How to use the @tensorflow/tfjs-node-gpu.input function in @tensorflow/tfjs-node-gpu

kernelSize: 5,
    strides: 2,
    padding: 'same',
    activation: 'tanh',
    kernelInitializer: 'glorotNormal'
  }));

  // Unlike most TensorFlow.js models, the generator part of an ACGAN has
  // two inputs:
  //   1. The latent vector that is used as the "seed" of the fake image
  //      generation.
  //   2. A class label that controls which of the ten MNIST digit classes
  //      the generated fake image is meant to belong to.

  // This is the z space commonly referred to in GAN papers.
  const latent = tf.input({shape: [latentSize]});

  // The desired label of the generated image, an integer in the interval
  // [0, NUM_CLASSES).
  const imageClass = tf.input({shape: [1]});

  // The desired label is converted to a vector of length `latentSize`
  // through embedding lookup.
  const classEmbedding = tf.layers.embedding({
    inputDim: NUM_CLASSES,
    outputDim: latentSize,
    embeddingsInitializer: 'glorotNormal'
  }).apply(imageClass);

  // Hadamard product between z-space and a class conditional embedding.
  const h = tf.layers.multiply().apply([latent, classEmbedding]);

kernelInitializer: 'glorotNormal'
  }));

  // Unlike most TensorFlow.js models, the generator part of an ACGAN has
  // two inputs:
  //   1. The latent vector that is used as the "seed" of the fake image
  //      generation.
  //   2. A class label that controls which of the ten MNIST digit classes
  //      the generated fake image is meant to belong to.

  // This is the z space commonly referred to in GAN papers.
  const latent = tf.input({shape: [latentSize]});

  // The desired label of the generated image, an integer in the interval
  // [0, NUM_CLASSES).
  const imageClass = tf.input({shape: [1]});

  // The desired label is converted to a vector of length `latentSize`
  // through embedding lookup.
  const classEmbedding = tf.layers.embedding({
    inputDim: NUM_CLASSES,
    outputDim: latentSize,
    embeddingsInitializer: 'glorotNormal'
  }).apply(imageClass);

  // Hadamard product between z-space and a class conditional embedding.
  const h = tf.layers.multiply().apply([latent, classEmbedding]);

  const fakeImage = cnn.apply(h);
  return tf.model({inputs: [latent, imageClass], outputs: fakeImage});
}

cnn.add(tf.layers.leakyReLU({alpha: 0.2}));
  cnn.add(tf.layers.dropout({rate: 0.3}));

  cnn.add(tf.layers.conv2d(
      {filters: 128, kernelSize: 3, padding: 'same', strides: 2}));
  cnn.add(tf.layers.leakyReLU({alpha: 0.2}));
  cnn.add(tf.layers.dropout({rate: 0.3}));

  cnn.add(tf.layers.conv2d(
      {filters: 256, kernelSize: 3, padding: 'same', strides: 1}));
  cnn.add(tf.layers.leakyReLU({alpha: 0.2}));
  cnn.add(tf.layers.dropout({rate: 0.3}));

  cnn.add(tf.layers.flatten());

  const image = tf.input({shape: [IMAGE_SIZE, IMAGE_SIZE, 1]});
  const features = cnn.apply(image);

  // Unlike most TensorFlow.js models, the discriminator has two outputs.

  // The 1st output is the probability score assigned by the discriminator to
  // how likely the input example is a real MNIST image (as versus
  // a "fake" one generated by the generator).
  const realnessScore =
      tf.layers.dense({units: 1, activation: 'sigmoid'}).apply(features);
  // The 2nd output is the softmax probabilities assign by the discriminator
  // for the 10 MNIST digit classes (0 through 9). "aux" stands for "auxiliary"
  // (the namesake of ACGAN) and refers to the fact that unlike a standard GAN
  // (which performs just binary real/fake classification), the discriminator
  // part of ACGAN also performs multi-class classification.
  const aux = tf.layers.dense({units: NUM_CLASSES, activation: 'softmax'})
                  .apply(features);

function buildCombinedModel(latentSize, generator, discriminator, optimizer) {
  // Latent vector. This is one of the two inputs to the generator.
  const latent = tf.input({shape: [latentSize]});
  // Desired image class. This is the second input to the generator.
  const imageClass = tf.input({shape: [1]});
  // Get the symbolic tensor for fake images generated by the generator.
  let fake = generator.apply([latent, imageClass]);
  let aux;

  // We only want to be able to train generation for the combined model.
  discriminator.trainable = false;
  [fake, aux] = discriminator.apply(fake);
  const combined =
      tf.model({inputs: [latent, imageClass], outputs: [fake, aux]});
  combined.compile({
    optimizer,
    loss: ['binaryCrossentropy', 'sparseCategoricalCrossentropy']
  });
  combined.summary();
  return combined;
}

function buildCombinedModel(latentSize, generator, discriminator, optimizer) {
  // Latent vector. This is one of the two inputs to the generator.
  const latent = tf.input({shape: [latentSize]});
  // Desired image class. This is the second input to the generator.
  const imageClass = tf.input({shape: [1]});
  // Get the symbolic tensor for fake images generated by the generator.
  let fake = generator.apply([latent, imageClass]);
  let aux;

  // We only want to be able to train generation for the combined model.
  discriminator.trainable = false;
  [fake, aux] = discriminator.apply(fake);
  const combined =
      tf.model({inputs: [latent, imageClass], outputs: [fake, aux]});
  combined.compile({
    optimizer,
    loss: ['binaryCrossentropy', 'sparseCategoricalCrossentropy']
  });
  combined.summary();