Package ai.djl.modality.cv.translator
Class BigGANTranslator
java.lang.Object
ai.djl.modality.cv.translator.BigGANTranslator
- All Implemented Interfaces:
NoBatchifyTranslator<int[],,Image[]> PostProcessor<Image[]>,PreProcessor<int[]>,Translator<int[],Image[]>
Built-in
Translator that provides preprocessing and postprocessing for BigGAN.-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionprocessInput(TranslatorContext ctx, int[] input) Processes the input and converts it to NDList.Image[]processOutput(TranslatorContext ctx, NDList list) Processes the output NDList to the corresponding output object.Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitMethods inherited from interface ai.djl.translate.NoBatchifyTranslator
getBatchifierMethods inherited from interface ai.djl.translate.Translator
batchProcessInput, batchProcessOutput, getExpansions, prepare
-
Constructor Details
-
BigGANTranslator
public BigGANTranslator(float truncation) Constructs a translator for BigGAN.- Parameters:
truncation- value used to scale the normal seed for BigGAN
-
-
Method Details
-
processOutput
Processes the output NDList to the corresponding output object.- Specified by:
processOutputin interfacePostProcessor<Image[]>- Parameters:
ctx- the toolkit used for post-processinglist- the output NDList after inference, usually immutable in engines like PyTorch. @see Issue 1774- Returns:
- the output object of expected type
-
processInput
Processes the input and converts it to NDList.- Specified by:
processInputin interfacePreProcessor<int[]>- Parameters:
ctx- the toolkit for creating the input NDArrayinput- the input object- Returns:
- the
NDListafter pre-processing - Throws:
Exception- if an error occurs during processing input
-