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.
x-logo: url: https://api.apis.guru/v2/cache/logo/https_twitter.com_awscloud_profile_image.png backgroundColor: "#FFFFFF" termsOfService: https://aws.amazon.com/service-terms/ contact: name: Mike Ralphson email: mike.ralphson@gmail.com url: https://github.com/mermade/aws2openapi x-twitter: PermittedSoc license: name: Apache 2.0 License url: http://www.apache.org/licenses/ x-providerName: amazonaws.com x-serviceName: lookoutvision x-aws-signingName: lookoutvision x-origin: - contentType: application/json url: https://raw.githubusercontent.com/aws/aws-sdk-js/master/apis/lookoutvision-2020-11-20.normal.json converter: url: https://github.com/mermade/aws2openapi version: 1.0.0 x-apisguru-driver: external x-apiClientRegistration: url: https://portal.aws.amazon.com/gp/aws/developer/registration/index.html?nc2=h_ct x-apisguru-categories: - cloud x-preferred: true externalDocs: description: Amazon Web Services documentation url: https://docs.aws.amazon.com/lookoutvision/ servers: - url: http://lookoutvision.{region}.amazonaws.com variables: region: description: The AWS region enum: - us-east-1 - us-east-2 - us-west-1 - us-west-2 - us-gov-west-1 - us-gov-east-1 - ca-central-1 - eu-north-1 - eu-west-1 - eu-west-2 - eu-west-3 - eu-central-1 - eu-south-1 - af-south-1 - ap-northeast-1 - ap-northeast-2 - ap-northeast-3 - ap-southeast-1 - ap-southeast-2 - ap-east-1 - ap-south-1 - sa-east-1 - me-south-1 default: us-east-1 description: The Amazon Lookout for Vision multi-region endpoint - url: https://lookoutvision.{region}.amazonaws.com variables: region: description: The AWS region enum: - us-east-1 - us-east-2 - us-west-1 - us-west-2 - us-gov-west-1 - us-gov-east-1 - ca-central-1 - eu-north-1 - eu-west-1 - eu-west-2 - eu-west-3 - eu-central-1 - eu-south-1 - af-south-1 - ap-northeast-1 - ap-northeast-2 - ap-northeast-3 - ap-southeast-1 - ap-southeast-2 - ap-east-1 - ap-south-1 - sa-east-1 - me-south-1 default: us-east-1 description: The Amazon Lookout for Vision multi-region endpoint - url: http://lookoutvision.{region}.amazonaws.com.cn variables: region: description: The AWS region enum: - cn-north-1 - cn-northwest-1 default: cn-north-1 description: The Amazon Lookout for Vision endpoint for China (Beijing) and China (Ningxia) - url: https://lookoutvision.{region}.amazonaws.com.cn variables: region: description: The AWS region enum: - cn-north-1 - cn-northwest-1 default: cn-north-1 description: The Amazon Lookout for Vision endpoint for China (Beijing) and China (Ningxia) x-hasEquivalentPaths: true paths: "/2020-11-20/projects/{projectName}/datasets": post: operationId: CreateDataset description: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.
ClientToken is an idempotency token that ensures a call to CreateDataset completes only once. You choose the value to pass. For example, An issue might prevent you
from getting a response from CreateDataset. In this case, safely retry your call to CreateDataset by using the same ClientToken parameter value.
If you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a network error from making multiple dataset
creation requests. You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are not the same as in the first request. Using a
different value for ClientToken is considered a new call to CreateDataset. An idempotency token is active for 8 hours.
train for a training dataset. Specify test for a test dataset.
type: string
pattern: train|test
minLength: 1
maxLength: 10
DatasetSource:
description: Information about the location of a manifest file that Amazon Lookout for Vision uses to to create a dataset.
type: object
properties:
GroundTruthManifest:
allOf:
- $ref: "#/components/schemas/DatasetGroundTruthManifest"
- description: Location information for the manifest file.
summary: Amazon Lookout for Vision Create Dataset
parameters:
- $ref: "#/components/parameters/X-Amz-Content-Sha256"
- $ref: "#/components/parameters/X-Amz-Date"
- $ref: "#/components/parameters/X-Amz-Algorithm"
- $ref: "#/components/parameters/X-Amz-Credential"
- $ref: "#/components/parameters/X-Amz-Security-Token"
- $ref: "#/components/parameters/X-Amz-Signature"
- $ref: "#/components/parameters/X-Amz-SignedHeaders"
"/2020-11-20/projects/{projectName}/models":
post:
operationId: CreateModel
description: 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.
ClientToken is an idempotency token that ensures a call to CreateModel completes only once. You choose the value to pass. For example, An issue might prevent you
from getting a response from CreateModel. In this case, safely retry your call to CreateModel by using the same ClientToken parameter value.
If
you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a network error from starting multiple training jobs.
You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are not the same as in the first request. Using a different value for
ClientToken is considered a new call to CreateModel. An idempotency token is active for 8 hours.
Lists 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.
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.
