tensorflow-framework/src/main/java/org/tensorflow/framework/losses/CategoricalCrossentropy.java [213:255]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    this.axis = axis;
  }

  /**
   * Generates an Operand that calculates the loss.
   *
   * <p>If run in Graph mode, the computation will throw {@link
   * org.tensorflow.exceptions.TFInvalidArgumentException} if the predictions values are outside the
   * range o [0. to 1.]. In Eager Mode, this call will throw {@link IllegalArgumentException}, if
   * the predictions values are outside the range o [0. to 1.]
   *
   * @param labels the truth values or labels
   * @param predictions the predictions, values must be in the range [0. to 1.] inclusive.
   * @param sampleWeights Optional SampleWeights acts as a coefficient for the loss. If a scalar is
   *     provided, then the loss is simply scaled by the given value. If SampleWeights is a tensor
   *     of size [batch_size], then the total loss for each sample of the batch is rescaled by the
   *     corresponding element in the SampleWeights vector. If the shape of SampleWeights is
   *     [batch_size, d0, .. dN-1] (or can be broadcast to this shape), then each loss element of
   *     predictions is scaled by the corresponding value of SampleWeights. (Note on dN-1: all loss
   *     functions reduce by 1 dimension, usually axis=-1.)
   * @param <T> The data type of the predictions, sampleWeights and loss.
   * @return the loss
   * @throws IllegalArgumentException if the predictions are outside the range [0.-1.].
   */
  @Override
  public <T extends TNumber> Operand<T> call(
      Ops tf, Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights) {

    Operand<T> lPredictions;
    if (!fromLogits) {
      // add predictions range check for 0 - 1
      lPredictions =
          LossesHelper.rangeCheck(
              tf,
              "predictions range check [0-1]",
              predictions,
              cast(tf, tf.constant(0), predictions.type()),
              cast(tf, tf.constant(1), predictions.type()));

    } else {
      lPredictions = predictions;
    }
    Operand<T> losses =
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow-framework/src/main/java/org/tensorflow/framework/losses/SparseCategoricalCrossentropy.java [168:211]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    this.axis = axis;
  }

  /**
   * Generates an Operand the calculates the loss.
   *
   * <p>If run in Graph mode, the computation will throw {@link
   * org.tensorflow.exceptions.TFInvalidArgumentException} if the predictions values are outside the
   * range o [0. to 1.]. In Eager Mode, this call will throw {@link IllegalArgumentException}, if
   * the predictions values are outside the range o [0. to 1.]
   *
   * @param tf the TensorFlow Ops
   * @param labels the truth values or labels
   * @param predictions the predictions, values must be in the range [0. to 1.] inclusive.
   * @param sampleWeights Optional SampleWeights acts as a coefficient for the loss. If a scalar is
   *     provided, then the loss is simply scaled by the given value. If SampleWeights is a tensor
   *     of size [batch_size], then the total loss for each sample of the batch is rescaled by the
   *     corresponding element in the SampleWeights vector. If the shape of SampleWeights is
   *     [batch_size, d0, .. dN-1] (or can be broadcast to this shape), then each loss element of
   *     predictions is scaled by the corresponding value of SampleWeights. (Note on dN-1: all loss
   *     functions reduce by 1 dimension, usually axis=-1.)
   * @param <T> The data type of the predictions, sampleWeights and loss.
   * @return the loss
   * @throws IllegalArgumentException if the predictions are outside the range [0.-1.].
   */
  @Override
  public <T extends TNumber> Operand<T> call(
      Ops tf, Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights) {

    Operand<T> lPredictions;
    if (!fromLogits) {
      // add predictions range check for 0 - 1
      lPredictions =
          LossesHelper.rangeCheck(
              tf,
              "predictions range check [0-1]",
              predictions,
              cast(tf, tf.constant(0), predictions.type()),
              cast(tf, tf.constant(1), predictions.type()));

    } else {
      lPredictions = predictions;
    }
    Operand<T> losses =
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -