/AWS1/CL_SGMRECOMMENDATIONJO02¶
Specifies mandatory fields for running an Inference Recommender job directly in the CreateInferenceRecommendationsJob API. The fields specified in ContainerConfig override the corresponding fields in the model package. Use ContainerConfig if you want to specify these fields for the recommendation job but don't want to edit them in your model package.
CONSTRUCTOR¶
IMPORTING¶
Optional arguments:¶
iv_domain TYPE /AWS1/SGMSTRING /AWS1/SGMSTRING¶
The machine learning domain of the model and its components.
Valid Values:
COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING
iv_task TYPE /AWS1/SGMSTRING /AWS1/SGMSTRING¶
The machine learning task that the model accomplishes.
Valid Values:
IMAGE_CLASSIFICATION | OBJECT_DETECTION | TEXT_GENERATION | IMAGE_SEGMENTATION | FILL_MASK | CLASSIFICATION | REGRESSION | OTHER
iv_framework TYPE /AWS1/SGMSTRING /AWS1/SGMSTRING¶
The machine learning framework of the container image.
Valid Values:
TENSORFLOW | PYTORCH | XGBOOST | SAGEMAKER-SCIKIT-LEARN
iv_frameworkversion TYPE /AWS1/SGMRECOMMENDATIONJOBFR00 /AWS1/SGMRECOMMENDATIONJOBFR00¶
The framework version of the container image.
io_payloadconfig TYPE REF TO /AWS1/CL_SGMRECOMMENDATIONJO03 /AWS1/CL_SGMRECOMMENDATIONJO03¶
Specifies the
SamplePayloadUrland all other sample payload-related fields.
iv_nearestmodelname TYPE /AWS1/SGMSTRING /AWS1/SGMSTRING¶
The name of a pre-trained machine learning model benchmarked by Amazon SageMaker Inference Recommender that matches your model.
Valid Values:
efficientnetb7 | unet | xgboost | faster-rcnn-resnet101 | nasnetlarge | vgg16 | inception-v3 | mask-rcnn | sagemaker-scikit-learn | densenet201-gluon | resnet18v2-gluon | xception | densenet201 | yolov4 | resnet152 | bert-base-cased | xceptionV1-keras | resnet50 | retinanet
it_supportedinstancetypes TYPE /AWS1/CL_SGMRECOMMENDATIONJO05=>TT_RECOMMENDATIONJOBSUPPEDIN00 TT_RECOMMENDATIONJOBSUPPEDIN00¶
A list of the instance types that are used to generate inferences in real-time.
iv_supportedendpointtype TYPE /AWS1/SGMRECOMMENDATIONJOBSU00 /AWS1/SGMRECOMMENDATIONJOBSU00¶
The endpoint type to receive recommendations for. By default this is null, and the results of the inference recommendation job return a combined list of both real-time and serverless benchmarks. By specifying a value for this field, you can receive a longer list of benchmarks for the desired endpoint type.
iv_datainputconfig TYPE /AWS1/SGMRECOMMENDATIONJOBDA00 /AWS1/SGMRECOMMENDATIONJOBDA00¶
Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. This field is used for optimizing your model using SageMaker Neo. For more information, see DataInputConfig.
it_supportedrspmimetypes TYPE /AWS1/CL_SGMRECOMMENDATIONJO13=>TT_RECOMMENDATIONJOBSUPPEDRS00 TT_RECOMMENDATIONJOBSUPPEDRS00¶
The supported MIME types for the output data.
Queryable Attributes¶
Domain¶
The machine learning domain of the model and its components.
Valid Values:
COMPUTER_VISION | NATURAL_LANGUAGE_PROCESSING | MACHINE_LEARNING
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_DOMAIN() |
Getter for DOMAIN, with configurable default |
ASK_DOMAIN() |
Getter for DOMAIN w/ exceptions if field has no value |
HAS_DOMAIN() |
Determine if DOMAIN has a value |
Task¶
The machine learning task that the model accomplishes.
