Merge branch 'zwei' into xgboost-uri

Author: laurenyu

src/sagemaker/chainer/estimator.py

@@ -214,7 +214,7 @@ def create_model(
         return ChainerModel(
             self.model_data,
             role or self.role,
-            entry_point or self.entry_point,
+            entry_point or self._model_entry_point(),
             source_dir=(source_dir or self._model_source_dir()),
             enable_cloudwatch_metrics=self.enable_cloudwatch_metrics,
             container_log_level=self.container_log_level,

src/sagemaker/estimator.py

@@ -1734,17 +1734,28 @@ def _stage_user_code_in_s3(self):
         )
 
     def _model_source_dir(self):
-        """Get the appropriate value to pass as source_dir to model constructor
-        on deploying
+        """Get the appropriate value to pass as ``source_dir`` to a model constructor.
 
         Returns:
-            str: Either a local or an S3 path pointing to the source_dir to be
-            used for code by the model to be deployed
+            str: Either a local or an S3 path pointing to the ``source_dir`` to be
+                used for code by the model to be deployed
         """
         return (
             self.source_dir if self.sagemaker_session.local_mode else self.uploaded_code.s3_prefix
         )
 
+    def _model_entry_point(self):
+        """Get the appropriate value to pass as ``entry_point`` to a model constructor.
+
+        Returns:
+            str: The path to the entry point script. This can be either an absolute path or
+                a path relative to ``self._model_source_dir()``.
+        """
+        if self.sagemaker_session.local_mode or (self._model_source_dir() is None):
+            return self.entry_point
+
+        return self.uploaded_code.script_name
+
     def hyperparameters(self):
         """Return the hyperparameters as a dictionary to use for training.
 

src/sagemaker/fw_utils.py

@@ -447,7 +447,7 @@ def tar_and_upload_dir(
             script name.
     """
     if directory and directory.lower().startswith("s3://"):
-        return UploadedCode(s3_prefix=directory, script_name=os.path.basename(script))
+        return UploadedCode(s3_prefix=directory, script_name=script)
 
     script_name = script if directory else os.path.basename(script)
     dependencies = dependencies or []

src/sagemaker/mxnet/estimator.py

@@ -218,10 +218,10 @@ def create_model(
 
         kwargs["name"] = self._get_or_create_name(kwargs.get("name"))
 
-        return MXNetModel(
+        model = MXNetModel(
             self.model_data,
             role or self.role,
-            entry_point or self.entry_point,
+            entry_point,
             framework_version=self.framework_version,
             py_version=self.py_version,
             source_dir=(source_dir or self._model_source_dir()),
@@ -235,6 +235,13 @@ def create_model(
             **kwargs
         )
 
+        if entry_point is None:
+            model.entry_point = (
+                self.entry_point if model._is_mms_version() else self._model_entry_point()
+            )
+
+        return model
+
     @classmethod
     def _prepare_init_params_from_job_description(cls, job_details, model_channel_name=None):
         """Convert the job description to init params that can be handled by the

src/sagemaker/pytorch/estimator.py

@@ -175,7 +175,7 @@ def create_model(
         return PyTorchModel(
             self.model_data,
             role or self.role,
-            entry_point or self.entry_point,
+            entry_point or self._model_entry_point(),
             framework_version=self.framework_version,
             py_version=self.py_version,
             source_dir=(source_dir or self._model_source_dir()),

src/sagemaker/rl/estimator.py

@@ -232,7 +232,7 @@ def create_model(
         if not entry_point and (source_dir or dependencies):
             raise AttributeError("Please provide an `entry_point`.")
 