ClientToken is an idempotency token that ensures a call to CreateProject completes only once. You choose the value to pass. For example, An issue might prevent you
from getting a response from CreateProject. In this case, safely retry your call to CreateProject by using the same ClientToken parameter value.
If you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a network error from making multiple project
creation requests. You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are not the same as in the first request. Using a
different value for ClientToken is considered a new call to CreateProject. An idempotency token is active for 8 hours.
Lists 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.
Deletes 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.
train to delete the training dataset. Specify test to delete the test dataset. To delete the dataset in a
single dataset project, specify train.
schema:
type: string
pattern: train|test
minLength: 1
maxLength: 10
- name: X-Amzn-Client-Token
in: header
required: false
description: ClientToken is an idempotency token that ensures a call to DeleteDataset completes only once. You choose the value to pass. For example, An issue might prevent you
from getting a response from DeleteDataset. In this case, safely retry your call to DeleteDataset by using the same ClientToken parameter value.
If you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a network error from making multiple deletetion
requests. You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are not the same as in the first request. Using a different value
for ClientToken is considered a new call to DeleteDataset. An idempotency token is active for 8 hours.
Describe an Amazon Lookout for Vision dataset.
This operation requires permissions to perform the lookoutvision:DescribeDataset operation.
train to describe the training dataset. Specify test to describe the test dataset. If you have a single dataset
project, specify train "
schema:
type: string
pattern: train|test
minLength: 1
maxLength: 10
summary: Amazon Lookout for Vision Describe Dataset
"/2020-11-20/projects/{projectName}/models/{modelVersion}":
delete:
operationId: DeleteModel
description: Deletes 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.
ClientToken is an idempotency token that ensures a call to DeleteModel completes only once. You choose the value to pass. For example, an issue might prevent you
from getting a response from DeleteModel. In this case, safely retry your call to DeleteModel by using the same ClientToken parameter value.
If you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a network error from making multiple model deletion requests. You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are not the same as in the first request. Using a different value for
ClientToken is considered a new call to DeleteModel. An idempotency token is active for 8 hours.
Describes a version of an Amazon Lookout for Vision model.
This operation requires permissions to perform the lookoutvision:DescribeModel 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.
ClientToken is an idempotency token that ensures a call to DeleteProject completes only once. You choose the value to pass. For example, An issue might prevent you
from getting a response from DeleteProject. In this case, safely retry your call to DeleteProject by using the same ClientToken parameter value.
If you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a network error from making multiple project
deletion requests. You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are not the same as in the first request. Using a
different value for ClientToken is considered a new call to DeleteProject. An idempotency token is active for 8 hours.
Describes an Amazon Lookout for Vision project.
This operation requires permissions to perform the lookoutvision:DescribeProject operation.
Describes 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.
responses: "200": description: Success content: application/json: schema: $ref: "#/components/schemas/DescribeModelPackagingJobResponse" "480": description: AccessDeniedException content: application/json: schema: $ref: "#/components/schemas/AccessDeniedException" "481": description: InternalServerException content: application/json: schema: $ref: "#/components/schemas/InternalServerException" "482": description: ValidationException content: application/json: schema: $ref: "#/components/schemas/ValidationException" "483": description: ResourceNotFoundException content: application/json: schema: $ref: "#/components/schemas/ResourceNotFoundException" "484": description: ThrottlingException content: application/json: schema: $ref: "#/components/schemas/ThrottlingException" parameters: - name: projectName in: path required: true description: "The name of the project that contains the model packaging job that you want to describe. " schema: type: string pattern: "[a-zA-Z0-9][a-zA-Z0-9_\\-]*" minLength: 1 maxLength: 255 - name: jobName in: path required: true description: "The job name for the model packaging job. " schema: type: string pattern: "[a-zA-Z0-9-]+" minLength: 1 maxLength: 64 summary: Amazon Lookout for Vision Describe Model Packaging Job parameters: - $ref: "#/components/parameters/X-Amz-Content-Sha256" - $ref: "#/components/parameters/X-Amz-Date" - $ref: "#/components/parameters/X-Amz-Algorithm" - $ref: "#/components/parameters/X-Amz-Credential" - $ref: "#/components/parameters/X-Amz-Security-Token" - $ref: "#/components/parameters/X-Amz-Signature" - $ref: "#/components/parameters/X-Amz-SignedHeaders" "/2020-11-20/projects/{projectName}/models/{modelVersion}/detect#Content-Type": post: operationId: DetectAnomalies description:Detects 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.
Body. Valid values are image/png (PNG format images) and image/jpeg (JPG format images). "
schema:
type: string
pattern: .*
minLength: 1
maxLength: 255
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- Body
properties:
Body:
description: "The unencrypted image bytes that you want to analyze. "
type: string
summary: Amazon Lookout for Vision Detect Anomalies
parameters:
- $ref: "#/components/parameters/X-Amz-Content-Sha256"
- $ref: "#/components/parameters/X-Amz-Date"
- $ref: "#/components/parameters/X-Amz-Algorithm"
- $ref: "#/components/parameters/X-Amz-Credential"
- $ref: "#/components/parameters/X-Amz-Security-Token"
- $ref: "#/components/parameters/X-Amz-Signature"
- $ref: "#/components/parameters/X-Amz-SignedHeaders"
"/2020-11-20/projects/{projectName}/datasets/{datasetType}/entries":
get:
operationId: ListDatasetEntries
description: Lists the JSON Lines within a dataset. An Amazon Lookout for Vision JSON Line contains the anomaly information for a single image, including the image location and the assigned label.
