View Source AWS.LookoutVision (aws-elixir v0.13.3)
This is the Amazon Lookout for Vision API Reference.
It provides descriptions of actions, data types, common parameters, and common errors.
Amazon Lookout for Vision enables you to find visual defects in industrial products, accurately and at scale. It uses computer vision to identify missing components in an industrial product, damage to vehicles or structures, irregularities in production lines, and even minuscule defects in silicon wafers — or any other physical item where quality is important such as a missing capacitor on printed circuit boards.
Link to this section Summary
Functions
Creates a new dataset in an Amazon Lookout for Vision project.
Creates a new version of a model within an an Amazon Lookout for Vision project.
Creates an empty Amazon Lookout for Vision project.
Deletes an existing Amazon Lookout for Vision dataset
.
Deletes an Amazon Lookout for Vision model.
Deletes an Amazon Lookout for Vision project.
Describe an Amazon Lookout for Vision dataset.
Describes a version of an Amazon Lookout for Vision model.
Describes an Amazon Lookout for Vision model packaging job.
Describes an Amazon Lookout for Vision project.
Detects anomalies in an image that you supply.
Lists the JSON Lines within a dataset.
Lists the model packaging jobs created for an Amazon Lookout for Vision project.
Lists the versions of a model in an Amazon Lookout for Vision project.
Lists the Amazon Lookout for Vision projects in your AWS account that are in the
AWS Region in which you call ListProjects
.
Returns a list of tags attached to the specified Amazon Lookout for Vision model.
Starts the running of the version of an Amazon Lookout for Vision model.
Starts an Amazon Lookout for Vision model packaging job.
Stops the hosting of a running model.
Adds one or more key-value tags to an Amazon Lookout for Vision model.
Removes one or more tags from an Amazon Lookout for Vision model.
Adds or updates one or more JSON Line entries in a dataset.
Link to this section Functions
Creates a new dataset in an Amazon Lookout for Vision project.
CreateDataset
can create a training or a test dataset from a valid dataset
source (DatasetSource
).
If you want a single dataset project, specify train
for the value of
DatasetType
.
To have a project with separate training and test datasets, call CreateDataset
twice. On the first call, specify train
for the value of DatasetType
. On the
second call, specify test
for the value of DatasetType
.
This operation requires permissions to perform the lookoutvision:CreateDataset
operation.
Creates a new version of a model within an an Amazon Lookout for Vision project.
CreateModel
is an asynchronous operation in which Amazon Lookout for Vision
trains, tests, and evaluates a new version of a model.
To get the current status, check the Status
field returned in the response
from DescribeModel
.
If the project has a single dataset, Amazon Lookout for Vision internally splits the dataset to create a training and a test dataset. If the project has a training and a test dataset, Lookout for Vision uses the respective datasets to train and test the model.
After training completes, the evaluation metrics are stored at the location
specified in OutputConfig
.
This operation requires permissions to perform the lookoutvision:CreateModel
operation. If you want to tag your model, you also require permission to the
lookoutvision:TagResource
operation.
Creates an empty Amazon Lookout for Vision project.
After you create the project, add a dataset by calling CreateDataset
.
This operation requires permissions to perform the lookoutvision:CreateProject
operation.
delete_dataset(client, dataset_type, project_name, input, options \\ [])
View SourceDeletes an existing Amazon Lookout for Vision dataset
.
If your the project has a single dataset, you must create a new dataset before you can create a model.
If you project has a training dataset and a test dataset consider the following.
If you delete the test dataset, your project reverts to a single dataset project. If you then train the model, Amazon Lookout for Vision internally splits the remaining dataset into a training and test dataset.
If you delete the training dataset, you must create a training dataset before you can create a model.
This operation requires permissions to perform the lookoutvision:DeleteDataset
operation.
delete_model(client, model_version, project_name, input, options \\ [])
View SourceDeletes an Amazon Lookout for Vision model.
You can't delete a running model. To stop a running model, use the StopModel
operation.
It might take a few seconds to delete a model. To determine if a model has been
deleted, call ListModels
and check if the version of the model
(ModelVersion
) is in the Models
array.
This operation requires permissions to perform the lookoutvision:DeleteModel
operation.
Deletes an Amazon Lookout for Vision project.
To delete a project, you must first delete each version of the model associated
with the project. To delete a model use the DeleteModel
operation.
You also have to delete the dataset(s) associated with the model. For more
information, see DeleteDataset
. The images referenced by the training and test
datasets aren't deleted.
This operation requires permissions to perform the lookoutvision:DeleteProject
operation.
describe_dataset(client, dataset_type, project_name, options \\ [])
View SourceDescribe an Amazon Lookout for Vision dataset.
This operation requires permissions to perform the
lookoutvision:DescribeDataset
operation.
describe_model(client, model_version, project_name, options \\ [])
View SourceDescribes a version of an Amazon Lookout for Vision model.
This operation requires permissions to perform the lookoutvision:DescribeModel
operation.
describe_model_packaging_job(client, job_name, project_name, options \\ [])
View SourceDescribes an Amazon Lookout for Vision model packaging job.
This operation requires permissions to perform the
lookoutvision:DescribeModelPackagingJob
operation.
For more information, see Using your Amazon Lookout for Vision model on an edge device in the Amazon Lookout for Vision Developer Guide.
Describes an Amazon Lookout for Vision project.
This operation requires permissions to perform the
lookoutvision:DescribeProject
operation.
detect_anomalies(client, model_version, project_name, input, options \\ [])
View SourceDetects anomalies in an image that you supply.
