Method predict

tfjs-layers/src/models.ts:786–792

* Generates output predictions for the input samples. * * Computation is done in batches. * * Note: the "step" mode of predict() is currently not supported. * This is because the TensorFlow.js core backend is imperative only. * * ```js * const model = tf.sequential({ *

(x: Tensor|Tensor[], args: ModelPredictArgs = {})

   * @doc {heading: 'Models', subheading: 'Classes'}
   */
  override predict(x: Tensor|Tensor[], args: ModelPredictArgs = {}):
      Tensor|Tensor[] {
    if (this.model == null) {
      this.build();
    }
    return this.model.predict(x, args);
  }

  /**
   * Returns predictions for a single batch of samples.