This operation requires permissions to perform the lookoutvision:ListDatasetEntries operation.
train to list the training dataset. Specify test to list the test dataset. If you have a single
dataset project, specify train.
schema:
type: string
pattern: train|test
minLength: 1
maxLength: 10
- name: labeled
in: query
required: false
description: Specify true to include labeled entries, otherwise specify false. If you don't specify a value, Lookout for Vision returns all entries.
schema:
type: boolean
- name: anomalyClass
in: query
required: false
description: Specify normal to include only normal images. Specify anomaly to only include anomalous entries. If you don't specify a value, Amazon Lookout for Vision
returns normal and anomalous images.
schema:
type: string
pattern: (normal|anomaly)
minLength: 1
maxLength: 10
- name: createdBefore
in: query
required: false
description: Only includes entries before the specified date in the response. For example, 2020-06-23T00:00:00.
schema:
type: string
format: date-time
- name: createdAfter
in: query
required: false
description: Only includes entries after the specified date in the response. For example, 2020-06-23T00:00:00.
schema:
type: string
format: date-time
- name: nextToken
in: query
required: false
description: If the previous response was incomplete (because there is more data to retrieve), Amazon Lookout for Vision returns a pagination token in the response. You can use this pagination
token to retrieve the next set of dataset entries.
schema:
type: string
pattern: ^[a-zA-Z0-9\/\+\=]{0,2048}$
maxLength: 2048
- name: maxResults
in: query
required: false
description: The maximum number of results to return per paginated call. The largest value you can specify is 100. If you specify a value greater than 100, a ValidationException error occurs.
The default value is 100.
schema:
type: integer
minimum: 1
maximum: 100
- name: sourceRefContains
in: query
required: false
description: Perform a "contains" search on the values of the source-ref key within the dataset. For example a value of "IMG_17" returns all JSON Lines where the
source-ref key value matches *IMG_17*.
schema:
type: string
pattern: .*\S.*
minLength: 1
maxLength: 2048
- name: MaxResults
in: query
schema:
type: string
description: Pagination limit
required: false
- name: NextToken
in: query
schema:
type: string
description: Pagination token
required: false
summary: Amazon Lookout for Vision List Dataset Entries
parameters:
- $ref: "#/components/parameters/X-Amz-Content-Sha256"
- $ref: "#/components/parameters/X-Amz-Date"
- $ref: "#/components/parameters/X-Amz-Algorithm"
- $ref: "#/components/parameters/X-Amz-Credential"
- $ref: "#/components/parameters/X-Amz-Security-Token"
- $ref: "#/components/parameters/X-Amz-Signature"
- $ref: "#/components/parameters/X-Amz-SignedHeaders"
patch:
operationId: UpdateDatasetEntries
description: Adds 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.
train to update the training dataset. Specify test to update the test dataset. If you have a
single dataset project, specify train.
schema:
type: string
pattern: train|test
minLength: 1
maxLength: 10
- name: X-Amzn-Client-Token
in: header
required: false
description: ClientToken is an idempotency token that ensures a call to UpdateDatasetEntries completes only once. You choose the value to pass. For example, An issue might
prevent you from getting a response from UpdateDatasetEntries. In this case, safely retry your call to UpdateDatasetEntries by using the same
ClientToken parameter value.
If you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a
network error from making multiple updates with the same dataset entries. You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are
not the same as in the first request. Using a different value for ClientToken is considered a new call to UpdateDatasetEntries. An idempotency token is active for 8
hours.
Lists 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.
