EN 1.0.0-M2
Multi-Project
Deeplearning4j
Model Zoo
Prebuilt model architectures and weights for out-of-the-box application.
Deeplearning4j has native model zoo that can be accessed and instantiated directly from DL4J. The model zoo also includes pretrained weights for different datasets that are downloaded automatically and checked for integrity using a checksum mechanism.
If you want to use the new model zoo, you will need to add it as a dependency. A Maven POM would add the following:
1
<dependency>
2
<groupId>org.deeplearning4j</groupId>
3
<artifactId>deeplearning4j-zoo</artifactId>
4
<version>1.0.0-M1.1</version>
5
</dependency>
Copied!
Getting started
Once you've successfully added the zoo dependency to your project, you can start to import and use models. Each model extends the
ZooModel abstract class and uses the InstantiableModel interface. These classes provide methods that help you initialize either an empty, fresh network or a pretrained network.Initializing fresh configurations
You can instantly instantiate a model from the zoo using the
.init() method. For example, if you want to instantiate a fresh, untrained network of AlexNet you can use the following code:1
import org.deeplearning4j.zoo.model.AlexNet
2
import org.deeplearning4j.zoo.*;
3
​
4
...
5
​
6
int numberOfClassesInYourData = 1000;
7
int randomSeed = 123;
8
​
9
ZooModel zooModel = AlexNet.builder()
10
.numClasses(numberOfClassesInYourData)
11
.seed(randomSeed)
12
.build();
13
Model net = zooModel.init();
Copied!
If you want to tune parameters or change the optimization algorithm, you can obtain a reference to the underlying network configuration:
1
ZooModel zooModel = AlexNet.builder()
2
.numClasses(numberOfClassesInYourData)
3
.seed(randomSeed)
4
.build();
5
MultiLayerConfiguration net = ((AlexNet) zooModel).conf();
Copied!
Initializing pretrained weights
Some models have pretrained weights available, and a small number of models are pretrained across different datasets.
PretrainedType is an enumerator that outlines different weight types, which includes IMAGENET, MNIST, CIFAR10, and VGGFACE.For example, you can initialize a VGG-16 model with ImageNet weights like so:
1
import org.deeplearning4j.zoo.model.VGG16;
2
import org.deeplearning4j.zoo.*;
3
​
4
...
5
​
6
ZooModel zooModel = VGG16.builder().build();;
7
Model net = zooModel.initPretrained(PretrainedType.IMAGENET);
Copied!
And initialize another VGG16 model with weights trained on VGGFace:
1
ZooModel zooModel = VGG16.builder().build();
2
Model net = zooModel.initPretrained(PretrainedType.VGGFACE);
Copied!
If you're not sure whether a model contains pretrained weights, you can use the
.pretrainedAvailable() method which returns a boolean. Simply pass a PretrainedType enum to this method, which returns true if weights are available.Note that for convolutional models, input shape information follows the NCHW convention. So if a model's input shape default is
new int[]{3, 224, 224}, this means the model has 3 channels and height/width of 224.What's in the zoo?
The model zoo comes with well-known image recognition configurations in the deep learning community. The zoo also includes an LSTM for text generation, and a simple CNN for general image recognition.
This includes ImageNet models such as VGG-16, ResNet-50, AlexNet, Inception-ResNet-v1, LeNet, and more.
Advanced usage
The zoo comes with a couple additional features if you're looking to use the models for different use cases.
Changing Inputs
Aside from passing certain configuration information to the constructor of a zoo model, you can also change its input shape using
.setInputShape().NOTE: this applies to fresh configurations only, and will not affect pretrained models:
1
int numberOfClassesInYourData = 10;
2
int randomSeed = 123;
3
​
4
ZooModel zooModel = ResNet50.builder()
5
.numClasses(numberOfClassesInYourData)
6
.seed(randomSeed)
7
.build();
8
zooModel.setInputShape(new int[][]{{3, 28, 28}});
Copied!
Transfer Learning
Pretrained models are perfect for transfer learning! You can read more about transfer learning using DL4J here.
Workspaces
Initialization methods often have an additional parameter named
workspaceMode. For the majority of users you will not need to use this; however, if you have a large machine that has "beefy" specifications, you can pass WorkspaceMode.SINGLE for models such as VGG-19 that have many millions of parameters. To learn more about workspaces, please see this section.Last modified 4mo ago