Edge Impulse API is one of 38 APIs that Edge Impulse publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Impulse. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.
This API exposes
18 operations
across 16 paths,
and defines 111 schemas.
It is described by OpenAPI 3.2.0, at version 1.0.0.
Requests are made against a single base URL, https://studio.edgeimpulse.com/v1.
The identity and technical contract details declared by the specification.
Edge Impulse API declares
4 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).
It supports OAuth 2.0 (OAuth2) using the authorizationCode, implicit, password and clientCredentials flows, exposing 3 scopes.
InputBlock
object
7 properties
7 required
BlockParamsVisualAnomalyGmm
object
1 property
TransferLearningModel
object
20 properties
8 required
DspPerformance
object
3 properties
2 required
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…
AnomalyConfig
object
7 properties
6 required
LearnBlockType
string
The type of learning block (anomaly, keras, keras-transfer-image, keras-transfer-kws, keras-object-detection, keras-regression). Each behaves differently.
KerasVisualLayerType
string
AdditionalMetric
object
5 properties
3 required
DSPGroup
object
2 properties
2 required
VerifyDspBlockUrlResponse
KerasModelLayer
object
2 properties
2 required
KerasModelMetadata
object
11 properties
10 required
VerifyDspBlockUrlRequest
object
1 property
1 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…
DetailedImpulseMetricFilteringType
object
2 properties
2 required
ModelEngineShortEnum
string
AnomalyGmmMetadata
object
3 properties
3 required
AugmentationPolicySpectrogram
object
5 properties
1 required
DSPNamedAxis
object
3 properties
3 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…
ImpulseDspBlock
object
14 properties
7 required
DetailedImpulseMetricCategory
string
KerasConfig
object
31 properties
18 required
DSPMetadata
object
14 properties
11 required
LearnBlock
object
11 properties
7 required
CreateNewEmptyImpulseResponse
GenericApiResponse
object
2 properties
1 required
KerasModelTypeEnum
string
GetAllDetailedImpulsesResponse
Impulse
object
5 properties
5 required
DSPGroupItem
object
16 properties
7 required
DSPConfig
object
3 properties
1 required
DependencyData
object
4 properties
4 required
SetLegacyImpulseStateInternalRequest
object
3 properties
3 required
KerasVisualLayer
object
8 properties
1 required
PublicProjectTierAvailability
string
For public blocks, this indicates the project tiers for which this block is available.
AugmentationPolicyImageEnum
string
The data augmentation policy to use with image input
ModelPrediction
object
8 properties
4 required
CreateImpulseRequest
object
4 properties
3 required
DetailedImpulse
object
9 properties
7 required
KerasCustomMetric
object
2 properties
2 required
CloneImpulseRequest
object
1 property
1 required
ImpulseLearnBlock
object
8 properties
6 required
ImpulseInputBlock
object
18 properties
5 required
AkidaEdgeLearningConfig
object
3 properties
1 required
DSPInfo
object
15 properties
10 required
KerasModelVariantEnum
string
ObjectDetectionLastLayer
string
KerasModelMetadataMetrics
object
13 properties
8 required
BlockDisplayCategory
string
Category to display this block in the UI.
DetailedImpulseMetric
object
9 properties
5 required
BlockParamsVisualAnomalyPatchcore
object
5 properties
AnomalyModelMetadata
object
10 properties
5 required
UpdateImpulseRequest
object
2 properties
DSPBlock
object
12 properties
9 required
ImageInputResizeMode
string
Input images are resized automatically before training and testing, to match the impulse input shape. This determines the resize mode used when the aspect rati…
KerasModelMetadataGraphSeries
object
2 properties
2 required
PostProcessingConfig
object
2 properties
2 required
KerasModelMetadataGraph
object
6 properties
2 required
CreateNewEmptyImpulseRequest
object
1 property
KerasConfig_2
object
31 properties
19 required
DSPMetadata_2
object
19 properties
12 required
DependencyData_2
object
5 properties
5 required
CreatedUpdatedByUser
object
4 properties
3 required
ModelPrediction_2
object
10 properties
4 required
CreateImpulseRequest_2
object
6 properties
3 required
DetailedImpulse_2
object
13 properties
10 required
ImpulseInputBlock_2
object
19 properties
4 required
ImpulseInputBlockDatasetSubset
object
Only generate features for samples where (sampleid + datasetSubsetSeed) % datasetSubset) == 0
2 properties
1 required
AnomalyModelMetadata_2
object
11 properties
7 required
ImpulseType
string
Specifies the type of impulse. Options include: - default: Standard Edge Impulse pipeline. - BYOM: Impulse that includes a pretrained model. - VLM: Impulse cre…
DSPBlock_2
object
13 properties
10 required
BoundingBoxWithScore
object
This has the ratio for x/y/w/h (so 0..1)
6 properties
6 required
AnomalyConfig_2
object
8 properties
7 required
KerasModelMetadata_2
object
13 properties
11 required
LearnBlock_2
object
12 properties
7 required
Impulse_2
object
7 properties
7 required
DSPGroupItem_2
object
22 properties
8 required
ImpulsePostProcessingBlock
object
7 properties
5 required
DSPInfo_2
object
17 properties
12 required
ImpulseLearnBlock_2
object
8 properties
5 required
GetAllTransferLearningModelsResponse
TransferLearningModel_2
object
23 properties
10 required
ImpulseDspBlock_2
object
13 properties
6 required
BlockThreshold
object
Configurable threshold for this block (e.g. minimum score before tagging as an anomaly, or the min. score to save bounding boxes)
7 properties
4 required
SetImpulseThresholdsResponse
SetImpulseThresholdsRequest
object
3 properties
2 required
GetImpulseBlocksResponse_2
ExperimentalImpulseSpecificGpuTrainingProcessor
string
EXPERIMENTAL: Training processor for the impulse-specific-gpu rollout. This field is currently gated by a project experiment and may change in future API versi…
BlockDisplayCategory_2
string
Category to display this block in the UI.
InputBlock_2
object
6 properties
6 required
LearnBlockType_2
string
The type of learning block (anomaly, keras, keras-transfer-image, keras-transfer-kws, keras-object-detection, keras-regression, keras-freeform). Each behaves d…
PostProcessingBlock
object
11 properties
10 required
DetailedImpulseMetricCategory_2
string
PublicProjectTierAvailability_2
string
For public blocks, this indicates the project tiers for which this block is available.
ObjectDetectionLastLayer_2
string
KerasModelMetadataMetrics_2
object
13 properties
8 required
UpdateImpulseRequest_2
object
3 properties
The full machine-readable OpenAPI contract behind this narrative.
Other APIs Edge Impulse publishes across the network.
