Changelog of the Inference YAML Configuration

Version 7

  • Sampling.EnsureInputImageMultipleOfDivisor is added to control the behaviour of padding the input image to a multiple of the DimensionDivisor.

This behaviour was default in versions 6 and less, but from version 7 will default to false.

Version 6

All engine related parameters are now listed in a subsection under the keyword Engine. The engine name is specified by the field Name.

Version 5

  • Sampling.SkipUnpadding now defaults to true.

  • Sampling.MirrorPadding is deprecated, use PaddingMode: Mirror instead. Other possible padding modes are Zero or Clamp.

Version 4

  • We no longer automatically insert a MakeFloat operation as first step of the PreProcessing sequence.

Version 3

  • Parameter Type now strictly refers to the type of model, and can take the values NeuralNetwork, RandomForest, and NeuralNetworkLegacy. Previously, type was sometimes used as PredictionType. This is still supported, but will be discontinued at some point.

  • Model configuration in the format .configtxt are no longer supported.