DJL de Java Deep Learning crea AlexNet

package com.example.demo.djl;

import ai.djl.Model;
import ai.djl.ModelException;
import ai.djl.basicdataset.FashionMnist;
import ai.djl.metric.Metrics;
import ai.djl.modality.cv.transform.Resize;
import ai.djl.modality.cv.transform.ToTensor;
import ai.djl.ndarray.NDArray;
import ai.djl.ndarray.NDManager;
import ai.djl.ndarray.types.Shape;
import ai.djl.nn.Activation;
import ai.djl.nn.Blocks;
import ai.djl.nn.SequentialBlock;
import ai.djl.nn.convolutional.Conv2d;
import ai.djl.nn.core.Linear;
import ai.djl.nn.norm.Dropout;
import ai.djl.nn.pooling.Pool;
import ai.djl.training.DefaultTrainingConfig;
import ai.djl.training.EasyTrain;
import ai.djl.training.Trainer;
import ai.djl.training.dataset.Dataset;
import ai.djl.training.dataset.RandomAccessDataset;
import ai.djl.training.evaluator.Accuracy;
import ai.djl.training.listener.TrainingListener;
import ai.djl.training.loss.Loss;
import ai.djl.training.optimizer.Optimizer;
import ai.djl.training.tracker.