-        entry_point = entry_point or self.entry_point
+        entry_point = entry_point or self._model_entry_point()
         source_dir = source_dir or self._model_source_dir()
         dependencies = dependencies or self.dependencies
 

src/sagemaker/sklearn/estimator.py

@@ -196,7 +196,7 @@ def create_model(
         return SKLearnModel(
             self.model_data,
             role,
-            entry_point or self.entry_point,
+            entry_point or self._model_entry_point(),
             source_dir=(source_dir or self._model_source_dir()),
             enable_cloudwatch_metrics=self.enable_cloudwatch_metrics,
             container_log_level=self.container_log_level,

src/sagemaker/xgboost/estimator.py

@@ -172,7 +172,7 @@ def create_model(
         return XGBoostModel(
             self.model_data,
             role,
-            entry_point or self.entry_point,
+            entry_point or self._model_entry_point(),
             framework_version=self.framework_version,
             source_dir=(source_dir or self._model_source_dir()),
             enable_cloudwatch_metrics=self.enable_cloudwatch_metrics,

tests/conftest.py

@@ -166,17 +166,18 @@ def xgboost_framework_version(xgboost_version):
     return xgboost_version
 
 
-@pytest.fixture(scope="module")
-def tf_version(tensorflow_training_version):
-    # TODO: remove this fixture and update tests
-    if tensorflow_training_version in ("1.13.1", "2.2", "2.2.0"):
-        pytest.skip("version isn't compatible with both training and inference.")
-    return tensorflow_training_version
+@pytest.fixture(scope="module", params=["py2", "py3"])
+def tensorflow_training_py_version(tensorflow_training_version, request):
+    return _tf_py_version(tensorflow_training_version, request)
 
 
 @pytest.fixture(scope="module", params=["py2", "py3"])
-def tf_py_version(tensorflow_training_version, request):
-    version = Version(tensorflow_training_version)
+def tensorflow_inference_py_version(tensorflow_inference_version, request):
+    return _tf_py_version(tensorflow_inference_version, request)
+
+
+def _tf_py_version(tf_version, request):
+    version = Version(tf_version)
     if version < Version("1.11"):
         return "py2"
     if version < Version("2.2"):
@@ -255,28 +256,18 @@ def sklearn_full_py_version():
 
 
 @pytest.fixture(scope="module")
-def tf_training_latest_version():
-    return "2.2.0"
-
-
-@pytest.fixture(scope="module")
-def tf_training_latest_py_version():
-    return "py37"
-
-
-@pytest.fixture(scope="module")
-def tf_serving_latest_version():
-    return "2.1.0"
-
-
-@pytest.fixture(scope="module")
-def tf_full_version(tf_training_latest_version, tf_serving_latest_version):
+def tf_full_version(tensorflow_training_latest_version, tensorflow_inference_latest_version):
     """Fixture for TF tests that test both training and inference.
 
     Fixture exists as such, since TF training and TFS have different latest versions.
     Otherwise, this would simply be a single latest version.
     """
-    return str(min(Version(tf_training_latest_version), Version(tf_serving_latest_version)))
+    return str(
+        min(
+            Version(tensorflow_training_latest_version),
+            Version(tensorflow_inference_latest_version),
+        )
+    )
 
 
 @pytest.fixture(scope="module")
@@ -294,11 +285,6 @@ def tf_full_py_version(tf_full_version):
     return "py37"
 
 
-@pytest.fixture(scope="module")
-def ei_tf_full_version():
-    return "2.0.0"
-
-
 @pytest.fixture(scope="module")
 def xgboost_full_version():
     return "1.0-1"

tests/data/mxnet_mnist/sourcedir.tar.gz

@@ -512,7 +512,10 @@ def test_sklearn_airflow_config_uploads_data_source_to_s3(
 
 @pytest.mark.canary_quick
 def test_tf_airflow_config_uploads_data_source_to_s3(
-    sagemaker_session, cpu_instance_type, tf_training_latest_version, tf_training_latest_py_version
+    sagemaker_session,
+    cpu_instance_type,
+    tensorflow_training_latest_version,
+    tensorflow_training_latest_py_version,
 ):
     with timeout(seconds=AIRFLOW_CONFIG_TIMEOUT_IN_SECONDS):
         tf = TensorFlow(
@@ -524,8 +527,8 @@ def test_tf_airflow_config_uploads_data_source_to_s3(
             instance_count=SINGLE_INSTANCE_COUNT,
             instance_type=cpu_instance_type,
             sagemaker_session=sagemaker_session,
-            framework_version=tf_training_latest_version,
-            py_version=tf_training_latest_py_version,
+            framework_version=tensorflow_training_latest_version,
+            py_version=tensorflow_training_latest_py_version,
             metric_definitions=[
                 {"Name": "train:global_steps", "Regex": r"global_step\/sec:\s(.*)"}
             ],

