`inference_output_type` for full integer quantized models. This allows
        users to modify the model input and output type to integer types
        (`tf.int8`, `tf.uint8`) instead of defaulting to float type
        (`tf.float32`).
*   NNAPI
    *   Adds NNAPI Delegation support for requantization use cases by converting
        the operation into a dequantize-quantize pair.

    private final int scale;

    private Scale(int scale) {
      checkArgument(scale > 0, "Quantile scale must be positive");
      this.scale = scale;
    }

    /**
     * Specifies a single quantile index to be calculated, i.e. the k in the kth q-quantile.
     *
     * @param index the quantile index, which must be in the inclusive range [0, q] for q-quantiles
     */

      return (lowerValue + upperValue) / 2.0;
    }
  }

  public void testPercentiles_index_compute_doubleCollection() {
    for (int index = 0; index <= 100; index++) {
      assertWithMessage("quantile at index " + index)
          .that(percentiles().index(index).compute(PSEUDORANDOM_DATASET))
          .isWithin(ALLOWED_ERROR)
          .of(expectedLargeDatasetPercentile(index));
    }
  }

      return (lowerValue + upperValue) / 2.0;
    }
  }

  public void testPercentiles_index_compute_doubleCollection() {
    for (int index = 0; index <= 100; index++) {
      assertWithMessage("quantile at index " + index)
          .that(percentiles().index(index).compute(PSEUDORANDOM_DATASET))
          .isWithin(ALLOWED_ERROR)
          .of(expectedLargeDatasetPercentile(index));
    }
  }

### Testé

* 100% <abbr title="La quantité de code qui est testé automatiquement">de couverture de test</abbr>.

Cela prendrait autant de temps pour finir avec ou sans sections (concurrence) et vous auriez effectué la même quantité de travail.