Package ai.djl.modality.cv.translator

Class ImageFeatureExtractor

java.lang.Object

ai.djl.modality.cv.translator.BaseImageTranslator<float[]>

ai.djl.modality.cv.translator.ImageFeatureExtractor

All Implemented Interfaces:

PostProcessor<float[]>, PreProcessor<Image>, Translator<Image,float[]>

public class ImageFeatureExtractor
extends BaseImageTranslator<float[]>

A generic Translator for Image Classification feature extraction tasks.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	ImageFeatureExtractor.Builder	A Builder to construct a ImageFeatureExtractor.

Nested classes/interfaces inherited from class ai.djl.modality.cv.translator.BaseImageTranslator

BaseImageTranslator.BaseBuilder<T extends BaseImageTranslator.BaseBuilder>, BaseImageTranslator.ClassificationBuilder<T extends BaseImageTranslator.BaseBuilder>, BaseImageTranslator.SynsetLoader

Field Summary

Fields inherited from class ai.djl.modality.cv.translator.BaseImageTranslator

height, pipeline, width

Method Summary

Modifier and Type	Method	Description
static ImageFeatureExtractor.Builder	builder()	Creates a builder to build a ImageFeatureExtractor.
static ImageFeatureExtractor.Builder	builder(Map<String,?> arguments)	Creates a builder to build a ImageFeatureExtractor with specified arguments.
float[]	processOutput(TranslatorContext ctx, NDList list)	Processes the output NDList to the corresponding output object.

Methods inherited from class ai.djl.modality.cv.translator.BaseImageTranslator

getBatchifier, processInput

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface ai.djl.translate.Translator

batchProcessInput, batchProcessOutput, getExpansions, prepare

Method Details

processOutput

public float[] processOutput(TranslatorContext ctx,
 NDList list)

Processes the output NDList to the corresponding output object.

Parameters:

ctx - the toolkit used for post-processing

list - the output NDList after inference, usually immutable in engines like PyTorch. @see Issue 1774

Returns:

the output object of expected type

builder

public static ImageFeatureExtractor.Builder builder()

Creates a builder to build a ImageFeatureExtractor.

Returns:

a new builder

builder

public static ImageFeatureExtractor.Builder builder(Map<String,?> arguments)

Creates a builder to build a ImageFeatureExtractor with specified arguments.

Parameters:

arguments - arguments to specify builder options

Returns:

a new builder