Java 프레임워크는 인공 지능 알고리즘 라이브러리와 어떻게 상호 작용합니까?

import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.tensorflow.keras.models.Model;
import org.tensorflow.keras.models.Sequential;
import org.tensorflow.keras.layers.Conv2D;
import org.tensorflow.keras.layers.Flatten;
import org.tensorflow.keras.layers.Dense;

@SpringBootApplication
public class ImageClassifierApplication {

    public static void main(String[] args) {
        SpringApplication.run(ImageClassifierApplication.class, args);
        
        // 创建一个序列模型
        Model model = new Sequential();
        
        // 添加卷积层、展平层和全连接层
        model.add(new Conv2D(32, (3, 3), activation="relu", inputShape=(28, 28, 1)));
        model.add(new Flatten());
        model.add(new Dense(128, activation="relu"));
        model.add(new Dense(10, activation="softmax"));
        
        // 编译模型
        model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"]);
        
        // 训练模型
        model.fit(trainData, trainLabels, epochs=5);
        
        // 保存模型
        model.save("image_classifier_model.h5");
    }
}

import javax.ws.rs.GET;
import javax.ws.rs.POST;
import javax.ws.rs.Path;
import javax.ws.rs.Produces;
import javax.ws.rs.Consumes;
import javax.ws.rs.QueryParam;
import javax.ws.rs.core.MediaType;

import org.apache.commons.lang3.StringUtils;
import org.scikitlearn.pipeline.Pipeline;
import org.scikitlearn.feature_extraction.text.TfidfVectorizer;
import org.scikitlearn.linear_model.LogisticRegression;

@Path("/text-classifier")
public class TextClassifierResource {

    private Pipeline pipeline;

    public TextClassifierResource() {
        // 训练模型
        TfidfVectorizer vectorizer = new TfidfVectorizer();
        LogisticRegression classifier = new LogisticRegression();
        pipeline = new Pipeline(vectorizer, classifier);
        pipeline.fit(trainData, trainLabels);
    }

    @GET
    @Produces(MediaType.TEXT_PLAIN)
    public String classify(@QueryParam("text") String text) {
        if (StringUtils.isBlank(text)) {
            return "Empty text";
        }
        
        // 使用模型进行预测
        Label label = (Label) pipeline.predict(text);
        
        return label.toString();
    }
}