The response from DetectAnomalies
includes a boolean prediction that the image
contains one or more anomalies and a confidence value for the prediction. If the
model is an image segmentation model, the response also includes segmentation
information for each type of anomaly found in the image.
Before calling DetectAnomalies
, you must first start your model with the
StartModel
operation. You are charged for the amount of time, in minutes, that
a model runs and for the number of anomaly detection units that your model uses.
If you are not using a model, use the StopModel
operation to stop your model.
For more information, see Detecting anomalies in an image in the Amazon Lookout for Vision developer guide.
This operation requires permissions to perform the
lookoutvision:DetectAnomalies
operation.
list_dataset_entries(client, dataset_type, project_name, after_creation_date \\ nil, anomaly_class \\ nil, before_creation_date \\ nil, labeled \\ nil, max_results \\ nil, next_token \\ nil, source_ref_contains \\ nil, options \\ [])
View SourceLists the JSON Lines within a dataset.
An Amazon Lookout for Vision JSON Line contains the anomaly information for a single image, including the image location and the assigned label.
This operation requires permissions to perform the
lookoutvision:ListDatasetEntries
operation.
list_model_packaging_jobs(client, project_name, max_results \\ nil, next_token \\ nil, options \\ [])
View SourceLists the model packaging jobs created for an Amazon Lookout for Vision project.
This operation requires permissions to perform the
lookoutvision:ListModelPackagingJobs
operation.
For more information, see Using your Amazon Lookout for Vision model on an edge device in the Amazon Lookout for Vision Developer Guide.
list_models(client, project_name, max_results \\ nil, next_token \\ nil, options \\ [])
View SourceLists the versions of a model in an Amazon Lookout for Vision project.
The ListModels
operation is eventually consistent. Recent calls to
CreateModel
might take a while to appear in the response from ListProjects
.
This operation requires permissions to perform the lookoutvision:ListModels
operation.
list_projects(client, max_results \\ nil, next_token \\ nil, options \\ [])
View SourceLists the Amazon Lookout for Vision projects in your AWS account that are in the
AWS Region in which you call ListProjects
.
The ListProjects
operation is eventually consistent. Recent calls to
CreateProject
and DeleteProject
might take a while to appear in the response
from ListProjects
.
This operation requires permissions to perform the lookoutvision:ListProjects
operation.
Returns a list of tags attached to the specified Amazon Lookout for Vision model.
This operation requires permissions to perform the
lookoutvision:ListTagsForResource
operation.
start_model(client, model_version, project_name, input, options \\ [])
View SourceStarts the running of the version of an Amazon Lookout for Vision model.
Starting a model takes a while to complete. To check the current state of the
model, use DescribeModel
.
A model is ready to use when its status is HOSTED
.
Once the model is running, you can detect custom labels in new images by calling
DetectAnomalies
.
You are charged for the amount of time that the model is running. To stop a
running model, call StopModel
.
This operation requires permissions to perform the lookoutvision:StartModel
operation.
start_model_packaging_job(client, project_name, input, options \\ [])
View SourceStarts an Amazon Lookout for Vision model packaging job.
A model packaging job creates an AWS IoT Greengrass component for a Lookout for Vision model. You can use the component to deploy your model to an edge device managed by Greengrass.
Use the DescribeModelPackagingJob
API to determine the current status of the
job. The model packaging job is complete if the value of Status
is
SUCCEEDED
.
To deploy the component to the target device, use the component name and component version with the AWS IoT Greengrass CreateDeployment API.
This operation requires the following permissions:
lookoutvision:StartModelPackagingJob
s3:PutObject
s3:GetBucketLocation
kms:GenerateDataKey
greengrass:CreateComponentVersion
greengrass:DescribeComponent
(Optional)
greengrass:TagResource
. Only required if you want to tag the component.
For more information, see Using your Amazon Lookout for Vision model on an edge device in the Amazon Lookout for Vision Developer Guide.
stop_model(client, model_version, project_name, input, options \\ [])
View SourceStops the hosting of a running model.
The operation might take a while to complete. To check the current status, call
DescribeModel
.
After the model hosting stops, the Status
of the model is TRAINED
.
This operation requires permissions to perform the lookoutvision:StopModel
operation.
Adds one or more key-value tags to an Amazon Lookout for Vision model.
For more information, see Tagging a model in the Amazon Lookout for Vision Developer Guide.
This operation requires permissions to perform the lookoutvision:TagResource
operation.
Removes one or more tags from an Amazon Lookout for Vision model.
For more information, see Tagging a model in the Amazon Lookout for Vision Developer Guide.
This operation requires permissions to perform the lookoutvision:UntagResource
operation.
update_dataset_entries(client, dataset_type, project_name, input, options \\ [])
View SourceAdds or updates one or more JSON Line entries in a dataset.
A JSON Line includes information about an image used for training or testing an Amazon Lookout for Vision model.
To update an existing JSON Line, use the source-ref
field to identify the JSON
Line. The JSON line that you supply replaces the existing JSON line. Any
existing annotations that are not in the new JSON line are removed from the
dataset.
For more information, see Defining JSON lines for anomaly classification in the Amazon Lookout for Vision Developer Guide.
The images you reference in the source-ref
field of a JSON line, must be in
the same S3 bucket as the existing images in the dataset.
Updating a dataset might take a while to complete. To check the current status,
call DescribeDataset
and check the Status
field in the response.
This operation requires permissions to perform the
lookoutvision:UpdateDatasetEntries
operation.