Valid Values:
IMAGE_CLASSIFICATION | OBJECT_DETECTION | TEXT_GENERATION | IMAGE_SEGMENTATION | FILL_MASK | CLASSIFICATION | REGRESSION | OTHER
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_TASK() |
Getter for TASK, with configurable default |
ASK_TASK() |
Getter for TASK w/ exceptions if field has no value |
HAS_TASK() |
Determine if TASK has a value |
Framework¶
The machine learning framework of the container image.
Valid Values:
TENSORFLOW | PYTORCH | XGBOOST | SAGEMAKER-SCIKIT-LEARN
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_FRAMEWORK() |
Getter for FRAMEWORK, with configurable default |
ASK_FRAMEWORK() |
Getter for FRAMEWORK w/ exceptions if field has no value |
HAS_FRAMEWORK() |
Determine if FRAMEWORK has a value |
FrameworkVersion¶
The framework version of the container image.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_FRAMEWORKVERSION() |
Getter for FRAMEWORKVERSION, with configurable default |
ASK_FRAMEWORKVERSION() |
Getter for FRAMEWORKVERSION w/ exceptions if field has no va |
HAS_FRAMEWORKVERSION() |
Determine if FRAMEWORKVERSION has a value |
PayloadConfig¶
Specifies the
SamplePayloadUrland all other sample payload-related fields.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_PAYLOADCONFIG() |
Getter for PAYLOADCONFIG |
NearestModelName¶
The name of a pre-trained machine learning model benchmarked by Amazon SageMaker Inference Recommender that matches your model.
Valid Values:
efficientnetb7 | unet | xgboost | faster-rcnn-resnet101 | nasnetlarge | vgg16 | inception-v3 | mask-rcnn | sagemaker-scikit-learn | densenet201-gluon | resnet18v2-gluon | xception | densenet201 | yolov4 | resnet152 | bert-base-cased | xceptionV1-keras | resnet50 | retinanet
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_NEARESTMODELNAME() |
Getter for NEARESTMODELNAME, with configurable default |
ASK_NEARESTMODELNAME() |
Getter for NEARESTMODELNAME w/ exceptions if field has no va |
HAS_NEARESTMODELNAME() |
Determine if NEARESTMODELNAME has a value |
SupportedInstanceTypes¶
A list of the instance types that are used to generate inferences in real-time.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_SUPPORTEDINSTANCETYPES() |
Getter for SUPPORTEDINSTANCETYPES, with configurable default |
ASK_SUPPORTEDINSTANCETYPES() |
Getter for SUPPORTEDINSTANCETYPES w/ exceptions if field has |
HAS_SUPPORTEDINSTANCETYPES() |
Determine if SUPPORTEDINSTANCETYPES has a value |
SupportedEndpointType¶
The endpoint type to receive recommendations for. By default this is null, and the results of the inference recommendation job return a combined list of both real-time and serverless benchmarks. By specifying a value for this field, you can receive a longer list of benchmarks for the desired endpoint type.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_SUPPORTEDENDPOINTTYPE() |
Getter for SUPPORTEDENDPOINTTYPE, with configurable default |
ASK_SUPPORTEDENDPOINTTYPE() |
Getter for SUPPORTEDENDPOINTTYPE w/ exceptions if field has |
HAS_SUPPORTEDENDPOINTTYPE() |
Determine if SUPPORTEDENDPOINTTYPE has a value |
DataInputConfig¶
Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. This field is used for optimizing your model using SageMaker Neo. For more information, see DataInputConfig.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_DATAINPUTCONFIG() |
Getter for DATAINPUTCONFIG, with configurable default |
ASK_DATAINPUTCONFIG() |
Getter for DATAINPUTCONFIG w/ exceptions if field has no val |
HAS_DATAINPUTCONFIG() |
Determine if DATAINPUTCONFIG has a value |
SupportedResponseMIMETypes¶
The supported MIME types for the output data.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_SUPPORTEDRSPMIMETYPES() |
Getter for SUPPORTEDRESPONSEMIMETYPES, with configurable def |
ASK_SUPPORTEDRSPMIMETYPES() |
Getter for SUPPORTEDRESPONSEMIMETYPES w/ exceptions if field |
HAS_SUPPORTEDRSPMIMETYPES() |
Determine if SUPPORTEDRESPONSEMIMETYPES has a value |