fix: Fix Pipeline variables related customer issues (#2959)

Co-authored-by: Dewen Qi <[email protected]>

Author: qidewenwhen

src/sagemaker/estimator.py

@@ -1879,7 +1879,9 @@ def _add_spot_checkpoint_args(cls, local_mode, estimator, train_args):
         if estimator.use_spot_instances:
             if local_mode:
                 raise ValueError("Spot training is not supported in local mode.")
-            train_args["use_spot_instances"] = True
+            # estimator.use_spot_instances may be a Pipeline ParameterBoolean object
+            # which is parsed during the Pipeline execution runtime
+            train_args["use_spot_instances"] = estimator.use_spot_instances
 
         if estimator.checkpoint_s3_uri:
             if local_mode:

src/sagemaker/model.py

@@ -37,6 +37,7 @@
 from sagemaker.utils import unique_name_from_base
 from sagemaker.async_inference import AsyncInferenceConfig
 from sagemaker.predictor_async import AsyncPredictor
+from sagemaker.workflow.entities import PipelineVariable
 
 LOGGER = logging.getLogger("sagemaker")
 
@@ -443,7 +444,7 @@ def _upload_code(self, key_prefix: str, repack: bool = False) -> None:
             )
 
         if repack and self.model_data is not None and self.entry_point is not None:
-            if isinstance(self.model_data, sagemaker.workflow.properties.Properties):
+            if isinstance(self.model_data, PipelineVariable):
                 # model is not yet there, defer repacking to later during pipeline execution
                 return
 

src/sagemaker/processing.py

@@ -36,7 +36,7 @@
 from sagemaker.session import Session
 from sagemaker.workflow.properties import Properties
 from sagemaker.workflow.parameters import Parameter
-from sagemaker.workflow.entities import Expression
+from sagemaker.workflow.entities import Expression, PipelineVariable
 from sagemaker.dataset_definition.inputs import S3Input, DatasetDefinition
 from sagemaker.apiutils._base_types import ApiObject
 from sagemaker.s3 import S3Uploader
@@ -233,6 +233,12 @@ def _normalize_args(
             kms_key (str): The ARN of the KMS key that is used to encrypt the
                 user code file (default: None).
         """
+        if code and isinstance(code, PipelineVariable):
+            raise ValueError(
+                "code argument has to be a valid S3 URI or local file path "
+                + "rather than a pipeline variable"
+            )
+
         self._current_job_name = self._generate_current_job_name(job_name=job_name)
 
         inputs_with_code = self._include_code_in_inputs(inputs, code, kms_key)

src/sagemaker/session.py

@@ -763,6 +763,8 @@ def _get_train_request(  # noqa: C901
             train_request["EnableInterContainerTrafficEncryption"] = encrypt_inter_container_traffic
 
         if use_spot_instances:
+            # estimator.use_spot_instances may be a Pipeline ParameterBoolean object
+            # which is parsed during the Pipeline execution runtime
             train_request["EnableManagedSpotTraining"] = use_spot_instances
 
         if checkpoint_s3_uri:
@@ -2340,13 +2342,17 @@ def _map_training_config(
             training_job_definition["VpcConfig"] = vpc_config
 
         if enable_network_isolation:
-            training_job_definition["EnableNetworkIsolation"] = True
+            training_job_definition["EnableNetworkIsolation"] = enable_network_isolation
 
         if encrypt_inter_container_traffic:
-            training_job_definition["EnableInterContainerTrafficEncryption"] = True
+            training_job_definition[
+                "EnableInterContainerTrafficEncryption"
+            ] = encrypt_inter_container_traffic
 
         if use_spot_instances:
-            training_job_definition["EnableManagedSpotTraining"] = True
+            # use_spot_instances may be a Pipeline ParameterBoolean object
+            # which is parsed during the Pipeline execution runtime
+            training_job_definition["EnableManagedSpotTraining"] = use_spot_instances
 
         if checkpoint_s3_uri:
             checkpoint_config = {"S3Uri": checkpoint_s3_uri}

src/sagemaker/tensorflow/model.py

@@ -21,6 +21,7 @@
 from sagemaker.deprecations import removed_kwargs
 from sagemaker.predictor import Predictor
 from sagemaker.serializers import JSONSerializer
+from sagemaker.workflow.entities import PipelineVariable
 
 
 class TensorFlowPredictor(Predictor):
@@ -330,7 +331,9 @@ def prepare_container_def(self, instance_type=None, accelerator_type=None):
         image_uri = self._get_image_uri(instance_type, accelerator_type)
         env = self._get_container_env()
 
-        if self.entry_point:
+        # If self.model_data is pipeline variable, model is not yet there.
+        # So defer repacking to later during pipeline execution
+        if self.entry_point and not isinstance(self.model_data, PipelineVariable):
             key_prefix = sagemaker.fw_utils.model_code_key_prefix(
                 self.key_prefix, self.name, image_uri
             )

src/sagemaker/tuner.py

@@ -39,9 +39,6 @@
     ParameterRange,
 )
 from sagemaker.workflow.entities import PipelineVariable
-from sagemaker.workflow.parameters import Parameter as PipelineParameter
-from sagemaker.workflow.functions import JsonGet as PipelineJsonGet
-from sagemaker.workflow.functions import Join as PipelineJoin
 
 from sagemaker.session import Session
 from sagemaker.utils import base_from_name, base_name_from_image, name_from_base
@@ -64,18 +61,6 @@
 logger = logging.getLogger(__name__)
 