tests/integ/test_airflow_config.py

@@ -41,7 +41,7 @@
 
 
 def test_enabling_data_capture_on_endpoint_shows_correct_data_capture_status(
-    sagemaker_session, tf_serving_latest_version
+    sagemaker_session, tensorflow_inference_latest_version
 ):
     endpoint_name = unique_name_from_base("sagemaker-tensorflow-serving")
     model_data = sagemaker_session.upload_data(
@@ -52,7 +52,7 @@ def test_enabling_data_capture_on_endpoint_shows_correct_data_capture_status(
         model = TensorFlowModel(
             model_data=model_data,
             role=ROLE,
-            framework_version=tf_serving_latest_version,
+            framework_version=tensorflow_inference_latest_version,
             sagemaker_session=sagemaker_session,
         )
         predictor = model.deploy(
@@ -98,7 +98,7 @@ def test_enabling_data_capture_on_endpoint_shows_correct_data_capture_status(
 
 
 def test_disabling_data_capture_on_endpoint_shows_correct_data_capture_status(
-    sagemaker_session, tf_serving_latest_version
+    sagemaker_session, tensorflow_inference_latest_version
 ):
     endpoint_name = unique_name_from_base("sagemaker-tensorflow-serving")
     model_data = sagemaker_session.upload_data(
@@ -109,7 +109,7 @@ def test_disabling_data_capture_on_endpoint_shows_correct_data_capture_status(
         model = TensorFlowModel(
             model_data=model_data,
             role=ROLE,
-            framework_version=tf_serving_latest_version,
+            framework_version=tensorflow_inference_latest_version,
             sagemaker_session=sagemaker_session,
         )
         destination_s3_uri = os.path.join(
@@ -184,7 +184,7 @@ def test_disabling_data_capture_on_endpoint_shows_correct_data_capture_status(
 
 
 def test_updating_data_capture_on_endpoint_shows_correct_data_capture_status(
-    sagemaker_session, tf_serving_latest_version
+    sagemaker_session, tensorflow_inference_latest_version
 ):
     endpoint_name = sagemaker.utils.unique_name_from_base("sagemaker-tensorflow-serving")
     model_data = sagemaker_session.upload_data(
@@ -195,7 +195,7 @@ def test_updating_data_capture_on_endpoint_shows_correct_data_capture_status(
         model = TensorFlowModel(
             model_data=model_data,
             role=ROLE,
-            framework_version=tf_serving_latest_version,
+            framework_version=tensorflow_inference_latest_version,
             sagemaker_session=sagemaker_session,
         )
         destination_s3_uri = os.path.join(

