feature: Data Serializer

src/sagemaker/serializers.py

@@ -18,7 +18,7 @@
 import csv
 import io
 import json
-
+import os
 import numpy as np
 from six import with_metaclass
 
@@ -357,3 +357,35 @@ def serialize(self, data):
             return data.read()
 
         raise ValueError("Unable to handle input format: %s" % type(data))
+
+
+class DataSerializer(SimpleBaseSerializer):
+    """Serialize data in any file by extracting raw bytes from the file."""
+
+    def __init__(self, content_type="file-path/raw-bytes"):
+        """Initialize a ``DataSerializer`` instance.
+
+        Args:
+            content_type (str): The MIME type to signal to the inference endpoint when sending
+                request data (default: "file-path/raw-bytes").
+        """
+        super(DataSerializer, self).__init__(content_type=content_type)
+
+    def serialize(self, data):
+        """Serialize file of various formats to a raw bytes.
+
+        Args:
+            data (object): Data to be serialized. The data can be a string,
+                representing file-path or the raw bytes from a file.
+        Returns:
+            raw-bytes: The data serialized as a raw-bytes from the input.
+        """
+        if isinstance(data, str):
+            if not os.path.exists(data):
+                raise ValueError(f"{data} is not a valid file path.")
+            image = open(data, "rb")
+            return image.read()
+        if isinstance(data, bytes):
+            return data
+
+        raise ValueError(f"Object of type {type(data)} is not Data serializable.")

tests/unit/sagemaker/test_serializers.py

@@ -28,6 +28,7 @@
     SparseMatrixSerializer,
     JSONLinesSerializer,
     LibSVMSerializer,
+    DataSerializer,
 )
 from tests.unit import DATA_DIR
 
@@ -331,3 +332,26 @@ def test_libsvm_serializer_file_like(libsvm_serializer):
         libsvm_file.seek(0)
         result = libsvm_serializer.serialize(libsvm_file)
         assert result == validation_data
+
+
+@pytest.fixture
+def data_serializer():
+    return DataSerializer()
+
+
+def test_data_serializer_raw(data_serializer):
+    input_image_file_path = os.path.join(DATA_DIR, "", "cuteCat.jpg")
+    with open(input_image_file_path, "rb") as image:
+        input_image = image.read()
+    input_image_data = data_serializer.serialize(input_image)
+    validation_image_file_path = os.path.join(DATA_DIR, "", "cuteCat.raw")
+    validation_image_data = open(validation_image_file_path, "rb").read()
+    assert input_image_data == validation_image_data
+
+
+def test_data_serializer_file_like(data_serializer):
+    input_image_file_path = os.path.join(DATA_DIR, "", "cuteCat.jpg")
+    validation_image_file_path = os.path.join(DATA_DIR, "", "cuteCat.raw")
+    input_image_data = data_serializer.serialize(input_image_file_path)
+    validation_image_data = open(validation_image_file_path, "rb").read()
+    assert input_image_data == validation_image_data