1. Persist the model using ModelSerializer:

File file = new File("cnntrainedmodel.zip");
 ModelSerializer.writeModel(model,file,true);
 ModelSerializer.addNormalizerToModel(file,scaler);

2. Restore the trained model using ModelSerializer to perform predictions:

MultiLayerNetwork network = ModelSerializer.restoreMultiLayerNetwork(modelFile);
 NormalizerStandardize normalizerStandardize = ModelSerializer.restoreNormalizerFromFile(modelFile);

3. Design an API method that accepts inputs from users and returns results. An example API method would look like the following:

public static INDArray generateOutput(File file) throws IOException, InterruptedException {
 final File modelFile = new File("cnnmodel.zip");
 final MultiLayerNetwork model = ModelSerializer.restoreMultiLayerNetwork(modelFile);
 final RecordReader imageRecordReader = generateReader(file);
 final NormalizerStandardize normalizerStandardize = ModelSerializer.restoreNormalizerFromFile(modelFile);
 final DataSetIterator dataSetIterator = new RecordReaderDataSetIterator.Builder(imageRecordReader,1).build();
 normalizerStandardize.fit(dataSetIterator);
 dataSetIterator.setPreProcessor(normalizerStandardize);
 return model.output(dataSetIterator);
 }

4. Create a URI mapping to service client requests, as shown in the following example:

@GetMapping("/")
 public String main(final Model model){
 model.addAttribute("message", "Welcome to Java deep learning!");
 return "welcome";
 }
 
 @PostMapping("/")
 public String fileUpload(final Model model, final @RequestParam("uploadFile")MultipartFile multipartFile) throws IOException, InterruptedException {
 final List<String> results = cookBookService.generateStringOutput(multipartFile);
 model.addAttribute("message", "Welcome to Java deep learning!");
 model.addAttribute("results",results);
 return "welcome";
 }

5. Build a cookbookapp-cnn project and add the API dependency to your Spring project:

<dependency>
 <groupId>com.javadeeplearningcookbook.app</groupId>
 <artifactId>cookbookapp-cnn</artifactId>
 <version>1.0-SNAPSHOT</version>
 </dependency>

6. Create the generateStringOutput() method in the service layer to serve API content:

@Override
 public List<String> generateStringOutput(MultipartFile multipartFile) throws IOException, InterruptedException {
 //TODO: MultiPartFile to File conversion (multipartFile -> convFile)
 INDArray indArray = ImageClassifierAPI.generateOutput(convFile);

 for(int i=0; i<indArray.rows();i++){
           for(int j=0;j<indArray.columns();j++){
                   DecimalFormat df2 = new DecimalFormat("#.####");
                   results.add(df2.format(indArray.getDouble(i,j)*100)+"%"); 
                //Later add them from list to the model display on UI.
            }            
        }
  convFile.deleteOnExit();
   return results;
 }
 

7. Download and install the Google Cloud SDK: https://cloud.google.com/sdk/.

8. Install the Cloud SDK app-engine-java component by running the following command on the Google Cloud console:

gcloud components install app-engine-java

9. Log in and configure Cloud SDK using the following command:

gcloud init

10. Add the following dependency for Maven App Engine in pom.xml:

<plugin>
 <groupId>com.google.cloud.tools</groupId>
 <artifactId>appengine-maven-plugin</artifactId>
 <version>2.1.0</version>
 </plugin>

11. Create an app.yaml file in your project as per the Google Cloud documentation:
    https://cloud.google.com/appengine/docs/flexible/java/configuring-your-app-with-app-yaml.
12. Navigate to Google App Engine and click on the Create Application button:

13. Pick a region and click on Create app:

14. Select Java and click the Next button:

Now, your app engine has been created at Google Cloud.

15. Build the spring boot application using Maven:

mvn clean install

16. Deploy the application using the following command:

mvn appengine:deploy