[tf.data] Implements `dataset` transformation `parse_example_dataset(..)` which will replace dataset.map(parsing_ops.parse_example(..)).

PiperOrigin-RevId: 209836033

2 files changed, 73 insertions, 0 deletions

diff --git a/tensorflow/core/api_def/base_api/api_def_ParseExampleDataset.pbtxt b/tensorflow/core/api_def/base_api/api_def_ParseExampleDataset.pbtxt
new file mode 100644
index 0000000000..3de2f18fc2
--- /dev/null
+++ b/tensorflow/core/api_def/base_api/api_def_ParseExampleDataset.pbtxt
@@ -0,0 +1,69 @@
+op {
+  graph_op_name: "ParseExampleDataset"
+  in_arg {
+    name: "dense_defaults"
+    description: <<END
+A dict mapping string keys to `Tensor`s.
+The keys of the dict must match the dense_keys of the feature.
+END
+  }
+  attr {
+    name: "sparse_keys"
+    description: <<END
+A list of string keys in the examples features.
+The results for these keys will be returned as `SparseTensor` objects.
+END
+  }
+  attr {
+    name: "dense_keys"
+    description: <<END
+A list of Ndense string Tensors (scalars).
+The keys expected in the Examples features associated with dense values.
+END
+  }
+  attr {
+    name: "sparse_types"
+    description: <<END
+A list of `DTypes` of the same length as `sparse_keys`.
+Only `tf.float32` (`FloatList`), `tf.int64` (`Int64List`),
+and `tf.string` (`BytesList`) are supported.
+END
+  }
+    attr {
+    name: "Tdense"
+    description: <<END
+A list of DTypes of the same length as `dense_keys`.
+Only `tf.float32` (`FloatList`), `tf.int64` (`Int64List`),
+and `tf.string` (`BytesList`) are supported.
+
+END
+  }
+  attr {
+    name: "dense_shapes"
+    description: <<END
+List of tuples with the same length as `dense_keys`.
+The shape of the data for each dense feature referenced by `dense_keys`.
+Required for any input tensors identified by `dense_keys`.  Must be
+either fully defined, or may contain an unknown first dimension.
+An unknown first dimension means the feature is treated as having
+a variable number of blocks, and the output shape along this dimension
+is considered unknown at graph build time.  Padding is applied for
+minibatch elements smaller than the maximum number of blocks for the
+given feature along this dimension.
+END
+  }
+    attr {
+    name: "output_types"
+    description: <<END
+The type list for the return values.
+END
+  }
+    attr {
+    name: "output_shapes"
+    description: <<END
+The list of shapes being produced.
+END
+  }
+   summary: "Transforms `input_dataset` containing `Example` protos as vectors of DT_STRING into a dataset of `Tensor` or `SparseTensor` objects representing the parsed features."
+}
+
diff --git a/tensorflow/core/api_def/python_api/api_def_ParseExampleDataset.pbtxt b/tensorflow/core/api_def/python_api/api_def_ParseExampleDataset.pbtxt
new file mode 100644
index 0000000000..45826b6fdc
--- /dev/null
+++ b/tensorflow/core/api_def/python_api/api_def_ParseExampleDataset.pbtxt
@@ -0,0 +1,4 @@
+op {
+  graph_op_name: "ParseExampleDataset"
+  visibility: HIDDEN
+}