feature: TensorFlow 2.4 for Neo

doc/doc_utils/jumpstart_doc_utils.py

@@ -78,7 +78,7 @@ def create_jumpstart_model_table():
     file_content.append("     - Latest Version\n")
     file_content.append("     - Min SDK Version\n")
 
-    for model in sorted(sdk_manifest, key=lambda elt: elt["model_id"]):
+    for model in sdk_manifest_top_versions_for_models.values():
         model_spec = get_jumpstart_sdk_spec(model["spec_key"])
         file_content.append("   * - {}\n".format(model["model_id"]))
         file_content.append("     - {}\n".format(model_spec["training_supported"]))

src/sagemaker/image_uri_config/neo-tensorflow.json

@@ -12,7 +12,8 @@
         "1.11.0": "1.15.3",
         "1.12.0": "1.15.3",
         "1.13.0": "1.15.3",
-        "1.14.0": "1.15.3"
+        "1.14.0": "1.15.3",
+        "2.4.2": "2.4.2"
     },
     "versions": {
         "1.15.3": {
@@ -44,6 +45,36 @@
                 "us-west-2": "301217895009"
             },
             "repository": "sagemaker-inference-tensorflow"
+        },
+        "2.4.2": {
+            "py_versions": ["py3"],
+            "registries": {
+                "af-south-1": "774647643957",
+                "ap-east-1": "110948597952",
+                "ap-northeast-1": "941853720454",
+                "ap-northeast-2": "151534178276",
+                "ap-northeast-3": "925152966179",
+                "ap-south-1": "763008648453",
+                "ap-southeast-1": "324986816169",
+                "ap-southeast-2": "355873309152",
+                "ca-central-1": "464438896020",
+                "cn-north-1": "472730292857",
+                "cn-northwest-1": "474822919863",
+                "eu-central-1": "746233611703",
+                "eu-north-1": "601324751636",
+                "eu-south-1": "966458181534",
+                "eu-west-1": "802834080501",
+                "eu-west-2": "205493899709",
+                "eu-west-3": "254080097072",
+                "me-south-1": "836785723513",
+                "sa-east-1": "756306329178",
+                "us-east-1": "785573368785",
+                "us-east-2": "007439368137",
+                "us-gov-west-1": "263933020539",
+                "us-west-1": "710691900526",
+                "us-west-2": "301217895009"
+            },
+            "repository": "sagemaker-inference-tensorflow"
         }
     }
 }

src/sagemaker/serializers.py

@@ -18,7 +18,6 @@
 import csv
 import io
 import json
-
 import numpy as np
 from six import with_metaclass
 
@@ -357,3 +356,38 @@ 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 data 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 raw-bytes from the input.
+        """
+        if isinstance(data, str):
+            try:
+                dataFile = open(data, "rb")
+                dataFileInfo = dataFile.read()
+                dataFile.close()
+                return dataFileInfo
+            except Exception as e:
+                raise ValueError(f"Could not open/read file: {data}. {e}")
+        if isinstance(data, bytes):
+            return data
+
+        raise ValueError(f"Object of type {type(data)} is not Data serializable.")

tests/scripts/run-notebook-test.sh

@@ -81,8 +81,15 @@ echo "$LIFECYCLE_CONFIG_CONTENT"
 
 set -euo pipefail
 
+# git doesn't work in codepipeline, use CODEBUILD_RESOLVED_SOURCE_VERSION to get commit id
+codebuild_initiator="${CODEBUILD_INITIATOR:-0}"
+if [ "${codebuild_initiator:0:12}" == "codepipeline" ]; then
+    COMMIT_ID="${CODEBUILD_RESOLVED_SOURCE_VERSION}"
+else
+    COMMIT_ID=$(git rev-parse --short HEAD)
+fi
+
 ACCOUNT_ID=$(aws sts get-caller-identity --query Account --output text)
-COMMIT_ID=$(git rev-parse --short HEAD)
 LIFECYCLE_CONFIG_NAME="install-python-sdk-$COMMIT_ID"
 
 python setup.py sdist

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