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 totrue
.Sampling.MirrorPadding
is deprecated, usePaddingMode: Mirror
instead. Other possible padding modes areZero
orClamp
.
Version 4
We no longer automatically insert a
MakeFloat
operation as first step of thePreProcessing
sequence.
Version 3
Parameter
Type
now strictly refers to the type of model, and can take the valuesNeuralNetwork
,RandomForest
, andNeuralNetworkLegacy
. Previously,type
was sometimes used asPredictionType
. This is still supported, but will be discontinued at some point.Model configuration in the format
.configtxt
are no longer supported.