ee.Model.fromVertexAi

  • Returns an ee.Model representing a Vertex AI model endpoint for making predictions within Earth Engine.

  • Enables integration with pre-trained or custom Vertex AI models for Earth Engine analysis.

  • Accepts various parameters for configuring model inputs, outputs, and prediction behavior.

  • Supports customization of data types, projections, tile sizes, and payload formats for model interaction.

  • This functionality is currently in public preview and subject to potential changes.

 Returns an ee.Model from a description of a Vertex AI model endpoint. (See https://cloud.google.com/vertex-ai).

UsageReturns
ee.Model.fromVertexAi(endpoint, inputProperties, inputTypeOverride, inputShapes, proj, fixInputProj, inputTileSize, inputOverlapSize, outputTileSize, outputBands, outputProperties, outputMultiplier, maxPayloadBytes, payloadFormat)Model
ArgumentTypeDetails
endpointStringThe endpoint name for predictions.
inputPropertiesList, default: nullProperties passed with each prediction instance. Image predictions are tiled, so these properties will be replicated into each image tile instance. Defaults to no properties.
inputTypeOverrideDictionary, default: nullTypes to which model inputs will be coerced if specified. Both Image bands and Image/Feature properties are valid.
inputShapesDictionary, default: nullThe fixed shape of input array bands. For each array band not specified, the fixed array shape will be automatically deduced from a non-masked pixel.
projProjection, default: nullThe input projection at which to sample all bands. Defaults to the default projection of an image's first band.
fixInputProjBoolean, default: nullIf true, pixels will be sampled in a fixed projection specified by 'proj'. The output projection is used otherwise. Defaults to false.
inputTileSizeList, default: nullRectangular dimensions of pixel tiles passed in to prediction instances. Required for image predictions.
inputOverlapSizeList, default: nullAmount of adjacent-tile overlap in X/Y along each edge of pixel tiles passed in to prediction instances. Defaults to [0, 0].
outputTileSizeList, default: nullRectangular dimensions of pixel tiles returned from AI Platform. Defaults to the value in 'inputTileSize'.
outputBandsDictionary, default: nullA map from output band names to a dictionary of output band info. Valid band info fields are 'type' and 'dimensions'. 'type' should be a ee.PixelType describing the output band, and 'dimensions' is an optional integer with the number of dimensions in that band e.g., "outputBands: {'p': {'type': ee.PixelType.int8(), 'dimensions': 1}}". Required for image predictions.
outputPropertiesDictionary, default: nullA map from output property names to a dictionary of output property info. Valid property info fields are 'type' and 'dimensions'. 'type' should be a ee.PixelType describing the output property, and 'dimensions' is an optional integer with the number of dimensions for that property if it is an array e.g., "outputBands: {'p': {'type': ee.PixelType.int8(), 'dimensions': 1}}". Required for predictions from FeatureCollections.
outputMultiplierFloat, default: nullAn approximation to the increase in data volume for the model outputs over the model inputs. If specified this must be >= 1. This is only needed if the model produces more data than it consumes, e.g., a model that takes 5 bands and produces 10 outputs per pixel.
maxPayloadBytesLong, default: nullThe prediction payload size limit in bytes. Defaults to 1.5MB (1500000 bytes.)
payloadFormatString, default: nullThe payload format of entries in prediction requests and responses. One of: ['SERIALIZED_TF_TENSORS, 'RAW_JSON', 'ND_ARRAYS', 'GRPC_TF_TENSORS', 'GRPC_SERIALIZED_TF_TENSORS', 'GRPC_TF_EXAMPLES']. Defaults to 'SERIALIZED_TF_TENSORS'.