Interface | Description |
---|---|
DataNormalization |
An interface for data normalizers.
|
MultiDataNormalization |
An interface for multi dataset normalizers.
|
Normalizer<T> |
Base interface for all normalizers
|
NormalizerStrategy<S extends NormalizerStats> |
Interface for strategies that can normalize and denormalize data arrays based on statistics of the population
|
Class | Description |
---|---|
AbstractDataSetNormalizer<S extends NormalizerStats> |
Abstract base class for normalizers
that act upon
DataSet instances
or iterators |
AbstractMultiDataSetNormalizer<S extends NormalizerStats> |
Abstract base class for normalizers that act upon
MultiDataSet instances or iterators |
AbstractNormalizer |
Abstract base class for normalizers for both DataSet and MultiDataSet processing
|
CompositeDataSetPreProcessor |
A simple Composite DataSetPreProcessor - allows you to apply multiple DataSetPreProcessors sequentially
on the one DataSet, in the order they are passed to the constructor
|
CompositeMultiDataSetPreProcessor |
A simple Composite MultiDataSetPreProcessor - allows you to apply multiple MultiDataSetPreProcessors sequentially
on the one MultiDataSet, in the order they are passed to the constructor
|
CropAndResizeDataSetPreProcessor |
The CropAndResizeDataSetPreProcessor will crop and resize the processed dataset.
|
ImageFlatteningDataSetPreProcessor |
A DataSetPreProcessor used to flatten a 4d CNN features array to a flattened 2d format (for use in networks such
as a DenseLayer/multi-layer perceptron)
|
ImageMultiPreProcessingScaler |
A preprocessor specifically for images that applies min max scaling to one or more of the feature arrays
in a MultiDataSet.
Can take a range, so pixel values can be scaled from 0->255 to minRange->maxRange default minRange = 0 and maxRange = 1; If pixel values are not 8 bits, you can specify the number of bits as the third argument in the constructor For values that are already floating point, specify the number of bits as 1 |
ImagePreProcessingScaler |
Created by susaneraly on 6/23/16.
|
LabelLastTimeStepPreProcessor |
Used to extract the labels from a 3d format (shape: [minibatch, nOut, sequenceLength]) to a 2d format (shape: [minibatch, nOut])
where the values are the last time step of the labels.
For example, for 2 sequences: [a, b, c, 0, 0] [p, q, r, s, t] (where a/b/p etc represet a vector of size numOutputs), and each row is the sequence for each [1, 1, 1, 0, 0] [1, 1, 1, 1, 1] The new labels would be a rank 2 array of shape [minibatch, nOut] with values: [c] [t] This preprocessor can be used for example to convert from "single non-masked time step" labels format (produced by RecordReaderDataSetIterator, used in RnnOutputLayer) to 2d labels format (used in OutputLayer). |
MinMaxStrategy |
NormalizerStrategy implementation that will normalize and denormalize data arrays to a given range, based on
statistics of the upper and lower bounds of the population |
MultiNormalizerHybrid |
Pre processor for MultiDataSet that can be configured to use different normalization strategies for different inputs
and outputs, or none at all.
|
MultiNormalizerMinMaxScaler |
Pre processor for MultiDataSet that normalizes feature values (and optionally label values) to lie between a minimum
and maximum value (by default between 0 and 1)
|
MultiNormalizerStandardize |
Pre processor for MultiDataSet that normalizes feature values (and optionally label values) to have 0 mean and
a standard deviation of 1
|
NormalizerMinMaxScaler |
Pre processor for DataSets that normalizes feature values (and optionally label values) to lie between a minimum
and maximum value (by default between 0 and 1)
|
NormalizerStandardize |
Created by susaneraly, Ede Meijer
variance and mean
Pre processor for DataSet that normalizes feature values (and optionally label values) to have 0 mean and a standard
deviation of 1
|
PermuteDataSetPreProcessor |
The PermuteDataSetPreProcessor will rearrange the dimensions.
|
RGBtoGrayscaleDataSetPreProcessor |
The RGBtoGrayscaleDataSetPreProcessor will turn a DataSet of a RGB image into a grayscale one.
|
StandardizeStrategy |
NormalizerStrategy implementation that will standardize and de-standardize data arrays, based on statistics
of the means and standard deviations of the population |
VGG16ImagePreProcessor |
This is a preprocessor specifically for VGG16.
|
Enum | Description |
---|---|
CropAndResizeDataSetPreProcessor.ResizeMethod | |
PermuteDataSetPreProcessor.PermutationTypes |
Copyright © 2019. All rights reserved.