0.6.0-alpha-1 (16/01/2023) New inference api with multiple inputs support
Pre-release
Pre-release
juliabeliaeva
released this
16 Jan 16:12
·
30 commits
to master
since this release
API changes:
- Changed
InferenceModel
interface:- Added type parameter representing inference result. #515
- Replaced classification function with general purpose prediction methods for single and multiple inputs.
Extensionsorg.jetbrains.kotlinx.dl.impl.inference.imagerecognition.PredictionKt.predictLabel
and
org.jetbrains.kotlinx.dl.impl.inference.imagerecognition.PredictionKt.predictProbabilities
were added for classification. #515 - Introduced
InferenceModel#resultConverter
to process inference results. #515 - Method
reshape
was removed, in favor of prediction methods receiving input asFloatData
containing input shape information. #513 - Parameters were removed from the
copy
function. #503
- Replaced
SavedModel#predict
withorg.jetbrains.kotlinx.dl.dataset.InferenceModelExtensionsKt.predict
extension. #515 - Added
predictionFunction
parameter to theorg.jetbrains.kotlinx.dl.dataset.InferenceModelExtensionsKt.predict
and
org.jetbrains.kotlinx.dl.dataset.InferenceModelExtensionsKt.evaluate
extension functions. #515 - Shape information was added to the dataset classes. #513
- Changed return type of the
Dataset.getX
function toFloatData
. - Added
TensorShape
parameter toDataBatch
andOnHeapDataset
constructors. - Removed
OnHeapDataset.Companion#createTrainAndTestDatasets
,
OnHeapDataset.Companion#create(String, String, int, Function1<String,float[][]>, Function2<String,Integer,float[]>)
,
OnHeapDataset.Companion#create(Function0<float[][]>, Function0<float[]>)
functions.
- Changed return type of the
- No-top models were moved to the separate model types
TFModels.CVnoTop
andONNXModels.CVnoTop
. #511 - Changed high-level model classes so they do not implement
InferenceModel
. #509 - Converted
SavingFormat
to a class and addedisKerasFullyCompatible
parameter toSavingFormat.JsonConfigCustomVariables
. #501 - Add basic multiple input support to
OnnxInferenceModel
. #417
Thanks to our contributors:
- Julia Beliaeva (@juliabeliaeva)
- Onuralp Sezer (@onuralpszr)