responses: "200": description: Success content: application/json: schema: $ref: "#/components/schemas/ListModelPackagingJobsResponse" "480": description: AccessDeniedException content: application/json: schema: $ref: "#/components/schemas/AccessDeniedException" "481": description: InternalServerException content: application/json: schema: $ref: "#/components/schemas/InternalServerException" "482": description: ValidationException content: application/json: schema: $ref: "#/components/schemas/ValidationException" "483": description: ResourceNotFoundException content: application/json: schema: $ref: "#/components/schemas/ResourceNotFoundException" "484": description: ThrottlingException content: application/json: schema: $ref: "#/components/schemas/ThrottlingException" parameters: - name: projectName in: path required: true description: " The name of the project for which you want to list the model packaging jobs. " schema: type: string pattern: "[a-zA-Z0-9][a-zA-Z0-9_\\-]*" minLength: 1 maxLength: 255 - name: nextToken in: query required: false description: "If the previous response was incomplete (because there is more results to retrieve), Amazon Lookout for Vision returns a pagination token in the response. You can use this pagination token to retrieve the next set of results. " schema: type: string pattern: ^[a-zA-Z0-9\/\+\=]{0,2048}$ maxLength: 2048 - name: maxResults in: query required: false description: "The maximum number of results to return per paginated call. The largest value you can specify is 100. If you specify a value greater than 100, a ValidationException error occurs. The default value is 100. " schema: type: integer minimum: 1 maximum: 100 - name: MaxResults in: query schema: type: string description: Pagination limit required: false - name: NextToken in: query schema: type: string description: Pagination token required: false summary: Amazon Lookout for Vision List Model Packaging Jobs parameters: - $ref: "#/components/parameters/X-Amz-Content-Sha256" - $ref: "#/components/parameters/X-Amz-Date" - $ref: "#/components/parameters/X-Amz-Algorithm" - $ref: "#/components/parameters/X-Amz-Credential" - $ref: "#/components/parameters/X-Amz-Security-Token" - $ref: "#/components/parameters/X-Amz-Signature" - $ref: "#/components/parameters/X-Amz-SignedHeaders" post: operationId: StartModelPackagingJob description:Starts 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.
responses: "200": description: Success content: application/json: schema: $ref: "#/components/schemas/StartModelPackagingJobResponse" "480": description: AccessDeniedException content: application/json: schema: $ref: "#/components/schemas/AccessDeniedException" "481": description: InternalServerException content: application/json: schema: $ref: "#/components/schemas/InternalServerException" "482": description: ValidationException content: application/json: schema: $ref: "#/components/schemas/ValidationException" "483": description: ConflictException content: application/json: schema: $ref: "#/components/schemas/ConflictException" "484": description: ResourceNotFoundException content: application/json: schema: $ref: "#/components/schemas/ResourceNotFoundException" "485": description: ThrottlingException content: application/json: schema: $ref: "#/components/schemas/ThrottlingException" "486": description: ServiceQuotaExceededException content: application/json: schema: $ref: "#/components/schemas/ServiceQuotaExceededException" parameters: - name: projectName in: path required: true description: " The name of the project which contains the version of the model that you want to package. " schema: type: string pattern: "[a-zA-Z0-9][a-zA-Z0-9_\\-]*" minLength: 1 maxLength: 255 - name: X-Amzn-Client-Token in: header required: false description:ClientToken is an idempotency token that ensures a call to StartModelPackagingJob completes only once. You choose the value to pass. For example, An issue might
prevent you from getting a response from StartModelPackagingJob. In this case, safely retry your call to StartModelPackagingJob by using the same
ClientToken parameter value.
If you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a
network error from making multiple dataset creation requests. You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are not the
same as in the first request. Using a different value for ClientToken is considered a new call to StartModelPackagingJob. An idempotency token is active for 8
hours.
Returns a list of tags attached to the specified Amazon Lookout for Vision model.
This operation requires permissions to perform the
lookoutvision:ListTagsForResource 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.
Starts 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.
ClientToken is an idempotency token that ensures a call to StartModel completes only once. You choose the value to pass. For example, An issue might prevent you
from getting a response from StartModel. In this case, safely retry your call to StartModel by using the same ClientToken parameter value.
If
you don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a network error from making multiple start requests.
You'll need to provide your own value for other use cases.
An error occurs if the other input parameters are not the same as in the first request. Using a different value for
ClientToken is considered a new call to StartModel. An idempotency token is active for 8 hours.
Stops 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.
ClientToken is an idempotency token that ensures a call to StopModel completes only once. You choose the value to pass. For example, An issue might prevent you
from getting a response from StopModel. In this case, safely retry your call to StopModel by using the same ClientToken parameter value.
If you
don't supply a value for ClientToken, the AWS SDK you are using inserts a value for you. This prevents retries after a network error from making multiple stop requests. You'll
need to provide your own value for other use cases.
An error occurs if the other input parameters are not the same as in the first request. Using a different value for
ClientToken is considered a new call to StopModel. An idempotency token is active for 8 hours.
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.
CreateModel.
S3Location:
type: object
required:
- Bucket
properties:
Bucket:
allOf:
- $ref: "#/components/schemas/S3BucketName"
- description: The S3 bucket that contains the training or model packaging job output. If you are training a model, the bucket must in your AWS account. If you use an S3 bucket for a model
packaging job, the S3 bucket must be in the same AWS Region and AWS account in which you use AWS IoT Greengrass.
Prefix:
allOf:
- $ref: "#/components/schemas/S3KeyPrefix"
- description: The path of the folder, within the S3 bucket, that contains the output.
description: Information about the location of training output or the output of a model packaging job.
Tag:
type: object
required:
- Key
- Value
properties:
Key:
allOf:
- $ref: "#/components/schemas/TagKey"
- description: The key of the tag that is attached to the specified model.
Value:
allOf:
- $ref: "#/components/schemas/TagValue"
- description: The value of the tag that is attached to the specified model.
description: A key and value pair that is attached to the specified Amazon Lookout for Vision model.
