Merge branch 'master' into callback-param-bug-fix

Author: icywang86rui

src/sagemaker/inputs.py

@@ -70,6 +70,8 @@ def __init__(
                         a local directory.
                     * 'Pipe' - Amazon SageMaker streams data directly from S3 to the container via
                         a Unix-named pipe.
+                    * 'FastFile' - Amazon SageMaker streams data from S3 on demand instead of
+                        downloading the entire dataset before training begins.
 
             attribute_names (list[str]): A list of one or more attribute names to use that are
                 found in a specified AugmentedManifestFile.

src/sagemaker/session.py

@@ -467,6 +467,8 @@ def train(  # noqa: C901
                 a directory in the Docker container.
                 * 'Pipe' - Amazon SageMaker streams data directly from S3 to the container via a
                 Unix-named pipe.
+                * 'FastFile' - Amazon SageMaker streams data from S3 on demand instead of
+                downloading the entire dataset before training begins.
             input_config (list): A list of Channel objects. Each channel is a named input source.
                 Please refer to the format details described:
                 https://botocore.readthedocs.io/en/latest/reference/services/sagemaker.html#SageMaker.Client.create_training_job
@@ -609,6 +611,8 @@ def _get_train_request(  # noqa: C901
                 a directory in the Docker container.
                 * 'Pipe' - Amazon SageMaker streams data directly from S3 to the container via a
                 Unix-named pipe.
+                * 'FastFile' - Amazon SageMaker streams data from S3 on demand instead of
+                downloading the entire dataset before training begins.
             input_config (list): A list of Channel objects. Each channel is a named input source.
                 Please refer to the format details described:
                 https://botocore.readthedocs.io/en/latest/reference/services/sagemaker.html#SageMaker.Client.create_training_job
@@ -1897,6 +1901,8 @@ def tune(  # noqa: C901
                 a directory in the Docker container.
                 * 'Pipe' - Amazon SageMaker streams data directly from S3 to the container via a
                 Unix-named pipe.
+                * 'FastFile' - Amazon SageMaker streams data from S3 on demand instead of
+                downloading the entire dataset before training begins.
             metric_definitions (list[dict]): A list of dictionaries that defines the metric(s)
                 used to evaluate the training jobs. Each dictionary contains two keys: 'Name' for
                 the name of the metric, and 'Regex' for the regular expression used to extract the
@@ -2180,6 +2186,8 @@ def _map_training_config(
                     a directory in the Docker container.
                 * 'Pipe' - Amazon SageMaker streams data directly from S3 to the container via a
                     Unix-named pipe.
+                * 'FastFile' - Amazon SageMaker streams data from S3 on demand instead of
+                    downloading the entire dataset before training begins.
             role (str): An AWS IAM role (either name or full ARN). The Amazon SageMaker training
                 jobs and APIs that create Amazon SageMaker endpoints use this role to access
                 training data and model artifacts. You must grant sufficient permissions to

src/sagemaker/workflow/steps.py

@@ -16,16 +16,12 @@
 import abc
 
 from enum import Enum
-from typing import Dict, List
+from typing import Dict, List, Union
 
 import attr
 
 from sagemaker.estimator import EstimatorBase, _TrainingJob
-from sagemaker.inputs import (
-    CreateModelInput,
-    TrainingInput,
-    TransformInput,
-)
+from sagemaker.inputs import CreateModelInput, TrainingInput, TransformInput, FileSystemInput
 from sagemaker.model import Model
 from sagemaker.processing import (
     ProcessingInput,
@@ -145,7 +141,7 @@ def __init__(
         self,
         name: str,
         estimator: EstimatorBase,
-        inputs: TrainingInput = None,
+        inputs: Union[TrainingInput, dict, str, FileSystemInput] = None,
         cache_config: CacheConfig = None,
         depends_on: List[str] = None,
     ):
@@ -157,7 +153,23 @@ def __init__(
         Args:
             name (str): The name of the training step.
             estimator (EstimatorBase): A `sagemaker.estimator.EstimatorBase` instance.
-            inputs (TrainingInput): A `sagemaker.inputs.TrainingInput` instance. Defaults to `None`.
+            inputs (str or dict or sagemaker.inputs.TrainingInput
+                or sagemaker.inputs.FileSystemInput): Information
+                about the training data. This can be one of three types:
+
+                * (str) the S3 location where training data is saved, or a file:// path in
+                    local mode.
+                * (dict[str, str] or dict[str, sagemaker.inputs.TrainingInput]) If using multiple
+                    channels for training data, you can specify a dict mapping channel names to
+                    strings or :func:`~sagemaker.inputs.TrainingInput` objects.
+                * (sagemaker.inputs.TrainingInput) - channel configuration for S3 data sources
+                    that can provide additional information as well as the path to the training
+                    dataset.
+                    See :func:`sagemaker.inputs.TrainingInput` for full details.
+                * (sagemaker.inputs.FileSystemInput) - channel configuration for
+                    a file system data source that can provide additional information as well as
+                    the path to the training dataset.
+
             cache_config (CacheConfig):  A `sagemaker.workflow.steps.CacheConfig` instance.
             depends_on (List[str]): A list of step names this `sagemaker.workflow.steps.TrainingStep`
                 depends on