Edge Impulse Learn API is one of 34 APIs that Edge Impulse publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Learn. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.
This API exposes
23 operations
across 21 paths,
and defines 63 schemas.
It is described by OpenAPI 3.0.0, at version 1.0.0.
Requests are made against a single base URL, https://studio.edgeimpulse.com/v1.
23 operations21 paths63 schemas15 GET8 POST
Metadata
The identity and technical contract details declared by the specification.
Specification
OpenAPI 3.0.0
API Version
1.0.0
Base URL
https://studio.edgeimpulse.com/v1
Authentication
API Key, API Key, API Key
Resource Areas
1
Authentication & Security 3
Edge Impulse Learn API declares
3 security schemes
for authenticating requests.
An API key is passed in the header as x-api-key (ApiKeyAuthentication).
An API key is passed in the cookie as jwt (JWTAuthentication).
An API key is passed in the header as x-jwt-token (JWTHttpHeaderAuthentication).
By default, every request must be authenticated.
Paths & Operations 23
Across 21 paths, the API surfaces 23 operations — 15 GET, 8 POST. Each is listed below with its method, path, parameters, and response codes.
The contract defines 63 schemas that model the data the API accepts and returns. The most detailed are KerasConfig (31 properties), SetKerasParameterRequest (24 properties), TransferLearningModel (20 properties), ImpulseInputBlock (18 properties). Each schema is shown below with its type and property counts.
BlockDisplayCategory
string
Category to display this block in the UI.
KerasModelVariantEnum
string
AnomalyGmmMetadata
object
3 properties3 required
ProfileModelTableMcu
object
5 properties2 required
BlockType
string
StartJobResponse
DeployPretrainedModelInputImage
object
2 properties1 required
ImpulseInputBlock
object
18 properties5 required
AddKerasFilesRequest
object
1 property1 required
ProfileModelTable
object
Performance for a range of device types. Note that MPU is referred to as CPU in Studio, as MPU and CPU are treated equivalent for performance estimation.
6 properties6 required
AnomalyConfig
object
7 properties6 required
BlockParameters
Training parameters specific to the type of the learn block. Parameters may be adjusted depending on the model defined in the visual layers. Used for our built…
GetDataExplorerFeaturesResponse
AnomalyCapacity
string
Capacity level for visual anomaly detection. Determines which set of default configurations to use. The higher capacity, the higher number of (Gaussian) compon…
TestPretrainedModelRequest
object
2 properties2 required
KerasCustomMetric
object
2 properties2 required
DeployPretrainedModelInputOther
object
1 property1 required
DeployPretrainedModelModelClassification
object
2 properties2 required
TestPretrainedModelResponse
SavePretrainedModelRequest
object
2 properties2 required
AdditionalMetric
object
5 properties3 required
AnomalyTrainedFeaturesResponse
AnomalyConfigResponse
ModelEngineShortEnum
string
UploadPretrainedModelRequest
object
5 properties3 required
ProfileModelInfoMemoryDetails
object
3 properties3 required
BoundingBoxWithScore
object
This has the ratio for x/y/w/h (so 0..1)
6 properties6 required
DependencyData
object
4 properties4 required
AnomalyModelMetadata
object
10 properties5 required
SetAnomalyParameterRequest
object
Only fields defined in this object are set
1 property
KerasVisualLayerType
string
ObjectDetectionLastLayer
string
DeployPretrainedModelModelRegression
object
1 property1 required
ProfileModelInfo
object
6 properties3 required
AnomalyGmmMetadataResponse
KerasVisualLayer
object
8 properties1 required
ImageInputScaling
string
Normalization that is applied to images. If this is not set then 0..1 is used. "0..1" gives you non-normalized pixels between 0 and 1. "-1..1" gives you non-no…
DeployPretrainedModelInputAudio
object
2 properties2 required
ProfileModelTableMpu
object
4 properties2 required
BlockParamsVisualAnomalyGmm
object
1 property
KerasConfig
object
31 properties18 required
PretrainedModelTensor
object
5 properties3 required
TransferLearningModel
object
20 properties8 required
KerasModelMetadataMetrics
object
13 properties8 required
GetPretrainedModelResponse
BlockParamsVisualAnomalyPatchcore
object
5 properties
DSPGroupItem
object
16 properties7 required
ModelPrediction
object
8 properties4 required
UploadKerasFilesRequest
object
1 property1 required
AkidaEdgeLearningConfig
object
3 properties1 required
KerasModelMetadataResponse
SetKerasParameterRequest
object
Only fields defined in this object are set
24 properties
AnomalyModelMetadataResponse
AugmentationPolicySpectrogram
object
5 properties1 required
KerasModelTypeEnum
string
KerasModelMetadata
object
11 properties10 required
KerasModelLayer
object
2 properties2 required
LearnBlockType
string
The type of learning block (anomaly, keras, keras-transfer-image, keras-transfer-kws, keras-object-detection, keras-regression). Each behaves differently.
DeployPretrainedModelModelObjectDetection
object
4 properties4 required
DeployPretrainedModelInputTimeSeries
object
3 properties3 required
KerasResponse
GenericApiResponse
object
2 properties1 required
AugmentationPolicyImageEnum
string
The data augmentation policy to use with image input
Specification
The full machine-readable OpenAPI contract behind this narrative.