CreateProjectResponse:
type: object
properties:
ProjectMetadata:
allOf:
- $ref: "#/components/schemas/ProjectMetadata"
- description: Information about the project.
DeleteDatasetResponse:
type: object
properties: {}
DeleteModelResponse:
type: object
properties:
ModelArn:
allOf:
- $ref: "#/components/schemas/ModelArn"
- description: The Amazon Resource Name (ARN) of the model that was deleted.
DeleteProjectResponse:
type: object
properties:
ProjectArn:
allOf:
- $ref: "#/components/schemas/ProjectArn"
- description: The Amazon Resource Name (ARN) of the project that was deleted.
DescribeDatasetResponse:
type: object
properties:
DatasetDescription:
allOf:
- $ref: "#/components/schemas/DatasetDescription"
- description: "The description of the requested dataset. "
DescribeModelResponse:
type: object
properties:
ModelDescription:
allOf:
- $ref: "#/components/schemas/ModelDescription"
- description: Contains the description of the model.
DescribeModelPackagingJobResponse:
type: object
properties:
ModelPackagingDescription:
allOf:
- $ref: "#/components/schemas/ModelPackagingDescription"
- description: "The description of the model packaging job. "
DescribeProjectResponse:
type: object
properties:
ProjectDescription:
allOf:
- $ref: "#/components/schemas/ProjectDescription"
- description: The description of the project.
DetectAnomaliesResponse:
type: object
properties:
DetectAnomalyResult:
allOf:
- $ref: "#/components/schemas/DetectAnomalyResult"
- description: The results of the DetectAnomalies operation.
ListDatasetEntriesResponse:
type: object
properties:
DatasetEntries:
allOf:
- $ref: "#/components/schemas/DatasetEntryList"
- description: A list of the entries (JSON Lines) within the dataset.
NextToken:
allOf:
- $ref: "#/components/schemas/PaginationToken"
- description: If the response is truncated, Amazon Lookout for Vision returns this token that you can use in the subsequent request to retrieve the next set ofdataset entries.
ListModelPackagingJobsResponse:
type: object
properties:
ModelPackagingJobs:
allOf:
- $ref: "#/components/schemas/ModelPackagingJobsList"
- description: " A list of the model packaging jobs created for the specified Amazon Lookout for Vision project. "
NextToken:
allOf:
- $ref: "#/components/schemas/PaginationToken"
- description: "If the previous response was incomplete (because there is more results to retrieve), Amazon Lookout for Vision returns a pagination token in the response. You can use this pagination
token to retrieve the next set of results. "
ListModelsResponse:
type: object
properties:
Models:
allOf:
- $ref: "#/components/schemas/ModelMetadataList"
- description: "A list of model versions in the specified project. "
NextToken:
allOf:
- $ref: "#/components/schemas/PaginationToken"
- description: "If the response is truncated, Amazon Lookout for Vision returns this token that you can use in the subsequent request to retrieve the next set of models. "
ListProjectsResponse:
type: object
properties:
Projects:
allOf:
- $ref: "#/components/schemas/ProjectMetadataList"
- description: A list of projects in your AWS account.
NextToken:
allOf:
- $ref: "#/components/schemas/PaginationToken"
- description: If the response is truncated, Amazon Lookout for Vision returns this token that you can use in the subsequent request to retrieve the next set of projects.
ListTagsForResourceResponse:
type: object
properties:
Tags:
allOf:
- $ref: "#/components/schemas/TagList"
- description: A map of tag keys and values attached to the specified model.
StartModelResponse:
type: object
properties:
Status:
allOf:
- $ref: "#/components/schemas/ModelHostingStatus"
- description: The current running status of the model.
StartModelPackagingJobResponse:
type: object
properties:
JobName:
allOf:
- $ref: "#/components/schemas/ModelPackagingJobName"
- description: "The job name for the model packaging job. If you don't supply a job name in the JobName input parameter, the service creates a job name for you. "
GreengrassConfiguration:
type: object
required:
- S3OutputLocation
- ComponentName
properties:
CompilerOptions:
allOf:
- $ref: "#/components/schemas/CompilerOptions"
- description: Additional compiler options for the Greengrass component. Currently, only NVIDIA Graphics Processing Units (GPU) and CPU accelerators are supported. If you specify
TargetDevice, don't specify CompilerOptions.
For more information, see Compiler options in the Amazon Lookout for Vision Developer Guide.
TargetDevice: allOf: - $ref: "#/components/schemas/TargetDevice" - description: "The target device for the model. Currently the only supported value isjetson_xavier. If you specify TargetDevice, you can't specify TargetPlatform. "
TargetPlatform:
allOf:
- $ref: "#/components/schemas/TargetPlatform"
- description: "The target platform for the model. If you specify TargetPlatform, you can't specify TargetDevice. "
S3OutputLocation:
allOf:
- $ref: "#/components/schemas/S3Location"
- description: " An S3 location in which Lookout for Vision stores the component artifacts. "
ComponentName:
allOf:
- $ref: "#/components/schemas/ComponentName"
- description: " A name for the AWS IoT Greengrass component. "
ComponentVersion:
allOf:
- $ref: "#/components/schemas/ComponentVersion"
- description: "A Version for the AWS IoT Greengrass component. If you don't provide a value, a default value of Model Version.0.0 is used. "
ComponentDescription:
allOf:
- $ref: "#/components/schemas/ComponentDescription"
- description: " A description for the AWS IoT Greengrass component. "
Tags:
allOf:
- $ref: "#/components/schemas/TagList"
- description: " A set of tags (key-value pairs) that you want to attach to the AWS IoT Greengrass component. "
description: Configuration information for the AWS IoT Greengrass component created in a model packaging job. For more information, see StartModelPackagingJob.
