DATASET_CLASS = wake_vision_dataset_builder.Builder
+  SPLITS = {
+      'train': 3,  # Number of fake train example
+      'test': 1,  # Number of fake test example
+  }
+
+  # If you are calling `download/download_and_extract` with a dict, like:
+  #   dl_manager.download({'some_key': 'http://a.org/out.txt', ...})
+  # then the tests needs to provide the fake output paths relative to the
+  # fake data directory
+  # DL_EXTRACT_RESULT = {'some_key': 'output_file1.txt', ...}
+
+
+if __name__ == '__main__':
+  tfds.testing.test_main()