Add transfer learning block

Add transfer learning block

Adds a transfer learning block.

post

/api/organizations/{organizationId}/transfer-learning

Authorizations

ApiKeyAuthenticationJWTAuthenticationJWTHttpHeaderAuthentication

Path parameters

organizationIdintegerrequired

Organization ID

Body

namestringrequired

dockerContainerstringrequired

descriptionstringrequired

operatesOnstring · enumrequired

Options: object_detection, audio, image, regression, other

objectDetectionLastLayerstring · enum

Options: mobilenet-ssd, fomo, yolov2-akida, yolov5, yolov5v5-drpai, yolox, yolov7, tao-retinanet, tao-ssd, tao-yolov3, tao-yolov4

implementationVersionintegerrequired

isPublicboolean

Whether this block is publicly available to Edge Impulse users (if false, then only for members of the owning organization)

publicProjectTierAvailabilitystring · enum

For public blocks, this indicates the project tiers for which this block is available.

Options: enterprise-only, pro-or-enterprise, all-projects

repositoryUrlstring

URL to the source code of this custom learn block.

imageInputScalingstring · enum

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-normalized pixels between -1 and 1. "0..255" gives you non-normalized pixels between 0 and 255. "-128..127" gives you non-normalized pixels between -128 and 127. "torch" first scales pixels between 0 and 1, then applies normalization using the ImageNet dataset (same as torchvision.transforms.Normalize()). "bgr-subtract-imagenet-mean" scales to 0..255, reorders pixels to BGR, and subtracts the ImageNet mean from each channel.

Options: 0..1, -1..1, -128..127, 0..255, torch, bgr-subtract-imagenet-mean

indRequiresGpuboolean

If set, requires this block to be scheduled on GPU.

displayCategorystring · enum

Category to display this block in the UI.

Options: classical, tao

isPublicForDevicesstring[]

If isPublic is true, the list of devices (from latencyDevices) for which this model can be shown.

parametersobject[]

List of parameters, spec'ed according to https://docs.edgeimpulse.com/docs/tips-and-tricks/adding-parameters-to-custom-blocks

customModelVariantsobject[]

List of custom model variants produced when this block is trained. This is experimental and may change in the future.

Responses

application/json

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://studio.edgeimpulse.com/v1/api/organizations/{organizationId}/transfer-learning' \
  --header 'x-api-key: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{"name":"text","dockerContainer":"text","description":"text","operatesOn":"object_detection","objectDetectionLastLayer":"mobilenet-ssd","implementationVersion":1,"publicProjectTierAvailability":"enterprise-only","imageInputScaling":"0..1","displayCategory":"classical","isPublicForDevices":[null],"parameters":[{}],"customModelVariants":[{"key":"text","name":"text","inferencingEntrypoint":"text","modelFiles":[{"id":"text","name":"text","description":"text","type":"binary"}]}]}'

200

200

{
  "success": true,
  "error": "text",
  "id": 1
}

OK