 
-def is_pipeline_parameters(value):
-    """Determine if a value is a pipeline parameter or function representation
-
-    Args:
-        value (float or int): The value to be verified.
-
-    Returns:
-        bool: True if it is, False otherwise.
-    """
-    return isinstance(value, (PipelineParameter, PipelineJsonGet, PipelineJoin))
-
-
 class WarmStartTypes(Enum):
     """Warm Start Configuration type.
 

src/sagemaker/workflow/_repack_model.py

@@ -39,14 +39,14 @@ def repack(inference_script, model_archive, dependencies=None, source_dir=None):
 
     Args:
         inference_script (str): The path to the custom entry point.
-        model_archive (str): The name of the model TAR archive.
+        model_archive (str): The name or path (e.g. s3 uri) of the model TAR archive.
         dependencies (str): A space-delimited string of paths to custom dependencies.
         source_dir (str): The path to a custom source directory.
     """
 
     # the data directory contains a model archive generated by a previous training job
     data_directory = "/opt/ml/input/data/training"
-    model_path = os.path.join(data_directory, model_archive)
+    model_path = os.path.join(data_directory, model_archive.split("/")[-1])
 
     # create a temporary directory
     with tempfile.TemporaryDirectory() as tmp:

src/sagemaker/workflow/_utils.py

@@ -137,12 +137,6 @@ def __init__(
         self._model_data = model_data
         self.sagemaker_session = sagemaker_session
         self.role = role
-        if isinstance(model_data, Properties):
-            self._model_prefix = model_data
-            self._model_archive = "model.tar.gz"
-        else:
-            self._model_prefix = "/".join(self._model_data.split("/")[:-1])
-            self._model_archive = self._model_data.split("/")[-1]
         self._entry_point = entry_point
         self._entry_point_basename = os.path.basename(self._entry_point)
         self._source_dir = source_dir
@@ -164,7 +158,7 @@ def __init__(
             role=self.role,
             hyperparameters={
                 "inference_script": self._entry_point_basename,
-                "model_archive": self._model_archive,
+                "model_archive": self._model_data,
                 "dependencies": dependencies_hyperparameter,
                 "source_dir": self._source_dir,
             },
@@ -173,7 +167,7 @@ def __init__(
             **kwargs,
         )
         repacker.disable_profiler = True
-        inputs = TrainingInput(self._model_prefix)
+        inputs = TrainingInput(self._model_data)
 
         # super!
         super(_RepackModelStep, self).__init__(

src/sagemaker/workflow/airflow.py

@@ -184,7 +184,9 @@ def training_base_config(estimator, inputs=None, job_name=None, mini_batch_size=
         train_config["VpcConfig"] = job_config["vpc_config"]
 
     if estimator.use_spot_instances:
-        train_config["EnableManagedSpotTraining"] = True
+        # estimator.use_spot_instances may be a Pipeline ParameterBoolean object
+        # which is parsed during the Pipeline execution runtime
+        train_config["EnableManagedSpotTraining"] = estimator.use_spot_instances
 
     if estimator.hyperparameters() is not None:
         hyperparameters = {str(k): str(v) for (k, v) in estimator.hyperparameters().items()}

src/sagemaker/workflow/clarify_check_step.py

@@ -37,8 +37,8 @@
 from sagemaker.model_monitor.model_monitoring import _MODEL_MONITOR_S3_PATH
 from sagemaker.processing import ProcessingInput, ProcessingOutput, ProcessingJob
 from sagemaker.utils import name_from_base
-from sagemaker.workflow import PipelineNonPrimitiveInputTypes, ExecutionVariable, Parameter
-from sagemaker.workflow.entities import RequestType, Expression
+from sagemaker.workflow import PipelineNonPrimitiveInputTypes
+from sagemaker.workflow.entities import RequestType, PipelineVariable
 from sagemaker.workflow.properties import Properties
 from sagemaker.workflow.steps import Step, StepTypeEnum, CacheConfig
 from sagemaker.workflow.check_job_config import CheckJobConfig
@@ -194,17 +194,15 @@ def __init__(
             )
 
         if isinstance(
-            clarify_check_config.data_config.s3_analysis_config_output_path,
-            (ExecutionVariable, Expression, Parameter, Properties),
+            clarify_check_config.data_config.s3_analysis_config_output_path, PipelineVariable
         ):
             raise RuntimeError(
                 "s3_analysis_config_output_path cannot be of type "
                 + "ExecutionVariable/Expression/Parameter/Properties"
             )
 
         if not clarify_check_config.data_config.s3_analysis_config_output_path and isinstance(
-            clarify_check_config.data_config.s3_output_path,
-            (ExecutionVariable, Expression, Parameter, Properties),
+            clarify_check_config.data_config.s3_output_path, PipelineVariable
         ):
             raise RuntimeError(
                 "`s3_output_path` cannot be of type ExecutionVariable/Expression/Parameter"