Train model (Keras)

POST {{baseUrl}}/api/:projectId/jobs/train/keras/:learnId

Take the output from a DSP block and train a neural network using Keras. Updates are streamed over the websocket API.

Request Body

{"mode"=>"<string>", "minimumConfidenceRating"=>"<number>", "selectedModelType"=>{"value"=>"<Error: Too many levels of nesting to fake this schema>"}, "script"=>"<string>", "visualLayers"=>[{"value"=>"<Error: Too many levels of nesting to fake this schema>"}, {"value"=>"<Error: Too many levels of nesting to fake this schema>"}], "trainingCycles"=>"<integer>", "learningRate"=>"<number>", "trainTestSplit"=>"<number>", "autoClassWeights"=>"<boolean>", "findLearningRate"=>"<boolean>", "augmentationPolicyImage"=>{"value"=>"<Error: Too many levels of nesting to fake this schema>"}, "augmentationPolicySpectrogram"=>{"value"=>"<Error: Too many levels of nesting to fake this schema>"}, "profileInt8"=>"<boolean>", "skipEmbeddingsAndMemory"=>"<boolean>", "customValidationMetadataKey"=>"<string>"}

HEADERS

RESPONSES

status: OK

{"id":{"value":"\u003cError: Too many levels of nesting to fake this schema\u003e"}}