You can't
specify a component with the same ComponentName and Componentversion as an existing component with the same component name and component version.
PixelAnomaly is only returned by image segmentation models.
Anomaly:
type: object
properties:
Name:
allOf:
- $ref: "#/components/schemas/AnomalyName"
- description: "The name of an anomaly type found in an image. Name maps to an anomaly type in the training dataset, apart from the anomaly type background. The service
automatically inserts the background anomaly type into the response from DetectAnomalies. "
PixelAnomaly:
allOf:
- $ref: "#/components/schemas/PixelAnomaly"
- description: Information about the pixel mask that covers an anomaly type.
description: Information about an anomaly type found on an image by an image segmentation model. For more information, see DetectAnomalies.
AnomalyClassFilter:
type: string
pattern: (normal|anomaly)
minLength: 1
maxLength: 10
AnomalyList:
type: array
items:
$ref: "#/components/schemas/Anomaly"
AnomalyMask:
type: string
minLength: 1
maxLength: 5242880
Boolean:
type: boolean
ClientToken:
type: string
pattern: ^[a-zA-Z0-9-]+$
minLength: 1
maxLength: 64
Color:
type: string
pattern: \#[a-zA-Z0-9]{6}
minLength: 7
maxLength: 7
CompilerOptions:
type: string
pattern: .*
minLength: 3
maxLength: 1024
ComponentDescription:
type: string
pattern: "[a-zA-Z0-9-_. ()':,;?]+"
minLength: 1
maxLength: 256
ComponentName:
type: string
pattern: "[a-zA-Z0-9-_.]+"
minLength: 1
maxLength: 128
ComponentVersion:
type: string
pattern: ^([0-9]{1,6})\.([0-9]{1,6})\.([0-9]{1,6})$
minLength: 1
maxLength: 64
ComponentVersionArn:
type: string
pattern: arn:[^:]*:greengrass:[^:]*:aws:components:[^:]+
ContentType:
type: string
pattern: .*
minLength: 1
maxLength: 255
ProjectName:
type: string
pattern: "[a-zA-Z0-9][a-zA-Z0-9_\\-]*"
minLength: 1
maxLength: 255
DatasetType:
type: string
pattern: train|test
minLength: 1
maxLength: 10
DatasetSource:
type: object
properties:
GroundTruthManifest:
allOf:
- $ref: "#/components/schemas/DatasetGroundTruthManifest"
- description: Location information for the manifest file.
description: Information about the location of a manifest file that Amazon Lookout for Vision uses to to create a dataset.
CreateDatasetRequest:
type: object
required:
- DatasetType
title: CreateDatasetRequest
properties:
DatasetType:
allOf:
- $ref: "#/components/schemas/DatasetType"
- description: The type of the dataset. Specify train for a training dataset. Specify test for a test dataset.
DatasetSource:
allOf:
- $ref: "#/components/schemas/DatasetSource"
- description: The location of the manifest file that Amazon Lookout for Vision uses to create the dataset.
If you don't specify DatasetSource, an empty dataset is
created and the operation synchronously returns. Later, you can add JSON Lines by calling UpdateDatasetEntries.
If you specify a value for DataSource, the
manifest at the S3 location is validated and used to create the dataset. The call to CreateDataset is asynchronous and might take a while to complete. To find out the
current status, Check the value of Status returned in a call to DescribeDataset.
train represents a training dataset or single dataset project. The value test represents a test dataset.
CreationTimestamp:
allOf:
- $ref: "#/components/schemas/DateTime"
- description: The Unix timestamp for the time and date that the dataset was created.
LastUpdatedTimestamp:
allOf:
- $ref: "#/components/schemas/DateTime"
- description: The Unix timestamp for the date and time that the dataset was last updated.
Status:
allOf:
- $ref: "#/components/schemas/DatasetStatus"
- description: The status of the dataset.
StatusMessage:
allOf:
- $ref: "#/components/schemas/DatasetStatusMessage"
- description: "The status message for the dataset. "
ImageStats:
allOf:
- $ref: "#/components/schemas/DatasetImageStats"
- description: Statistics about the images in a dataset.
description: The description for a dataset. For more information, see DescribeDataset.
