Expand description
Data structures used by operation inputs/outputs.
Modules§
Structs§
- Anomaly
Information about an anomaly type found on an image by an image segmentation model. For more information, see
DetectAnomalies
.- Dataset
Description The description for a dataset. For more information, see
DescribeDataset
.- Dataset
Ground Truth Manifest Location information about a manifest file. You can use a manifest file to create a dataset.
- Dataset
Image Stats Statistics about the images in a dataset.
- Dataset
Metadata Summary information for an Amazon Lookout for Vision dataset. For more information, see
DescribeDataset
andProjectDescription
.- Dataset
Source Information about the location of a manifest file that Amazon Lookout for Vision uses to to create a dataset.
- Detect
Anomaly Result The prediction results from a call to
DetectAnomalies
.DetectAnomalyResult
includes classification information for the prediction (IsAnomalous
andConfidence
). If the model you use is an image segementation model,DetectAnomalyResult
also includes segmentation information (Anomalies
andAnomalyMask
). Classification information is calculated separately from segmentation information and you shouldn't assume a relationship between them.- Greengrass
Configuration 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
andComponentversion
as an existing component with the same component name and component version.- Greengrass
Output Details Information about the AWS IoT Greengrass component created by a model packaging job.
- Image
Source The source for an image.
- Input
S3Object Amazon S3 Location information for an input manifest file.
- Model
Description Describes an Amazon Lookout for Vision model.
- Model
Metadata Describes an Amazon Lookout for Vision model.
- Model
Packaging Configuration Configuration information for a Amazon Lookout for Vision model packaging job. For more information, see
StartModelPackagingJob
.- Model
Packaging Description Information about a model packaging job. For more information, see
DescribeModelPackagingJob
.- Model
Packaging JobMetadata Metadata for a model packaging job. For more information, see
ListModelPackagingJobs
.- Model
Packaging Output Details Information about the output from a model packaging job.
- Model
Performance Information about the evaluation performance of a trained model.
- Output
Config The S3 location where Amazon Lookout for Vision saves model training files.
- Output
S3Object The S3 location where Amazon Lookout for Vision saves training output.
- Pixel
Anomaly Information about the pixels in an anomaly mask. For more information, see
Anomaly
.PixelAnomaly
is only returned by image segmentation models.- Project
Description Describe an Amazon Lookout for Vision project. For more information, see
DescribeProject
.- Project
Metadata Metadata about an Amazon Lookout for Vision project.
- S3Location
Information about the location of training output or the output of a model packaging job.
- Tag
A key and value pair that is attached to the specified Amazon Lookout for Vision model.
- Target
Platform The platform on which a model runs on an AWS IoT Greengrass core device.
Enums§
- Dataset
Status - When writing a match expression against
DatasetStatus
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Model
Hosting Status - When writing a match expression against
ModelHostingStatus
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Model
Packaging JobStatus - When writing a match expression against
ModelPackagingJobStatus
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Model
Status - When writing a match expression against
ModelStatus
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Resource
Type - When writing a match expression against
ResourceType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Target
Device - When writing a match expression against
TargetDevice
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Target
Platform Accelerator - When writing a match expression against
TargetPlatformAccelerator
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Target
Platform Arch - When writing a match expression against
TargetPlatformArch
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Target
Platform Os - When writing a match expression against
TargetPlatformOs
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.