ai.djl.modality.cv.zoo

Class ObjectDetectionModelLoader

java.lang.Object

ai.djl.repository.zoo.BaseModelLoader

ai.djl.modality.cv.zoo.ObjectDetectionModelLoader

All Implemented Interfaces:

ModelLoader

Direct Known Subclasses:

YoloModelLoader

public class ObjectDetectionModelLoader
extends BaseModelLoader

A ModelLoader for Single Shot Detection (SSD) models.

These models were built as part of the Gluon CV library and imported into DJL.

SSD is a model to solve Application.CV#OBJECT_DETECTION. Prior models before SSD typically used non-deep learning strategies to find object proposals and then would execute classification at those proposed locations. SSD integrated the proposal process into the model and then classifies at all of those locations in parallel. This both simplifies the model and training process while better leveraging the power of model DL engines. [paper]

Today, SSD is not typically used in favor of newer models which outperform it.

Field Summary

Fields inherited from class ai.djl.repository.zoo.BaseModelLoader

factories, modelZoo, resource

Constructor Summary

Constructors

Constructor and Description
ObjectDetectionModelLoader(Repository repository, java.lang.String groupId, java.lang.String artifactId, java.lang.String version, ModelZoo modelZoo) Creates the Model loader from the given repository.

Method Summary

Modifier and Type	Method and Description
ZooModel<Image,DetectedObjects>	loadModel() Loads the model.
ZooModel<Image,DetectedObjects>	loadModel(java.util.Map<java.lang.String,java.lang.String> filters, Device device, ai.djl.util.Progress progress) Loads the model with the given search filters.
ZooModel<Image,DetectedObjects>	loadModel(ai.djl.util.Progress progress) Loads the model.

Methods inherited from class ai.djl.repository.zoo.BaseModelLoader

createModel, getApplication, getArtifactId, listModels, loadModel, toString

Methods inherited from class java.lang.Object

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

Constructor Detail

ObjectDetectionModelLoader

public ObjectDetectionModelLoader(Repository repository,
                                  java.lang.String groupId,
                                  java.lang.String artifactId,
                                  java.lang.String version,
                                  ModelZoo modelZoo)

Creates the Model loader from the given repository.

Parameters:

repository - the repository to load the model from

groupId - the group id of the model

artifactId - the artifact id of the model

version - the version number of the model

modelZoo - the modelZoo type that is being used to get supported engine types

Method Detail

loadModel

public ZooModel<Image,DetectedObjects> loadModel()
                                          throws MalformedModelException,
                                                 ModelNotFoundException,
                                                 java.io.IOException

Loads the model.

Returns:

the loaded model

Throws:

java.io.IOException - for various exceptions loading data from the repository

ModelNotFoundException - if no model with the specified criteria is found

MalformedModelException - if the model data is malformed

loadModel

public ZooModel<Image,DetectedObjects> loadModel(ai.djl.util.Progress progress)
                                          throws MalformedModelException,
                                                 ModelNotFoundException,
                                                 java.io.IOException

Loads the model.

Parameters:

progress - the progress tracker to update while loading the model

Returns:

the loaded model

Throws:

java.io.IOException - for various exceptions loading data from the repository

ModelNotFoundException - if no model with the specified criteria is found

MalformedModelException - if the model data is malformed

loadModel

public ZooModel<Image,DetectedObjects> loadModel(java.util.Map<java.lang.String,java.lang.String> filters,
                                                 Device device,
                                                 ai.djl.util.Progress progress)
                                          throws java.io.IOException,
                                                 ModelNotFoundException,
                                                 MalformedModelException

Loads the model with the given search filters.

Parameters:

filters - the search filters to match against the loaded model

device - the device the loaded model should use

progress - the progress tracker to update while loading the model

Returns:

the loaded model

Throws:

java.io.IOException - for various exceptions loading data from the repository

ModelNotFoundException - if no model with the specified criteria is found

MalformedModelException - if the model data is malformed