tests/integ/test_data_capture_config.py

@@ -31,15 +31,15 @@
 @pytest.mark.canary_quick
 def test_hvd_cpu(
     sagemaker_session,
-    tf_training_latest_version,
-    tf_training_latest_py_version,
+    tensorflow_training_latest_version,
+    tensorflow_training_latest_py_version,
     cpu_instance_type,
     tmpdir,
 ):
     _create_and_fit_estimator(
         sagemaker_session,
-        tf_training_latest_version,
-        tf_training_latest_py_version,
+        tensorflow_training_latest_version,
+        tensorflow_training_latest_py_version,
         cpu_instance_type,
         tmpdir,
     )
@@ -50,12 +50,15 @@ def test_hvd_cpu(
     integ.test_region() in integ.TRAINING_NO_P2_REGIONS, reason="no ml.p2 instances in this region"
 )
 def test_hvd_gpu(
-    sagemaker_session, tf_training_latest_version, tf_training_latest_py_version, tmpdir
+    sagemaker_session,
+    tensorflow_training_latest_version,
+    tensorflow_training_latest_py_version,
+    tmpdir,
 ):
     _create_and_fit_estimator(
         sagemaker_session,
-        tf_training_latest_version,
-        tf_training_latest_py_version,
+        tensorflow_training_latest_version,
+        tensorflow_training_latest_py_version,
         "ml.p2.xlarge",
         tmpdir,
     )
@@ -65,8 +68,8 @@ def test_hvd_gpu(
 @pytest.mark.parametrize("instances, processes", [[1, 2], (2, 1), (2, 2)])
 def test_horovod_local_mode(
     sagemaker_local_session,
-    tf_training_latest_version,
-    tf_training_latest_py_version,
+    tensorflow_training_latest_version,
+    tensorflow_training_latest_py_version,
     instances,
     processes,
     tmpdir,
@@ -80,8 +83,8 @@ def test_horovod_local_mode(
         instance_type="local",
         sagemaker_session=sagemaker_local_session,
         output_path=output_path,
-        framework_version=tf_training_latest_version,
-        py_version=tf_training_latest_py_version,
+        framework_version=tensorflow_training_latest_version,
+        py_version=tensorflow_training_latest_py_version,
         distribution={"mpi": {"enabled": True, "processes_per_host": processes}},
     )
 

tests/integ/test_horovod.py

@@ -88,7 +88,7 @@
 
 
 @pytest.fixture(scope="module")
-def predictor(sagemaker_session, tf_serving_latest_version):
+def predictor(sagemaker_session, tensorflow_inference_latest_version):
     endpoint_name = unique_name_from_base("sagemaker-tensorflow-serving")
     model_data = sagemaker_session.upload_data(
         path=os.path.join(tests.integ.DATA_DIR, "tensorflow-serving-test-model.tar.gz"),
@@ -100,7 +100,7 @@ def predictor(sagemaker_session, tf_serving_latest_version):
         model = TensorFlowModel(
             model_data=model_data,
             role=ROLE,
-            framework_version=tf_serving_latest_version,
+            framework_version=tensorflow_inference_latest_version,
             sagemaker_session=sagemaker_session,
         )
         predictor = model.deploy(

tests/integ/test_model_monitor.py

@@ -32,11 +32,16 @@ def mxnet_training_job(
     sagemaker_session, mxnet_full_version, mxnet_full_py_version, cpu_instance_type
 ):
     with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
-        script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist.py")
+        s3_prefix = "integ-test-data/mxnet_mnist"
         data_path = os.path.join(DATA_DIR, "mxnet_mnist")
 
+        s3_source = sagemaker_session.upload_data(
+            path=os.path.join(data_path, "sourcedir.tar.gz"), key_prefix="{}/src".format(s3_prefix)
+        )
+
         mx = MXNet(
-            entry_point=script_path,
+            entry_point="mxnet_mnist/mnist.py",
+            source_dir=s3_source,
             role="SageMakerRole",
             framework_version=mxnet_full_version,
             py_version=mxnet_full_py_version,
@@ -46,10 +51,10 @@ def mxnet_training_job(
         )
 
         train_input = mx.sagemaker_session.upload_data(
-            path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
+            path=os.path.join(data_path, "train"), key_prefix="{}/train".format(s3_prefix)
         )
         test_input = mx.sagemaker_session.upload_data(
-            path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
+            path=os.path.join(data_path, "test"), key_prefix="{}/test".format(s3_prefix)
         )
 
         mx.fit({"train": train_input, "test": test_input})
@@ -62,7 +67,13 @@ def test_attach_deploy(mxnet_training_job, sagemaker_session, cpu_instance_type)
 
     with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
         estimator = MXNet.attach(mxnet_training_job, sagemaker_session=sagemaker_session)
-        predictor = estimator.deploy(1, cpu_instance_type, endpoint_name=endpoint_name)
+        predictor = estimator.deploy(
+            1,
+            cpu_instance_type,
+            entry_point="mnist.py",
+            source_dir=os.path.join(DATA_DIR, "mxnet_mnist"),
+            endpoint_name=endpoint_name,
+        )
         data = numpy.zeros(shape=(1, 1, 28, 28))
         result = predictor.predict(data)
         assert result is not None