Examples

There are three scenarios:

• Releasing a dataset version
• Releasing a labeling job version
• Releasing a version based on the output of the labeling phase

from modelarts import workflow as wf
# Use ReleaseDatasetStep to release a version of the input dataset and output the dataset with version information.

# Define the dataset.
dataset = wf.data.DatasetPlaceholder(name="input_dataset")

# Define the split ratio between the training set and validation set
train_ration = wf.Placeholder(name="placeholder_name", placeholder_type=wf.PlaceholderType.STR, default="0.8")

release_version = wf.steps.ReleaseDatasetStep(
    name="release_dataset", # Name of the dataset release phase. The name contains a maximum of 64 characters, including only letters, digits, underscores (_), and hyphens (-). It must start with a letter and must be unique in a workflow.
    title="Dataset version release", # Title, which defaults to the value of name
    inputs=wf.steps.ReleaseDatasetInput(name="input_name", data=dataset), # ReleaseDatasetStep inputs. The dataset object is configured when the workflow is running. You can also use wf.data.Dataset(dataset_name="dataset_name") for the data field.
    outputs=wf.steps.ReleaseDatasetOutput(
        name="output_name", 
        dataset_version_config=wf.data.DatasetVersionConfig(
            label_task_type=wf.data.LabelTaskTypeEnum.IMAGE_CLASSIFICATION,  # Labeling job type for dataset version release
            train_evaluate_sample_ratio=train_ration # Split ratio between the training set and validation set
            )
    ) # ReleaseDatasetStep outputs
)

workflow = wf.Workflow(
    name="dataset-release-demo",
    desc="this is a demo workflow",
    steps=[release_version]
)

from modelarts import workflow as wf
# Use ReleaseDatasetStep to release a version of the input labeling job and output the dataset with version information.

# Define the labeling job.
label_task = wf.data.LabelTaskPlaceholder(name="label_task_placeholder_name")

# Define the split ratio between the training set and validation set
train_ration = wf.Placeholder(name="placeholder_name", placeholder_type=wf.PlaceholderType.STR, default="0.8")

release_version = wf.steps.ReleaseDatasetStep(
    name="release_dataset", # Name of the dataset release phase. The name contains a maximum of 64 characters, including only letters, digits, underscores (_), and hyphens (-). It must start with a letter and must be unique in a workflow.
    title="Dataset version release", # Title, which defaults to the value of name
    inputs=wf.steps.ReleaseDatasetInput(name="input_name", data=label_task), # ReleaseDatasetStep inputs
The labeling job object is configured when the workflow is running. You can also use wf.data.LabelTask(dataset_name="dataset_name", task_name="label_task_name") for the data field.
    outputs=wf.steps.ReleaseDatasetOutput(name="output_name", dataset_version_config=wf.data.DatasetVersionConfig(train_evaluate_sample_ratio=train_ration)), # Split ratio between the training set and validation set
)

workflow = wf.Workflow(
    name="dataset-release-demo",
    desc="this is a demo workflow",
    steps=[release_version]
)

from modelarts import workflow as wf
# Use ReleaseDatasetStep to release a version of the input labeling job and output the dataset with version information.

# Define the split ratio between the training set and validation set
train_ration = wf.Placeholder(name="placeholder_name", placeholder_type=wf.PlaceholderType.STR, default="0.8")

release_version = wf.steps.ReleaseDatasetStep(
    name="release_dataset", # Name of the dataset release phase. The name contains a maximum of 64 characters, including only letters, digits, underscores (_), and hyphens (-). It must start with a letter and must be unique in a workflow.
    title="Dataset version release", # Title, which defaults to the value of name
    inputs=wf.steps.ReleaseDatasetInput(name="input_name", data=labeling_step.outputs["output_name"].as_input()), # ReleaseDatasetStep inputs
The labeling job object is configured when the workflow is running. You can also use wf.data.LabelTask(dataset_name="dataset_name", task_name="label_task_name") for the data field.
    outputs=wf.steps.ReleaseDatasetOutput(name="output_name", dataset_version_config=wf.data.DatasetVersionConfig(train_evaluate_sample_ratio=train_ration)), # Split ratio between the training set and validation set
    depend_steps = [labeling_step] # Preceding labeling phase
)
# labeling_step is an instance object of wf.steps.LabelingStep and output_name is the value of the name field of wf.steps.LabelingOutput.

workflow = wf.Workflow(
    name="dataset-release-demo",
    desc="this is a demo workflow",
    steps=[release_version]
)