public class TinyImageNetDataSetIterator extends RecordReaderDataSetIterator
RecordReaderDataSetIterator.Builder
Modifier and Type | Field and Description |
---|---|
protected DataSetPreProcessor |
preProcessor |
batchNum, batchSize, converter, labelIndex, labelIndexTo, last, maxNumBatches, numPossibleLabels, recordReader, regression, sequenceIter, useCurrent
Constructor and Description |
---|
TinyImageNetDataSetIterator(int batchSize)
Create an iterator for the training set, with random iteration order (RNG seed fixed to 123)
|
TinyImageNetDataSetIterator(int batchSize,
DataSetType set)
* Create an iterator for the training or test set, with random iteration order (RNG seed fixed to 123)
|
TinyImageNetDataSetIterator(int batchSize,
int[] imgDim,
DataSetType set)
Get the Tiny ImageNet iterator with specified train/test set, with random iteration order (RNG seed fixed to 123)
|
TinyImageNetDataSetIterator(int batchSize,
int[] imgDim,
DataSetType set,
ImageTransform imageTransform,
long rngSeed)
Get the Tiny ImageNet iterator with specified train/test set and (optional) custom transform.
|
Modifier and Type | Method and Description |
---|---|
static List<String> |
getLabels(boolean categories)
Get the labels - either in "categories" (imagenet synsets format, "n01910747" or similar) or human-readable format,
such as "jellyfish"
|
asyncSupported, batch, getLabels, hasNext, inputColumns, loadFromMetaData, loadFromMetaData, next, next, remove, reset, resetSupported, setCollectMetaData, setPreProcessor, totalOutcomes
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
getPreProcessor
forEachRemaining
protected DataSetPreProcessor preProcessor
public TinyImageNetDataSetIterator(int batchSize)
batchSize
- Minibatch size for the iteratorpublic TinyImageNetDataSetIterator(int batchSize, DataSetType set)
batchSize
- Minibatch size for the iteratorset
- The dataset (train or test)public TinyImageNetDataSetIterator(int batchSize, int[] imgDim, DataSetType set)
batchSize
- Size of each patchimgDim
- Dimensions of desired output - for example, {64, 64}set
- Train, test, or validationpublic TinyImageNetDataSetIterator(int batchSize, int[] imgDim, DataSetType set, ImageTransform imageTransform, long rngSeed)
batchSize
- Size of each patchimgDim
- Dimensions of desired output - for example, {64, 64}set
- Train, test, or validationimageTransform
- Additional image transform for outputrngSeed
- random number generator seed to use when shuffling examplespublic static List<String> getLabels(boolean categories)
categories
- If true: return category/synset format; false: return "human readable" label formatCopyright © 2020. All rights reserved.