otcextensions.sdk.modelartsv1.v1.model¶
The AS Configuration Class¶
The Config
class inherits from
Resource
.
- class otcextensions.sdk.modelartsv1.v1.model.Model(_synchronized=False, connection=None, **attrs)¶
The base resource
- Parameters:
_synchronized (bool) – This is not intended to be used directly. See
new()
andexisting()
.connection (openstack.connection.Connection) – Reference to the Connection being used. Defaults to None to allow Resource objects to be used without an active Connection, such as in unit tests. Use of
self._connection
in Resource code should protect itself with a check for None.
- base_path: str = '/models'¶
The base part of the URI for this resource.
- resources_key: ty.Optional[str] = 'models'¶
Plural form of key for resource.
- allow_create = True¶
Allow create operation for this resource.
- allow_list = True¶
Allow list operation for this resource.
- allow_delete = True¶
Allow delete operation for this resource.
- allow_fetch = True¶
Allow get operation for this resource.
- ai_project¶
AI project.
- apis¶
All input and output apis parameter information of a model, which is obtained from the model preview.
- config¶
Model configurations.
- created_at¶
Time when a model is created, in milliseconds calculated from 1970.
- dependencies¶
Package required for inference code and model.
- description¶
Model description.
- execution_code¶
OBS path for storing the execution code. The name of the execution code file is fixed to customize_service.py.
- health¶
Model health check interface information.
- initial_config¶
Character string converted from the final model configuration file.
- image_address¶
image path generated after model packaging.
- input_params¶
Collection of input parameters of a model.
- install_type¶
Supported service type for deployment.
- is_publishable¶
Whether a model can be published to the marketplace.
- is_subscribed¶
Whether a model is subscribed from the marketplace.
- is_tunable¶
Whether a model can be tuned.
- labels_map¶
Model label map.
- model_algorithm¶
Model algorithm type. The value can be predict_analysis, object_detection, or image_classification.
- model_docs¶
List of model description documents.
- model_id¶
Model ID.
- model_labels¶
Model label array.
- model_metrics¶
Model precision, which is read from the configuration file.
- model_name¶
Model name.
- model_size¶
Model size, in bytes.
- model_source¶
Model source.
- model_status¶
Model status.
- model_type¶
Model type. The value can be TensorFlow, MXNet, Spark_MLlib, Scikit_Learn, XGBoost, Image, or PyTorch.
- model_version¶
Model version.
- name: ty.Union[Body, URI]¶
Model name.
- output_params¶
Collection of output parameters of a model.
- owner_id¶
User to which a model belongs.
- project_id¶
Project to which a model belongs.
- runtime¶
Model runtime environment.
- schema_doc¶
Download address of the model schema file.
- source_job_id¶
ID of the source training job.
- source_job_version¶
Version of the source training job.
- source_location¶
OBS path where the model is located or the SWR image location.
- source_type¶
Model source type. If a model is deployed through ExeML, the value is auto. If a model is deployed through a training job or an OBS model file, this parameter is left blank.
- specification¶
Minimum model deployment specifications.
- template¶
Template configuration items.
- status¶
Model status.
- tenant_id¶
Tenant to which a model belongs.
- version¶
Model version.
- workspace_id¶
ID of the workspace to which a service belongs.