DatasetEntry:
type: string
pattern: ^\{.*\}$
minLength: 2
maxLength: 8192
DatasetEntryList:
type: array
items:
$ref: "#/components/schemas/DatasetEntry"
InputS3Object:
type: object
required:
- Bucket
- Key
properties:
Bucket:
allOf:
- $ref: "#/components/schemas/S3BucketName"
- description: The Amazon S3 bucket that contains the manifest.
Key:
allOf:
- $ref: "#/components/schemas/S3ObjectKey"
- description: The name and location of the manifest file withiin the bucket.
VersionId:
allOf:
- $ref: "#/components/schemas/S3ObjectVersion"
- description: The version ID of the bucket.
description: "Amazon S3 Location information for an input manifest file. "
Integer:
type: integer
DatasetMetadataList:
type: array
items:
$ref: "#/components/schemas/DatasetMetadata"
DeleteDatasetRequest:
type: object
title: DeleteDatasetRequest
properties: {}
ModelVersionNoLatest:
type: string
pattern: ([1-9][0-9]*)
minLength: 1
maxLength: 10
DeleteModelRequest:
type: object
title: DeleteModelRequest
properties: {}
ModelArn:
type: string
DeleteProjectRequest:
type: object
title: DeleteProjectRequest
properties: {}
ProjectArn:
type: string
DescribeDatasetRequest:
type: object
title: DescribeDatasetRequest
properties: {}
ModelPackagingJobName:
type: string
pattern: "[a-zA-Z0-9-]+"
minLength: 1
maxLength: 64
DescribeModelPackagingJobRequest:
type: object
title: DescribeModelPackagingJobRequest
properties: {}
ModelPackagingDescription:
type: object
properties:
JobName:
allOf:
- $ref: "#/components/schemas/ModelPackagingJobName"
- description: " The name of the model packaging job. "
ProjectName:
allOf:
- $ref: "#/components/schemas/ProjectName"
- description: "The name of the project that's associated with a model that's in the model package. "
ModelVersion:
allOf:
- $ref: "#/components/schemas/ModelVersion"
- description: "The version of the model used in the model packaging job. "
ModelPackagingConfiguration:
allOf:
- $ref: "#/components/schemas/ModelPackagingConfiguration"
- description: " The configuration information used in the model packaging job. "
ModelPackagingJobDescription:
allOf:
- $ref: "#/components/schemas/ModelPackagingJobDescription"
- description: "The description for the model packaging job. "
ModelPackagingMethod:
allOf:
- $ref: "#/components/schemas/ModelPackagingMethod"
- description: "The AWS service used to package the job. Currently Lookout for Vision can package jobs with AWS IoT Greengrass. "
ModelPackagingOutputDetails:
allOf:
- $ref: "#/components/schemas/ModelPackagingOutputDetails"
- description: "Information about the output of the model packaging job. For more information, see DescribeModelPackagingJob. "
Status:
allOf:
- $ref: "#/components/schemas/ModelPackagingJobStatus"
- description: " The status of the model packaging job. "
StatusMessage:
allOf:
- $ref: "#/components/schemas/ModelPackagingStatusMessage"
- description: " The status message for the model packaging job. "
CreationTimestamp:
allOf:
- $ref: "#/components/schemas/DateTime"
- description: " The Unix timestamp for the time and date that the model packaging job was created. "
LastUpdatedTimestamp:
allOf:
- $ref: "#/components/schemas/DateTime"
- description: " The Unix timestamp for the time and date that the model packaging job was last updated. "
description: " Information about a model packaging job. For more information, see DescribeModelPackagingJob. "
ModelVersion:
type: string
pattern: ([1-9][0-9]*|latest)
minLength: 1
maxLength: 10
DescribeModelRequest:
type: object
title: DescribeModelRequest
properties: {}
ModelDescription:
type: object
properties:
ModelVersion:
allOf:
- $ref: "#/components/schemas/ModelVersion"
- description: The version of the model
ModelArn:
allOf:
- $ref: "#/components/schemas/ModelArn"
- description: The Amazon Resource Name (ARN) of the model.
CreationTimestamp:
allOf:
- $ref: "#/components/schemas/DateTime"
- description: "The unix timestamp for the date and time that the model was created. "
Description:
allOf:
- $ref: "#/components/schemas/ModelDescriptionMessage"
- description: The description for the model.
Status:
allOf:
- $ref: "#/components/schemas/ModelStatus"
- description: The status of the model.
StatusMessage:
allOf:
- $ref: "#/components/schemas/ModelStatusMessage"
- description: The status message for the model.
Performance:
allOf:
- $ref: "#/components/schemas/ModelPerformance"
- description: Performance metrics for the model. Created during training.
OutputConfig:
allOf:
- $ref: "#/components/schemas/OutputConfig"
- description: The S3 location where Amazon Lookout for Vision saves model training files.
EvaluationManifest:
allOf:
- $ref: "#/components/schemas/OutputS3Object"
- description: The S3 location where Amazon Lookout for Vision saves the manifest file that was used to test the trained model and generate the performance scores.
EvaluationResult:
allOf:
- $ref: "#/components/schemas/OutputS3Object"
- description: The S3 location where Amazon Lookout for Vision saves the performance metrics.
