A reference Java project is provided in the Example repository from with a Maven pom.xml dependencies file. If using the IntelliJ IDEA IDE, open the java folder as a Maven project and run the main function of Example_1_Dl4jStep class.
Configure the step
Let's start from the main function by getting the trained model.
//get the file of trained model
Train.ModelTrainResult modelTrainResult = Train.dl4jIrisModel();
Create an inference configuration by default.
//a default Inference Configuration
InferenceConfiguration inferenceConfiguration = new InferenceConfiguration();
We'll need to include DL4JStep into the pipeline and bind with the inference configuration. Specify the following:
modelUri : the model file path
inputNames : names for model's input layer
outputNames : names for model's output layer
//include pipeline step into the Inference Configuration
inferenceConfiguration.pipeline(SequencePipeline.builder()
.add(new DL4JStep() //add DL4JStep into pipeline
.modelUri(modelTrainResult.modelPath())
.inputNames(modelTrainResult.inputNames())
.outputNames(modelTrainResult.outputNames())
).build()
);
Deploy the server
Let's deploy the model in the server by calling DeployKonduitServing with the configuration made before. The handler, a callback function, is implemented to capture a successful or failed server deployment state.
//deploy the model in server
DeployKonduitServing.deploy(new VertxOptions(), new DeploymentOptions(),
inferenceConfiguration,
handler -> {
if (handler.succeeded()) { // If the server is sucessfully running
// Getting the result of the deployment
InferenceDeploymentResult inferenceDeploymentResult = handler.result();
int runnningPort = inferenceDeploymentResult.getActualPort();
String deploymentId = inferenceDeploymentResult.getDeploymentId();
System.out.format("The server is running on port %s with deployment id of %s%n",
runnningPort, deploymentId);
try {
String result = Unirest.post(String.format("http://localhost:%s/predict", runnningPort))
.header("Content-Type", "application/json")
.header("Accept", "application/json")
.body(new JSONObject().put("layer0",
new JSONArray().put(Arrays.asList(1.0, 1.0, 1.0, 1.0)))
)
.asString().getBody();
System.out.format("Result from server : %s%n", result);
System.exit(0);
} catch (UnirestException e) {
e.printStackTrace();
System.exit(1);
}
} else { // If the server failed to run
System.out.println(handler.cause().getMessage());
System.exit(1);
}
});
Note that we consider only one test input array in this example for inference to show the model's deployment in Konduit-Serving. After execution, the successful server deployment gives below output text.
The server is running on port 39615 with deployment id of 2fe69a2d-1276-4a1d-b5af-50191640019f
Result from server : {
"layer2" : [ [ 5.287693E-4, 0.02540398, 0.9740673 ] ]
}
Process finished with exit code 0
The complete inference configuration in YAML format is as follows.