EvaluationEndTimestamp:
allOf:
- $ref: "#/components/schemas/DateTime"
- description: "The unix timestamp for the date and time that the evaluation ended. "
KmsKeyId:
allOf:
- $ref: "#/components/schemas/KmsKeyId"
- description: The identifer for the AWS Key Management Service (AWS KMS) key that was used to encrypt the model during training.
MinInferenceUnits:
allOf:
- $ref: "#/components/schemas/InferenceUnits"
- description: "The minimum number of inference units used by the model. For more information, see StartModel "
MaxInferenceUnits:
allOf:
- $ref: "#/components/schemas/InferenceUnits"
- description: The maximum number of inference units Amazon Lookout for Vision uses to auto-scale the model. For more information, see StartModel.
description: Describes an Amazon Lookout for Vision model.
DescribeProjectRequest:
type: object
title: DescribeProjectRequest
properties: {}
ProjectDescription:
type: object
properties:
ProjectArn:
allOf:
- $ref: "#/components/schemas/ProjectArn"
- description: The Amazon Resource Name (ARN) of the project.
ProjectName:
allOf:
- $ref: "#/components/schemas/ProjectName"
- description: The name of the project.
CreationTimestamp:
allOf:
- $ref: "#/components/schemas/DateTime"
- description: "The unix timestamp for the date and time that the project was created. "
Datasets:
allOf:
- $ref: "#/components/schemas/DatasetMetadataList"
- description: A list of datasets in the project.
description: Describe an Amazon Lookout for Vision project. For more information, see DescribeProject.
Stream:
type: string
DetectAnomaliesRequest:
type: object
required:
- Body
title: DetectAnomaliesRequest
properties:
Body:
allOf:
- $ref: "#/components/schemas/Stream"
- description: "The unencrypted image bytes that you want to analyze. "
DetectAnomalyResult:
type: object
properties:
Source:
allOf:
- $ref: "#/components/schemas/ImageSource"
- description: The source of the image that was analyzed. direct means that the images was supplied from the local computer. No other values are supported.
IsAnomalous:
allOf:
- $ref: "#/components/schemas/Boolean"
- description: True if Amazon Lookout for Vision classifies the image as containing an anomaly, otherwise false.
Confidence:
allOf:
- $ref: "#/components/schemas/Float"
- description: The confidence that Lookout for Vision has in the accuracy of the classification in IsAnomalous.
Anomalies:
allOf:
- $ref: "#/components/schemas/AnomalyList"
- description: If the model is an image segmentation model, Anomalies contains a list of anomaly types found in the image. There is one entry for each type of anomaly found
(even if multiple instances of an anomaly type exist on the image). The first element in the list is always an anomaly type representing the image background ('background') and shouldn't
be considered an anomaly. Amazon Lookout for Vision automatically add the background anomaly type to the response, and you don't need to declare a background anomaly type in your
dataset.
If the list has one entry ('background'), no anomalies were found on the image.
An image classification model doesn't return an Anomalies list.
If the model is an image segmentation model, AnomalyMask contains pixel masks that covers all anomaly types found on the image. Each anomaly type has a
different mask color. To map a color to an anomaly type, see the color field of the PixelAnomaly object.
An image classification model doesn't return an
Anomalies list.
DetectAnomalyResult includes classification information for the prediction (IsAnomalous and
Confidence). If the model you use is an image segementation model, DetectAnomalyResult also includes segmentation information (Anomalies and
AnomalyMask). Classification information is calculated separately from segmentation information and you shouldn't assume a relationship between them.
ImageSource:
type: object
properties:
Type:
allOf:
- $ref: "#/components/schemas/ImageSourceType"
- description: The type of the image.
description: The source for an image.
Float:
type: number
format: float
TargetDevice:
type: string
enum:
- jetson_xavier
TargetPlatform:
type: object
required:
- Os
- Arch
properties:
Os:
allOf:
- $ref: "#/components/schemas/TargetPlatformOs"
- description: "The target operating system for the model. Linux is the only operating system that is currently supported. "
Arch:
allOf:
- $ref: "#/components/schemas/TargetPlatformArch"
- description: "The target architecture for the model. The currently supported architectures are X86_64 (64-bit version of the x86 instruction set) and ARM_64 (ARMv8 64-bit CPU). "
Accelerator:
allOf:
- $ref: "#/components/schemas/TargetPlatformAccelerator"
- description: "The target accelerator for the model. Currently, Amazon Lookout for Vision only supports NVIDIA (Nvidia graphics processing unit) and CPU accelerators. If you specify NVIDIA
as an accelerator, you must also specify the gpu-code, trt-ver, and cuda-ver compiler options. If you don't specify an accelerator, Lookout for Vision
uses the CPU for compilation and we highly recommend that you use the GreengrassConfiguration$CompilerOptions field. For example, you can use the following compiler options for CPU:
mcpu: CPU micro-architecture. For example, {'mcpu': 'skylake-avx512'}
mattr: CPU flags. For example, {'mattr':
['+neon', '+vfpv4']}